ubowang commited on
Commit
c065692
·
verified ·
1 Parent(s): 8beeb08

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +3 -0
  2. v0-20260118-111123/args.json +393 -0
  3. v0-20260118-111123/checkpoint-400/added_tokens.json +24 -0
  4. v0-20260118-111123/checkpoint-400/args.json +393 -0
  5. v0-20260118-111123/checkpoint-400/chat_template.jinja +54 -0
  6. v0-20260118-111123/checkpoint-400/config.json +58 -0
  7. v0-20260118-111123/checkpoint-400/generation_config.json +14 -0
  8. v0-20260118-111123/checkpoint-400/merges.txt +0 -0
  9. v0-20260118-111123/checkpoint-400/model-00001-of-00004.safetensors +3 -0
  10. v0-20260118-111123/checkpoint-400/model-00002-of-00004.safetensors +3 -0
  11. v0-20260118-111123/checkpoint-400/model-00003-of-00004.safetensors +3 -0
  12. v0-20260118-111123/checkpoint-400/model-00004-of-00004.safetensors +3 -0
  13. v0-20260118-111123/checkpoint-400/model.safetensors.index.json +347 -0
  14. v0-20260118-111123/checkpoint-400/special_tokens_map.json +31 -0
  15. v0-20260118-111123/checkpoint-400/tokenizer.json +3 -0
  16. v0-20260118-111123/checkpoint-400/tokenizer_config.json +207 -0
  17. v0-20260118-111123/checkpoint-400/trainer_state.json +3234 -0
  18. v0-20260118-111123/checkpoint-400/training_args.bin +3 -0
  19. v0-20260118-111123/checkpoint-400/vocab.json +0 -0
  20. v0-20260118-111123/checkpoint-800/added_tokens.json +24 -0
  21. v0-20260118-111123/checkpoint-800/args.json +393 -0
  22. v0-20260118-111123/checkpoint-800/chat_template.jinja +54 -0
  23. v0-20260118-111123/checkpoint-800/config.json +58 -0
  24. v0-20260118-111123/checkpoint-800/generation_config.json +14 -0
  25. v0-20260118-111123/checkpoint-800/merges.txt +0 -0
  26. v0-20260118-111123/checkpoint-800/model-00001-of-00004.safetensors +3 -0
  27. v0-20260118-111123/checkpoint-800/model-00002-of-00004.safetensors +3 -0
  28. v0-20260118-111123/checkpoint-800/model-00003-of-00004.safetensors +3 -0
  29. v0-20260118-111123/checkpoint-800/model-00004-of-00004.safetensors +3 -0
  30. v0-20260118-111123/checkpoint-800/model.safetensors.index.json +347 -0
  31. v0-20260118-111123/checkpoint-800/special_tokens_map.json +31 -0
  32. v0-20260118-111123/checkpoint-800/tokenizer.json +3 -0
  33. v0-20260118-111123/checkpoint-800/tokenizer_config.json +207 -0
  34. v0-20260118-111123/checkpoint-800/trainer_state.json +0 -0
  35. v0-20260118-111123/checkpoint-800/training_args.bin +3 -0
  36. v0-20260118-111123/checkpoint-800/vocab.json +0 -0
  37. v0-20260118-111123/checkpoint-808/added_tokens.json +24 -0
  38. v0-20260118-111123/checkpoint-808/args.json +393 -0
  39. v0-20260118-111123/checkpoint-808/chat_template.jinja +54 -0
  40. v0-20260118-111123/checkpoint-808/config.json +58 -0
  41. v0-20260118-111123/checkpoint-808/generation_config.json +14 -0
  42. v0-20260118-111123/checkpoint-808/merges.txt +0 -0
  43. v0-20260118-111123/checkpoint-808/model-00001-of-00004.safetensors +3 -0
  44. v0-20260118-111123/checkpoint-808/model-00002-of-00004.safetensors +3 -0
  45. v0-20260118-111123/checkpoint-808/model-00003-of-00004.safetensors +3 -0
  46. v0-20260118-111123/checkpoint-808/model-00004-of-00004.safetensors +3 -0
  47. v0-20260118-111123/checkpoint-808/model.safetensors.index.json +347 -0
  48. v0-20260118-111123/checkpoint-808/special_tokens_map.json +31 -0
  49. v0-20260118-111123/checkpoint-808/tokenizer.json +3 -0
  50. v0-20260118-111123/checkpoint-808/tokenizer_config.json +207 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ v0-20260118-111123/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ v0-20260118-111123/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ v0-20260118-111123/checkpoint-808/tokenizer.json filter=lfs diff=lfs merge=lfs -text
v0-20260118-111123/args.json ADDED
@@ -0,0 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 1,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.05,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 2.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 400.0,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": true,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": "nccl",
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": 400.0,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": false,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch_fused",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "none"
132
+ ],
133
+ "project": "huggingface",
134
+ "trackio_space_id": "trackio",
135
+ "ddp_find_unused_parameters": null,
136
+ "ddp_bucket_cap_mb": null,
137
+ "ddp_broadcast_buffers": null,
138
+ "dataloader_pin_memory": true,
139
+ "dataloader_persistent_workers": false,
140
+ "skip_memory_metrics": true,
141
+ "use_legacy_prediction_loop": false,
142
+ "push_to_hub": false,
143
+ "resume_from_checkpoint": null,
144
+ "hub_model_id": null,
145
+ "hub_strategy": "every_save",
146
+ "hub_token": null,
147
+ "hub_private_repo": null,
148
+ "hub_always_push": false,
149
+ "hub_revision": null,
150
+ "gradient_checkpointing": true,
151
+ "gradient_checkpointing_kwargs": null,
152
+ "include_inputs_for_metrics": false,
153
+ "include_for_metrics": [],
154
+ "eval_do_concat_batches": true,
155
+ "fp16_backend": "auto",
156
+ "push_to_hub_model_id": null,
157
+ "push_to_hub_organization": null,
158
+ "push_to_hub_token": null,
159
+ "mp_parameters": "",
160
+ "auto_find_batch_size": false,
161
+ "full_determinism": false,
162
+ "torchdynamo": null,
163
+ "ray_scope": "last",
164
+ "ddp_timeout": 18000000,
165
+ "torch_compile": false,
166
+ "torch_compile_backend": null,
167
+ "torch_compile_mode": null,
168
+ "include_tokens_per_second": false,
169
+ "include_num_input_tokens_seen": false,
170
+ "neftune_noise_alpha": null,
171
+ "optim_target_modules": null,
172
+ "batch_eval_metrics": false,
173
+ "eval_on_start": false,
174
+ "use_liger_kernel": false,
175
+ "liger_kernel_config": null,
176
+ "eval_use_gather_object": false,
177
+ "average_tokens_across_devices": true,
178
+ "sortish_sampler": false,
179
+ "predict_with_generate": false,
180
+ "generation_max_length": null,
181
+ "generation_num_beams": null,
182
+ "generation_config": null,
183
+ "tuner_backend": "peft",
184
+ "vit_gradient_checkpointing": null,
185
+ "router_aux_loss_coef": 0.0,
186
+ "enable_dft_loss": false,
187
+ "enable_channel_loss": false,
188
+ "check_model": true,
189
+ "acc_strategy": "token",
190
+ "train_dataloader_shuffle": true,
191
+ "max_epochs": null,
192
+ "aligner_lr": null,
193
+ "vit_lr": null,
194
+ "use_logits_to_keep": null,
195
+ "ds3_gather_for_generation": true,
196
+ "resume_only_model": false,
197
+ "optimizer": null,
198
+ "loss_type": null,
199
+ "metric": null,
200
+ "eval_use_evalscope": false,
201
+ "eval_dataset": [],
202
+ "eval_dataset_args": null,
203
+ "eval_limit": null,
204
+ "eval_generation_config": null,
205
+ "extra_eval_args": null,
206
+ "use_flash_ckpt": false,
207
+ "use_ray": false,
208
+ "ray_exp_name": null,
209
+ "device_groups": null,
210
+ "model": "ubowang/fim_qwen25_coder_7b_ins_0116-ckpt_4500",
211
+ "model_type": "qwen2_5",
212
+ "model_revision": null,
213
+ "task_type": "causal_lm",
214
+ "torch_dtype": "bfloat16",
215
+ "attn_impl": "flash_attn",
216
+ "new_special_tokens": [],
217
+ "num_labels": null,
218
+ "problem_type": null,
219
+ "rope_scaling": null,
220
+ "device_map": null,
221
+ "max_memory": {},
222
+ "max_model_len": null,
223
+ "local_repo_path": null,
224
+ "init_strategy": null,
225
+ "template": "qwen2_5",
226
+ "system": null,
227
+ "max_length": 32768,
228
+ "truncation_strategy": "delete",
229
+ "max_pixels": null,
230
+ "agent_template": null,
231
+ "norm_bbox": null,
232
+ "use_chat_template": true,
233
+ "padding_side": "right",
234
+ "padding_free": false,
235
+ "loss_scale": "default",
236
+ "sequence_parallel_size": 1,
237
+ "template_backend": "swift",
238
+ "response_prefix": null,
239
+ "enable_thinking": null,
240
+ "add_non_thinking_prefix": true,
241
+ "dataset": [
242
+ "/data2/yubo/datasets/R2EGym-Data/R2EGym-SFT-Trajectories.jsonl"
243
+ ],
244
+ "val_dataset": [],
245
+ "cached_dataset": [],
246
+ "cached_val_dataset": [],
247
+ "split_dataset_ratio": 0.0,
248
+ "dataset_num_proc": 8,
249
+ "load_from_cache_file": false,
250
+ "dataset_shuffle": true,
251
+ "val_dataset_shuffle": false,
252
+ "streaming": false,
253
+ "interleave_prob": null,
254
+ "stopping_strategy": "first_exhausted",
255
+ "shuffle_buffer_size": 1000,
256
+ "download_mode": "reuse_dataset_if_exists",
257
+ "columns": {},
258
+ "strict": false,
259
+ "model_name": null,
260
+ "model_author": null,
261
+ "custom_dataset_info": [],
262
+ "quant_method": null,
263
+ "quant_bits": null,
264
+ "hqq_axis": null,
265
+ "bnb_4bit_compute_dtype": "bfloat16",
266
+ "bnb_4bit_quant_type": "nf4",
267
+ "bnb_4bit_use_double_quant": true,
268
+ "bnb_4bit_quant_storage": null,
269
+ "max_new_tokens": 64,
270
+ "temperature": 0.0,
271
+ "top_k": null,
272
+ "top_p": null,
273
+ "repetition_penalty": null,
274
+ "num_beams": 1,
275
+ "stream": false,
276
+ "stop_words": [],
277
+ "logprobs": false,
278
+ "top_logprobs": null,
279
+ "structured_outputs_regex": null,
280
+ "ckpt_dir": null,
281
+ "lora_modules": [],
282
+ "train_type": "full",
283
+ "adapters": [],
284
+ "external_plugins": [],
285
+ "model_kwargs": {},
286
+ "load_args": false,
287
+ "load_data_args": false,
288
+ "packing": false,
289
+ "packing_length": null,
290
+ "packing_num_proc": 1,
291
+ "lazy_tokenize": false,
292
+ "custom_register_path": [],
293
+ "use_hf": true,
294
+ "ignore_args_error": false,
295
+ "use_swift_lora": false,
296
+ "freeze_parameters": [],
297
+ "freeze_parameters_regex": null,
298
+ "freeze_parameters_ratio": 0.0,
299
+ "trainable_parameters": [],
300
+ "trainable_parameters_regex": null,
301
+ "freeze_llm": false,
302
+ "freeze_vit": false,
303
+ "freeze_aligner": false,
304
+ "target_modules": [
305
+ "all-linear"
306
+ ],
307
+ "target_regex": null,
308
+ "target_parameters": null,
309
+ "modules_to_save": [],
310
+ "lora_rank": 8,
311
+ "lora_alpha": 32,
312
+ "lora_dropout": 0.05,
313
+ "lora_bias": "none",
314
+ "lora_dtype": null,
315
+ "lorap_lr_ratio": null,
316
+ "use_rslora": false,
317
+ "use_dora": false,
318
+ "lora_ga_batch_size": 2,
319
+ "lora_ga_iters": 2,
320
+ "lora_ga_max_length": 1024,
321
+ "lora_ga_direction": "ArB2r",
322
+ "lora_ga_scale": "stable",
323
+ "lora_ga_stable_gamma": 16,
324
+ "init_weights": true,
325
+ "fourier_n_frequency": 2000,
326
+ "fourier_scaling": 300.0,
327
+ "boft_block_size": 4,
328
+ "boft_block_num": 0,
329
+ "boft_n_butterfly_factor": 1,
330
+ "boft_dropout": 0.0,
331
+ "vera_rank": 256,
332
+ "vera_projection_prng_key": 0,
333
+ "vera_dropout": 0.0,
334
+ "vera_d_initial": 0.1,
335
+ "adapter_act": "gelu",
336
+ "adapter_length": 128,
337
+ "use_galore": false,
338
+ "galore_target_modules": null,
339
+ "galore_rank": 128,
340
+ "galore_update_proj_gap": 50,
341
+ "galore_scale": 1.0,
342
+ "galore_proj_type": "std",
343
+ "galore_optim_per_parameter": false,
344
+ "galore_with_embedding": false,
345
+ "galore_quantization": false,
346
+ "galore_proj_quant": false,
347
+ "galore_proj_bits": 4,
348
+ "galore_proj_group_size": 256,
349
+ "galore_cos_threshold": 0.4,
350
+ "galore_gamma_proj": 2,
351
+ "galore_queue_size": 5,
352
+ "adalora_target_r": 8,
353
+ "adalora_init_r": 12,
354
+ "adalora_tinit": 0,
355
+ "adalora_tfinal": 0,
356
+ "adalora_deltaT": 1,
357
+ "adalora_beta1": 0.85,
358
+ "adalora_beta2": 0.85,
359
+ "adalora_orth_reg_weight": 0.5,
360
+ "llamapro_num_new_blocks": 4,
361
+ "llamapro_num_groups": null,
362
+ "lisa_activated_layers": 0,
363
+ "lisa_step_interval": 20,
364
+ "reft_layer_key": null,
365
+ "reft_layers": null,
366
+ "reft_rank": 4,
367
+ "reft_intervention_type": "LoreftIntervention",
368
+ "reft_args": null,
369
+ "swanlab_token": null,
370
+ "swanlab_project": "ms-swift",
371
+ "swanlab_workspace": null,
372
+ "swanlab_exp_name": null,
373
+ "swanlab_notification_method": null,
374
+ "swanlab_webhook_url": null,
375
+ "swanlab_secret": null,
376
+ "swanlab_mode": "cloud",
377
+ "add_version": true,
378
+ "create_checkpoint_symlink": false,
379
+ "zero_hpz_partition_size": null,
380
+ "deepspeed_autotp_size": null,
381
+ "early_stop_interval": null,
382
+ "rank": 0,
383
+ "global_world_size": 4,
384
+ "local_world_size": 4,
385
+ "model_suffix": "fim_qwen25_coder_7b_ins_0116-ckpt_4500",
386
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/home/user/.cache/huggingface/hub/models--ubowang--fim_qwen25_coder_7b_ins_0116-ckpt_4500/snapshots/415fd793976200fcfc97bc543ccab8e73dd4843e', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
387
+ "model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='moonshotai/Kimi-Dev-72B', hf_model_id='moonshotai/Kimi-Dev-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x7ff22745e5c0>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
388
+ "model_dir": "/home/user/.cache/huggingface/hub/models--ubowang--fim_qwen25_coder_7b_ins_0116-ckpt_4500/snapshots/415fd793976200fcfc97bc543ccab8e73dd4843e",
389
+ "_val_dataset_exists": [],
390
+ "hub": "<class 'swift.hub.hub.HFHub'>",
391
+ "evaluation_strategy": "steps",
392
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.05, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=400, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=400.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=[], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
393
+ }
v0-20260118-111123/checkpoint-400/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
v0-20260118-111123/checkpoint-400/args.json ADDED
@@ -0,0 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 1,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.05,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 2.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 400.0,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": true,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": "nccl",
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": 400.0,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": false,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch_fused",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "none"
132
+ ],
133
+ "project": "huggingface",
134
+ "trackio_space_id": "trackio",
135
+ "ddp_find_unused_parameters": null,
136
+ "ddp_bucket_cap_mb": null,
137
+ "ddp_broadcast_buffers": null,
138
+ "dataloader_pin_memory": true,
139
+ "dataloader_persistent_workers": false,
140
+ "skip_memory_metrics": true,
141
+ "use_legacy_prediction_loop": false,
142
+ "push_to_hub": false,
143
+ "resume_from_checkpoint": null,
144
+ "hub_model_id": null,
145
+ "hub_strategy": "every_save",
146
+ "hub_token": null,
147
+ "hub_private_repo": null,
148
+ "hub_always_push": false,
149
+ "hub_revision": null,
150
+ "gradient_checkpointing": true,
151
+ "gradient_checkpointing_kwargs": null,
152
+ "include_inputs_for_metrics": false,
153
+ "include_for_metrics": [],
154
+ "eval_do_concat_batches": true,
155
+ "fp16_backend": "auto",
156
+ "push_to_hub_model_id": null,
157
+ "push_to_hub_organization": null,
158
+ "push_to_hub_token": null,
159
+ "mp_parameters": "",
160
+ "auto_find_batch_size": false,
161
+ "full_determinism": false,
162
+ "torchdynamo": null,
163
+ "ray_scope": "last",
164
+ "ddp_timeout": 18000000,
165
+ "torch_compile": false,
166
+ "torch_compile_backend": null,
167
+ "torch_compile_mode": null,
168
+ "include_tokens_per_second": false,
169
+ "include_num_input_tokens_seen": false,
170
+ "neftune_noise_alpha": null,
171
+ "optim_target_modules": null,
172
+ "batch_eval_metrics": false,
173
+ "eval_on_start": false,
174
+ "use_liger_kernel": false,
175
+ "liger_kernel_config": null,
176
+ "eval_use_gather_object": false,
177
+ "average_tokens_across_devices": true,
178
+ "sortish_sampler": false,
179
+ "predict_with_generate": false,
180
+ "generation_max_length": null,
181
+ "generation_num_beams": null,
182
+ "generation_config": null,
183
+ "tuner_backend": "peft",
184
+ "vit_gradient_checkpointing": null,
185
+ "router_aux_loss_coef": 0.0,
186
+ "enable_dft_loss": false,
187
+ "enable_channel_loss": false,
188
+ "check_model": true,
189
+ "acc_strategy": "token",
190
+ "train_dataloader_shuffle": true,
191
+ "max_epochs": null,
192
+ "aligner_lr": null,
193
+ "vit_lr": null,
194
+ "use_logits_to_keep": null,
195
+ "ds3_gather_for_generation": true,
196
+ "resume_only_model": false,
197
+ "optimizer": null,
198
+ "loss_type": null,
199
+ "metric": null,
200
+ "eval_use_evalscope": false,
201
+ "eval_dataset": [],
202
+ "eval_dataset_args": null,
203
+ "eval_limit": null,
204
+ "eval_generation_config": null,
205
+ "extra_eval_args": null,
206
+ "use_flash_ckpt": false,
207
+ "use_ray": false,
208
+ "ray_exp_name": null,
209
+ "device_groups": null,
210
+ "model": "ubowang/fim_qwen25_coder_7b_ins_0116-ckpt_4500",
211
+ "model_type": "qwen2_5",
212
+ "model_revision": null,
213
+ "task_type": "causal_lm",
214
+ "torch_dtype": "bfloat16",
215
+ "attn_impl": "flash_attn",
216
+ "new_special_tokens": [],
217
+ "num_labels": null,
218
+ "problem_type": null,
219
+ "rope_scaling": null,
220
+ "device_map": null,
221
+ "max_memory": {},
222
+ "max_model_len": null,
223
+ "local_repo_path": null,
224
+ "init_strategy": null,
225
+ "template": "qwen2_5",
226
+ "system": null,
227
+ "max_length": 32768,
228
+ "truncation_strategy": "delete",
229
+ "max_pixels": null,
230
+ "agent_template": null,
231
+ "norm_bbox": null,
232
+ "use_chat_template": true,
233
+ "padding_side": "right",
234
+ "padding_free": false,
235
+ "loss_scale": "default",
236
+ "sequence_parallel_size": 1,
237
+ "template_backend": "swift",
238
+ "response_prefix": null,
239
+ "enable_thinking": null,
240
+ "add_non_thinking_prefix": true,
241
+ "dataset": [
242
+ "/data2/yubo/datasets/R2EGym-Data/R2EGym-SFT-Trajectories.jsonl"
243
+ ],
244
+ "val_dataset": [],
245
+ "cached_dataset": [],
246
+ "cached_val_dataset": [],
247
+ "split_dataset_ratio": 0.0,
248
+ "dataset_num_proc": 8,
249
+ "load_from_cache_file": false,
250
+ "dataset_shuffle": true,
251
+ "val_dataset_shuffle": false,
252
+ "streaming": false,
253
+ "interleave_prob": null,
254
+ "stopping_strategy": "first_exhausted",
255
+ "shuffle_buffer_size": 1000,
256
+ "download_mode": "reuse_dataset_if_exists",
257
+ "columns": {},
258
+ "strict": false,
259
+ "model_name": null,
260
+ "model_author": null,
261
+ "custom_dataset_info": [],
262
+ "quant_method": null,
263
+ "quant_bits": null,
264
+ "hqq_axis": null,
265
+ "bnb_4bit_compute_dtype": "bfloat16",
266
+ "bnb_4bit_quant_type": "nf4",
267
+ "bnb_4bit_use_double_quant": true,
268
+ "bnb_4bit_quant_storage": null,
269
+ "max_new_tokens": 64,
270
+ "temperature": 0.0,
271
+ "top_k": null,
272
+ "top_p": null,
273
+ "repetition_penalty": null,
274
+ "num_beams": 1,
275
+ "stream": false,
276
+ "stop_words": [],
277
+ "logprobs": false,
278
+ "top_logprobs": null,
279
+ "structured_outputs_regex": null,
280
+ "ckpt_dir": null,
281
+ "lora_modules": [],
282
+ "train_type": "full",
283
+ "adapters": [],
284
+ "external_plugins": [],
285
+ "model_kwargs": {},
286
+ "load_args": false,
287
+ "load_data_args": false,
288
+ "packing": false,
289
+ "packing_length": null,
290
+ "packing_num_proc": 1,
291
+ "lazy_tokenize": false,
292
+ "custom_register_path": [],
293
+ "use_hf": true,
294
+ "ignore_args_error": false,
295
+ "use_swift_lora": false,
296
+ "freeze_parameters": [],
297
+ "freeze_parameters_regex": null,
298
+ "freeze_parameters_ratio": 0.0,
299
+ "trainable_parameters": [],
300
+ "trainable_parameters_regex": null,
301
+ "freeze_llm": false,
302
+ "freeze_vit": false,
303
+ "freeze_aligner": false,
304
+ "target_modules": [
305
+ "all-linear"
306
+ ],
307
+ "target_regex": null,
308
+ "target_parameters": null,
309
+ "modules_to_save": [],
310
+ "lora_rank": 8,
311
+ "lora_alpha": 32,
312
+ "lora_dropout": 0.05,
313
+ "lora_bias": "none",
314
+ "lora_dtype": null,
315
+ "lorap_lr_ratio": null,
316
+ "use_rslora": false,
317
+ "use_dora": false,
318
+ "lora_ga_batch_size": 2,
319
+ "lora_ga_iters": 2,
320
+ "lora_ga_max_length": 1024,
321
+ "lora_ga_direction": "ArB2r",
322
+ "lora_ga_scale": "stable",
323
+ "lora_ga_stable_gamma": 16,
324
+ "init_weights": true,
325
+ "fourier_n_frequency": 2000,
326
+ "fourier_scaling": 300.0,
327
+ "boft_block_size": 4,
328
+ "boft_block_num": 0,
329
+ "boft_n_butterfly_factor": 1,
330
+ "boft_dropout": 0.0,
331
+ "vera_rank": 256,
332
+ "vera_projection_prng_key": 0,
333
+ "vera_dropout": 0.0,
334
+ "vera_d_initial": 0.1,
335
+ "adapter_act": "gelu",
336
+ "adapter_length": 128,
337
+ "use_galore": false,
338
+ "galore_target_modules": null,
339
+ "galore_rank": 128,
340
+ "galore_update_proj_gap": 50,
341
+ "galore_scale": 1.0,
342
+ "galore_proj_type": "std",
343
+ "galore_optim_per_parameter": false,
344
+ "galore_with_embedding": false,
345
+ "galore_quantization": false,
346
+ "galore_proj_quant": false,
347
+ "galore_proj_bits": 4,
348
+ "galore_proj_group_size": 256,
349
+ "galore_cos_threshold": 0.4,
350
+ "galore_gamma_proj": 2,
351
+ "galore_queue_size": 5,
352
+ "adalora_target_r": 8,
353
+ "adalora_init_r": 12,
354
+ "adalora_tinit": 0,
355
+ "adalora_tfinal": 0,
356
+ "adalora_deltaT": 1,
357
+ "adalora_beta1": 0.85,
358
+ "adalora_beta2": 0.85,
359
+ "adalora_orth_reg_weight": 0.5,
360
+ "llamapro_num_new_blocks": 4,
361
+ "llamapro_num_groups": null,
362
+ "lisa_activated_layers": 0,
363
+ "lisa_step_interval": 20,
364
+ "reft_layer_key": null,
365
+ "reft_layers": null,
366
+ "reft_rank": 4,
367
+ "reft_intervention_type": "LoreftIntervention",
368
+ "reft_args": null,
369
+ "swanlab_token": null,
370
+ "swanlab_project": "ms-swift",
371
+ "swanlab_workspace": null,
372
+ "swanlab_exp_name": null,
373
+ "swanlab_notification_method": null,
374
+ "swanlab_webhook_url": null,
375
+ "swanlab_secret": null,
376
+ "swanlab_mode": "cloud",
377
+ "add_version": true,
378
+ "create_checkpoint_symlink": false,
379
+ "zero_hpz_partition_size": null,
380
+ "deepspeed_autotp_size": null,
381
+ "early_stop_interval": null,
382
+ "rank": 0,
383
+ "global_world_size": 4,
384
+ "local_world_size": 4,
385
+ "model_suffix": "fim_qwen25_coder_7b_ins_0116-ckpt_4500",
386
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/home/user/.cache/huggingface/hub/models--ubowang--fim_qwen25_coder_7b_ins_0116-ckpt_4500/snapshots/415fd793976200fcfc97bc543ccab8e73dd4843e', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
387
+ "model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='moonshotai/Kimi-Dev-72B', hf_model_id='moonshotai/Kimi-Dev-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x7ff22745e5c0>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
388
+ "model_dir": "/home/user/.cache/huggingface/hub/models--ubowang--fim_qwen25_coder_7b_ins_0116-ckpt_4500/snapshots/415fd793976200fcfc97bc543ccab8e73dd4843e",
389
+ "_val_dataset_exists": [],
390
+ "hub": "<class 'swift.hub.hub.HFHub'>",
391
+ "evaluation_strategy": "steps",
392
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.05, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=400, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=400.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=[], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
393
+ }
v0-20260118-111123/checkpoint-400/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
v0-20260118-111123/checkpoint-400/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "pad_token_id": 151643,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
51
+ "rope_theta": 1000000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": false,
54
+ "transformers_version": "4.57.6",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
v0-20260118-111123/checkpoint-400/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.57.6"
14
+ }
v0-20260118-111123/checkpoint-400/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
v0-20260118-111123/checkpoint-400/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad1b686f8f46f45e53ea0533c1875353c7729ff932dce221a60a77bbcb30b3a
3
+ size 4877660776
v0-20260118-111123/checkpoint-400/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76e1f401f146eb252b3839b819ba8730426ff0a64b8c54b179e2af2a37db2328
3
+ size 4932751008
v0-20260118-111123/checkpoint-400/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc54fb3e1e3b81c7abb6c0fdf61e7aca31500c63253f140b25eab4c3c0fa507
3
+ size 4330865200
v0-20260118-111123/checkpoint-400/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a98edf9938cbaa2e35be1209f55cb0fb025b773ce3707ca66c773d317109313
3
+ size 1089994880
v0-20260118-111123/checkpoint-400/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 333312,
4
+ "total_size": 15231233024
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.norm.weight": "model-00003-of-00004.safetensors"
346
+ }
347
+ }
v0-20260118-111123/checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
v0-20260118-111123/checkpoint-400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
v0-20260118-111123/checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 32768,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
v0-20260118-111123/checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,3234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9913258983890955,
6
+ "eval_steps": 400.0,
7
+ "global_step": 400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0024783147459727386,
14
+ "grad_norm": 5.152741770615492,
15
+ "learning_rate": 2.439024390243903e-07,
16
+ "loss": 0.6280399560928345,
17
+ "step": 1,
18
+ "token_acc": 0.8466100336592403
19
+ },
20
+ {
21
+ "epoch": 0.004956629491945477,
22
+ "grad_norm": 6.659799212146136,
23
+ "learning_rate": 4.878048780487805e-07,
24
+ "loss": 0.5871974229812622,
25
+ "step": 2,
26
+ "token_acc": 0.8527404702916503
27
+ },
28
+ {
29
+ "epoch": 0.007434944237918215,
30
+ "grad_norm": 5.773096627351697,
31
+ "learning_rate": 7.317073170731707e-07,
32
+ "loss": 0.7266889810562134,
33
+ "step": 3,
34
+ "token_acc": 0.8195014575525016
35
+ },
36
+ {
37
+ "epoch": 0.009913258983890954,
38
+ "grad_norm": 4.891845561619584,
39
+ "learning_rate": 9.75609756097561e-07,
40
+ "loss": 0.6311039924621582,
41
+ "step": 4,
42
+ "token_acc": 0.8406489039478413
43
+ },
44
+ {
45
+ "epoch": 0.012391573729863693,
46
+ "grad_norm": 4.9367172329095,
47
+ "learning_rate": 1.2195121951219514e-06,
48
+ "loss": 0.5827497243881226,
49
+ "step": 5,
50
+ "token_acc": 0.8533709521202678
51
+ },
52
+ {
53
+ "epoch": 0.01486988847583643,
54
+ "grad_norm": 4.132958552073457,
55
+ "learning_rate": 1.4634146341463414e-06,
56
+ "loss": 0.5859498381614685,
57
+ "step": 6,
58
+ "token_acc": 0.8499663129526697
59
+ },
60
+ {
61
+ "epoch": 0.01734820322180917,
62
+ "grad_norm": 6.68685711165827,
63
+ "learning_rate": 1.707317073170732e-06,
64
+ "loss": 0.877733588218689,
65
+ "step": 7,
66
+ "token_acc": 0.7847027585189555
67
+ },
68
+ {
69
+ "epoch": 0.01982651796778191,
70
+ "grad_norm": 4.092598456192427,
71
+ "learning_rate": 1.951219512195122e-06,
72
+ "loss": 0.6047767400741577,
73
+ "step": 8,
74
+ "token_acc": 0.8413619032275388
75
+ },
76
+ {
77
+ "epoch": 0.022304832713754646,
78
+ "grad_norm": 3.450726245722557,
79
+ "learning_rate": 2.1951219512195125e-06,
80
+ "loss": 0.552032470703125,
81
+ "step": 9,
82
+ "token_acc": 0.8579693650116186
83
+ },
84
+ {
85
+ "epoch": 0.024783147459727387,
86
+ "grad_norm": 2.82777314462075,
87
+ "learning_rate": 2.4390243902439027e-06,
88
+ "loss": 0.5181818008422852,
89
+ "step": 10,
90
+ "token_acc": 0.8583218707015131
91
+ },
92
+ {
93
+ "epoch": 0.027261462205700124,
94
+ "grad_norm": 2.939274816084272,
95
+ "learning_rate": 2.682926829268293e-06,
96
+ "loss": 0.5806674957275391,
97
+ "step": 11,
98
+ "token_acc": 0.8409493851873034
99
+ },
100
+ {
101
+ "epoch": 0.02973977695167286,
102
+ "grad_norm": 1.5725338975804757,
103
+ "learning_rate": 2.926829268292683e-06,
104
+ "loss": 0.34537217020988464,
105
+ "step": 12,
106
+ "token_acc": 0.9047040971168437
107
+ },
108
+ {
109
+ "epoch": 0.0322180916976456,
110
+ "grad_norm": 2.2372720247977376,
111
+ "learning_rate": 3.1707317073170736e-06,
112
+ "loss": 0.5229507684707642,
113
+ "step": 13,
114
+ "token_acc": 0.8485535670507477
115
+ },
116
+ {
117
+ "epoch": 0.03469640644361834,
118
+ "grad_norm": 1.6095106609123735,
119
+ "learning_rate": 3.414634146341464e-06,
120
+ "loss": 0.4263688325881958,
121
+ "step": 14,
122
+ "token_acc": 0.8758990453772721
123
+ },
124
+ {
125
+ "epoch": 0.03717472118959108,
126
+ "grad_norm": 1.6297815842292906,
127
+ "learning_rate": 3.6585365853658537e-06,
128
+ "loss": 0.4802149534225464,
129
+ "step": 15,
130
+ "token_acc": 0.8577548387096774
131
+ },
132
+ {
133
+ "epoch": 0.03965303593556382,
134
+ "grad_norm": 1.5017200528745334,
135
+ "learning_rate": 3.902439024390244e-06,
136
+ "loss": 0.43823671340942383,
137
+ "step": 16,
138
+ "token_acc": 0.8716156345377573
139
+ },
140
+ {
141
+ "epoch": 0.042131350681536554,
142
+ "grad_norm": 1.1196694831188256,
143
+ "learning_rate": 4.146341463414634e-06,
144
+ "loss": 0.37166303396224976,
145
+ "step": 17,
146
+ "token_acc": 0.8925267476470115
147
+ },
148
+ {
149
+ "epoch": 0.04460966542750929,
150
+ "grad_norm": 1.096950979407087,
151
+ "learning_rate": 4.390243902439025e-06,
152
+ "loss": 0.3061826825141907,
153
+ "step": 18,
154
+ "token_acc": 0.9092237508019103
155
+ },
156
+ {
157
+ "epoch": 0.04708798017348203,
158
+ "grad_norm": 1.3024439530847205,
159
+ "learning_rate": 4.634146341463416e-06,
160
+ "loss": 0.4149131774902344,
161
+ "step": 19,
162
+ "token_acc": 0.8787490134175217
163
+ },
164
+ {
165
+ "epoch": 0.04956629491945477,
166
+ "grad_norm": 1.2653781544873204,
167
+ "learning_rate": 4.8780487804878055e-06,
168
+ "loss": 0.3670874536037445,
169
+ "step": 20,
170
+ "token_acc": 0.8923605604017976
171
+ },
172
+ {
173
+ "epoch": 0.05204460966542751,
174
+ "grad_norm": 1.042321818634765,
175
+ "learning_rate": 5.121951219512195e-06,
176
+ "loss": 0.3364541530609131,
177
+ "step": 21,
178
+ "token_acc": 0.9012175708815557
179
+ },
180
+ {
181
+ "epoch": 0.05452292441140025,
182
+ "grad_norm": 1.0473566879501226,
183
+ "learning_rate": 5.365853658536586e-06,
184
+ "loss": 0.32251593470573425,
185
+ "step": 22,
186
+ "token_acc": 0.9029631305134584
187
+ },
188
+ {
189
+ "epoch": 0.057001239157372985,
190
+ "grad_norm": 0.9185957485423069,
191
+ "learning_rate": 5.609756097560977e-06,
192
+ "loss": 0.2922986149787903,
193
+ "step": 23,
194
+ "token_acc": 0.9114104737264698
195
+ },
196
+ {
197
+ "epoch": 0.05947955390334572,
198
+ "grad_norm": 0.8849708686190303,
199
+ "learning_rate": 5.853658536585366e-06,
200
+ "loss": 0.2975844740867615,
201
+ "step": 24,
202
+ "token_acc": 0.9106641721234799
203
+ },
204
+ {
205
+ "epoch": 0.061957868649318466,
206
+ "grad_norm": 0.7522567244792215,
207
+ "learning_rate": 6.0975609756097564e-06,
208
+ "loss": 0.27499863505363464,
209
+ "step": 25,
210
+ "token_acc": 0.9186848213976371
211
+ },
212
+ {
213
+ "epoch": 0.0644361833952912,
214
+ "grad_norm": 0.8830568235669662,
215
+ "learning_rate": 6.341463414634147e-06,
216
+ "loss": 0.3373298645019531,
217
+ "step": 26,
218
+ "token_acc": 0.8991897152686614
219
+ },
220
+ {
221
+ "epoch": 0.06691449814126393,
222
+ "grad_norm": 1.0428133440278322,
223
+ "learning_rate": 6.585365853658538e-06,
224
+ "loss": 0.2516224682331085,
225
+ "step": 27,
226
+ "token_acc": 0.9209082669465248
227
+ },
228
+ {
229
+ "epoch": 0.06939281288723669,
230
+ "grad_norm": 0.8473054048647722,
231
+ "learning_rate": 6.829268292682928e-06,
232
+ "loss": 0.3105623126029968,
233
+ "step": 28,
234
+ "token_acc": 0.9049088492214205
235
+ },
236
+ {
237
+ "epoch": 0.07187112763320942,
238
+ "grad_norm": 0.7781697391643599,
239
+ "learning_rate": 7.0731707317073175e-06,
240
+ "loss": 0.27655029296875,
241
+ "step": 29,
242
+ "token_acc": 0.9142247456464581
243
+ },
244
+ {
245
+ "epoch": 0.07434944237918216,
246
+ "grad_norm": 1.175017796953967,
247
+ "learning_rate": 7.317073170731707e-06,
248
+ "loss": 0.28853511810302734,
249
+ "step": 30,
250
+ "token_acc": 0.9114284262411708
251
+ },
252
+ {
253
+ "epoch": 0.0768277571251549,
254
+ "grad_norm": 0.8709379398086571,
255
+ "learning_rate": 7.560975609756098e-06,
256
+ "loss": 0.2936350107192993,
257
+ "step": 31,
258
+ "token_acc": 0.9083111041372457
259
+ },
260
+ {
261
+ "epoch": 0.07930607187112763,
262
+ "grad_norm": 0.743964311077829,
263
+ "learning_rate": 7.804878048780489e-06,
264
+ "loss": 0.263607382774353,
265
+ "step": 32,
266
+ "token_acc": 0.914971964181103
267
+ },
268
+ {
269
+ "epoch": 0.08178438661710037,
270
+ "grad_norm": 0.6693404368618299,
271
+ "learning_rate": 8.048780487804879e-06,
272
+ "loss": 0.2529938817024231,
273
+ "step": 33,
274
+ "token_acc": 0.9186398628187822
275
+ },
276
+ {
277
+ "epoch": 0.08426270136307311,
278
+ "grad_norm": 0.7778307845277825,
279
+ "learning_rate": 8.292682926829268e-06,
280
+ "loss": 0.274678111076355,
281
+ "step": 34,
282
+ "token_acc": 0.9140374078972228
283
+ },
284
+ {
285
+ "epoch": 0.08674101610904585,
286
+ "grad_norm": 0.6453540682137648,
287
+ "learning_rate": 8.536585365853658e-06,
288
+ "loss": 0.2406301498413086,
289
+ "step": 35,
290
+ "token_acc": 0.9253312848089111
291
+ },
292
+ {
293
+ "epoch": 0.08921933085501858,
294
+ "grad_norm": 0.6486127774886041,
295
+ "learning_rate": 8.78048780487805e-06,
296
+ "loss": 0.2274288833141327,
297
+ "step": 36,
298
+ "token_acc": 0.9271211335752548
299
+ },
300
+ {
301
+ "epoch": 0.09169764560099132,
302
+ "grad_norm": 0.6428660359148164,
303
+ "learning_rate": 9.02439024390244e-06,
304
+ "loss": 0.25187456607818604,
305
+ "step": 37,
306
+ "token_acc": 0.9196449427703808
307
+ },
308
+ {
309
+ "epoch": 0.09417596034696406,
310
+ "grad_norm": 0.7440422572002309,
311
+ "learning_rate": 9.268292682926831e-06,
312
+ "loss": 0.25542035698890686,
313
+ "step": 38,
314
+ "token_acc": 0.9165800415800416
315
+ },
316
+ {
317
+ "epoch": 0.09665427509293681,
318
+ "grad_norm": 0.8121763291754459,
319
+ "learning_rate": 9.51219512195122e-06,
320
+ "loss": 0.29406723380088806,
321
+ "step": 39,
322
+ "token_acc": 0.9044053413203544
323
+ },
324
+ {
325
+ "epoch": 0.09913258983890955,
326
+ "grad_norm": 0.7075293006253646,
327
+ "learning_rate": 9.756097560975611e-06,
328
+ "loss": 0.24274387955665588,
329
+ "step": 40,
330
+ "token_acc": 0.9228802337792795
331
+ },
332
+ {
333
+ "epoch": 0.10161090458488228,
334
+ "grad_norm": 0.7001184277066227,
335
+ "learning_rate": 1e-05,
336
+ "loss": 0.25826495885849,
337
+ "step": 41,
338
+ "token_acc": 0.91692122790325
339
+ },
340
+ {
341
+ "epoch": 0.10408921933085502,
342
+ "grad_norm": 0.8289483682931322,
343
+ "learning_rate": 9.999958058069237e-06,
344
+ "loss": 0.307015061378479,
345
+ "step": 42,
346
+ "token_acc": 0.9035457758522404
347
+ },
348
+ {
349
+ "epoch": 0.10656753407682776,
350
+ "grad_norm": 0.8576026586334142,
351
+ "learning_rate": 9.999832232980598e-06,
352
+ "loss": 0.29618990421295166,
353
+ "step": 43,
354
+ "token_acc": 0.9024422268907563
355
+ },
356
+ {
357
+ "epoch": 0.1090458488228005,
358
+ "grad_norm": 0.7706795040958865,
359
+ "learning_rate": 9.99962252684502e-06,
360
+ "loss": 0.2699882984161377,
361
+ "step": 44,
362
+ "token_acc": 0.9110377959136424
363
+ },
364
+ {
365
+ "epoch": 0.11152416356877323,
366
+ "grad_norm": 0.7674521933852734,
367
+ "learning_rate": 9.999328943180696e-06,
368
+ "loss": 0.2609761357307434,
369
+ "step": 45,
370
+ "token_acc": 0.9139467662290738
371
+ },
372
+ {
373
+ "epoch": 0.11400247831474597,
374
+ "grad_norm": 0.7910398585026672,
375
+ "learning_rate": 9.998951486913015e-06,
376
+ "loss": 0.264095276594162,
377
+ "step": 46,
378
+ "token_acc": 0.9147150663544106
379
+ },
380
+ {
381
+ "epoch": 0.11648079306071871,
382
+ "grad_norm": 0.730661799880672,
383
+ "learning_rate": 9.998490164374472e-06,
384
+ "loss": 0.27300259470939636,
385
+ "step": 47,
386
+ "token_acc": 0.9099099099099099
387
+ },
388
+ {
389
+ "epoch": 0.11895910780669144,
390
+ "grad_norm": 0.6887734004489385,
391
+ "learning_rate": 9.99794498330457e-06,
392
+ "loss": 0.2652634084224701,
393
+ "step": 48,
394
+ "token_acc": 0.911517403206883
395
+ },
396
+ {
397
+ "epoch": 0.12143742255266418,
398
+ "grad_norm": 0.8681120120839262,
399
+ "learning_rate": 9.99731595284969e-06,
400
+ "loss": 0.30215466022491455,
401
+ "step": 49,
402
+ "token_acc": 0.9014267990074442
403
+ },
404
+ {
405
+ "epoch": 0.12391573729863693,
406
+ "grad_norm": 0.8383434490720347,
407
+ "learning_rate": 9.996603083562928e-06,
408
+ "loss": 0.28113776445388794,
409
+ "step": 50,
410
+ "token_acc": 0.9063655268022182
411
+ },
412
+ {
413
+ "epoch": 0.12639405204460966,
414
+ "grad_norm": 0.8494844754006111,
415
+ "learning_rate": 9.995806387403935e-06,
416
+ "loss": 0.29393693804740906,
417
+ "step": 51,
418
+ "token_acc": 0.9052440133373749
419
+ },
420
+ {
421
+ "epoch": 0.1288723667905824,
422
+ "grad_norm": 0.6486365110403891,
423
+ "learning_rate": 9.9949258777387e-06,
424
+ "loss": 0.24308419227600098,
425
+ "step": 52,
426
+ "token_acc": 0.9189137041146109
427
+ },
428
+ {
429
+ "epoch": 0.13135068153655513,
430
+ "grad_norm": 0.6416358040195514,
431
+ "learning_rate": 9.99396156933933e-06,
432
+ "loss": 0.23135429620742798,
433
+ "step": 53,
434
+ "token_acc": 0.9248362818883784
435
+ },
436
+ {
437
+ "epoch": 0.13382899628252787,
438
+ "grad_norm": 0.5926230753034153,
439
+ "learning_rate": 9.99291347838381e-06,
440
+ "loss": 0.21786190569400787,
441
+ "step": 54,
442
+ "token_acc": 0.9290858499058843
443
+ },
444
+ {
445
+ "epoch": 0.13630731102850063,
446
+ "grad_norm": 0.5316199275550064,
447
+ "learning_rate": 9.991781622455723e-06,
448
+ "loss": 0.18058544397354126,
449
+ "step": 55,
450
+ "token_acc": 0.9416021278260189
451
+ },
452
+ {
453
+ "epoch": 0.13878562577447337,
454
+ "grad_norm": 0.7432922658151926,
455
+ "learning_rate": 9.99056602054396e-06,
456
+ "loss": 0.2626504600048065,
457
+ "step": 56,
458
+ "token_acc": 0.9162135297900953
459
+ },
460
+ {
461
+ "epoch": 0.1412639405204461,
462
+ "grad_norm": 0.6824907609437474,
463
+ "learning_rate": 9.989266693042394e-06,
464
+ "loss": 0.24713991582393646,
465
+ "step": 57,
466
+ "token_acc": 0.915455261086329
467
+ },
468
+ {
469
+ "epoch": 0.14374225526641884,
470
+ "grad_norm": 0.6846394038528598,
471
+ "learning_rate": 9.987883661749548e-06,
472
+ "loss": 0.24615027010440826,
473
+ "step": 58,
474
+ "token_acc": 0.9182628965237661
475
+ },
476
+ {
477
+ "epoch": 0.14622057001239158,
478
+ "grad_norm": 0.671032402631692,
479
+ "learning_rate": 9.986416949868223e-06,
480
+ "loss": 0.23045897483825684,
481
+ "step": 59,
482
+ "token_acc": 0.9223265895953757
483
+ },
484
+ {
485
+ "epoch": 0.14869888475836432,
486
+ "grad_norm": 0.590392296403256,
487
+ "learning_rate": 9.984866582005112e-06,
488
+ "loss": 0.23017142713069916,
489
+ "step": 60,
490
+ "token_acc": 0.9249714565323764
491
+ },
492
+ {
493
+ "epoch": 0.15117719950433706,
494
+ "grad_norm": 0.7332906653262294,
495
+ "learning_rate": 9.98323258417038e-06,
496
+ "loss": 0.21902009844779968,
497
+ "step": 61,
498
+ "token_acc": 0.9296413980935089
499
+ },
500
+ {
501
+ "epoch": 0.1536555142503098,
502
+ "grad_norm": 0.6119683891294139,
503
+ "learning_rate": 9.98151498377724e-06,
504
+ "loss": 0.226226806640625,
505
+ "step": 62,
506
+ "token_acc": 0.9257288597686997
507
+ },
508
+ {
509
+ "epoch": 0.15613382899628253,
510
+ "grad_norm": 0.5886025443793597,
511
+ "learning_rate": 9.979713809641482e-06,
512
+ "loss": 0.21773485839366913,
513
+ "step": 63,
514
+ "token_acc": 0.9285835525757448
515
+ },
516
+ {
517
+ "epoch": 0.15861214374225527,
518
+ "grad_norm": 0.542790729138002,
519
+ "learning_rate": 9.977829091980996e-06,
520
+ "loss": 0.18839819729328156,
521
+ "step": 64,
522
+ "token_acc": 0.937266340741958
523
+ },
524
+ {
525
+ "epoch": 0.161090458488228,
526
+ "grad_norm": 0.6035397948632573,
527
+ "learning_rate": 9.975860862415255e-06,
528
+ "loss": 0.24017992615699768,
529
+ "step": 65,
530
+ "token_acc": 0.9217032967032966
531
+ },
532
+ {
533
+ "epoch": 0.16356877323420074,
534
+ "grad_norm": 0.73394638336352,
535
+ "learning_rate": 9.973809153964803e-06,
536
+ "loss": 0.2492518126964569,
537
+ "step": 66,
538
+ "token_acc": 0.9189417393751759
539
+ },
540
+ {
541
+ "epoch": 0.16604708798017348,
542
+ "grad_norm": 0.7395334010170984,
543
+ "learning_rate": 9.971674001050687e-06,
544
+ "loss": 0.22974947094917297,
545
+ "step": 67,
546
+ "token_acc": 0.9226286966046002
547
+ },
548
+ {
549
+ "epoch": 0.16852540272614622,
550
+ "grad_norm": 0.747379700769761,
551
+ "learning_rate": 9.969455439493877e-06,
552
+ "loss": 0.22691377997398376,
553
+ "step": 68,
554
+ "token_acc": 0.9222686151704941
555
+ },
556
+ {
557
+ "epoch": 0.17100371747211895,
558
+ "grad_norm": 0.658865137496205,
559
+ "learning_rate": 9.967153506514677e-06,
560
+ "loss": 0.22380544245243073,
561
+ "step": 69,
562
+ "token_acc": 0.9252806813782424
563
+ },
564
+ {
565
+ "epoch": 0.1734820322180917,
566
+ "grad_norm": 0.7356775318215079,
567
+ "learning_rate": 9.964768240732094e-06,
568
+ "loss": 0.2645195722579956,
569
+ "step": 70,
570
+ "token_acc": 0.9151927662957074
571
+ },
572
+ {
573
+ "epoch": 0.17596034696406443,
574
+ "grad_norm": 0.6105835902909259,
575
+ "learning_rate": 9.962299682163185e-06,
576
+ "loss": 0.2146928757429123,
577
+ "step": 71,
578
+ "token_acc": 0.9290130223177094
579
+ },
580
+ {
581
+ "epoch": 0.17843866171003717,
582
+ "grad_norm": 0.5329367804171343,
583
+ "learning_rate": 9.9597478722224e-06,
584
+ "loss": 0.2094036340713501,
585
+ "step": 72,
586
+ "token_acc": 0.9313269098913789
587
+ },
588
+ {
589
+ "epoch": 0.1809169764560099,
590
+ "grad_norm": 0.5747322260053925,
591
+ "learning_rate": 9.95711285372087e-06,
592
+ "loss": 0.208097904920578,
593
+ "step": 73,
594
+ "token_acc": 0.9322465208747515
595
+ },
596
+ {
597
+ "epoch": 0.18339529120198264,
598
+ "grad_norm": 0.5727093669360868,
599
+ "learning_rate": 9.954394670865701e-06,
600
+ "loss": 0.1939130574464798,
601
+ "step": 74,
602
+ "token_acc": 0.9365079365079365
603
+ },
604
+ {
605
+ "epoch": 0.18587360594795538,
606
+ "grad_norm": 0.7526598862000905,
607
+ "learning_rate": 9.95159336925923e-06,
608
+ "loss": 0.24381700158119202,
609
+ "step": 75,
610
+ "token_acc": 0.9202645132574553
611
+ },
612
+ {
613
+ "epoch": 0.18835192069392812,
614
+ "grad_norm": 0.4831188265033829,
615
+ "learning_rate": 9.948708995898251e-06,
616
+ "loss": 0.19075995683670044,
617
+ "step": 76,
618
+ "token_acc": 0.9386913802188265
619
+ },
620
+ {
621
+ "epoch": 0.19083023543990088,
622
+ "grad_norm": 0.5959016019532168,
623
+ "learning_rate": 9.945741599173244e-06,
624
+ "loss": 0.203287273645401,
625
+ "step": 77,
626
+ "token_acc": 0.9333607062204886
627
+ },
628
+ {
629
+ "epoch": 0.19330855018587362,
630
+ "grad_norm": 0.6718307740654204,
631
+ "learning_rate": 9.942691228867548e-06,
632
+ "loss": 0.230672687292099,
633
+ "step": 78,
634
+ "token_acc": 0.9241523213354199
635
+ },
636
+ {
637
+ "epoch": 0.19578686493184635,
638
+ "grad_norm": 0.7568556510207133,
639
+ "learning_rate": 9.939557936156527e-06,
640
+ "loss": 0.2662471532821655,
641
+ "step": 79,
642
+ "token_acc": 0.9116592482690405
643
+ },
644
+ {
645
+ "epoch": 0.1982651796778191,
646
+ "grad_norm": 0.6132832698144588,
647
+ "learning_rate": 9.936341773606723e-06,
648
+ "loss": 0.22949030995368958,
649
+ "step": 80,
650
+ "token_acc": 0.923230403800475
651
+ },
652
+ {
653
+ "epoch": 0.20074349442379183,
654
+ "grad_norm": 0.6142608403486509,
655
+ "learning_rate": 9.933042795174964e-06,
656
+ "loss": 0.2260524034500122,
657
+ "step": 81,
658
+ "token_acc": 0.9238841336621694
659
+ },
660
+ {
661
+ "epoch": 0.20322180916976457,
662
+ "grad_norm": 0.6225877998684491,
663
+ "learning_rate": 9.929661056207455e-06,
664
+ "loss": 0.22532519698143005,
665
+ "step": 82,
666
+ "token_acc": 0.9259611724400457
667
+ },
668
+ {
669
+ "epoch": 0.2057001239157373,
670
+ "grad_norm": 0.5949768512952913,
671
+ "learning_rate": 9.926196613438866e-06,
672
+ "loss": 0.22014835476875305,
673
+ "step": 83,
674
+ "token_acc": 0.927879393491767
675
+ },
676
+ {
677
+ "epoch": 0.20817843866171004,
678
+ "grad_norm": 0.47559912232542845,
679
+ "learning_rate": 9.922649524991359e-06,
680
+ "loss": 0.19228321313858032,
681
+ "step": 84,
682
+ "token_acc": 0.9367929993596975
683
+ },
684
+ {
685
+ "epoch": 0.21065675340768278,
686
+ "grad_norm": 0.7197566393432097,
687
+ "learning_rate": 9.919019850373635e-06,
688
+ "loss": 0.2401162087917328,
689
+ "step": 85,
690
+ "token_acc": 0.9200677392040644
691
+ },
692
+ {
693
+ "epoch": 0.21313506815365552,
694
+ "grad_norm": 0.5558026136873683,
695
+ "learning_rate": 9.915307650479915e-06,
696
+ "loss": 0.22521266341209412,
697
+ "step": 86,
698
+ "token_acc": 0.9251803095021357
699
+ },
700
+ {
701
+ "epoch": 0.21561338289962825,
702
+ "grad_norm": 0.7799930478623432,
703
+ "learning_rate": 9.911512987588932e-06,
704
+ "loss": 0.25759661197662354,
705
+ "step": 87,
706
+ "token_acc": 0.9134508141869284
707
+ },
708
+ {
709
+ "epoch": 0.218091697645601,
710
+ "grad_norm": 0.73854821966703,
711
+ "learning_rate": 9.90763592536288e-06,
712
+ "loss": 0.2677152156829834,
713
+ "step": 88,
714
+ "token_acc": 0.9098903675910184
715
+ },
716
+ {
717
+ "epoch": 0.22057001239157373,
718
+ "grad_norm": 0.6560010388105352,
719
+ "learning_rate": 9.903676528846353e-06,
720
+ "loss": 0.21643874049186707,
721
+ "step": 89,
722
+ "token_acc": 0.9248446592366111
723
+ },
724
+ {
725
+ "epoch": 0.22304832713754646,
726
+ "grad_norm": 0.6870658702391815,
727
+ "learning_rate": 9.899634864465242e-06,
728
+ "loss": 0.22982674837112427,
729
+ "step": 90,
730
+ "token_acc": 0.9247239879558381
731
+ },
732
+ {
733
+ "epoch": 0.2255266418835192,
734
+ "grad_norm": 0.8171389676709397,
735
+ "learning_rate": 9.89551100002563e-06,
736
+ "loss": 0.3131510615348816,
737
+ "step": 91,
738
+ "token_acc": 0.898832016489179
739
+ },
740
+ {
741
+ "epoch": 0.22800495662949194,
742
+ "grad_norm": 0.6475997236770011,
743
+ "learning_rate": 9.891305004712652e-06,
744
+ "loss": 0.22935685515403748,
745
+ "step": 92,
746
+ "token_acc": 0.9246883302677295
747
+ },
748
+ {
749
+ "epoch": 0.23048327137546468,
750
+ "grad_norm": 0.6984914148854385,
751
+ "learning_rate": 9.887016949089334e-06,
752
+ "loss": 0.27030426263809204,
753
+ "step": 93,
754
+ "token_acc": 0.9117368079476811
755
+ },
756
+ {
757
+ "epoch": 0.23296158612143741,
758
+ "grad_norm": 0.7155477681646722,
759
+ "learning_rate": 9.88264690509541e-06,
760
+ "loss": 0.24020570516586304,
761
+ "step": 94,
762
+ "token_acc": 0.9189102392549376
763
+ },
764
+ {
765
+ "epoch": 0.23543990086741015,
766
+ "grad_norm": 0.6625014013987743,
767
+ "learning_rate": 9.87819494604611e-06,
768
+ "loss": 0.21902109682559967,
769
+ "step": 95,
770
+ "token_acc": 0.9258085943487814
771
+ },
772
+ {
773
+ "epoch": 0.2379182156133829,
774
+ "grad_norm": 0.6857615175082238,
775
+ "learning_rate": 9.87366114663094e-06,
776
+ "loss": 0.23725655674934387,
777
+ "step": 96,
778
+ "token_acc": 0.9202574146614437
779
+ },
780
+ {
781
+ "epoch": 0.24039653035935563,
782
+ "grad_norm": 0.5382472824063855,
783
+ "learning_rate": 9.869045582912419e-06,
784
+ "loss": 0.1930842399597168,
785
+ "step": 97,
786
+ "token_acc": 0.9355825614005269
787
+ },
788
+ {
789
+ "epoch": 0.24287484510532836,
790
+ "grad_norm": 0.5917468629160709,
791
+ "learning_rate": 9.864348332324811e-06,
792
+ "loss": 0.2038682997226715,
793
+ "step": 98,
794
+ "token_acc": 0.930703241382853
795
+ },
796
+ {
797
+ "epoch": 0.24535315985130113,
798
+ "grad_norm": 0.7370278763672347,
799
+ "learning_rate": 9.859569473672816e-06,
800
+ "loss": 0.2568693161010742,
801
+ "step": 99,
802
+ "token_acc": 0.9163040989237463
803
+ },
804
+ {
805
+ "epoch": 0.24783147459727387,
806
+ "grad_norm": 0.699776450459087,
807
+ "learning_rate": 9.854709087130261e-06,
808
+ "loss": 0.23611804842948914,
809
+ "step": 100,
810
+ "token_acc": 0.9206951776499199
811
+ },
812
+ {
813
+ "epoch": 0.2503097893432466,
814
+ "grad_norm": 0.6436747511962065,
815
+ "learning_rate": 9.849767254238741e-06,
816
+ "loss": 0.2255825400352478,
817
+ "step": 101,
818
+ "token_acc": 0.9254596818159291
819
+ },
820
+ {
821
+ "epoch": 0.2527881040892193,
822
+ "grad_norm": 0.6968897120394955,
823
+ "learning_rate": 9.844744057906263e-06,
824
+ "loss": 0.22949333488941193,
825
+ "step": 102,
826
+ "token_acc": 0.9230900700734918
827
+ },
828
+ {
829
+ "epoch": 0.2552664188351921,
830
+ "grad_norm": 0.6021525343654722,
831
+ "learning_rate": 9.83963958240585e-06,
832
+ "loss": 0.22275502979755402,
833
+ "step": 103,
834
+ "token_acc": 0.9239624505928854
835
+ },
836
+ {
837
+ "epoch": 0.2577447335811648,
838
+ "grad_norm": 0.6040196891936457,
839
+ "learning_rate": 9.83445391337412e-06,
840
+ "loss": 0.20589368045330048,
841
+ "step": 104,
842
+ "token_acc": 0.9333070866141733
843
+ },
844
+ {
845
+ "epoch": 0.26022304832713755,
846
+ "grad_norm": 0.5180043364755613,
847
+ "learning_rate": 9.829187137809865e-06,
848
+ "loss": 0.1843060851097107,
849
+ "step": 105,
850
+ "token_acc": 0.9390032847102038
851
+ },
852
+ {
853
+ "epoch": 0.26270136307311026,
854
+ "grad_norm": 0.7311666721720581,
855
+ "learning_rate": 9.823839344072582e-06,
856
+ "loss": 0.24487090110778809,
857
+ "step": 106,
858
+ "token_acc": 0.9175579794556814
859
+ },
860
+ {
861
+ "epoch": 0.265179677819083,
862
+ "grad_norm": 0.5681200462480614,
863
+ "learning_rate": 9.818410621880983e-06,
864
+ "loss": 0.1999751329421997,
865
+ "step": 107,
866
+ "token_acc": 0.9352977539666186
867
+ },
868
+ {
869
+ "epoch": 0.26765799256505574,
870
+ "grad_norm": 0.8188515220846709,
871
+ "learning_rate": 9.812901062311508e-06,
872
+ "loss": 0.2684789001941681,
873
+ "step": 108,
874
+ "token_acc": 0.9121413408203793
875
+ },
876
+ {
877
+ "epoch": 0.2701363073110285,
878
+ "grad_norm": 0.7867950263321067,
879
+ "learning_rate": 9.807310757796782e-06,
880
+ "loss": 0.27002137899398804,
881
+ "step": 109,
882
+ "token_acc": 0.9115319045299561
883
+ },
884
+ {
885
+ "epoch": 0.27261462205700127,
886
+ "grad_norm": 0.5338114705656758,
887
+ "learning_rate": 9.801639802124073e-06,
888
+ "loss": 0.16630269587039948,
889
+ "step": 110,
890
+ "token_acc": 0.9444096657067735
891
+ },
892
+ {
893
+ "epoch": 0.275092936802974,
894
+ "grad_norm": 0.6396839603648911,
895
+ "learning_rate": 9.795888290433709e-06,
896
+ "loss": 0.2209298461675644,
897
+ "step": 111,
898
+ "token_acc": 0.927190623572987
899
+ },
900
+ {
901
+ "epoch": 0.27757125154894674,
902
+ "grad_norm": 0.7368184475989802,
903
+ "learning_rate": 9.790056319217496e-06,
904
+ "loss": 0.22379571199417114,
905
+ "step": 112,
906
+ "token_acc": 0.9253403601229688
907
+ },
908
+ {
909
+ "epoch": 0.28004956629491945,
910
+ "grad_norm": 0.6648239863886829,
911
+ "learning_rate": 9.784143986317084e-06,
912
+ "loss": 0.21828393638134003,
913
+ "step": 113,
914
+ "token_acc": 0.9292559769167353
915
+ },
916
+ {
917
+ "epoch": 0.2825278810408922,
918
+ "grad_norm": 0.658844948786081,
919
+ "learning_rate": 9.77815139092234e-06,
920
+ "loss": 0.22107566893100739,
921
+ "step": 114,
922
+ "token_acc": 0.9247939747857884
923
+ },
924
+ {
925
+ "epoch": 0.2850061957868649,
926
+ "grad_norm": 0.5599548678008707,
927
+ "learning_rate": 9.772078633569671e-06,
928
+ "loss": 0.1864532232284546,
929
+ "step": 115,
930
+ "token_acc": 0.9381483174513872
931
+ },
932
+ {
933
+ "epoch": 0.2874845105328377,
934
+ "grad_norm": 0.6790526573037045,
935
+ "learning_rate": 9.76592581614034e-06,
936
+ "loss": 0.2198459506034851,
937
+ "step": 116,
938
+ "token_acc": 0.9259069714545661
939
+ },
940
+ {
941
+ "epoch": 0.2899628252788104,
942
+ "grad_norm": 0.6223213126222148,
943
+ "learning_rate": 9.75969304185877e-06,
944
+ "loss": 0.21157419681549072,
945
+ "step": 117,
946
+ "token_acc": 0.9291258859264259
947
+ },
948
+ {
949
+ "epoch": 0.29244114002478316,
950
+ "grad_norm": 0.5350239894828026,
951
+ "learning_rate": 9.753380415290793e-06,
952
+ "loss": 0.182597815990448,
953
+ "step": 118,
954
+ "token_acc": 0.9411955027096983
955
+ },
956
+ {
957
+ "epoch": 0.2949194547707559,
958
+ "grad_norm": 0.5901037896882932,
959
+ "learning_rate": 9.746988042341907e-06,
960
+ "loss": 0.2082580327987671,
961
+ "step": 119,
962
+ "token_acc": 0.9305013020833334
963
+ },
964
+ {
965
+ "epoch": 0.29739776951672864,
966
+ "grad_norm": 0.6899271504906435,
967
+ "learning_rate": 9.7405160302555e-06,
968
+ "loss": 0.22355863451957703,
969
+ "step": 120,
970
+ "token_acc": 0.9284356537374775
971
+ },
972
+ {
973
+ "epoch": 0.29987608426270135,
974
+ "grad_norm": 0.49820686098077066,
975
+ "learning_rate": 9.733964487611044e-06,
976
+ "loss": 0.18118801712989807,
977
+ "step": 121,
978
+ "token_acc": 0.9391537046328817
979
+ },
980
+ {
981
+ "epoch": 0.3023543990086741,
982
+ "grad_norm": 0.6124435134555859,
983
+ "learning_rate": 9.727333524322274e-06,
984
+ "loss": 0.2028205245733261,
985
+ "step": 122,
986
+ "token_acc": 0.9331186055323987
987
+ },
988
+ {
989
+ "epoch": 0.3048327137546468,
990
+ "grad_norm": 0.6111929270056039,
991
+ "learning_rate": 9.720623251635358e-06,
992
+ "loss": 0.20341047644615173,
993
+ "step": 123,
994
+ "token_acc": 0.9306522052118827
995
+ },
996
+ {
997
+ "epoch": 0.3073110285006196,
998
+ "grad_norm": 0.6226614735059314,
999
+ "learning_rate": 9.713833782127008e-06,
1000
+ "loss": 0.2207832634449005,
1001
+ "step": 124,
1002
+ "token_acc": 0.927799011839284
1003
+ },
1004
+ {
1005
+ "epoch": 0.3097893432465923,
1006
+ "grad_norm": 0.7500226651440616,
1007
+ "learning_rate": 9.706965229702614e-06,
1008
+ "loss": 0.21534043550491333,
1009
+ "step": 125,
1010
+ "token_acc": 0.9283111600711804
1011
+ },
1012
+ {
1013
+ "epoch": 0.31226765799256506,
1014
+ "grad_norm": 0.5969983142881393,
1015
+ "learning_rate": 9.70001770959431e-06,
1016
+ "loss": 0.20864689350128174,
1017
+ "step": 126,
1018
+ "token_acc": 0.930216098895914
1019
+ },
1020
+ {
1021
+ "epoch": 0.31474597273853777,
1022
+ "grad_norm": 0.662250864463595,
1023
+ "learning_rate": 9.69299133835906e-06,
1024
+ "loss": 0.22514306008815765,
1025
+ "step": 127,
1026
+ "token_acc": 0.9244858443665288
1027
+ },
1028
+ {
1029
+ "epoch": 0.31722428748451054,
1030
+ "grad_norm": 0.6555705461454898,
1031
+ "learning_rate": 9.685886233876696e-06,
1032
+ "loss": 0.2551542818546295,
1033
+ "step": 128,
1034
+ "token_acc": 0.9149975574010747
1035
+ },
1036
+ {
1037
+ "epoch": 0.31970260223048325,
1038
+ "grad_norm": 0.683327108993182,
1039
+ "learning_rate": 9.678702515347937e-06,
1040
+ "loss": 0.20765897631645203,
1041
+ "step": 129,
1042
+ "token_acc": 0.9301343570057582
1043
+ },
1044
+ {
1045
+ "epoch": 0.322180916976456,
1046
+ "grad_norm": 0.7477289101621784,
1047
+ "learning_rate": 9.671440303292395e-06,
1048
+ "loss": 0.2211070954799652,
1049
+ "step": 130,
1050
+ "token_acc": 0.924435318275154
1051
+ },
1052
+ {
1053
+ "epoch": 0.3246592317224288,
1054
+ "grad_norm": 0.5455390247008853,
1055
+ "learning_rate": 9.664099719546547e-06,
1056
+ "loss": 0.21397201716899872,
1057
+ "step": 131,
1058
+ "token_acc": 0.9294995544995545
1059
+ },
1060
+ {
1061
+ "epoch": 0.3271375464684015,
1062
+ "grad_norm": 0.6276994581992864,
1063
+ "learning_rate": 9.656680887261693e-06,
1064
+ "loss": 0.22758865356445312,
1065
+ "step": 132,
1066
+ "token_acc": 0.9251353373531095
1067
+ },
1068
+ {
1069
+ "epoch": 0.32961586121437425,
1070
+ "grad_norm": 0.7151498487405634,
1071
+ "learning_rate": 9.649183930901895e-06,
1072
+ "loss": 0.23220603168010712,
1073
+ "step": 133,
1074
+ "token_acc": 0.920151313771598
1075
+ },
1076
+ {
1077
+ "epoch": 0.33209417596034696,
1078
+ "grad_norm": 0.7673728081031518,
1079
+ "learning_rate": 9.641608976241883e-06,
1080
+ "loss": 0.2098277360200882,
1081
+ "step": 134,
1082
+ "token_acc": 0.930225169770859
1083
+ },
1084
+ {
1085
+ "epoch": 0.3345724907063197,
1086
+ "grad_norm": 0.596061647283099,
1087
+ "learning_rate": 9.633956150364948e-06,
1088
+ "loss": 0.20195722579956055,
1089
+ "step": 135,
1090
+ "token_acc": 0.932075655175767
1091
+ },
1092
+ {
1093
+ "epoch": 0.33705080545229243,
1094
+ "grad_norm": 0.7823858157558046,
1095
+ "learning_rate": 9.626225581660802e-06,
1096
+ "loss": 0.25131508708000183,
1097
+ "step": 136,
1098
+ "token_acc": 0.9164817956413938
1099
+ },
1100
+ {
1101
+ "epoch": 0.3395291201982652,
1102
+ "grad_norm": 1.0075044360123926,
1103
+ "learning_rate": 9.618417399823442e-06,
1104
+ "loss": 0.24758443236351013,
1105
+ "step": 137,
1106
+ "token_acc": 0.9178075588121867
1107
+ },
1108
+ {
1109
+ "epoch": 0.3420074349442379,
1110
+ "grad_norm": 0.5986943628118782,
1111
+ "learning_rate": 9.610531735848953e-06,
1112
+ "loss": 0.2083842158317566,
1113
+ "step": 138,
1114
+ "token_acc": 0.9286983562860951
1115
+ },
1116
+ {
1117
+ "epoch": 0.3444857496902107,
1118
+ "grad_norm": 0.5952153058165217,
1119
+ "learning_rate": 9.602568722033325e-06,
1120
+ "loss": 0.1876327097415924,
1121
+ "step": 139,
1122
+ "token_acc": 0.9359681372549019
1123
+ },
1124
+ {
1125
+ "epoch": 0.3469640644361834,
1126
+ "grad_norm": 0.5183427523589083,
1127
+ "learning_rate": 9.594528491970228e-06,
1128
+ "loss": 0.19901341199874878,
1129
+ "step": 140,
1130
+ "token_acc": 0.9340257879656161
1131
+ },
1132
+ {
1133
+ "epoch": 0.34944237918215615,
1134
+ "grad_norm": 0.5452552403488217,
1135
+ "learning_rate": 9.586411180548771e-06,
1136
+ "loss": 0.20106159150600433,
1137
+ "step": 141,
1138
+ "token_acc": 0.9313363158918498
1139
+ },
1140
+ {
1141
+ "epoch": 0.35192069392812886,
1142
+ "grad_norm": 0.5999451588134254,
1143
+ "learning_rate": 9.57821692395124e-06,
1144
+ "loss": 0.21889635920524597,
1145
+ "step": 142,
1146
+ "token_acc": 0.9280405700795663
1147
+ },
1148
+ {
1149
+ "epoch": 0.3543990086741016,
1150
+ "grad_norm": 0.5974507676980582,
1151
+ "learning_rate": 9.56994585965081e-06,
1152
+ "loss": 0.21680448949337006,
1153
+ "step": 143,
1154
+ "token_acc": 0.9278524214801054
1155
+ },
1156
+ {
1157
+ "epoch": 0.35687732342007433,
1158
+ "grad_norm": 0.7743435372125036,
1159
+ "learning_rate": 9.561598126409247e-06,
1160
+ "loss": 0.25729891657829285,
1161
+ "step": 144,
1162
+ "token_acc": 0.912291576272237
1163
+ },
1164
+ {
1165
+ "epoch": 0.3593556381660471,
1166
+ "grad_norm": 0.5078695699272778,
1167
+ "learning_rate": 9.553173864274567e-06,
1168
+ "loss": 0.20655712485313416,
1169
+ "step": 145,
1170
+ "token_acc": 0.9319226900416726
1171
+ },
1172
+ {
1173
+ "epoch": 0.3618339529120198,
1174
+ "grad_norm": 0.7207127634706177,
1175
+ "learning_rate": 9.544673214578699e-06,
1176
+ "loss": 0.2392895221710205,
1177
+ "step": 146,
1178
+ "token_acc": 0.9207130424344278
1179
+ },
1180
+ {
1181
+ "epoch": 0.3643122676579926,
1182
+ "grad_norm": 0.622946767457105,
1183
+ "learning_rate": 9.536096319935109e-06,
1184
+ "loss": 0.22302767634391785,
1185
+ "step": 147,
1186
+ "token_acc": 0.9265117176198283
1187
+ },
1188
+ {
1189
+ "epoch": 0.3667905824039653,
1190
+ "grad_norm": 0.5908133002046843,
1191
+ "learning_rate": 9.527443324236403e-06,
1192
+ "loss": 0.21955880522727966,
1193
+ "step": 148,
1194
+ "token_acc": 0.9266511479300744
1195
+ },
1196
+ {
1197
+ "epoch": 0.36926889714993805,
1198
+ "grad_norm": 0.4522147594338494,
1199
+ "learning_rate": 9.518714372651922e-06,
1200
+ "loss": 0.16142085194587708,
1201
+ "step": 149,
1202
+ "token_acc": 0.9463032367972742
1203
+ },
1204
+ {
1205
+ "epoch": 0.37174721189591076,
1206
+ "grad_norm": 0.5720588141222915,
1207
+ "learning_rate": 9.509909611625298e-06,
1208
+ "loss": 0.2138223499059677,
1209
+ "step": 150,
1210
+ "token_acc": 0.928613329723388
1211
+ },
1212
+ {
1213
+ "epoch": 0.3742255266418835,
1214
+ "grad_norm": 0.4943942859840436,
1215
+ "learning_rate": 9.501029188872005e-06,
1216
+ "loss": 0.17425626516342163,
1217
+ "step": 151,
1218
+ "token_acc": 0.9433260023684655
1219
+ },
1220
+ {
1221
+ "epoch": 0.37670384138785623,
1222
+ "grad_norm": 0.6527934352729676,
1223
+ "learning_rate": 9.492073253376865e-06,
1224
+ "loss": 0.2078697383403778,
1225
+ "step": 152,
1226
+ "token_acc": 0.9277951545353337
1227
+ },
1228
+ {
1229
+ "epoch": 0.379182156133829,
1230
+ "grad_norm": 0.4497291806325161,
1231
+ "learning_rate": 9.48304195539158e-06,
1232
+ "loss": 0.16898579895496368,
1233
+ "step": 153,
1234
+ "token_acc": 0.9435264652881707
1235
+ },
1236
+ {
1237
+ "epoch": 0.38166047087980176,
1238
+ "grad_norm": 0.6127675342176715,
1239
+ "learning_rate": 9.473935446432169e-06,
1240
+ "loss": 0.19827896356582642,
1241
+ "step": 154,
1242
+ "token_acc": 0.9336007600548929
1243
+ },
1244
+ {
1245
+ "epoch": 0.38413878562577447,
1246
+ "grad_norm": 0.7096891416229003,
1247
+ "learning_rate": 9.464753879276467e-06,
1248
+ "loss": 0.233689546585083,
1249
+ "step": 155,
1250
+ "token_acc": 0.9231079921239965
1251
+ },
1252
+ {
1253
+ "epoch": 0.38661710037174724,
1254
+ "grad_norm": 0.5728479819889174,
1255
+ "learning_rate": 9.455497407961533e-06,
1256
+ "loss": 0.1872008740901947,
1257
+ "step": 156,
1258
+ "token_acc": 0.937733499377335
1259
+ },
1260
+ {
1261
+ "epoch": 0.38909541511771994,
1262
+ "grad_norm": 0.6547957251367851,
1263
+ "learning_rate": 9.446166187781077e-06,
1264
+ "loss": 0.22588671743869781,
1265
+ "step": 157,
1266
+ "token_acc": 0.9274172044157645
1267
+ },
1268
+ {
1269
+ "epoch": 0.3915737298636927,
1270
+ "grad_norm": 0.6016683712884341,
1271
+ "learning_rate": 9.436760375282858e-06,
1272
+ "loss": 0.20258094370365143,
1273
+ "step": 158,
1274
+ "token_acc": 0.9315724080806221
1275
+ },
1276
+ {
1277
+ "epoch": 0.3940520446096654,
1278
+ "grad_norm": 0.6675699675761844,
1279
+ "learning_rate": 9.427280128266049e-06,
1280
+ "loss": 0.21901801228523254,
1281
+ "step": 159,
1282
+ "token_acc": 0.9276966951853716
1283
+ },
1284
+ {
1285
+ "epoch": 0.3965303593556382,
1286
+ "grad_norm": 0.5118656045501407,
1287
+ "learning_rate": 9.417725605778599e-06,
1288
+ "loss": 0.18115557730197906,
1289
+ "step": 160,
1290
+ "token_acc": 0.9402752842609216
1291
+ },
1292
+ {
1293
+ "epoch": 0.3990086741016109,
1294
+ "grad_norm": 0.7409945280488002,
1295
+ "learning_rate": 9.40809696811455e-06,
1296
+ "loss": 0.2291238158941269,
1297
+ "step": 161,
1298
+ "token_acc": 0.9199870003249919
1299
+ },
1300
+ {
1301
+ "epoch": 0.40148698884758366,
1302
+ "grad_norm": 0.6725407819754182,
1303
+ "learning_rate": 9.398394376811368e-06,
1304
+ "loss": 0.20657752454280853,
1305
+ "step": 162,
1306
+ "token_acc": 0.930211616389014
1307
+ },
1308
+ {
1309
+ "epoch": 0.40396530359355637,
1310
+ "grad_norm": 0.6967521104190997,
1311
+ "learning_rate": 9.388617994647217e-06,
1312
+ "loss": 0.2295343577861786,
1313
+ "step": 163,
1314
+ "token_acc": 0.9222472442811426
1315
+ },
1316
+ {
1317
+ "epoch": 0.40644361833952913,
1318
+ "grad_norm": 0.7643832297278348,
1319
+ "learning_rate": 9.378767985638236e-06,
1320
+ "loss": 0.23990485072135925,
1321
+ "step": 164,
1322
+ "token_acc": 0.9184399456697497
1323
+ },
1324
+ {
1325
+ "epoch": 0.40892193308550184,
1326
+ "grad_norm": 0.7715949830831554,
1327
+ "learning_rate": 9.36884451503578e-06,
1328
+ "loss": 0.24740955233573914,
1329
+ "step": 165,
1330
+ "token_acc": 0.917276720351391
1331
+ },
1332
+ {
1333
+ "epoch": 0.4114002478314746,
1334
+ "grad_norm": 0.5697851408224738,
1335
+ "learning_rate": 9.35884774932366e-06,
1336
+ "loss": 0.21267423033714294,
1337
+ "step": 166,
1338
+ "token_acc": 0.9315465540685608
1339
+ },
1340
+ {
1341
+ "epoch": 0.4138785625774473,
1342
+ "grad_norm": 0.6886247346760123,
1343
+ "learning_rate": 9.348777856215335e-06,
1344
+ "loss": 0.21335873007774353,
1345
+ "step": 167,
1346
+ "token_acc": 0.928654612319951
1347
+ },
1348
+ {
1349
+ "epoch": 0.4163568773234201,
1350
+ "grad_norm": 0.6261097332803759,
1351
+ "learning_rate": 9.338635004651108e-06,
1352
+ "loss": 0.20825815200805664,
1353
+ "step": 168,
1354
+ "token_acc": 0.9295616335706257
1355
+ },
1356
+ {
1357
+ "epoch": 0.4188351920693928,
1358
+ "grad_norm": 0.6303597982966119,
1359
+ "learning_rate": 9.328419364795295e-06,
1360
+ "loss": 0.2024286389350891,
1361
+ "step": 169,
1362
+ "token_acc": 0.9301979935240724
1363
+ },
1364
+ {
1365
+ "epoch": 0.42131350681536556,
1366
+ "grad_norm": 0.6206905984226895,
1367
+ "learning_rate": 9.318131108033355e-06,
1368
+ "loss": 0.20811644196510315,
1369
+ "step": 170,
1370
+ "token_acc": 0.930644985266834
1371
+ },
1372
+ {
1373
+ "epoch": 0.42379182156133827,
1374
+ "grad_norm": 0.5943317451869768,
1375
+ "learning_rate": 9.307770406969032e-06,
1376
+ "loss": 0.19503767788410187,
1377
+ "step": 171,
1378
+ "token_acc": 0.9341296060991106
1379
+ },
1380
+ {
1381
+ "epoch": 0.42627013630731103,
1382
+ "grad_norm": 0.6126151366224994,
1383
+ "learning_rate": 9.297337435421447e-06,
1384
+ "loss": 0.20809343457221985,
1385
+ "step": 172,
1386
+ "token_acc": 0.9288450488412182
1387
+ },
1388
+ {
1389
+ "epoch": 0.42874845105328374,
1390
+ "grad_norm": 0.6788218864204016,
1391
+ "learning_rate": 9.286832368422188e-06,
1392
+ "loss": 0.20489490032196045,
1393
+ "step": 173,
1394
+ "token_acc": 0.9300904655899209
1395
+ },
1396
+ {
1397
+ "epoch": 0.4312267657992565,
1398
+ "grad_norm": 0.6404215130267227,
1399
+ "learning_rate": 9.276255382212374e-06,
1400
+ "loss": 0.18863528966903687,
1401
+ "step": 174,
1402
+ "token_acc": 0.9369472649852604
1403
+ },
1404
+ {
1405
+ "epoch": 0.43370508054522927,
1406
+ "grad_norm": 0.5728255373041314,
1407
+ "learning_rate": 9.265606654239691e-06,
1408
+ "loss": 0.20224620401859283,
1409
+ "step": 175,
1410
+ "token_acc": 0.9329154872624343
1411
+ },
1412
+ {
1413
+ "epoch": 0.436183395291202,
1414
+ "grad_norm": 0.6768672942702793,
1415
+ "learning_rate": 9.254886363155429e-06,
1416
+ "loss": 0.22328388690948486,
1417
+ "step": 176,
1418
+ "token_acc": 0.9273435938436938
1419
+ },
1420
+ {
1421
+ "epoch": 0.43866171003717475,
1422
+ "grad_norm": 0.5556571349300881,
1423
+ "learning_rate": 9.244094688811464e-06,
1424
+ "loss": 0.20803725719451904,
1425
+ "step": 177,
1426
+ "token_acc": 0.932695288282703
1427
+ },
1428
+ {
1429
+ "epoch": 0.44114002478314746,
1430
+ "grad_norm": 0.6836526040258791,
1431
+ "learning_rate": 9.233231812257266e-06,
1432
+ "loss": 0.23436599969863892,
1433
+ "step": 178,
1434
+ "token_acc": 0.9234674588171753
1435
+ },
1436
+ {
1437
+ "epoch": 0.4436183395291202,
1438
+ "grad_norm": 0.5115737682699049,
1439
+ "learning_rate": 9.222297915736835e-06,
1440
+ "loss": 0.18506181240081787,
1441
+ "step": 179,
1442
+ "token_acc": 0.9362190523036563
1443
+ },
1444
+ {
1445
+ "epoch": 0.44609665427509293,
1446
+ "grad_norm": 0.6061460775954828,
1447
+ "learning_rate": 9.211293182685668e-06,
1448
+ "loss": 0.215117409825325,
1449
+ "step": 180,
1450
+ "token_acc": 0.9277006751687922
1451
+ },
1452
+ {
1453
+ "epoch": 0.4485749690210657,
1454
+ "grad_norm": 0.591950015825152,
1455
+ "learning_rate": 9.200217797727663e-06,
1456
+ "loss": 0.22198429703712463,
1457
+ "step": 181,
1458
+ "token_acc": 0.9248879908635684
1459
+ },
1460
+ {
1461
+ "epoch": 0.4510532837670384,
1462
+ "grad_norm": 0.4538802292516009,
1463
+ "learning_rate": 9.189071946672034e-06,
1464
+ "loss": 0.16771917045116425,
1465
+ "step": 182,
1466
+ "token_acc": 0.9441254125412541
1467
+ },
1468
+ {
1469
+ "epoch": 0.45353159851301117,
1470
+ "grad_norm": 0.6128474793597602,
1471
+ "learning_rate": 9.177855816510184e-06,
1472
+ "loss": 0.19308242201805115,
1473
+ "step": 183,
1474
+ "token_acc": 0.9330043053659561
1475
+ },
1476
+ {
1477
+ "epoch": 0.4560099132589839,
1478
+ "grad_norm": 0.55222460978056,
1479
+ "learning_rate": 9.166569595412576e-06,
1480
+ "loss": 0.2128337025642395,
1481
+ "step": 184,
1482
+ "token_acc": 0.9311995099352961
1483
+ },
1484
+ {
1485
+ "epoch": 0.45848822800495664,
1486
+ "grad_norm": 0.6386137881232289,
1487
+ "learning_rate": 9.155213472725572e-06,
1488
+ "loss": 0.2336462289094925,
1489
+ "step": 185,
1490
+ "token_acc": 0.9228890272522631
1491
+ },
1492
+ {
1493
+ "epoch": 0.46096654275092935,
1494
+ "grad_norm": 0.6127306575194315,
1495
+ "learning_rate": 9.143787638968255e-06,
1496
+ "loss": 0.21513040363788605,
1497
+ "step": 186,
1498
+ "token_acc": 0.9265172550575168
1499
+ },
1500
+ {
1501
+ "epoch": 0.4634448574969021,
1502
+ "grad_norm": 0.575851496597772,
1503
+ "learning_rate": 9.132292285829237e-06,
1504
+ "loss": 0.20915384590625763,
1505
+ "step": 187,
1506
+ "token_acc": 0.931789091209381
1507
+ },
1508
+ {
1509
+ "epoch": 0.46592317224287483,
1510
+ "grad_norm": 0.6866894639350581,
1511
+ "learning_rate": 9.120727606163443e-06,
1512
+ "loss": 0.22709913551807404,
1513
+ "step": 188,
1514
+ "token_acc": 0.923712540005819
1515
+ },
1516
+ {
1517
+ "epoch": 0.4684014869888476,
1518
+ "grad_norm": 0.4616829532580403,
1519
+ "learning_rate": 9.109093793988866e-06,
1520
+ "loss": 0.18237143754959106,
1521
+ "step": 189,
1522
+ "token_acc": 0.9395834018888414
1523
+ },
1524
+ {
1525
+ "epoch": 0.4708798017348203,
1526
+ "grad_norm": 0.548795282831021,
1527
+ "learning_rate": 9.097391044483325e-06,
1528
+ "loss": 0.20833724737167358,
1529
+ "step": 190,
1530
+ "token_acc": 0.9314953134153485
1531
+ },
1532
+ {
1533
+ "epoch": 0.47335811648079307,
1534
+ "grad_norm": 0.6327097980649957,
1535
+ "learning_rate": 9.085619553981186e-06,
1536
+ "loss": 0.2095174491405487,
1537
+ "step": 191,
1538
+ "token_acc": 0.9328789958815454
1539
+ },
1540
+ {
1541
+ "epoch": 0.4758364312267658,
1542
+ "grad_norm": 0.6160991485228637,
1543
+ "learning_rate": 9.073779519970066e-06,
1544
+ "loss": 0.19501489400863647,
1545
+ "step": 192,
1546
+ "token_acc": 0.9346656418139893
1547
+ },
1548
+ {
1549
+ "epoch": 0.47831474597273854,
1550
+ "grad_norm": 0.5960561111706792,
1551
+ "learning_rate": 9.061871141087514e-06,
1552
+ "loss": 0.1809541881084442,
1553
+ "step": 193,
1554
+ "token_acc": 0.9378167443746199
1555
+ },
1556
+ {
1557
+ "epoch": 0.48079306071871125,
1558
+ "grad_norm": 0.7276209164820154,
1559
+ "learning_rate": 9.049894617117697e-06,
1560
+ "loss": 0.24918077886104584,
1561
+ "step": 194,
1562
+ "token_acc": 0.9183673469387755
1563
+ },
1564
+ {
1565
+ "epoch": 0.483271375464684,
1566
+ "grad_norm": 0.554916168082306,
1567
+ "learning_rate": 9.037850148988025e-06,
1568
+ "loss": 0.19706270098686218,
1569
+ "step": 195,
1570
+ "token_acc": 0.9340307429547395
1571
+ },
1572
+ {
1573
+ "epoch": 0.4857496902106567,
1574
+ "grad_norm": 0.5525088244186964,
1575
+ "learning_rate": 9.025737938765803e-06,
1576
+ "loss": 0.1933058351278305,
1577
+ "step": 196,
1578
+ "token_acc": 0.9362774155305276
1579
+ },
1580
+ {
1581
+ "epoch": 0.4882280049566295,
1582
+ "grad_norm": 0.6615575939404142,
1583
+ "learning_rate": 9.013558189654819e-06,
1584
+ "loss": 0.22180849313735962,
1585
+ "step": 197,
1586
+ "token_acc": 0.9267689831580157
1587
+ },
1588
+ {
1589
+ "epoch": 0.49070631970260226,
1590
+ "grad_norm": 0.5699662005218245,
1591
+ "learning_rate": 9.001311105991955e-06,
1592
+ "loss": 0.1945004016160965,
1593
+ "step": 198,
1594
+ "token_acc": 0.9362623461295188
1595
+ },
1596
+ {
1597
+ "epoch": 0.49318463444857497,
1598
+ "grad_norm": 0.5168450613257835,
1599
+ "learning_rate": 8.988996893243742e-06,
1600
+ "loss": 0.18494272232055664,
1601
+ "step": 199,
1602
+ "token_acc": 0.9360994536384512
1603
+ },
1604
+ {
1605
+ "epoch": 0.49566294919454773,
1606
+ "grad_norm": 0.6441504216639822,
1607
+ "learning_rate": 8.976615758002924e-06,
1608
+ "loss": 0.2066703736782074,
1609
+ "step": 200,
1610
+ "token_acc": 0.9319045189091115
1611
+ },
1612
+ {
1613
+ "epoch": 0.49814126394052044,
1614
+ "grad_norm": 0.5425403166000218,
1615
+ "learning_rate": 8.964167907984989e-06,
1616
+ "loss": 0.18388336896896362,
1617
+ "step": 201,
1618
+ "token_acc": 0.9378851695854578
1619
+ },
1620
+ {
1621
+ "epoch": 0.5006195786864932,
1622
+ "grad_norm": 0.5670187583380683,
1623
+ "learning_rate": 8.951653552024681e-06,
1624
+ "loss": 0.20241166651248932,
1625
+ "step": 202,
1626
+ "token_acc": 0.9331740169454703
1627
+ },
1628
+ {
1629
+ "epoch": 0.5030978934324659,
1630
+ "grad_norm": 0.6094012967081582,
1631
+ "learning_rate": 8.939072900072501e-06,
1632
+ "loss": 0.21230348944664001,
1633
+ "step": 203,
1634
+ "token_acc": 0.9279327178693992
1635
+ },
1636
+ {
1637
+ "epoch": 0.5055762081784386,
1638
+ "grad_norm": 0.6303810872406085,
1639
+ "learning_rate": 8.926426163191181e-06,
1640
+ "loss": 0.21831145882606506,
1641
+ "step": 204,
1642
+ "token_acc": 0.9257009113091977
1643
+ },
1644
+ {
1645
+ "epoch": 0.5080545229244114,
1646
+ "grad_norm": 0.6156218842788619,
1647
+ "learning_rate": 8.91371355355215e-06,
1648
+ "loss": 0.1960335373878479,
1649
+ "step": 205,
1650
+ "token_acc": 0.9342589670768907
1651
+ },
1652
+ {
1653
+ "epoch": 0.5105328376703842,
1654
+ "grad_norm": 0.6627128477954752,
1655
+ "learning_rate": 8.900935284431962e-06,
1656
+ "loss": 0.19027288258075714,
1657
+ "step": 206,
1658
+ "token_acc": 0.9349287287055279
1659
+ },
1660
+ {
1661
+ "epoch": 0.5130111524163569,
1662
+ "grad_norm": 0.6340261974079812,
1663
+ "learning_rate": 8.88809157020873e-06,
1664
+ "loss": 0.20443886518478394,
1665
+ "step": 207,
1666
+ "token_acc": 0.9333368521059854
1667
+ },
1668
+ {
1669
+ "epoch": 0.5154894671623296,
1670
+ "grad_norm": 0.5767153471346033,
1671
+ "learning_rate": 8.87518262635852e-06,
1672
+ "loss": 0.18431372940540314,
1673
+ "step": 208,
1674
+ "token_acc": 0.9386541227695059
1675
+ },
1676
+ {
1677
+ "epoch": 0.5179677819083024,
1678
+ "grad_norm": 0.6050668883402591,
1679
+ "learning_rate": 8.862208669451748e-06,
1680
+ "loss": 0.18826642632484436,
1681
+ "step": 209,
1682
+ "token_acc": 0.936156656188939
1683
+ },
1684
+ {
1685
+ "epoch": 0.5204460966542751,
1686
+ "grad_norm": 0.673772081004713,
1687
+ "learning_rate": 8.849169917149532e-06,
1688
+ "loss": 0.20627078413963318,
1689
+ "step": 210,
1690
+ "token_acc": 0.930515419452232
1691
+ },
1692
+ {
1693
+ "epoch": 0.5229244114002478,
1694
+ "grad_norm": 0.6215232261448561,
1695
+ "learning_rate": 8.836066588200052e-06,
1696
+ "loss": 0.2205003947019577,
1697
+ "step": 211,
1698
+ "token_acc": 0.9264755338826299
1699
+ },
1700
+ {
1701
+ "epoch": 0.5254027261462205,
1702
+ "grad_norm": 0.7248808212519059,
1703
+ "learning_rate": 8.822898902434873e-06,
1704
+ "loss": 0.22443747520446777,
1705
+ "step": 212,
1706
+ "token_acc": 0.9233211728144846
1707
+ },
1708
+ {
1709
+ "epoch": 0.5278810408921933,
1710
+ "grad_norm": 0.6280987767213878,
1711
+ "learning_rate": 8.809667080765262e-06,
1712
+ "loss": 0.18426331877708435,
1713
+ "step": 213,
1714
+ "token_acc": 0.9382728562740725
1715
+ },
1716
+ {
1717
+ "epoch": 0.530359355638166,
1718
+ "grad_norm": 0.5978638418562406,
1719
+ "learning_rate": 8.796371345178477e-06,
1720
+ "loss": 0.1726296991109848,
1721
+ "step": 214,
1722
+ "token_acc": 0.9419966825627203
1723
+ },
1724
+ {
1725
+ "epoch": 0.5328376703841388,
1726
+ "grad_norm": 0.6527625381905422,
1727
+ "learning_rate": 8.783011918734048e-06,
1728
+ "loss": 0.20930975675582886,
1729
+ "step": 215,
1730
+ "token_acc": 0.9278489944725391
1731
+ },
1732
+ {
1733
+ "epoch": 0.5353159851301115,
1734
+ "grad_norm": 0.6680676347048132,
1735
+ "learning_rate": 8.76958902556003e-06,
1736
+ "loss": 0.20613038539886475,
1737
+ "step": 216,
1738
+ "token_acc": 0.9301850380292882
1739
+ },
1740
+ {
1741
+ "epoch": 0.5377942998760843,
1742
+ "grad_norm": 0.5772203949335407,
1743
+ "learning_rate": 8.756102890849246e-06,
1744
+ "loss": 0.20074130594730377,
1745
+ "step": 217,
1746
+ "token_acc": 0.9329715061058345
1747
+ },
1748
+ {
1749
+ "epoch": 0.540272614622057,
1750
+ "grad_norm": 0.630539379087199,
1751
+ "learning_rate": 8.742553740855507e-06,
1752
+ "loss": 0.20127221941947937,
1753
+ "step": 218,
1754
+ "token_acc": 0.9320888316704217
1755
+ },
1756
+ {
1757
+ "epoch": 0.5427509293680297,
1758
+ "grad_norm": 0.5573207953422571,
1759
+ "learning_rate": 8.728941802889816e-06,
1760
+ "loss": 0.20900793373584747,
1761
+ "step": 219,
1762
+ "token_acc": 0.928890106449593
1763
+ },
1764
+ {
1765
+ "epoch": 0.5452292441140025,
1766
+ "grad_norm": 0.706977642744395,
1767
+ "learning_rate": 8.715267305316559e-06,
1768
+ "loss": 0.2161339521408081,
1769
+ "step": 220,
1770
+ "token_acc": 0.9270858671855996
1771
+ },
1772
+ {
1773
+ "epoch": 0.5477075588599752,
1774
+ "grad_norm": 0.7323208978556871,
1775
+ "learning_rate": 8.701530477549666e-06,
1776
+ "loss": 0.23490123450756073,
1777
+ "step": 221,
1778
+ "token_acc": 0.920802465088835
1779
+ },
1780
+ {
1781
+ "epoch": 0.550185873605948,
1782
+ "grad_norm": 0.678466158061068,
1783
+ "learning_rate": 8.68773155004877e-06,
1784
+ "loss": 0.20276901125907898,
1785
+ "step": 222,
1786
+ "token_acc": 0.9296047532937226
1787
+ },
1788
+ {
1789
+ "epoch": 0.5526641883519207,
1790
+ "grad_norm": 0.6838979877015406,
1791
+ "learning_rate": 8.673870754315336e-06,
1792
+ "loss": 0.19441470503807068,
1793
+ "step": 223,
1794
+ "token_acc": 0.934516396845164
1795
+ },
1796
+ {
1797
+ "epoch": 0.5551425030978935,
1798
+ "grad_norm": 0.5146729571241255,
1799
+ "learning_rate": 8.659948322888778e-06,
1800
+ "loss": 0.1790175884962082,
1801
+ "step": 224,
1802
+ "token_acc": 0.9439331157639984
1803
+ },
1804
+ {
1805
+ "epoch": 0.5576208178438662,
1806
+ "grad_norm": 0.5939369307546807,
1807
+ "learning_rate": 8.645964489342558e-06,
1808
+ "loss": 0.18272292613983154,
1809
+ "step": 225,
1810
+ "token_acc": 0.9374338904167548
1811
+ },
1812
+ {
1813
+ "epoch": 0.5600991325898389,
1814
+ "grad_norm": 0.7314426384555642,
1815
+ "learning_rate": 8.631919488280267e-06,
1816
+ "loss": 0.2382984757423401,
1817
+ "step": 226,
1818
+ "token_acc": 0.9210972508174882
1819
+ },
1820
+ {
1821
+ "epoch": 0.5625774473358116,
1822
+ "grad_norm": 0.55314163014409,
1823
+ "learning_rate": 8.61781355533169e-06,
1824
+ "loss": 0.18015334010124207,
1825
+ "step": 227,
1826
+ "token_acc": 0.9404659188955996
1827
+ },
1828
+ {
1829
+ "epoch": 0.5650557620817844,
1830
+ "grad_norm": 0.5790780923764937,
1831
+ "learning_rate": 8.60364692714885e-06,
1832
+ "loss": 0.22071409225463867,
1833
+ "step": 228,
1834
+ "token_acc": 0.9261137420896023
1835
+ },
1836
+ {
1837
+ "epoch": 0.5675340768277571,
1838
+ "grad_norm": 0.5388610489460713,
1839
+ "learning_rate": 8.589419841402046e-06,
1840
+ "loss": 0.19880539178848267,
1841
+ "step": 229,
1842
+ "token_acc": 0.9337815810920945
1843
+ },
1844
+ {
1845
+ "epoch": 0.5700123915737298,
1846
+ "grad_norm": 0.5062223819784819,
1847
+ "learning_rate": 8.575132536775854e-06,
1848
+ "loss": 0.1726711392402649,
1849
+ "step": 230,
1850
+ "token_acc": 0.941608678739681
1851
+ },
1852
+ {
1853
+ "epoch": 0.5724907063197026,
1854
+ "grad_norm": 0.5700260555970162,
1855
+ "learning_rate": 8.560785252965131e-06,
1856
+ "loss": 0.17924195528030396,
1857
+ "step": 231,
1858
+ "token_acc": 0.9390111312451462
1859
+ },
1860
+ {
1861
+ "epoch": 0.5749690210656754,
1862
+ "grad_norm": 0.5687606803661089,
1863
+ "learning_rate": 8.546378230670992e-06,
1864
+ "loss": 0.20395219326019287,
1865
+ "step": 232,
1866
+ "token_acc": 0.9305410912383971
1867
+ },
1868
+ {
1869
+ "epoch": 0.5774473358116481,
1870
+ "grad_norm": 0.5400095751423698,
1871
+ "learning_rate": 8.531911711596767e-06,
1872
+ "loss": 0.17791907489299774,
1873
+ "step": 233,
1874
+ "token_acc": 0.9411820152700537
1875
+ },
1876
+ {
1877
+ "epoch": 0.5799256505576208,
1878
+ "grad_norm": 0.6627759646192548,
1879
+ "learning_rate": 8.517385938443955e-06,
1880
+ "loss": 0.21611914038658142,
1881
+ "step": 234,
1882
+ "token_acc": 0.9283404550179004
1883
+ },
1884
+ {
1885
+ "epoch": 0.5824039653035935,
1886
+ "grad_norm": 0.6250073221544682,
1887
+ "learning_rate": 8.502801154908142e-06,
1888
+ "loss": 0.21550783514976501,
1889
+ "step": 235,
1890
+ "token_acc": 0.9273776471228701
1891
+ },
1892
+ {
1893
+ "epoch": 0.5848822800495663,
1894
+ "grad_norm": 0.5646934768164484,
1895
+ "learning_rate": 8.488157605674924e-06,
1896
+ "loss": 0.18716537952423096,
1897
+ "step": 236,
1898
+ "token_acc": 0.9344546381243629
1899
+ },
1900
+ {
1901
+ "epoch": 0.587360594795539,
1902
+ "grad_norm": 0.6528211084204466,
1903
+ "learning_rate": 8.47345553641579e-06,
1904
+ "loss": 0.21393099427223206,
1905
+ "step": 237,
1906
+ "token_acc": 0.9265933559790431
1907
+ },
1908
+ {
1909
+ "epoch": 0.5898389095415117,
1910
+ "grad_norm": 0.6034916566195073,
1911
+ "learning_rate": 8.45869519378401e-06,
1912
+ "loss": 0.19407245516777039,
1913
+ "step": 238,
1914
+ "token_acc": 0.9347174540896954
1915
+ },
1916
+ {
1917
+ "epoch": 0.5923172242874845,
1918
+ "grad_norm": 0.626877334263163,
1919
+ "learning_rate": 8.443876825410488e-06,
1920
+ "loss": 0.2260097861289978,
1921
+ "step": 239,
1922
+ "token_acc": 0.9232705620370819
1923
+ },
1924
+ {
1925
+ "epoch": 0.5947955390334573,
1926
+ "grad_norm": 1.171144060805512,
1927
+ "learning_rate": 8.42900067989962e-06,
1928
+ "loss": 0.23795972764492035,
1929
+ "step": 240,
1930
+ "token_acc": 0.9191248770894789
1931
+ },
1932
+ {
1933
+ "epoch": 0.59727385377943,
1934
+ "grad_norm": 0.5935481164796732,
1935
+ "learning_rate": 8.414067006825108e-06,
1936
+ "loss": 0.1915152370929718,
1937
+ "step": 241,
1938
+ "token_acc": 0.9368189491993656
1939
+ },
1940
+ {
1941
+ "epoch": 0.5997521685254027,
1942
+ "grad_norm": 0.5177092917429869,
1943
+ "learning_rate": 8.39907605672579e-06,
1944
+ "loss": 0.1808878481388092,
1945
+ "step": 242,
1946
+ "token_acc": 0.9389654041646172
1947
+ },
1948
+ {
1949
+ "epoch": 0.6022304832713755,
1950
+ "grad_norm": 0.5689840506690478,
1951
+ "learning_rate": 8.384028081101419e-06,
1952
+ "loss": 0.21098077297210693,
1953
+ "step": 243,
1954
+ "token_acc": 0.9286966919091272
1955
+ },
1956
+ {
1957
+ "epoch": 0.6047087980173482,
1958
+ "grad_norm": 0.6625490667351845,
1959
+ "learning_rate": 8.368923332408458e-06,
1960
+ "loss": 0.23235644400119781,
1961
+ "step": 244,
1962
+ "token_acc": 0.920873431256683
1963
+ },
1964
+ {
1965
+ "epoch": 0.6071871127633209,
1966
+ "grad_norm": 0.6358060572009174,
1967
+ "learning_rate": 8.353762064055832e-06,
1968
+ "loss": 0.1980096697807312,
1969
+ "step": 245,
1970
+ "token_acc": 0.9334184604159066
1971
+ },
1972
+ {
1973
+ "epoch": 0.6096654275092936,
1974
+ "grad_norm": 0.5563438771858398,
1975
+ "learning_rate": 8.338544530400693e-06,
1976
+ "loss": 0.20029008388519287,
1977
+ "step": 246,
1978
+ "token_acc": 0.9327420217507577
1979
+ },
1980
+ {
1981
+ "epoch": 0.6121437422552665,
1982
+ "grad_norm": 0.4168473960177944,
1983
+ "learning_rate": 8.323270986744137e-06,
1984
+ "loss": 0.1664401888847351,
1985
+ "step": 247,
1986
+ "token_acc": 0.9462456564435715
1987
+ },
1988
+ {
1989
+ "epoch": 0.6146220570012392,
1990
+ "grad_norm": 0.5004898966926267,
1991
+ "learning_rate": 8.307941689326926e-06,
1992
+ "loss": 0.1937483549118042,
1993
+ "step": 248,
1994
+ "token_acc": 0.9359970674486804
1995
+ },
1996
+ {
1997
+ "epoch": 0.6171003717472119,
1998
+ "grad_norm": 0.7477820522230303,
1999
+ "learning_rate": 8.292556895325195e-06,
2000
+ "loss": 0.21603208780288696,
2001
+ "step": 249,
2002
+ "token_acc": 0.9262365090457334
2003
+ },
2004
+ {
2005
+ "epoch": 0.6195786864931846,
2006
+ "grad_norm": 0.5818096175116726,
2007
+ "learning_rate": 8.277116862846127e-06,
2008
+ "loss": 0.21266460418701172,
2009
+ "step": 250,
2010
+ "token_acc": 0.9294168177913524
2011
+ },
2012
+ {
2013
+ "epoch": 0.6220570012391574,
2014
+ "grad_norm": 0.5937754927981138,
2015
+ "learning_rate": 8.261621850923634e-06,
2016
+ "loss": 0.22889626026153564,
2017
+ "step": 251,
2018
+ "token_acc": 0.9259275349726301
2019
+ },
2020
+ {
2021
+ "epoch": 0.6245353159851301,
2022
+ "grad_norm": 0.5508671109709956,
2023
+ "learning_rate": 8.246072119514002e-06,
2024
+ "loss": 0.1992526799440384,
2025
+ "step": 252,
2026
+ "token_acc": 0.9345569370436155
2027
+ },
2028
+ {
2029
+ "epoch": 0.6270136307311028,
2030
+ "grad_norm": 0.6532930689067593,
2031
+ "learning_rate": 8.230467929491533e-06,
2032
+ "loss": 0.1896224319934845,
2033
+ "step": 253,
2034
+ "token_acc": 0.9324170298357358
2035
+ },
2036
+ {
2037
+ "epoch": 0.6294919454770755,
2038
+ "grad_norm": 0.5866405166556274,
2039
+ "learning_rate": 8.214809542644173e-06,
2040
+ "loss": 0.20115667581558228,
2041
+ "step": 254,
2042
+ "token_acc": 0.933378196500673
2043
+ },
2044
+ {
2045
+ "epoch": 0.6319702602230484,
2046
+ "grad_norm": 0.6222964865692054,
2047
+ "learning_rate": 8.19909722166911e-06,
2048
+ "loss": 0.2246522754430771,
2049
+ "step": 255,
2050
+ "token_acc": 0.9247518736074539
2051
+ },
2052
+ {
2053
+ "epoch": 0.6344485749690211,
2054
+ "grad_norm": 0.600425273762884,
2055
+ "learning_rate": 8.183331230168376e-06,
2056
+ "loss": 0.1945718377828598,
2057
+ "step": 256,
2058
+ "token_acc": 0.9320788441487513
2059
+ },
2060
+ {
2061
+ "epoch": 0.6369268897149938,
2062
+ "grad_norm": 0.5667425615175953,
2063
+ "learning_rate": 8.167511832644423e-06,
2064
+ "loss": 0.1906515657901764,
2065
+ "step": 257,
2066
+ "token_acc": 0.9347599659123189
2067
+ },
2068
+ {
2069
+ "epoch": 0.6394052044609665,
2070
+ "grad_norm": 0.5182925994116764,
2071
+ "learning_rate": 8.151639294495678e-06,
2072
+ "loss": 0.17993804812431335,
2073
+ "step": 258,
2074
+ "token_acc": 0.938014381010136
2075
+ },
2076
+ {
2077
+ "epoch": 0.6418835192069393,
2078
+ "grad_norm": 0.49728703734755825,
2079
+ "learning_rate": 8.135713882012102e-06,
2080
+ "loss": 0.15953490138053894,
2081
+ "step": 259,
2082
+ "token_acc": 0.9461400359066428
2083
+ },
2084
+ {
2085
+ "epoch": 0.644361833952912,
2086
+ "grad_norm": 0.46783465054741635,
2087
+ "learning_rate": 8.11973586237071e-06,
2088
+ "loss": 0.17956344783306122,
2089
+ "step": 260,
2090
+ "token_acc": 0.9405183542418325
2091
+ },
2092
+ {
2093
+ "epoch": 0.6468401486988847,
2094
+ "grad_norm": 0.7319638710672299,
2095
+ "learning_rate": 8.103705503631103e-06,
2096
+ "loss": 0.2269260287284851,
2097
+ "step": 261,
2098
+ "token_acc": 0.9224162817551963
2099
+ },
2100
+ {
2101
+ "epoch": 0.6493184634448576,
2102
+ "grad_norm": 0.4995015656344108,
2103
+ "learning_rate": 8.08762307473096e-06,
2104
+ "loss": 0.1820226013660431,
2105
+ "step": 262,
2106
+ "token_acc": 0.9379474940334129
2107
+ },
2108
+ {
2109
+ "epoch": 0.6517967781908303,
2110
+ "grad_norm": 0.5788698092106506,
2111
+ "learning_rate": 8.071488845481528e-06,
2112
+ "loss": 0.18767325580120087,
2113
+ "step": 263,
2114
+ "token_acc": 0.9344489447878918
2115
+ },
2116
+ {
2117
+ "epoch": 0.654275092936803,
2118
+ "grad_norm": 0.6162397655104307,
2119
+ "learning_rate": 8.055303086563095e-06,
2120
+ "loss": 0.210616797208786,
2121
+ "step": 264,
2122
+ "token_acc": 0.927035175879397
2123
+ },
2124
+ {
2125
+ "epoch": 0.6567534076827757,
2126
+ "grad_norm": 0.5590643590623036,
2127
+ "learning_rate": 8.039066069520455e-06,
2128
+ "loss": 0.19739603996276855,
2129
+ "step": 265,
2130
+ "token_acc": 0.9343771218596477
2131
+ },
2132
+ {
2133
+ "epoch": 0.6592317224287485,
2134
+ "grad_norm": 0.5474408000165578,
2135
+ "learning_rate": 8.022778066758348e-06,
2136
+ "loss": 0.1951625943183899,
2137
+ "step": 266,
2138
+ "token_acc": 0.9340235208645506
2139
+ },
2140
+ {
2141
+ "epoch": 0.6617100371747212,
2142
+ "grad_norm": 0.5263224136495609,
2143
+ "learning_rate": 8.006439351536884e-06,
2144
+ "loss": 0.15536092221736908,
2145
+ "step": 267,
2146
+ "token_acc": 0.9457600874396576
2147
+ },
2148
+ {
2149
+ "epoch": 0.6641883519206939,
2150
+ "grad_norm": 0.6000925509427537,
2151
+ "learning_rate": 7.99005019796697e-06,
2152
+ "loss": 0.19458061456680298,
2153
+ "step": 268,
2154
+ "token_acc": 0.9349200637433814
2155
+ },
2156
+ {
2157
+ "epoch": 0.6666666666666666,
2158
+ "grad_norm": 0.6109362743814596,
2159
+ "learning_rate": 7.973610881005702e-06,
2160
+ "loss": 0.22864320874214172,
2161
+ "step": 269,
2162
+ "token_acc": 0.9233961764316305
2163
+ },
2164
+ {
2165
+ "epoch": 0.6691449814126395,
2166
+ "grad_norm": 0.5515360866507103,
2167
+ "learning_rate": 7.95712167645176e-06,
2168
+ "loss": 0.17370453476905823,
2169
+ "step": 270,
2170
+ "token_acc": 0.9400685735756893
2171
+ },
2172
+ {
2173
+ "epoch": 0.6716232961586122,
2174
+ "grad_norm": 0.5517581110380569,
2175
+ "learning_rate": 7.940582860940771e-06,
2176
+ "loss": 0.1959170252084732,
2177
+ "step": 271,
2178
+ "token_acc": 0.9334157210800285
2179
+ },
2180
+ {
2181
+ "epoch": 0.6741016109045849,
2182
+ "grad_norm": 0.6023695000385836,
2183
+ "learning_rate": 7.923994711940682e-06,
2184
+ "loss": 0.20243093371391296,
2185
+ "step": 272,
2186
+ "token_acc": 0.9320584504064277
2187
+ },
2188
+ {
2189
+ "epoch": 0.6765799256505576,
2190
+ "grad_norm": 0.579838691115063,
2191
+ "learning_rate": 7.907357507747087e-06,
2192
+ "loss": 0.1811404824256897,
2193
+ "step": 273,
2194
+ "token_acc": 0.9389541799495646
2195
+ },
2196
+ {
2197
+ "epoch": 0.6790582403965304,
2198
+ "grad_norm": 0.5410980235074818,
2199
+ "learning_rate": 7.890671527478575e-06,
2200
+ "loss": 0.17881739139556885,
2201
+ "step": 274,
2202
+ "token_acc": 0.9382754069511658
2203
+ },
2204
+ {
2205
+ "epoch": 0.6815365551425031,
2206
+ "grad_norm": 0.6303396215802266,
2207
+ "learning_rate": 7.873937051072037e-06,
2208
+ "loss": 0.22740472853183746,
2209
+ "step": 275,
2210
+ "token_acc": 0.9244822146455651
2211
+ },
2212
+ {
2213
+ "epoch": 0.6840148698884758,
2214
+ "grad_norm": 0.534856159094388,
2215
+ "learning_rate": 7.857154359277972e-06,
2216
+ "loss": 0.19125010073184967,
2217
+ "step": 276,
2218
+ "token_acc": 0.9334574028122415
2219
+ },
2220
+ {
2221
+ "epoch": 0.6864931846344485,
2222
+ "grad_norm": 0.58199519274568,
2223
+ "learning_rate": 7.84032373365578e-06,
2224
+ "loss": 0.20449823141098022,
2225
+ "step": 277,
2226
+ "token_acc": 0.9327064485939659
2227
+ },
2228
+ {
2229
+ "epoch": 0.6889714993804213,
2230
+ "grad_norm": 0.7394397701801595,
2231
+ "learning_rate": 7.823445456569036e-06,
2232
+ "loss": 0.2184322476387024,
2233
+ "step": 278,
2234
+ "token_acc": 0.9259209645010047
2235
+ },
2236
+ {
2237
+ "epoch": 0.6914498141263941,
2238
+ "grad_norm": 0.6521911100329248,
2239
+ "learning_rate": 7.80651981118075e-06,
2240
+ "loss": 0.21323230862617493,
2241
+ "step": 279,
2242
+ "token_acc": 0.9276371054842194
2243
+ },
2244
+ {
2245
+ "epoch": 0.6939281288723668,
2246
+ "grad_norm": 0.5697117731472794,
2247
+ "learning_rate": 7.789547081448622e-06,
2248
+ "loss": 0.20801597833633423,
2249
+ "step": 280,
2250
+ "token_acc": 0.930193800295224
2251
+ },
2252
+ {
2253
+ "epoch": 0.6964064436183395,
2254
+ "grad_norm": 0.656090212866248,
2255
+ "learning_rate": 7.772527552120274e-06,
2256
+ "loss": 0.21424278616905212,
2257
+ "step": 281,
2258
+ "token_acc": 0.9280575539568345
2259
+ },
2260
+ {
2261
+ "epoch": 0.6988847583643123,
2262
+ "grad_norm": 0.5743969737426162,
2263
+ "learning_rate": 7.755461508728473e-06,
2264
+ "loss": 0.19612297415733337,
2265
+ "step": 282,
2266
+ "token_acc": 0.9327879292607651
2267
+ },
2268
+ {
2269
+ "epoch": 0.701363073110285,
2270
+ "grad_norm": 0.5792095358639111,
2271
+ "learning_rate": 7.738349237586344e-06,
2272
+ "loss": 0.18293830752372742,
2273
+ "step": 283,
2274
+ "token_acc": 0.9371380846325167
2275
+ },
2276
+ {
2277
+ "epoch": 0.7038413878562577,
2278
+ "grad_norm": 0.6075004036847184,
2279
+ "learning_rate": 7.721191025782563e-06,
2280
+ "loss": 0.18939663469791412,
2281
+ "step": 284,
2282
+ "token_acc": 0.9343621068424155
2283
+ },
2284
+ {
2285
+ "epoch": 0.7063197026022305,
2286
+ "grad_norm": 0.4872633175900578,
2287
+ "learning_rate": 7.703987161176545e-06,
2288
+ "loss": 0.18252162635326385,
2289
+ "step": 285,
2290
+ "token_acc": 0.9388334209143457
2291
+ },
2292
+ {
2293
+ "epoch": 0.7087980173482032,
2294
+ "grad_norm": 0.6246293156496817,
2295
+ "learning_rate": 7.686737932393606e-06,
2296
+ "loss": 0.21944214403629303,
2297
+ "step": 286,
2298
+ "token_acc": 0.9269831730769231
2299
+ },
2300
+ {
2301
+ "epoch": 0.711276332094176,
2302
+ "grad_norm": 0.5299883361203443,
2303
+ "learning_rate": 7.66944362882013e-06,
2304
+ "loss": 0.18632715940475464,
2305
+ "step": 287,
2306
+ "token_acc": 0.9367708105746122
2307
+ },
2308
+ {
2309
+ "epoch": 0.7137546468401487,
2310
+ "grad_norm": 0.6117209586255409,
2311
+ "learning_rate": 7.652104540598712e-06,
2312
+ "loss": 0.21137729287147522,
2313
+ "step": 288,
2314
+ "token_acc": 0.9294571372778754
2315
+ },
2316
+ {
2317
+ "epoch": 0.7162329615861215,
2318
+ "grad_norm": 0.6572478191645179,
2319
+ "learning_rate": 7.634720958623287e-06,
2320
+ "loss": 0.20750752091407776,
2321
+ "step": 289,
2322
+ "token_acc": 0.9291399844395236
2323
+ },
2324
+ {
2325
+ "epoch": 0.7187112763320942,
2326
+ "grad_norm": 0.47910401018331705,
2327
+ "learning_rate": 7.617293174534252e-06,
2328
+ "loss": 0.17338941991329193,
2329
+ "step": 290,
2330
+ "token_acc": 0.9426690391459075
2331
+ },
2332
+ {
2333
+ "epoch": 0.7211895910780669,
2334
+ "grad_norm": 0.5377221892461833,
2335
+ "learning_rate": 7.599821480713571e-06,
2336
+ "loss": 0.19114184379577637,
2337
+ "step": 291,
2338
+ "token_acc": 0.9377901175653984
2339
+ },
2340
+ {
2341
+ "epoch": 0.7236679058240396,
2342
+ "grad_norm": 0.6115410286839338,
2343
+ "learning_rate": 7.582306170279873e-06,
2344
+ "loss": 0.20206016302108765,
2345
+ "step": 292,
2346
+ "token_acc": 0.9323294629898403
2347
+ },
2348
+ {
2349
+ "epoch": 0.7261462205700124,
2350
+ "grad_norm": 0.4279550372611684,
2351
+ "learning_rate": 7.564747537083533e-06,
2352
+ "loss": 0.1663416624069214,
2353
+ "step": 293,
2354
+ "token_acc": 0.9443231767484974
2355
+ },
2356
+ {
2357
+ "epoch": 0.7286245353159851,
2358
+ "grad_norm": 0.5848129427187966,
2359
+ "learning_rate": 7.547145875701744e-06,
2360
+ "loss": 0.20620694756507874,
2361
+ "step": 294,
2362
+ "token_acc": 0.9294997662459094
2363
+ },
2364
+ {
2365
+ "epoch": 0.7311028500619579,
2366
+ "grad_norm": 0.6355812473873715,
2367
+ "learning_rate": 7.52950148143357e-06,
2368
+ "loss": 0.1970592439174652,
2369
+ "step": 295,
2370
+ "token_acc": 0.9324528513067323
2371
+ },
2372
+ {
2373
+ "epoch": 0.7335811648079306,
2374
+ "grad_norm": 0.5580070454330123,
2375
+ "learning_rate": 7.511814650294994e-06,
2376
+ "loss": 0.17839810252189636,
2377
+ "step": 296,
2378
+ "token_acc": 0.9410022216736609
2379
+ },
2380
+ {
2381
+ "epoch": 0.7360594795539034,
2382
+ "grad_norm": 0.7275718966914226,
2383
+ "learning_rate": 7.494085679013959e-06,
2384
+ "loss": 0.2294643223285675,
2385
+ "step": 297,
2386
+ "token_acc": 0.9234541719133144
2387
+ },
2388
+ {
2389
+ "epoch": 0.7385377942998761,
2390
+ "grad_norm": 0.5964011648720088,
2391
+ "learning_rate": 7.476314865025376e-06,
2392
+ "loss": 0.19412359595298767,
2393
+ "step": 298,
2394
+ "token_acc": 0.9333266088359895
2395
+ },
2396
+ {
2397
+ "epoch": 0.7410161090458488,
2398
+ "grad_norm": 0.5039555343899965,
2399
+ "learning_rate": 7.458502506466146e-06,
2400
+ "loss": 0.16995006799697876,
2401
+ "step": 299,
2402
+ "token_acc": 0.9432942637017563
2403
+ },
2404
+ {
2405
+ "epoch": 0.7434944237918215,
2406
+ "grad_norm": 0.6398992419325267,
2407
+ "learning_rate": 7.440648902170153e-06,
2408
+ "loss": 0.18903273344039917,
2409
+ "step": 300,
2410
+ "token_acc": 0.9334855837853269
2411
+ },
2412
+ {
2413
+ "epoch": 0.7459727385377943,
2414
+ "grad_norm": 0.5421990175916391,
2415
+ "learning_rate": 7.422754351663252e-06,
2416
+ "loss": 0.19011856615543365,
2417
+ "step": 301,
2418
+ "token_acc": 0.9360713997253857
2419
+ },
2420
+ {
2421
+ "epoch": 0.748451053283767,
2422
+ "grad_norm": 0.6140288431029091,
2423
+ "learning_rate": 7.40481915515824e-06,
2424
+ "loss": 0.17020569741725922,
2425
+ "step": 302,
2426
+ "token_acc": 0.9416936603424341
2427
+ },
2428
+ {
2429
+ "epoch": 0.7509293680297398,
2430
+ "grad_norm": 0.5982403316873622,
2431
+ "learning_rate": 7.386843613549828e-06,
2432
+ "loss": 0.17316171526908875,
2433
+ "step": 303,
2434
+ "token_acc": 0.9399900398406374
2435
+ },
2436
+ {
2437
+ "epoch": 0.7534076827757125,
2438
+ "grad_norm": 0.7851257524727686,
2439
+ "learning_rate": 7.368828028409581e-06,
2440
+ "loss": 0.23701409995555878,
2441
+ "step": 304,
2442
+ "token_acc": 0.9165071418053305
2443
+ },
2444
+ {
2445
+ "epoch": 0.7558859975216853,
2446
+ "grad_norm": 0.45666946025221367,
2447
+ "learning_rate": 7.350772701980873e-06,
2448
+ "loss": 0.16829898953437805,
2449
+ "step": 305,
2450
+ "token_acc": 0.9441734417344173
2451
+ },
2452
+ {
2453
+ "epoch": 0.758364312267658,
2454
+ "grad_norm": 0.5741027060975898,
2455
+ "learning_rate": 7.3326779371738e-06,
2456
+ "loss": 0.17554450035095215,
2457
+ "step": 306,
2458
+ "token_acc": 0.9402452507789728
2459
+ },
2460
+ {
2461
+ "epoch": 0.7608426270136307,
2462
+ "grad_norm": 0.6549678676805689,
2463
+ "learning_rate": 7.314544037560115e-06,
2464
+ "loss": 0.21247723698616028,
2465
+ "step": 307,
2466
+ "token_acc": 0.9304372041214146
2467
+ },
2468
+ {
2469
+ "epoch": 0.7633209417596035,
2470
+ "grad_norm": 0.7385901437352895,
2471
+ "learning_rate": 7.29637130736812e-06,
2472
+ "loss": 0.22944791615009308,
2473
+ "step": 308,
2474
+ "token_acc": 0.92206132879046
2475
+ },
2476
+ {
2477
+ "epoch": 0.7657992565055762,
2478
+ "grad_norm": 0.5144341401490085,
2479
+ "learning_rate": 7.278160051477574e-06,
2480
+ "loss": 0.1714993715286255,
2481
+ "step": 309,
2482
+ "token_acc": 0.940737916719617
2483
+ },
2484
+ {
2485
+ "epoch": 0.7682775712515489,
2486
+ "grad_norm": 0.5198966028685696,
2487
+ "learning_rate": 7.259910575414569e-06,
2488
+ "loss": 0.17764417827129364,
2489
+ "step": 310,
2490
+ "token_acc": 0.94173100365705
2491
+ },
2492
+ {
2493
+ "epoch": 0.7707558859975217,
2494
+ "grad_norm": 0.559356037335089,
2495
+ "learning_rate": 7.241623185346409e-06,
2496
+ "loss": 0.18551871180534363,
2497
+ "step": 311,
2498
+ "token_acc": 0.9365185581727338
2499
+ },
2500
+ {
2501
+ "epoch": 0.7732342007434945,
2502
+ "grad_norm": 0.5447581960295469,
2503
+ "learning_rate": 7.223298188076475e-06,
2504
+ "loss": 0.18551039695739746,
2505
+ "step": 312,
2506
+ "token_acc": 0.9366012198922576
2507
+ },
2508
+ {
2509
+ "epoch": 0.7757125154894672,
2510
+ "grad_norm": 0.5956272946818882,
2511
+ "learning_rate": 7.204935891039071e-06,
2512
+ "loss": 0.19738194346427917,
2513
+ "step": 313,
2514
+ "token_acc": 0.9336264207591679
2515
+ },
2516
+ {
2517
+ "epoch": 0.7781908302354399,
2518
+ "grad_norm": 0.6156247677333414,
2519
+ "learning_rate": 7.186536602294278e-06,
2520
+ "loss": 0.19386141002178192,
2521
+ "step": 314,
2522
+ "token_acc": 0.9333576110706482
2523
+ },
2524
+ {
2525
+ "epoch": 0.7806691449814126,
2526
+ "grad_norm": 0.5913126460909635,
2527
+ "learning_rate": 7.168100630522769e-06,
2528
+ "loss": 0.17603059113025665,
2529
+ "step": 315,
2530
+ "token_acc": 0.9404875463698993
2531
+ },
2532
+ {
2533
+ "epoch": 0.7831474597273854,
2534
+ "grad_norm": 0.6156468190469662,
2535
+ "learning_rate": 7.149628285020647e-06,
2536
+ "loss": 0.17938795685768127,
2537
+ "step": 316,
2538
+ "token_acc": 0.9378924042841315
2539
+ },
2540
+ {
2541
+ "epoch": 0.7856257744733581,
2542
+ "grad_norm": 0.5554521957848949,
2543
+ "learning_rate": 7.131119875694246e-06,
2544
+ "loss": 0.17076990008354187,
2545
+ "step": 317,
2546
+ "token_acc": 0.9421808877079028
2547
+ },
2548
+ {
2549
+ "epoch": 0.7881040892193308,
2550
+ "grad_norm": 0.45494925279745124,
2551
+ "learning_rate": 7.112575713054937e-06,
2552
+ "loss": 0.16329985857009888,
2553
+ "step": 318,
2554
+ "token_acc": 0.946594907886566
2555
+ },
2556
+ {
2557
+ "epoch": 0.7905824039653035,
2558
+ "grad_norm": 0.5852901237954785,
2559
+ "learning_rate": 7.09399610821391e-06,
2560
+ "loss": 0.19399097561836243,
2561
+ "step": 319,
2562
+ "token_acc": 0.933989751833618
2563
+ },
2564
+ {
2565
+ "epoch": 0.7930607187112764,
2566
+ "grad_norm": 0.5144931542602342,
2567
+ "learning_rate": 7.075381372876969e-06,
2568
+ "loss": 0.1819971203804016,
2569
+ "step": 320,
2570
+ "token_acc": 0.9393325432929394
2571
+ },
2572
+ {
2573
+ "epoch": 0.7955390334572491,
2574
+ "grad_norm": 0.6053879815647109,
2575
+ "learning_rate": 7.056731819339287e-06,
2576
+ "loss": 0.19436374306678772,
2577
+ "step": 321,
2578
+ "token_acc": 0.9340544494957412
2579
+ },
2580
+ {
2581
+ "epoch": 0.7980173482032218,
2582
+ "grad_norm": 0.650218400875679,
2583
+ "learning_rate": 7.0380477604801786e-06,
2584
+ "loss": 0.19260971248149872,
2585
+ "step": 322,
2586
+ "token_acc": 0.9355844155844156
2587
+ },
2588
+ {
2589
+ "epoch": 0.8004956629491945,
2590
+ "grad_norm": 0.6927995413369397,
2591
+ "learning_rate": 7.019329509757845e-06,
2592
+ "loss": 0.2514747381210327,
2593
+ "step": 323,
2594
+ "token_acc": 0.916455562592358
2595
+ },
2596
+ {
2597
+ "epoch": 0.8029739776951673,
2598
+ "grad_norm": 0.6628203337351111,
2599
+ "learning_rate": 7.000577381204119e-06,
2600
+ "loss": 0.20861145853996277,
2601
+ "step": 324,
2602
+ "token_acc": 0.9286525246489393
2603
+ },
2604
+ {
2605
+ "epoch": 0.80545229244114,
2606
+ "grad_norm": 0.5446705759993885,
2607
+ "learning_rate": 6.981791689419187e-06,
2608
+ "loss": 0.19650927186012268,
2609
+ "step": 325,
2610
+ "token_acc": 0.9323333757044193
2611
+ },
2612
+ {
2613
+ "epoch": 0.8079306071871127,
2614
+ "grad_norm": 0.690888081296392,
2615
+ "learning_rate": 6.9629727495663265e-06,
2616
+ "loss": 0.21079204976558685,
2617
+ "step": 326,
2618
+ "token_acc": 0.9264723964096889
2619
+ },
2620
+ {
2621
+ "epoch": 0.8104089219330854,
2622
+ "grad_norm": 0.5441216259690024,
2623
+ "learning_rate": 6.944120877366605e-06,
2624
+ "loss": 0.18361029028892517,
2625
+ "step": 327,
2626
+ "token_acc": 0.9384538611885058
2627
+ },
2628
+ {
2629
+ "epoch": 0.8128872366790583,
2630
+ "grad_norm": 0.5996138029900019,
2631
+ "learning_rate": 6.925236389093588e-06,
2632
+ "loss": 0.18431442975997925,
2633
+ "step": 328,
2634
+ "token_acc": 0.9374512961712297
2635
+ },
2636
+ {
2637
+ "epoch": 0.815365551425031,
2638
+ "grad_norm": 0.7203332147407779,
2639
+ "learning_rate": 6.906319601568039e-06,
2640
+ "loss": 0.21725746989250183,
2641
+ "step": 329,
2642
+ "token_acc": 0.9251507626818021
2643
+ },
2644
+ {
2645
+ "epoch": 0.8178438661710037,
2646
+ "grad_norm": 0.7061408752241958,
2647
+ "learning_rate": 6.8873708321525925e-06,
2648
+ "loss": 0.20691266655921936,
2649
+ "step": 330,
2650
+ "token_acc": 0.9305555555555556
2651
+ },
2652
+ {
2653
+ "epoch": 0.8203221809169765,
2654
+ "grad_norm": 0.739638865187876,
2655
+ "learning_rate": 6.86839039874644e-06,
2656
+ "loss": 0.21497470140457153,
2657
+ "step": 331,
2658
+ "token_acc": 0.926947355518784
2659
+ },
2660
+ {
2661
+ "epoch": 0.8228004956629492,
2662
+ "grad_norm": 0.5550764847568598,
2663
+ "learning_rate": 6.849378619779989e-06,
2664
+ "loss": 0.16336879134178162,
2665
+ "step": 332,
2666
+ "token_acc": 0.9456177118598528
2667
+ },
2668
+ {
2669
+ "epoch": 0.8252788104089219,
2670
+ "grad_norm": 0.46018708417936377,
2671
+ "learning_rate": 6.830335814209527e-06,
2672
+ "loss": 0.16997572779655457,
2673
+ "step": 333,
2674
+ "token_acc": 0.9435462670872765
2675
+ },
2676
+ {
2677
+ "epoch": 0.8277571251548946,
2678
+ "grad_norm": 0.6130699582046176,
2679
+ "learning_rate": 6.8112623015118695e-06,
2680
+ "loss": 0.20551201701164246,
2681
+ "step": 334,
2682
+ "token_acc": 0.9305078475928764
2683
+ },
2684
+ {
2685
+ "epoch": 0.8302354399008675,
2686
+ "grad_norm": 0.5844044940247498,
2687
+ "learning_rate": 6.7921584016789945e-06,
2688
+ "loss": 0.1819285750389099,
2689
+ "step": 335,
2690
+ "token_acc": 0.9391255447771686
2691
+ },
2692
+ {
2693
+ "epoch": 0.8327137546468402,
2694
+ "grad_norm": 0.5448688189149371,
2695
+ "learning_rate": 6.773024435212678e-06,
2696
+ "loss": 0.18144120275974274,
2697
+ "step": 336,
2698
+ "token_acc": 0.937613822087322
2699
+ },
2700
+ {
2701
+ "epoch": 0.8351920693928129,
2702
+ "grad_norm": 0.4979114160815145,
2703
+ "learning_rate": 6.753860723119122e-06,
2704
+ "loss": 0.16096332669258118,
2705
+ "step": 337,
2706
+ "token_acc": 0.9465835840137516
2707
+ },
2708
+ {
2709
+ "epoch": 0.8376703841387856,
2710
+ "grad_norm": 0.5494514984772891,
2711
+ "learning_rate": 6.734667586903557e-06,
2712
+ "loss": 0.16589075326919556,
2713
+ "step": 338,
2714
+ "token_acc": 0.9436148550373316
2715
+ },
2716
+ {
2717
+ "epoch": 0.8401486988847584,
2718
+ "grad_norm": 0.5850765356427753,
2719
+ "learning_rate": 6.715445348564863e-06,
2720
+ "loss": 0.18757903575897217,
2721
+ "step": 339,
2722
+ "token_acc": 0.9360860860860861
2723
+ },
2724
+ {
2725
+ "epoch": 0.8426270136307311,
2726
+ "grad_norm": 0.5399633025058113,
2727
+ "learning_rate": 6.6961943305901515e-06,
2728
+ "loss": 0.20864208042621613,
2729
+ "step": 340,
2730
+ "token_acc": 0.9299855937435686
2731
+ },
2732
+ {
2733
+ "epoch": 0.8451053283767038,
2734
+ "grad_norm": 0.5140619654826223,
2735
+ "learning_rate": 6.676914855949372e-06,
2736
+ "loss": 0.17430901527404785,
2737
+ "step": 341,
2738
+ "token_acc": 0.9395597664066647
2739
+ },
2740
+ {
2741
+ "epoch": 0.8475836431226765,
2742
+ "grad_norm": 0.44397443886422366,
2743
+ "learning_rate": 6.657607248089879e-06,
2744
+ "loss": 0.14214351773262024,
2745
+ "step": 342,
2746
+ "token_acc": 0.9524850437183617
2747
+ },
2748
+ {
2749
+ "epoch": 0.8500619578686494,
2750
+ "grad_norm": 0.6456944870789697,
2751
+ "learning_rate": 6.638271830931011e-06,
2752
+ "loss": 0.206203892827034,
2753
+ "step": 343,
2754
+ "token_acc": 0.9305646749835851
2755
+ },
2756
+ {
2757
+ "epoch": 0.8525402726146221,
2758
+ "grad_norm": 0.6038908348082955,
2759
+ "learning_rate": 6.618908928858663e-06,
2760
+ "loss": 0.19610990583896637,
2761
+ "step": 344,
2762
+ "token_acc": 0.9328902658404957
2763
+ },
2764
+ {
2765
+ "epoch": 0.8550185873605948,
2766
+ "grad_norm": 0.5495386106507599,
2767
+ "learning_rate": 6.599518866719832e-06,
2768
+ "loss": 0.16991761326789856,
2769
+ "step": 345,
2770
+ "token_acc": 0.9420851314240879
2771
+ },
2772
+ {
2773
+ "epoch": 0.8574969021065675,
2774
+ "grad_norm": 0.549951806639056,
2775
+ "learning_rate": 6.580101969817176e-06,
2776
+ "loss": 0.1928429901599884,
2777
+ "step": 346,
2778
+ "token_acc": 0.9353661353661353
2779
+ },
2780
+ {
2781
+ "epoch": 0.8599752168525403,
2782
+ "grad_norm": 0.5512589876930394,
2783
+ "learning_rate": 6.560658563903552e-06,
2784
+ "loss": 0.18611253798007965,
2785
+ "step": 347,
2786
+ "token_acc": 0.9366203925323121
2787
+ },
2788
+ {
2789
+ "epoch": 0.862453531598513,
2790
+ "grad_norm": 0.5865468615625143,
2791
+ "learning_rate": 6.541188975176557e-06,
2792
+ "loss": 0.17572996020317078,
2793
+ "step": 348,
2794
+ "token_acc": 0.9399966290241025
2795
+ },
2796
+ {
2797
+ "epoch": 0.8649318463444857,
2798
+ "grad_norm": 0.5251637449426728,
2799
+ "learning_rate": 6.521693530273046e-06,
2800
+ "loss": 0.1767703741788864,
2801
+ "step": 349,
2802
+ "token_acc": 0.9404241615678336
2803
+ },
2804
+ {
2805
+ "epoch": 0.8674101610904585,
2806
+ "grad_norm": 0.6104543428217437,
2807
+ "learning_rate": 6.502172556263656e-06,
2808
+ "loss": 0.18647098541259766,
2809
+ "step": 350,
2810
+ "token_acc": 0.9353623022897276
2811
+ },
2812
+ {
2813
+ "epoch": 0.8698884758364313,
2814
+ "grad_norm": 0.6238223874669917,
2815
+ "learning_rate": 6.48262638064733e-06,
2816
+ "loss": 0.1781601756811142,
2817
+ "step": 351,
2818
+ "token_acc": 0.9411801012220713
2819
+ },
2820
+ {
2821
+ "epoch": 0.872366790582404,
2822
+ "grad_norm": 0.5861100917100243,
2823
+ "learning_rate": 6.4630553313457985e-06,
2824
+ "loss": 0.19208556413650513,
2825
+ "step": 352,
2826
+ "token_acc": 0.9337118523775727
2827
+ },
2828
+ {
2829
+ "epoch": 0.8748451053283767,
2830
+ "grad_norm": 0.6175525569005312,
2831
+ "learning_rate": 6.443459736698106e-06,
2832
+ "loss": 0.18548664450645447,
2833
+ "step": 353,
2834
+ "token_acc": 0.9386069519897531
2835
+ },
2836
+ {
2837
+ "epoch": 0.8773234200743495,
2838
+ "grad_norm": 0.6638086200585978,
2839
+ "learning_rate": 6.423839925455078e-06,
2840
+ "loss": 0.21412134170532227,
2841
+ "step": 354,
2842
+ "token_acc": 0.9282160257074739
2843
+ },
2844
+ {
2845
+ "epoch": 0.8798017348203222,
2846
+ "grad_norm": 0.5687655384821003,
2847
+ "learning_rate": 6.40419622677382e-06,
2848
+ "loss": 0.19178852438926697,
2849
+ "step": 355,
2850
+ "token_acc": 0.9339067451335445
2851
+ },
2852
+ {
2853
+ "epoch": 0.8822800495662949,
2854
+ "grad_norm": 0.6438700078860072,
2855
+ "learning_rate": 6.384528970212196e-06,
2856
+ "loss": 0.2100120335817337,
2857
+ "step": 356,
2858
+ "token_acc": 0.929322697017428
2859
+ },
2860
+ {
2861
+ "epoch": 0.8847583643122676,
2862
+ "grad_norm": 0.5187678943939543,
2863
+ "learning_rate": 6.364838485723286e-06,
2864
+ "loss": 0.1823013722896576,
2865
+ "step": 357,
2866
+ "token_acc": 0.9372864170641031
2867
+ },
2868
+ {
2869
+ "epoch": 0.8872366790582404,
2870
+ "grad_norm": 0.7008931403238787,
2871
+ "learning_rate": 6.34512510364987e-06,
2872
+ "loss": 0.21314826607704163,
2873
+ "step": 358,
2874
+ "token_acc": 0.9309123117803366
2875
+ },
2876
+ {
2877
+ "epoch": 0.8897149938042132,
2878
+ "grad_norm": 0.4684955452797199,
2879
+ "learning_rate": 6.325389154718865e-06,
2880
+ "loss": 0.15992307662963867,
2881
+ "step": 359,
2882
+ "token_acc": 0.9466835810076114
2883
+ },
2884
+ {
2885
+ "epoch": 0.8921933085501859,
2886
+ "grad_norm": 0.7093193254981369,
2887
+ "learning_rate": 6.305630970035796e-06,
2888
+ "loss": 0.19820962846279144,
2889
+ "step": 360,
2890
+ "token_acc": 0.9311410133186874
2891
+ },
2892
+ {
2893
+ "epoch": 0.8946716232961586,
2894
+ "grad_norm": 0.6971720322816753,
2895
+ "learning_rate": 6.285850881079229e-06,
2896
+ "loss": 0.2410978525876999,
2897
+ "step": 361,
2898
+ "token_acc": 0.9183133479705005
2899
+ },
2900
+ {
2901
+ "epoch": 0.8971499380421314,
2902
+ "grad_norm": 0.5798730665306432,
2903
+ "learning_rate": 6.266049219695211e-06,
2904
+ "loss": 0.20267970860004425,
2905
+ "step": 362,
2906
+ "token_acc": 0.9333963390370076
2907
+ },
2908
+ {
2909
+ "epoch": 0.8996282527881041,
2910
+ "grad_norm": 0.5888906774545503,
2911
+ "learning_rate": 6.246226318091708e-06,
2912
+ "loss": 0.18350443243980408,
2913
+ "step": 363,
2914
+ "token_acc": 0.9382874116562532
2915
+ },
2916
+ {
2917
+ "epoch": 0.9021065675340768,
2918
+ "grad_norm": 0.4438401374827572,
2919
+ "learning_rate": 6.2263825088330254e-06,
2920
+ "loss": 0.14044809341430664,
2921
+ "step": 364,
2922
+ "token_acc": 0.9516898801986948
2923
+ },
2924
+ {
2925
+ "epoch": 0.9045848822800495,
2926
+ "grad_norm": 0.4941874739282007,
2927
+ "learning_rate": 6.206518124834231e-06,
2928
+ "loss": 0.17817911505699158,
2929
+ "step": 365,
2930
+ "token_acc": 0.9410047166279853
2931
+ },
2932
+ {
2933
+ "epoch": 0.9070631970260223,
2934
+ "grad_norm": 0.5116786582745578,
2935
+ "learning_rate": 6.186633499355576e-06,
2936
+ "loss": 0.1637290120124817,
2937
+ "step": 366,
2938
+ "token_acc": 0.9440909967225757
2939
+ },
2940
+ {
2941
+ "epoch": 0.909541511771995,
2942
+ "grad_norm": 0.5397800157697495,
2943
+ "learning_rate": 6.16672896599689e-06,
2944
+ "loss": 0.18025127053260803,
2945
+ "step": 367,
2946
+ "token_acc": 0.938099173553719
2947
+ },
2948
+ {
2949
+ "epoch": 0.9120198265179678,
2950
+ "grad_norm": 0.5421454820647157,
2951
+ "learning_rate": 6.146804858692001e-06,
2952
+ "loss": 0.17670249938964844,
2953
+ "step": 368,
2954
+ "token_acc": 0.9375969903597461
2955
+ },
2956
+ {
2957
+ "epoch": 0.9144981412639405,
2958
+ "grad_norm": 0.5521936218217984,
2959
+ "learning_rate": 6.126861511703119e-06,
2960
+ "loss": 0.17623640596866608,
2961
+ "step": 369,
2962
+ "token_acc": 0.938034188034188
2963
+ },
2964
+ {
2965
+ "epoch": 0.9169764560099133,
2966
+ "grad_norm": 0.6290270262768498,
2967
+ "learning_rate": 6.1068992596152355e-06,
2968
+ "loss": 0.1962592899799347,
2969
+ "step": 370,
2970
+ "token_acc": 0.9332259318926727
2971
+ },
2972
+ {
2973
+ "epoch": 0.919454770755886,
2974
+ "grad_norm": 0.4671394853843183,
2975
+ "learning_rate": 6.086918437330508e-06,
2976
+ "loss": 0.16493193805217743,
2977
+ "step": 371,
2978
+ "token_acc": 0.945803564985206
2979
+ },
2980
+ {
2981
+ "epoch": 0.9219330855018587,
2982
+ "grad_norm": 0.546984468211384,
2983
+ "learning_rate": 6.066919380062644e-06,
2984
+ "loss": 0.182471364736557,
2985
+ "step": 372,
2986
+ "token_acc": 0.9386115073704232
2987
+ },
2988
+ {
2989
+ "epoch": 0.9244114002478315,
2990
+ "grad_norm": 0.48129971590341114,
2991
+ "learning_rate": 6.046902423331271e-06,
2992
+ "loss": 0.17034727334976196,
2993
+ "step": 373,
2994
+ "token_acc": 0.9405193236714976
2995
+ },
2996
+ {
2997
+ "epoch": 0.9268897149938042,
2998
+ "grad_norm": 0.5079807208127743,
2999
+ "learning_rate": 6.026867902956317e-06,
3000
+ "loss": 0.18423601984977722,
3001
+ "step": 374,
3002
+ "token_acc": 0.9381341063391563
3003
+ },
3004
+ {
3005
+ "epoch": 0.929368029739777,
3006
+ "grad_norm": 0.5550349877125086,
3007
+ "learning_rate": 6.006816155052366e-06,
3008
+ "loss": 0.181596040725708,
3009
+ "step": 375,
3010
+ "token_acc": 0.9398745850239764
3011
+ },
3012
+ {
3013
+ "epoch": 0.9318463444857497,
3014
+ "grad_norm": 0.7137457961830891,
3015
+ "learning_rate": 5.986747516023031e-06,
3016
+ "loss": 0.22559146583080292,
3017
+ "step": 376,
3018
+ "token_acc": 0.9251993713254555
3019
+ },
3020
+ {
3021
+ "epoch": 0.9343246592317225,
3022
+ "grad_norm": 0.6195725763578181,
3023
+ "learning_rate": 5.966662322555295e-06,
3024
+ "loss": 0.20806604623794556,
3025
+ "step": 377,
3026
+ "token_acc": 0.9297776881584917
3027
+ },
3028
+ {
3029
+ "epoch": 0.9368029739776952,
3030
+ "grad_norm": 0.6214235013705115,
3031
+ "learning_rate": 5.946560911613877e-06,
3032
+ "loss": 0.1806526482105255,
3033
+ "step": 378,
3034
+ "token_acc": 0.9402472146776786
3035
+ },
3036
+ {
3037
+ "epoch": 0.9392812887236679,
3038
+ "grad_norm": 0.619892424335576,
3039
+ "learning_rate": 5.926443620435572e-06,
3040
+ "loss": 0.21241208910942078,
3041
+ "step": 379,
3042
+ "token_acc": 0.9281962391007459
3043
+ },
3044
+ {
3045
+ "epoch": 0.9417596034696406,
3046
+ "grad_norm": 0.5610334539110594,
3047
+ "learning_rate": 5.906310786523594e-06,
3048
+ "loss": 0.18094947934150696,
3049
+ "step": 380,
3050
+ "token_acc": 0.9387107018100984
3051
+ },
3052
+ {
3053
+ "epoch": 0.9442379182156134,
3054
+ "grad_norm": 0.6291606104313001,
3055
+ "learning_rate": 5.886162747641912e-06,
3056
+ "loss": 0.18630896508693695,
3057
+ "step": 381,
3058
+ "token_acc": 0.9353342941287048
3059
+ },
3060
+ {
3061
+ "epoch": 0.9467162329615861,
3062
+ "grad_norm": 0.6029989366399096,
3063
+ "learning_rate": 5.8659998418095865e-06,
3064
+ "loss": 0.18783429265022278,
3065
+ "step": 382,
3066
+ "token_acc": 0.9373857404021938
3067
+ },
3068
+ {
3069
+ "epoch": 0.9491945477075588,
3070
+ "grad_norm": 0.46408751068285836,
3071
+ "learning_rate": 5.845822407295101e-06,
3072
+ "loss": 0.18516132235527039,
3073
+ "step": 383,
3074
+ "token_acc": 0.9385469573172656
3075
+ },
3076
+ {
3077
+ "epoch": 0.9516728624535316,
3078
+ "grad_norm": 0.612993930771964,
3079
+ "learning_rate": 5.825630782610676e-06,
3080
+ "loss": 0.20001889765262604,
3081
+ "step": 384,
3082
+ "token_acc": 0.9328035050180855
3083
+ },
3084
+ {
3085
+ "epoch": 0.9541511771995044,
3086
+ "grad_norm": 0.6864088018447264,
3087
+ "learning_rate": 5.805425306506602e-06,
3088
+ "loss": 0.2024618238210678,
3089
+ "step": 385,
3090
+ "token_acc": 0.9303036213510175
3091
+ },
3092
+ {
3093
+ "epoch": 0.9566294919454771,
3094
+ "grad_norm": 0.5939683411874609,
3095
+ "learning_rate": 5.785206317965554e-06,
3096
+ "loss": 0.18140359222888947,
3097
+ "step": 386,
3098
+ "token_acc": 0.9374970716394134
3099
+ },
3100
+ {
3101
+ "epoch": 0.9591078066914498,
3102
+ "grad_norm": 0.6088125393963071,
3103
+ "learning_rate": 5.764974156196895e-06,
3104
+ "loss": 0.2035776674747467,
3105
+ "step": 387,
3106
+ "token_acc": 0.9312286240463036
3107
+ },
3108
+ {
3109
+ "epoch": 0.9615861214374225,
3110
+ "grad_norm": 0.7336766511647727,
3111
+ "learning_rate": 5.744729160630998e-06,
3112
+ "loss": 0.22366486489772797,
3113
+ "step": 388,
3114
+ "token_acc": 0.9254956067097524
3115
+ },
3116
+ {
3117
+ "epoch": 0.9640644361833953,
3118
+ "grad_norm": 0.6358696615588187,
3119
+ "learning_rate": 5.724471670913545e-06,
3120
+ "loss": 0.20231348276138306,
3121
+ "step": 389,
3122
+ "token_acc": 0.932510562597287
3123
+ },
3124
+ {
3125
+ "epoch": 0.966542750929368,
3126
+ "grad_norm": 0.6559875937069032,
3127
+ "learning_rate": 5.704202026899827e-06,
3128
+ "loss": 0.20032212138175964,
3129
+ "step": 390,
3130
+ "token_acc": 0.9320229815542788
3131
+ },
3132
+ {
3133
+ "epoch": 0.9690210656753407,
3134
+ "grad_norm": 0.5553921325890104,
3135
+ "learning_rate": 5.6839205686490474e-06,
3136
+ "loss": 0.20753684639930725,
3137
+ "step": 391,
3138
+ "token_acc": 0.9317560234425873
3139
+ },
3140
+ {
3141
+ "epoch": 0.9714993804213135,
3142
+ "grad_norm": 0.5790773834042127,
3143
+ "learning_rate": 5.663627636418611e-06,
3144
+ "loss": 0.19933849573135376,
3145
+ "step": 392,
3146
+ "token_acc": 0.9320876585928489
3147
+ },
3148
+ {
3149
+ "epoch": 0.9739776951672863,
3150
+ "grad_norm": 0.6048116933959292,
3151
+ "learning_rate": 5.6433235706584245e-06,
3152
+ "loss": 0.17828413844108582,
3153
+ "step": 393,
3154
+ "token_acc": 0.9381983240223464
3155
+ },
3156
+ {
3157
+ "epoch": 0.976456009913259,
3158
+ "grad_norm": 0.7249058399669792,
3159
+ "learning_rate": 5.6230087120051724e-06,
3160
+ "loss": 0.1717335432767868,
3161
+ "step": 394,
3162
+ "token_acc": 0.9421272747824121
3163
+ },
3164
+ {
3165
+ "epoch": 0.9789343246592317,
3166
+ "grad_norm": 0.5770177783064109,
3167
+ "learning_rate": 5.6026834012766155e-06,
3168
+ "loss": 0.19472819566726685,
3169
+ "step": 395,
3170
+ "token_acc": 0.9339223265230996
3171
+ },
3172
+ {
3173
+ "epoch": 0.9814126394052045,
3174
+ "grad_norm": 0.4889275587412367,
3175
+ "learning_rate": 5.582347979465864e-06,
3176
+ "loss": 0.15470196306705475,
3177
+ "step": 396,
3178
+ "token_acc": 0.9471021567409248
3179
+ },
3180
+ {
3181
+ "epoch": 0.9838909541511772,
3182
+ "grad_norm": 0.5349732049962183,
3183
+ "learning_rate": 5.562002787735658e-06,
3184
+ "loss": 0.188591867685318,
3185
+ "step": 397,
3186
+ "token_acc": 0.9351314148062115
3187
+ },
3188
+ {
3189
+ "epoch": 0.9863692688971499,
3190
+ "grad_norm": 0.5409005167566334,
3191
+ "learning_rate": 5.541648167412648e-06,
3192
+ "loss": 0.1926460862159729,
3193
+ "step": 398,
3194
+ "token_acc": 0.9344948330344179
3195
+ },
3196
+ {
3197
+ "epoch": 0.9888475836431226,
3198
+ "grad_norm": 0.4941504014606478,
3199
+ "learning_rate": 5.521284459981662e-06,
3200
+ "loss": 0.1656017005443573,
3201
+ "step": 399,
3202
+ "token_acc": 0.9449271039188635
3203
+ },
3204
+ {
3205
+ "epoch": 0.9913258983890955,
3206
+ "grad_norm": 0.54064933012267,
3207
+ "learning_rate": 5.500912007079987e-06,
3208
+ "loss": 0.175786554813385,
3209
+ "step": 400,
3210
+ "token_acc": 0.9386102162908422
3211
+ }
3212
+ ],
3213
+ "logging_steps": 1,
3214
+ "max_steps": 808,
3215
+ "num_input_tokens_seen": 0,
3216
+ "num_train_epochs": 2,
3217
+ "save_steps": 400,
3218
+ "stateful_callbacks": {
3219
+ "TrainerControl": {
3220
+ "args": {
3221
+ "should_epoch_stop": false,
3222
+ "should_evaluate": false,
3223
+ "should_log": false,
3224
+ "should_save": true,
3225
+ "should_training_stop": false
3226
+ },
3227
+ "attributes": {}
3228
+ }
3229
+ },
3230
+ "total_flos": 89241210011648.0,
3231
+ "train_batch_size": 1,
3232
+ "trial_name": null,
3233
+ "trial_params": null
3234
+ }
v0-20260118-111123/checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2af38b97928d7a6d29bc705d94e6ceb3f08920a2f404a386aaac89911b7f0f9
3
+ size 9489
v0-20260118-111123/checkpoint-400/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
v0-20260118-111123/checkpoint-800/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
v0-20260118-111123/checkpoint-800/args.json ADDED
@@ -0,0 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 1,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.05,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 2.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 400.0,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": true,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": "nccl",
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": 400.0,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": false,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch_fused",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "none"
132
+ ],
133
+ "project": "huggingface",
134
+ "trackio_space_id": "trackio",
135
+ "ddp_find_unused_parameters": null,
136
+ "ddp_bucket_cap_mb": null,
137
+ "ddp_broadcast_buffers": null,
138
+ "dataloader_pin_memory": true,
139
+ "dataloader_persistent_workers": false,
140
+ "skip_memory_metrics": true,
141
+ "use_legacy_prediction_loop": false,
142
+ "push_to_hub": false,
143
+ "resume_from_checkpoint": null,
144
+ "hub_model_id": null,
145
+ "hub_strategy": "every_save",
146
+ "hub_token": null,
147
+ "hub_private_repo": null,
148
+ "hub_always_push": false,
149
+ "hub_revision": null,
150
+ "gradient_checkpointing": true,
151
+ "gradient_checkpointing_kwargs": null,
152
+ "include_inputs_for_metrics": false,
153
+ "include_for_metrics": [],
154
+ "eval_do_concat_batches": true,
155
+ "fp16_backend": "auto",
156
+ "push_to_hub_model_id": null,
157
+ "push_to_hub_organization": null,
158
+ "push_to_hub_token": null,
159
+ "mp_parameters": "",
160
+ "auto_find_batch_size": false,
161
+ "full_determinism": false,
162
+ "torchdynamo": null,
163
+ "ray_scope": "last",
164
+ "ddp_timeout": 18000000,
165
+ "torch_compile": false,
166
+ "torch_compile_backend": null,
167
+ "torch_compile_mode": null,
168
+ "include_tokens_per_second": false,
169
+ "include_num_input_tokens_seen": false,
170
+ "neftune_noise_alpha": null,
171
+ "optim_target_modules": null,
172
+ "batch_eval_metrics": false,
173
+ "eval_on_start": false,
174
+ "use_liger_kernel": false,
175
+ "liger_kernel_config": null,
176
+ "eval_use_gather_object": false,
177
+ "average_tokens_across_devices": true,
178
+ "sortish_sampler": false,
179
+ "predict_with_generate": false,
180
+ "generation_max_length": null,
181
+ "generation_num_beams": null,
182
+ "generation_config": null,
183
+ "tuner_backend": "peft",
184
+ "vit_gradient_checkpointing": null,
185
+ "router_aux_loss_coef": 0.0,
186
+ "enable_dft_loss": false,
187
+ "enable_channel_loss": false,
188
+ "check_model": true,
189
+ "acc_strategy": "token",
190
+ "train_dataloader_shuffle": true,
191
+ "max_epochs": null,
192
+ "aligner_lr": null,
193
+ "vit_lr": null,
194
+ "use_logits_to_keep": null,
195
+ "ds3_gather_for_generation": true,
196
+ "resume_only_model": false,
197
+ "optimizer": null,
198
+ "loss_type": null,
199
+ "metric": null,
200
+ "eval_use_evalscope": false,
201
+ "eval_dataset": [],
202
+ "eval_dataset_args": null,
203
+ "eval_limit": null,
204
+ "eval_generation_config": null,
205
+ "extra_eval_args": null,
206
+ "use_flash_ckpt": false,
207
+ "use_ray": false,
208
+ "ray_exp_name": null,
209
+ "device_groups": null,
210
+ "model": "ubowang/fim_qwen25_coder_7b_ins_0116-ckpt_4500",
211
+ "model_type": "qwen2_5",
212
+ "model_revision": null,
213
+ "task_type": "causal_lm",
214
+ "torch_dtype": "bfloat16",
215
+ "attn_impl": "flash_attn",
216
+ "new_special_tokens": [],
217
+ "num_labels": null,
218
+ "problem_type": null,
219
+ "rope_scaling": null,
220
+ "device_map": null,
221
+ "max_memory": {},
222
+ "max_model_len": null,
223
+ "local_repo_path": null,
224
+ "init_strategy": null,
225
+ "template": "qwen2_5",
226
+ "system": null,
227
+ "max_length": 32768,
228
+ "truncation_strategy": "delete",
229
+ "max_pixels": null,
230
+ "agent_template": null,
231
+ "norm_bbox": null,
232
+ "use_chat_template": true,
233
+ "padding_side": "right",
234
+ "padding_free": false,
235
+ "loss_scale": "default",
236
+ "sequence_parallel_size": 1,
237
+ "template_backend": "swift",
238
+ "response_prefix": null,
239
+ "enable_thinking": null,
240
+ "add_non_thinking_prefix": true,
241
+ "dataset": [
242
+ "/data2/yubo/datasets/R2EGym-Data/R2EGym-SFT-Trajectories.jsonl"
243
+ ],
244
+ "val_dataset": [],
245
+ "cached_dataset": [],
246
+ "cached_val_dataset": [],
247
+ "split_dataset_ratio": 0.0,
248
+ "dataset_num_proc": 8,
249
+ "load_from_cache_file": false,
250
+ "dataset_shuffle": true,
251
+ "val_dataset_shuffle": false,
252
+ "streaming": false,
253
+ "interleave_prob": null,
254
+ "stopping_strategy": "first_exhausted",
255
+ "shuffle_buffer_size": 1000,
256
+ "download_mode": "reuse_dataset_if_exists",
257
+ "columns": {},
258
+ "strict": false,
259
+ "model_name": null,
260
+ "model_author": null,
261
+ "custom_dataset_info": [],
262
+ "quant_method": null,
263
+ "quant_bits": null,
264
+ "hqq_axis": null,
265
+ "bnb_4bit_compute_dtype": "bfloat16",
266
+ "bnb_4bit_quant_type": "nf4",
267
+ "bnb_4bit_use_double_quant": true,
268
+ "bnb_4bit_quant_storage": null,
269
+ "max_new_tokens": 64,
270
+ "temperature": 0.0,
271
+ "top_k": null,
272
+ "top_p": null,
273
+ "repetition_penalty": null,
274
+ "num_beams": 1,
275
+ "stream": false,
276
+ "stop_words": [],
277
+ "logprobs": false,
278
+ "top_logprobs": null,
279
+ "structured_outputs_regex": null,
280
+ "ckpt_dir": null,
281
+ "lora_modules": [],
282
+ "train_type": "full",
283
+ "adapters": [],
284
+ "external_plugins": [],
285
+ "model_kwargs": {},
286
+ "load_args": false,
287
+ "load_data_args": false,
288
+ "packing": false,
289
+ "packing_length": null,
290
+ "packing_num_proc": 1,
291
+ "lazy_tokenize": false,
292
+ "custom_register_path": [],
293
+ "use_hf": true,
294
+ "ignore_args_error": false,
295
+ "use_swift_lora": false,
296
+ "freeze_parameters": [],
297
+ "freeze_parameters_regex": null,
298
+ "freeze_parameters_ratio": 0.0,
299
+ "trainable_parameters": [],
300
+ "trainable_parameters_regex": null,
301
+ "freeze_llm": false,
302
+ "freeze_vit": false,
303
+ "freeze_aligner": false,
304
+ "target_modules": [
305
+ "all-linear"
306
+ ],
307
+ "target_regex": null,
308
+ "target_parameters": null,
309
+ "modules_to_save": [],
310
+ "lora_rank": 8,
311
+ "lora_alpha": 32,
312
+ "lora_dropout": 0.05,
313
+ "lora_bias": "none",
314
+ "lora_dtype": null,
315
+ "lorap_lr_ratio": null,
316
+ "use_rslora": false,
317
+ "use_dora": false,
318
+ "lora_ga_batch_size": 2,
319
+ "lora_ga_iters": 2,
320
+ "lora_ga_max_length": 1024,
321
+ "lora_ga_direction": "ArB2r",
322
+ "lora_ga_scale": "stable",
323
+ "lora_ga_stable_gamma": 16,
324
+ "init_weights": true,
325
+ "fourier_n_frequency": 2000,
326
+ "fourier_scaling": 300.0,
327
+ "boft_block_size": 4,
328
+ "boft_block_num": 0,
329
+ "boft_n_butterfly_factor": 1,
330
+ "boft_dropout": 0.0,
331
+ "vera_rank": 256,
332
+ "vera_projection_prng_key": 0,
333
+ "vera_dropout": 0.0,
334
+ "vera_d_initial": 0.1,
335
+ "adapter_act": "gelu",
336
+ "adapter_length": 128,
337
+ "use_galore": false,
338
+ "galore_target_modules": null,
339
+ "galore_rank": 128,
340
+ "galore_update_proj_gap": 50,
341
+ "galore_scale": 1.0,
342
+ "galore_proj_type": "std",
343
+ "galore_optim_per_parameter": false,
344
+ "galore_with_embedding": false,
345
+ "galore_quantization": false,
346
+ "galore_proj_quant": false,
347
+ "galore_proj_bits": 4,
348
+ "galore_proj_group_size": 256,
349
+ "galore_cos_threshold": 0.4,
350
+ "galore_gamma_proj": 2,
351
+ "galore_queue_size": 5,
352
+ "adalora_target_r": 8,
353
+ "adalora_init_r": 12,
354
+ "adalora_tinit": 0,
355
+ "adalora_tfinal": 0,
356
+ "adalora_deltaT": 1,
357
+ "adalora_beta1": 0.85,
358
+ "adalora_beta2": 0.85,
359
+ "adalora_orth_reg_weight": 0.5,
360
+ "llamapro_num_new_blocks": 4,
361
+ "llamapro_num_groups": null,
362
+ "lisa_activated_layers": 0,
363
+ "lisa_step_interval": 20,
364
+ "reft_layer_key": null,
365
+ "reft_layers": null,
366
+ "reft_rank": 4,
367
+ "reft_intervention_type": "LoreftIntervention",
368
+ "reft_args": null,
369
+ "swanlab_token": null,
370
+ "swanlab_project": "ms-swift",
371
+ "swanlab_workspace": null,
372
+ "swanlab_exp_name": null,
373
+ "swanlab_notification_method": null,
374
+ "swanlab_webhook_url": null,
375
+ "swanlab_secret": null,
376
+ "swanlab_mode": "cloud",
377
+ "add_version": true,
378
+ "create_checkpoint_symlink": false,
379
+ "zero_hpz_partition_size": null,
380
+ "deepspeed_autotp_size": null,
381
+ "early_stop_interval": null,
382
+ "rank": 0,
383
+ "global_world_size": 4,
384
+ "local_world_size": 4,
385
+ "model_suffix": "fim_qwen25_coder_7b_ins_0116-ckpt_4500",
386
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/home/user/.cache/huggingface/hub/models--ubowang--fim_qwen25_coder_7b_ins_0116-ckpt_4500/snapshots/415fd793976200fcfc97bc543ccab8e73dd4843e', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
387
+ "model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='moonshotai/Kimi-Dev-72B', hf_model_id='moonshotai/Kimi-Dev-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x7ff22745e5c0>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
388
+ "model_dir": "/home/user/.cache/huggingface/hub/models--ubowang--fim_qwen25_coder_7b_ins_0116-ckpt_4500/snapshots/415fd793976200fcfc97bc543ccab8e73dd4843e",
389
+ "_val_dataset_exists": [],
390
+ "hub": "<class 'swift.hub.hub.HFHub'>",
391
+ "evaluation_strategy": "steps",
392
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.05, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=400, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=400.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=[], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
393
+ }
v0-20260118-111123/checkpoint-800/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
v0-20260118-111123/checkpoint-800/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "pad_token_id": 151643,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
51
+ "rope_theta": 1000000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": false,
54
+ "transformers_version": "4.57.6",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
v0-20260118-111123/checkpoint-800/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.57.6"
14
+ }
v0-20260118-111123/checkpoint-800/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
v0-20260118-111123/checkpoint-800/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f778776f91021c3b80798b752ac2f171042583c13f53a310edf07c877412b8a
3
+ size 4877660776
v0-20260118-111123/checkpoint-800/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1fd552ffd1abad13997884df3dc2d6931fbbea2127daa37c129fbf3571bd861
3
+ size 4932751008
v0-20260118-111123/checkpoint-800/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a610d0bb99267661f1a980bcd8fbf395aa010a479178b33a4a991c8d76db58d1
3
+ size 4330865200
v0-20260118-111123/checkpoint-800/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf2c8a572300b1fab8f3777b96a7339e12bdca09d3a46128a52bedda24188f77
3
+ size 1089994880
v0-20260118-111123/checkpoint-800/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 333312,
4
+ "total_size": 15231233024
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.norm.weight": "model-00003-of-00004.safetensors"
346
+ }
347
+ }
v0-20260118-111123/checkpoint-800/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
v0-20260118-111123/checkpoint-800/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
v0-20260118-111123/checkpoint-800/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 32768,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
v0-20260118-111123/checkpoint-800/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
v0-20260118-111123/checkpoint-800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2af38b97928d7a6d29bc705d94e6ceb3f08920a2f404a386aaac89911b7f0f9
3
+ size 9489
v0-20260118-111123/checkpoint-800/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
v0-20260118-111123/checkpoint-808/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
v0-20260118-111123/checkpoint-808/args.json ADDED
@@ -0,0 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 1,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 2,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.05,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 2.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 400.0,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": true,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": "nccl",
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": 400.0,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": false,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch_fused",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "none"
132
+ ],
133
+ "project": "huggingface",
134
+ "trackio_space_id": "trackio",
135
+ "ddp_find_unused_parameters": null,
136
+ "ddp_bucket_cap_mb": null,
137
+ "ddp_broadcast_buffers": null,
138
+ "dataloader_pin_memory": true,
139
+ "dataloader_persistent_workers": false,
140
+ "skip_memory_metrics": true,
141
+ "use_legacy_prediction_loop": false,
142
+ "push_to_hub": false,
143
+ "resume_from_checkpoint": null,
144
+ "hub_model_id": null,
145
+ "hub_strategy": "every_save",
146
+ "hub_token": null,
147
+ "hub_private_repo": null,
148
+ "hub_always_push": false,
149
+ "hub_revision": null,
150
+ "gradient_checkpointing": true,
151
+ "gradient_checkpointing_kwargs": null,
152
+ "include_inputs_for_metrics": false,
153
+ "include_for_metrics": [],
154
+ "eval_do_concat_batches": true,
155
+ "fp16_backend": "auto",
156
+ "push_to_hub_model_id": null,
157
+ "push_to_hub_organization": null,
158
+ "push_to_hub_token": null,
159
+ "mp_parameters": "",
160
+ "auto_find_batch_size": false,
161
+ "full_determinism": false,
162
+ "torchdynamo": null,
163
+ "ray_scope": "last",
164
+ "ddp_timeout": 18000000,
165
+ "torch_compile": false,
166
+ "torch_compile_backend": null,
167
+ "torch_compile_mode": null,
168
+ "include_tokens_per_second": false,
169
+ "include_num_input_tokens_seen": false,
170
+ "neftune_noise_alpha": null,
171
+ "optim_target_modules": null,
172
+ "batch_eval_metrics": false,
173
+ "eval_on_start": false,
174
+ "use_liger_kernel": false,
175
+ "liger_kernel_config": null,
176
+ "eval_use_gather_object": false,
177
+ "average_tokens_across_devices": true,
178
+ "sortish_sampler": false,
179
+ "predict_with_generate": false,
180
+ "generation_max_length": null,
181
+ "generation_num_beams": null,
182
+ "generation_config": null,
183
+ "tuner_backend": "peft",
184
+ "vit_gradient_checkpointing": null,
185
+ "router_aux_loss_coef": 0.0,
186
+ "enable_dft_loss": false,
187
+ "enable_channel_loss": false,
188
+ "check_model": true,
189
+ "acc_strategy": "token",
190
+ "train_dataloader_shuffle": true,
191
+ "max_epochs": null,
192
+ "aligner_lr": null,
193
+ "vit_lr": null,
194
+ "use_logits_to_keep": null,
195
+ "ds3_gather_for_generation": true,
196
+ "resume_only_model": false,
197
+ "optimizer": null,
198
+ "loss_type": null,
199
+ "metric": null,
200
+ "eval_use_evalscope": false,
201
+ "eval_dataset": [],
202
+ "eval_dataset_args": null,
203
+ "eval_limit": null,
204
+ "eval_generation_config": null,
205
+ "extra_eval_args": null,
206
+ "use_flash_ckpt": false,
207
+ "use_ray": false,
208
+ "ray_exp_name": null,
209
+ "device_groups": null,
210
+ "model": "ubowang/fim_qwen25_coder_7b_ins_0116-ckpt_4500",
211
+ "model_type": "qwen2_5",
212
+ "model_revision": null,
213
+ "task_type": "causal_lm",
214
+ "torch_dtype": "bfloat16",
215
+ "attn_impl": "flash_attn",
216
+ "new_special_tokens": [],
217
+ "num_labels": null,
218
+ "problem_type": null,
219
+ "rope_scaling": null,
220
+ "device_map": null,
221
+ "max_memory": {},
222
+ "max_model_len": null,
223
+ "local_repo_path": null,
224
+ "init_strategy": null,
225
+ "template": "qwen2_5",
226
+ "system": null,
227
+ "max_length": 32768,
228
+ "truncation_strategy": "delete",
229
+ "max_pixels": null,
230
+ "agent_template": null,
231
+ "norm_bbox": null,
232
+ "use_chat_template": true,
233
+ "padding_side": "right",
234
+ "padding_free": false,
235
+ "loss_scale": "default",
236
+ "sequence_parallel_size": 1,
237
+ "template_backend": "swift",
238
+ "response_prefix": null,
239
+ "enable_thinking": null,
240
+ "add_non_thinking_prefix": true,
241
+ "dataset": [
242
+ "/data2/yubo/datasets/R2EGym-Data/R2EGym-SFT-Trajectories.jsonl"
243
+ ],
244
+ "val_dataset": [],
245
+ "cached_dataset": [],
246
+ "cached_val_dataset": [],
247
+ "split_dataset_ratio": 0.0,
248
+ "dataset_num_proc": 8,
249
+ "load_from_cache_file": false,
250
+ "dataset_shuffle": true,
251
+ "val_dataset_shuffle": false,
252
+ "streaming": false,
253
+ "interleave_prob": null,
254
+ "stopping_strategy": "first_exhausted",
255
+ "shuffle_buffer_size": 1000,
256
+ "download_mode": "reuse_dataset_if_exists",
257
+ "columns": {},
258
+ "strict": false,
259
+ "model_name": null,
260
+ "model_author": null,
261
+ "custom_dataset_info": [],
262
+ "quant_method": null,
263
+ "quant_bits": null,
264
+ "hqq_axis": null,
265
+ "bnb_4bit_compute_dtype": "bfloat16",
266
+ "bnb_4bit_quant_type": "nf4",
267
+ "bnb_4bit_use_double_quant": true,
268
+ "bnb_4bit_quant_storage": null,
269
+ "max_new_tokens": 64,
270
+ "temperature": 0.0,
271
+ "top_k": null,
272
+ "top_p": null,
273
+ "repetition_penalty": null,
274
+ "num_beams": 1,
275
+ "stream": false,
276
+ "stop_words": [],
277
+ "logprobs": false,
278
+ "top_logprobs": null,
279
+ "structured_outputs_regex": null,
280
+ "ckpt_dir": null,
281
+ "lora_modules": [],
282
+ "train_type": "full",
283
+ "adapters": [],
284
+ "external_plugins": [],
285
+ "model_kwargs": {},
286
+ "load_args": false,
287
+ "load_data_args": false,
288
+ "packing": false,
289
+ "packing_length": null,
290
+ "packing_num_proc": 1,
291
+ "lazy_tokenize": false,
292
+ "custom_register_path": [],
293
+ "use_hf": true,
294
+ "ignore_args_error": false,
295
+ "use_swift_lora": false,
296
+ "freeze_parameters": [],
297
+ "freeze_parameters_regex": null,
298
+ "freeze_parameters_ratio": 0.0,
299
+ "trainable_parameters": [],
300
+ "trainable_parameters_regex": null,
301
+ "freeze_llm": false,
302
+ "freeze_vit": false,
303
+ "freeze_aligner": false,
304
+ "target_modules": [
305
+ "all-linear"
306
+ ],
307
+ "target_regex": null,
308
+ "target_parameters": null,
309
+ "modules_to_save": [],
310
+ "lora_rank": 8,
311
+ "lora_alpha": 32,
312
+ "lora_dropout": 0.05,
313
+ "lora_bias": "none",
314
+ "lora_dtype": null,
315
+ "lorap_lr_ratio": null,
316
+ "use_rslora": false,
317
+ "use_dora": false,
318
+ "lora_ga_batch_size": 2,
319
+ "lora_ga_iters": 2,
320
+ "lora_ga_max_length": 1024,
321
+ "lora_ga_direction": "ArB2r",
322
+ "lora_ga_scale": "stable",
323
+ "lora_ga_stable_gamma": 16,
324
+ "init_weights": true,
325
+ "fourier_n_frequency": 2000,
326
+ "fourier_scaling": 300.0,
327
+ "boft_block_size": 4,
328
+ "boft_block_num": 0,
329
+ "boft_n_butterfly_factor": 1,
330
+ "boft_dropout": 0.0,
331
+ "vera_rank": 256,
332
+ "vera_projection_prng_key": 0,
333
+ "vera_dropout": 0.0,
334
+ "vera_d_initial": 0.1,
335
+ "adapter_act": "gelu",
336
+ "adapter_length": 128,
337
+ "use_galore": false,
338
+ "galore_target_modules": null,
339
+ "galore_rank": 128,
340
+ "galore_update_proj_gap": 50,
341
+ "galore_scale": 1.0,
342
+ "galore_proj_type": "std",
343
+ "galore_optim_per_parameter": false,
344
+ "galore_with_embedding": false,
345
+ "galore_quantization": false,
346
+ "galore_proj_quant": false,
347
+ "galore_proj_bits": 4,
348
+ "galore_proj_group_size": 256,
349
+ "galore_cos_threshold": 0.4,
350
+ "galore_gamma_proj": 2,
351
+ "galore_queue_size": 5,
352
+ "adalora_target_r": 8,
353
+ "adalora_init_r": 12,
354
+ "adalora_tinit": 0,
355
+ "adalora_tfinal": 0,
356
+ "adalora_deltaT": 1,
357
+ "adalora_beta1": 0.85,
358
+ "adalora_beta2": 0.85,
359
+ "adalora_orth_reg_weight": 0.5,
360
+ "llamapro_num_new_blocks": 4,
361
+ "llamapro_num_groups": null,
362
+ "lisa_activated_layers": 0,
363
+ "lisa_step_interval": 20,
364
+ "reft_layer_key": null,
365
+ "reft_layers": null,
366
+ "reft_rank": 4,
367
+ "reft_intervention_type": "LoreftIntervention",
368
+ "reft_args": null,
369
+ "swanlab_token": null,
370
+ "swanlab_project": "ms-swift",
371
+ "swanlab_workspace": null,
372
+ "swanlab_exp_name": null,
373
+ "swanlab_notification_method": null,
374
+ "swanlab_webhook_url": null,
375
+ "swanlab_secret": null,
376
+ "swanlab_mode": "cloud",
377
+ "add_version": true,
378
+ "create_checkpoint_symlink": false,
379
+ "zero_hpz_partition_size": null,
380
+ "deepspeed_autotp_size": null,
381
+ "early_stop_interval": null,
382
+ "rank": 0,
383
+ "global_world_size": 4,
384
+ "local_world_size": 4,
385
+ "model_suffix": "fim_qwen25_coder_7b_ins_0116-ckpt_4500",
386
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/home/user/.cache/huggingface/hub/models--ubowang--fim_qwen25_coder_7b_ins_0116-ckpt_4500/snapshots/415fd793976200fcfc97bc543ccab8e73dd4843e', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
387
+ "model_meta": "ModelMeta(model_type='qwen2_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct', hf_model_id='Qwen/Qwen2.5-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct', hf_model_id='Qwen/Qwen2.5-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct', hf_model_id='Qwen/Qwen2.5-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct', hf_model_id='Qwen/Qwen2.5-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct', hf_model_id='Qwen/Qwen2.5-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B', hf_model_id='Qwen/Qwen2.5-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B', hf_model_id='Qwen/Qwen2.5-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B', hf_model_id='Qwen/Qwen2.5-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B', hf_model_id='Qwen/Qwen2.5-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B', hf_model_id='Qwen/Qwen2.5-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B', hf_model_id='Qwen/Qwen2.5-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B', hf_model_id='Qwen/Qwen2.5-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B', hf_model_id='Qwen/Qwen2.5-Coder-0.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B', hf_model_id='Qwen/Qwen2.5-Coder-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B', hf_model_id='Qwen/Qwen2.5-Coder-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B', hf_model_id='Qwen/Qwen2.5-Coder-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B', hf_model_id='Qwen/Qwen2.5-Coder-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B', hf_model_id='Qwen/Qwen2.5-Coder-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=['coding']), ModelGroup(models=[Model(ms_model_id='moonshotai/Kimi-Dev-72B', hf_model_id='moonshotai/Kimi-Dev-72B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5', get_function=<function get_model_tokenizer_with_flash_attn at 0x7ff22745e5c0>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen2ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
388
+ "model_dir": "/home/user/.cache/huggingface/hub/models--ubowang--fim_qwen25_coder_7b_ins_0116-ckpt_4500/snapshots/415fd793976200fcfc97bc543ccab8e73dd4843e",
389
+ "_val_dataset_exists": [],
390
+ "hub": "<class 'swift.hub.hub.HFHub'>",
391
+ "evaluation_strategy": "steps",
392
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.05, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=400, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=400.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/data2/yubo/sft_ckpts/fim_qwen25_coder_7b_ins_0116-ckpt_4500_r2egym_sft_0117/v0-20260118-111123', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=[], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
393
+ }
v0-20260118-111123/checkpoint-808/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
v0-20260118-111123/checkpoint-808/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "pad_token_id": 151643,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
51
+ "rope_theta": 1000000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": false,
54
+ "transformers_version": "4.57.6",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }
v0-20260118-111123/checkpoint-808/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.57.6"
14
+ }
v0-20260118-111123/checkpoint-808/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
v0-20260118-111123/checkpoint-808/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b123ece7d796b44b8c2de98b465892c172a365eb8530c0ff85d54c9838bd1e
3
+ size 4877660776
v0-20260118-111123/checkpoint-808/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797fd5b83e9e9522ba733e5d195b97514a8183f38baa28b826cb2f89b2942352
3
+ size 4932751008
v0-20260118-111123/checkpoint-808/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dc0024173c4711aca6d0757d736b85d289758a8fac18cb0007308eb90ffbe9e
3
+ size 4330865200
v0-20260118-111123/checkpoint-808/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f40d5f7108fd1147f9b1d171a9d520f139b130bc4126bc6e21d73c92e71671
3
+ size 1089994880
v0-20260118-111123/checkpoint-808/model.safetensors.index.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 333312,
4
+ "total_size": 15231233024
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.norm.weight": "model-00003-of-00004.safetensors"
346
+ }
347
+ }
v0-20260118-111123/checkpoint-808/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
v0-20260118-111123/checkpoint-808/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
v0-20260118-111123/checkpoint-808/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 32768,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }