hongzhuyi commited on
Commit
90efe2c
·
verified ·
1 Parent(s): 58f3955

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-rft1-newbs-old-click-2ep-lr1e-6/args.json +384 -0
  3. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/added_tokens.json +24 -0
  4. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/args.json +384 -0
  5. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/chat_template.jinja +54 -0
  6. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/config.json +59 -0
  7. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/generation_config.json +14 -0
  8. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/latest +1 -0
  9. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/merges.txt +0 -0
  10. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/model-00001-of-00004.safetensors +3 -0
  11. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/model-00002-of-00004.safetensors +3 -0
  12. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/model-00003-of-00004.safetensors +3 -0
  13. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/model-00004-of-00004.safetensors +3 -0
  14. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/model.safetensors.index.json +347 -0
  15. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/rng_state_0.pth +3 -0
  16. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/rng_state_1.pth +3 -0
  17. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/rng_state_2.pth +3 -0
  18. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/rng_state_3.pth +3 -0
  19. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/rng_state_4.pth +3 -0
  20. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/rng_state_5.pth +3 -0
  21. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/rng_state_6.pth +3 -0
  22. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/rng_state_7.pth +3 -0
  23. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/scheduler.pt +3 -0
  24. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/special_tokens_map.json +31 -0
  25. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/tokenizer.json +3 -0
  26. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/tokenizer_config.json +207 -0
  27. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/trainer_state.json +1547 -0
  28. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/training_args.bin +3 -0
  29. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/vocab.json +0 -0
  30. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/zero_to_fp32.py +760 -0
  31. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/added_tokens.json +24 -0
  32. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/args.json +384 -0
  33. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/chat_template.jinja +54 -0
  34. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/config.json +59 -0
  35. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/generation_config.json +14 -0
  36. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/latest +1 -0
  37. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/merges.txt +0 -0
  38. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/model-00001-of-00004.safetensors +3 -0
  39. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/model-00002-of-00004.safetensors +3 -0
  40. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/model-00003-of-00004.safetensors +3 -0
  41. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/model-00004-of-00004.safetensors +3 -0
  42. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/model.safetensors.index.json +347 -0
  43. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/rng_state_0.pth +3 -0
  44. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/rng_state_1.pth +3 -0
  45. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/rng_state_2.pth +3 -0
  46. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/rng_state_3.pth +3 -0
  47. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/rng_state_4.pth +3 -0
  48. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/rng_state_5.pth +3 -0
  49. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/rng_state_6.pth +3 -0
  50. qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/rng_state_7.pth +3 -0
.gitattributes CHANGED
@@ -72,3 +72,5 @@ qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-375/to
72
  qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
  qwen2.5-7b-2000q-2000q-1369q-nomemory-newbs-old-click-2ep-lr1e-6/checkpoint-318/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
  qwen2.5-7b-2000q-2000q-1369q-nomemory-newbs-old-click-2ep-lr1e-6/checkpoint-636/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
72
  qwen2.5-7b-2000q-2000q-1369q-noinfo-newbs-old-click-2ep-lr1e-6/checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
  qwen2.5-7b-2000q-2000q-1369q-nomemory-newbs-old-click-2ep-lr1e-6/checkpoint-318/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
  qwen2.5-7b-2000q-2000q-1369q-nomemory-newbs-old-click-2ep-lr1e-6/checkpoint-636/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/args.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722",
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": 1,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 16,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-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/v4-20250916-174722/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": 100.0,
65
+ "dataloader_num_workers": 48,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722",
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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
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/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/data/self_2000_2000_1369_4_nq400_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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
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": "checkpoint-636",
378
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636', 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 0x7f75be369990>, 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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
381
+ "hub": "<class 'swift.hub.hub.MSHub'>",
382
+ "evaluation_strategy": "epoch",
383
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722', 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=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-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/v4-20250916-174722/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=100.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722', 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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/args.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722",
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": 1,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 16,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-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/v4-20250916-174722/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": 100.0,
65
+ "dataloader_num_workers": 48,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722",
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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
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/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/data/self_2000_2000_1369_4_nq400_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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
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": "checkpoint-636",
378
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636', 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 0x7f75be369990>, 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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
381
+ "hub": "<class 'swift.hub.hub.MSHub'>",
382
+ "evaluation_strategy": "epoch",
383
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722', 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=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-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/v4-20250916-174722/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=100.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722', 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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step188
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d85fd2d460227586addc7400905a53889c56851aa5d8cc5b0dba83cec84ca6
3
+ size 4877660776
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad4a044e2bae346fc82e0eca97ee9486612d546b8fa912c7f05759d377a593e
3
+ size 4932751008
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c7352c7abc8296e3ba604a57a44e1faac279d1a714d9c19f6e61d418f47694
3
+ size 4330865200
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cccc00f0c33396a79568f30234ffcbbc537bbbd4bda837211bea71afbdd3f808
3
+ size 1089994880
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382588112ed4de2fad9d6ae2eb73288af01bbadae900f489c09f1ed4854914b0
3
+ size 1465
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/trainer_state.json ADDED
@@ -0,0 +1,1547 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 188,
3
+ "best_metric": 0.28944254,
4
+ "best_model_checkpoint": "/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722/checkpoint-188",
5
+ "epoch": 1.0,
6
+ "eval_steps": 100.0,
7
+ "global_step": 188,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0053404539385847796,
14
+ "grad_norm": 1.4680844344295192,
15
+ "learning_rate": 5.2631578947368416e-08,
16
+ "loss": 0.28618815541267395,
17
+ "step": 1,
18
+ "token_acc": 0.8993438482284546
19
+ },
20
+ {
21
+ "epoch": 0.010680907877169559,
22
+ "grad_norm": 1.6685681306773734,
23
+ "learning_rate": 1.0526315789473683e-07,
24
+ "loss": 0.3127783238887787,
25
+ "step": 2,
26
+ "token_acc": 0.8937526345252991
27
+ },
28
+ {
29
+ "epoch": 0.01602136181575434,
30
+ "grad_norm": 1.4357694002934198,
31
+ "learning_rate": 1.5789473684210525e-07,
32
+ "loss": 0.27423810958862305,
33
+ "step": 3,
34
+ "token_acc": 0.9052796959877014
35
+ },
36
+ {
37
+ "epoch": 0.021361815754339118,
38
+ "grad_norm": 1.4730832359618218,
39
+ "learning_rate": 2.1052631578947366e-07,
40
+ "loss": 0.29357409477233887,
41
+ "step": 4,
42
+ "token_acc": 0.8994738459587097
43
+ },
44
+ {
45
+ "epoch": 0.0267022696929239,
46
+ "grad_norm": 1.5683917577404938,
47
+ "learning_rate": 2.631578947368421e-07,
48
+ "loss": 0.3035960793495178,
49
+ "step": 5,
50
+ "token_acc": 0.8966883420944214
51
+ },
52
+ {
53
+ "epoch": 0.03204272363150868,
54
+ "grad_norm": 1.4633956584310943,
55
+ "learning_rate": 3.157894736842105e-07,
56
+ "loss": 0.2846561670303345,
57
+ "step": 6,
58
+ "token_acc": 0.8998727202415466
59
+ },
60
+ {
61
+ "epoch": 0.037383177570093455,
62
+ "grad_norm": 1.5193698521980548,
63
+ "learning_rate": 3.684210526315789e-07,
64
+ "loss": 0.27327555418014526,
65
+ "step": 7,
66
+ "token_acc": 0.9057236909866333
67
+ },
68
+ {
69
+ "epoch": 0.042723631508678236,
70
+ "grad_norm": 1.5085350745441748,
71
+ "learning_rate": 4.2105263157894733e-07,
72
+ "loss": 0.29018205404281616,
73
+ "step": 8,
74
+ "token_acc": 0.9011104702949524
75
+ },
76
+ {
77
+ "epoch": 0.04806408544726302,
78
+ "grad_norm": 1.5689240737231291,
79
+ "learning_rate": 4.7368421052631574e-07,
80
+ "loss": 0.2944909334182739,
81
+ "step": 9,
82
+ "token_acc": 0.9000617265701294
83
+ },
84
+ {
85
+ "epoch": 0.0534045393858478,
86
+ "grad_norm": 1.3525300533751718,
87
+ "learning_rate": 5.263157894736842e-07,
88
+ "loss": 0.25412237644195557,
89
+ "step": 10,
90
+ "token_acc": 0.913280725479126
91
+ },
92
+ {
93
+ "epoch": 0.05874499332443257,
94
+ "grad_norm": 1.5332051047815112,
95
+ "learning_rate": 5.789473684210526e-07,
96
+ "loss": 0.2714199125766754,
97
+ "step": 11,
98
+ "token_acc": 0.9061141014099121
99
+ },
100
+ {
101
+ "epoch": 0.06408544726301736,
102
+ "grad_norm": 1.6675024272172654,
103
+ "learning_rate": 6.31578947368421e-07,
104
+ "loss": 0.2993066906929016,
105
+ "step": 12,
106
+ "token_acc": 0.8960835933685303
107
+ },
108
+ {
109
+ "epoch": 0.06942590120160214,
110
+ "grad_norm": 1.5387437343480326,
111
+ "learning_rate": 6.842105263157895e-07,
112
+ "loss": 0.3007085919380188,
113
+ "step": 13,
114
+ "token_acc": 0.8965851664543152
115
+ },
116
+ {
117
+ "epoch": 0.07476635514018691,
118
+ "grad_norm": 1.5009599762006036,
119
+ "learning_rate": 7.368421052631578e-07,
120
+ "loss": 0.2959010601043701,
121
+ "step": 14,
122
+ "token_acc": 0.8978061676025391
123
+ },
124
+ {
125
+ "epoch": 0.0801068090787717,
126
+ "grad_norm": 1.5918906035265024,
127
+ "learning_rate": 7.894736842105263e-07,
128
+ "loss": 0.2931970953941345,
129
+ "step": 15,
130
+ "token_acc": 0.8976789712905884
131
+ },
132
+ {
133
+ "epoch": 0.08544726301735647,
134
+ "grad_norm": 1.3571249600452637,
135
+ "learning_rate": 8.421052631578947e-07,
136
+ "loss": 0.25758588314056396,
137
+ "step": 16,
138
+ "token_acc": 0.9122288823127747
139
+ },
140
+ {
141
+ "epoch": 0.09078771695594126,
142
+ "grad_norm": 1.4960297904157556,
143
+ "learning_rate": 8.947368421052631e-07,
144
+ "loss": 0.311839759349823,
145
+ "step": 17,
146
+ "token_acc": 0.8928477168083191
147
+ },
148
+ {
149
+ "epoch": 0.09612817089452604,
150
+ "grad_norm": 1.5167929236403785,
151
+ "learning_rate": 9.473684210526315e-07,
152
+ "loss": 0.317889928817749,
153
+ "step": 18,
154
+ "token_acc": 0.889501690864563
155
+ },
156
+ {
157
+ "epoch": 0.10146862483311081,
158
+ "grad_norm": 1.440565799039953,
159
+ "learning_rate": 1e-06,
160
+ "loss": 0.2831297516822815,
161
+ "step": 19,
162
+ "token_acc": 0.9045619964599609
163
+ },
164
+ {
165
+ "epoch": 0.1068090787716956,
166
+ "grad_norm": 1.406346333791705,
167
+ "learning_rate": 9.999806402154789e-07,
168
+ "loss": 0.2887258231639862,
169
+ "step": 20,
170
+ "token_acc": 0.9011761546134949
171
+ },
172
+ {
173
+ "epoch": 0.11214953271028037,
174
+ "grad_norm": 1.5111427184007904,
175
+ "learning_rate": 9.999225623611207e-07,
176
+ "loss": 0.31958216428756714,
177
+ "step": 21,
178
+ "token_acc": 0.8933359384536743
179
+ },
180
+ {
181
+ "epoch": 0.11748998664886515,
182
+ "grad_norm": 1.380820258533298,
183
+ "learning_rate": 9.998257709344243e-07,
184
+ "loss": 0.287494033575058,
185
+ "step": 22,
186
+ "token_acc": 0.9029217958450317
187
+ },
188
+ {
189
+ "epoch": 0.12283044058744993,
190
+ "grad_norm": 1.501227290349748,
191
+ "learning_rate": 9.996902734308345e-07,
192
+ "loss": 0.3120245337486267,
193
+ "step": 23,
194
+ "token_acc": 0.8955358266830444
195
+ },
196
+ {
197
+ "epoch": 0.12817089452603472,
198
+ "grad_norm": 1.3907620713631643,
199
+ "learning_rate": 9.995160803431612e-07,
200
+ "loss": 0.2652924954891205,
201
+ "step": 24,
202
+ "token_acc": 0.911475658416748
203
+ },
204
+ {
205
+ "epoch": 0.13351134846461948,
206
+ "grad_norm": 1.4894374866926008,
207
+ "learning_rate": 9.993032051607668e-07,
208
+ "loss": 0.3017966151237488,
209
+ "step": 25,
210
+ "token_acc": 0.8967162370681763
211
+ },
212
+ {
213
+ "epoch": 0.13885180240320427,
214
+ "grad_norm": 1.4377257049445678,
215
+ "learning_rate": 9.990516643685221e-07,
216
+ "loss": 0.30019575357437134,
217
+ "step": 26,
218
+ "token_acc": 0.8983671069145203
219
+ },
220
+ {
221
+ "epoch": 0.14419225634178906,
222
+ "grad_norm": 1.444789517167666,
223
+ "learning_rate": 9.98761477445529e-07,
224
+ "loss": 0.29359400272369385,
225
+ "step": 27,
226
+ "token_acc": 0.898292064666748
227
+ },
228
+ {
229
+ "epoch": 0.14953271028037382,
230
+ "grad_norm": 1.5166558298180315,
231
+ "learning_rate": 9.98432666863613e-07,
232
+ "loss": 0.28964900970458984,
233
+ "step": 28,
234
+ "token_acc": 0.9022803902626038
235
+ },
236
+ {
237
+ "epoch": 0.1548731642189586,
238
+ "grad_norm": 1.4267991552660044,
239
+ "learning_rate": 9.980652580855819e-07,
240
+ "loss": 0.280508816242218,
241
+ "step": 29,
242
+ "token_acc": 0.9031826257705688
243
+ },
244
+ {
245
+ "epoch": 0.1602136181575434,
246
+ "grad_norm": 1.5835260406220442,
247
+ "learning_rate": 9.97659279563255e-07,
248
+ "loss": 0.32461118698120117,
249
+ "step": 30,
250
+ "token_acc": 0.890064001083374
251
+ },
252
+ {
253
+ "epoch": 0.16555407209612816,
254
+ "grad_norm": 1.458595332392139,
255
+ "learning_rate": 9.972147627352593e-07,
256
+ "loss": 0.2812092900276184,
257
+ "step": 31,
258
+ "token_acc": 0.9043583273887634
259
+ },
260
+ {
261
+ "epoch": 0.17089452603471295,
262
+ "grad_norm": 1.4247084503881582,
263
+ "learning_rate": 9.96731742024594e-07,
264
+ "loss": 0.29723116755485535,
265
+ "step": 32,
266
+ "token_acc": 0.898239016532898
267
+ },
268
+ {
269
+ "epoch": 0.17623497997329773,
270
+ "grad_norm": 1.4162726844062017,
271
+ "learning_rate": 9.96210254835968e-07,
272
+ "loss": 0.2897300720214844,
273
+ "step": 33,
274
+ "token_acc": 0.9001203179359436
275
+ },
276
+ {
277
+ "epoch": 0.18157543391188252,
278
+ "grad_norm": 1.5506961166890605,
279
+ "learning_rate": 9.956503415528982e-07,
280
+ "loss": 0.25957155227661133,
281
+ "step": 34,
282
+ "token_acc": 0.9100760817527771
283
+ },
284
+ {
285
+ "epoch": 0.18691588785046728,
286
+ "grad_norm": 1.440608304077442,
287
+ "learning_rate": 9.95052045534588e-07,
288
+ "loss": 0.2758601903915405,
289
+ "step": 35,
290
+ "token_acc": 0.9061575531959534
291
+ },
292
+ {
293
+ "epoch": 0.19225634178905207,
294
+ "grad_norm": 1.5192839960137057,
295
+ "learning_rate": 9.944154131125642e-07,
296
+ "loss": 0.2823089063167572,
297
+ "step": 36,
298
+ "token_acc": 0.9057112336158752
299
+ },
300
+ {
301
+ "epoch": 0.19759679572763686,
302
+ "grad_norm": 1.4943292164165989,
303
+ "learning_rate": 9.937404935870937e-07,
304
+ "loss": 0.2794153690338135,
305
+ "step": 37,
306
+ "token_acc": 0.9042868614196777
307
+ },
308
+ {
309
+ "epoch": 0.20293724966622162,
310
+ "grad_norm": 1.4635503317305278,
311
+ "learning_rate": 9.930273392233624e-07,
312
+ "loss": 0.28065863251686096,
313
+ "step": 38,
314
+ "token_acc": 0.9040310978889465
315
+ },
316
+ {
317
+ "epoch": 0.2082777036048064,
318
+ "grad_norm": 1.4609796175621217,
319
+ "learning_rate": 9.922760052474294e-07,
320
+ "loss": 0.27919909358024597,
321
+ "step": 39,
322
+ "token_acc": 0.9046768546104431
323
+ },
324
+ {
325
+ "epoch": 0.2136181575433912,
326
+ "grad_norm": 1.4677584371951407,
327
+ "learning_rate": 9.91486549841951e-07,
328
+ "loss": 0.2925993502140045,
329
+ "step": 40,
330
+ "token_acc": 0.9009308218955994
331
+ },
332
+ {
333
+ "epoch": 0.21895861148197596,
334
+ "grad_norm": 1.4405005579476842,
335
+ "learning_rate": 9.906590341416723e-07,
336
+ "loss": 0.27640053629875183,
337
+ "step": 41,
338
+ "token_acc": 0.9062628746032715
339
+ },
340
+ {
341
+ "epoch": 0.22429906542056074,
342
+ "grad_norm": 1.5453992146200137,
343
+ "learning_rate": 9.897935222286966e-07,
344
+ "loss": 0.29461127519607544,
345
+ "step": 42,
346
+ "token_acc": 0.8993297815322876
347
+ },
348
+ {
349
+ "epoch": 0.22963951935914553,
350
+ "grad_norm": 1.5735314554728557,
351
+ "learning_rate": 9.888900811275203e-07,
352
+ "loss": 0.314420223236084,
353
+ "step": 43,
354
+ "token_acc": 0.8900313377380371
355
+ },
356
+ {
357
+ "epoch": 0.2349799732977303,
358
+ "grad_norm": 1.480951808194191,
359
+ "learning_rate": 9.879487807998435e-07,
360
+ "loss": 0.29261118173599243,
361
+ "step": 44,
362
+ "token_acc": 0.901530385017395
363
+ },
364
+ {
365
+ "epoch": 0.24032042723631508,
366
+ "grad_norm": 1.4386926707775394,
367
+ "learning_rate": 9.869696941391523e-07,
368
+ "loss": 0.28782376646995544,
369
+ "step": 45,
370
+ "token_acc": 0.9029006958007812
371
+ },
372
+ {
373
+ "epoch": 0.24566088117489987,
374
+ "grad_norm": 1.533482422206995,
375
+ "learning_rate": 9.859528969650737e-07,
376
+ "loss": 0.3115203082561493,
377
+ "step": 46,
378
+ "token_acc": 0.8934023380279541
379
+ },
380
+ {
381
+ "epoch": 0.25100133511348466,
382
+ "grad_norm": 1.5248490732703248,
383
+ "learning_rate": 9.848984680175048e-07,
384
+ "loss": 0.30711060762405396,
385
+ "step": 47,
386
+ "token_acc": 0.8952121734619141
387
+ },
388
+ {
389
+ "epoch": 0.25634178905206945,
390
+ "grad_norm": 1.4301160521804694,
391
+ "learning_rate": 9.83806488950514e-07,
392
+ "loss": 0.27855733036994934,
393
+ "step": 48,
394
+ "token_acc": 0.9025441408157349
395
+ },
396
+ {
397
+ "epoch": 0.2616822429906542,
398
+ "grad_norm": 1.4439078814307809,
399
+ "learning_rate": 9.826770443260193e-07,
400
+ "loss": 0.268754780292511,
401
+ "step": 49,
402
+ "token_acc": 0.9062784910202026
403
+ },
404
+ {
405
+ "epoch": 0.26702269692923897,
406
+ "grad_norm": 1.3756290389467116,
407
+ "learning_rate": 9.81510221607239e-07,
408
+ "loss": 0.2641981542110443,
409
+ "step": 50,
410
+ "token_acc": 0.9079115986824036
411
+ },
412
+ {
413
+ "epoch": 0.27236315086782376,
414
+ "grad_norm": 1.3801487007930435,
415
+ "learning_rate": 9.803061111519185e-07,
416
+ "loss": 0.2629387378692627,
417
+ "step": 51,
418
+ "token_acc": 0.9080008268356323
419
+ },
420
+ {
421
+ "epoch": 0.27770360480640854,
422
+ "grad_norm": 1.4769272869669696,
423
+ "learning_rate": 9.79064806205334e-07,
424
+ "loss": 0.2927890419960022,
425
+ "step": 52,
426
+ "token_acc": 0.8967737555503845
427
+ },
428
+ {
429
+ "epoch": 0.28304405874499333,
430
+ "grad_norm": 1.44443609487884,
431
+ "learning_rate": 9.777864028930705e-07,
432
+ "loss": 0.2803707718849182,
433
+ "step": 53,
434
+ "token_acc": 0.9024505615234375
435
+ },
436
+ {
437
+ "epoch": 0.2883845126835781,
438
+ "grad_norm": 1.4098880500394106,
439
+ "learning_rate": 9.764710002135782e-07,
440
+ "loss": 0.2643783986568451,
441
+ "step": 54,
442
+ "token_acc": 0.9092001914978027
443
+ },
444
+ {
445
+ "epoch": 0.2937249666221629,
446
+ "grad_norm": 1.5158998686252954,
447
+ "learning_rate": 9.751187000305074e-07,
448
+ "loss": 0.3155965209007263,
449
+ "step": 55,
450
+ "token_acc": 0.8920438885688782
451
+ },
452
+ {
453
+ "epoch": 0.29906542056074764,
454
+ "grad_norm": 1.4283142529712562,
455
+ "learning_rate": 9.737296070648186e-07,
456
+ "loss": 0.2711144685745239,
457
+ "step": 56,
458
+ "token_acc": 0.9078071117401123
459
+ },
460
+ {
461
+ "epoch": 0.30440587449933243,
462
+ "grad_norm": 1.445103036518831,
463
+ "learning_rate": 9.723038288866736e-07,
464
+ "loss": 0.2946472764015198,
465
+ "step": 57,
466
+ "token_acc": 0.9006671905517578
467
+ },
468
+ {
469
+ "epoch": 0.3097463284379172,
470
+ "grad_norm": 1.5469319594722661,
471
+ "learning_rate": 9.708414759071057e-07,
472
+ "loss": 0.2815186381340027,
473
+ "step": 58,
474
+ "token_acc": 0.9045448303222656
475
+ },
476
+ {
477
+ "epoch": 0.315086782376502,
478
+ "grad_norm": 1.6171152135871012,
479
+ "learning_rate": 9.693426613694692e-07,
480
+ "loss": 0.31847983598709106,
481
+ "step": 59,
482
+ "token_acc": 0.8905124664306641
483
+ },
484
+ {
485
+ "epoch": 0.3204272363150868,
486
+ "grad_norm": 1.4706442684944392,
487
+ "learning_rate": 9.678075013406702e-07,
488
+ "loss": 0.2880111336708069,
489
+ "step": 60,
490
+ "token_acc": 0.899748682975769
491
+ },
492
+ {
493
+ "epoch": 0.3257676902536716,
494
+ "grad_norm": 1.5860771109565805,
495
+ "learning_rate": 9.66236114702178e-07,
496
+ "loss": 0.29920926690101624,
497
+ "step": 61,
498
+ "token_acc": 0.897007942199707
499
+ },
500
+ {
501
+ "epoch": 0.3311081441922563,
502
+ "grad_norm": 1.5010123249171283,
503
+ "learning_rate": 9.646286231408192e-07,
504
+ "loss": 0.297206312417984,
505
+ "step": 62,
506
+ "token_acc": 0.8984295129776001
507
+ },
508
+ {
509
+ "epoch": 0.3364485981308411,
510
+ "grad_norm": 1.4938645899870184,
511
+ "learning_rate": 9.629851511393555e-07,
512
+ "loss": 0.29847198724746704,
513
+ "step": 63,
514
+ "token_acc": 0.8973211050033569
515
+ },
516
+ {
517
+ "epoch": 0.3417890520694259,
518
+ "grad_norm": 1.5454968109005192,
519
+ "learning_rate": 9.613058259668414e-07,
520
+ "loss": 0.2826240658760071,
521
+ "step": 64,
522
+ "token_acc": 0.9042453169822693
523
+ },
524
+ {
525
+ "epoch": 0.3471295060080107,
526
+ "grad_norm": 1.4274151779113933,
527
+ "learning_rate": 9.595907776687713e-07,
528
+ "loss": 0.28468042612075806,
529
+ "step": 65,
530
+ "token_acc": 0.9014208912849426
531
+ },
532
+ {
533
+ "epoch": 0.35246995994659547,
534
+ "grad_norm": 1.5919794599897976,
535
+ "learning_rate": 9.57840139057007e-07,
536
+ "loss": 0.3108655512332916,
537
+ "step": 66,
538
+ "token_acc": 0.8931441903114319
539
+ },
540
+ {
541
+ "epoch": 0.35781041388518026,
542
+ "grad_norm": 1.42662289804713,
543
+ "learning_rate": 9.560540456994939e-07,
544
+ "loss": 0.2712291479110718,
545
+ "step": 67,
546
+ "token_acc": 0.9068335890769958
547
+ },
548
+ {
549
+ "epoch": 0.36315086782376504,
550
+ "grad_norm": 1.4428041843820245,
551
+ "learning_rate": 9.542326359097617e-07,
552
+ "loss": 0.29337918758392334,
553
+ "step": 68,
554
+ "token_acc": 0.9008380770683289
555
+ },
556
+ {
557
+ "epoch": 0.3684913217623498,
558
+ "grad_norm": 1.4505913834841988,
559
+ "learning_rate": 9.523760507362151e-07,
560
+ "loss": 0.2790825366973877,
561
+ "step": 69,
562
+ "token_acc": 0.9048055410385132
563
+ },
564
+ {
565
+ "epoch": 0.37383177570093457,
566
+ "grad_norm": 1.4289939758067638,
567
+ "learning_rate": 9.504844339512094e-07,
568
+ "loss": 0.2657867670059204,
569
+ "step": 70,
570
+ "token_acc": 0.9082612991333008
571
+ },
572
+ {
573
+ "epoch": 0.37917222963951935,
574
+ "grad_norm": 1.510860982065089,
575
+ "learning_rate": 9.485579320399183e-07,
576
+ "loss": 0.3108121156692505,
577
+ "step": 71,
578
+ "token_acc": 0.8939459323883057
579
+ },
580
+ {
581
+ "epoch": 0.38451268357810414,
582
+ "grad_norm": 1.312682482794381,
583
+ "learning_rate": 9.465966941889891e-07,
584
+ "loss": 0.23279854655265808,
585
+ "step": 72,
586
+ "token_acc": 0.9207527041435242
587
+ },
588
+ {
589
+ "epoch": 0.38985313751668893,
590
+ "grad_norm": 1.4699417988775814,
591
+ "learning_rate": 9.446008722749905e-07,
592
+ "loss": 0.28645938634872437,
593
+ "step": 73,
594
+ "token_acc": 0.9035031795501709
595
+ },
596
+ {
597
+ "epoch": 0.3951935914552737,
598
+ "grad_norm": 1.3500117274900032,
599
+ "learning_rate": 9.425706208526515e-07,
600
+ "loss": 0.27431654930114746,
601
+ "step": 74,
602
+ "token_acc": 0.9042099714279175
603
+ },
604
+ {
605
+ "epoch": 0.40053404539385845,
606
+ "grad_norm": 1.4713499460053907,
607
+ "learning_rate": 9.405060971428922e-07,
608
+ "loss": 0.29679012298583984,
609
+ "step": 75,
610
+ "token_acc": 0.8999800086021423
611
+ },
612
+ {
613
+ "epoch": 0.40587449933244324,
614
+ "grad_norm": 1.4818382523702867,
615
+ "learning_rate": 9.384074610206493e-07,
616
+ "loss": 0.29305019974708557,
617
+ "step": 76,
618
+ "token_acc": 0.898842990398407
619
+ },
620
+ {
621
+ "epoch": 0.411214953271028,
622
+ "grad_norm": 1.4493370130800018,
623
+ "learning_rate": 9.362748750024952e-07,
624
+ "loss": 0.2696800231933594,
625
+ "step": 77,
626
+ "token_acc": 0.9080367088317871
627
+ },
628
+ {
629
+ "epoch": 0.4165554072096128,
630
+ "grad_norm": 1.5709905022949062,
631
+ "learning_rate": 9.341085042340531e-07,
632
+ "loss": 0.32400715351104736,
633
+ "step": 78,
634
+ "token_acc": 0.8896335363388062
635
+ },
636
+ {
637
+ "epoch": 0.4218958611481976,
638
+ "grad_norm": 1.571526565600695,
639
+ "learning_rate": 9.31908516477208e-07,
640
+ "loss": 0.30972063541412354,
641
+ "step": 79,
642
+ "token_acc": 0.8935267925262451
643
+ },
644
+ {
645
+ "epoch": 0.4272363150867824,
646
+ "grad_norm": 1.4042062660347052,
647
+ "learning_rate": 9.296750820971157e-07,
648
+ "loss": 0.2732260227203369,
649
+ "step": 80,
650
+ "token_acc": 0.9055958390235901
651
+ },
652
+ {
653
+ "epoch": 0.4325767690253672,
654
+ "grad_norm": 1.4305861561440973,
655
+ "learning_rate": 9.274083740490096e-07,
656
+ "loss": 0.26816362142562866,
657
+ "step": 81,
658
+ "token_acc": 0.9088789820671082
659
+ },
660
+ {
661
+ "epoch": 0.4379172229639519,
662
+ "grad_norm": 1.4109974033898394,
663
+ "learning_rate": 9.251085678648071e-07,
664
+ "loss": 0.23632025718688965,
665
+ "step": 82,
666
+ "token_acc": 0.9193145036697388
667
+ },
668
+ {
669
+ "epoch": 0.4432576769025367,
670
+ "grad_norm": 1.579783094360126,
671
+ "learning_rate": 9.227758416395169e-07,
672
+ "loss": 0.32243475317955017,
673
+ "step": 83,
674
+ "token_acc": 0.8915097713470459
675
+ },
676
+ {
677
+ "epoch": 0.4485981308411215,
678
+ "grad_norm": 1.444883529989335,
679
+ "learning_rate": 9.204103760174471e-07,
680
+ "loss": 0.27780580520629883,
681
+ "step": 84,
682
+ "token_acc": 0.903154730796814
683
+ },
684
+ {
685
+ "epoch": 0.4539385847797063,
686
+ "grad_norm": 1.4743610793683541,
687
+ "learning_rate": 9.18012354178217e-07,
688
+ "loss": 0.290909081697464,
689
+ "step": 85,
690
+ "token_acc": 0.8995449542999268
691
+ },
692
+ {
693
+ "epoch": 0.45927903871829107,
694
+ "grad_norm": 1.4453910878354272,
695
+ "learning_rate": 9.155819618225706e-07,
696
+ "loss": 0.2741404175758362,
697
+ "step": 86,
698
+ "token_acc": 0.9050561785697937
699
+ },
700
+ {
701
+ "epoch": 0.46461949265687585,
702
+ "grad_norm": 1.5341161775376193,
703
+ "learning_rate": 9.131193871579974e-07,
704
+ "loss": 0.29184362292289734,
705
+ "step": 87,
706
+ "token_acc": 0.8988983631134033
707
+ },
708
+ {
709
+ "epoch": 0.4699599465954606,
710
+ "grad_norm": 1.4215267618699114,
711
+ "learning_rate": 9.106248208841568e-07,
712
+ "loss": 0.27542126178741455,
713
+ "step": 88,
714
+ "token_acc": 0.906243622303009
715
+ },
716
+ {
717
+ "epoch": 0.4753004005340454,
718
+ "grad_norm": 1.4725473172620342,
719
+ "learning_rate": 9.080984561781109e-07,
720
+ "loss": 0.2945716977119446,
721
+ "step": 89,
722
+ "token_acc": 0.8966306447982788
723
+ },
724
+ {
725
+ "epoch": 0.48064085447263016,
726
+ "grad_norm": 1.4591526761766243,
727
+ "learning_rate": 9.05540488679365e-07,
728
+ "loss": 0.2776861786842346,
729
+ "step": 90,
730
+ "token_acc": 0.9028105139732361
731
+ },
732
+ {
733
+ "epoch": 0.48598130841121495,
734
+ "grad_norm": 1.431454776628444,
735
+ "learning_rate": 9.029511164747175e-07,
736
+ "loss": 0.28304219245910645,
737
+ "step": 91,
738
+ "token_acc": 0.9032279849052429
739
+ },
740
+ {
741
+ "epoch": 0.49132176234979974,
742
+ "grad_norm": 1.4748810607233322,
743
+ "learning_rate": 9.0033054008292e-07,
744
+ "loss": 0.27895230054855347,
745
+ "step": 92,
746
+ "token_acc": 0.9046729207038879
747
+ },
748
+ {
749
+ "epoch": 0.49666221628838453,
750
+ "grad_norm": 1.5007381614880584,
751
+ "learning_rate": 8.976789624391497e-07,
752
+ "loss": 0.28230053186416626,
753
+ "step": 93,
754
+ "token_acc": 0.9033601880073547
755
+ },
756
+ {
757
+ "epoch": 0.5020026702269693,
758
+ "grad_norm": 1.4839915635561016,
759
+ "learning_rate": 8.94996588879294e-07,
760
+ "loss": 0.27275383472442627,
761
+ "step": 94,
762
+ "token_acc": 0.9072387218475342
763
+ },
764
+ {
765
+ "epoch": 0.507343124165554,
766
+ "grad_norm": 1.4575359090259006,
767
+ "learning_rate": 8.922836271240491e-07,
768
+ "loss": 0.2795729637145996,
769
+ "step": 95,
770
+ "token_acc": 0.9037200808525085
771
+ },
772
+ {
773
+ "epoch": 0.5126835781041389,
774
+ "grad_norm": 1.4275482143438216,
775
+ "learning_rate": 8.895402872628351e-07,
776
+ "loss": 0.2748318910598755,
777
+ "step": 96,
778
+ "token_acc": 0.9038447737693787
779
+ },
780
+ {
781
+ "epoch": 0.5180240320427236,
782
+ "grad_norm": 1.4996164861212264,
783
+ "learning_rate": 8.867667817375265e-07,
784
+ "loss": 0.30395227670669556,
785
+ "step": 97,
786
+ "token_acc": 0.8991894125938416
787
+ },
788
+ {
789
+ "epoch": 0.5233644859813084,
790
+ "grad_norm": 1.63200655269095,
791
+ "learning_rate": 8.839633253260005e-07,
792
+ "loss": 0.3181121051311493,
793
+ "step": 98,
794
+ "token_acc": 0.8909761309623718
795
+ },
796
+ {
797
+ "epoch": 0.5287049399198932,
798
+ "grad_norm": 1.4487856510791033,
799
+ "learning_rate": 8.811301351255052e-07,
800
+ "loss": 0.27428990602493286,
801
+ "step": 99,
802
+ "token_acc": 0.9081797003746033
803
+ },
804
+ {
805
+ "epoch": 0.5340453938584779,
806
+ "grad_norm": 1.3755745306694576,
807
+ "learning_rate": 8.782674305358479e-07,
808
+ "loss": 0.23392319679260254,
809
+ "step": 100,
810
+ "token_acc": 0.9194831848144531
811
+ },
812
+ {
813
+ "epoch": 0.5393858477970628,
814
+ "grad_norm": 1.3783872170462725,
815
+ "learning_rate": 8.753754332424046e-07,
816
+ "loss": 0.25885897874832153,
817
+ "step": 101,
818
+ "token_acc": 0.9093189835548401
819
+ },
820
+ {
821
+ "epoch": 0.5447263017356475,
822
+ "grad_norm": 1.4673998061357842,
823
+ "learning_rate": 8.724543671989529e-07,
824
+ "loss": 0.27853184938430786,
825
+ "step": 102,
826
+ "token_acc": 0.9039020538330078
827
+ },
828
+ {
829
+ "epoch": 0.5500667556742324,
830
+ "grad_norm": 1.468751593365532,
831
+ "learning_rate": 8.695044586103295e-07,
832
+ "loss": 0.2907976508140564,
833
+ "step": 103,
834
+ "token_acc": 0.9023234248161316
835
+ },
836
+ {
837
+ "epoch": 0.5554072096128171,
838
+ "grad_norm": 1.3942453997655584,
839
+ "learning_rate": 8.66525935914913e-07,
840
+ "loss": 0.26022887229919434,
841
+ "step": 104,
842
+ "token_acc": 0.9076283574104309
843
+ },
844
+ {
845
+ "epoch": 0.5607476635514018,
846
+ "grad_norm": 1.4405529584001042,
847
+ "learning_rate": 8.635190297669339e-07,
848
+ "loss": 0.26023077964782715,
849
+ "step": 105,
850
+ "token_acc": 0.9096285700798035
851
+ },
852
+ {
853
+ "epoch": 0.5660881174899867,
854
+ "grad_norm": 1.4704608320018198,
855
+ "learning_rate": 8.604839730186124e-07,
856
+ "loss": 0.257341593503952,
857
+ "step": 106,
858
+ "token_acc": 0.9118361473083496
859
+ },
860
+ {
861
+ "epoch": 0.5714285714285714,
862
+ "grad_norm": 1.448708511759169,
863
+ "learning_rate": 8.57421000702127e-07,
864
+ "loss": 0.27755892276763916,
865
+ "step": 107,
866
+ "token_acc": 0.9039767384529114
867
+ },
868
+ {
869
+ "epoch": 0.5767690253671562,
870
+ "grad_norm": 1.3687283265061863,
871
+ "learning_rate": 8.543303500114141e-07,
872
+ "loss": 0.2541080713272095,
873
+ "step": 108,
874
+ "token_acc": 0.9100450873374939
875
+ },
876
+ {
877
+ "epoch": 0.582109479305741,
878
+ "grad_norm": 1.5076396646770536,
879
+ "learning_rate": 8.512122602837992e-07,
880
+ "loss": 0.3047584295272827,
881
+ "step": 109,
882
+ "token_acc": 0.8959829211235046
883
+ },
884
+ {
885
+ "epoch": 0.5874499332443258,
886
+ "grad_norm": 1.5146292336620015,
887
+ "learning_rate": 8.480669729814633e-07,
888
+ "loss": 0.30244219303131104,
889
+ "step": 110,
890
+ "token_acc": 0.8954659104347229
891
+ },
892
+ {
893
+ "epoch": 0.5927903871829105,
894
+ "grad_norm": 1.5321775985722281,
895
+ "learning_rate": 8.448947316727442e-07,
896
+ "loss": 0.31041330099105835,
897
+ "step": 111,
898
+ "token_acc": 0.894790768623352
899
+ },
900
+ {
901
+ "epoch": 0.5981308411214953,
902
+ "grad_norm": 1.5104925518676726,
903
+ "learning_rate": 8.416957820132741e-07,
904
+ "loss": 0.29461923241615295,
905
+ "step": 112,
906
+ "token_acc": 0.8996652960777283
907
+ },
908
+ {
909
+ "epoch": 0.6034712950600801,
910
+ "grad_norm": 1.5074874404548617,
911
+ "learning_rate": 8.384703717269583e-07,
912
+ "loss": 0.30026569962501526,
913
+ "step": 113,
914
+ "token_acc": 0.8964109420776367
915
+ },
916
+ {
917
+ "epoch": 0.6088117489986649,
918
+ "grad_norm": 1.430948277878645,
919
+ "learning_rate": 8.35218750586789e-07,
920
+ "loss": 0.27259859442710876,
921
+ "step": 114,
922
+ "token_acc": 0.9043173789978027
923
+ },
924
+ {
925
+ "epoch": 0.6141522029372497,
926
+ "grad_norm": 1.4730184398133797,
927
+ "learning_rate": 8.319411703955041e-07,
928
+ "loss": 0.28818240761756897,
929
+ "step": 115,
930
+ "token_acc": 0.901012659072876
931
+ },
932
+ {
933
+ "epoch": 0.6194926568758344,
934
+ "grad_norm": 1.4737839717551757,
935
+ "learning_rate": 8.286378849660895e-07,
936
+ "loss": 0.27523326873779297,
937
+ "step": 116,
938
+ "token_acc": 0.9044082164764404
939
+ },
940
+ {
941
+ "epoch": 0.6248331108144193,
942
+ "grad_norm": 1.3893191266941896,
943
+ "learning_rate": 8.25309150102121e-07,
944
+ "loss": 0.2681213617324829,
945
+ "step": 117,
946
+ "token_acc": 0.9055965542793274
947
+ },
948
+ {
949
+ "epoch": 0.630173564753004,
950
+ "grad_norm": 1.4487156196233832,
951
+ "learning_rate": 8.219552235779578e-07,
952
+ "loss": 0.2612762451171875,
953
+ "step": 118,
954
+ "token_acc": 0.9065930247306824
955
+ },
956
+ {
957
+ "epoch": 0.6355140186915887,
958
+ "grad_norm": 1.3809737797890187,
959
+ "learning_rate": 8.185763651187789e-07,
960
+ "loss": 0.26775848865509033,
961
+ "step": 119,
962
+ "token_acc": 0.9093659520149231
963
+ },
964
+ {
965
+ "epoch": 0.6408544726301736,
966
+ "grad_norm": 1.4475105084507855,
967
+ "learning_rate": 8.151728363804713e-07,
968
+ "loss": 0.2951820492744446,
969
+ "step": 120,
970
+ "token_acc": 0.8978663682937622
971
+ },
972
+ {
973
+ "epoch": 0.6461949265687583,
974
+ "grad_norm": 1.4139139859602043,
975
+ "learning_rate": 8.117449009293668e-07,
976
+ "loss": 0.2766643762588501,
977
+ "step": 121,
978
+ "token_acc": 0.9017517566680908
979
+ },
980
+ {
981
+ "epoch": 0.6515353805073432,
982
+ "grad_norm": 1.5121148872564947,
983
+ "learning_rate": 8.082928242218321e-07,
984
+ "loss": 0.30561524629592896,
985
+ "step": 122,
986
+ "token_acc": 0.897788941860199
987
+ },
988
+ {
989
+ "epoch": 0.6568758344459279,
990
+ "grad_norm": 1.4841028682972484,
991
+ "learning_rate": 8.04816873583712e-07,
992
+ "loss": 0.2939586043357849,
993
+ "step": 123,
994
+ "token_acc": 0.9001566171646118
995
+ },
996
+ {
997
+ "epoch": 0.6622162883845126,
998
+ "grad_norm": 1.4245067768897755,
999
+ "learning_rate": 8.013173181896282e-07,
1000
+ "loss": 0.2514035105705261,
1001
+ "step": 124,
1002
+ "token_acc": 0.9155417680740356
1003
+ },
1004
+ {
1005
+ "epoch": 0.6675567423230975,
1006
+ "grad_norm": 1.3802195837048552,
1007
+ "learning_rate": 7.977944290421339e-07,
1008
+ "loss": 0.2620801329612732,
1009
+ "step": 125,
1010
+ "token_acc": 0.9096019268035889
1011
+ },
1012
+ {
1013
+ "epoch": 0.6728971962616822,
1014
+ "grad_norm": 1.461725826567453,
1015
+ "learning_rate": 7.942484789507282e-07,
1016
+ "loss": 0.27589190006256104,
1017
+ "step": 126,
1018
+ "token_acc": 0.9012653231620789
1019
+ },
1020
+ {
1021
+ "epoch": 0.678237650200267,
1022
+ "grad_norm": 1.4413519022677317,
1023
+ "learning_rate": 7.906797425107298e-07,
1024
+ "loss": 0.26920682191848755,
1025
+ "step": 127,
1026
+ "token_acc": 0.9086182713508606
1027
+ },
1028
+ {
1029
+ "epoch": 0.6835781041388518,
1030
+ "grad_norm": 1.367892107085817,
1031
+ "learning_rate": 7.870884960820129e-07,
1032
+ "loss": 0.2539078891277313,
1033
+ "step": 128,
1034
+ "token_acc": 0.9143032431602478
1035
+ },
1036
+ {
1037
+ "epoch": 0.6889185580774366,
1038
+ "grad_norm": 1.5817696641183787,
1039
+ "learning_rate": 7.834750177676057e-07,
1040
+ "loss": 0.3091282248497009,
1041
+ "step": 129,
1042
+ "token_acc": 0.891278862953186
1043
+ },
1044
+ {
1045
+ "epoch": 0.6942590120160214,
1046
+ "grad_norm": 1.5302522292243204,
1047
+ "learning_rate": 7.798395873921541e-07,
1048
+ "loss": 0.27863165736198425,
1049
+ "step": 130,
1050
+ "token_acc": 0.9007149338722229
1051
+ },
1052
+ {
1053
+ "epoch": 0.6995994659546061,
1054
+ "grad_norm": 1.4659073800662585,
1055
+ "learning_rate": 7.761824864802528e-07,
1056
+ "loss": 0.28092169761657715,
1057
+ "step": 131,
1058
+ "token_acc": 0.9041672348976135
1059
+ },
1060
+ {
1061
+ "epoch": 0.7049399198931909,
1062
+ "grad_norm": 1.5118745047717976,
1063
+ "learning_rate": 7.725039982346448e-07,
1064
+ "loss": 0.30099111795425415,
1065
+ "step": 132,
1066
+ "token_acc": 0.8950716257095337
1067
+ },
1068
+ {
1069
+ "epoch": 0.7102803738317757,
1070
+ "grad_norm": 1.457094154522222,
1071
+ "learning_rate": 7.688044075142887e-07,
1072
+ "loss": 0.29831060767173767,
1073
+ "step": 133,
1074
+ "token_acc": 0.8978042602539062
1075
+ },
1076
+ {
1077
+ "epoch": 0.7156208277703605,
1078
+ "grad_norm": 1.4662059075543796,
1079
+ "learning_rate": 7.650840008123014e-07,
1080
+ "loss": 0.27699634432792664,
1081
+ "step": 134,
1082
+ "token_acc": 0.9014725685119629
1083
+ },
1084
+ {
1085
+ "epoch": 0.7209612817089452,
1086
+ "grad_norm": 1.4413615253320124,
1087
+ "learning_rate": 7.613430662337714e-07,
1088
+ "loss": 0.28902721405029297,
1089
+ "step": 135,
1090
+ "token_acc": 0.9037944078445435
1091
+ },
1092
+ {
1093
+ "epoch": 0.7263017356475301,
1094
+ "grad_norm": 1.5447834440335302,
1095
+ "learning_rate": 7.575818934734479e-07,
1096
+ "loss": 0.30010080337524414,
1097
+ "step": 136,
1098
+ "token_acc": 0.897688627243042
1099
+ },
1100
+ {
1101
+ "epoch": 0.7316421895861148,
1102
+ "grad_norm": 1.534480828454567,
1103
+ "learning_rate": 7.538007737933079e-07,
1104
+ "loss": 0.28456270694732666,
1105
+ "step": 137,
1106
+ "token_acc": 0.9014143347740173
1107
+ },
1108
+ {
1109
+ "epoch": 0.7369826435246996,
1110
+ "grad_norm": 1.4040106816829079,
1111
+ "learning_rate": 7.5e-07,
1112
+ "loss": 0.2786479890346527,
1113
+ "step": 138,
1114
+ "token_acc": 0.9083135724067688
1115
+ },
1116
+ {
1117
+ "epoch": 0.7423230974632844,
1118
+ "grad_norm": 1.693219878226182,
1119
+ "learning_rate": 7.46179866422171e-07,
1120
+ "loss": 0.30642837285995483,
1121
+ "step": 139,
1122
+ "token_acc": 0.8953761458396912
1123
+ },
1124
+ {
1125
+ "epoch": 0.7476635514018691,
1126
+ "grad_norm": 1.5123956340013087,
1127
+ "learning_rate": 7.423406688876726e-07,
1128
+ "loss": 0.2847447991371155,
1129
+ "step": 140,
1130
+ "token_acc": 0.9026427268981934
1131
+ },
1132
+ {
1133
+ "epoch": 0.753004005340454,
1134
+ "grad_norm": 1.5165972852128844,
1135
+ "learning_rate": 7.384827047006529e-07,
1136
+ "loss": 0.28060221672058105,
1137
+ "step": 141,
1138
+ "token_acc": 0.9037265181541443
1139
+ },
1140
+ {
1141
+ "epoch": 0.7583444592790387,
1142
+ "grad_norm": 1.4884818065566605,
1143
+ "learning_rate": 7.346062726185331e-07,
1144
+ "loss": 0.29293128848075867,
1145
+ "step": 142,
1146
+ "token_acc": 0.8995508551597595
1147
+ },
1148
+ {
1149
+ "epoch": 0.7636849132176236,
1150
+ "grad_norm": 1.448783078032984,
1151
+ "learning_rate": 7.307116728288726e-07,
1152
+ "loss": 0.2762266993522644,
1153
+ "step": 143,
1154
+ "token_acc": 0.905832052230835
1155
+ },
1156
+ {
1157
+ "epoch": 0.7690253671562083,
1158
+ "grad_norm": 1.4969627454330798,
1159
+ "learning_rate": 7.267992069261221e-07,
1160
+ "loss": 0.30249935388565063,
1161
+ "step": 144,
1162
+ "token_acc": 0.8975799083709717
1163
+ },
1164
+ {
1165
+ "epoch": 0.774365821094793,
1166
+ "grad_norm": 1.4402831472902118,
1167
+ "learning_rate": 7.228691778882692e-07,
1168
+ "loss": 0.267535924911499,
1169
+ "step": 145,
1170
+ "token_acc": 0.9076101183891296
1171
+ },
1172
+ {
1173
+ "epoch": 0.7797062750333779,
1174
+ "grad_norm": 1.4908723191951325,
1175
+ "learning_rate": 7.189218900533749e-07,
1176
+ "loss": 0.3062886595726013,
1177
+ "step": 146,
1178
+ "token_acc": 0.8947438597679138
1179
+ },
1180
+ {
1181
+ "epoch": 0.7850467289719626,
1182
+ "grad_norm": 1.4437415050725992,
1183
+ "learning_rate": 7.149576490960072e-07,
1184
+ "loss": 0.2801040709018707,
1185
+ "step": 147,
1186
+ "token_acc": 0.9041796326637268
1187
+ },
1188
+ {
1189
+ "epoch": 0.7903871829105474,
1190
+ "grad_norm": 1.4899191386757624,
1191
+ "learning_rate": 7.109767620035688e-07,
1192
+ "loss": 0.28240880370140076,
1193
+ "step": 148,
1194
+ "token_acc": 0.902775764465332
1195
+ },
1196
+ {
1197
+ "epoch": 0.7957276368491322,
1198
+ "grad_norm": 1.3643095946721608,
1199
+ "learning_rate": 7.069795370525251e-07,
1200
+ "loss": 0.25867897272109985,
1201
+ "step": 149,
1202
+ "token_acc": 0.9112460613250732
1203
+ },
1204
+ {
1205
+ "epoch": 0.8010680907877169,
1206
+ "grad_norm": 1.4178796095004065,
1207
+ "learning_rate": 7.029662837845311e-07,
1208
+ "loss": 0.276249498128891,
1209
+ "step": 150,
1210
+ "token_acc": 0.9065636396408081
1211
+ },
1212
+ {
1213
+ "epoch": 0.8064085447263017,
1214
+ "grad_norm": 1.472665746353715,
1215
+ "learning_rate": 6.989373129824604e-07,
1216
+ "loss": 0.27797502279281616,
1217
+ "step": 151,
1218
+ "token_acc": 0.9020600318908691
1219
+ },
1220
+ {
1221
+ "epoch": 0.8117489986648865,
1222
+ "grad_norm": 1.2857162836865903,
1223
+ "learning_rate": 6.948929366463396e-07,
1224
+ "loss": 0.22690004110336304,
1225
+ "step": 152,
1226
+ "token_acc": 0.9221194386482239
1227
+ },
1228
+ {
1229
+ "epoch": 0.8170894526034713,
1230
+ "grad_norm": 1.5413852318610612,
1231
+ "learning_rate": 6.908334679691863e-07,
1232
+ "loss": 0.3124600648880005,
1233
+ "step": 153,
1234
+ "token_acc": 0.895993709564209
1235
+ },
1236
+ {
1237
+ "epoch": 0.822429906542056,
1238
+ "grad_norm": 1.5503364220585383,
1239
+ "learning_rate": 6.867592213127557e-07,
1240
+ "loss": 0.2983526289463043,
1241
+ "step": 154,
1242
+ "token_acc": 0.8980738520622253
1243
+ },
1244
+ {
1245
+ "epoch": 0.8277703604806409,
1246
+ "grad_norm": 1.456305481825788,
1247
+ "learning_rate": 6.826705121831976e-07,
1248
+ "loss": 0.2825569212436676,
1249
+ "step": 155,
1250
+ "token_acc": 0.9024941921234131
1251
+ },
1252
+ {
1253
+ "epoch": 0.8331108144192256,
1254
+ "grad_norm": 1.552345382355808,
1255
+ "learning_rate": 6.785676572066223e-07,
1256
+ "loss": 0.28823018074035645,
1257
+ "step": 156,
1258
+ "token_acc": 0.8996476531028748
1259
+ },
1260
+ {
1261
+ "epoch": 0.8384512683578104,
1262
+ "grad_norm": 1.463702360369313,
1263
+ "learning_rate": 6.744509741045834e-07,
1264
+ "loss": 0.2687251567840576,
1265
+ "step": 157,
1266
+ "token_acc": 0.9064703583717346
1267
+ },
1268
+ {
1269
+ "epoch": 0.8437917222963952,
1270
+ "grad_norm": 1.3516216726169812,
1271
+ "learning_rate": 6.703207816694718e-07,
1272
+ "loss": 0.26400265097618103,
1273
+ "step": 158,
1274
+ "token_acc": 0.905772864818573
1275
+ },
1276
+ {
1277
+ "epoch": 0.8491321762349799,
1278
+ "grad_norm": 1.4476139419013239,
1279
+ "learning_rate": 6.661773997398297e-07,
1280
+ "loss": 0.26589322090148926,
1281
+ "step": 159,
1282
+ "token_acc": 0.9063243269920349
1283
+ },
1284
+ {
1285
+ "epoch": 0.8544726301735648,
1286
+ "grad_norm": 1.367534189635397,
1287
+ "learning_rate": 6.62021149175583e-07,
1288
+ "loss": 0.25522464513778687,
1289
+ "step": 160,
1290
+ "token_acc": 0.9129465818405151
1291
+ },
1292
+ {
1293
+ "epoch": 0.8598130841121495,
1294
+ "grad_norm": 1.4613995712079086,
1295
+ "learning_rate": 6.578523518331926e-07,
1296
+ "loss": 0.29331648349761963,
1297
+ "step": 161,
1298
+ "token_acc": 0.8985590934753418
1299
+ },
1300
+ {
1301
+ "epoch": 0.8651535380507344,
1302
+ "grad_norm": 1.4125807144896219,
1303
+ "learning_rate": 6.536713305407314e-07,
1304
+ "loss": 0.26160115003585815,
1305
+ "step": 162,
1306
+ "token_acc": 0.9072727560997009
1307
+ },
1308
+ {
1309
+ "epoch": 0.8704939919893191,
1310
+ "grad_norm": 1.54523708977056,
1311
+ "learning_rate": 6.494784090728851e-07,
1312
+ "loss": 0.30150866508483887,
1313
+ "step": 163,
1314
+ "token_acc": 0.896626889705658
1315
+ },
1316
+ {
1317
+ "epoch": 0.8758344459279038,
1318
+ "grad_norm": 1.41010615455906,
1319
+ "learning_rate": 6.45273912125878e-07,
1320
+ "loss": 0.2659100294113159,
1321
+ "step": 164,
1322
+ "token_acc": 0.9065546989440918
1323
+ },
1324
+ {
1325
+ "epoch": 0.8811748998664887,
1326
+ "grad_norm": 1.4727634670720684,
1327
+ "learning_rate": 6.410581652923297e-07,
1328
+ "loss": 0.27308836579322815,
1329
+ "step": 165,
1330
+ "token_acc": 0.9060620665550232
1331
+ },
1332
+ {
1333
+ "epoch": 0.8865153538050734,
1334
+ "grad_norm": 1.4505380629695295,
1335
+ "learning_rate": 6.368314950360415e-07,
1336
+ "loss": 0.2644720673561096,
1337
+ "step": 166,
1338
+ "token_acc": 0.9064491391181946
1339
+ },
1340
+ {
1341
+ "epoch": 0.8918558077436582,
1342
+ "grad_norm": 1.4149838933079968,
1343
+ "learning_rate": 6.325942286667148e-07,
1344
+ "loss": 0.252743661403656,
1345
+ "step": 167,
1346
+ "token_acc": 0.9134348630905151
1347
+ },
1348
+ {
1349
+ "epoch": 0.897196261682243,
1350
+ "grad_norm": 1.4192512704646,
1351
+ "learning_rate": 6.283466943146051e-07,
1352
+ "loss": 0.2717309594154358,
1353
+ "step": 168,
1354
+ "token_acc": 0.9042630195617676
1355
+ },
1356
+ {
1357
+ "epoch": 0.9025367156208278,
1358
+ "grad_norm": 1.4874485589098323,
1359
+ "learning_rate": 6.240892209051119e-07,
1360
+ "loss": 0.2797185778617859,
1361
+ "step": 169,
1362
+ "token_acc": 0.9046774506568909
1363
+ },
1364
+ {
1365
+ "epoch": 0.9078771695594126,
1366
+ "grad_norm": 1.5220997493997237,
1367
+ "learning_rate": 6.198221381333063e-07,
1368
+ "loss": 0.3090575933456421,
1369
+ "step": 170,
1370
+ "token_acc": 0.8961625099182129
1371
+ },
1372
+ {
1373
+ "epoch": 0.9132176234979973,
1374
+ "grad_norm": 1.467678079871528,
1375
+ "learning_rate": 6.155457764384e-07,
1376
+ "loss": 0.30064499378204346,
1377
+ "step": 171,
1378
+ "token_acc": 0.8983897566795349
1379
+ },
1380
+ {
1381
+ "epoch": 0.9185580774365821,
1382
+ "grad_norm": 1.5213816256226624,
1383
+ "learning_rate": 6.112604669781572e-07,
1384
+ "loss": 0.29739877581596375,
1385
+ "step": 172,
1386
+ "token_acc": 0.8958553075790405
1387
+ },
1388
+ {
1389
+ "epoch": 0.9238985313751669,
1390
+ "grad_norm": 1.4056572448993678,
1391
+ "learning_rate": 6.069665416032486e-07,
1392
+ "loss": 0.24357512593269348,
1393
+ "step": 173,
1394
+ "token_acc": 0.9159275889396667
1395
+ },
1396
+ {
1397
+ "epoch": 0.9292389853137517,
1398
+ "grad_norm": 1.4132964934246643,
1399
+ "learning_rate": 6.026643328315545e-07,
1400
+ "loss": 0.2843455672264099,
1401
+ "step": 174,
1402
+ "token_acc": 0.8996742963790894
1403
+ },
1404
+ {
1405
+ "epoch": 0.9345794392523364,
1406
+ "grad_norm": 1.5158651145960838,
1407
+ "learning_rate": 5.98354173822414e-07,
1408
+ "loss": 0.30474793910980225,
1409
+ "step": 175,
1410
+ "token_acc": 0.8991747498512268
1411
+ },
1412
+ {
1413
+ "epoch": 0.9399198931909212,
1414
+ "grad_norm": 1.5682686186076444,
1415
+ "learning_rate": 5.940363983508256e-07,
1416
+ "loss": 0.3241081237792969,
1417
+ "step": 176,
1418
+ "token_acc": 0.8867406845092773
1419
+ },
1420
+ {
1421
+ "epoch": 0.945260347129506,
1422
+ "grad_norm": 1.488780669927335,
1423
+ "learning_rate": 5.897113407816006e-07,
1424
+ "loss": 0.27237415313720703,
1425
+ "step": 177,
1426
+ "token_acc": 0.9065018892288208
1427
+ },
1428
+ {
1429
+ "epoch": 0.9506008010680908,
1430
+ "grad_norm": 1.441648821258601,
1431
+ "learning_rate": 5.853793360434687e-07,
1432
+ "loss": 0.2751544117927551,
1433
+ "step": 178,
1434
+ "token_acc": 0.9051114320755005
1435
+ },
1436
+ {
1437
+ "epoch": 0.9559412550066756,
1438
+ "grad_norm": 1.4510757578550872,
1439
+ "learning_rate": 5.810407196031436e-07,
1440
+ "loss": 0.2876569628715515,
1441
+ "step": 179,
1442
+ "token_acc": 0.9022960662841797
1443
+ },
1444
+ {
1445
+ "epoch": 0.9612817089452603,
1446
+ "grad_norm": 1.5177733417316286,
1447
+ "learning_rate": 5.766958274393428e-07,
1448
+ "loss": 0.2696794867515564,
1449
+ "step": 180,
1450
+ "token_acc": 0.9082053303718567
1451
+ },
1452
+ {
1453
+ "epoch": 0.9666221628838452,
1454
+ "grad_norm": 1.526410901108856,
1455
+ "learning_rate": 5.723449960167703e-07,
1456
+ "loss": 0.29867053031921387,
1457
+ "step": 181,
1458
+ "token_acc": 0.8969375491142273
1459
+ },
1460
+ {
1461
+ "epoch": 0.9719626168224299,
1462
+ "grad_norm": 1.5830878812419842,
1463
+ "learning_rate": 5.679885622600616e-07,
1464
+ "loss": 0.31017428636550903,
1465
+ "step": 182,
1466
+ "token_acc": 0.8941692113876343
1467
+ },
1468
+ {
1469
+ "epoch": 0.9773030707610146,
1470
+ "grad_norm": 1.479189267754833,
1471
+ "learning_rate": 5.636268635276917e-07,
1472
+ "loss": 0.2776733636856079,
1473
+ "step": 183,
1474
+ "token_acc": 0.9059219360351562
1475
+ },
1476
+ {
1477
+ "epoch": 0.9826435246995995,
1478
+ "grad_norm": 1.5067298012627606,
1479
+ "learning_rate": 5.592602375858513e-07,
1480
+ "loss": 0.2824113667011261,
1481
+ "step": 184,
1482
+ "token_acc": 0.902838408946991
1483
+ },
1484
+ {
1485
+ "epoch": 0.9879839786381842,
1486
+ "grad_norm": 1.4272874923061691,
1487
+ "learning_rate": 5.548890225822896e-07,
1488
+ "loss": 0.23751461505889893,
1489
+ "step": 185,
1490
+ "token_acc": 0.9159970879554749
1491
+ },
1492
+ {
1493
+ "epoch": 0.9933244325767691,
1494
+ "grad_norm": 1.4812489898470391,
1495
+ "learning_rate": 5.505135570201289e-07,
1496
+ "loss": 0.2700713872909546,
1497
+ "step": 186,
1498
+ "token_acc": 0.9049946069717407
1499
+ },
1500
+ {
1501
+ "epoch": 0.9986648865153538,
1502
+ "grad_norm": 1.5086585649641973,
1503
+ "learning_rate": 5.46134179731651e-07,
1504
+ "loss": 0.277831107378006,
1505
+ "step": 187,
1506
+ "token_acc": 0.9033421874046326
1507
+ },
1508
+ {
1509
+ "epoch": 1.0,
1510
+ "grad_norm": 3.0592845448074675,
1511
+ "learning_rate": 5.417512298520584e-07,
1512
+ "loss": 0.34686022996902466,
1513
+ "step": 188,
1514
+ "token_acc": 0.8805857300758362
1515
+ },
1516
+ {
1517
+ "epoch": 1.0,
1518
+ "eval_loss": 0.2894425392150879,
1519
+ "eval_runtime": 4.387,
1520
+ "eval_samples_per_second": 4.787,
1521
+ "eval_steps_per_second": 0.684,
1522
+ "eval_token_acc": 0.89005047082901,
1523
+ "step": 188
1524
+ }
1525
+ ],
1526
+ "logging_steps": 1,
1527
+ "max_steps": 376,
1528
+ "num_input_tokens_seen": 0,
1529
+ "num_train_epochs": 2,
1530
+ "save_steps": 500,
1531
+ "stateful_callbacks": {
1532
+ "TrainerControl": {
1533
+ "args": {
1534
+ "should_epoch_stop": false,
1535
+ "should_evaluate": false,
1536
+ "should_log": false,
1537
+ "should_save": true,
1538
+ "should_training_stop": false
1539
+ },
1540
+ "attributes": {}
1541
+ }
1542
+ },
1543
+ "total_flos": 135202588082176.0,
1544
+ "train_batch_size": 1,
1545
+ "trial_name": null,
1546
+ "trial_params": null
1547
+ }
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f46c42d7eaa8f379341619f987477062e2b43be458dc7a8af273d22d1ee8f5a
3
+ size 9041
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-188/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/args.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722",
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": 1,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 16,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-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/v4-20250916-174722/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": 100.0,
65
+ "dataloader_num_workers": 48,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722",
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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
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/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/data/self_2000_2000_1369_4_nq400_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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
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": "checkpoint-636",
378
+ "model_info": "ModelInfo(model_type='qwen2_5', model_dir='/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636', 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 0x7f75be369990>, 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": "/group/40143/hongzhuyi/model/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/qwen2.5-7b-2225q-2069q-1369q-newbs-old-click-xep-lr5e-6/checkpoint-636",
381
+ "hub": "<class 'swift.hub.hub.MSHub'>",
382
+ "evaluation_strategy": "epoch",
383
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722', 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=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-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/v4-20250916-174722/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=100.0, dataloader_num_workers=48, dataloader_prefetch_factor=10, past_index=-1, run_name='/group/40143/hongzhuyi/ms-swift/output/v4-20250916-174722', 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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step376
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d318c8063369ba228b5e1e50ef26dc81b4038206198a96d54b67d13d4a188a41
3
+ size 4877660776
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6f5eb922c504cf5b4da4e1919f0223e03a7ff5fb5454270a33e75b170d28fe
3
+ size 4932751008
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69afac47b13807f5d21689112241b2717223566631212636e42c5795f0617348
3
+ size 4330865200
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74233f4dcbcb35490f498e79d72ac661f0a4e3ada8a4c82e975c77a8207ab63d
3
+ size 1089994880
qwen2.5-7b-2225q-2069q-1369q-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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-rft1-newbs-old-click-2ep-lr1e-6/checkpoint-376/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