hongzhuyi commited on
Commit
93b1df0
·
verified ·
1 Parent(s): f914235

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 +2 -0
  2. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/args.json +384 -0
  3. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/added_tokens.json +24 -0
  4. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/args.json +384 -0
  5. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/chat_template.jinja +54 -0
  6. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/config.json +59 -0
  7. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/generation_config.json +14 -0
  8. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/latest +1 -0
  9. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/merges.txt +0 -0
  10. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/model-00001-of-00004.safetensors +3 -0
  11. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/model-00002-of-00004.safetensors +3 -0
  12. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/model-00003-of-00004.safetensors +3 -0
  13. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/model-00004-of-00004.safetensors +3 -0
  14. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/model.safetensors.index.json +347 -0
  15. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_0.pth +3 -0
  16. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_1.pth +3 -0
  17. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_2.pth +3 -0
  18. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_3.pth +3 -0
  19. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_4.pth +3 -0
  20. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_5.pth +3 -0
  21. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_6.pth +3 -0
  22. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_7.pth +3 -0
  23. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/scheduler.pt +3 -0
  24. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/special_tokens_map.json +31 -0
  25. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/tokenizer.json +3 -0
  26. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/tokenizer_config.json +207 -0
  27. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/trainer_state.json +3043 -0
  28. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/training_args.bin +3 -0
  29. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/vocab.json +0 -0
  30. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/zero_to_fp32.py +760 -0
  31. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/added_tokens.json +24 -0
  32. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/args.json +384 -0
  33. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/chat_template.jinja +54 -0
  34. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/config.json +59 -0
  35. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/generation_config.json +14 -0
  36. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/latest +1 -0
  37. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/merges.txt +0 -0
  38. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/model-00001-of-00004.safetensors +3 -0
  39. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/model-00002-of-00004.safetensors +3 -0
  40. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/model-00003-of-00004.safetensors +3 -0
  41. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/model-00004-of-00004.safetensors +3 -0
  42. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/model.safetensors.index.json +347 -0
  43. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_0.pth +3 -0
  44. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_1.pth +3 -0
  45. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_2.pth +3 -0
  46. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_3.pth +3 -0
  47. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_4.pth +3 -0
  48. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_5.pth +3 -0
  49. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_6.pth +3 -0
  50. qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_7.pth +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/args.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "epoch",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 2,
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": 4,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 5e-06,
18
+ "weight_decay": 0.1,
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": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "epoch",
38
+ "save_steps": 500,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
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
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 2000.0,
65
+ "dataloader_num_workers": 48,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
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
+ "tensorboard"
132
+ ],
133
+ "ddp_find_unused_parameters": null,
134
+ "ddp_bucket_cap_mb": null,
135
+ "ddp_broadcast_buffers": null,
136
+ "dataloader_pin_memory": true,
137
+ "dataloader_persistent_workers": false,
138
+ "skip_memory_metrics": true,
139
+ "use_legacy_prediction_loop": false,
140
+ "push_to_hub": false,
141
+ "resume_from_checkpoint": null,
142
+ "hub_model_id": null,
143
+ "hub_strategy": "every_save",
144
+ "hub_token": null,
145
+ "hub_private_repo": null,
146
+ "hub_always_push": false,
147
+ "hub_revision": null,
148
+ "gradient_checkpointing": true,
149
+ "gradient_checkpointing_kwargs": null,
150
+ "include_inputs_for_metrics": false,
151
+ "include_for_metrics": [],
152
+ "eval_do_concat_batches": true,
153
+ "fp16_backend": "auto",
154
+ "push_to_hub_model_id": null,
155
+ "push_to_hub_organization": null,
156
+ "push_to_hub_token": null,
157
+ "mp_parameters": "",
158
+ "auto_find_batch_size": false,
159
+ "full_determinism": false,
160
+ "torchdynamo": null,
161
+ "ray_scope": "last",
162
+ "ddp_timeout": 18000000,
163
+ "torch_compile": false,
164
+ "torch_compile_backend": null,
165
+ "torch_compile_mode": null,
166
+ "include_tokens_per_second": false,
167
+ "include_num_input_tokens_seen": false,
168
+ "neftune_noise_alpha": null,
169
+ "optim_target_modules": null,
170
+ "batch_eval_metrics": false,
171
+ "eval_on_start": false,
172
+ "use_liger_kernel": false,
173
+ "liger_kernel_config": null,
174
+ "eval_use_gather_object": false,
175
+ "average_tokens_across_devices": true,
176
+ "sortish_sampler": false,
177
+ "predict_with_generate": false,
178
+ "generation_max_length": null,
179
+ "generation_num_beams": null,
180
+ "generation_config": null,
181
+ "tuner_backend": "peft",
182
+ "vit_gradient_checkpointing": null,
183
+ "router_aux_loss_coef": 0.0,
184
+ "enable_dft_loss": false,
185
+ "check_model": true,
186
+ "acc_strategy": "token",
187
+ "train_dataloader_shuffle": true,
188
+ "max_epochs": null,
189
+ "aligner_lr": null,
190
+ "vit_lr": null,
191
+ "use_logits_to_keep": null,
192
+ "channels": null,
193
+ "ds3_gather_for_generation": true,
194
+ "resume_only_model": false,
195
+ "optimizer": null,
196
+ "loss_type": null,
197
+ "metric": null,
198
+ "eval_use_evalscope": false,
199
+ "eval_dataset": [],
200
+ "eval_dataset_args": null,
201
+ "eval_limit": null,
202
+ "eval_generation_config": null,
203
+ "extra_eval_args": null,
204
+ "use_flash_ckpt": false,
205
+ "model": "Qwen/Qwen2.5-7B-Instruct",
206
+ "model_type": "qwen2_5",
207
+ "model_revision": null,
208
+ "task_type": "causal_lm",
209
+ "torch_dtype": "bfloat16",
210
+ "attn_impl": null,
211
+ "new_special_tokens": [],
212
+ "num_labels": null,
213
+ "problem_type": null,
214
+ "rope_scaling": null,
215
+ "device_map": null,
216
+ "max_memory": {},
217
+ "max_model_len": null,
218
+ "local_repo_path": null,
219
+ "init_strategy": null,
220
+ "template": "qwen2_5",
221
+ "system": null,
222
+ "max_length": 16240,
223
+ "truncation_strategy": "delete",
224
+ "max_pixels": null,
225
+ "agent_template": null,
226
+ "norm_bbox": null,
227
+ "use_chat_template": true,
228
+ "padding_free": false,
229
+ "padding_side": "right",
230
+ "loss_scale": "default",
231
+ "sequence_parallel_size": 1,
232
+ "response_prefix": null,
233
+ "template_backend": "swift",
234
+ "dataset": [
235
+ "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_2083q_0.8_swift.jsonl",
236
+ "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_new1369q_format_0.8_swift.jsonl",
237
+ "/group/40143/hongzhuyi/ms-swift/data/corr_nq_2225q_0.8_swift.jsonl",
238
+ "/group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_hp673_swift.jsonl",
239
+ "/group/40143/hongzhuyi/ms-swift/self_2000_2000_1369_4_nq400_noinfo_swift.jsonl"
240
+ ],
241
+ "val_dataset": [],
242
+ "split_dataset_ratio": 0.001,
243
+ "dataset_num_proc": 100,
244
+ "load_from_cache_file": true,
245
+ "dataset_shuffle": true,
246
+ "val_dataset_shuffle": false,
247
+ "streaming": false,
248
+ "interleave_prob": null,
249
+ "stopping_strategy": "first_exhausted",
250
+ "shuffle_buffer_size": 1000,
251
+ "download_mode": "reuse_dataset_if_exists",
252
+ "columns": {},
253
+ "strict": false,
254
+ "model_name": null,
255
+ "model_author": null,
256
+ "custom_dataset_info": [],
257
+ "quant_method": null,
258
+ "quant_bits": null,
259
+ "hqq_axis": null,
260
+ "bnb_4bit_compute_dtype": "bfloat16",
261
+ "bnb_4bit_quant_type": "nf4",
262
+ "bnb_4bit_use_double_quant": true,
263
+ "bnb_4bit_quant_storage": null,
264
+ "max_new_tokens": 64,
265
+ "temperature": 0.0,
266
+ "top_k": null,
267
+ "top_p": null,
268
+ "repetition_penalty": null,
269
+ "num_beams": 1,
270
+ "stream": false,
271
+ "stop_words": [],
272
+ "logprobs": false,
273
+ "top_logprobs": null,
274
+ "ckpt_dir": null,
275
+ "lora_modules": [],
276
+ "train_type": "full",
277
+ "adapters": [],
278
+ "external_plugins": [],
279
+ "model_kwargs": {},
280
+ "load_args": false,
281
+ "load_data_args": false,
282
+ "packing": false,
283
+ "packing_length": null,
284
+ "lazy_tokenize": false,
285
+ "cached_dataset": [],
286
+ "custom_register_path": [],
287
+ "use_hf": false,
288
+ "ignore_args_error": false,
289
+ "use_swift_lora": false,
290
+ "freeze_parameters": [],
291
+ "freeze_parameters_regex": null,
292
+ "freeze_parameters_ratio": 0.0,
293
+ "trainable_parameters": [],
294
+ "trainable_parameters_regex": null,
295
+ "freeze_llm": false,
296
+ "freeze_vit": true,
297
+ "freeze_aligner": false,
298
+ "target_modules": [
299
+ "all-linear"
300
+ ],
301
+ "target_regex": null,
302
+ "modules_to_save": [],
303
+ "lora_rank": 8,
304
+ "lora_alpha": 32,
305
+ "lora_dropout": 0.05,
306
+ "lora_bias": "none",
307
+ "lora_dtype": null,
308
+ "lorap_lr_ratio": null,
309
+ "use_rslora": false,
310
+ "use_dora": false,
311
+ "lora_ga_batch_size": 2,
312
+ "lora_ga_iters": 2,
313
+ "lora_ga_max_length": 1024,
314
+ "lora_ga_direction": "ArB2r",
315
+ "lora_ga_scale": "stable",
316
+ "lora_ga_stable_gamma": 16,
317
+ "init_weights": true,
318
+ "fourier_n_frequency": 2000,
319
+ "fourier_scaling": 300.0,
320
+ "boft_block_size": 4,
321
+ "boft_block_num": 0,
322
+ "boft_n_butterfly_factor": 1,
323
+ "boft_dropout": 0.0,
324
+ "vera_rank": 256,
325
+ "vera_projection_prng_key": 0,
326
+ "vera_dropout": 0.0,
327
+ "vera_d_initial": 0.1,
328
+ "adapter_act": "gelu",
329
+ "adapter_length": 128,
330
+ "use_galore": false,
331
+ "galore_target_modules": null,
332
+ "galore_rank": 128,
333
+ "galore_update_proj_gap": 50,
334
+ "galore_scale": 1.0,
335
+ "galore_proj_type": "std",
336
+ "galore_optim_per_parameter": false,
337
+ "galore_with_embedding": false,
338
+ "galore_quantization": false,
339
+ "galore_proj_quant": false,
340
+ "galore_proj_bits": 4,
341
+ "galore_proj_group_size": 256,
342
+ "galore_cos_threshold": 0.4,
343
+ "galore_gamma_proj": 2,
344
+ "galore_queue_size": 5,
345
+ "adalora_target_r": 8,
346
+ "adalora_init_r": 12,
347
+ "adalora_tinit": 0,
348
+ "adalora_tfinal": 0,
349
+ "adalora_deltaT": 1,
350
+ "adalora_beta1": 0.85,
351
+ "adalora_beta2": 0.85,
352
+ "adalora_orth_reg_weight": 0.5,
353
+ "llamapro_num_new_blocks": 4,
354
+ "llamapro_num_groups": null,
355
+ "lisa_activated_layers": 0,
356
+ "lisa_step_interval": 20,
357
+ "reft_layer_key": null,
358
+ "reft_layers": null,
359
+ "reft_rank": 4,
360
+ "reft_intervention_type": "LoreftIntervention",
361
+ "reft_args": null,
362
+ "swanlab_token": null,
363
+ "swanlab_project": null,
364
+ "swanlab_workspace": null,
365
+ "swanlab_exp_name": null,
366
+ "swanlab_lark_webhook_url": null,
367
+ "swanlab_lark_secret": null,
368
+ "swanlab_mode": "cloud",
369
+ "add_version": true,
370
+ "create_checkpoint_symlink": false,
371
+ "zero_hpz_partition_size": null,
372
+ "deepspeed_autotp_size": null,
373
+ "early_stop_interval": null,
374
+ "rank": 0,
375
+ "global_world_size": 8,
376
+ "local_world_size": 8,
377
+ "model_suffix": "Qwen2.5-7B-Instruct",
378
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
379
+ "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 0x7f18b0b01ab0>, 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, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
380
+ "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct",
381
+ "hub": "<class 'swift.hub.hub.MSHub'>",
382
+ "evaluation_strategy": "epoch",
383
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.1, 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='/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, 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, use_ipex=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=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949', 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), 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=['tensorboard'], 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, channels=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, train_type='full', local_repo_path=None, galore_config=None)"
384
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/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
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/args.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "epoch",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 2,
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": 4,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 5e-06,
18
+ "weight_decay": 0.1,
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": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "epoch",
38
+ "save_steps": 500,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
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
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 2000.0,
65
+ "dataloader_num_workers": 48,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
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
+ "tensorboard"
132
+ ],
133
+ "ddp_find_unused_parameters": null,
134
+ "ddp_bucket_cap_mb": null,
135
+ "ddp_broadcast_buffers": null,
136
+ "dataloader_pin_memory": true,
137
+ "dataloader_persistent_workers": false,
138
+ "skip_memory_metrics": true,
139
+ "use_legacy_prediction_loop": false,
140
+ "push_to_hub": false,
141
+ "resume_from_checkpoint": null,
142
+ "hub_model_id": null,
143
+ "hub_strategy": "every_save",
144
+ "hub_token": null,
145
+ "hub_private_repo": null,
146
+ "hub_always_push": false,
147
+ "hub_revision": null,
148
+ "gradient_checkpointing": true,
149
+ "gradient_checkpointing_kwargs": null,
150
+ "include_inputs_for_metrics": false,
151
+ "include_for_metrics": [],
152
+ "eval_do_concat_batches": true,
153
+ "fp16_backend": "auto",
154
+ "push_to_hub_model_id": null,
155
+ "push_to_hub_organization": null,
156
+ "push_to_hub_token": null,
157
+ "mp_parameters": "",
158
+ "auto_find_batch_size": false,
159
+ "full_determinism": false,
160
+ "torchdynamo": null,
161
+ "ray_scope": "last",
162
+ "ddp_timeout": 18000000,
163
+ "torch_compile": false,
164
+ "torch_compile_backend": null,
165
+ "torch_compile_mode": null,
166
+ "include_tokens_per_second": false,
167
+ "include_num_input_tokens_seen": false,
168
+ "neftune_noise_alpha": null,
169
+ "optim_target_modules": null,
170
+ "batch_eval_metrics": false,
171
+ "eval_on_start": false,
172
+ "use_liger_kernel": false,
173
+ "liger_kernel_config": null,
174
+ "eval_use_gather_object": false,
175
+ "average_tokens_across_devices": true,
176
+ "sortish_sampler": false,
177
+ "predict_with_generate": false,
178
+ "generation_max_length": null,
179
+ "generation_num_beams": null,
180
+ "generation_config": null,
181
+ "tuner_backend": "peft",
182
+ "vit_gradient_checkpointing": null,
183
+ "router_aux_loss_coef": 0.0,
184
+ "enable_dft_loss": false,
185
+ "check_model": true,
186
+ "acc_strategy": "token",
187
+ "train_dataloader_shuffle": true,
188
+ "max_epochs": null,
189
+ "aligner_lr": null,
190
+ "vit_lr": null,
191
+ "use_logits_to_keep": null,
192
+ "channels": null,
193
+ "ds3_gather_for_generation": true,
194
+ "resume_only_model": false,
195
+ "optimizer": null,
196
+ "loss_type": null,
197
+ "metric": null,
198
+ "eval_use_evalscope": false,
199
+ "eval_dataset": [],
200
+ "eval_dataset_args": null,
201
+ "eval_limit": null,
202
+ "eval_generation_config": null,
203
+ "extra_eval_args": null,
204
+ "use_flash_ckpt": false,
205
+ "model": "Qwen/Qwen2.5-7B-Instruct",
206
+ "model_type": "qwen2_5",
207
+ "model_revision": null,
208
+ "task_type": "causal_lm",
209
+ "torch_dtype": "bfloat16",
210
+ "attn_impl": null,
211
+ "new_special_tokens": [],
212
+ "num_labels": null,
213
+ "problem_type": null,
214
+ "rope_scaling": null,
215
+ "device_map": null,
216
+ "max_memory": {},
217
+ "max_model_len": null,
218
+ "local_repo_path": null,
219
+ "init_strategy": null,
220
+ "template": "qwen2_5",
221
+ "system": null,
222
+ "max_length": 16240,
223
+ "truncation_strategy": "delete",
224
+ "max_pixels": null,
225
+ "agent_template": null,
226
+ "norm_bbox": null,
227
+ "use_chat_template": true,
228
+ "padding_free": false,
229
+ "padding_side": "right",
230
+ "loss_scale": "default",
231
+ "sequence_parallel_size": 1,
232
+ "response_prefix": null,
233
+ "template_backend": "swift",
234
+ "dataset": [
235
+ "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_2083q_0.8_swift.jsonl",
236
+ "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_new1369q_format_0.8_swift.jsonl",
237
+ "/group/40143/hongzhuyi/ms-swift/data/corr_nq_2225q_0.8_swift.jsonl",
238
+ "/group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_hp673_swift.jsonl",
239
+ "/group/40143/hongzhuyi/ms-swift/self_2000_2000_1369_4_nq400_noinfo_swift.jsonl"
240
+ ],
241
+ "val_dataset": [],
242
+ "split_dataset_ratio": 0.001,
243
+ "dataset_num_proc": 100,
244
+ "load_from_cache_file": true,
245
+ "dataset_shuffle": true,
246
+ "val_dataset_shuffle": false,
247
+ "streaming": false,
248
+ "interleave_prob": null,
249
+ "stopping_strategy": "first_exhausted",
250
+ "shuffle_buffer_size": 1000,
251
+ "download_mode": "reuse_dataset_if_exists",
252
+ "columns": {},
253
+ "strict": false,
254
+ "model_name": null,
255
+ "model_author": null,
256
+ "custom_dataset_info": [],
257
+ "quant_method": null,
258
+ "quant_bits": null,
259
+ "hqq_axis": null,
260
+ "bnb_4bit_compute_dtype": "bfloat16",
261
+ "bnb_4bit_quant_type": "nf4",
262
+ "bnb_4bit_use_double_quant": true,
263
+ "bnb_4bit_quant_storage": null,
264
+ "max_new_tokens": 64,
265
+ "temperature": 0.0,
266
+ "top_k": null,
267
+ "top_p": null,
268
+ "repetition_penalty": null,
269
+ "num_beams": 1,
270
+ "stream": false,
271
+ "stop_words": [],
272
+ "logprobs": false,
273
+ "top_logprobs": null,
274
+ "ckpt_dir": null,
275
+ "lora_modules": [],
276
+ "train_type": "full",
277
+ "adapters": [],
278
+ "external_plugins": [],
279
+ "model_kwargs": {},
280
+ "load_args": false,
281
+ "load_data_args": false,
282
+ "packing": false,
283
+ "packing_length": null,
284
+ "lazy_tokenize": false,
285
+ "cached_dataset": [],
286
+ "custom_register_path": [],
287
+ "use_hf": false,
288
+ "ignore_args_error": false,
289
+ "use_swift_lora": false,
290
+ "freeze_parameters": [],
291
+ "freeze_parameters_regex": null,
292
+ "freeze_parameters_ratio": 0.0,
293
+ "trainable_parameters": [],
294
+ "trainable_parameters_regex": null,
295
+ "freeze_llm": false,
296
+ "freeze_vit": true,
297
+ "freeze_aligner": false,
298
+ "target_modules": [
299
+ "all-linear"
300
+ ],
301
+ "target_regex": null,
302
+ "modules_to_save": [],
303
+ "lora_rank": 8,
304
+ "lora_alpha": 32,
305
+ "lora_dropout": 0.05,
306
+ "lora_bias": "none",
307
+ "lora_dtype": null,
308
+ "lorap_lr_ratio": null,
309
+ "use_rslora": false,
310
+ "use_dora": false,
311
+ "lora_ga_batch_size": 2,
312
+ "lora_ga_iters": 2,
313
+ "lora_ga_max_length": 1024,
314
+ "lora_ga_direction": "ArB2r",
315
+ "lora_ga_scale": "stable",
316
+ "lora_ga_stable_gamma": 16,
317
+ "init_weights": true,
318
+ "fourier_n_frequency": 2000,
319
+ "fourier_scaling": 300.0,
320
+ "boft_block_size": 4,
321
+ "boft_block_num": 0,
322
+ "boft_n_butterfly_factor": 1,
323
+ "boft_dropout": 0.0,
324
+ "vera_rank": 256,
325
+ "vera_projection_prng_key": 0,
326
+ "vera_dropout": 0.0,
327
+ "vera_d_initial": 0.1,
328
+ "adapter_act": "gelu",
329
+ "adapter_length": 128,
330
+ "use_galore": false,
331
+ "galore_target_modules": null,
332
+ "galore_rank": 128,
333
+ "galore_update_proj_gap": 50,
334
+ "galore_scale": 1.0,
335
+ "galore_proj_type": "std",
336
+ "galore_optim_per_parameter": false,
337
+ "galore_with_embedding": false,
338
+ "galore_quantization": false,
339
+ "galore_proj_quant": false,
340
+ "galore_proj_bits": 4,
341
+ "galore_proj_group_size": 256,
342
+ "galore_cos_threshold": 0.4,
343
+ "galore_gamma_proj": 2,
344
+ "galore_queue_size": 5,
345
+ "adalora_target_r": 8,
346
+ "adalora_init_r": 12,
347
+ "adalora_tinit": 0,
348
+ "adalora_tfinal": 0,
349
+ "adalora_deltaT": 1,
350
+ "adalora_beta1": 0.85,
351
+ "adalora_beta2": 0.85,
352
+ "adalora_orth_reg_weight": 0.5,
353
+ "llamapro_num_new_blocks": 4,
354
+ "llamapro_num_groups": null,
355
+ "lisa_activated_layers": 0,
356
+ "lisa_step_interval": 20,
357
+ "reft_layer_key": null,
358
+ "reft_layers": null,
359
+ "reft_rank": 4,
360
+ "reft_intervention_type": "LoreftIntervention",
361
+ "reft_args": null,
362
+ "swanlab_token": null,
363
+ "swanlab_project": null,
364
+ "swanlab_workspace": null,
365
+ "swanlab_exp_name": null,
366
+ "swanlab_lark_webhook_url": null,
367
+ "swanlab_lark_secret": null,
368
+ "swanlab_mode": "cloud",
369
+ "add_version": true,
370
+ "create_checkpoint_symlink": false,
371
+ "zero_hpz_partition_size": null,
372
+ "deepspeed_autotp_size": null,
373
+ "early_stop_interval": null,
374
+ "rank": 0,
375
+ "global_world_size": 8,
376
+ "local_world_size": 8,
377
+ "model_suffix": "Qwen2.5-7B-Instruct",
378
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
379
+ "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 0x7f18b0b01ab0>, 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, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
380
+ "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct",
381
+ "hub": "<class 'swift.hub.hub.MSHub'>",
382
+ "evaluation_strategy": "epoch",
383
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.1, 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='/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, 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, use_ipex=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=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949', 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), 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=['tensorboard'], 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, channels=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, train_type='full', local_repo_path=None, galore_config=None)"
384
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/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 %}
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
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
+ "torch_dtype": "bfloat16",
55
+ "transformers_version": "4.55.4",
56
+ "use_cache": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 152064
59
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/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": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.55.4"
14
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step375
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f794c69a9236dbf76f7942ab71775885de2a14216e46e5a6ce23f238181bee90
3
+ size 4877660776
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e973686bed7736d8293ab02152e0ef0707792bef8cf9cae89265addb38704ba4
3
+ size 4932751008
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5263fe395d72ae861037a7a12da6140f94a2106ddb64222557592da640b2f40
3
+ size 4330865200
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9deed18bff7a7c6b125149e0ac9b1ce7b6318d544e260eca1cfeaac366f7cd9
3
+ size 1089994880
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/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
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bfe1981024ef92f2da08a90c72c7c793d1cc9de1547abd2556c968be70232eb
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a35b845d476d830805793c3dcf8ac2daad87fec289bff3f7eda9e72fc374eda1
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e9880996b01262a807d1ec3ebd91eee540e08130a14a45a4648731fd0d48a9
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee25c237d6fe62ec76adcf7daf899d7ed32eab5d1a5b447b911f4451c9a1b258
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6b31133f29a8fc0cb538aa807d6a403bd51939336bfd425cd3d122d8c5595c
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a26c55b5c7fa0522b1d27b2c00a7ea77ad010f19a1321991165c5c972b8fa97a
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a1a3cf85626196804f25a8293e22dc561bba068a70fb123e04afe4896c33972
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f87c1ee5f5db346c7b913137cbccd196eaf8ec5a4cf9f192418a3069269b49
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3293eb4f3d09b3c0ad001c0ec959ebfed63746d27379ad9bed17d07329bfa7a4
3
+ size 1465
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/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
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/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": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/trainer_state.json ADDED
@@ -0,0 +1,3043 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 375,
3
+ "best_metric": 0.40452611,
4
+ "best_model_checkpoint": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949/checkpoint-375",
5
+ "epoch": 1.0,
6
+ "eval_steps": 2000.0,
7
+ "global_step": 375,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0026702269692923898,
14
+ "grad_norm": 25.9951738787524,
15
+ "learning_rate": 1.3157894736842107e-07,
16
+ "loss": 1.2784477472305298,
17
+ "step": 1,
18
+ "token_acc": 0.7311307191848755
19
+ },
20
+ {
21
+ "epoch": 0.0053404539385847796,
22
+ "grad_norm": 26.0134582343188,
23
+ "learning_rate": 2.6315789473684213e-07,
24
+ "loss": 1.2746286392211914,
25
+ "step": 2,
26
+ "token_acc": 0.7251728773117065
27
+ },
28
+ {
29
+ "epoch": 0.00801068090787717,
30
+ "grad_norm": 27.789625459473513,
31
+ "learning_rate": 3.9473684210526315e-07,
32
+ "loss": 1.3924554586410522,
33
+ "step": 3,
34
+ "token_acc": 0.6993290185928345
35
+ },
36
+ {
37
+ "epoch": 0.010680907877169559,
38
+ "grad_norm": 25.883737905229633,
39
+ "learning_rate": 5.263157894736843e-07,
40
+ "loss": 1.261012077331543,
41
+ "step": 4,
42
+ "token_acc": 0.7253642082214355
43
+ },
44
+ {
45
+ "epoch": 0.01335113484646195,
46
+ "grad_norm": 27.268729077679687,
47
+ "learning_rate": 6.578947368421053e-07,
48
+ "loss": 1.303070068359375,
49
+ "step": 5,
50
+ "token_acc": 0.7242323756217957
51
+ },
52
+ {
53
+ "epoch": 0.01602136181575434,
54
+ "grad_norm": 25.551794480304583,
55
+ "learning_rate": 7.894736842105263e-07,
56
+ "loss": 1.2236071825027466,
57
+ "step": 6,
58
+ "token_acc": 0.7291103005409241
59
+ },
60
+ {
61
+ "epoch": 0.018691588785046728,
62
+ "grad_norm": 23.075827750998485,
63
+ "learning_rate": 9.210526315789474e-07,
64
+ "loss": 1.2412211894989014,
65
+ "step": 7,
66
+ "token_acc": 0.7204470634460449
67
+ },
68
+ {
69
+ "epoch": 0.021361815754339118,
70
+ "grad_norm": 22.209971641266176,
71
+ "learning_rate": 1.0526315789473685e-06,
72
+ "loss": 1.1496518850326538,
73
+ "step": 8,
74
+ "token_acc": 0.7288557291030884
75
+ },
76
+ {
77
+ "epoch": 0.02403204272363151,
78
+ "grad_norm": 20.49459930365545,
79
+ "learning_rate": 1.1842105263157894e-06,
80
+ "loss": 1.1063605546951294,
81
+ "step": 9,
82
+ "token_acc": 0.744395911693573
83
+ },
84
+ {
85
+ "epoch": 0.0267022696929239,
86
+ "grad_norm": 13.490920525684345,
87
+ "learning_rate": 1.3157894736842106e-06,
88
+ "loss": 1.0211771726608276,
89
+ "step": 10,
90
+ "token_acc": 0.7293604016304016
91
+ },
92
+ {
93
+ "epoch": 0.029372496662216287,
94
+ "grad_norm": 11.636461611349967,
95
+ "learning_rate": 1.4473684210526317e-06,
96
+ "loss": 0.9103009700775146,
97
+ "step": 11,
98
+ "token_acc": 0.7503692507743835
99
+ },
100
+ {
101
+ "epoch": 0.03204272363150868,
102
+ "grad_norm": 10.67731610894816,
103
+ "learning_rate": 1.5789473684210526e-06,
104
+ "loss": 0.9402506351470947,
105
+ "step": 12,
106
+ "token_acc": 0.73384028673172
107
+ },
108
+ {
109
+ "epoch": 0.03471295060080107,
110
+ "grad_norm": 8.832140118227038,
111
+ "learning_rate": 1.710526315789474e-06,
112
+ "loss": 0.8835819363594055,
113
+ "step": 13,
114
+ "token_acc": 0.7434419393539429
115
+ },
116
+ {
117
+ "epoch": 0.037383177570093455,
118
+ "grad_norm": 8.464705533543322,
119
+ "learning_rate": 1.8421052631578948e-06,
120
+ "loss": 0.7797865867614746,
121
+ "step": 14,
122
+ "token_acc": 0.7653090357780457
123
+ },
124
+ {
125
+ "epoch": 0.04005340453938585,
126
+ "grad_norm": 7.271002146671567,
127
+ "learning_rate": 1.973684210526316e-06,
128
+ "loss": 0.7792782783508301,
129
+ "step": 15,
130
+ "token_acc": 0.7714757919311523
131
+ },
132
+ {
133
+ "epoch": 0.042723631508678236,
134
+ "grad_norm": 7.181347189496973,
135
+ "learning_rate": 2.105263157894737e-06,
136
+ "loss": 0.8469322323799133,
137
+ "step": 16,
138
+ "token_acc": 0.7528302073478699
139
+ },
140
+ {
141
+ "epoch": 0.04539385847797063,
142
+ "grad_norm": 5.70513851667843,
143
+ "learning_rate": 2.236842105263158e-06,
144
+ "loss": 0.7800362706184387,
145
+ "step": 17,
146
+ "token_acc": 0.7738492488861084
147
+ },
148
+ {
149
+ "epoch": 0.04806408544726302,
150
+ "grad_norm": 5.664002619153287,
151
+ "learning_rate": 2.368421052631579e-06,
152
+ "loss": 0.7836983799934387,
153
+ "step": 18,
154
+ "token_acc": 0.7714446783065796
155
+ },
156
+ {
157
+ "epoch": 0.050734312416555405,
158
+ "grad_norm": 5.208416599483479,
159
+ "learning_rate": 2.5e-06,
160
+ "loss": 0.7131199240684509,
161
+ "step": 19,
162
+ "token_acc": 0.7841575741767883
163
+ },
164
+ {
165
+ "epoch": 0.0534045393858478,
166
+ "grad_norm": 4.748749346318206,
167
+ "learning_rate": 2.631578947368421e-06,
168
+ "loss": 0.6718606352806091,
169
+ "step": 20,
170
+ "token_acc": 0.8004783391952515
171
+ },
172
+ {
173
+ "epoch": 0.056074766355140186,
174
+ "grad_norm": 4.782636323379019,
175
+ "learning_rate": 2.7631578947368424e-06,
176
+ "loss": 0.691372275352478,
177
+ "step": 21,
178
+ "token_acc": 0.7920792102813721
179
+ },
180
+ {
181
+ "epoch": 0.05874499332443257,
182
+ "grad_norm": 4.499637754384628,
183
+ "learning_rate": 2.8947368421052634e-06,
184
+ "loss": 0.6496959924697876,
185
+ "step": 22,
186
+ "token_acc": 0.8037581443786621
187
+ },
188
+ {
189
+ "epoch": 0.06141522029372497,
190
+ "grad_norm": 4.212769125124917,
191
+ "learning_rate": 3.0263157894736843e-06,
192
+ "loss": 0.6970880031585693,
193
+ "step": 23,
194
+ "token_acc": 0.788820743560791
195
+ },
196
+ {
197
+ "epoch": 0.06408544726301736,
198
+ "grad_norm": 4.009535539570785,
199
+ "learning_rate": 3.157894736842105e-06,
200
+ "loss": 0.6617268919944763,
201
+ "step": 24,
202
+ "token_acc": 0.7970311045646667
203
+ },
204
+ {
205
+ "epoch": 0.06675567423230974,
206
+ "grad_norm": 4.6741564332136045,
207
+ "learning_rate": 3.289473684210527e-06,
208
+ "loss": 0.6658329963684082,
209
+ "step": 25,
210
+ "token_acc": 0.7937344312667847
211
+ },
212
+ {
213
+ "epoch": 0.06942590120160214,
214
+ "grad_norm": 4.335919646872255,
215
+ "learning_rate": 3.421052631578948e-06,
216
+ "loss": 0.6085357666015625,
217
+ "step": 26,
218
+ "token_acc": 0.8088857531547546
219
+ },
220
+ {
221
+ "epoch": 0.07209612817089453,
222
+ "grad_norm": 4.576263341558673,
223
+ "learning_rate": 3.5526315789473687e-06,
224
+ "loss": 0.6815857887268066,
225
+ "step": 27,
226
+ "token_acc": 0.7941006422042847
227
+ },
228
+ {
229
+ "epoch": 0.07476635514018691,
230
+ "grad_norm": 3.8485944621680637,
231
+ "learning_rate": 3.6842105263157896e-06,
232
+ "loss": 0.5761784315109253,
233
+ "step": 28,
234
+ "token_acc": 0.8145171999931335
235
+ },
236
+ {
237
+ "epoch": 0.0774365821094793,
238
+ "grad_norm": 3.789723262016889,
239
+ "learning_rate": 3.815789473684211e-06,
240
+ "loss": 0.5897889137268066,
241
+ "step": 29,
242
+ "token_acc": 0.8165714144706726
243
+ },
244
+ {
245
+ "epoch": 0.0801068090787717,
246
+ "grad_norm": 3.8089647099503248,
247
+ "learning_rate": 3.947368421052632e-06,
248
+ "loss": 0.6500604152679443,
249
+ "step": 30,
250
+ "token_acc": 0.7970352172851562
251
+ },
252
+ {
253
+ "epoch": 0.08277703604806408,
254
+ "grad_norm": 3.487147971187521,
255
+ "learning_rate": 4.078947368421053e-06,
256
+ "loss": 0.5655121803283691,
257
+ "step": 31,
258
+ "token_acc": 0.8189091086387634
259
+ },
260
+ {
261
+ "epoch": 0.08544726301735647,
262
+ "grad_norm": 3.464574041878132,
263
+ "learning_rate": 4.210526315789474e-06,
264
+ "loss": 0.5646066069602966,
265
+ "step": 32,
266
+ "token_acc": 0.8225899934768677
267
+ },
268
+ {
269
+ "epoch": 0.08811748998664887,
270
+ "grad_norm": 3.22141668756312,
271
+ "learning_rate": 4.342105263157895e-06,
272
+ "loss": 0.6030318140983582,
273
+ "step": 33,
274
+ "token_acc": 0.8073717355728149
275
+ },
276
+ {
277
+ "epoch": 0.09078771695594126,
278
+ "grad_norm": 3.2123227244638084,
279
+ "learning_rate": 4.473684210526316e-06,
280
+ "loss": 0.5760718584060669,
281
+ "step": 34,
282
+ "token_acc": 0.8139848709106445
283
+ },
284
+ {
285
+ "epoch": 0.09345794392523364,
286
+ "grad_norm": 3.3457970954870975,
287
+ "learning_rate": 4.605263157894737e-06,
288
+ "loss": 0.6047664284706116,
289
+ "step": 35,
290
+ "token_acc": 0.8085699081420898
291
+ },
292
+ {
293
+ "epoch": 0.09612817089452604,
294
+ "grad_norm": 3.2168262417574858,
295
+ "learning_rate": 4.736842105263158e-06,
296
+ "loss": 0.5822433233261108,
297
+ "step": 36,
298
+ "token_acc": 0.8101453185081482
299
+ },
300
+ {
301
+ "epoch": 0.09879839786381843,
302
+ "grad_norm": 3.2212924267445895,
303
+ "learning_rate": 4.8684210526315795e-06,
304
+ "loss": 0.5573239922523499,
305
+ "step": 37,
306
+ "token_acc": 0.823554515838623
307
+ },
308
+ {
309
+ "epoch": 0.10146862483311081,
310
+ "grad_norm": 3.1187155597636456,
311
+ "learning_rate": 5e-06,
312
+ "loss": 0.5128908157348633,
313
+ "step": 38,
314
+ "token_acc": 0.8298919796943665
315
+ },
316
+ {
317
+ "epoch": 0.1041388518024032,
318
+ "grad_norm": 3.4130504203518313,
319
+ "learning_rate": 4.999975664007296e-06,
320
+ "loss": 0.5583573579788208,
321
+ "step": 39,
322
+ "token_acc": 0.817588210105896
323
+ },
324
+ {
325
+ "epoch": 0.1068090787716956,
326
+ "grad_norm": 3.1079985124933995,
327
+ "learning_rate": 4.999902656502973e-06,
328
+ "loss": 0.5571855306625366,
329
+ "step": 40,
330
+ "token_acc": 0.8224899768829346
331
+ },
332
+ {
333
+ "epoch": 0.10947930574098798,
334
+ "grad_norm": 2.9665344244686556,
335
+ "learning_rate": 4.9997809789084015e-06,
336
+ "loss": 0.545729398727417,
337
+ "step": 41,
338
+ "token_acc": 0.8314932584762573
339
+ },
340
+ {
341
+ "epoch": 0.11214953271028037,
342
+ "grad_norm": 3.024150362088527,
343
+ "learning_rate": 4.9996106335924965e-06,
344
+ "loss": 0.6088305711746216,
345
+ "step": 42,
346
+ "token_acc": 0.8083910346031189
347
+ },
348
+ {
349
+ "epoch": 0.11481975967957277,
350
+ "grad_norm": 2.807191274611665,
351
+ "learning_rate": 4.999391623871676e-06,
352
+ "loss": 0.5560564994812012,
353
+ "step": 43,
354
+ "token_acc": 0.8238644003868103
355
+ },
356
+ {
357
+ "epoch": 0.11748998664886515,
358
+ "grad_norm": 2.909990558067392,
359
+ "learning_rate": 4.999123954009797e-06,
360
+ "loss": 0.5078028440475464,
361
+ "step": 44,
362
+ "token_acc": 0.8343728184700012
363
+ },
364
+ {
365
+ "epoch": 0.12016021361815754,
366
+ "grad_norm": 2.9677950498002073,
367
+ "learning_rate": 4.998807629218065e-06,
368
+ "loss": 0.4990992844104767,
369
+ "step": 45,
370
+ "token_acc": 0.8367020487785339
371
+ },
372
+ {
373
+ "epoch": 0.12283044058744993,
374
+ "grad_norm": 2.9866303063613033,
375
+ "learning_rate": 4.998442655654946e-06,
376
+ "loss": 0.5906006097793579,
377
+ "step": 46,
378
+ "token_acc": 0.8131707906723022
379
+ },
380
+ {
381
+ "epoch": 0.12550066755674233,
382
+ "grad_norm": 2.8636335558590207,
383
+ "learning_rate": 4.998029040426034e-06,
384
+ "loss": 0.5083811283111572,
385
+ "step": 47,
386
+ "token_acc": 0.8387569785118103
387
+ },
388
+ {
389
+ "epoch": 0.12817089452603472,
390
+ "grad_norm": 2.859469411402867,
391
+ "learning_rate": 4.997566791583916e-06,
392
+ "loss": 0.48888710141181946,
393
+ "step": 48,
394
+ "token_acc": 0.8355937004089355
395
+ },
396
+ {
397
+ "epoch": 0.1308411214953271,
398
+ "grad_norm": 2.998235299244795,
399
+ "learning_rate": 4.997055918128024e-06,
400
+ "loss": 0.5488249063491821,
401
+ "step": 49,
402
+ "token_acc": 0.8204185366630554
403
+ },
404
+ {
405
+ "epoch": 0.13351134846461948,
406
+ "grad_norm": 2.8486501408481586,
407
+ "learning_rate": 4.996496430004446e-06,
408
+ "loss": 0.5021145343780518,
409
+ "step": 50,
410
+ "token_acc": 0.8342471718788147
411
+ },
412
+ {
413
+ "epoch": 0.13618157543391188,
414
+ "grad_norm": 2.954641954110101,
415
+ "learning_rate": 4.995888338105742e-06,
416
+ "loss": 0.48680126667022705,
417
+ "step": 51,
418
+ "token_acc": 0.8417078256607056
419
+ },
420
+ {
421
+ "epoch": 0.13885180240320427,
422
+ "grad_norm": 2.7757060036765964,
423
+ "learning_rate": 4.995231654270726e-06,
424
+ "loss": 0.550148606300354,
425
+ "step": 52,
426
+ "token_acc": 0.8193753957748413
427
+ },
428
+ {
429
+ "epoch": 0.14152202937249667,
430
+ "grad_norm": 2.873790502222367,
431
+ "learning_rate": 4.994526391284242e-06,
432
+ "loss": 0.5617198944091797,
433
+ "step": 53,
434
+ "token_acc": 0.8200406432151794
435
+ },
436
+ {
437
+ "epoch": 0.14419225634178906,
438
+ "grad_norm": 2.8556275959576958,
439
+ "learning_rate": 4.993772562876909e-06,
440
+ "loss": 0.45519453287124634,
441
+ "step": 54,
442
+ "token_acc": 0.8451218008995056
443
+ },
444
+ {
445
+ "epoch": 0.14686248331108145,
446
+ "grad_norm": 2.992091191090329,
447
+ "learning_rate": 4.99297018372486e-06,
448
+ "loss": 0.5109154582023621,
449
+ "step": 55,
450
+ "token_acc": 0.828966498374939
451
+ },
452
+ {
453
+ "epoch": 0.14953271028037382,
454
+ "grad_norm": 2.7857995064782823,
455
+ "learning_rate": 4.992119269449445e-06,
456
+ "loss": 0.484749436378479,
457
+ "step": 56,
458
+ "token_acc": 0.836266815662384
459
+ },
460
+ {
461
+ "epoch": 0.15220293724966621,
462
+ "grad_norm": 2.6507818563981966,
463
+ "learning_rate": 4.9912198366169425e-06,
464
+ "loss": 0.49329179525375366,
465
+ "step": 57,
466
+ "token_acc": 0.8366071581840515
467
+ },
468
+ {
469
+ "epoch": 0.1548731642189586,
470
+ "grad_norm": 3.0228383426947185,
471
+ "learning_rate": 4.990271902738223e-06,
472
+ "loss": 0.5079492330551147,
473
+ "step": 58,
474
+ "token_acc": 0.8311025500297546
475
+ },
476
+ {
477
+ "epoch": 0.157543391188251,
478
+ "grad_norm": 2.698182226956831,
479
+ "learning_rate": 4.989275486268417e-06,
480
+ "loss": 0.49793922901153564,
481
+ "step": 59,
482
+ "token_acc": 0.8327831625938416
483
+ },
484
+ {
485
+ "epoch": 0.1602136181575434,
486
+ "grad_norm": 2.977614337097939,
487
+ "learning_rate": 4.988230606606552e-06,
488
+ "loss": 0.5468940734863281,
489
+ "step": 60,
490
+ "token_acc": 0.8215152025222778
491
+ },
492
+ {
493
+ "epoch": 0.1628838451268358,
494
+ "grad_norm": 3.0952893303022373,
495
+ "learning_rate": 4.9871372840951745e-06,
496
+ "loss": 0.471064031124115,
497
+ "step": 61,
498
+ "token_acc": 0.8421275019645691
499
+ },
500
+ {
501
+ "epoch": 0.16555407209612816,
502
+ "grad_norm": 2.9165080460985946,
503
+ "learning_rate": 4.985995540019956e-06,
504
+ "loss": 0.5136542916297913,
505
+ "step": 62,
506
+ "token_acc": 0.8301562070846558
507
+ },
508
+ {
509
+ "epoch": 0.16822429906542055,
510
+ "grad_norm": 2.865964197829534,
511
+ "learning_rate": 4.984805396609275e-06,
512
+ "loss": 0.5066840648651123,
513
+ "step": 63,
514
+ "token_acc": 0.8333961367607117
515
+ },
516
+ {
517
+ "epoch": 0.17089452603471295,
518
+ "grad_norm": 2.6287996056340845,
519
+ "learning_rate": 4.983566877033791e-06,
520
+ "loss": 0.4876897931098938,
521
+ "step": 64,
522
+ "token_acc": 0.8414356708526611
523
+ },
524
+ {
525
+ "epoch": 0.17356475300400534,
526
+ "grad_norm": 2.7667854024584924,
527
+ "learning_rate": 4.982280005405986e-06,
528
+ "loss": 0.478080689907074,
529
+ "step": 65,
530
+ "token_acc": 0.8451737761497498
531
+ },
532
+ {
533
+ "epoch": 0.17623497997329773,
534
+ "grad_norm": 2.6685049053377092,
535
+ "learning_rate": 4.980944806779698e-06,
536
+ "loss": 0.513857364654541,
537
+ "step": 66,
538
+ "token_acc": 0.8314993977546692
539
+ },
540
+ {
541
+ "epoch": 0.17890520694259013,
542
+ "grad_norm": 2.907912812806632,
543
+ "learning_rate": 4.979561307149635e-06,
544
+ "loss": 0.46788477897644043,
545
+ "step": 67,
546
+ "token_acc": 0.8453928232192993
547
+ },
548
+ {
549
+ "epoch": 0.18157543391188252,
550
+ "grad_norm": 2.856555918974467,
551
+ "learning_rate": 4.9781295334508664e-06,
552
+ "loss": 0.49202442169189453,
553
+ "step": 68,
554
+ "token_acc": 0.8402069211006165
555
+ },
556
+ {
557
+ "epoch": 0.1842456608811749,
558
+ "grad_norm": 2.83720612847393,
559
+ "learning_rate": 4.976649513558299e-06,
560
+ "loss": 0.4952801764011383,
561
+ "step": 69,
562
+ "token_acc": 0.8359651565551758
563
+ },
564
+ {
565
+ "epoch": 0.18691588785046728,
566
+ "grad_norm": 2.768961275201744,
567
+ "learning_rate": 4.975121276286136e-06,
568
+ "loss": 0.49208366870880127,
569
+ "step": 70,
570
+ "token_acc": 0.835932195186615
571
+ },
572
+ {
573
+ "epoch": 0.18958611481975968,
574
+ "grad_norm": 2.686635064971432,
575
+ "learning_rate": 4.973544851387315e-06,
576
+ "loss": 0.5072571039199829,
577
+ "step": 71,
578
+ "token_acc": 0.837751030921936
579
+ },
580
+ {
581
+ "epoch": 0.19225634178905207,
582
+ "grad_norm": 2.476707993358583,
583
+ "learning_rate": 4.9719202695529265e-06,
584
+ "loss": 0.4340510964393616,
585
+ "step": 72,
586
+ "token_acc": 0.8518267273902893
587
+ },
588
+ {
589
+ "epoch": 0.19492656875834447,
590
+ "grad_norm": 2.5752024586646844,
591
+ "learning_rate": 4.9702475624116206e-06,
592
+ "loss": 0.42714187502861023,
593
+ "step": 73,
594
+ "token_acc": 0.8572417497634888
595
+ },
596
+ {
597
+ "epoch": 0.19759679572763686,
598
+ "grad_norm": 2.990445045854445,
599
+ "learning_rate": 4.968526762528988e-06,
600
+ "loss": 0.5057822465896606,
601
+ "step": 74,
602
+ "token_acc": 0.83729088306427
603
+ },
604
+ {
605
+ "epoch": 0.20026702269692923,
606
+ "grad_norm": 3.094588183329357,
607
+ "learning_rate": 4.966757903406928e-06,
608
+ "loss": 0.5105546712875366,
609
+ "step": 75,
610
+ "token_acc": 0.8271516561508179
611
+ },
612
+ {
613
+ "epoch": 0.20293724966622162,
614
+ "grad_norm": 2.6374793658698974,
615
+ "learning_rate": 4.964941019482995e-06,
616
+ "loss": 0.4578150808811188,
617
+ "step": 76,
618
+ "token_acc": 0.8516289591789246
619
+ },
620
+ {
621
+ "epoch": 0.205607476635514,
622
+ "grad_norm": 2.713598660561642,
623
+ "learning_rate": 4.963076146129726e-06,
624
+ "loss": 0.4840947985649109,
625
+ "step": 77,
626
+ "token_acc": 0.8387418389320374
627
+ },
628
+ {
629
+ "epoch": 0.2082777036048064,
630
+ "grad_norm": 2.46367456759054,
631
+ "learning_rate": 4.961163319653959e-06,
632
+ "loss": 0.4561350643634796,
633
+ "step": 78,
634
+ "token_acc": 0.8493353128433228
635
+ },
636
+ {
637
+ "epoch": 0.2109479305740988,
638
+ "grad_norm": 2.6829301858674026,
639
+ "learning_rate": 4.959202577296117e-06,
640
+ "loss": 0.4757446348667145,
641
+ "step": 79,
642
+ "token_acc": 0.8415343761444092
643
+ },
644
+ {
645
+ "epoch": 0.2136181575433912,
646
+ "grad_norm": 2.779414787207709,
647
+ "learning_rate": 4.9571939572294914e-06,
648
+ "loss": 0.5293632745742798,
649
+ "step": 80,
650
+ "token_acc": 0.8276843428611755
651
+ },
652
+ {
653
+ "epoch": 0.2162883845126836,
654
+ "grad_norm": 2.4970148616770724,
655
+ "learning_rate": 4.955137498559491e-06,
656
+ "loss": 0.44986119866371155,
657
+ "step": 81,
658
+ "token_acc": 0.849868893623352
659
+ },
660
+ {
661
+ "epoch": 0.21895861148197596,
662
+ "grad_norm": 2.662151036336258,
663
+ "learning_rate": 4.953033241322887e-06,
664
+ "loss": 0.4561771750450134,
665
+ "step": 82,
666
+ "token_acc": 0.845279335975647
667
+ },
668
+ {
669
+ "epoch": 0.22162883845126835,
670
+ "grad_norm": 2.8316421050114173,
671
+ "learning_rate": 4.95088122648703e-06,
672
+ "loss": 0.49068668484687805,
673
+ "step": 83,
674
+ "token_acc": 0.8331988453865051
675
+ },
676
+ {
677
+ "epoch": 0.22429906542056074,
678
+ "grad_norm": 2.620701723146304,
679
+ "learning_rate": 4.948681495949055e-06,
680
+ "loss": 0.4708014130592346,
681
+ "step": 84,
682
+ "token_acc": 0.843478262424469
683
+ },
684
+ {
685
+ "epoch": 0.22696929238985314,
686
+ "grad_norm": 2.9430948999262756,
687
+ "learning_rate": 4.9464340925350624e-06,
688
+ "loss": 0.5356360673904419,
689
+ "step": 85,
690
+ "token_acc": 0.8235377073287964
691
+ },
692
+ {
693
+ "epoch": 0.22963951935914553,
694
+ "grad_norm": 2.8689851582637,
695
+ "learning_rate": 4.944139059999286e-06,
696
+ "loss": 0.47248947620391846,
697
+ "step": 86,
698
+ "token_acc": 0.8433862328529358
699
+ },
700
+ {
701
+ "epoch": 0.23230974632843793,
702
+ "grad_norm": 2.569976834463926,
703
+ "learning_rate": 4.941796443023243e-06,
704
+ "loss": 0.46606525778770447,
705
+ "step": 87,
706
+ "token_acc": 0.8461019396781921
707
+ },
708
+ {
709
+ "epoch": 0.2349799732977303,
710
+ "grad_norm": 2.745805696173523,
711
+ "learning_rate": 4.939406287214861e-06,
712
+ "loss": 0.5027751922607422,
713
+ "step": 88,
714
+ "token_acc": 0.8389756679534912
715
+ },
716
+ {
717
+ "epoch": 0.2376502002670227,
718
+ "grad_norm": 2.6765497306131176,
719
+ "learning_rate": 4.936968639107591e-06,
720
+ "loss": 0.493681401014328,
721
+ "step": 89,
722
+ "token_acc": 0.8358249664306641
723
+ },
724
+ {
725
+ "epoch": 0.24032042723631508,
726
+ "grad_norm": 2.6599785314912645,
727
+ "learning_rate": 4.9344835461595016e-06,
728
+ "loss": 0.4906979203224182,
729
+ "step": 90,
730
+ "token_acc": 0.838015615940094
731
+ },
732
+ {
733
+ "epoch": 0.24299065420560748,
734
+ "grad_norm": 2.6684119224897347,
735
+ "learning_rate": 4.9319510567523566e-06,
736
+ "loss": 0.5154832005500793,
737
+ "step": 91,
738
+ "token_acc": 0.8292044997215271
739
+ },
740
+ {
741
+ "epoch": 0.24566088117489987,
742
+ "grad_norm": 2.7698467507994575,
743
+ "learning_rate": 4.929371220190671e-06,
744
+ "loss": 0.4774641990661621,
745
+ "step": 92,
746
+ "token_acc": 0.8410144448280334
747
+ },
748
+ {
749
+ "epoch": 0.24833110814419226,
750
+ "grad_norm": 2.6295351013564976,
751
+ "learning_rate": 4.926744086700752e-06,
752
+ "loss": 0.5144312381744385,
753
+ "step": 93,
754
+ "token_acc": 0.8328940272331238
755
+ },
756
+ {
757
+ "epoch": 0.25100133511348466,
758
+ "grad_norm": 2.7323403928899563,
759
+ "learning_rate": 4.9240697074297205e-06,
760
+ "loss": 0.48028236627578735,
761
+ "step": 94,
762
+ "token_acc": 0.8403794169425964
763
+ },
764
+ {
765
+ "epoch": 0.253671562082777,
766
+ "grad_norm": 2.410025898588041,
767
+ "learning_rate": 4.921348134444516e-06,
768
+ "loss": 0.4648444652557373,
769
+ "step": 95,
770
+ "token_acc": 0.845313310623169
771
+ },
772
+ {
773
+ "epoch": 0.25634178905206945,
774
+ "grad_norm": 2.531641996939488,
775
+ "learning_rate": 4.918579420730884e-06,
776
+ "loss": 0.4263961613178253,
777
+ "step": 96,
778
+ "token_acc": 0.8554727435112
779
+ },
780
+ {
781
+ "epoch": 0.2590120160213618,
782
+ "grad_norm": 2.7166151491885073,
783
+ "learning_rate": 4.9157636201923385e-06,
784
+ "loss": 0.43437933921813965,
785
+ "step": 97,
786
+ "token_acc": 0.8528169989585876
787
+ },
788
+ {
789
+ "epoch": 0.2616822429906542,
790
+ "grad_norm": 2.69671582054589,
791
+ "learning_rate": 4.912900787649124e-06,
792
+ "loss": 0.4674450755119324,
793
+ "step": 98,
794
+ "token_acc": 0.8463652729988098
795
+ },
796
+ {
797
+ "epoch": 0.2643524699599466,
798
+ "grad_norm": 2.9775748653740948,
799
+ "learning_rate": 4.909990978837137e-06,
800
+ "loss": 0.4577414095401764,
801
+ "step": 99,
802
+ "token_acc": 0.8503103852272034
803
+ },
804
+ {
805
+ "epoch": 0.26702269692923897,
806
+ "grad_norm": 2.519209757520852,
807
+ "learning_rate": 4.907034250406846e-06,
808
+ "loss": 0.45865607261657715,
809
+ "step": 100,
810
+ "token_acc": 0.8510278463363647
811
+ },
812
+ {
813
+ "epoch": 0.2696929238985314,
814
+ "grad_norm": 2.781075999646215,
815
+ "learning_rate": 4.904030659922188e-06,
816
+ "loss": 0.4701615571975708,
817
+ "step": 101,
818
+ "token_acc": 0.8452981114387512
819
+ },
820
+ {
821
+ "epoch": 0.27236315086782376,
822
+ "grad_norm": 2.9690855212550473,
823
+ "learning_rate": 4.900980265859449e-06,
824
+ "loss": 0.47470730543136597,
825
+ "step": 102,
826
+ "token_acc": 0.8398820161819458
827
+ },
828
+ {
829
+ "epoch": 0.2750333778371162,
830
+ "grad_norm": 2.779823482085574,
831
+ "learning_rate": 4.897883127606121e-06,
832
+ "loss": 0.459528386592865,
833
+ "step": 103,
834
+ "token_acc": 0.8435173630714417
835
+ },
836
+ {
837
+ "epoch": 0.27770360480640854,
838
+ "grad_norm": 2.6409294509414396,
839
+ "learning_rate": 4.894739305459754e-06,
840
+ "loss": 0.46661314368247986,
841
+ "step": 104,
842
+ "token_acc": 0.8413355350494385
843
+ },
844
+ {
845
+ "epoch": 0.2803738317757009,
846
+ "grad_norm": 2.6690597708970594,
847
+ "learning_rate": 4.891548860626772e-06,
848
+ "loss": 0.4770851135253906,
849
+ "step": 105,
850
+ "token_acc": 0.8401432633399963
851
+ },
852
+ {
853
+ "epoch": 0.28304405874499333,
854
+ "grad_norm": 2.557201702907276,
855
+ "learning_rate": 4.88831185522129e-06,
856
+ "loss": 0.4580926299095154,
857
+ "step": 106,
858
+ "token_acc": 0.8482392430305481
859
+ },
860
+ {
861
+ "epoch": 0.2857142857142857,
862
+ "grad_norm": 2.5838963309370877,
863
+ "learning_rate": 4.885028352263898e-06,
864
+ "loss": 0.4886952042579651,
865
+ "step": 107,
866
+ "token_acc": 0.8389544486999512
867
+ },
868
+ {
869
+ "epoch": 0.2883845126835781,
870
+ "grad_norm": 2.552737753281325,
871
+ "learning_rate": 4.881698415680442e-06,
872
+ "loss": 0.4570938050746918,
873
+ "step": 108,
874
+ "token_acc": 0.8504659533500671
875
+ },
876
+ {
877
+ "epoch": 0.2910547396528705,
878
+ "grad_norm": 2.745451254507048,
879
+ "learning_rate": 4.878322110300771e-06,
880
+ "loss": 0.539262056350708,
881
+ "step": 109,
882
+ "token_acc": 0.825426459312439
883
+ },
884
+ {
885
+ "epoch": 0.2937249666221629,
886
+ "grad_norm": 2.863130638994318,
887
+ "learning_rate": 4.874899501857477e-06,
888
+ "loss": 0.45649611949920654,
889
+ "step": 110,
890
+ "token_acc": 0.8448225855827332
891
+ },
892
+ {
893
+ "epoch": 0.2963951935914553,
894
+ "grad_norm": 2.664117644747291,
895
+ "learning_rate": 4.871430656984623e-06,
896
+ "loss": 0.4779259264469147,
897
+ "step": 111,
898
+ "token_acc": 0.8417208790779114
899
+ },
900
+ {
901
+ "epoch": 0.29906542056074764,
902
+ "grad_norm": 2.4791469123801884,
903
+ "learning_rate": 4.867915643216434e-06,
904
+ "loss": 0.41383033990859985,
905
+ "step": 112,
906
+ "token_acc": 0.8608695864677429
907
+ },
908
+ {
909
+ "epoch": 0.30173564753004006,
910
+ "grad_norm": 2.517359113640716,
911
+ "learning_rate": 4.864354528985989e-06,
912
+ "loss": 0.4821171760559082,
913
+ "step": 113,
914
+ "token_acc": 0.8395127654075623
915
+ },
916
+ {
917
+ "epoch": 0.30440587449933243,
918
+ "grad_norm": 2.7149864097363468,
919
+ "learning_rate": 4.860747383623889e-06,
920
+ "loss": 0.4742806553840637,
921
+ "step": 114,
922
+ "token_acc": 0.8428994417190552
923
+ },
924
+ {
925
+ "epoch": 0.30707610146862485,
926
+ "grad_norm": 2.8072339189221043,
927
+ "learning_rate": 4.857094277356905e-06,
928
+ "loss": 0.4662167727947235,
929
+ "step": 115,
930
+ "token_acc": 0.8428978323936462
931
+ },
932
+ {
933
+ "epoch": 0.3097463284379172,
934
+ "grad_norm": 2.488318597434865,
935
+ "learning_rate": 4.85339528130661e-06,
936
+ "loss": 0.44936496019363403,
937
+ "step": 116,
938
+ "token_acc": 0.8470027446746826
939
+ },
940
+ {
941
+ "epoch": 0.31241655540720964,
942
+ "grad_norm": 2.6416123865841206,
943
+ "learning_rate": 4.849650467487996e-06,
944
+ "loss": 0.5037504434585571,
945
+ "step": 117,
946
+ "token_acc": 0.829302966594696
947
+ },
948
+ {
949
+ "epoch": 0.315086782376502,
950
+ "grad_norm": 2.7164641437787784,
951
+ "learning_rate": 4.845859908808074e-06,
952
+ "loss": 0.4293018579483032,
953
+ "step": 118,
954
+ "token_acc": 0.8532283902168274
955
+ },
956
+ {
957
+ "epoch": 0.3177570093457944,
958
+ "grad_norm": 2.5869504971179778,
959
+ "learning_rate": 4.84202367906445e-06,
960
+ "loss": 0.4592546224594116,
961
+ "step": 119,
962
+ "token_acc": 0.8481976389884949
963
+ },
964
+ {
965
+ "epoch": 0.3204272363150868,
966
+ "grad_norm": 2.6148825087644303,
967
+ "learning_rate": 4.838141852943891e-06,
968
+ "loss": 0.4671098589897156,
969
+ "step": 120,
970
+ "token_acc": 0.8434999585151672
971
+ },
972
+ {
973
+ "epoch": 0.32309746328437916,
974
+ "grad_norm": 2.6063705556692818,
975
+ "learning_rate": 4.834214506020871e-06,
976
+ "loss": 0.46162307262420654,
977
+ "step": 121,
978
+ "token_acc": 0.8456430435180664
979
+ },
980
+ {
981
+ "epoch": 0.3257676902536716,
982
+ "grad_norm": 2.6813767753734403,
983
+ "learning_rate": 4.830241714756099e-06,
984
+ "loss": 0.4838264584541321,
985
+ "step": 122,
986
+ "token_acc": 0.8361061215400696
987
+ },
988
+ {
989
+ "epoch": 0.32843791722296395,
990
+ "grad_norm": 2.6059863428969616,
991
+ "learning_rate": 4.826223556495031e-06,
992
+ "loss": 0.44379669427871704,
993
+ "step": 123,
994
+ "token_acc": 0.8507857322692871
995
+ },
996
+ {
997
+ "epoch": 0.3311081441922563,
998
+ "grad_norm": 2.5706517211769486,
999
+ "learning_rate": 4.822160109466361e-06,
1000
+ "loss": 0.4725993871688843,
1001
+ "step": 124,
1002
+ "token_acc": 0.8372030258178711
1003
+ },
1004
+ {
1005
+ "epoch": 0.33377837116154874,
1006
+ "grad_norm": 2.6687762719060735,
1007
+ "learning_rate": 4.818051452780505e-06,
1008
+ "loss": 0.4378458261489868,
1009
+ "step": 125,
1010
+ "token_acc": 0.8532850742340088
1011
+ },
1012
+ {
1013
+ "epoch": 0.3364485981308411,
1014
+ "grad_norm": 2.6824080581323924,
1015
+ "learning_rate": 4.813897666428054e-06,
1016
+ "loss": 0.4978247284889221,
1017
+ "step": 126,
1018
+ "token_acc": 0.8349565267562866
1019
+ },
1020
+ {
1021
+ "epoch": 0.3391188251001335,
1022
+ "grad_norm": 2.768740972568306,
1023
+ "learning_rate": 4.809698831278217e-06,
1024
+ "loss": 0.45435789227485657,
1025
+ "step": 127,
1026
+ "token_acc": 0.8471603393554688
1027
+ },
1028
+ {
1029
+ "epoch": 0.3417890520694259,
1030
+ "grad_norm": 2.920108910909366,
1031
+ "learning_rate": 4.805455029077255e-06,
1032
+ "loss": 0.4446132779121399,
1033
+ "step": 128,
1034
+ "token_acc": 0.8496423959732056
1035
+ },
1036
+ {
1037
+ "epoch": 0.3444592790387183,
1038
+ "grad_norm": 2.7692194344349463,
1039
+ "learning_rate": 4.801166342446877e-06,
1040
+ "loss": 0.46422040462493896,
1041
+ "step": 129,
1042
+ "token_acc": 0.8420339822769165
1043
+ },
1044
+ {
1045
+ "epoch": 0.3471295060080107,
1046
+ "grad_norm": 2.4755852218008334,
1047
+ "learning_rate": 4.79683285488264e-06,
1048
+ "loss": 0.45947498083114624,
1049
+ "step": 130,
1050
+ "token_acc": 0.8488883376121521
1051
+ },
1052
+ {
1053
+ "epoch": 0.34979973297730305,
1054
+ "grad_norm": 2.6805786961608997,
1055
+ "learning_rate": 4.792454650752324e-06,
1056
+ "loss": 0.5025047063827515,
1057
+ "step": 131,
1058
+ "token_acc": 0.8290598392486572
1059
+ },
1060
+ {
1061
+ "epoch": 0.35246995994659547,
1062
+ "grad_norm": 2.786394198507592,
1063
+ "learning_rate": 4.788031815294282e-06,
1064
+ "loss": 0.4801027178764343,
1065
+ "step": 132,
1066
+ "token_acc": 0.8388292789459229
1067
+ },
1068
+ {
1069
+ "epoch": 0.35514018691588783,
1070
+ "grad_norm": 2.4827646692441436,
1071
+ "learning_rate": 4.783564434615788e-06,
1072
+ "loss": 0.44011634588241577,
1073
+ "step": 133,
1074
+ "token_acc": 0.8533205389976501
1075
+ },
1076
+ {
1077
+ "epoch": 0.35781041388518026,
1078
+ "grad_norm": 2.679300946091702,
1079
+ "learning_rate": 4.779052595691355e-06,
1080
+ "loss": 0.46361014246940613,
1081
+ "step": 134,
1082
+ "token_acc": 0.8467062711715698
1083
+ },
1084
+ {
1085
+ "epoch": 0.3604806408544726,
1086
+ "grad_norm": 2.4602272349621326,
1087
+ "learning_rate": 4.774496386361049e-06,
1088
+ "loss": 0.4593627452850342,
1089
+ "step": 135,
1090
+ "token_acc": 0.8477495312690735
1091
+ },
1092
+ {
1093
+ "epoch": 0.36315086782376504,
1094
+ "grad_norm": 2.734540514137931,
1095
+ "learning_rate": 4.76989589532877e-06,
1096
+ "loss": 0.44871199131011963,
1097
+ "step": 136,
1098
+ "token_acc": 0.8520923256874084
1099
+ },
1100
+ {
1101
+ "epoch": 0.3658210947930574,
1102
+ "grad_norm": 2.5844554385246705,
1103
+ "learning_rate": 4.765251212160531e-06,
1104
+ "loss": 0.4495413899421692,
1105
+ "step": 137,
1106
+ "token_acc": 0.85186767578125
1107
+ },
1108
+ {
1109
+ "epoch": 0.3684913217623498,
1110
+ "grad_norm": 2.511411602552799,
1111
+ "learning_rate": 4.7605624272827125e-06,
1112
+ "loss": 0.4278019070625305,
1113
+ "step": 138,
1114
+ "token_acc": 0.8554805517196655
1115
+ },
1116
+ {
1117
+ "epoch": 0.3711615487316422,
1118
+ "grad_norm": 2.4745294956114607,
1119
+ "learning_rate": 4.755829631980303e-06,
1120
+ "loss": 0.4258793592453003,
1121
+ "step": 139,
1122
+ "token_acc": 0.8546519875526428
1123
+ },
1124
+ {
1125
+ "epoch": 0.37383177570093457,
1126
+ "grad_norm": 2.5234826970243383,
1127
+ "learning_rate": 4.75105291839512e-06,
1128
+ "loss": 0.45688676834106445,
1129
+ "step": 140,
1130
+ "token_acc": 0.8474181890487671
1131
+ },
1132
+ {
1133
+ "epoch": 0.376502002670227,
1134
+ "grad_norm": 2.6089576740729203,
1135
+ "learning_rate": 4.746232379524016e-06,
1136
+ "loss": 0.45167502760887146,
1137
+ "step": 141,
1138
+ "token_acc": 0.8504248261451721
1139
+ },
1140
+ {
1141
+ "epoch": 0.37917222963951935,
1142
+ "grad_norm": 2.7543779565500195,
1143
+ "learning_rate": 4.741368109217072e-06,
1144
+ "loss": 0.5100749731063843,
1145
+ "step": 142,
1146
+ "token_acc": 0.8278107643127441
1147
+ },
1148
+ {
1149
+ "epoch": 0.3818424566088118,
1150
+ "grad_norm": 2.316938740840274,
1151
+ "learning_rate": 4.736460202175763e-06,
1152
+ "loss": 0.41679853200912476,
1153
+ "step": 143,
1154
+ "token_acc": 0.8646016716957092
1155
+ },
1156
+ {
1157
+ "epoch": 0.38451268357810414,
1158
+ "grad_norm": 2.4672086481418534,
1159
+ "learning_rate": 4.7315087539511225e-06,
1160
+ "loss": 0.4222088158130646,
1161
+ "step": 144,
1162
+ "token_acc": 0.8630399107933044
1163
+ },
1164
+ {
1165
+ "epoch": 0.3871829105473965,
1166
+ "grad_norm": 2.479936039467969,
1167
+ "learning_rate": 4.7265138609418755e-06,
1168
+ "loss": 0.47112199664115906,
1169
+ "step": 145,
1170
+ "token_acc": 0.8412138223648071
1171
+ },
1172
+ {
1173
+ "epoch": 0.38985313751668893,
1174
+ "grad_norm": 2.6072887624292176,
1175
+ "learning_rate": 4.721475620392567e-06,
1176
+ "loss": 0.4519212543964386,
1177
+ "step": 146,
1178
+ "token_acc": 0.8470008969306946
1179
+ },
1180
+ {
1181
+ "epoch": 0.3925233644859813,
1182
+ "grad_norm": 2.429018446753939,
1183
+ "learning_rate": 4.716394130391666e-06,
1184
+ "loss": 0.4776603579521179,
1185
+ "step": 147,
1186
+ "token_acc": 0.8396811485290527
1187
+ },
1188
+ {
1189
+ "epoch": 0.3951935914552737,
1190
+ "grad_norm": 2.323688300416439,
1191
+ "learning_rate": 4.711269489869654e-06,
1192
+ "loss": 0.4410521686077118,
1193
+ "step": 148,
1194
+ "token_acc": 0.8526735901832581
1195
+ },
1196
+ {
1197
+ "epoch": 0.3978638184245661,
1198
+ "grad_norm": 2.5158272944750744,
1199
+ "learning_rate": 4.706101798597102e-06,
1200
+ "loss": 0.4635973572731018,
1201
+ "step": 149,
1202
+ "token_acc": 0.8436339497566223
1203
+ },
1204
+ {
1205
+ "epoch": 0.40053404539385845,
1206
+ "grad_norm": 2.4586073022743293,
1207
+ "learning_rate": 4.700891157182729e-06,
1208
+ "loss": 0.45162177085876465,
1209
+ "step": 150,
1210
+ "token_acc": 0.853174090385437
1211
+ },
1212
+ {
1213
+ "epoch": 0.4032042723631509,
1214
+ "grad_norm": 2.4694677352249554,
1215
+ "learning_rate": 4.6956376670714395e-06,
1216
+ "loss": 0.465873122215271,
1217
+ "step": 151,
1218
+ "token_acc": 0.8441933989524841
1219
+ },
1220
+ {
1221
+ "epoch": 0.40587449933244324,
1222
+ "grad_norm": 2.521035498787654,
1223
+ "learning_rate": 4.690341430542351e-06,
1224
+ "loss": 0.4403953552246094,
1225
+ "step": 152,
1226
+ "token_acc": 0.851689875125885
1227
+ },
1228
+ {
1229
+ "epoch": 0.40854472630173566,
1230
+ "grad_norm": 2.282782183628756,
1231
+ "learning_rate": 4.685002550706803e-06,
1232
+ "loss": 0.3890649676322937,
1233
+ "step": 153,
1234
+ "token_acc": 0.8681288361549377
1235
+ },
1236
+ {
1237
+ "epoch": 0.411214953271028,
1238
+ "grad_norm": 2.7937216143349084,
1239
+ "learning_rate": 4.679621131506347e-06,
1240
+ "loss": 0.48725152015686035,
1241
+ "step": 154,
1242
+ "token_acc": 0.8374608159065247
1243
+ },
1244
+ {
1245
+ "epoch": 0.41388518024032045,
1246
+ "grad_norm": 2.663143001243766,
1247
+ "learning_rate": 4.674197277710727e-06,
1248
+ "loss": 0.5070767402648926,
1249
+ "step": 155,
1250
+ "token_acc": 0.8333563208580017
1251
+ },
1252
+ {
1253
+ "epoch": 0.4165554072096128,
1254
+ "grad_norm": 2.4996947846812594,
1255
+ "learning_rate": 4.668731094915835e-06,
1256
+ "loss": 0.4651419520378113,
1257
+ "step": 156,
1258
+ "token_acc": 0.8445397019386292
1259
+ },
1260
+ {
1261
+ "epoch": 0.4192256341789052,
1262
+ "grad_norm": 2.457518562084891,
1263
+ "learning_rate": 4.66322268954166e-06,
1264
+ "loss": 0.4390435218811035,
1265
+ "step": 157,
1266
+ "token_acc": 0.8504458069801331
1267
+ },
1268
+ {
1269
+ "epoch": 0.4218958611481976,
1270
+ "grad_norm": 2.5244443152780476,
1271
+ "learning_rate": 4.657672168830211e-06,
1272
+ "loss": 0.4770355820655823,
1273
+ "step": 158,
1274
+ "token_acc": 0.8391281962394714
1275
+ },
1276
+ {
1277
+ "epoch": 0.42456608811748997,
1278
+ "grad_norm": 2.5869289528229644,
1279
+ "learning_rate": 4.652079640843434e-06,
1280
+ "loss": 0.4601481854915619,
1281
+ "step": 159,
1282
+ "token_acc": 0.8448412418365479
1283
+ },
1284
+ {
1285
+ "epoch": 0.4272363150867824,
1286
+ "grad_norm": 2.5726889048577988,
1287
+ "learning_rate": 4.646445214461105e-06,
1288
+ "loss": 0.4462675452232361,
1289
+ "step": 160,
1290
+ "token_acc": 0.8541839122772217
1291
+ },
1292
+ {
1293
+ "epoch": 0.42990654205607476,
1294
+ "grad_norm": 2.57624818335164,
1295
+ "learning_rate": 4.6407689993787105e-06,
1296
+ "loss": 0.4376230239868164,
1297
+ "step": 161,
1298
+ "token_acc": 0.8541486263275146
1299
+ },
1300
+ {
1301
+ "epoch": 0.4325767690253672,
1302
+ "grad_norm": 2.4689486034810617,
1303
+ "learning_rate": 4.635051106105316e-06,
1304
+ "loss": 0.4593527317047119,
1305
+ "step": 162,
1306
+ "token_acc": 0.8511290550231934
1307
+ },
1308
+ {
1309
+ "epoch": 0.43524699599465955,
1310
+ "grad_norm": 2.4315313732311314,
1311
+ "learning_rate": 4.629291645961407e-06,
1312
+ "loss": 0.422754168510437,
1313
+ "step": 163,
1314
+ "token_acc": 0.8603886961936951
1315
+ },
1316
+ {
1317
+ "epoch": 0.4379172229639519,
1318
+ "grad_norm": 2.6835556622372434,
1319
+ "learning_rate": 4.623490731076728e-06,
1320
+ "loss": 0.40657132863998413,
1321
+ "step": 164,
1322
+ "token_acc": 0.8609955310821533
1323
+ },
1324
+ {
1325
+ "epoch": 0.44058744993324434,
1326
+ "grad_norm": 2.487085585134308,
1327
+ "learning_rate": 4.617648474388097e-06,
1328
+ "loss": 0.4761599004268646,
1329
+ "step": 165,
1330
+ "token_acc": 0.8410378098487854
1331
+ },
1332
+ {
1333
+ "epoch": 0.4432576769025367,
1334
+ "grad_norm": 2.7632880655750562,
1335
+ "learning_rate": 4.6117649896372055e-06,
1336
+ "loss": 0.47588837146759033,
1337
+ "step": 166,
1338
+ "token_acc": 0.8406272530555725
1339
+ },
1340
+ {
1341
+ "epoch": 0.4459279038718291,
1342
+ "grad_norm": 2.5396112959535517,
1343
+ "learning_rate": 4.605840391368409e-06,
1344
+ "loss": 0.45352819561958313,
1345
+ "step": 167,
1346
+ "token_acc": 0.8428268432617188
1347
+ },
1348
+ {
1349
+ "epoch": 0.4485981308411215,
1350
+ "grad_norm": 2.4726513449657554,
1351
+ "learning_rate": 4.59987479492649e-06,
1352
+ "loss": 0.41487815976142883,
1353
+ "step": 168,
1354
+ "token_acc": 0.859792947769165
1355
+ },
1356
+ {
1357
+ "epoch": 0.4512683578104139,
1358
+ "grad_norm": 2.5559580236334747,
1359
+ "learning_rate": 4.59386831645442e-06,
1360
+ "loss": 0.44197559356689453,
1361
+ "step": 169,
1362
+ "token_acc": 0.8479768633842468
1363
+ },
1364
+ {
1365
+ "epoch": 0.4539385847797063,
1366
+ "grad_norm": 2.360886901192167,
1367
+ "learning_rate": 4.587821072891089e-06,
1368
+ "loss": 0.4298216700553894,
1369
+ "step": 170,
1370
+ "token_acc": 0.8545623421669006
1371
+ },
1372
+ {
1373
+ "epoch": 0.45660881174899864,
1374
+ "grad_norm": 2.5892086201316165,
1375
+ "learning_rate": 4.58173318196904e-06,
1376
+ "loss": 0.4283745288848877,
1377
+ "step": 171,
1378
+ "token_acc": 0.8581973314285278
1379
+ },
1380
+ {
1381
+ "epoch": 0.45927903871829107,
1382
+ "grad_norm": 2.564115376922902,
1383
+ "learning_rate": 4.5756047622121665e-06,
1384
+ "loss": 0.4546971917152405,
1385
+ "step": 172,
1386
+ "token_acc": 0.8476163744926453
1387
+ },
1388
+ {
1389
+ "epoch": 0.46194926568758343,
1390
+ "grad_norm": 2.615054030097829,
1391
+ "learning_rate": 4.569435932933412e-06,
1392
+ "loss": 0.4751259684562683,
1393
+ "step": 173,
1394
+ "token_acc": 0.8419067859649658
1395
+ },
1396
+ {
1397
+ "epoch": 0.46461949265687585,
1398
+ "grad_norm": 2.5468201088177516,
1399
+ "learning_rate": 4.563226814232444e-06,
1400
+ "loss": 0.45504915714263916,
1401
+ "step": 174,
1402
+ "token_acc": 0.8453890681266785
1403
+ },
1404
+ {
1405
+ "epoch": 0.4672897196261682,
1406
+ "grad_norm": 2.3970157615320016,
1407
+ "learning_rate": 4.556977526993316e-06,
1408
+ "loss": 0.48890262842178345,
1409
+ "step": 175,
1410
+ "token_acc": 0.8347364068031311
1411
+ },
1412
+ {
1413
+ "epoch": 0.4699599465954606,
1414
+ "grad_norm": 2.501270938480645,
1415
+ "learning_rate": 4.550688192882115e-06,
1416
+ "loss": 0.40380796790122986,
1417
+ "step": 176,
1418
+ "token_acc": 0.8650723099708557
1419
+ },
1420
+ {
1421
+ "epoch": 0.472630173564753,
1422
+ "grad_norm": 2.446920292551538,
1423
+ "learning_rate": 4.544358934344593e-06,
1424
+ "loss": 0.44594672322273254,
1425
+ "step": 177,
1426
+ "token_acc": 0.8508905172348022
1427
+ },
1428
+ {
1429
+ "epoch": 0.4753004005340454,
1430
+ "grad_norm": 2.4755096838013255,
1431
+ "learning_rate": 4.53798987460378e-06,
1432
+ "loss": 0.4555642008781433,
1433
+ "step": 178,
1434
+ "token_acc": 0.8454092741012573
1435
+ },
1436
+ {
1437
+ "epoch": 0.4779706275033378,
1438
+ "grad_norm": 2.4327301018702223,
1439
+ "learning_rate": 4.531581137657591e-06,
1440
+ "loss": 0.4370790719985962,
1441
+ "step": 179,
1442
+ "token_acc": 0.8532300591468811
1443
+ },
1444
+ {
1445
+ "epoch": 0.48064085447263016,
1446
+ "grad_norm": 2.47256487143946,
1447
+ "learning_rate": 4.525132848276405e-06,
1448
+ "loss": 0.44074761867523193,
1449
+ "step": 180,
1450
+ "token_acc": 0.8526509404182434
1451
+ },
1452
+ {
1453
+ "epoch": 0.4833110814419226,
1454
+ "grad_norm": 2.429133920036761,
1455
+ "learning_rate": 4.518645132000643e-06,
1456
+ "loss": 0.43956151604652405,
1457
+ "step": 181,
1458
+ "token_acc": 0.8535059690475464
1459
+ },
1460
+ {
1461
+ "epoch": 0.48598130841121495,
1462
+ "grad_norm": 2.356679604976614,
1463
+ "learning_rate": 4.512118115138315e-06,
1464
+ "loss": 0.40330106019973755,
1465
+ "step": 182,
1466
+ "token_acc": 0.8588146567344666
1467
+ },
1468
+ {
1469
+ "epoch": 0.4886515353805073,
1470
+ "grad_norm": 2.524847566547435,
1471
+ "learning_rate": 4.5055519247625696e-06,
1472
+ "loss": 0.4202161729335785,
1473
+ "step": 183,
1474
+ "token_acc": 0.8603784441947937
1475
+ },
1476
+ {
1477
+ "epoch": 0.49132176234979974,
1478
+ "grad_norm": 2.5426107701623146,
1479
+ "learning_rate": 4.498946688709216e-06,
1480
+ "loss": 0.46760302782058716,
1481
+ "step": 184,
1482
+ "token_acc": 0.8443537354469299
1483
+ },
1484
+ {
1485
+ "epoch": 0.4939919893190921,
1486
+ "grad_norm": 2.4227279278938014,
1487
+ "learning_rate": 4.4923025355742356e-06,
1488
+ "loss": 0.41832929849624634,
1489
+ "step": 185,
1490
+ "token_acc": 0.8571034073829651
1491
+ },
1492
+ {
1493
+ "epoch": 0.49666221628838453,
1494
+ "grad_norm": 2.439691805120163,
1495
+ "learning_rate": 4.485619594711278e-06,
1496
+ "loss": 0.4662773609161377,
1497
+ "step": 186,
1498
+ "token_acc": 0.8421644568443298
1499
+ },
1500
+ {
1501
+ "epoch": 0.4993324432576769,
1502
+ "grad_norm": 2.5728685504428244,
1503
+ "learning_rate": 4.478897996229142e-06,
1504
+ "loss": 0.4209333062171936,
1505
+ "step": 187,
1506
+ "token_acc": 0.8550014495849609
1507
+ },
1508
+ {
1509
+ "epoch": 0.5020026702269693,
1510
+ "grad_norm": 2.6472811903159155,
1511
+ "learning_rate": 4.4721378709892475e-06,
1512
+ "loss": 0.4457632303237915,
1513
+ "step": 188,
1514
+ "token_acc": 0.8514215350151062
1515
+ },
1516
+ {
1517
+ "epoch": 0.5046728971962616,
1518
+ "grad_norm": 2.5443799154697864,
1519
+ "learning_rate": 4.46533935060308e-06,
1520
+ "loss": 0.42790117859840393,
1521
+ "step": 189,
1522
+ "token_acc": 0.8522346615791321
1523
+ },
1524
+ {
1525
+ "epoch": 0.507343124165554,
1526
+ "grad_norm": 2.420932052293168,
1527
+ "learning_rate": 4.4585025674296315e-06,
1528
+ "loss": 0.4350992441177368,
1529
+ "step": 190,
1530
+ "token_acc": 0.8564444184303284
1531
+ },
1532
+ {
1533
+ "epoch": 0.5100133511348465,
1534
+ "grad_norm": 2.4726361056841397,
1535
+ "learning_rate": 4.45162765457283e-06,
1536
+ "loss": 0.4694499671459198,
1537
+ "step": 191,
1538
+ "token_acc": 0.8431693315505981
1539
+ },
1540
+ {
1541
+ "epoch": 0.5126835781041389,
1542
+ "grad_norm": 2.3467379644019046,
1543
+ "learning_rate": 4.444714745878936e-06,
1544
+ "loss": 0.4131624698638916,
1545
+ "step": 192,
1546
+ "token_acc": 0.8589171171188354
1547
+ },
1548
+ {
1549
+ "epoch": 0.5153538050734312,
1550
+ "grad_norm": 2.4247211565913234,
1551
+ "learning_rate": 4.437763975933947e-06,
1552
+ "loss": 0.4394494891166687,
1553
+ "step": 193,
1554
+ "token_acc": 0.8501139283180237
1555
+ },
1556
+ {
1557
+ "epoch": 0.5180240320427236,
1558
+ "grad_norm": 2.3623843689004604,
1559
+ "learning_rate": 4.430775480060973e-06,
1560
+ "loss": 0.4677477777004242,
1561
+ "step": 194,
1562
+ "token_acc": 0.8495354056358337
1563
+ },
1564
+ {
1565
+ "epoch": 0.520694259012016,
1566
+ "grad_norm": 2.4965381528142165,
1567
+ "learning_rate": 4.4237493943176e-06,
1568
+ "loss": 0.42583468556404114,
1569
+ "step": 195,
1570
+ "token_acc": 0.8587666749954224
1571
+ },
1572
+ {
1573
+ "epoch": 0.5233644859813084,
1574
+ "grad_norm": 2.6887962364661764,
1575
+ "learning_rate": 4.416685855493246e-06,
1576
+ "loss": 0.47108498215675354,
1577
+ "step": 196,
1578
+ "token_acc": 0.8400888442993164
1579
+ },
1580
+ {
1581
+ "epoch": 0.5260347129506008,
1582
+ "grad_norm": 2.372747953430907,
1583
+ "learning_rate": 4.409585001106496e-06,
1584
+ "loss": 0.43690264225006104,
1585
+ "step": 197,
1586
+ "token_acc": 0.854030191898346
1587
+ },
1588
+ {
1589
+ "epoch": 0.5287049399198932,
1590
+ "grad_norm": 2.4817118032435723,
1591
+ "learning_rate": 4.4024469694024194e-06,
1592
+ "loss": 0.4165182113647461,
1593
+ "step": 198,
1594
+ "token_acc": 0.859004557132721
1595
+ },
1596
+ {
1597
+ "epoch": 0.5313751668891856,
1598
+ "grad_norm": 2.507828874274413,
1599
+ "learning_rate": 4.395271899349889e-06,
1600
+ "loss": 0.4124438762664795,
1601
+ "step": 199,
1602
+ "token_acc": 0.8650221824645996
1603
+ },
1604
+ {
1605
+ "epoch": 0.5340453938584779,
1606
+ "grad_norm": 2.255320653498364,
1607
+ "learning_rate": 4.388059930638865e-06,
1608
+ "loss": 0.3895377814769745,
1609
+ "step": 200,
1610
+ "token_acc": 0.8657457232475281
1611
+ },
1612
+ {
1613
+ "epoch": 0.5367156208277704,
1614
+ "grad_norm": 2.584958447427038,
1615
+ "learning_rate": 4.380811203677682e-06,
1616
+ "loss": 0.43062788248062134,
1617
+ "step": 201,
1618
+ "token_acc": 0.853506863117218
1619
+ },
1620
+ {
1621
+ "epoch": 0.5393858477970628,
1622
+ "grad_norm": 2.3942229000146305,
1623
+ "learning_rate": 4.373525859590313e-06,
1624
+ "loss": 0.417319655418396,
1625
+ "step": 202,
1626
+ "token_acc": 0.8587780594825745
1627
+ },
1628
+ {
1629
+ "epoch": 0.5420560747663551,
1630
+ "grad_norm": 2.391181613450999,
1631
+ "learning_rate": 4.3662040402136235e-06,
1632
+ "loss": 0.4113706052303314,
1633
+ "step": 203,
1634
+ "token_acc": 0.8585078120231628
1635
+ },
1636
+ {
1637
+ "epoch": 0.5447263017356475,
1638
+ "grad_norm": 2.348231297600076,
1639
+ "learning_rate": 4.358845888094607e-06,
1640
+ "loss": 0.44794076681137085,
1641
+ "step": 204,
1642
+ "token_acc": 0.8509410619735718
1643
+ },
1644
+ {
1645
+ "epoch": 0.5473965287049399,
1646
+ "grad_norm": 2.2773262743894542,
1647
+ "learning_rate": 4.351451546487613e-06,
1648
+ "loss": 0.4400603175163269,
1649
+ "step": 205,
1650
+ "token_acc": 0.852226197719574
1651
+ },
1652
+ {
1653
+ "epoch": 0.5500667556742324,
1654
+ "grad_norm": 2.3054376038504483,
1655
+ "learning_rate": 4.3440211593515556e-06,
1656
+ "loss": 0.4051324725151062,
1657
+ "step": 206,
1658
+ "token_acc": 0.8594557046890259
1659
+ },
1660
+ {
1661
+ "epoch": 0.5527369826435247,
1662
+ "grad_norm": 2.320714021396527,
1663
+ "learning_rate": 4.336554871347114e-06,
1664
+ "loss": 0.43094950914382935,
1665
+ "step": 207,
1666
+ "token_acc": 0.8550279140472412
1667
+ },
1668
+ {
1669
+ "epoch": 0.5554072096128171,
1670
+ "grad_norm": 2.281043501837322,
1671
+ "learning_rate": 4.32905282783391e-06,
1672
+ "loss": 0.46687984466552734,
1673
+ "step": 208,
1674
+ "token_acc": 0.8438752889633179
1675
+ },
1676
+ {
1677
+ "epoch": 0.5580774365821095,
1678
+ "grad_norm": 2.543555920373721,
1679
+ "learning_rate": 4.321515174867686e-06,
1680
+ "loss": 0.4430418908596039,
1681
+ "step": 209,
1682
+ "token_acc": 0.8470456600189209
1683
+ },
1684
+ {
1685
+ "epoch": 0.5607476635514018,
1686
+ "grad_norm": 2.3253704693626163,
1687
+ "learning_rate": 4.313942059197457e-06,
1688
+ "loss": 0.42164865136146545,
1689
+ "step": 210,
1690
+ "token_acc": 0.8623253703117371
1691
+ },
1692
+ {
1693
+ "epoch": 0.5634178905206942,
1694
+ "grad_norm": 2.382653131073417,
1695
+ "learning_rate": 4.306333628262652e-06,
1696
+ "loss": 0.431625634431839,
1697
+ "step": 211,
1698
+ "token_acc": 0.8514564633369446
1699
+ },
1700
+ {
1701
+ "epoch": 0.5660881174899867,
1702
+ "grad_norm": 2.202869592257826,
1703
+ "learning_rate": 4.298690030190247e-06,
1704
+ "loss": 0.4085538387298584,
1705
+ "step": 212,
1706
+ "token_acc": 0.8645986318588257
1707
+ },
1708
+ {
1709
+ "epoch": 0.5687583444592791,
1710
+ "grad_norm": 2.098272031696689,
1711
+ "learning_rate": 4.291011413791879e-06,
1712
+ "loss": 0.3832152485847473,
1713
+ "step": 213,
1714
+ "token_acc": 0.8645978569984436
1715
+ },
1716
+ {
1717
+ "epoch": 0.5714285714285714,
1718
+ "grad_norm": 2.3570663067339903,
1719
+ "learning_rate": 4.283297928560951e-06,
1720
+ "loss": 0.43713682889938354,
1721
+ "step": 214,
1722
+ "token_acc": 0.8492448925971985
1723
+ },
1724
+ {
1725
+ "epoch": 0.5740987983978638,
1726
+ "grad_norm": 2.2838948247125765,
1727
+ "learning_rate": 4.275549724669719e-06,
1728
+ "loss": 0.41322723031044006,
1729
+ "step": 215,
1730
+ "token_acc": 0.8603949546813965
1731
+ },
1732
+ {
1733
+ "epoch": 0.5767690253671562,
1734
+ "grad_norm": 2.4673466482815263,
1735
+ "learning_rate": 4.267766952966369e-06,
1736
+ "loss": 0.4351772964000702,
1737
+ "step": 216,
1738
+ "token_acc": 0.8541877865791321
1739
+ },
1740
+ {
1741
+ "epoch": 0.5794392523364486,
1742
+ "grad_norm": 2.3009193382209263,
1743
+ "learning_rate": 4.259949764972083e-06,
1744
+ "loss": 0.43076395988464355,
1745
+ "step": 217,
1746
+ "token_acc": 0.8549311757087708
1747
+ },
1748
+ {
1749
+ "epoch": 0.582109479305741,
1750
+ "grad_norm": 2.4480528711998044,
1751
+ "learning_rate": 4.252098312878083e-06,
1752
+ "loss": 0.4582253694534302,
1753
+ "step": 218,
1754
+ "token_acc": 0.8471966981887817
1755
+ },
1756
+ {
1757
+ "epoch": 0.5847797062750334,
1758
+ "grad_norm": 2.4576190070629633,
1759
+ "learning_rate": 4.244212749542675e-06,
1760
+ "loss": 0.48930877447128296,
1761
+ "step": 219,
1762
+ "token_acc": 0.8384159207344055
1763
+ },
1764
+ {
1765
+ "epoch": 0.5874499332443258,
1766
+ "grad_norm": 2.19337263006742,
1767
+ "learning_rate": 4.236293228488267e-06,
1768
+ "loss": 0.40265780687332153,
1769
+ "step": 220,
1770
+ "token_acc": 0.863872230052948
1771
+ },
1772
+ {
1773
+ "epoch": 0.5901201602136181,
1774
+ "grad_norm": 2.279450532416618,
1775
+ "learning_rate": 4.228339903898387e-06,
1776
+ "loss": 0.4493134021759033,
1777
+ "step": 221,
1778
+ "token_acc": 0.8475393652915955
1779
+ },
1780
+ {
1781
+ "epoch": 0.5927903871829105,
1782
+ "grad_norm": 2.3966173786182035,
1783
+ "learning_rate": 4.220352930614672e-06,
1784
+ "loss": 0.4592990279197693,
1785
+ "step": 222,
1786
+ "token_acc": 0.8495376706123352
1787
+ },
1788
+ {
1789
+ "epoch": 0.595460614152203,
1790
+ "grad_norm": 2.314005380261546,
1791
+ "learning_rate": 4.212332464133862e-06,
1792
+ "loss": 0.45050233602523804,
1793
+ "step": 223,
1794
+ "token_acc": 0.846325159072876
1795
+ },
1796
+ {
1797
+ "epoch": 0.5981308411214953,
1798
+ "grad_norm": 2.5246563012662557,
1799
+ "learning_rate": 4.204278660604767e-06,
1800
+ "loss": 0.4538397789001465,
1801
+ "step": 224,
1802
+ "token_acc": 0.8436514735221863
1803
+ },
1804
+ {
1805
+ "epoch": 0.6008010680907877,
1806
+ "grad_norm": 2.472821070699973,
1807
+ "learning_rate": 4.196191676825232e-06,
1808
+ "loss": 0.4549878239631653,
1809
+ "step": 225,
1810
+ "token_acc": 0.8476305603981018
1811
+ },
1812
+ {
1813
+ "epoch": 0.6034712950600801,
1814
+ "grad_norm": 2.4203904830697804,
1815
+ "learning_rate": 4.1880716702390764e-06,
1816
+ "loss": 0.4366474151611328,
1817
+ "step": 226,
1818
+ "token_acc": 0.850104033946991
1819
+ },
1820
+ {
1821
+ "epoch": 0.6061415220293725,
1822
+ "grad_norm": 2.502976930466313,
1823
+ "learning_rate": 4.17991879893304e-06,
1824
+ "loss": 0.44235122203826904,
1825
+ "step": 227,
1826
+ "token_acc": 0.8512928485870361
1827
+ },
1828
+ {
1829
+ "epoch": 0.6088117489986649,
1830
+ "grad_norm": 2.3871736003541275,
1831
+ "learning_rate": 4.171733221633695e-06,
1832
+ "loss": 0.4302646517753601,
1833
+ "step": 228,
1834
+ "token_acc": 0.8582147359848022
1835
+ },
1836
+ {
1837
+ "epoch": 0.6114819759679573,
1838
+ "grad_norm": 2.366622725861706,
1839
+ "learning_rate": 4.163515097704361e-06,
1840
+ "loss": 0.4315718710422516,
1841
+ "step": 229,
1842
+ "token_acc": 0.8561064004898071
1843
+ },
1844
+ {
1845
+ "epoch": 0.6141522029372497,
1846
+ "grad_norm": 2.4976147966031688,
1847
+ "learning_rate": 4.155264587142002e-06,
1848
+ "loss": 0.46325528621673584,
1849
+ "step": 230,
1850
+ "token_acc": 0.8459770083427429
1851
+ },
1852
+ {
1853
+ "epoch": 0.616822429906542,
1854
+ "grad_norm": 2.4348282920473863,
1855
+ "learning_rate": 4.146981850574107e-06,
1856
+ "loss": 0.40404918789863586,
1857
+ "step": 231,
1858
+ "token_acc": 0.8660968542098999
1859
+ },
1860
+ {
1861
+ "epoch": 0.6194926568758344,
1862
+ "grad_norm": 2.5516342018934446,
1863
+ "learning_rate": 4.138667049255574e-06,
1864
+ "loss": 0.4561244249343872,
1865
+ "step": 232,
1866
+ "token_acc": 0.8451762199401855
1867
+ },
1868
+ {
1869
+ "epoch": 0.6221628838451269,
1870
+ "grad_norm": 2.3309188449817704,
1871
+ "learning_rate": 4.130320345065554e-06,
1872
+ "loss": 0.4312426447868347,
1873
+ "step": 233,
1874
+ "token_acc": 0.858094334602356
1875
+ },
1876
+ {
1877
+ "epoch": 0.6248331108144193,
1878
+ "grad_norm": 2.3988489647600932,
1879
+ "learning_rate": 4.121941900504316e-06,
1880
+ "loss": 0.4118894040584564,
1881
+ "step": 234,
1882
+ "token_acc": 0.8580255508422852
1883
+ },
1884
+ {
1885
+ "epoch": 0.6275033377837116,
1886
+ "grad_norm": 2.6071877106568437,
1887
+ "learning_rate": 4.1135318786900704e-06,
1888
+ "loss": 0.42171400785446167,
1889
+ "step": 235,
1890
+ "token_acc": 0.8522070050239563
1891
+ },
1892
+ {
1893
+ "epoch": 0.630173564753004,
1894
+ "grad_norm": 2.4148225457713832,
1895
+ "learning_rate": 4.105090443355801e-06,
1896
+ "loss": 0.400443434715271,
1897
+ "step": 236,
1898
+ "token_acc": 0.8602768182754517
1899
+ },
1900
+ {
1901
+ "epoch": 0.6328437917222964,
1902
+ "grad_norm": 2.3350081863756422,
1903
+ "learning_rate": 4.096617758846077e-06,
1904
+ "loss": 0.44139355421066284,
1905
+ "step": 237,
1906
+ "token_acc": 0.8529062867164612
1907
+ },
1908
+ {
1909
+ "epoch": 0.6355140186915887,
1910
+ "grad_norm": 2.1348772568141046,
1911
+ "learning_rate": 4.088113990113846e-06,
1912
+ "loss": 0.3878358006477356,
1913
+ "step": 238,
1914
+ "token_acc": 0.8694049715995789
1915
+ },
1916
+ {
1917
+ "epoch": 0.6381842456608812,
1918
+ "grad_norm": 2.17372202580671,
1919
+ "learning_rate": 4.079579302717234e-06,
1920
+ "loss": 0.3901534080505371,
1921
+ "step": 239,
1922
+ "token_acc": 0.8662952780723572
1923
+ },
1924
+ {
1925
+ "epoch": 0.6408544726301736,
1926
+ "grad_norm": 2.2153199516522726,
1927
+ "learning_rate": 4.071013862816311e-06,
1928
+ "loss": 0.4507509171962738,
1929
+ "step": 240,
1930
+ "token_acc": 0.8491714000701904
1931
+ },
1932
+ {
1933
+ "epoch": 0.6435246995994659,
1934
+ "grad_norm": 2.4108888803650137,
1935
+ "learning_rate": 4.062417837169865e-06,
1936
+ "loss": 0.3946835398674011,
1937
+ "step": 241,
1938
+ "token_acc": 0.8637107610702515
1939
+ },
1940
+ {
1941
+ "epoch": 0.6461949265687583,
1942
+ "grad_norm": 2.5578894134096033,
1943
+ "learning_rate": 4.0537913931321495e-06,
1944
+ "loss": 0.442746102809906,
1945
+ "step": 242,
1946
+ "token_acc": 0.8524382710456848
1947
+ },
1948
+ {
1949
+ "epoch": 0.6488651535380507,
1950
+ "grad_norm": 2.3216990414556036,
1951
+ "learning_rate": 4.045134698649625e-06,
1952
+ "loss": 0.44268563389778137,
1953
+ "step": 243,
1954
+ "token_acc": 0.8513710498809814
1955
+ },
1956
+ {
1957
+ "epoch": 0.6515353805073432,
1958
+ "grad_norm": 2.449649917138565,
1959
+ "learning_rate": 4.036447922257699e-06,
1960
+ "loss": 0.4419565200805664,
1961
+ "step": 244,
1962
+ "token_acc": 0.8472241759300232
1963
+ },
1964
+ {
1965
+ "epoch": 0.6542056074766355,
1966
+ "grad_norm": 2.3484505110123393,
1967
+ "learning_rate": 4.027731233077431e-06,
1968
+ "loss": 0.4158861041069031,
1969
+ "step": 245,
1970
+ "token_acc": 0.8598523139953613
1971
+ },
1972
+ {
1973
+ "epoch": 0.6568758344459279,
1974
+ "grad_norm": 2.4337665559940946,
1975
+ "learning_rate": 4.018984800812248e-06,
1976
+ "loss": 0.4734154939651489,
1977
+ "step": 246,
1978
+ "token_acc": 0.845433235168457
1979
+ },
1980
+ {
1981
+ "epoch": 0.6595460614152203,
1982
+ "grad_norm": 2.3257367075934487,
1983
+ "learning_rate": 4.010208795744639e-06,
1984
+ "loss": 0.3812839686870575,
1985
+ "step": 247,
1986
+ "token_acc": 0.8693907856941223
1987
+ },
1988
+ {
1989
+ "epoch": 0.6622162883845126,
1990
+ "grad_norm": 2.4378618622731327,
1991
+ "learning_rate": 4.001403388732842e-06,
1992
+ "loss": 0.39083486795425415,
1993
+ "step": 248,
1994
+ "token_acc": 0.8710182309150696
1995
+ },
1996
+ {
1997
+ "epoch": 0.664886515353805,
1998
+ "grad_norm": 2.293688311988354,
1999
+ "learning_rate": 3.992568751207513e-06,
2000
+ "loss": 0.412398099899292,
2001
+ "step": 249,
2002
+ "token_acc": 0.8590843081474304
2003
+ },
2004
+ {
2005
+ "epoch": 0.6675567423230975,
2006
+ "grad_norm": 2.41334223392958,
2007
+ "learning_rate": 3.983705055168391e-06,
2008
+ "loss": 0.44147831201553345,
2009
+ "step": 250,
2010
+ "token_acc": 0.8507301211357117
2011
+ },
2012
+ {
2013
+ "epoch": 0.6702269692923899,
2014
+ "grad_norm": 2.416713713955315,
2015
+ "learning_rate": 3.97481247318095e-06,
2016
+ "loss": 0.42483946681022644,
2017
+ "step": 251,
2018
+ "token_acc": 0.8535153865814209
2019
+ },
2020
+ {
2021
+ "epoch": 0.6728971962616822,
2022
+ "grad_norm": 2.175477724451994,
2023
+ "learning_rate": 3.965891178373038e-06,
2024
+ "loss": 0.4062314033508301,
2025
+ "step": 252,
2026
+ "token_acc": 0.8626396059989929
2027
+ },
2028
+ {
2029
+ "epoch": 0.6755674232309746,
2030
+ "grad_norm": 2.4472923322751057,
2031
+ "learning_rate": 3.956941344431508e-06,
2032
+ "loss": 0.4437641203403473,
2033
+ "step": 253,
2034
+ "token_acc": 0.8513161540031433
2035
+ },
2036
+ {
2037
+ "epoch": 0.678237650200267,
2038
+ "grad_norm": 2.3139123179572993,
2039
+ "learning_rate": 3.947963145598833e-06,
2040
+ "loss": 0.3942599296569824,
2041
+ "step": 254,
2042
+ "token_acc": 0.8642499446868896
2043
+ },
2044
+ {
2045
+ "epoch": 0.6809078771695594,
2046
+ "grad_norm": 2.1831072762922936,
2047
+ "learning_rate": 3.938956756669722e-06,
2048
+ "loss": 0.4110143780708313,
2049
+ "step": 255,
2050
+ "token_acc": 0.8636785745620728
2051
+ },
2052
+ {
2053
+ "epoch": 0.6835781041388518,
2054
+ "grad_norm": 2.162339235676344,
2055
+ "learning_rate": 3.929922352987702e-06,
2056
+ "loss": 0.38868942856788635,
2057
+ "step": 256,
2058
+ "token_acc": 0.8654695749282837
2059
+ },
2060
+ {
2061
+ "epoch": 0.6862483311081442,
2062
+ "grad_norm": 2.4992958153575735,
2063
+ "learning_rate": 3.920860110441723e-06,
2064
+ "loss": 0.4590440094470978,
2065
+ "step": 257,
2066
+ "token_acc": 0.8423796892166138
2067
+ },
2068
+ {
2069
+ "epoch": 0.6889185580774366,
2070
+ "grad_norm": 2.4388856080981998,
2071
+ "learning_rate": 3.911770205462717e-06,
2072
+ "loss": 0.41952669620513916,
2073
+ "step": 258,
2074
+ "token_acc": 0.857813835144043
2075
+ },
2076
+ {
2077
+ "epoch": 0.6915887850467289,
2078
+ "grad_norm": 2.428020451082309,
2079
+ "learning_rate": 3.902652815020175e-06,
2080
+ "loss": 0.39870864152908325,
2081
+ "step": 259,
2082
+ "token_acc": 0.8620949387550354
2083
+ },
2084
+ {
2085
+ "epoch": 0.6942590120160214,
2086
+ "grad_norm": 2.5221676869907887,
2087
+ "learning_rate": 3.8935081166186935e-06,
2088
+ "loss": 0.451211541891098,
2089
+ "step": 260,
2090
+ "token_acc": 0.8464188575744629
2091
+ },
2092
+ {
2093
+ "epoch": 0.6969292389853138,
2094
+ "grad_norm": 2.4290886620438825,
2095
+ "learning_rate": 3.884336288294523e-06,
2096
+ "loss": 0.44460415840148926,
2097
+ "step": 261,
2098
+ "token_acc": 0.8528732061386108
2099
+ },
2100
+ {
2101
+ "epoch": 0.6995994659546061,
2102
+ "grad_norm": 2.257525790210845,
2103
+ "learning_rate": 3.875137508612104e-06,
2104
+ "loss": 0.42338326573371887,
2105
+ "step": 262,
2106
+ "token_acc": 0.8576461672782898
2107
+ },
2108
+ {
2109
+ "epoch": 0.7022696929238985,
2110
+ "grad_norm": 2.2280729896884566,
2111
+ "learning_rate": 3.865911956660581e-06,
2112
+ "loss": 0.4038681089878082,
2113
+ "step": 263,
2114
+ "token_acc": 0.864154040813446
2115
+ },
2116
+ {
2117
+ "epoch": 0.7049399198931909,
2118
+ "grad_norm": 2.602304522948634,
2119
+ "learning_rate": 3.856659812050328e-06,
2120
+ "loss": 0.46356073021888733,
2121
+ "step": 264,
2122
+ "token_acc": 0.8445596098899841
2123
+ },
2124
+ {
2125
+ "epoch": 0.7076101468624834,
2126
+ "grad_norm": 2.4936788661987146,
2127
+ "learning_rate": 3.847381254909445e-06,
2128
+ "loss": 0.4358750879764557,
2129
+ "step": 265,
2130
+ "token_acc": 0.8509325385093689
2131
+ },
2132
+ {
2133
+ "epoch": 0.7102803738317757,
2134
+ "grad_norm": 2.4138364480205867,
2135
+ "learning_rate": 3.838076465880248e-06,
2136
+ "loss": 0.4416617751121521,
2137
+ "step": 266,
2138
+ "token_acc": 0.8505957722663879
2139
+ },
2140
+ {
2141
+ "epoch": 0.7129506008010681,
2142
+ "grad_norm": 2.3708422462528853,
2143
+ "learning_rate": 3.828745626115763e-06,
2144
+ "loss": 0.4336203932762146,
2145
+ "step": 267,
2146
+ "token_acc": 0.8537970185279846
2147
+ },
2148
+ {
2149
+ "epoch": 0.7156208277703605,
2150
+ "grad_norm": 2.326428711260563,
2151
+ "learning_rate": 3.819388917276186e-06,
2152
+ "loss": 0.4520704448223114,
2153
+ "step": 268,
2154
+ "token_acc": 0.8481835722923279
2155
+ },
2156
+ {
2157
+ "epoch": 0.7182910547396528,
2158
+ "grad_norm": 2.3748087865615557,
2159
+ "learning_rate": 3.8100065215253563e-06,
2160
+ "loss": 0.4207550585269928,
2161
+ "step": 269,
2162
+ "token_acc": 0.8562021255493164
2163
+ },
2164
+ {
2165
+ "epoch": 0.7209612817089452,
2166
+ "grad_norm": 2.2857308148176188,
2167
+ "learning_rate": 3.8005986215272056e-06,
2168
+ "loss": 0.45390063524246216,
2169
+ "step": 270,
2170
+ "token_acc": 0.8494418859481812
2171
+ },
2172
+ {
2173
+ "epoch": 0.7236315086782377,
2174
+ "grad_norm": 2.4163944702120403,
2175
+ "learning_rate": 3.7911654004422025e-06,
2176
+ "loss": 0.4408589005470276,
2177
+ "step": 271,
2178
+ "token_acc": 0.846950352191925
2179
+ },
2180
+ {
2181
+ "epoch": 0.7263017356475301,
2182
+ "grad_norm": 2.5493659370017996,
2183
+ "learning_rate": 3.7817070419237866e-06,
2184
+ "loss": 0.4724009931087494,
2185
+ "step": 272,
2186
+ "token_acc": 0.8386212587356567
2187
+ },
2188
+ {
2189
+ "epoch": 0.7289719626168224,
2190
+ "grad_norm": 2.4489095727015036,
2191
+ "learning_rate": 3.7722237301147937e-06,
2192
+ "loss": 0.45564085245132446,
2193
+ "step": 273,
2194
+ "token_acc": 0.847298264503479
2195
+ },
2196
+ {
2197
+ "epoch": 0.7316421895861148,
2198
+ "grad_norm": 2.3069057011013747,
2199
+ "learning_rate": 3.7627156496438686e-06,
2200
+ "loss": 0.4171178340911865,
2201
+ "step": 274,
2202
+ "token_acc": 0.8601161241531372
2203
+ },
2204
+ {
2205
+ "epoch": 0.7343124165554072,
2206
+ "grad_norm": 2.331561039760162,
2207
+ "learning_rate": 3.753182985621873e-06,
2208
+ "loss": 0.44008728861808777,
2209
+ "step": 275,
2210
+ "token_acc": 0.8578534126281738
2211
+ },
2212
+ {
2213
+ "epoch": 0.7369826435246996,
2214
+ "grad_norm": 2.360572815409469,
2215
+ "learning_rate": 3.7436259236382797e-06,
2216
+ "loss": 0.4406012296676636,
2217
+ "step": 276,
2218
+ "token_acc": 0.8510209321975708
2219
+ },
2220
+ {
2221
+ "epoch": 0.739652870493992,
2222
+ "grad_norm": 2.2084665729308623,
2223
+ "learning_rate": 3.7340446497575632e-06,
2224
+ "loss": 0.4022600054740906,
2225
+ "step": 277,
2226
+ "token_acc": 0.8659807443618774
2227
+ },
2228
+ {
2229
+ "epoch": 0.7423230974632844,
2230
+ "grad_norm": 2.199643772359588,
2231
+ "learning_rate": 3.7244393505155713e-06,
2232
+ "loss": 0.44380104541778564,
2233
+ "step": 278,
2234
+ "token_acc": 0.8511156439781189
2235
+ },
2236
+ {
2237
+ "epoch": 0.7449933244325768,
2238
+ "grad_norm": 2.2245211565125547,
2239
+ "learning_rate": 3.7148102129158973e-06,
2240
+ "loss": 0.389880895614624,
2241
+ "step": 279,
2242
+ "token_acc": 0.8672800660133362
2243
+ },
2244
+ {
2245
+ "epoch": 0.7476635514018691,
2246
+ "grad_norm": 2.4639078888113057,
2247
+ "learning_rate": 3.7051574244262412e-06,
2248
+ "loss": 0.46051520109176636,
2249
+ "step": 280,
2250
+ "token_acc": 0.8465862274169922
2251
+ },
2252
+ {
2253
+ "epoch": 0.7503337783711616,
2254
+ "grad_norm": 2.3625708379846,
2255
+ "learning_rate": 3.695481172974753e-06,
2256
+ "loss": 0.40404459834098816,
2257
+ "step": 281,
2258
+ "token_acc": 0.8619518876075745
2259
+ },
2260
+ {
2261
+ "epoch": 0.753004005340454,
2262
+ "grad_norm": 2.258533592272975,
2263
+ "learning_rate": 3.6857816469463806e-06,
2264
+ "loss": 0.4102287292480469,
2265
+ "step": 282,
2266
+ "token_acc": 0.854707658290863
2267
+ },
2268
+ {
2269
+ "epoch": 0.7556742323097463,
2270
+ "grad_norm": 2.320019531055125,
2271
+ "learning_rate": 3.6760590351792013e-06,
2272
+ "loss": 0.4418216347694397,
2273
+ "step": 283,
2274
+ "token_acc": 0.8489851355552673
2275
+ },
2276
+ {
2277
+ "epoch": 0.7583444592790387,
2278
+ "grad_norm": 2.239456098431946,
2279
+ "learning_rate": 3.6663135269607413e-06,
2280
+ "loss": 0.43022388219833374,
2281
+ "step": 284,
2282
+ "token_acc": 0.8563932776451111
2283
+ },
2284
+ {
2285
+ "epoch": 0.7610146862483311,
2286
+ "grad_norm": 2.2191407186090757,
2287
+ "learning_rate": 3.6565453120242943e-06,
2288
+ "loss": 0.43869519233703613,
2289
+ "step": 285,
2290
+ "token_acc": 0.8506224155426025
2291
+ },
2292
+ {
2293
+ "epoch": 0.7636849132176236,
2294
+ "grad_norm": 2.412667898900189,
2295
+ "learning_rate": 3.6467545805452266e-06,
2296
+ "loss": 0.43426942825317383,
2297
+ "step": 286,
2298
+ "token_acc": 0.8564399480819702
2299
+ },
2300
+ {
2301
+ "epoch": 0.7663551401869159,
2302
+ "grad_norm": 2.314528118131923,
2303
+ "learning_rate": 3.6369415231372734e-06,
2304
+ "loss": 0.45144137740135193,
2305
+ "step": 287,
2306
+ "token_acc": 0.8505134582519531
2307
+ },
2308
+ {
2309
+ "epoch": 0.7690253671562083,
2310
+ "grad_norm": 2.407840522509518,
2311
+ "learning_rate": 3.6271063308488298e-06,
2312
+ "loss": 0.4491138756275177,
2313
+ "step": 288,
2314
+ "token_acc": 0.8491296172142029
2315
+ },
2316
+ {
2317
+ "epoch": 0.7716955941255007,
2318
+ "grad_norm": 2.2913112999410963,
2319
+ "learning_rate": 3.6172491951592305e-06,
2320
+ "loss": 0.45237940549850464,
2321
+ "step": 289,
2322
+ "token_acc": 0.8555259704589844
2323
+ },
2324
+ {
2325
+ "epoch": 0.774365821094793,
2326
+ "grad_norm": 2.208007129471344,
2327
+ "learning_rate": 3.6073703079750204e-06,
2328
+ "loss": 0.3926496207714081,
2329
+ "step": 290,
2330
+ "token_acc": 0.8631168603897095
2331
+ },
2332
+ {
2333
+ "epoch": 0.7770360480640854,
2334
+ "grad_norm": 2.274791194303811,
2335
+ "learning_rate": 3.597469861626221e-06,
2336
+ "loss": 0.45420050621032715,
2337
+ "step": 291,
2338
+ "token_acc": 0.8452543020248413
2339
+ },
2340
+ {
2341
+ "epoch": 0.7797062750333779,
2342
+ "grad_norm": 2.4766163247000077,
2343
+ "learning_rate": 3.5875480488625847e-06,
2344
+ "loss": 0.45179054141044617,
2345
+ "step": 292,
2346
+ "token_acc": 0.8442568778991699
2347
+ },
2348
+ {
2349
+ "epoch": 0.7823765020026703,
2350
+ "grad_norm": 2.1274576066285142,
2351
+ "learning_rate": 3.5776050628498415e-06,
2352
+ "loss": 0.40227341651916504,
2353
+ "step": 293,
2354
+ "token_acc": 0.8601976037025452
2355
+ },
2356
+ {
2357
+ "epoch": 0.7850467289719626,
2358
+ "grad_norm": 2.3221231731554046,
2359
+ "learning_rate": 3.5676410971659404e-06,
2360
+ "loss": 0.43593835830688477,
2361
+ "step": 294,
2362
+ "token_acc": 0.8535004258155823
2363
+ },
2364
+ {
2365
+ "epoch": 0.787716955941255,
2366
+ "grad_norm": 2.2281623143084865,
2367
+ "learning_rate": 3.5576563457972767e-06,
2368
+ "loss": 0.4257349967956543,
2369
+ "step": 295,
2370
+ "token_acc": 0.8528762459754944
2371
+ },
2372
+ {
2373
+ "epoch": 0.7903871829105474,
2374
+ "grad_norm": 2.4744075239021988,
2375
+ "learning_rate": 3.547651003134921e-06,
2376
+ "loss": 0.43228963017463684,
2377
+ "step": 296,
2378
+ "token_acc": 0.8521751165390015
2379
+ },
2380
+ {
2381
+ "epoch": 0.7930574098798397,
2382
+ "grad_norm": 2.173172271677684,
2383
+ "learning_rate": 3.53762526397083e-06,
2384
+ "loss": 0.40511733293533325,
2385
+ "step": 297,
2386
+ "token_acc": 0.8658920526504517
2387
+ },
2388
+ {
2389
+ "epoch": 0.7957276368491322,
2390
+ "grad_norm": 2.348393916101237,
2391
+ "learning_rate": 3.527579323494055e-06,
2392
+ "loss": 0.3884103298187256,
2393
+ "step": 298,
2394
+ "token_acc": 0.8676092624664307
2395
+ },
2396
+ {
2397
+ "epoch": 0.7983978638184246,
2398
+ "grad_norm": 2.2767444643885435,
2399
+ "learning_rate": 3.517513377286944e-06,
2400
+ "loss": 0.4461408257484436,
2401
+ "step": 299,
2402
+ "token_acc": 0.8518761396408081
2403
+ },
2404
+ {
2405
+ "epoch": 0.8010680907877169,
2406
+ "grad_norm": 2.2064345696345344,
2407
+ "learning_rate": 3.507427621321331e-06,
2408
+ "loss": 0.44151389598846436,
2409
+ "step": 300,
2410
+ "token_acc": 0.8526713252067566
2411
+ },
2412
+ {
2413
+ "epoch": 0.8037383177570093,
2414
+ "grad_norm": 2.3892638879691006,
2415
+ "learning_rate": 3.4973222519547246e-06,
2416
+ "loss": 0.4137862026691437,
2417
+ "step": 301,
2418
+ "token_acc": 0.8525737524032593
2419
+ },
2420
+ {
2421
+ "epoch": 0.8064085447263017,
2422
+ "grad_norm": 2.2363714712140976,
2423
+ "learning_rate": 3.4871974659264786e-06,
2424
+ "loss": 0.3928898572921753,
2425
+ "step": 302,
2426
+ "token_acc": 0.8654588460922241
2427
+ },
2428
+ {
2429
+ "epoch": 0.8090787716955942,
2430
+ "grad_norm": 2.10911416280479,
2431
+ "learning_rate": 3.4770534603539694e-06,
2432
+ "loss": 0.3800258934497833,
2433
+ "step": 303,
2434
+ "token_acc": 0.8674206137657166
2435
+ },
2436
+ {
2437
+ "epoch": 0.8117489986648865,
2438
+ "grad_norm": 2.1184863005845873,
2439
+ "learning_rate": 3.466890432728754e-06,
2440
+ "loss": 0.36905455589294434,
2441
+ "step": 304,
2442
+ "token_acc": 0.8739654421806335
2443
+ },
2444
+ {
2445
+ "epoch": 0.8144192256341789,
2446
+ "grad_norm": 2.4093223917427697,
2447
+ "learning_rate": 3.4567085809127247e-06,
2448
+ "loss": 0.43884479999542236,
2449
+ "step": 305,
2450
+ "token_acc": 0.8516155481338501
2451
+ },
2452
+ {
2453
+ "epoch": 0.8170894526034713,
2454
+ "grad_norm": 2.153754763982819,
2455
+ "learning_rate": 3.446508103134259e-06,
2456
+ "loss": 0.42132729291915894,
2457
+ "step": 306,
2458
+ "token_acc": 0.8623113036155701
2459
+ },
2460
+ {
2461
+ "epoch": 0.8197596795727636,
2462
+ "grad_norm": 2.4180843979283098,
2463
+ "learning_rate": 3.4362891979843583e-06,
2464
+ "loss": 0.4459989070892334,
2465
+ "step": 307,
2466
+ "token_acc": 0.8531468510627747
2467
+ },
2468
+ {
2469
+ "epoch": 0.822429906542056,
2470
+ "grad_norm": 2.366487705733103,
2471
+ "learning_rate": 3.426052064412785e-06,
2472
+ "loss": 0.42301076650619507,
2473
+ "step": 308,
2474
+ "token_acc": 0.8568209409713745
2475
+ },
2476
+ {
2477
+ "epoch": 0.8251001335113485,
2478
+ "grad_norm": 2.2577952473760745,
2479
+ "learning_rate": 3.415796901724183e-06,
2480
+ "loss": 0.4184911251068115,
2481
+ "step": 309,
2482
+ "token_acc": 0.8600525856018066
2483
+ },
2484
+ {
2485
+ "epoch": 0.8277703604806409,
2486
+ "grad_norm": 2.272798495466072,
2487
+ "learning_rate": 3.4055239095742067e-06,
2488
+ "loss": 0.4150565266609192,
2489
+ "step": 310,
2490
+ "token_acc": 0.8560513257980347
2491
+ },
2492
+ {
2493
+ "epoch": 0.8304405874499332,
2494
+ "grad_norm": 2.307045625452628,
2495
+ "learning_rate": 3.3952332879656238e-06,
2496
+ "loss": 0.42295610904693604,
2497
+ "step": 311,
2498
+ "token_acc": 0.8568536639213562
2499
+ },
2500
+ {
2501
+ "epoch": 0.8331108144192256,
2502
+ "grad_norm": 2.356438561952695,
2503
+ "learning_rate": 3.3849252372444295e-06,
2504
+ "loss": 0.43763798475265503,
2505
+ "step": 312,
2506
+ "token_acc": 0.8552359938621521
2507
+ },
2508
+ {
2509
+ "epoch": 0.835781041388518,
2510
+ "grad_norm": 2.196991388696865,
2511
+ "learning_rate": 3.37459995809594e-06,
2512
+ "loss": 0.40753644704818726,
2513
+ "step": 313,
2514
+ "token_acc": 0.8627873659133911
2515
+ },
2516
+ {
2517
+ "epoch": 0.8384512683578104,
2518
+ "grad_norm": 2.3263172574950897,
2519
+ "learning_rate": 3.364257651540891e-06,
2520
+ "loss": 0.41269251704216003,
2521
+ "step": 314,
2522
+ "token_acc": 0.8560525178909302
2523
+ },
2524
+ {
2525
+ "epoch": 0.8411214953271028,
2526
+ "grad_norm": 2.350617973992072,
2527
+ "learning_rate": 3.35389851893152e-06,
2528
+ "loss": 0.4604400396347046,
2529
+ "step": 315,
2530
+ "token_acc": 0.8413700461387634
2531
+ },
2532
+ {
2533
+ "epoch": 0.8437917222963952,
2534
+ "grad_norm": 2.1150288161980373,
2535
+ "learning_rate": 3.343522761947646e-06,
2536
+ "loss": 0.35596567392349243,
2537
+ "step": 316,
2538
+ "token_acc": 0.8782225847244263
2539
+ },
2540
+ {
2541
+ "epoch": 0.8464619492656876,
2542
+ "grad_norm": 2.427998298148871,
2543
+ "learning_rate": 3.333130582592748e-06,
2544
+ "loss": 0.4479413330554962,
2545
+ "step": 317,
2546
+ "token_acc": 0.8485423922538757
2547
+ },
2548
+ {
2549
+ "epoch": 0.8491321762349799,
2550
+ "grad_norm": 2.3279398903568524,
2551
+ "learning_rate": 3.322722183190025e-06,
2552
+ "loss": 0.3884989619255066,
2553
+ "step": 318,
2554
+ "token_acc": 0.8613360524177551
2555
+ },
2556
+ {
2557
+ "epoch": 0.8518024032042724,
2558
+ "grad_norm": 2.2789108218993896,
2559
+ "learning_rate": 3.3122977663784643e-06,
2560
+ "loss": 0.40324780344963074,
2561
+ "step": 319,
2562
+ "token_acc": 0.8602093458175659
2563
+ },
2564
+ {
2565
+ "epoch": 0.8544726301735648,
2566
+ "grad_norm": 2.14017165974169,
2567
+ "learning_rate": 3.3018575351088894e-06,
2568
+ "loss": 0.4083625078201294,
2569
+ "step": 320,
2570
+ "token_acc": 0.8600194454193115
2571
+ },
2572
+ {
2573
+ "epoch": 0.8571428571428571,
2574
+ "grad_norm": 2.100990794809228,
2575
+ "learning_rate": 3.291401692640015e-06,
2576
+ "loss": 0.42288291454315186,
2577
+ "step": 321,
2578
+ "token_acc": 0.8547579050064087
2579
+ },
2580
+ {
2581
+ "epoch": 0.8598130841121495,
2582
+ "grad_norm": 2.23696027079152,
2583
+ "learning_rate": 3.280930442534486e-06,
2584
+ "loss": 0.4231698513031006,
2585
+ "step": 322,
2586
+ "token_acc": 0.8543514609336853
2587
+ },
2588
+ {
2589
+ "epoch": 0.8624833110814419,
2590
+ "grad_norm": 2.3727342029244367,
2591
+ "learning_rate": 3.2704439886549144e-06,
2592
+ "loss": 0.40619805455207825,
2593
+ "step": 323,
2594
+ "token_acc": 0.8601211309432983
2595
+ },
2596
+ {
2597
+ "epoch": 0.8651535380507344,
2598
+ "grad_norm": 2.2323974734091605,
2599
+ "learning_rate": 3.2599425351599136e-06,
2600
+ "loss": 0.4134262800216675,
2601
+ "step": 324,
2602
+ "token_acc": 0.8574932217597961
2603
+ },
2604
+ {
2605
+ "epoch": 0.8678237650200267,
2606
+ "grad_norm": 2.3308642001326976,
2607
+ "learning_rate": 3.249426286500118e-06,
2608
+ "loss": 0.4392201900482178,
2609
+ "step": 325,
2610
+ "token_acc": 0.8543046116828918
2611
+ },
2612
+ {
2613
+ "epoch": 0.8704939919893191,
2614
+ "grad_norm": 2.293651119927858,
2615
+ "learning_rate": 3.238895447414211e-06,
2616
+ "loss": 0.4126027822494507,
2617
+ "step": 326,
2618
+ "token_acc": 0.8571838140487671
2619
+ },
2620
+ {
2621
+ "epoch": 0.8731642189586115,
2622
+ "grad_norm": 2.1646455936364544,
2623
+ "learning_rate": 3.2283502229249286e-06,
2624
+ "loss": 0.4263336658477783,
2625
+ "step": 327,
2626
+ "token_acc": 0.8559183478355408
2627
+ },
2628
+ {
2629
+ "epoch": 0.8758344459279038,
2630
+ "grad_norm": 2.218285516934927,
2631
+ "learning_rate": 3.217790818335077e-06,
2632
+ "loss": 0.3973150849342346,
2633
+ "step": 328,
2634
+ "token_acc": 0.8625034093856812
2635
+ },
2636
+ {
2637
+ "epoch": 0.8785046728971962,
2638
+ "grad_norm": 2.0817436151233646,
2639
+ "learning_rate": 3.2072174392235305e-06,
2640
+ "loss": 0.37638282775878906,
2641
+ "step": 329,
2642
+ "token_acc": 0.8756998777389526
2643
+ },
2644
+ {
2645
+ "epoch": 0.8811748998664887,
2646
+ "grad_norm": 2.2498888133223476,
2647
+ "learning_rate": 3.196630291441231e-06,
2648
+ "loss": 0.420512318611145,
2649
+ "step": 330,
2650
+ "token_acc": 0.8518001437187195
2651
+ },
2652
+ {
2653
+ "epoch": 0.8838451268357811,
2654
+ "grad_norm": 2.334898673587732,
2655
+ "learning_rate": 3.186029581107179e-06,
2656
+ "loss": 0.3659869432449341,
2657
+ "step": 331,
2658
+ "token_acc": 0.8699054718017578
2659
+ },
2660
+ {
2661
+ "epoch": 0.8865153538050734,
2662
+ "grad_norm": 2.1866139390892654,
2663
+ "learning_rate": 3.175415514604422e-06,
2664
+ "loss": 0.4169244170188904,
2665
+ "step": 332,
2666
+ "token_acc": 0.8576473593711853
2667
+ },
2668
+ {
2669
+ "epoch": 0.8891855807743658,
2670
+ "grad_norm": 2.197749313892869,
2671
+ "learning_rate": 3.164788298576036e-06,
2672
+ "loss": 0.44280239939689636,
2673
+ "step": 333,
2674
+ "token_acc": 0.8511455655097961
2675
+ },
2676
+ {
2677
+ "epoch": 0.8918558077436582,
2678
+ "grad_norm": 2.088344735779412,
2679
+ "learning_rate": 3.154148139921102e-06,
2680
+ "loss": 0.3601936101913452,
2681
+ "step": 334,
2682
+ "token_acc": 0.8790379166603088
2683
+ },
2684
+ {
2685
+ "epoch": 0.8945260347129506,
2686
+ "grad_norm": 2.099275973735432,
2687
+ "learning_rate": 3.14349524579068e-06,
2688
+ "loss": 0.39613986015319824,
2689
+ "step": 335,
2690
+ "token_acc": 0.8654648065567017
2691
+ },
2692
+ {
2693
+ "epoch": 0.897196261682243,
2694
+ "grad_norm": 2.2370994799468633,
2695
+ "learning_rate": 3.132829823583771e-06,
2696
+ "loss": 0.42986831068992615,
2697
+ "step": 336,
2698
+ "token_acc": 0.8542926907539368
2699
+ },
2700
+ {
2701
+ "epoch": 0.8998664886515354,
2702
+ "grad_norm": 2.2087715838536193,
2703
+ "learning_rate": 3.122152080943287e-06,
2704
+ "loss": 0.42689549922943115,
2705
+ "step": 337,
2706
+ "token_acc": 0.8599311113357544
2707
+ },
2708
+ {
2709
+ "epoch": 0.9025367156208278,
2710
+ "grad_norm": 2.3280483782119066,
2711
+ "learning_rate": 3.1114622257520004e-06,
2712
+ "loss": 0.43518245220184326,
2713
+ "step": 338,
2714
+ "token_acc": 0.8456082940101624
2715
+ },
2716
+ {
2717
+ "epoch": 0.9052069425901201,
2718
+ "grad_norm": 2.2829698843890425,
2719
+ "learning_rate": 3.1007604661285012e-06,
2720
+ "loss": 0.4234972596168518,
2721
+ "step": 339,
2722
+ "token_acc": 0.8607065677642822
2723
+ },
2724
+ {
2725
+ "epoch": 0.9078771695594126,
2726
+ "grad_norm": 2.262513322485581,
2727
+ "learning_rate": 3.0900470104231456e-06,
2728
+ "loss": 0.4469085931777954,
2729
+ "step": 340,
2730
+ "token_acc": 0.8491241931915283
2731
+ },
2732
+ {
2733
+ "epoch": 0.910547396528705,
2734
+ "grad_norm": 2.43719150955656,
2735
+ "learning_rate": 3.079322067213997e-06,
2736
+ "loss": 0.46270620822906494,
2737
+ "step": 341,
2738
+ "token_acc": 0.8476319313049316
2739
+ },
2740
+ {
2741
+ "epoch": 0.9132176234979973,
2742
+ "grad_norm": 2.108305945026917,
2743
+ "learning_rate": 3.0685858453027668e-06,
2744
+ "loss": 0.39521580934524536,
2745
+ "step": 342,
2746
+ "token_acc": 0.8654271364212036
2747
+ },
2748
+ {
2749
+ "epoch": 0.9158878504672897,
2750
+ "grad_norm": 2.242001862391107,
2751
+ "learning_rate": 3.0578385537107497e-06,
2752
+ "loss": 0.4084666967391968,
2753
+ "step": 343,
2754
+ "token_acc": 0.8584118485450745
2755
+ },
2756
+ {
2757
+ "epoch": 0.9185580774365821,
2758
+ "grad_norm": 2.4071794793582972,
2759
+ "learning_rate": 3.047080401674754e-06,
2760
+ "loss": 0.4503254294395447,
2761
+ "step": 344,
2762
+ "token_acc": 0.843314528465271
2763
+ },
2764
+ {
2765
+ "epoch": 0.9212283044058746,
2766
+ "grad_norm": 2.123804007583984,
2767
+ "learning_rate": 3.0363115986430267e-06,
2768
+ "loss": 0.37792646884918213,
2769
+ "step": 345,
2770
+ "token_acc": 0.8711110949516296
2771
+ },
2772
+ {
2773
+ "epoch": 0.9238985313751669,
2774
+ "grad_norm": 2.21699368907369,
2775
+ "learning_rate": 3.0255323542711784e-06,
2776
+ "loss": 0.39545828104019165,
2777
+ "step": 346,
2778
+ "token_acc": 0.862930178642273
2779
+ },
2780
+ {
2781
+ "epoch": 0.9265687583444593,
2782
+ "grad_norm": 2.1501503607338117,
2783
+ "learning_rate": 3.0147428784180976e-06,
2784
+ "loss": 0.4291766583919525,
2785
+ "step": 347,
2786
+ "token_acc": 0.8475905656814575
2787
+ },
2788
+ {
2789
+ "epoch": 0.9292389853137517,
2790
+ "grad_norm": 2.2213485854006567,
2791
+ "learning_rate": 3.00394338114187e-06,
2792
+ "loss": 0.3883587121963501,
2793
+ "step": 348,
2794
+ "token_acc": 0.8651607632637024
2795
+ },
2796
+ {
2797
+ "epoch": 0.931909212283044,
2798
+ "grad_norm": 2.4155344798973664,
2799
+ "learning_rate": 2.9931340726956844e-06,
2800
+ "loss": 0.44997814297676086,
2801
+ "step": 349,
2802
+ "token_acc": 0.8457612991333008
2803
+ },
2804
+ {
2805
+ "epoch": 0.9345794392523364,
2806
+ "grad_norm": 2.2116609998510492,
2807
+ "learning_rate": 2.9823151635237424e-06,
2808
+ "loss": 0.44884175062179565,
2809
+ "step": 350,
2810
+ "token_acc": 0.8491075038909912
2811
+ },
2812
+ {
2813
+ "epoch": 0.9372496662216289,
2814
+ "grad_norm": 2.2316893481433375,
2815
+ "learning_rate": 2.9714868642571593e-06,
2816
+ "loss": 0.4209368824958801,
2817
+ "step": 351,
2818
+ "token_acc": 0.8569639921188354
2819
+ },
2820
+ {
2821
+ "epoch": 0.9399198931909212,
2822
+ "grad_norm": 2.426290316255868,
2823
+ "learning_rate": 2.9606493857098657e-06,
2824
+ "loss": 0.4949773848056793,
2825
+ "step": 352,
2826
+ "token_acc": 0.8267987370491028
2827
+ },
2828
+ {
2829
+ "epoch": 0.9425901201602136,
2830
+ "grad_norm": 2.251552494738796,
2831
+ "learning_rate": 2.9498029388744992e-06,
2832
+ "loss": 0.3735668957233429,
2833
+ "step": 353,
2834
+ "token_acc": 0.8712621331214905
2835
+ },
2836
+ {
2837
+ "epoch": 0.945260347129506,
2838
+ "grad_norm": 2.159831334914302,
2839
+ "learning_rate": 2.938947734918302e-06,
2840
+ "loss": 0.41402506828308105,
2841
+ "step": 354,
2842
+ "token_acc": 0.8622187376022339
2843
+ },
2844
+ {
2845
+ "epoch": 0.9479305740987984,
2846
+ "grad_norm": 2.1174314869196538,
2847
+ "learning_rate": 2.928083985179005e-06,
2848
+ "loss": 0.4044073522090912,
2849
+ "step": 355,
2850
+ "token_acc": 0.8614546060562134
2851
+ },
2852
+ {
2853
+ "epoch": 0.9506008010680908,
2854
+ "grad_norm": 2.374563606753829,
2855
+ "learning_rate": 2.9172119011607153e-06,
2856
+ "loss": 0.4143449664115906,
2857
+ "step": 356,
2858
+ "token_acc": 0.8544071912765503
2859
+ },
2860
+ {
2861
+ "epoch": 0.9532710280373832,
2862
+ "grad_norm": 2.294896152134026,
2863
+ "learning_rate": 2.9063316945297992e-06,
2864
+ "loss": 0.43211933970451355,
2865
+ "step": 357,
2866
+ "token_acc": 0.8568835258483887
2867
+ },
2868
+ {
2869
+ "epoch": 0.9559412550066756,
2870
+ "grad_norm": 2.2261965219375974,
2871
+ "learning_rate": 2.8954435771107604e-06,
2872
+ "loss": 0.4158693850040436,
2873
+ "step": 358,
2874
+ "token_acc": 0.8592675924301147
2875
+ },
2876
+ {
2877
+ "epoch": 0.9586114819759679,
2878
+ "grad_norm": 2.263833200175103,
2879
+ "learning_rate": 2.884547760882115e-06,
2880
+ "loss": 0.41552162170410156,
2881
+ "step": 359,
2882
+ "token_acc": 0.8596687912940979
2883
+ },
2884
+ {
2885
+ "epoch": 0.9612817089452603,
2886
+ "grad_norm": 2.431219991596061,
2887
+ "learning_rate": 2.8736444579722665e-06,
2888
+ "loss": 0.4636494517326355,
2889
+ "step": 360,
2890
+ "token_acc": 0.841825008392334
2891
+ },
2892
+ {
2893
+ "epoch": 0.9639519359145527,
2894
+ "grad_norm": 2.3823132934564293,
2895
+ "learning_rate": 2.8627338806553754e-06,
2896
+ "loss": 0.42841193079948425,
2897
+ "step": 361,
2898
+ "token_acc": 0.8527615666389465
2899
+ },
2900
+ {
2901
+ "epoch": 0.9666221628838452,
2902
+ "grad_norm": 2.2587644155534417,
2903
+ "learning_rate": 2.8518162413472266e-06,
2904
+ "loss": 0.42093145847320557,
2905
+ "step": 362,
2906
+ "token_acc": 0.8558091521263123
2907
+ },
2908
+ {
2909
+ "epoch": 0.9692923898531375,
2910
+ "grad_norm": 2.321983278619323,
2911
+ "learning_rate": 2.840891752601091e-06,
2912
+ "loss": 0.4125031530857086,
2913
+ "step": 363,
2914
+ "token_acc": 0.8578940033912659
2915
+ },
2916
+ {
2917
+ "epoch": 0.9719626168224299,
2918
+ "grad_norm": 2.3676633772039906,
2919
+ "learning_rate": 2.8299606271035913e-06,
2920
+ "loss": 0.45884716510772705,
2921
+ "step": 364,
2922
+ "token_acc": 0.8460044264793396
2923
+ },
2924
+ {
2925
+ "epoch": 0.9746328437917223,
2926
+ "grad_norm": 2.220007438229548,
2927
+ "learning_rate": 2.8190230776705606e-06,
2928
+ "loss": 0.42842674255371094,
2929
+ "step": 365,
2930
+ "token_acc": 0.8562912940979004
2931
+ },
2932
+ {
2933
+ "epoch": 0.9773030707610146,
2934
+ "grad_norm": 2.3494613525314394,
2935
+ "learning_rate": 2.8080793172428965e-06,
2936
+ "loss": 0.39079129695892334,
2937
+ "step": 366,
2938
+ "token_acc": 0.872724711894989
2939
+ },
2940
+ {
2941
+ "epoch": 0.9799732977303071,
2942
+ "grad_norm": 2.2099625930261917,
2943
+ "learning_rate": 2.79712955888242e-06,
2944
+ "loss": 0.41564232110977173,
2945
+ "step": 367,
2946
+ "token_acc": 0.8558210134506226
2947
+ },
2948
+ {
2949
+ "epoch": 0.9826435246995995,
2950
+ "grad_norm": 2.201693209999341,
2951
+ "learning_rate": 2.786174015767721e-06,
2952
+ "loss": 0.387314110994339,
2953
+ "step": 368,
2954
+ "token_acc": 0.8686463832855225
2955
+ },
2956
+ {
2957
+ "epoch": 0.9853137516688919,
2958
+ "grad_norm": 2.3128832949723583,
2959
+ "learning_rate": 2.7752129011900143e-06,
2960
+ "loss": 0.38916295766830444,
2961
+ "step": 369,
2962
+ "token_acc": 0.864463746547699
2963
+ },
2964
+ {
2965
+ "epoch": 0.9879839786381842,
2966
+ "grad_norm": 1.9857609060455137,
2967
+ "learning_rate": 2.764246428548983e-06,
2968
+ "loss": 0.34753191471099854,
2969
+ "step": 370,
2970
+ "token_acc": 0.8804298043251038
2971
+ },
2972
+ {
2973
+ "epoch": 0.9906542056074766,
2974
+ "grad_norm": 2.4420271305997905,
2975
+ "learning_rate": 2.7532748113486254e-06,
2976
+ "loss": 0.4207770526409149,
2977
+ "step": 371,
2978
+ "token_acc": 0.8588183522224426
2979
+ },
2980
+ {
2981
+ "epoch": 0.9933244325767691,
2982
+ "grad_norm": 2.2897736560508632,
2983
+ "learning_rate": 2.742298263193099e-06,
2984
+ "loss": 0.40927761793136597,
2985
+ "step": 372,
2986
+ "token_acc": 0.8623603582382202
2987
+ },
2988
+ {
2989
+ "epoch": 0.9959946595460614,
2990
+ "grad_norm": 2.3499129827865906,
2991
+ "learning_rate": 2.73131699778256e-06,
2992
+ "loss": 0.43391793966293335,
2993
+ "step": 373,
2994
+ "token_acc": 0.8543037176132202
2995
+ },
2996
+ {
2997
+ "epoch": 0.9986648865153538,
2998
+ "grad_norm": 2.1734366644042487,
2999
+ "learning_rate": 2.720331228909005e-06,
3000
+ "loss": 0.3679766058921814,
3001
+ "step": 374,
3002
+ "token_acc": 0.8691184520721436
3003
+ },
3004
+ {
3005
+ "epoch": 1.0,
3006
+ "grad_norm": 3.3262997375261216,
3007
+ "learning_rate": 2.7093411704521056e-06,
3008
+ "loss": 0.4927346706390381,
3009
+ "step": 375,
3010
+ "token_acc": 0.8314176201820374
3011
+ },
3012
+ {
3013
+ "epoch": 1.0,
3014
+ "eval_loss": 0.40452611446380615,
3015
+ "eval_runtime": 4.5267,
3016
+ "eval_samples_per_second": 4.639,
3017
+ "eval_steps_per_second": 0.663,
3018
+ "eval_token_acc": 0.8610218167304993,
3019
+ "step": 375
3020
+ }
3021
+ ],
3022
+ "logging_steps": 1,
3023
+ "max_steps": 750,
3024
+ "num_input_tokens_seen": 0,
3025
+ "num_train_epochs": 2,
3026
+ "save_steps": 500,
3027
+ "stateful_callbacks": {
3028
+ "TrainerControl": {
3029
+ "args": {
3030
+ "should_epoch_stop": false,
3031
+ "should_evaluate": false,
3032
+ "should_log": false,
3033
+ "should_save": true,
3034
+ "should_training_stop": false
3035
+ },
3036
+ "attributes": {}
3037
+ }
3038
+ },
3039
+ "total_flos": 158336037453824.0,
3040
+ "train_batch_size": 2,
3041
+ "trial_name": null,
3042
+ "trial_params": null
3043
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e1d01009862b38d4dd3a06f19a68c1fd0ddf813bb462cf301fc114879d980e
3
+ size 9041
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-375/zero_to_fp32.py ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import gc
25
+ import json
26
+ import numpy as np
27
+ from tqdm import tqdm
28
+ from collections import OrderedDict
29
+ from dataclasses import dataclass
30
+
31
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
32
+ # DeepSpeed data structures it has to be available in the current python environment.
33
+ from deepspeed.utils import logger
34
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
35
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
36
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
37
+
38
+
39
+ @dataclass
40
+ class zero_model_state:
41
+ buffers: dict()
42
+ param_shapes: dict()
43
+ shared_params: list
44
+ ds_version: int
45
+ frozen_param_shapes: dict()
46
+ frozen_param_fragments: dict()
47
+
48
+
49
+ debug = 0
50
+
51
+ # load to cpu
52
+ device = torch.device('cpu')
53
+
54
+
55
+ def atoi(text):
56
+ return int(text) if text.isdigit() else text
57
+
58
+
59
+ def natural_keys(text):
60
+ '''
61
+ alist.sort(key=natural_keys) sorts in human order
62
+ http://nedbatchelder.com/blog/200712/human_sorting.html
63
+ (See Toothy's implementation in the comments)
64
+ '''
65
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
66
+
67
+
68
+ def get_model_state_file(checkpoint_dir, zero_stage):
69
+ if not os.path.isdir(checkpoint_dir):
70
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
71
+
72
+ # there should be only one file
73
+ if zero_stage <= 2:
74
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
75
+ elif zero_stage == 3:
76
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
77
+
78
+ if not os.path.exists(file):
79
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
80
+
81
+ return file
82
+
83
+
84
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
85
+ # XXX: need to test that this simple glob rule works for multi-node setup too
86
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
87
+
88
+ if len(ckpt_files) == 0:
89
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
90
+
91
+ return ckpt_files
92
+
93
+
94
+ def get_optim_files(checkpoint_dir):
95
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
96
+
97
+
98
+ def get_model_state_files(checkpoint_dir):
99
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
100
+
101
+
102
+ def parse_model_states(files):
103
+ zero_model_states = []
104
+ for file in files:
105
+ state_dict = torch.load(file, map_location=device, weights_only=False)
106
+
107
+ if BUFFER_NAMES not in state_dict:
108
+ raise ValueError(f"{file} is not a model state checkpoint")
109
+ buffer_names = state_dict[BUFFER_NAMES]
110
+ if debug:
111
+ print("Found buffers:", buffer_names)
112
+
113
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
114
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
115
+ param_shapes = state_dict[PARAM_SHAPES]
116
+
117
+ # collect parameters that are included in param_shapes
118
+ param_names = []
119
+ for s in param_shapes:
120
+ for name in s.keys():
121
+ param_names.append(name)
122
+
123
+ # update with frozen parameters
124
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
125
+ if frozen_param_shapes is not None:
126
+ if debug:
127
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
128
+ param_names += list(frozen_param_shapes.keys())
129
+
130
+ # handle shared params
131
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
132
+
133
+ ds_version = state_dict.get(DS_VERSION, None)
134
+
135
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
136
+
137
+ z_model_state = zero_model_state(buffers=buffers,
138
+ param_shapes=param_shapes,
139
+ shared_params=shared_params,
140
+ ds_version=ds_version,
141
+ frozen_param_shapes=frozen_param_shapes,
142
+ frozen_param_fragments=frozen_param_fragments)
143
+ zero_model_states.append(z_model_state)
144
+
145
+ return zero_model_states
146
+
147
+
148
+ def parse_optim_states(files, ds_checkpoint_dir):
149
+ total_files = len(files)
150
+ state_dicts = []
151
+ for f in tqdm(files, desc='Loading checkpoint shards'):
152
+ state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
153
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
154
+ # and also handle the case where it was already removed by another helper script
155
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
156
+ state_dicts.append(state_dict)
157
+
158
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
159
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
160
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
161
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
162
+
163
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
164
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
165
+ # use the max of the partition_count to get the dp world_size.
166
+
167
+ if type(world_size) is list:
168
+ world_size = max(world_size)
169
+
170
+ if world_size != total_files:
171
+ raise ValueError(
172
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
173
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
174
+ )
175
+
176
+ # the groups are named differently in each stage
177
+ if zero_stage <= 2:
178
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
179
+ elif zero_stage == 3:
180
+ fp32_groups_key = FP32_FLAT_GROUPS
181
+ else:
182
+ raise ValueError(f"unknown zero stage {zero_stage}")
183
+
184
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
185
+ return zero_stage, world_size, fp32_flat_groups
186
+
187
+
188
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
189
+ """
190
+ Returns fp32 state_dict reconstructed from ds checkpoint
191
+
192
+ Args:
193
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
194
+
195
+ """
196
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
197
+
198
+ optim_files = get_optim_files(ds_checkpoint_dir)
199
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
200
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
201
+
202
+ model_files = get_model_state_files(ds_checkpoint_dir)
203
+
204
+ zero_model_states = parse_model_states(model_files)
205
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
206
+
207
+ if zero_stage <= 2:
208
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
209
+ exclude_frozen_parameters)
210
+ elif zero_stage == 3:
211
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
212
+ exclude_frozen_parameters)
213
+
214
+
215
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
216
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
217
+ return
218
+
219
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
220
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
221
+
222
+ if debug:
223
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
224
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
225
+
226
+ wanted_params = len(frozen_param_shapes)
227
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
228
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
229
+ print(f'Frozen params: Have {avail_numel} numels to process.')
230
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
231
+
232
+ total_params = 0
233
+ total_numel = 0
234
+ for name, shape in frozen_param_shapes.items():
235
+ total_params += 1
236
+ unpartitioned_numel = shape.numel()
237
+ total_numel += unpartitioned_numel
238
+
239
+ state_dict[name] = frozen_param_fragments[name]
240
+
241
+ if debug:
242
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
243
+
244
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
245
+
246
+
247
+ def _has_callable(obj, fn):
248
+ attr = getattr(obj, fn, None)
249
+ return callable(attr)
250
+
251
+
252
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
253
+ param_shapes = zero_model_states[0].param_shapes
254
+
255
+ # Reconstruction protocol:
256
+ #
257
+ # XXX: document this
258
+
259
+ if debug:
260
+ for i in range(world_size):
261
+ for j in range(len(fp32_flat_groups[0])):
262
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
263
+
264
+ # XXX: memory usage doubles here (zero2)
265
+ num_param_groups = len(fp32_flat_groups[0])
266
+ merged_single_partition_of_fp32_groups = []
267
+ for i in range(num_param_groups):
268
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
269
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
270
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
271
+ avail_numel = sum(
272
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
273
+
274
+ if debug:
275
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
276
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
277
+ # not asserting if there is a mismatch due to possible padding
278
+ print(f"Have {avail_numel} numels to process.")
279
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
280
+
281
+ # params
282
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
283
+ # out-of-core computing solution
284
+ total_numel = 0
285
+ total_params = 0
286
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
287
+ offset = 0
288
+ avail_numel = full_single_fp32_vector.numel()
289
+ for name, shape in shapes.items():
290
+
291
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
292
+ total_numel += unpartitioned_numel
293
+ total_params += 1
294
+
295
+ if debug:
296
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
297
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
298
+ offset += unpartitioned_numel
299
+
300
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
301
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
302
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
303
+ # live optimizer object, so we are checking that the numbers are within the right range
304
+ align_to = 2 * world_size
305
+
306
+ def zero2_align(x):
307
+ return align_to * math.ceil(x / align_to)
308
+
309
+ if debug:
310
+ print(f"original offset={offset}, avail_numel={avail_numel}")
311
+
312
+ offset = zero2_align(offset)
313
+ avail_numel = zero2_align(avail_numel)
314
+
315
+ if debug:
316
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
317
+
318
+ # Sanity check
319
+ if offset != avail_numel:
320
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
321
+
322
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
323
+
324
+
325
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
326
+ exclude_frozen_parameters):
327
+ state_dict = OrderedDict()
328
+
329
+ # buffers
330
+ buffers = zero_model_states[0].buffers
331
+ state_dict.update(buffers)
332
+ if debug:
333
+ print(f"added {len(buffers)} buffers")
334
+
335
+ if not exclude_frozen_parameters:
336
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
337
+
338
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
339
+
340
+ # recover shared parameters
341
+ for pair in zero_model_states[0].shared_params:
342
+ if pair[1] in state_dict:
343
+ state_dict[pair[0]] = state_dict[pair[1]]
344
+
345
+ return state_dict
346
+
347
+
348
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
349
+ remainder = unpartitioned_numel % world_size
350
+ padding_numel = (world_size - remainder) if remainder else 0
351
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
352
+ return partitioned_numel, padding_numel
353
+
354
+
355
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
356
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
357
+ return
358
+
359
+ if debug:
360
+ for i in range(world_size):
361
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
362
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
363
+
364
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
365
+ wanted_params = len(frozen_param_shapes)
366
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
367
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
368
+ print(f'Frozen params: Have {avail_numel} numels to process.')
369
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
370
+
371
+ total_params = 0
372
+ total_numel = 0
373
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
374
+ total_params += 1
375
+ unpartitioned_numel = shape.numel()
376
+ total_numel += unpartitioned_numel
377
+
378
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
379
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
380
+
381
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
382
+
383
+ if debug:
384
+ print(
385
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
386
+ )
387
+
388
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
389
+
390
+
391
+ class GatheredTensor:
392
+ """
393
+ A pseudo tensor that collects partitioned weights.
394
+ It is more memory efficient when there are multiple groups.
395
+ """
396
+
397
+ def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
398
+ self.flat_groups = flat_groups
399
+ self.flat_groups_offset = flat_groups_offset
400
+ self.offset = offset
401
+ self.partitioned_numel = partitioned_numel
402
+ self.shape = shape
403
+ self.dtype = self.flat_groups[0][0].dtype
404
+
405
+ def contiguous(self):
406
+ """
407
+ Merge partitioned weights from flat_groups into a single tensor.
408
+ """
409
+ end_idx = self.offset + self.partitioned_numel
410
+ world_size = len(self.flat_groups)
411
+ pad_flat_param_chunks = []
412
+
413
+ for rank_i in range(world_size):
414
+ # for each rank, we need to collect weights from related group/groups
415
+ flat_groups_at_rank_i = self.flat_groups[rank_i]
416
+ start_group_id = None
417
+ end_group_id = None
418
+ for group_id in range(len(self.flat_groups_offset)):
419
+ if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
420
+ start_group_id = group_id
421
+ if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
422
+ end_group_id = group_id
423
+ break
424
+ # collect weights from related group/groups
425
+ for group_id in range(start_group_id, end_group_id + 1):
426
+ flat_tensor = flat_groups_at_rank_i[group_id]
427
+ start_offset = self.offset - self.flat_groups_offset[group_id]
428
+ end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
429
+ pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
430
+
431
+ # collect weights from all ranks
432
+ pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
433
+ param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
434
+ return param
435
+
436
+
437
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
438
+ param_shapes = zero_model_states[0].param_shapes
439
+ avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
440
+
441
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
442
+ # param, re-consolidating each param, while dealing with padding if any
443
+
444
+ # merge list of dicts, preserving order
445
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
446
+
447
+ if debug:
448
+ for i in range(world_size):
449
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
450
+
451
+ wanted_params = len(param_shapes)
452
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
453
+ # not asserting if there is a mismatch due to possible padding
454
+ avail_numel = fp32_flat_groups[0].numel() * world_size
455
+ print(f"Trainable params: Have {avail_numel} numels to process.")
456
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
457
+
458
+ # params
459
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
460
+ # out-of-core computing solution
461
+ offset = 0
462
+ total_numel = 0
463
+ total_params = 0
464
+ flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
465
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
466
+ unpartitioned_numel = shape.numel()
467
+ total_numel += unpartitioned_numel
468
+ total_params += 1
469
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
470
+
471
+ if debug:
472
+ print(
473
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
474
+ )
475
+
476
+ # memory efficient tensor
477
+ tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
478
+ state_dict[name] = tensor
479
+ offset += partitioned_numel
480
+
481
+ offset *= world_size
482
+
483
+ # Sanity check
484
+ if offset != avail_numel:
485
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
486
+
487
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
488
+
489
+
490
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
491
+ exclude_frozen_parameters):
492
+ state_dict = OrderedDict()
493
+
494
+ # buffers
495
+ buffers = zero_model_states[0].buffers
496
+ state_dict.update(buffers)
497
+ if debug:
498
+ print(f"added {len(buffers)} buffers")
499
+
500
+ if not exclude_frozen_parameters:
501
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
502
+
503
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
504
+
505
+ # recover shared parameters
506
+ for pair in zero_model_states[0].shared_params:
507
+ if pair[1] in state_dict:
508
+ state_dict[pair[0]] = state_dict[pair[1]]
509
+
510
+ return state_dict
511
+
512
+
513
+ def to_torch_tensor(state_dict, return_empty_tensor=False):
514
+ """
515
+ Convert state_dict of GatheredTensor to torch tensor
516
+ """
517
+ torch_state_dict = {}
518
+ converted_tensors = {}
519
+ for name, tensor in state_dict.items():
520
+ tensor_id = id(tensor)
521
+ if tensor_id in converted_tensors: # shared tensors
522
+ shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
523
+ torch_state_dict[name] = shared_tensor
524
+ else:
525
+ converted_tensors[tensor_id] = name
526
+ if return_empty_tensor:
527
+ torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
528
+ else:
529
+ torch_state_dict[name] = tensor.contiguous()
530
+ return torch_state_dict
531
+
532
+
533
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
534
+ tag=None,
535
+ exclude_frozen_parameters=False,
536
+ lazy_mode=False):
537
+ """
538
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
539
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
540
+ via a model hub.
541
+
542
+ Args:
543
+ - ``checkpoint_dir``: path to the desired checkpoint folder
544
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
545
+ - ``exclude_frozen_parameters``: exclude frozen parameters
546
+ - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
547
+ Convert the pesduo tensor to torch tensor by ``.contiguous()``
548
+
549
+ Returns:
550
+ - pytorch ``state_dict``
551
+
552
+ A typical usage might be ::
553
+
554
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
555
+ # do the training and checkpoint saving
556
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
557
+ model = model.cpu() # move to cpu
558
+ model.load_state_dict(state_dict)
559
+ # submit to model hub or save the model to share with others
560
+
561
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
562
+ application. i.e. you will need to re-initialize the deepspeed engine, since
563
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
564
+
565
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
566
+
567
+ Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
568
+ You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
569
+ the checkpoint. Or you can load state_dict in lazy mode ::
570
+
571
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
572
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
573
+ for name, lazy_tensor in state_dict.item():
574
+ tensor = lazy_tensor.contiguous() # to cpu
575
+ print(name, tensor)
576
+ # del tensor to release memory if it no longer in use
577
+ """
578
+ if tag is None:
579
+ latest_path = os.path.join(checkpoint_dir, 'latest')
580
+ if os.path.isfile(latest_path):
581
+ with open(latest_path, 'r') as fd:
582
+ tag = fd.read().strip()
583
+ else:
584
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
585
+
586
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
587
+
588
+ if not os.path.isdir(ds_checkpoint_dir):
589
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
590
+
591
+ state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
592
+ if lazy_mode:
593
+ return state_dict
594
+ else:
595
+ return to_torch_tensor(state_dict)
596
+
597
+
598
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
599
+ output_dir,
600
+ max_shard_size="5GB",
601
+ safe_serialization=False,
602
+ tag=None,
603
+ exclude_frozen_parameters=False):
604
+ """
605
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
606
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
607
+
608
+ Args:
609
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
610
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
611
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
612
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
613
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
614
+ - ``exclude_frozen_parameters``: exclude frozen parameters
615
+ """
616
+
617
+ # Dependency pre-check
618
+ if safe_serialization:
619
+ try:
620
+ from safetensors.torch import save_file
621
+ except ImportError:
622
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
623
+ raise
624
+ if max_shard_size is not None:
625
+ try:
626
+ from huggingface_hub import split_torch_state_dict_into_shards
627
+ except ImportError:
628
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
629
+ raise
630
+
631
+ # Convert zero checkpoint to state_dict
632
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
633
+ tag,
634
+ exclude_frozen_parameters,
635
+ lazy_mode=True)
636
+
637
+ # Shard the model if it is too big.
638
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
639
+ if max_shard_size is not None:
640
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
641
+ # an memory-efficient approach for sharding
642
+ empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
643
+ state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
644
+ filename_pattern=filename_pattern,
645
+ max_shard_size=max_shard_size)
646
+ else:
647
+ from collections import namedtuple
648
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
649
+ state_dict_split = StateDictSplit(is_sharded=False,
650
+ filename_to_tensors={weights_name: list(state_dict.keys())})
651
+
652
+ # Save the model by shard
653
+ os.makedirs(output_dir, exist_ok=True)
654
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
655
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
656
+ shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
657
+ shard_state_dict = to_torch_tensor(shard_state_dict)
658
+ output_path = os.path.join(output_dir, shard_file)
659
+ if safe_serialization:
660
+ save_file(shard_state_dict, output_path, metadata={"format": "pt"})
661
+ else:
662
+ torch.save(shard_state_dict, output_path)
663
+ # release the memory of current shard
664
+ for tensor_name in list(shard_state_dict.keys()):
665
+ del state_dict[tensor_name]
666
+ del shard_state_dict[tensor_name]
667
+ del shard_state_dict
668
+ gc.collect()
669
+
670
+ # Save index if sharded
671
+ if state_dict_split.is_sharded:
672
+ index = {
673
+ "metadata": state_dict_split.metadata,
674
+ "weight_map": state_dict_split.tensor_to_filename,
675
+ }
676
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
677
+ save_index_file = os.path.join(output_dir, save_index_file)
678
+ with open(save_index_file, "w", encoding="utf-8") as f:
679
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
680
+ f.write(content)
681
+
682
+
683
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
684
+ """
685
+ 1. Put the provided model to cpu
686
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
687
+ 3. Load it into the provided model
688
+
689
+ Args:
690
+ - ``model``: the model object to update
691
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
692
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
693
+
694
+ Returns:
695
+ - ``model`: modified model
696
+
697
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
698
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
699
+ conveniently placed for you in the checkpoint folder.
700
+
701
+ A typical usage might be ::
702
+
703
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
704
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
705
+ # submit to model hub or save the model to share with others
706
+
707
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
708
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
709
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
710
+
711
+ """
712
+ logger.info(f"Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info(f"Overwriting model with fp32 weights")
716
+ model = model.cpu()
717
+ model.load_state_dict(state_dict, strict=False)
718
+
719
+ return model
720
+
721
+
722
+ if __name__ == "__main__":
723
+ parser = argparse.ArgumentParser()
724
+ parser.add_argument("checkpoint_dir",
725
+ type=str,
726
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
727
+ parser.add_argument("output_dir",
728
+ type=str,
729
+ help="directory to the pytorch fp32 state_dict output files"
730
+ "(e.g. path/checkpoint-12-output/)")
731
+ parser.add_argument(
732
+ "--max_shard_size",
733
+ type=str,
734
+ default="5GB",
735
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
736
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
737
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
738
+ "without CPU OOM issues.")
739
+ parser.add_argument(
740
+ "--safe_serialization",
741
+ default=False,
742
+ action='store_true',
743
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
744
+ parser.add_argument("-t",
745
+ "--tag",
746
+ type=str,
747
+ default=None,
748
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
749
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
750
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
751
+ args = parser.parse_args()
752
+
753
+ debug = args.debug
754
+
755
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
756
+ args.output_dir,
757
+ max_shard_size=args.max_shard_size,
758
+ safe_serialization=args.safe_serialization,
759
+ tag=args.tag,
760
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/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
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/args.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "epoch",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 2,
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": 4,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 5e-06,
18
+ "weight_decay": 0.1,
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": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "epoch",
38
+ "save_steps": 500,
39
+ "save_total_limit": null,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
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
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 2000.0,
65
+ "dataloader_num_workers": 48,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
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
+ "tensorboard"
132
+ ],
133
+ "ddp_find_unused_parameters": null,
134
+ "ddp_bucket_cap_mb": null,
135
+ "ddp_broadcast_buffers": null,
136
+ "dataloader_pin_memory": true,
137
+ "dataloader_persistent_workers": false,
138
+ "skip_memory_metrics": true,
139
+ "use_legacy_prediction_loop": false,
140
+ "push_to_hub": false,
141
+ "resume_from_checkpoint": null,
142
+ "hub_model_id": null,
143
+ "hub_strategy": "every_save",
144
+ "hub_token": null,
145
+ "hub_private_repo": null,
146
+ "hub_always_push": false,
147
+ "hub_revision": null,
148
+ "gradient_checkpointing": true,
149
+ "gradient_checkpointing_kwargs": null,
150
+ "include_inputs_for_metrics": false,
151
+ "include_for_metrics": [],
152
+ "eval_do_concat_batches": true,
153
+ "fp16_backend": "auto",
154
+ "push_to_hub_model_id": null,
155
+ "push_to_hub_organization": null,
156
+ "push_to_hub_token": null,
157
+ "mp_parameters": "",
158
+ "auto_find_batch_size": false,
159
+ "full_determinism": false,
160
+ "torchdynamo": null,
161
+ "ray_scope": "last",
162
+ "ddp_timeout": 18000000,
163
+ "torch_compile": false,
164
+ "torch_compile_backend": null,
165
+ "torch_compile_mode": null,
166
+ "include_tokens_per_second": false,
167
+ "include_num_input_tokens_seen": false,
168
+ "neftune_noise_alpha": null,
169
+ "optim_target_modules": null,
170
+ "batch_eval_metrics": false,
171
+ "eval_on_start": false,
172
+ "use_liger_kernel": false,
173
+ "liger_kernel_config": null,
174
+ "eval_use_gather_object": false,
175
+ "average_tokens_across_devices": true,
176
+ "sortish_sampler": false,
177
+ "predict_with_generate": false,
178
+ "generation_max_length": null,
179
+ "generation_num_beams": null,
180
+ "generation_config": null,
181
+ "tuner_backend": "peft",
182
+ "vit_gradient_checkpointing": null,
183
+ "router_aux_loss_coef": 0.0,
184
+ "enable_dft_loss": false,
185
+ "check_model": true,
186
+ "acc_strategy": "token",
187
+ "train_dataloader_shuffle": true,
188
+ "max_epochs": null,
189
+ "aligner_lr": null,
190
+ "vit_lr": null,
191
+ "use_logits_to_keep": null,
192
+ "channels": null,
193
+ "ds3_gather_for_generation": true,
194
+ "resume_only_model": false,
195
+ "optimizer": null,
196
+ "loss_type": null,
197
+ "metric": null,
198
+ "eval_use_evalscope": false,
199
+ "eval_dataset": [],
200
+ "eval_dataset_args": null,
201
+ "eval_limit": null,
202
+ "eval_generation_config": null,
203
+ "extra_eval_args": null,
204
+ "use_flash_ckpt": false,
205
+ "model": "Qwen/Qwen2.5-7B-Instruct",
206
+ "model_type": "qwen2_5",
207
+ "model_revision": null,
208
+ "task_type": "causal_lm",
209
+ "torch_dtype": "bfloat16",
210
+ "attn_impl": null,
211
+ "new_special_tokens": [],
212
+ "num_labels": null,
213
+ "problem_type": null,
214
+ "rope_scaling": null,
215
+ "device_map": null,
216
+ "max_memory": {},
217
+ "max_model_len": null,
218
+ "local_repo_path": null,
219
+ "init_strategy": null,
220
+ "template": "qwen2_5",
221
+ "system": null,
222
+ "max_length": 16240,
223
+ "truncation_strategy": "delete",
224
+ "max_pixels": null,
225
+ "agent_template": null,
226
+ "norm_bbox": null,
227
+ "use_chat_template": true,
228
+ "padding_free": false,
229
+ "padding_side": "right",
230
+ "loss_scale": "default",
231
+ "sequence_parallel_size": 1,
232
+ "response_prefix": null,
233
+ "template_backend": "swift",
234
+ "dataset": [
235
+ "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_2083q_0.8_swift.jsonl",
236
+ "/group/40143/hongzhuyi/ms-swift/data/corr_hotpot_new1369q_format_0.8_swift.jsonl",
237
+ "/group/40143/hongzhuyi/ms-swift/data/corr_nq_2225q_0.8_swift.jsonl",
238
+ "/group/40143/hongzhuyi/ms-swift/data/self_2000_2000_1369_4_hp673_swift.jsonl",
239
+ "/group/40143/hongzhuyi/ms-swift/self_2000_2000_1369_4_nq400_noinfo_swift.jsonl"
240
+ ],
241
+ "val_dataset": [],
242
+ "split_dataset_ratio": 0.001,
243
+ "dataset_num_proc": 100,
244
+ "load_from_cache_file": true,
245
+ "dataset_shuffle": true,
246
+ "val_dataset_shuffle": false,
247
+ "streaming": false,
248
+ "interleave_prob": null,
249
+ "stopping_strategy": "first_exhausted",
250
+ "shuffle_buffer_size": 1000,
251
+ "download_mode": "reuse_dataset_if_exists",
252
+ "columns": {},
253
+ "strict": false,
254
+ "model_name": null,
255
+ "model_author": null,
256
+ "custom_dataset_info": [],
257
+ "quant_method": null,
258
+ "quant_bits": null,
259
+ "hqq_axis": null,
260
+ "bnb_4bit_compute_dtype": "bfloat16",
261
+ "bnb_4bit_quant_type": "nf4",
262
+ "bnb_4bit_use_double_quant": true,
263
+ "bnb_4bit_quant_storage": null,
264
+ "max_new_tokens": 64,
265
+ "temperature": 0.0,
266
+ "top_k": null,
267
+ "top_p": null,
268
+ "repetition_penalty": null,
269
+ "num_beams": 1,
270
+ "stream": false,
271
+ "stop_words": [],
272
+ "logprobs": false,
273
+ "top_logprobs": null,
274
+ "ckpt_dir": null,
275
+ "lora_modules": [],
276
+ "train_type": "full",
277
+ "adapters": [],
278
+ "external_plugins": [],
279
+ "model_kwargs": {},
280
+ "load_args": false,
281
+ "load_data_args": false,
282
+ "packing": false,
283
+ "packing_length": null,
284
+ "lazy_tokenize": false,
285
+ "cached_dataset": [],
286
+ "custom_register_path": [],
287
+ "use_hf": false,
288
+ "ignore_args_error": false,
289
+ "use_swift_lora": false,
290
+ "freeze_parameters": [],
291
+ "freeze_parameters_regex": null,
292
+ "freeze_parameters_ratio": 0.0,
293
+ "trainable_parameters": [],
294
+ "trainable_parameters_regex": null,
295
+ "freeze_llm": false,
296
+ "freeze_vit": true,
297
+ "freeze_aligner": false,
298
+ "target_modules": [
299
+ "all-linear"
300
+ ],
301
+ "target_regex": null,
302
+ "modules_to_save": [],
303
+ "lora_rank": 8,
304
+ "lora_alpha": 32,
305
+ "lora_dropout": 0.05,
306
+ "lora_bias": "none",
307
+ "lora_dtype": null,
308
+ "lorap_lr_ratio": null,
309
+ "use_rslora": false,
310
+ "use_dora": false,
311
+ "lora_ga_batch_size": 2,
312
+ "lora_ga_iters": 2,
313
+ "lora_ga_max_length": 1024,
314
+ "lora_ga_direction": "ArB2r",
315
+ "lora_ga_scale": "stable",
316
+ "lora_ga_stable_gamma": 16,
317
+ "init_weights": true,
318
+ "fourier_n_frequency": 2000,
319
+ "fourier_scaling": 300.0,
320
+ "boft_block_size": 4,
321
+ "boft_block_num": 0,
322
+ "boft_n_butterfly_factor": 1,
323
+ "boft_dropout": 0.0,
324
+ "vera_rank": 256,
325
+ "vera_projection_prng_key": 0,
326
+ "vera_dropout": 0.0,
327
+ "vera_d_initial": 0.1,
328
+ "adapter_act": "gelu",
329
+ "adapter_length": 128,
330
+ "use_galore": false,
331
+ "galore_target_modules": null,
332
+ "galore_rank": 128,
333
+ "galore_update_proj_gap": 50,
334
+ "galore_scale": 1.0,
335
+ "galore_proj_type": "std",
336
+ "galore_optim_per_parameter": false,
337
+ "galore_with_embedding": false,
338
+ "galore_quantization": false,
339
+ "galore_proj_quant": false,
340
+ "galore_proj_bits": 4,
341
+ "galore_proj_group_size": 256,
342
+ "galore_cos_threshold": 0.4,
343
+ "galore_gamma_proj": 2,
344
+ "galore_queue_size": 5,
345
+ "adalora_target_r": 8,
346
+ "adalora_init_r": 12,
347
+ "adalora_tinit": 0,
348
+ "adalora_tfinal": 0,
349
+ "adalora_deltaT": 1,
350
+ "adalora_beta1": 0.85,
351
+ "adalora_beta2": 0.85,
352
+ "adalora_orth_reg_weight": 0.5,
353
+ "llamapro_num_new_blocks": 4,
354
+ "llamapro_num_groups": null,
355
+ "lisa_activated_layers": 0,
356
+ "lisa_step_interval": 20,
357
+ "reft_layer_key": null,
358
+ "reft_layers": null,
359
+ "reft_rank": 4,
360
+ "reft_intervention_type": "LoreftIntervention",
361
+ "reft_args": null,
362
+ "swanlab_token": null,
363
+ "swanlab_project": null,
364
+ "swanlab_workspace": null,
365
+ "swanlab_exp_name": null,
366
+ "swanlab_lark_webhook_url": null,
367
+ "swanlab_lark_secret": null,
368
+ "swanlab_mode": "cloud",
369
+ "add_version": true,
370
+ "create_checkpoint_symlink": false,
371
+ "zero_hpz_partition_size": null,
372
+ "deepspeed_autotp_size": null,
373
+ "early_stop_interval": null,
374
+ "rank": 0,
375
+ "global_world_size": 8,
376
+ "local_world_size": 8,
377
+ "model_suffix": "Qwen2.5-7B-Instruct",
378
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
379
+ "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 0x7f18b0b01ab0>, 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, task_type=None, ignore_patterns=None, requires=['transformers>=4.37'], tags=[])",
380
+ "model_dir": "/root/.cache/modelscope/hub/models/Qwen/Qwen2___5-7B-Instruct",
381
+ "hub": "<class 'swift.hub.hub.MSHub'>",
382
+ "evaluation_strategy": "epoch",
383
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-06, weight_decay=0.1, 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='/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, 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, use_ipex=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=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v6-20250917-134949', 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), 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=['tensorboard'], 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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, channels=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, train_type='full', local_repo_path=None, galore_config=None)"
384
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/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 %}
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
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
+ "torch_dtype": "bfloat16",
55
+ "transformers_version": "4.55.4",
56
+ "use_cache": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 152064
59
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/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": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.55.4"
14
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step750
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb47d7249053835a8df6af66ed05db185485dc094f7e1bc4782163fbb832e4a
3
+ size 4877660776
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fbfd5f58cafa9acee37bc430c4ebc3a7fd023ed84a5d6215e795491a6b5abf3
3
+ size 4932751008
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b045c507384954da434f9d3aa3b196284011e7da80215259f1ede13225b9a948
3
+ size 4330865200
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c42735d2d48f2cd8cd291cf77dbeb563f8d9386b458aa0fe2ede85e9e9c298
3
+ size 1089994880
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/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
+ }
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e5f48b40f283c2be57ffeca20c84e74d5bad51d76da17d127991b78da5289d
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c3696205cbf4679a7f2faf48351e924c79ada4cfd81a956e03e4319cf3d05b5
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403766b1961af9b11405f33af2b272a2d6287cefdee9eb7e26e1dc71e3ed3707
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f6e3e08fea79c105dbd92657538a3cb15e89872360a3c3072b758835ca5ebc
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0203808a2df05d235c57b83a0a087bae98ef6e47f06d685a0bddaa460a16c910
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b492b10406611c53f05fd065d6968c7e5e3797fd0008fca46cad009936c67e
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d44646ad1e32ad260756d9c2e6927a7a101af3a5c9265d8db8a1d4def7d446cb
3
+ size 16389
qwen2.5-7b-2225q-2069q-1369q-rft2-newbs-old-click-2ep-lr5e-6/checkpoint-750/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b83b78288d5cea0b10985a2d48c3c0b12d2ff3f99104720c1b3281409b3b752
3
+ size 16389