leiwx52 commited on
Commit
fb99f85
·
verified ·
1 Parent(s): 54b02ee

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. .gitattributes +1 -0
  2. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/added_tokens.json +28 -0
  3. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/args.json +392 -0
  4. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/chat_template.jinja +120 -0
  5. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/config.json +70 -0
  6. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/generation_config.json +13 -0
  7. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/latest +1 -0
  8. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/merges.txt +0 -0
  9. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/model-00001-of-00002.safetensors +3 -0
  10. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/model-00002-of-00002.safetensors +3 -0
  11. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/model.safetensors.index.json +722 -0
  12. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/preprocessor_config.json +21 -0
  13. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/special_tokens_map.json +31 -0
  14. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/tokenizer.json +3 -0
  15. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/tokenizer_config.json +240 -0
  16. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/trainer_state.json +3534 -0
  17. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/training_args.bin +3 -0
  18. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/video_preprocessor_config.json +41 -0
  19. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/vocab.json +0 -0
  20. qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/zero_to_fp32.py +760 -0
.gitattributes CHANGED
@@ -73,3 +73,4 @@ qwen3-vl-4b-agentnet_shortest-30pct_lr2e-5_vit1e-5_aligner1e-5_bs384-step1564/to
73
  qwen3-vl-4b-agentnet_filter_failure_loss_reweight_lr2e-5_vit1e-5_aligner1e-5_bs384-step3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
  qwen3-vl-4b-agentnet_filter_failure_ubuntu-only_lr2e-5_vit1e-5_aligner1e-5_bs384-step636/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
  qwen3-vl-4b-agentnet_filter_failure_ubuntu-only_lr2e-5_vit1e-5_aligner1e-5_bs384_ep5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
73
  qwen3-vl-4b-agentnet_filter_failure_loss_reweight_lr2e-5_vit1e-5_aligner1e-5_bs384-step3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
  qwen3-vl-4b-agentnet_filter_failure_ubuntu-only_lr2e-5_vit1e-5_aligner1e-5_bs384-step636/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
  qwen3-vl-4b-agentnet_filter_failure_ubuntu-only_lr2e-5_vit1e-5_aligner1e-5_bs384_ep5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/args.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "no",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 4,
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": 1,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 2e-05,
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": 1.0,
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": "/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 1,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 500.0,
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
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": null,
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": 10000.0,
64
+ "dataloader_num_workers": 8,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453",
68
+ "disable_tqdm": null,
69
+ "remove_unused_columns": true,
70
+ "label_names": null,
71
+ "load_best_model_at_end": false,
72
+ "metric_for_best_model": "loss",
73
+ "greater_is_better": false,
74
+ "ignore_data_skip": false,
75
+ "fsdp": [],
76
+ "fsdp_min_num_params": 0,
77
+ "fsdp_config": null,
78
+ "fsdp_transformer_layer_cls_to_wrap": null,
79
+ "accelerator_config": {
80
+ "dispatch_batches": false
81
+ },
82
+ "parallelism_config": null,
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto",
86
+ "loss_scale": 0,
87
+ "loss_scale_window": 1000,
88
+ "initial_scale_power": 16,
89
+ "hysteresis": 2,
90
+ "min_loss_scale": 1
91
+ },
92
+ "bf16": {
93
+ "enabled": "auto"
94
+ },
95
+ "zero_optimization": {
96
+ "stage": 1,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "allgather_partitions": true,
102
+ "allgather_bucket_size": 200000000.0,
103
+ "overlap_comm": false,
104
+ "reduce_scatter": true,
105
+ "reduce_bucket_size": 200000000.0,
106
+ "contiguous_gradients": true
107
+ },
108
+ "gradient_accumulation_steps": "auto",
109
+ "gradient_clipping": "auto",
110
+ "steps_per_print": 2000,
111
+ "train_batch_size": "auto",
112
+ "train_micro_batch_size_per_gpu": "auto",
113
+ "wall_clock_breakdown": false
114
+ },
115
+ "label_smoothing_factor": 0.0,
116
+ "optim": "adamw_torch_fused",
117
+ "optim_args": null,
118
+ "adafactor": false,
119
+ "group_by_length": false,
120
+ "length_column_name": "length",
121
+ "report_to": [
122
+ "wandb"
123
+ ],
124
+ "project": "huggingface",
125
+ "trackio_space_id": "trackio",
126
+ "ddp_find_unused_parameters": null,
127
+ "ddp_bucket_cap_mb": null,
128
+ "ddp_broadcast_buffers": null,
129
+ "dataloader_pin_memory": true,
130
+ "dataloader_persistent_workers": false,
131
+ "skip_memory_metrics": true,
132
+ "use_legacy_prediction_loop": false,
133
+ "push_to_hub": false,
134
+ "resume_from_checkpoint": null,
135
+ "hub_model_id": null,
136
+ "hub_strategy": "every_save",
137
+ "hub_token": null,
138
+ "hub_private_repo": null,
139
+ "hub_always_push": false,
140
+ "hub_revision": null,
141
+ "gradient_checkpointing": true,
142
+ "gradient_checkpointing_kwargs": null,
143
+ "include_inputs_for_metrics": false,
144
+ "include_for_metrics": [],
145
+ "eval_do_concat_batches": true,
146
+ "fp16_backend": "auto",
147
+ "push_to_hub_model_id": null,
148
+ "push_to_hub_organization": null,
149
+ "push_to_hub_token": null,
150
+ "mp_parameters": "",
151
+ "auto_find_batch_size": false,
152
+ "full_determinism": false,
153
+ "torchdynamo": null,
154
+ "ray_scope": "last",
155
+ "ddp_timeout": 18000000,
156
+ "torch_compile": false,
157
+ "torch_compile_backend": null,
158
+ "torch_compile_mode": null,
159
+ "include_tokens_per_second": false,
160
+ "include_num_input_tokens_seen": false,
161
+ "neftune_noise_alpha": null,
162
+ "optim_target_modules": null,
163
+ "batch_eval_metrics": false,
164
+ "eval_on_start": false,
165
+ "use_liger_kernel": true,
166
+ "liger_kernel_config": null,
167
+ "eval_use_gather_object": false,
168
+ "average_tokens_across_devices": true,
169
+ "sortish_sampler": false,
170
+ "predict_with_generate": false,
171
+ "generation_max_length": null,
172
+ "generation_num_beams": null,
173
+ "generation_config": null,
174
+ "tuner_backend": "peft",
175
+ "vit_gradient_checkpointing": null,
176
+ "router_aux_loss_coef": 0.0,
177
+ "enable_dft_loss": false,
178
+ "enable_channel_loss": false,
179
+ "check_model": true,
180
+ "acc_strategy": "token",
181
+ "train_dataloader_shuffle": true,
182
+ "max_epochs": null,
183
+ "aligner_lr": 1e-05,
184
+ "vit_lr": 1e-05,
185
+ "use_logits_to_keep": null,
186
+ "ds3_gather_for_generation": true,
187
+ "resume_only_model": false,
188
+ "optimizer": null,
189
+ "loss_type": null,
190
+ "metric": null,
191
+ "eval_use_evalscope": false,
192
+ "eval_dataset": [],
193
+ "eval_dataset_args": null,
194
+ "eval_limit": null,
195
+ "eval_generation_config": null,
196
+ "extra_eval_args": null,
197
+ "use_flash_ckpt": false,
198
+ "use_ray": false,
199
+ "ray_exp_name": null,
200
+ "device_groups": null,
201
+ "model": "/apdcephfs_fsgm/share_304220499/mclan/checkpoints/Qwen3-VL-4B-Instruct",
202
+ "model_type": "qwen3_vl",
203
+ "model_revision": null,
204
+ "task_type": "causal_lm",
205
+ "torch_dtype": "bfloat16",
206
+ "attn_impl": "flash_attn",
207
+ "new_special_tokens": [],
208
+ "num_labels": null,
209
+ "problem_type": null,
210
+ "rope_scaling": null,
211
+ "device_map": null,
212
+ "max_memory": {},
213
+ "max_model_len": null,
214
+ "local_repo_path": null,
215
+ "init_strategy": null,
216
+ "template": "qwen3_vl",
217
+ "system": null,
218
+ "max_length": 65536,
219
+ "truncation_strategy": "delete",
220
+ "max_pixels": null,
221
+ "agent_template": null,
222
+ "norm_bbox": null,
223
+ "use_chat_template": true,
224
+ "padding_side": "right",
225
+ "padding_free": true,
226
+ "loss_scale": "default",
227
+ "sequence_parallel_size": 1,
228
+ "template_backend": "swift",
229
+ "response_prefix": null,
230
+ "enable_thinking": null,
231
+ "add_non_thinking_prefix": true,
232
+ "dataset": [
233
+ "/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_ubuntu_5k.train0107.openai_unified_converted.swift.ws4.l1.jsonl#163000",
234
+ "/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_win_mac_18k.train0107.openai_unified_converted.swift.ws4.l1.jsonl#339000",
235
+ "/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_ubuntu_5k.train0107.openai_unified_converted.swift.ws4.l2.jsonl#163000",
236
+ "/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_win_mac_18k.train0107.openai_unified_converted.swift.ws4.l2.jsonl#339000",
237
+ "/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_ubuntu_5k.train0107.openai_unified_converted.swift.ws4.l3.jsonl#163000",
238
+ "/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_win_mac_18k.train0107.openai_unified_converted.swift.ws4.l3.jsonl#339000"
239
+ ],
240
+ "val_dataset": [],
241
+ "cached_dataset": [],
242
+ "cached_val_dataset": [],
243
+ "split_dataset_ratio": 0.0,
244
+ "dataset_num_proc": 8,
245
+ "load_from_cache_file": false,
246
+ "dataset_shuffle": true,
247
+ "val_dataset_shuffle": false,
248
+ "streaming": false,
249
+ "interleave_prob": null,
250
+ "stopping_strategy": "first_exhausted",
251
+ "shuffle_buffer_size": 1000,
252
+ "download_mode": "reuse_dataset_if_exists",
253
+ "columns": {},
254
+ "strict": false,
255
+ "model_name": null,
256
+ "model_author": null,
257
+ "custom_dataset_info": [],
258
+ "quant_method": null,
259
+ "quant_bits": null,
260
+ "hqq_axis": null,
261
+ "bnb_4bit_compute_dtype": "bfloat16",
262
+ "bnb_4bit_quant_type": "nf4",
263
+ "bnb_4bit_use_double_quant": true,
264
+ "bnb_4bit_quant_storage": null,
265
+ "max_new_tokens": 64,
266
+ "temperature": 0.0,
267
+ "top_k": null,
268
+ "top_p": null,
269
+ "repetition_penalty": null,
270
+ "num_beams": 1,
271
+ "stream": false,
272
+ "stop_words": [],
273
+ "logprobs": false,
274
+ "top_logprobs": null,
275
+ "structured_outputs_regex": null,
276
+ "ckpt_dir": null,
277
+ "lora_modules": [],
278
+ "train_type": "full",
279
+ "adapters": [],
280
+ "external_plugins": [],
281
+ "model_kwargs": {},
282
+ "load_args": false,
283
+ "load_data_args": false,
284
+ "packing": false,
285
+ "packing_length": null,
286
+ "packing_num_proc": 1,
287
+ "lazy_tokenize": true,
288
+ "custom_register_path": [],
289
+ "use_hf": false,
290
+ "ignore_args_error": false,
291
+ "use_swift_lora": false,
292
+ "freeze_parameters": [],
293
+ "freeze_parameters_regex": null,
294
+ "freeze_parameters_ratio": 0.0,
295
+ "trainable_parameters": [
296
+ "model.visual.merger",
297
+ "model.visual.deepstack_merger_list"
298
+ ],
299
+ "trainable_parameters_regex": null,
300
+ "freeze_llm": false,
301
+ "freeze_vit": false,
302
+ "freeze_aligner": false,
303
+ "target_modules": [
304
+ "all-linear"
305
+ ],
306
+ "target_regex": null,
307
+ "target_parameters": null,
308
+ "modules_to_save": [],
309
+ "lora_rank": 8,
310
+ "lora_alpha": 32,
311
+ "lora_dropout": 0.05,
312
+ "lora_bias": "none",
313
+ "lora_dtype": null,
314
+ "lorap_lr_ratio": null,
315
+ "use_rslora": false,
316
+ "use_dora": false,
317
+ "lora_ga_batch_size": 2,
318
+ "lora_ga_iters": 2,
319
+ "lora_ga_max_length": 1024,
320
+ "lora_ga_direction": "ArB2r",
321
+ "lora_ga_scale": "stable",
322
+ "lora_ga_stable_gamma": 16,
323
+ "init_weights": true,
324
+ "fourier_n_frequency": 2000,
325
+ "fourier_scaling": 300.0,
326
+ "boft_block_size": 4,
327
+ "boft_block_num": 0,
328
+ "boft_n_butterfly_factor": 1,
329
+ "boft_dropout": 0.0,
330
+ "vera_rank": 256,
331
+ "vera_projection_prng_key": 0,
332
+ "vera_dropout": 0.0,
333
+ "vera_d_initial": 0.1,
334
+ "adapter_act": "gelu",
335
+ "adapter_length": 128,
336
+ "use_galore": false,
337
+ "galore_target_modules": null,
338
+ "galore_rank": 128,
339
+ "galore_update_proj_gap": 50,
340
+ "galore_scale": 1.0,
341
+ "galore_proj_type": "std",
342
+ "galore_optim_per_parameter": false,
343
+ "galore_with_embedding": false,
344
+ "galore_quantization": false,
345
+ "galore_proj_quant": false,
346
+ "galore_proj_bits": 4,
347
+ "galore_proj_group_size": 256,
348
+ "galore_cos_threshold": 0.4,
349
+ "galore_gamma_proj": 2,
350
+ "galore_queue_size": 5,
351
+ "adalora_target_r": 8,
352
+ "adalora_init_r": 12,
353
+ "adalora_tinit": 0,
354
+ "adalora_tfinal": 0,
355
+ "adalora_deltaT": 1,
356
+ "adalora_beta1": 0.85,
357
+ "adalora_beta2": 0.85,
358
+ "adalora_orth_reg_weight": 0.5,
359
+ "llamapro_num_new_blocks": 4,
360
+ "llamapro_num_groups": null,
361
+ "lisa_activated_layers": 0,
362
+ "lisa_step_interval": 20,
363
+ "reft_layer_key": null,
364
+ "reft_layers": null,
365
+ "reft_rank": 4,
366
+ "reft_intervention_type": "LoreftIntervention",
367
+ "reft_args": null,
368
+ "swanlab_token": null,
369
+ "swanlab_project": "ms-swift",
370
+ "swanlab_workspace": null,
371
+ "swanlab_exp_name": null,
372
+ "swanlab_notification_method": null,
373
+ "swanlab_webhook_url": null,
374
+ "swanlab_secret": null,
375
+ "swanlab_mode": "cloud",
376
+ "add_version": true,
377
+ "create_checkpoint_symlink": false,
378
+ "zero_hpz_partition_size": null,
379
+ "deepspeed_autotp_size": null,
380
+ "early_stop_interval": null,
381
+ "rank": 0,
382
+ "global_world_size": 96,
383
+ "local_world_size": 8,
384
+ "model_suffix": "Qwen3-VL-4B-Instruct",
385
+ "model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/apdcephfs_fsgm/share_304220499/mclan/checkpoints/Qwen3-VL-4B-Instruct', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
386
+ "model_meta": "ModelMeta(model_type='qwen3_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct', hf_model_id='Qwen/Qwen3-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking', hf_model_id='Qwen/Qwen3-VL-2B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct', hf_model_id='Qwen/Qwen3-VL-4B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking', hf_model_id='Qwen/Qwen3-VL-4B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct', hf_model_id='Qwen/Qwen3-VL-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking', hf_model_id='Qwen/Qwen3-VL-8B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct', hf_model_id='Qwen/Qwen3-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking', hf_model_id='Qwen/Qwen3-VL-32B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=<function get_model_tokenizer_qwen3_vl at 0x7f78135487c0>, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])",
387
+ "model_dir": "/apdcephfs_fsgm/share_304220499/mclan/checkpoints/Qwen3-VL-4B-Instruct",
388
+ "_val_dataset_exists": [],
389
+ "hub": "<class 'swift.hub.hub.MSHub'>",
390
+ "evaluation_strategy": "steps",
391
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=4, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=1, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, 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='/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=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, 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=10000.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 1, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': 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=['wandb'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=True, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=1e-05, vit_lr=1e-05, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
392
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/chat_template.jinja ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {%- if messages[0].content is string %}
5
+ {{- messages[0].content }}
6
+ {%- else %}
7
+ {%- for content in messages[0].content %}
8
+ {%- if 'text' in content %}
9
+ {{- content.text }}
10
+ {%- endif %}
11
+ {%- endfor %}
12
+ {%- endif %}
13
+ {{- '\n\n' }}
14
+ {%- endif %}
15
+ {{- "# 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>" }}
16
+ {%- for tool in tools %}
17
+ {{- "\n" }}
18
+ {{- tool | tojson }}
19
+ {%- endfor %}
20
+ {{- "\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" }}
21
+ {%- else %}
22
+ {%- if messages[0].role == 'system' %}
23
+ {{- '<|im_start|>system\n' }}
24
+ {%- if messages[0].content is string %}
25
+ {{- messages[0].content }}
26
+ {%- else %}
27
+ {%- for content in messages[0].content %}
28
+ {%- if 'text' in content %}
29
+ {{- content.text }}
30
+ {%- endif %}
31
+ {%- endfor %}
32
+ {%- endif %}
33
+ {{- '<|im_end|>\n' }}
34
+ {%- endif %}
35
+ {%- endif %}
36
+ {%- set image_count = namespace(value=0) %}
37
+ {%- set video_count = namespace(value=0) %}
38
+ {%- for message in messages %}
39
+ {%- if message.role == "user" %}
40
+ {{- '<|im_start|>' + message.role + '\n' }}
41
+ {%- if message.content is string %}
42
+ {{- message.content }}
43
+ {%- else %}
44
+ {%- for content in message.content %}
45
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
46
+ {%- set image_count.value = image_count.value + 1 %}
47
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
48
+ <|vision_start|><|image_pad|><|vision_end|>
49
+ {%- elif content.type == 'video' or 'video' in content %}
50
+ {%- set video_count.value = video_count.value + 1 %}
51
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
52
+ <|vision_start|><|video_pad|><|vision_end|>
53
+ {%- elif 'text' in content %}
54
+ {{- content.text }}
55
+ {%- endif %}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {{- '<|im_end|>\n' }}
59
+ {%- elif message.role == "assistant" %}
60
+ {{- '<|im_start|>' + message.role + '\n' }}
61
+ {%- if message.content is string %}
62
+ {{- message.content }}
63
+ {%- else %}
64
+ {%- for content_item in message.content %}
65
+ {%- if 'text' in content_item %}
66
+ {{- content_item.text }}
67
+ {%- endif %}
68
+ {%- endfor %}
69
+ {%- endif %}
70
+ {%- if message.tool_calls %}
71
+ {%- for tool_call in message.tool_calls %}
72
+ {%- if (loop.first and message.content) or (not loop.first) %}
73
+ {{- '\n' }}
74
+ {%- endif %}
75
+ {%- if tool_call.function %}
76
+ {%- set tool_call = tool_call.function %}
77
+ {%- endif %}
78
+ {{- '<tool_call>\n{"name": "' }}
79
+ {{- tool_call.name }}
80
+ {{- '", "arguments": ' }}
81
+ {%- if tool_call.arguments is string %}
82
+ {{- tool_call.arguments }}
83
+ {%- else %}
84
+ {{- tool_call.arguments | tojson }}
85
+ {%- endif %}
86
+ {{- '}\n</tool_call>' }}
87
+ {%- endfor %}
88
+ {%- endif %}
89
+ {{- '<|im_end|>\n' }}
90
+ {%- elif message.role == "tool" %}
91
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
92
+ {{- '<|im_start|>user' }}
93
+ {%- endif %}
94
+ {{- '\n<tool_response>\n' }}
95
+ {%- if message.content is string %}
96
+ {{- message.content }}
97
+ {%- else %}
98
+ {%- for content in message.content %}
99
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
100
+ {%- set image_count.value = image_count.value + 1 %}
101
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
102
+ <|vision_start|><|image_pad|><|vision_end|>
103
+ {%- elif content.type == 'video' or 'video' in content %}
104
+ {%- set video_count.value = video_count.value + 1 %}
105
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
106
+ <|vision_start|><|video_pad|><|vision_end|>
107
+ {%- elif 'text' in content %}
108
+ {{- content.text }}
109
+ {%- endif %}
110
+ {%- endfor %}
111
+ {%- endif %}
112
+ {{- '\n</tool_response>' }}
113
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
114
+ {{- '<|im_end|>\n' }}
115
+ {%- endif %}
116
+ {%- endif %}
117
+ {%- endfor %}
118
+ {%- if add_generation_prompt %}
119
+ {{- '<|im_start|>assistant\n' }}
120
+ {%- endif %}
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 151645,
7
+ "hidden_size": 2560,
8
+ "image_token_id": 151655,
9
+ "model_type": "qwen3_vl",
10
+ "pad_token_id": 151643,
11
+ "text_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "bos_token_id": 151643,
15
+ "dtype": "bfloat16",
16
+ "eos_token_id": 151645,
17
+ "head_dim": 128,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 2560,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 9728,
22
+ "max_position_embeddings": 262144,
23
+ "model_type": "qwen3_vl_text",
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 36,
26
+ "num_key_value_heads": 8,
27
+ "pad_token_id": 151643,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_scaling": {
30
+ "mrope_interleaved": true,
31
+ "mrope_section": [
32
+ 24,
33
+ 20,
34
+ 20
35
+ ],
36
+ "rope_type": "default"
37
+ },
38
+ "rope_theta": 5000000,
39
+ "tie_word_embeddings": true,
40
+ "use_cache": false,
41
+ "vocab_size": 151936
42
+ },
43
+ "tie_word_embeddings": true,
44
+ "transformers_version": "4.57.1",
45
+ "video_token_id": 151656,
46
+ "vision_config": {
47
+ "deepstack_visual_indexes": [
48
+ 5,
49
+ 11,
50
+ 17
51
+ ],
52
+ "depth": 24,
53
+ "dtype": "bfloat16",
54
+ "hidden_act": "gelu_pytorch_tanh",
55
+ "hidden_size": 1024,
56
+ "in_channels": 3,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 4096,
59
+ "model_type": "qwen3_vl",
60
+ "num_heads": 16,
61
+ "num_position_embeddings": 2304,
62
+ "out_hidden_size": 2560,
63
+ "pad_token_id": 151643,
64
+ "patch_size": 16,
65
+ "spatial_merge_size": 2,
66
+ "temporal_patch_size": 2
67
+ },
68
+ "vision_end_token_id": 151653,
69
+ "vision_start_token_id": 151652
70
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.1"
13
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step500
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b130fa2b71319f11479489c2f6c4e9cff8605cd4cd2e0ee3f828178aef2f6088
3
+ size 4990497880
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e717d3c72f84363f5efcae0edaa621f842a3e36299567ce5501e77e71ed8e94f
3
+ size 4663133960
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/model.safetensors.index.json ADDED
@@ -0,0 +1,722 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4437815808,
4
+ "total_size": 9653543936
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00002-of-00002.safetensors",
8
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
15
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
18
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
26
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
29
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
37
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
40
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
43
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
48
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
51
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
59
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
62
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
70
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
73
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
81
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
84
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
87
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
91
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
92
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
95
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
98
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
102
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
103
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
106
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
109
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
114
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
116
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
117
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
119
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
120
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
124
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
125
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
128
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
134
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
136
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
139
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
147
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
150
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
158
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
161
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
164
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
168
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
169
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
172
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
180
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
183
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
186
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
190
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
191
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
194
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
197
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
202
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
205
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
208
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
213
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
216
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
219
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
223
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
224
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
227
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
235
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
238
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
241
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
245
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
246
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
249
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
252
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
256
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
257
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
260
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
263
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
267
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
268
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
271
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
274
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
277
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
278
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
279
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
282
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
285
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
288
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
289
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
290
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
292
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
293
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
295
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
296
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
301
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
304
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
307
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
311
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
312
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
315
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
318
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
321
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
322
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
323
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
325
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
326
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
329
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
332
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
334
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
337
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
340
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
344
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
345
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
348
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
350
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
351
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
354
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
355
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
356
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
358
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
359
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
361
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
362
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
365
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
366
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
367
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
370
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
378
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
381
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
384
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
388
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
389
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
392
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
395
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
399
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
400
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
403
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
406
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
407
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
409
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
410
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
411
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
412
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
413
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
414
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
415
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
416
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
417
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
418
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
419
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
421
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
422
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
423
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
424
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
425
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
426
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
427
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
428
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
429
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
430
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
431
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
433
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
434
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
435
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
436
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
437
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
438
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
439
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
440
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
441
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
442
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
443
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
445
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
446
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
447
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
448
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
449
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
450
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
451
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
452
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
453
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
454
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
455
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
457
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
458
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
459
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
460
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
461
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
462
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
463
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
464
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
465
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
466
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
467
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
468
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
469
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
470
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
471
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
472
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
473
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
474
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
475
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
476
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
477
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
478
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
479
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
480
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
481
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
482
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
483
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
484
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
485
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
486
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
487
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
488
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
489
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
490
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
491
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
492
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
493
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
494
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
495
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
496
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
497
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
498
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
499
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
500
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
501
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
502
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
503
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
504
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
505
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
506
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
507
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
508
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
509
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
510
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
511
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
512
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
513
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
514
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
515
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
516
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
517
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
518
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
519
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
520
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
521
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
522
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
523
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
524
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
525
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
526
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
527
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
528
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
529
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
530
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
531
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
532
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
533
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
534
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
535
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
536
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
537
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
538
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
539
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
540
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
541
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
542
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
543
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
544
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
545
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
546
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
547
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
548
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
549
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
550
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
551
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
552
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
553
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
554
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
555
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
556
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
557
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
558
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
559
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
560
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
561
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
562
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
563
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
564
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
565
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
566
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
567
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
568
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
569
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
570
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
571
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
572
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
573
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
574
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
575
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
576
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
577
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
578
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
579
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
580
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
581
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
582
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
583
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
584
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
585
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
586
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
587
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
588
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
589
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
590
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
591
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
592
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
593
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
594
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
595
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
596
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
597
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
598
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
599
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
600
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
601
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
602
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
603
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
604
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
605
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
606
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
607
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
608
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
609
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
610
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
611
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
612
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
613
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
614
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
615
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
616
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
617
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
618
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
619
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
620
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
621
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
622
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
623
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
624
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
625
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
626
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
627
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
628
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
629
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
630
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
631
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
632
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
633
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
634
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
635
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
636
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
637
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
638
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
639
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
640
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
641
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
642
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
643
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
644
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
645
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
646
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
647
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
648
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
649
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
650
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
651
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
652
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
653
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
654
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
655
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
656
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
657
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
658
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
659
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
660
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
661
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
662
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
663
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
664
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
665
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
666
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
667
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
668
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
669
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
670
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
671
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
672
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
673
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
674
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
675
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
676
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
677
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
678
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
679
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
680
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
681
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
682
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
683
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
684
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
685
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
686
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
687
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
688
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
689
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
690
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
691
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
692
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
693
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
694
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
695
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
696
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
697
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
698
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
699
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
700
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
701
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
702
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
703
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
704
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
705
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
706
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
707
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
708
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
709
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
710
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
711
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
712
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
713
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
714
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
715
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
716
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
717
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
718
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
719
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
720
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
721
+ }
722
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/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
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 262144,
235
+ "pad_token": "<|endoftext|>",
236
+ "processor_class": "Qwen3VLProcessor",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/trainer_state.json ADDED
@@ -0,0 +1,3534 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.12748597654258031,
6
+ "eval_steps": 10000.0,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00025497195308516065,
14
+ "grad_norm": 15.415260314941406,
15
+ "learning_rate": 5.076142131979696e-08,
16
+ "loss": 1.1610933542251587,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0005099439061703213,
21
+ "grad_norm": 15.637948989868164,
22
+ "learning_rate": 1.0152284263959391e-07,
23
+ "loss": 1.1993461847305298,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0007649158592554819,
28
+ "grad_norm": 15.91840648651123,
29
+ "learning_rate": 1.5228426395939088e-07,
30
+ "loss": 1.1827669143676758,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0010198878123406426,
35
+ "grad_norm": 15.478428840637207,
36
+ "learning_rate": 2.0304568527918783e-07,
37
+ "loss": 1.176124930381775,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.0012748597654258032,
42
+ "grad_norm": 15.785908699035645,
43
+ "learning_rate": 2.538071065989848e-07,
44
+ "loss": 1.1965456008911133,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.0015298317185109638,
49
+ "grad_norm": 15.270750999450684,
50
+ "learning_rate": 3.0456852791878176e-07,
51
+ "loss": 1.1675349473953247,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0017848036715961244,
56
+ "grad_norm": 15.401095390319824,
57
+ "learning_rate": 3.553299492385787e-07,
58
+ "loss": 1.2026066780090332,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.002039775624681285,
63
+ "grad_norm": 14.897509574890137,
64
+ "learning_rate": 4.0609137055837566e-07,
65
+ "loss": 1.1604423522949219,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0022947475777664456,
70
+ "grad_norm": 15.150520324707031,
71
+ "learning_rate": 4.568527918781726e-07,
72
+ "loss": 1.1517817974090576,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.0025497195308516064,
77
+ "grad_norm": 15.229615211486816,
78
+ "learning_rate": 5.076142131979696e-07,
79
+ "loss": 1.152367115020752,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.0028046914839367667,
84
+ "grad_norm": 12.473063468933105,
85
+ "learning_rate": 5.583756345177665e-07,
86
+ "loss": 1.0538256168365479,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.0030596634370219276,
91
+ "grad_norm": 12.416116714477539,
92
+ "learning_rate": 6.091370558375635e-07,
93
+ "loss": 1.0510058403015137,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.0033146353901070884,
98
+ "grad_norm": 11.904985427856445,
99
+ "learning_rate": 6.598984771573605e-07,
100
+ "loss": 1.0342445373535156,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.0035696073431922487,
105
+ "grad_norm": 7.985447883605957,
106
+ "learning_rate": 7.106598984771574e-07,
107
+ "loss": 0.909122109413147,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.0038245792962774095,
112
+ "grad_norm": 7.608842372894287,
113
+ "learning_rate": 7.614213197969544e-07,
114
+ "loss": 0.900871217250824,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.00407955124936257,
119
+ "grad_norm": 7.21879243850708,
120
+ "learning_rate": 8.121827411167513e-07,
121
+ "loss": 0.8900021314620972,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.004334523202447731,
126
+ "grad_norm": 6.9251909255981445,
127
+ "learning_rate": 8.629441624365482e-07,
128
+ "loss": 0.867794394493103,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.004589495155532891,
133
+ "grad_norm": 6.087664604187012,
134
+ "learning_rate": 9.137055837563452e-07,
135
+ "loss": 0.8714677095413208,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.004844467108618052,
140
+ "grad_norm": 4.437993049621582,
141
+ "learning_rate": 9.644670050761422e-07,
142
+ "loss": 0.7944602370262146,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.005099439061703213,
147
+ "grad_norm": 3.9098119735717773,
148
+ "learning_rate": 1.0152284263959392e-06,
149
+ "loss": 0.7696177959442139,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.0053544110147883735,
154
+ "grad_norm": 5.06033992767334,
155
+ "learning_rate": 1.0659898477157362e-06,
156
+ "loss": 0.7556478381156921,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.0056093829678735335,
161
+ "grad_norm": 3.4315176010131836,
162
+ "learning_rate": 1.116751269035533e-06,
163
+ "loss": 0.766305148601532,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.005864354920958694,
168
+ "grad_norm": 4.819195747375488,
169
+ "learning_rate": 1.16751269035533e-06,
170
+ "loss": 0.7652184367179871,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.006119326874043855,
175
+ "grad_norm": 3.1732325553894043,
176
+ "learning_rate": 1.218274111675127e-06,
177
+ "loss": 0.7531844973564148,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.006374298827129016,
182
+ "grad_norm": 3.403918504714966,
183
+ "learning_rate": 1.2690355329949238e-06,
184
+ "loss": 0.7432605624198914,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.006629270780214177,
189
+ "grad_norm": 6.011890888214111,
190
+ "learning_rate": 1.319796954314721e-06,
191
+ "loss": 0.7286916971206665,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.006884242733299337,
196
+ "grad_norm": 3.864213466644287,
197
+ "learning_rate": 1.3705583756345178e-06,
198
+ "loss": 0.7215209007263184,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.0071392146863844975,
203
+ "grad_norm": 4.094939231872559,
204
+ "learning_rate": 1.4213197969543148e-06,
205
+ "loss": 0.7281020879745483,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.007394186639469658,
210
+ "grad_norm": 3.790905475616455,
211
+ "learning_rate": 1.4720812182741118e-06,
212
+ "loss": 0.7287170886993408,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.007649158592554819,
217
+ "grad_norm": 4.714667797088623,
218
+ "learning_rate": 1.5228426395939088e-06,
219
+ "loss": 0.730525016784668,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.00790413054563998,
224
+ "grad_norm": 3.4293529987335205,
225
+ "learning_rate": 1.5736040609137056e-06,
226
+ "loss": 0.7161718606948853,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.00815910249872514,
231
+ "grad_norm": 2.985097885131836,
232
+ "learning_rate": 1.6243654822335026e-06,
233
+ "loss": 0.70013427734375,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.008414074451810302,
238
+ "grad_norm": 3.2844507694244385,
239
+ "learning_rate": 1.6751269035532996e-06,
240
+ "loss": 0.7102205157279968,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.008669046404895462,
245
+ "grad_norm": 2.9922728538513184,
246
+ "learning_rate": 1.7258883248730964e-06,
247
+ "loss": 0.6986203193664551,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.008924018357980621,
252
+ "grad_norm": 3.494112253189087,
253
+ "learning_rate": 1.7766497461928936e-06,
254
+ "loss": 0.705012321472168,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.009178990311065782,
259
+ "grad_norm": 2.92978572845459,
260
+ "learning_rate": 1.8274111675126904e-06,
261
+ "loss": 0.6996530294418335,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.009433962264150943,
266
+ "grad_norm": 4.036802768707275,
267
+ "learning_rate": 1.8781725888324874e-06,
268
+ "loss": 0.7008537650108337,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.009688934217236104,
273
+ "grad_norm": 7.8610358238220215,
274
+ "learning_rate": 1.9289340101522844e-06,
275
+ "loss": 0.6845177412033081,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.009943906170321265,
280
+ "grad_norm": 3.7339322566986084,
281
+ "learning_rate": 1.9796954314720814e-06,
282
+ "loss": 0.6841769218444824,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.010198878123406425,
287
+ "grad_norm": 2.830705165863037,
288
+ "learning_rate": 2.0304568527918785e-06,
289
+ "loss": 0.699475884437561,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.010453850076491586,
294
+ "grad_norm": 12.568126678466797,
295
+ "learning_rate": 2.0812182741116755e-06,
296
+ "loss": 0.6735811233520508,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.010708822029576747,
301
+ "grad_norm": 3.7829558849334717,
302
+ "learning_rate": 2.1319796954314725e-06,
303
+ "loss": 0.6893086433410645,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.010963793982661908,
308
+ "grad_norm": 4.368283271789551,
309
+ "learning_rate": 2.182741116751269e-06,
310
+ "loss": 0.6826390027999878,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.011218765935747067,
315
+ "grad_norm": 3.3035032749176025,
316
+ "learning_rate": 2.233502538071066e-06,
317
+ "loss": 0.668271541595459,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.011473737888832228,
322
+ "grad_norm": 3.9567983150482178,
323
+ "learning_rate": 2.284263959390863e-06,
324
+ "loss": 0.6784211993217468,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.011728709841917389,
329
+ "grad_norm": 3.4999377727508545,
330
+ "learning_rate": 2.33502538071066e-06,
331
+ "loss": 0.6874396204948425,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.01198368179500255,
336
+ "grad_norm": 3.2631001472473145,
337
+ "learning_rate": 2.385786802030457e-06,
338
+ "loss": 0.6772322654724121,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.01223865374808771,
343
+ "grad_norm": 20.580337524414062,
344
+ "learning_rate": 2.436548223350254e-06,
345
+ "loss": 0.6612566709518433,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.012493625701172871,
350
+ "grad_norm": 8.252683639526367,
351
+ "learning_rate": 2.487309644670051e-06,
352
+ "loss": 0.6630977392196655,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.012748597654258032,
357
+ "grad_norm": 4.531806468963623,
358
+ "learning_rate": 2.5380710659898476e-06,
359
+ "loss": 0.6681995391845703,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.013003569607343193,
364
+ "grad_norm": 3.459275960922241,
365
+ "learning_rate": 2.588832487309645e-06,
366
+ "loss": 0.6613768339157104,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.013258541560428353,
371
+ "grad_norm": 5.5584940910339355,
372
+ "learning_rate": 2.639593908629442e-06,
373
+ "loss": 0.6634055376052856,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.013513513513513514,
378
+ "grad_norm": 5.6429524421691895,
379
+ "learning_rate": 2.6903553299492387e-06,
380
+ "loss": 0.6786404848098755,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.013768485466598673,
385
+ "grad_norm": 4.319962978363037,
386
+ "learning_rate": 2.7411167512690357e-06,
387
+ "loss": 0.654949426651001,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.014023457419683834,
392
+ "grad_norm": 6.052556037902832,
393
+ "learning_rate": 2.7918781725888327e-06,
394
+ "loss": 0.6762086749076843,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.014278429372768995,
399
+ "grad_norm": 5.070164680480957,
400
+ "learning_rate": 2.8426395939086297e-06,
401
+ "loss": 0.6505463123321533,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.014533401325854156,
406
+ "grad_norm": 3.3184974193573,
407
+ "learning_rate": 2.8934010152284262e-06,
408
+ "loss": 0.6489129662513733,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.014788373278939317,
413
+ "grad_norm": 5.315630912780762,
414
+ "learning_rate": 2.9441624365482237e-06,
415
+ "loss": 0.6476598978042603,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.015043345232024477,
420
+ "grad_norm": 3.659990072250366,
421
+ "learning_rate": 2.9949238578680207e-06,
422
+ "loss": 0.6501700282096863,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.015298317185109638,
427
+ "grad_norm": 3.4091506004333496,
428
+ "learning_rate": 3.0456852791878177e-06,
429
+ "loss": 0.6517801880836487,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.015553289138194799,
434
+ "grad_norm": 3.8126204013824463,
435
+ "learning_rate": 3.0964467005076143e-06,
436
+ "loss": 0.6425204277038574,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.01580826109127996,
441
+ "grad_norm": 3.711880922317505,
442
+ "learning_rate": 3.1472081218274113e-06,
443
+ "loss": 0.638529360294342,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.01606323304436512,
448
+ "grad_norm": 7.707905292510986,
449
+ "learning_rate": 3.1979695431472087e-06,
450
+ "loss": 0.6470184922218323,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.01631820499745028,
455
+ "grad_norm": 7.1005072593688965,
456
+ "learning_rate": 3.2487309644670053e-06,
457
+ "loss": 0.6359443664550781,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.01657317695053544,
462
+ "grad_norm": 6.728579521179199,
463
+ "learning_rate": 3.2994923857868023e-06,
464
+ "loss": 0.6561862230300903,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.016828148903620603,
469
+ "grad_norm": 4.356357574462891,
470
+ "learning_rate": 3.3502538071065993e-06,
471
+ "loss": 0.6496514081954956,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.017083120856705762,
476
+ "grad_norm": 5.432864189147949,
477
+ "learning_rate": 3.4010152284263963e-06,
478
+ "loss": 0.6436284184455872,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.017338092809790925,
483
+ "grad_norm": 5.1800408363342285,
484
+ "learning_rate": 3.451776649746193e-06,
485
+ "loss": 0.6394556760787964,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.017593064762876084,
490
+ "grad_norm": 9.765804290771484,
491
+ "learning_rate": 3.5025380710659903e-06,
492
+ "loss": 0.6331816911697388,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.017848036715961243,
497
+ "grad_norm": 4.826832294464111,
498
+ "learning_rate": 3.5532994923857873e-06,
499
+ "loss": 0.6390204429626465,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.018103008669046405,
504
+ "grad_norm": 5.472368240356445,
505
+ "learning_rate": 3.6040609137055843e-06,
506
+ "loss": 0.6334278583526611,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.018357980622131564,
511
+ "grad_norm": 5.457934856414795,
512
+ "learning_rate": 3.654822335025381e-06,
513
+ "loss": 0.6240629553794861,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.018612952575216727,
518
+ "grad_norm": 6.780310153961182,
519
+ "learning_rate": 3.705583756345178e-06,
520
+ "loss": 0.63517826795578,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.018867924528301886,
525
+ "grad_norm": 3.7166168689727783,
526
+ "learning_rate": 3.756345177664975e-06,
527
+ "loss": 0.627025306224823,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.01912289648138705,
532
+ "grad_norm": 4.887142181396484,
533
+ "learning_rate": 3.8071065989847715e-06,
534
+ "loss": 0.6309980154037476,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.019377868434472208,
539
+ "grad_norm": 6.183432579040527,
540
+ "learning_rate": 3.857868020304569e-06,
541
+ "loss": 0.6254815459251404,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.01963284038755737,
546
+ "grad_norm": 4.948214530944824,
547
+ "learning_rate": 3.9086294416243655e-06,
548
+ "loss": 0.6244087219238281,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.01988781234064253,
553
+ "grad_norm": 5.138155460357666,
554
+ "learning_rate": 3.959390862944163e-06,
555
+ "loss": 0.6282638311386108,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.02014278429372769,
560
+ "grad_norm": 4.594997882843018,
561
+ "learning_rate": 4.0101522842639595e-06,
562
+ "loss": 0.6211766004562378,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.02039775624681285,
567
+ "grad_norm": 5.657145023345947,
568
+ "learning_rate": 4.060913705583757e-06,
569
+ "loss": 0.6292088627815247,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.02065272819989801,
574
+ "grad_norm": 7.0994343757629395,
575
+ "learning_rate": 4.1116751269035535e-06,
576
+ "loss": 0.6266737580299377,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.020907700152983173,
581
+ "grad_norm": 4.467260360717773,
582
+ "learning_rate": 4.162436548223351e-06,
583
+ "loss": 0.6084794998168945,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.02116267210606833,
588
+ "grad_norm": 4.804591655731201,
589
+ "learning_rate": 4.2131979695431475e-06,
590
+ "loss": 0.6341028213500977,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.021417644059153494,
595
+ "grad_norm": 4.987437725067139,
596
+ "learning_rate": 4.263959390862945e-06,
597
+ "loss": 0.6339101791381836,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.021672616012238653,
602
+ "grad_norm": 6.195011138916016,
603
+ "learning_rate": 4.3147208121827415e-06,
604
+ "loss": 0.6330238580703735,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.021927587965323816,
609
+ "grad_norm": 5.589010715484619,
610
+ "learning_rate": 4.365482233502538e-06,
611
+ "loss": 0.6271764636039734,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.022182559918408975,
616
+ "grad_norm": 10.114912033081055,
617
+ "learning_rate": 4.4162436548223355e-06,
618
+ "loss": 0.638175904750824,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.022437531871494134,
623
+ "grad_norm": 7.669949054718018,
624
+ "learning_rate": 4.467005076142132e-06,
625
+ "loss": 0.624021053314209,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.022692503824579296,
630
+ "grad_norm": 8.180469512939453,
631
+ "learning_rate": 4.5177664974619295e-06,
632
+ "loss": 0.6178176403045654,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.022947475777664456,
637
+ "grad_norm": 5.518604755401611,
638
+ "learning_rate": 4.568527918781726e-06,
639
+ "loss": 0.6195391416549683,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.023202447730749618,
644
+ "grad_norm": 5.258211612701416,
645
+ "learning_rate": 4.6192893401015235e-06,
646
+ "loss": 0.6231352686882019,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.023457419683834777,
651
+ "grad_norm": 3.893946647644043,
652
+ "learning_rate": 4.67005076142132e-06,
653
+ "loss": 0.6193073987960815,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.02371239163691994,
658
+ "grad_norm": 5.802011489868164,
659
+ "learning_rate": 4.7208121827411175e-06,
660
+ "loss": 0.6172696948051453,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.0239673635900051,
665
+ "grad_norm": 5.073032855987549,
666
+ "learning_rate": 4.771573604060914e-06,
667
+ "loss": 0.6240885853767395,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.02422233554309026,
672
+ "grad_norm": 5.177947998046875,
673
+ "learning_rate": 4.822335025380711e-06,
674
+ "loss": 0.6277825236320496,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.02447730749617542,
679
+ "grad_norm": 5.730579376220703,
680
+ "learning_rate": 4.873096446700508e-06,
681
+ "loss": 0.6149629950523376,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.024732279449260583,
686
+ "grad_norm": 6.5996551513671875,
687
+ "learning_rate": 4.923857868020305e-06,
688
+ "loss": 0.6126458644866943,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.024987251402345742,
693
+ "grad_norm": 13.988277435302734,
694
+ "learning_rate": 4.974619289340102e-06,
695
+ "loss": 0.6055952310562134,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.0252422233554309,
700
+ "grad_norm": 5.046289443969727,
701
+ "learning_rate": 5.025380710659899e-06,
702
+ "loss": 0.6105412244796753,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.025497195308516064,
707
+ "grad_norm": 5.086366176605225,
708
+ "learning_rate": 5.076142131979695e-06,
709
+ "loss": 0.6258758902549744,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.025752167261601223,
714
+ "grad_norm": 7.642775058746338,
715
+ "learning_rate": 5.126903553299493e-06,
716
+ "loss": 0.6233373880386353,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.026007139214686385,
721
+ "grad_norm": 7.112648963928223,
722
+ "learning_rate": 5.17766497461929e-06,
723
+ "loss": 0.6140401363372803,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.026262111167771544,
728
+ "grad_norm": 5.693024158477783,
729
+ "learning_rate": 5.228426395939087e-06,
730
+ "loss": 0.6101027727127075,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.026517083120856707,
735
+ "grad_norm": 4.558701515197754,
736
+ "learning_rate": 5.279187817258884e-06,
737
+ "loss": 0.6059219837188721,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.026772055073941866,
742
+ "grad_norm": 4.841275691986084,
743
+ "learning_rate": 5.329949238578681e-06,
744
+ "loss": 0.643490731716156,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.02702702702702703,
749
+ "grad_norm": 5.6230363845825195,
750
+ "learning_rate": 5.380710659898477e-06,
751
+ "loss": 0.6232346296310425,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.027281998980112188,
756
+ "grad_norm": 4.623135089874268,
757
+ "learning_rate": 5.431472081218274e-06,
758
+ "loss": 0.612013578414917,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.027536970933197347,
763
+ "grad_norm": 9.732264518737793,
764
+ "learning_rate": 5.482233502538071e-06,
765
+ "loss": 0.5976157188415527,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.02779194288628251,
770
+ "grad_norm": 6.726062774658203,
771
+ "learning_rate": 5.532994923857869e-06,
772
+ "loss": 0.6107317209243774,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.02804691483936767,
777
+ "grad_norm": 7.107174396514893,
778
+ "learning_rate": 5.583756345177665e-06,
779
+ "loss": 0.6086596846580505,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.02830188679245283,
784
+ "grad_norm": 6.202098846435547,
785
+ "learning_rate": 5.634517766497463e-06,
786
+ "loss": 0.6037451028823853,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.02855685874553799,
791
+ "grad_norm": 7.4830851554870605,
792
+ "learning_rate": 5.685279187817259e-06,
793
+ "loss": 0.6132713556289673,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.028811830698623152,
798
+ "grad_norm": 3.917173147201538,
799
+ "learning_rate": 5.736040609137057e-06,
800
+ "loss": 0.6098322868347168,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.02906680265170831,
805
+ "grad_norm": 7.616724014282227,
806
+ "learning_rate": 5.7868020304568525e-06,
807
+ "loss": 0.6145272254943848,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.029321774604793474,
812
+ "grad_norm": 4.091442108154297,
813
+ "learning_rate": 5.83756345177665e-06,
814
+ "loss": 0.6086658239364624,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.029576746557878633,
819
+ "grad_norm": 6.2335124015808105,
820
+ "learning_rate": 5.888324873096447e-06,
821
+ "loss": 0.6011253595352173,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.029831718510963796,
826
+ "grad_norm": 5.550269603729248,
827
+ "learning_rate": 5.939086294416244e-06,
828
+ "loss": 0.6046299338340759,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.030086690464048955,
833
+ "grad_norm": 7.084855079650879,
834
+ "learning_rate": 5.989847715736041e-06,
835
+ "loss": 0.6061999201774597,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.030341662417134114,
840
+ "grad_norm": 10.455710411071777,
841
+ "learning_rate": 6.040609137055839e-06,
842
+ "loss": 0.6251656413078308,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.030596634370219276,
847
+ "grad_norm": 8.010490417480469,
848
+ "learning_rate": 6.091370558375635e-06,
849
+ "loss": 0.6025846004486084,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.030851606323304435,
854
+ "grad_norm": 7.11653470993042,
855
+ "learning_rate": 6.142131979695432e-06,
856
+ "loss": 0.6091961860656738,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.031106578276389598,
861
+ "grad_norm": 4.968122959136963,
862
+ "learning_rate": 6.1928934010152285e-06,
863
+ "loss": 0.6093355417251587,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.03136155022947476,
868
+ "grad_norm": 10.246641159057617,
869
+ "learning_rate": 6.243654822335026e-06,
870
+ "loss": 0.6043275594711304,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.03161652218255992,
875
+ "grad_norm": 7.461697578430176,
876
+ "learning_rate": 6.2944162436548225e-06,
877
+ "loss": 0.5993828773498535,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.03187149413564508,
882
+ "grad_norm": 13.019267082214355,
883
+ "learning_rate": 6.34517766497462e-06,
884
+ "loss": 0.6082757711410522,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.03212646608873024,
889
+ "grad_norm": 5.950469493865967,
890
+ "learning_rate": 6.395939086294417e-06,
891
+ "loss": 0.6167939901351929,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.0323814380418154,
896
+ "grad_norm": 5.954137325286865,
897
+ "learning_rate": 6.446700507614214e-06,
898
+ "loss": 0.597322940826416,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.03263640999490056,
903
+ "grad_norm": 7.5997443199157715,
904
+ "learning_rate": 6.4974619289340105e-06,
905
+ "loss": 0.6099976301193237,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.03289138194798572,
910
+ "grad_norm": 8.977588653564453,
911
+ "learning_rate": 6.548223350253807e-06,
912
+ "loss": 0.6011739373207092,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.03314635390107088,
917
+ "grad_norm": 17.733882904052734,
918
+ "learning_rate": 6.5989847715736045e-06,
919
+ "loss": 0.6014074087142944,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.03340132585415604,
924
+ "grad_norm": 5.899418830871582,
925
+ "learning_rate": 6.649746192893401e-06,
926
+ "loss": 0.6007720828056335,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.033656297807241206,
931
+ "grad_norm": 8.74870777130127,
932
+ "learning_rate": 6.7005076142131985e-06,
933
+ "loss": 0.6171366572380066,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.033911269760326365,
938
+ "grad_norm": 4.3337788581848145,
939
+ "learning_rate": 6.751269035532996e-06,
940
+ "loss": 0.614408552646637,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.034166241713411524,
945
+ "grad_norm": 8.11375904083252,
946
+ "learning_rate": 6.8020304568527926e-06,
947
+ "loss": 0.5979299545288086,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.03442121366649668,
952
+ "grad_norm": 7.533430099487305,
953
+ "learning_rate": 6.852791878172589e-06,
954
+ "loss": 0.616156280040741,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.03467618561958185,
959
+ "grad_norm": 8.658021926879883,
960
+ "learning_rate": 6.903553299492386e-06,
961
+ "loss": 0.5952839255332947,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.03493115757266701,
966
+ "grad_norm": 4.664230823516846,
967
+ "learning_rate": 6.954314720812183e-06,
968
+ "loss": 0.6029950380325317,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.03518612952575217,
973
+ "grad_norm": 6.2738237380981445,
974
+ "learning_rate": 7.0050761421319806e-06,
975
+ "loss": 0.6155085563659668,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.03544110147883733,
980
+ "grad_norm": 6.849208354949951,
981
+ "learning_rate": 7.055837563451777e-06,
982
+ "loss": 0.6097654104232788,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.035696073431922486,
987
+ "grad_norm": 5.106319427490234,
988
+ "learning_rate": 7.106598984771575e-06,
989
+ "loss": 0.6000968217849731,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.03595104538500765,
994
+ "grad_norm": 4.99149751663208,
995
+ "learning_rate": 7.157360406091371e-06,
996
+ "loss": 0.5965438485145569,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.03620601733809281,
1001
+ "grad_norm": 4.150666236877441,
1002
+ "learning_rate": 7.208121827411169e-06,
1003
+ "loss": 0.6034414768218994,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.03646098929117797,
1008
+ "grad_norm": 4.380922794342041,
1009
+ "learning_rate": 7.258883248730964e-06,
1010
+ "loss": 0.5983131527900696,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.03671596124426313,
1015
+ "grad_norm": 4.286844730377197,
1016
+ "learning_rate": 7.309644670050762e-06,
1017
+ "loss": 0.6075978875160217,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.036970933197348295,
1022
+ "grad_norm": 4.61534309387207,
1023
+ "learning_rate": 7.360406091370559e-06,
1024
+ "loss": 0.6174564957618713,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.037225905150433454,
1029
+ "grad_norm": 7.377719402313232,
1030
+ "learning_rate": 7.411167512690356e-06,
1031
+ "loss": 0.6060669422149658,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.03748087710351861,
1036
+ "grad_norm": 4.636322975158691,
1037
+ "learning_rate": 7.461928934010153e-06,
1038
+ "loss": 0.5887423753738403,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.03773584905660377,
1043
+ "grad_norm": 3.755432367324829,
1044
+ "learning_rate": 7.51269035532995e-06,
1045
+ "loss": 0.5913705229759216,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.03799082100968893,
1050
+ "grad_norm": 5.489928722381592,
1051
+ "learning_rate": 7.563451776649747e-06,
1052
+ "loss": 0.6052175760269165,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.0382457929627741,
1057
+ "grad_norm": 5.9897027015686035,
1058
+ "learning_rate": 7.614213197969543e-06,
1059
+ "loss": 0.5902068018913269,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.038500764915859256,
1064
+ "grad_norm": 8.362554550170898,
1065
+ "learning_rate": 7.664974619289341e-06,
1066
+ "loss": 0.5992493033409119,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.038755736868944415,
1071
+ "grad_norm": 5.351855754852295,
1072
+ "learning_rate": 7.715736040609138e-06,
1073
+ "loss": 0.6087163090705872,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.039010708822029574,
1078
+ "grad_norm": 5.387552261352539,
1079
+ "learning_rate": 7.766497461928934e-06,
1080
+ "loss": 0.6069482564926147,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.03926568077511474,
1085
+ "grad_norm": 5.964528560638428,
1086
+ "learning_rate": 7.817258883248731e-06,
1087
+ "loss": 0.5993782877922058,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.0395206527281999,
1092
+ "grad_norm": 10.254500389099121,
1093
+ "learning_rate": 7.86802030456853e-06,
1094
+ "loss": 0.6070284247398376,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.03977562468128506,
1099
+ "grad_norm": 7.0304341316223145,
1100
+ "learning_rate": 7.918781725888326e-06,
1101
+ "loss": 0.6082167625427246,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.04003059663437022,
1106
+ "grad_norm": 5.818995475769043,
1107
+ "learning_rate": 7.969543147208122e-06,
1108
+ "loss": 0.6076909303665161,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.04028556858745538,
1113
+ "grad_norm": 29.615108489990234,
1114
+ "learning_rate": 8.020304568527919e-06,
1115
+ "loss": 0.6017455458641052,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.04054054054054054,
1120
+ "grad_norm": 3.735245704650879,
1121
+ "learning_rate": 8.071065989847716e-06,
1122
+ "loss": 0.6166393160820007,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.0407955124936257,
1127
+ "grad_norm": 5.8766703605651855,
1128
+ "learning_rate": 8.121827411167514e-06,
1129
+ "loss": 0.5874968767166138,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.04105048444671086,
1134
+ "grad_norm": 3.799036979675293,
1135
+ "learning_rate": 8.17258883248731e-06,
1136
+ "loss": 0.6069945693016052,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.04130545639979602,
1141
+ "grad_norm": 4.457949161529541,
1142
+ "learning_rate": 8.223350253807107e-06,
1143
+ "loss": 0.6015027761459351,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.041560428352881186,
1148
+ "grad_norm": 9.537139892578125,
1149
+ "learning_rate": 8.274111675126905e-06,
1150
+ "loss": 0.5889110565185547,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.041815400305966345,
1155
+ "grad_norm": 4.916431903839111,
1156
+ "learning_rate": 8.324873096446702e-06,
1157
+ "loss": 0.6008636951446533,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.042070372259051504,
1162
+ "grad_norm": 3.8718481063842773,
1163
+ "learning_rate": 8.375634517766498e-06,
1164
+ "loss": 0.5849786996841431,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.04232534421213666,
1169
+ "grad_norm": 4.909853458404541,
1170
+ "learning_rate": 8.426395939086295e-06,
1171
+ "loss": 0.5965617299079895,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.04258031616522182,
1176
+ "grad_norm": 5.692605495452881,
1177
+ "learning_rate": 8.477157360406092e-06,
1178
+ "loss": 0.6011509299278259,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.04283528811830699,
1183
+ "grad_norm": 5.997374057769775,
1184
+ "learning_rate": 8.52791878172589e-06,
1185
+ "loss": 0.5989026427268982,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.04309026007139215,
1190
+ "grad_norm": 4.384658336639404,
1191
+ "learning_rate": 8.578680203045686e-06,
1192
+ "loss": 0.6050680875778198,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.043345232024477306,
1197
+ "grad_norm": 7.642217636108398,
1198
+ "learning_rate": 8.629441624365483e-06,
1199
+ "loss": 0.6081173419952393,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.043600203977562466,
1204
+ "grad_norm": 3.865013360977173,
1205
+ "learning_rate": 8.68020304568528e-06,
1206
+ "loss": 0.5977111458778381,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.04385517593064763,
1211
+ "grad_norm": 3.2660181522369385,
1212
+ "learning_rate": 8.730964467005076e-06,
1213
+ "loss": 0.6077733039855957,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.04411014788373279,
1218
+ "grad_norm": 6.390474796295166,
1219
+ "learning_rate": 8.781725888324873e-06,
1220
+ "loss": 0.5887953639030457,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.04436511983681795,
1225
+ "grad_norm": 3.376460313796997,
1226
+ "learning_rate": 8.832487309644671e-06,
1227
+ "loss": 0.6023260951042175,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.04462009178990311,
1232
+ "grad_norm": 11.863870620727539,
1233
+ "learning_rate": 8.883248730964468e-06,
1234
+ "loss": 0.581910252571106,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.04487506374298827,
1239
+ "grad_norm": 3.767972707748413,
1240
+ "learning_rate": 8.934010152284264e-06,
1241
+ "loss": 0.5987359285354614,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.045130035696073434,
1246
+ "grad_norm": 4.307549953460693,
1247
+ "learning_rate": 8.984771573604062e-06,
1248
+ "loss": 0.5949980020523071,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.04538500764915859,
1253
+ "grad_norm": 3.665287494659424,
1254
+ "learning_rate": 9.035532994923859e-06,
1255
+ "loss": 0.5925557017326355,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.04563997960224375,
1260
+ "grad_norm": 3.1785333156585693,
1261
+ "learning_rate": 9.086294416243656e-06,
1262
+ "loss": 0.6000990271568298,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.04589495155532891,
1267
+ "grad_norm": 7.793868541717529,
1268
+ "learning_rate": 9.137055837563452e-06,
1269
+ "loss": 0.588386058807373,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.04614992350841408,
1274
+ "grad_norm": 3.8479087352752686,
1275
+ "learning_rate": 9.187817258883249e-06,
1276
+ "loss": 0.6026387214660645,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.046404895461499236,
1281
+ "grad_norm": 4.099995136260986,
1282
+ "learning_rate": 9.238578680203047e-06,
1283
+ "loss": 0.6077677607536316,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.046659867414584395,
1288
+ "grad_norm": 4.00807523727417,
1289
+ "learning_rate": 9.289340101522844e-06,
1290
+ "loss": 0.5968591570854187,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.046914839367669554,
1295
+ "grad_norm": 3.527108669281006,
1296
+ "learning_rate": 9.34010152284264e-06,
1297
+ "loss": 0.6021297574043274,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.04716981132075472,
1302
+ "grad_norm": 3.72705078125,
1303
+ "learning_rate": 9.390862944162438e-06,
1304
+ "loss": 0.6009560823440552,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.04742478327383988,
1309
+ "grad_norm": 3.00913143157959,
1310
+ "learning_rate": 9.441624365482235e-06,
1311
+ "loss": 0.61063551902771,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.04767975522692504,
1316
+ "grad_norm": 3.3247106075286865,
1317
+ "learning_rate": 9.492385786802032e-06,
1318
+ "loss": 0.5803219676017761,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.0479347271800102,
1323
+ "grad_norm": 4.032495498657227,
1324
+ "learning_rate": 9.543147208121828e-06,
1325
+ "loss": 0.5938379168510437,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.04818969913309536,
1330
+ "grad_norm": 2.833737373352051,
1331
+ "learning_rate": 9.593908629441625e-06,
1332
+ "loss": 0.597266674041748,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.04844467108618052,
1337
+ "grad_norm": 4.320077419281006,
1338
+ "learning_rate": 9.644670050761421e-06,
1339
+ "loss": 0.6046103835105896,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.04869964303926568,
1344
+ "grad_norm": 4.185924530029297,
1345
+ "learning_rate": 9.69543147208122e-06,
1346
+ "loss": 0.6062490344047546,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.04895461499235084,
1351
+ "grad_norm": 5.10711669921875,
1352
+ "learning_rate": 9.746192893401016e-06,
1353
+ "loss": 0.6057544946670532,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.049209586945436,
1358
+ "grad_norm": 3.324521780014038,
1359
+ "learning_rate": 9.796954314720813e-06,
1360
+ "loss": 0.5799339413642883,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.049464558898521166,
1365
+ "grad_norm": 3.1842339038848877,
1366
+ "learning_rate": 9.84771573604061e-06,
1367
+ "loss": 0.6013438105583191,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.049719530851606325,
1372
+ "grad_norm": 2.3341190814971924,
1373
+ "learning_rate": 9.898477157360406e-06,
1374
+ "loss": 0.59135502576828,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.049974502804691484,
1379
+ "grad_norm": 2.7749569416046143,
1380
+ "learning_rate": 9.949238578680204e-06,
1381
+ "loss": 0.5952393412590027,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.05022947475777664,
1386
+ "grad_norm": 3.0547854900360107,
1387
+ "learning_rate": 1e-05,
1388
+ "loss": 0.5911858081817627,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.0504844467108618,
1393
+ "grad_norm": 3.5078237056732178,
1394
+ "learning_rate": 9.999998221773107e-06,
1395
+ "loss": 0.5847702026367188,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.05073941866394697,
1400
+ "grad_norm": 3.5228848457336426,
1401
+ "learning_rate": 9.999992887093691e-06,
1402
+ "loss": 0.6045140624046326,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.05099439061703213,
1407
+ "grad_norm": 2.6987292766571045,
1408
+ "learning_rate": 9.999983995965547e-06,
1409
+ "loss": 0.604773223400116,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.051249362570117286,
1414
+ "grad_norm": 2.957871198654175,
1415
+ "learning_rate": 9.999971548395e-06,
1416
+ "loss": 0.5873357057571411,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.051504334523202445,
1421
+ "grad_norm": 3.11552357673645,
1422
+ "learning_rate": 9.999955544390902e-06,
1423
+ "loss": 0.5930721759796143,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.05175930647628761,
1428
+ "grad_norm": 2.396313428878784,
1429
+ "learning_rate": 9.999935983964639e-06,
1430
+ "loss": 0.5927582383155823,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.05201427842937277,
1435
+ "grad_norm": 2.3981285095214844,
1436
+ "learning_rate": 9.999912867130124e-06,
1437
+ "loss": 0.5999355316162109,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.05226925038245793,
1442
+ "grad_norm": 2.930799722671509,
1443
+ "learning_rate": 9.999886193903796e-06,
1444
+ "loss": 0.5816469192504883,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.05252422233554309,
1449
+ "grad_norm": 3.259716272354126,
1450
+ "learning_rate": 9.999855964304633e-06,
1451
+ "loss": 0.5927892327308655,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.05277919428862825,
1456
+ "grad_norm": 2.8784027099609375,
1457
+ "learning_rate": 9.999822178354131e-06,
1458
+ "loss": 0.59906005859375,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.053034166241713414,
1463
+ "grad_norm": 5.081634998321533,
1464
+ "learning_rate": 9.999784836076325e-06,
1465
+ "loss": 0.5926652550697327,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.05328913819479857,
1470
+ "grad_norm": 2.9275574684143066,
1471
+ "learning_rate": 9.999743937497778e-06,
1472
+ "loss": 0.6022918224334717,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.05354411014788373,
1477
+ "grad_norm": 3.017028570175171,
1478
+ "learning_rate": 9.999699482647578e-06,
1479
+ "loss": 0.5827761888504028,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.05379908210096889,
1484
+ "grad_norm": 2.75286602973938,
1485
+ "learning_rate": 9.999651471557346e-06,
1486
+ "loss": 0.5874055027961731,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.05405405405405406,
1491
+ "grad_norm": 15.714319229125977,
1492
+ "learning_rate": 9.99959990426123e-06,
1493
+ "loss": 0.6002755165100098,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.054309026007139216,
1498
+ "grad_norm": 4.887640476226807,
1499
+ "learning_rate": 9.999544780795913e-06,
1500
+ "loss": 0.5951391458511353,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.054563997960224375,
1505
+ "grad_norm": 4.7820844650268555,
1506
+ "learning_rate": 9.999486101200603e-06,
1507
+ "loss": 0.5926157832145691,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.054818969913309534,
1512
+ "grad_norm": 3.6625335216522217,
1513
+ "learning_rate": 9.999423865517037e-06,
1514
+ "loss": 0.5840062499046326,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.05507394186639469,
1519
+ "grad_norm": 2.7337467670440674,
1520
+ "learning_rate": 9.999358073789481e-06,
1521
+ "loss": 0.5910326242446899,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.05532891381947986,
1526
+ "grad_norm": 2.746720790863037,
1527
+ "learning_rate": 9.999288726064735e-06,
1528
+ "loss": 0.5885810852050781,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.05558388577256502,
1533
+ "grad_norm": 2.9541351795196533,
1534
+ "learning_rate": 9.999215822392125e-06,
1535
+ "loss": 0.5852217674255371,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.05583885772565018,
1540
+ "grad_norm": 3.7349913120269775,
1541
+ "learning_rate": 9.999139362823507e-06,
1542
+ "loss": 0.5871468782424927,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.05609382967873534,
1547
+ "grad_norm": 2.559229612350464,
1548
+ "learning_rate": 9.999059347413262e-06,
1549
+ "loss": 0.5802211761474609,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.0563488016318205,
1554
+ "grad_norm": 3.2847959995269775,
1555
+ "learning_rate": 9.99897577621831e-06,
1556
+ "loss": 0.5856022834777832,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.05660377358490566,
1561
+ "grad_norm": 4.062271595001221,
1562
+ "learning_rate": 9.99888864929809e-06,
1563
+ "loss": 0.5967508554458618,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.05685874553799082,
1568
+ "grad_norm": 4.350281238555908,
1569
+ "learning_rate": 9.99879796671458e-06,
1570
+ "loss": 0.5894291400909424,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.05711371749107598,
1575
+ "grad_norm": 2.316976547241211,
1576
+ "learning_rate": 9.998703728532273e-06,
1577
+ "loss": 0.5789750218391418,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.05736868944416114,
1582
+ "grad_norm": 2.7369654178619385,
1583
+ "learning_rate": 9.998605934818208e-06,
1584
+ "loss": 0.5857868790626526,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.057623661397246305,
1589
+ "grad_norm": 3.066457748413086,
1590
+ "learning_rate": 9.998504585641941e-06,
1591
+ "loss": 0.5850772857666016,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.057878633350331464,
1596
+ "grad_norm": 3.2670044898986816,
1597
+ "learning_rate": 9.998399681075562e-06,
1598
+ "loss": 0.5871639251708984,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.05813360530341662,
1603
+ "grad_norm": 3.2137832641601562,
1604
+ "learning_rate": 9.998291221193685e-06,
1605
+ "loss": 0.5901861190795898,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.05838857725650178,
1610
+ "grad_norm": 4.253380298614502,
1611
+ "learning_rate": 9.998179206073461e-06,
1612
+ "loss": 0.5958875417709351,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.05864354920958695,
1617
+ "grad_norm": 2.9854331016540527,
1618
+ "learning_rate": 9.998063635794566e-06,
1619
+ "loss": 0.5908941626548767,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.05889852116267211,
1624
+ "grad_norm": 2.664669990539551,
1625
+ "learning_rate": 9.9979445104392e-06,
1626
+ "loss": 0.574123740196228,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.059153493115757266,
1631
+ "grad_norm": 2.4796957969665527,
1632
+ "learning_rate": 9.997821830092095e-06,
1633
+ "loss": 0.5850093364715576,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.059408465068842425,
1638
+ "grad_norm": 2.0589680671691895,
1639
+ "learning_rate": 9.99769559484052e-06,
1640
+ "loss": 0.5854530334472656,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.05966343702192759,
1645
+ "grad_norm": 1.7592800855636597,
1646
+ "learning_rate": 9.997565804774257e-06,
1647
+ "loss": 0.5807881951332092,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.05991840897501275,
1652
+ "grad_norm": 1.856603980064392,
1653
+ "learning_rate": 9.997432459985627e-06,
1654
+ "loss": 0.5874162912368774,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.06017338092809791,
1659
+ "grad_norm": 1.8138952255249023,
1660
+ "learning_rate": 9.997295560569477e-06,
1661
+ "loss": 0.5984858274459839,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.06042835288118307,
1666
+ "grad_norm": 1.8532931804656982,
1667
+ "learning_rate": 9.997155106623184e-06,
1668
+ "loss": 0.586401104927063,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.06068332483426823,
1673
+ "grad_norm": 2.2513363361358643,
1674
+ "learning_rate": 9.99701109824665e-06,
1675
+ "loss": 0.5933905839920044,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.060938296787353394,
1680
+ "grad_norm": 2.3893911838531494,
1681
+ "learning_rate": 9.996863535542306e-06,
1682
+ "loss": 0.5808255672454834,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.06119326874043855,
1687
+ "grad_norm": 2.2882018089294434,
1688
+ "learning_rate": 9.996712418615116e-06,
1689
+ "loss": 0.5888140201568604,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.06144824069352371,
1694
+ "grad_norm": 2.062934637069702,
1695
+ "learning_rate": 9.996557747572562e-06,
1696
+ "loss": 0.589434027671814,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.06170321264660887,
1701
+ "grad_norm": 2.081850051879883,
1702
+ "learning_rate": 9.996399522524664e-06,
1703
+ "loss": 0.5899481773376465,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.06195818459969404,
1708
+ "grad_norm": 2.06208872795105,
1709
+ "learning_rate": 9.996237743583965e-06,
1710
+ "loss": 0.5857259631156921,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.062213156552779196,
1715
+ "grad_norm": 1.8559035062789917,
1716
+ "learning_rate": 9.996072410865538e-06,
1717
+ "loss": 0.5844748020172119,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.062468128505864355,
1722
+ "grad_norm": 1.9922292232513428,
1723
+ "learning_rate": 9.99590352448698e-06,
1724
+ "loss": 0.5953148603439331,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 0.06272310045894952,
1729
+ "grad_norm": 2.6719133853912354,
1730
+ "learning_rate": 9.995731084568421e-06,
1731
+ "loss": 0.5793883204460144,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 0.06297807241203468,
1736
+ "grad_norm": 1.8634369373321533,
1737
+ "learning_rate": 9.995555091232516e-06,
1738
+ "loss": 0.5814319849014282,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 0.06323304436511984,
1743
+ "grad_norm": 1.8876395225524902,
1744
+ "learning_rate": 9.995375544604447e-06,
1745
+ "loss": 0.572151780128479,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 0.063488016318205,
1750
+ "grad_norm": 1.8171889781951904,
1751
+ "learning_rate": 9.99519244481192e-06,
1752
+ "loss": 0.5862112045288086,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 0.06374298827129016,
1757
+ "grad_norm": 2.4239213466644287,
1758
+ "learning_rate": 9.995005791985178e-06,
1759
+ "loss": 0.579311728477478,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 0.06399796022437532,
1764
+ "grad_norm": 2.0270440578460693,
1765
+ "learning_rate": 9.99481558625698e-06,
1766
+ "loss": 0.5841118097305298,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 0.06425293217746048,
1771
+ "grad_norm": 1.6712284088134766,
1772
+ "learning_rate": 9.994621827762624e-06,
1773
+ "loss": 0.5896538496017456,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 0.06450790413054563,
1778
+ "grad_norm": 1.8382529020309448,
1779
+ "learning_rate": 9.994424516639924e-06,
1780
+ "loss": 0.5876548290252686,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 0.0647628760836308,
1785
+ "grad_norm": 2.464630603790283,
1786
+ "learning_rate": 9.994223653029225e-06,
1787
+ "loss": 0.56418776512146,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 0.06501784803671597,
1792
+ "grad_norm": 5.462632656097412,
1793
+ "learning_rate": 9.994019237073402e-06,
1794
+ "loss": 0.5843555927276611,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 0.06527281998980113,
1799
+ "grad_norm": 2.105456829071045,
1800
+ "learning_rate": 9.993811268917854e-06,
1801
+ "loss": 0.5954089164733887,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 0.06552779194288628,
1806
+ "grad_norm": 2.2847952842712402,
1807
+ "learning_rate": 9.993599748710505e-06,
1808
+ "loss": 0.58359694480896,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 0.06578276389597144,
1813
+ "grad_norm": 1.971805453300476,
1814
+ "learning_rate": 9.99338467660181e-06,
1815
+ "loss": 0.5963630676269531,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 0.0660377358490566,
1820
+ "grad_norm": 2.609140396118164,
1821
+ "learning_rate": 9.993166052744745e-06,
1822
+ "loss": 0.5824004411697388,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 0.06629270780214176,
1827
+ "grad_norm": 5.869304180145264,
1828
+ "learning_rate": 9.992943877294817e-06,
1829
+ "loss": 0.5748361349105835,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 0.06654767975522692,
1834
+ "grad_norm": 4.773970603942871,
1835
+ "learning_rate": 9.992718150410054e-06,
1836
+ "loss": 0.5913362503051758,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 0.06680265170831208,
1841
+ "grad_norm": 2.3107783794403076,
1842
+ "learning_rate": 9.992488872251019e-06,
1843
+ "loss": 0.5675320625305176,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 0.06705762366139725,
1848
+ "grad_norm": 3.1674349308013916,
1849
+ "learning_rate": 9.992256042980792e-06,
1850
+ "loss": 0.5810559988021851,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 0.06731259561448241,
1855
+ "grad_norm": 2.4077420234680176,
1856
+ "learning_rate": 9.992019662764982e-06,
1857
+ "loss": 0.586556613445282,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 0.06756756756756757,
1862
+ "grad_norm": 2.182682514190674,
1863
+ "learning_rate": 9.991779731771727e-06,
1864
+ "loss": 0.5913389325141907,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 0.06782253952065273,
1869
+ "grad_norm": 2.2735114097595215,
1870
+ "learning_rate": 9.991536250171683e-06,
1871
+ "loss": 0.5736482739448547,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 0.06807751147373789,
1876
+ "grad_norm": 2.0414175987243652,
1877
+ "learning_rate": 9.991289218138042e-06,
1878
+ "loss": 0.5860854983329773,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 0.06833248342682305,
1883
+ "grad_norm": 2.2997677326202393,
1884
+ "learning_rate": 9.99103863584651e-06,
1885
+ "loss": 0.5764031410217285,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 0.06858745537990821,
1890
+ "grad_norm": 2.6660847663879395,
1891
+ "learning_rate": 9.990784503475327e-06,
1892
+ "loss": 0.5681920051574707,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 0.06884242733299337,
1897
+ "grad_norm": 3.4867351055145264,
1898
+ "learning_rate": 9.990526821205256e-06,
1899
+ "loss": 0.5747722387313843,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 0.06909739928607853,
1904
+ "grad_norm": 2.430447816848755,
1905
+ "learning_rate": 9.990265589219578e-06,
1906
+ "loss": 0.5789008140563965,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 0.0693523712391637,
1911
+ "grad_norm": 2.5677506923675537,
1912
+ "learning_rate": 9.990000807704114e-06,
1913
+ "loss": 0.5765048265457153,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 0.06960734319224886,
1918
+ "grad_norm": 2.7650086879730225,
1919
+ "learning_rate": 9.989732476847194e-06,
1920
+ "loss": 0.575411319732666,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 0.06986231514533402,
1925
+ "grad_norm": 1.8177183866500854,
1926
+ "learning_rate": 9.989460596839681e-06,
1927
+ "loss": 0.5772970914840698,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 0.07011728709841918,
1932
+ "grad_norm": 4.586569786071777,
1933
+ "learning_rate": 9.98918516787496e-06,
1934
+ "loss": 0.581605076789856,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 0.07037225905150434,
1939
+ "grad_norm": 3.1498584747314453,
1940
+ "learning_rate": 9.988906190148944e-06,
1941
+ "loss": 0.5844799876213074,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 0.0706272310045895,
1946
+ "grad_norm": 4.407031536102295,
1947
+ "learning_rate": 9.988623663860064e-06,
1948
+ "loss": 0.5937627553939819,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 0.07088220295767465,
1953
+ "grad_norm": 2.287809371948242,
1954
+ "learning_rate": 9.988337589209281e-06,
1955
+ "loss": 0.5812350511550903,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 0.07113717491075981,
1960
+ "grad_norm": 3.0038914680480957,
1961
+ "learning_rate": 9.988047966400074e-06,
1962
+ "loss": 0.5812468528747559,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 0.07139214686384497,
1967
+ "grad_norm": 2.2336087226867676,
1968
+ "learning_rate": 9.987754795638451e-06,
1969
+ "loss": 0.5780528783798218,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 0.07164711881693014,
1974
+ "grad_norm": 2.0841615200042725,
1975
+ "learning_rate": 9.987458077132943e-06,
1976
+ "loss": 0.5742005705833435,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 0.0719020907700153,
1981
+ "grad_norm": 2.2732021808624268,
1982
+ "learning_rate": 9.9871578110946e-06,
1983
+ "loss": 0.5748374462127686,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 0.07215706272310046,
1988
+ "grad_norm": 2.061392307281494,
1989
+ "learning_rate": 9.986853997737e-06,
1990
+ "loss": 0.5818248987197876,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 0.07241203467618562,
1995
+ "grad_norm": 2.114393949508667,
1996
+ "learning_rate": 9.986546637276245e-06,
1997
+ "loss": 0.5788212418556213,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 0.07266700662927078,
2002
+ "grad_norm": 2.8290114402770996,
2003
+ "learning_rate": 9.986235729930954e-06,
2004
+ "loss": 0.5592154264450073,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 0.07292197858235594,
2009
+ "grad_norm": 2.5851333141326904,
2010
+ "learning_rate": 9.985921275922275e-06,
2011
+ "loss": 0.5769827961921692,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 0.0731769505354411,
2016
+ "grad_norm": 3.3514719009399414,
2017
+ "learning_rate": 9.985603275473874e-06,
2018
+ "loss": 0.5761103630065918,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 0.07343192248852626,
2023
+ "grad_norm": 2.6545956134796143,
2024
+ "learning_rate": 9.985281728811943e-06,
2025
+ "loss": 0.5879877805709839,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 0.07368689444161142,
2030
+ "grad_norm": 3.3587162494659424,
2031
+ "learning_rate": 9.984956636165194e-06,
2032
+ "loss": 0.5736678838729858,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 0.07394186639469659,
2037
+ "grad_norm": 4.441765785217285,
2038
+ "learning_rate": 9.984627997764866e-06,
2039
+ "loss": 0.5688061118125916,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 0.07419683834778175,
2044
+ "grad_norm": 3.293834924697876,
2045
+ "learning_rate": 9.984295813844714e-06,
2046
+ "loss": 0.5717458128929138,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 0.07445181030086691,
2051
+ "grad_norm": 5.738956928253174,
2052
+ "learning_rate": 9.983960084641014e-06,
2053
+ "loss": 0.5693488121032715,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 0.07470678225395207,
2058
+ "grad_norm": 2.3275930881500244,
2059
+ "learning_rate": 9.983620810392574e-06,
2060
+ "loss": 0.5773096084594727,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 0.07496175420703723,
2065
+ "grad_norm": 20.73316192626953,
2066
+ "learning_rate": 9.983277991340709e-06,
2067
+ "loss": 0.5704731345176697,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 0.07521672616012239,
2072
+ "grad_norm": 2.5347342491149902,
2073
+ "learning_rate": 9.98293162772927e-06,
2074
+ "loss": 0.5738517045974731,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 0.07547169811320754,
2079
+ "grad_norm": 2.9725821018218994,
2080
+ "learning_rate": 9.98258171980462e-06,
2081
+ "loss": 0.5762280225753784,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 0.0757266700662927,
2086
+ "grad_norm": 2.1470696926116943,
2087
+ "learning_rate": 9.982228267815644e-06,
2088
+ "loss": 0.5746186375617981,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 0.07598164201937786,
2093
+ "grad_norm": 3.3097052574157715,
2094
+ "learning_rate": 9.981871272013747e-06,
2095
+ "loss": 0.571082353591919,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 0.07623661397246304,
2100
+ "grad_norm": 2.7459795475006104,
2101
+ "learning_rate": 9.981510732652862e-06,
2102
+ "loss": 0.5818139910697937,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 0.0764915859255482,
2107
+ "grad_norm": 18.801685333251953,
2108
+ "learning_rate": 9.981146649989435e-06,
2109
+ "loss": 0.5743539333343506,
2110
+ "step": 300
2111
+ },
2112
+ {
2113
+ "epoch": 0.07674655787863335,
2114
+ "grad_norm": 2.2822065353393555,
2115
+ "learning_rate": 9.980779024282434e-06,
2116
+ "loss": 0.5851568579673767,
2117
+ "step": 301
2118
+ },
2119
+ {
2120
+ "epoch": 0.07700152983171851,
2121
+ "grad_norm": 4.970335006713867,
2122
+ "learning_rate": 9.980407855793348e-06,
2123
+ "loss": 0.567683756351471,
2124
+ "step": 302
2125
+ },
2126
+ {
2127
+ "epoch": 0.07725650178480367,
2128
+ "grad_norm": 2.375314950942993,
2129
+ "learning_rate": 9.980033144786186e-06,
2130
+ "loss": 0.5673696994781494,
2131
+ "step": 303
2132
+ },
2133
+ {
2134
+ "epoch": 0.07751147373788883,
2135
+ "grad_norm": 3.8067612648010254,
2136
+ "learning_rate": 9.979654891527476e-06,
2137
+ "loss": 0.5791069865226746,
2138
+ "step": 304
2139
+ },
2140
+ {
2141
+ "epoch": 0.07776644569097399,
2142
+ "grad_norm": 2.5518550872802734,
2143
+ "learning_rate": 9.979273096286268e-06,
2144
+ "loss": 0.5585265159606934,
2145
+ "step": 305
2146
+ },
2147
+ {
2148
+ "epoch": 0.07802141764405915,
2149
+ "grad_norm": 5.341617584228516,
2150
+ "learning_rate": 9.978887759334125e-06,
2151
+ "loss": 0.5657647848129272,
2152
+ "step": 306
2153
+ },
2154
+ {
2155
+ "epoch": 0.07827638959714431,
2156
+ "grad_norm": 2.304340124130249,
2157
+ "learning_rate": 9.978498880945138e-06,
2158
+ "loss": 0.5609466433525085,
2159
+ "step": 307
2160
+ },
2161
+ {
2162
+ "epoch": 0.07853136155022948,
2163
+ "grad_norm": 4.493840217590332,
2164
+ "learning_rate": 9.978106461395912e-06,
2165
+ "loss": 0.5843234062194824,
2166
+ "step": 308
2167
+ },
2168
+ {
2169
+ "epoch": 0.07878633350331464,
2170
+ "grad_norm": 3.806673526763916,
2171
+ "learning_rate": 9.97771050096557e-06,
2172
+ "loss": 0.5767306089401245,
2173
+ "step": 309
2174
+ },
2175
+ {
2176
+ "epoch": 0.0790413054563998,
2177
+ "grad_norm": 4.547685623168945,
2178
+ "learning_rate": 9.977310999935756e-06,
2179
+ "loss": 0.5610491037368774,
2180
+ "step": 310
2181
+ },
2182
+ {
2183
+ "epoch": 0.07929627740948496,
2184
+ "grad_norm": 2.6244962215423584,
2185
+ "learning_rate": 9.976907958590629e-06,
2186
+ "loss": 0.563437819480896,
2187
+ "step": 311
2188
+ },
2189
+ {
2190
+ "epoch": 0.07955124936257012,
2191
+ "grad_norm": 2.8524208068847656,
2192
+ "learning_rate": 9.976501377216871e-06,
2193
+ "loss": 0.5713075995445251,
2194
+ "step": 312
2195
+ },
2196
+ {
2197
+ "epoch": 0.07980622131565528,
2198
+ "grad_norm": 3.662938117980957,
2199
+ "learning_rate": 9.97609125610368e-06,
2200
+ "loss": 0.5592581629753113,
2201
+ "step": 313
2202
+ },
2203
+ {
2204
+ "epoch": 0.08006119326874044,
2205
+ "grad_norm": 2.5013678073883057,
2206
+ "learning_rate": 9.97567759554277e-06,
2207
+ "loss": 0.571389377117157,
2208
+ "step": 314
2209
+ },
2210
+ {
2211
+ "epoch": 0.0803161652218256,
2212
+ "grad_norm": 3.6687936782836914,
2213
+ "learning_rate": 9.975260395828376e-06,
2214
+ "loss": 0.575724720954895,
2215
+ "step": 315
2216
+ },
2217
+ {
2218
+ "epoch": 0.08057113717491075,
2219
+ "grad_norm": 2.705265760421753,
2220
+ "learning_rate": 9.974839657257245e-06,
2221
+ "loss": 0.5768415331840515,
2222
+ "step": 316
2223
+ },
2224
+ {
2225
+ "epoch": 0.08082610912799593,
2226
+ "grad_norm": 3.3716695308685303,
2227
+ "learning_rate": 9.974415380128646e-06,
2228
+ "loss": 0.5781106948852539,
2229
+ "step": 317
2230
+ },
2231
+ {
2232
+ "epoch": 0.08108108108108109,
2233
+ "grad_norm": 2.1914381980895996,
2234
+ "learning_rate": 9.973987564744363e-06,
2235
+ "loss": 0.5832979679107666,
2236
+ "step": 318
2237
+ },
2238
+ {
2239
+ "epoch": 0.08133605303416624,
2240
+ "grad_norm": 2.789609432220459,
2241
+ "learning_rate": 9.973556211408699e-06,
2242
+ "loss": 0.5669206380844116,
2243
+ "step": 319
2244
+ },
2245
+ {
2246
+ "epoch": 0.0815910249872514,
2247
+ "grad_norm": 2.268644332885742,
2248
+ "learning_rate": 9.97312132042847e-06,
2249
+ "loss": 0.5540966391563416,
2250
+ "step": 320
2251
+ },
2252
+ {
2253
+ "epoch": 0.08184599694033656,
2254
+ "grad_norm": 5.483611583709717,
2255
+ "learning_rate": 9.972682892113009e-06,
2256
+ "loss": 0.5671651363372803,
2257
+ "step": 321
2258
+ },
2259
+ {
2260
+ "epoch": 0.08210096889342172,
2261
+ "grad_norm": 2.727654457092285,
2262
+ "learning_rate": 9.972240926774167e-06,
2263
+ "loss": 0.5680763125419617,
2264
+ "step": 322
2265
+ },
2266
+ {
2267
+ "epoch": 0.08235594084650688,
2268
+ "grad_norm": 3.385113000869751,
2269
+ "learning_rate": 9.97179542472631e-06,
2270
+ "loss": 0.5710451006889343,
2271
+ "step": 323
2272
+ },
2273
+ {
2274
+ "epoch": 0.08261091279959204,
2275
+ "grad_norm": 2.97533917427063,
2276
+ "learning_rate": 9.971346386286323e-06,
2277
+ "loss": 0.5777047872543335,
2278
+ "step": 324
2279
+ },
2280
+ {
2281
+ "epoch": 0.0828658847526772,
2282
+ "grad_norm": 2.553302526473999,
2283
+ "learning_rate": 9.970893811773597e-06,
2284
+ "loss": 0.5666846036911011,
2285
+ "step": 325
2286
+ },
2287
+ {
2288
+ "epoch": 0.08312085670576237,
2289
+ "grad_norm": 2.8742709159851074,
2290
+ "learning_rate": 9.970437701510047e-06,
2291
+ "loss": 0.5720920562744141,
2292
+ "step": 326
2293
+ },
2294
+ {
2295
+ "epoch": 0.08337582865884753,
2296
+ "grad_norm": 5.297033786773682,
2297
+ "learning_rate": 9.969978055820099e-06,
2298
+ "loss": 0.5806701183319092,
2299
+ "step": 327
2300
+ },
2301
+ {
2302
+ "epoch": 0.08363080061193269,
2303
+ "grad_norm": 5.130199432373047,
2304
+ "learning_rate": 9.969514875030695e-06,
2305
+ "loss": 0.5766419768333435,
2306
+ "step": 328
2307
+ },
2308
+ {
2309
+ "epoch": 0.08388577256501785,
2310
+ "grad_norm": 5.532764911651611,
2311
+ "learning_rate": 9.969048159471291e-06,
2312
+ "loss": 0.5834259390830994,
2313
+ "step": 329
2314
+ },
2315
+ {
2316
+ "epoch": 0.08414074451810301,
2317
+ "grad_norm": 2.856757640838623,
2318
+ "learning_rate": 9.96857790947386e-06,
2319
+ "loss": 0.5710228085517883,
2320
+ "step": 330
2321
+ },
2322
+ {
2323
+ "epoch": 0.08439571647118817,
2324
+ "grad_norm": 2.8127498626708984,
2325
+ "learning_rate": 9.968104125372883e-06,
2326
+ "loss": 0.5596293210983276,
2327
+ "step": 331
2328
+ },
2329
+ {
2330
+ "epoch": 0.08465068842427333,
2331
+ "grad_norm": 3.476436138153076,
2332
+ "learning_rate": 9.967626807505359e-06,
2333
+ "loss": 0.5636457800865173,
2334
+ "step": 332
2335
+ },
2336
+ {
2337
+ "epoch": 0.08490566037735849,
2338
+ "grad_norm": 3.897481679916382,
2339
+ "learning_rate": 9.967145956210801e-06,
2340
+ "loss": 0.579216480255127,
2341
+ "step": 333
2342
+ },
2343
+ {
2344
+ "epoch": 0.08516063233044364,
2345
+ "grad_norm": 4.0459818840026855,
2346
+ "learning_rate": 9.966661571831235e-06,
2347
+ "loss": 0.5644032955169678,
2348
+ "step": 334
2349
+ },
2350
+ {
2351
+ "epoch": 0.08541560428352882,
2352
+ "grad_norm": 2.3585076332092285,
2353
+ "learning_rate": 9.966173654711197e-06,
2354
+ "loss": 0.5744975805282593,
2355
+ "step": 335
2356
+ },
2357
+ {
2358
+ "epoch": 0.08567057623661398,
2359
+ "grad_norm": 4.57792854309082,
2360
+ "learning_rate": 9.965682205197737e-06,
2361
+ "loss": 0.5631759762763977,
2362
+ "step": 336
2363
+ },
2364
+ {
2365
+ "epoch": 0.08592554818969914,
2366
+ "grad_norm": 2.656183958053589,
2367
+ "learning_rate": 9.965187223640422e-06,
2368
+ "loss": 0.5689008235931396,
2369
+ "step": 337
2370
+ },
2371
+ {
2372
+ "epoch": 0.0861805201427843,
2373
+ "grad_norm": 2.8403210639953613,
2374
+ "learning_rate": 9.964688710391325e-06,
2375
+ "loss": 0.5751459002494812,
2376
+ "step": 338
2377
+ },
2378
+ {
2379
+ "epoch": 0.08643549209586945,
2380
+ "grad_norm": 2.4729552268981934,
2381
+ "learning_rate": 9.964186665805034e-06,
2382
+ "loss": 0.5721454620361328,
2383
+ "step": 339
2384
+ },
2385
+ {
2386
+ "epoch": 0.08669046404895461,
2387
+ "grad_norm": 2.7285823822021484,
2388
+ "learning_rate": 9.96368109023865e-06,
2389
+ "loss": 0.5654371380805969,
2390
+ "step": 340
2391
+ },
2392
+ {
2393
+ "epoch": 0.08694543600203977,
2394
+ "grad_norm": 2.1327974796295166,
2395
+ "learning_rate": 9.963171984051786e-06,
2396
+ "loss": 0.5701696276664734,
2397
+ "step": 341
2398
+ },
2399
+ {
2400
+ "epoch": 0.08720040795512493,
2401
+ "grad_norm": 2.0096259117126465,
2402
+ "learning_rate": 9.96265934760656e-06,
2403
+ "loss": 0.5614428520202637,
2404
+ "step": 342
2405
+ },
2406
+ {
2407
+ "epoch": 0.08745537990821009,
2408
+ "grad_norm": 2.1693127155303955,
2409
+ "learning_rate": 9.962143181267607e-06,
2410
+ "loss": 0.559285581111908,
2411
+ "step": 343
2412
+ },
2413
+ {
2414
+ "epoch": 0.08771035186129526,
2415
+ "grad_norm": 21.574602127075195,
2416
+ "learning_rate": 9.961623485402074e-06,
2417
+ "loss": 0.5767900347709656,
2418
+ "step": 344
2419
+ },
2420
+ {
2421
+ "epoch": 0.08796532381438042,
2422
+ "grad_norm": 3.6397855281829834,
2423
+ "learning_rate": 9.961100260379612e-06,
2424
+ "loss": 0.5654720067977905,
2425
+ "step": 345
2426
+ },
2427
+ {
2428
+ "epoch": 0.08822029576746558,
2429
+ "grad_norm": 2.2064383029937744,
2430
+ "learning_rate": 9.960573506572391e-06,
2431
+ "loss": 0.5701004266738892,
2432
+ "step": 346
2433
+ },
2434
+ {
2435
+ "epoch": 0.08847526772055074,
2436
+ "grad_norm": 8.230388641357422,
2437
+ "learning_rate": 9.960043224355081e-06,
2438
+ "loss": 0.5593109130859375,
2439
+ "step": 347
2440
+ },
2441
+ {
2442
+ "epoch": 0.0887302396736359,
2443
+ "grad_norm": 2.8151967525482178,
2444
+ "learning_rate": 9.959509414104868e-06,
2445
+ "loss": 0.5906691551208496,
2446
+ "step": 348
2447
+ },
2448
+ {
2449
+ "epoch": 0.08898521162672106,
2450
+ "grad_norm": 2.6584460735321045,
2451
+ "learning_rate": 9.95897207620145e-06,
2452
+ "loss": 0.5554200410842896,
2453
+ "step": 349
2454
+ },
2455
+ {
2456
+ "epoch": 0.08924018357980622,
2457
+ "grad_norm": 2.230492353439331,
2458
+ "learning_rate": 9.958431211027026e-06,
2459
+ "loss": 0.5893738269805908,
2460
+ "step": 350
2461
+ },
2462
+ {
2463
+ "epoch": 0.08949515553289138,
2464
+ "grad_norm": 2.6074323654174805,
2465
+ "learning_rate": 9.95788681896631e-06,
2466
+ "loss": 0.5782200694084167,
2467
+ "step": 351
2468
+ },
2469
+ {
2470
+ "epoch": 0.08975012748597654,
2471
+ "grad_norm": 1.678154706954956,
2472
+ "learning_rate": 9.957338900406525e-06,
2473
+ "loss": 0.5617006421089172,
2474
+ "step": 352
2475
+ },
2476
+ {
2477
+ "epoch": 0.09000509943906171,
2478
+ "grad_norm": 1.8922593593597412,
2479
+ "learning_rate": 9.956787455737397e-06,
2480
+ "loss": 0.5668175220489502,
2481
+ "step": 353
2482
+ },
2483
+ {
2484
+ "epoch": 0.09026007139214687,
2485
+ "grad_norm": 2.508108615875244,
2486
+ "learning_rate": 9.956232485351167e-06,
2487
+ "loss": 0.5639225244522095,
2488
+ "step": 354
2489
+ },
2490
+ {
2491
+ "epoch": 0.09051504334523203,
2492
+ "grad_norm": 3.1573591232299805,
2493
+ "learning_rate": 9.955673989642578e-06,
2494
+ "loss": 0.557616651058197,
2495
+ "step": 355
2496
+ },
2497
+ {
2498
+ "epoch": 0.09077001529831719,
2499
+ "grad_norm": 2.6363086700439453,
2500
+ "learning_rate": 9.955111969008884e-06,
2501
+ "loss": 0.5727308988571167,
2502
+ "step": 356
2503
+ },
2504
+ {
2505
+ "epoch": 0.09102498725140235,
2506
+ "grad_norm": 3.0296366214752197,
2507
+ "learning_rate": 9.954546423849842e-06,
2508
+ "loss": 0.5857377052307129,
2509
+ "step": 357
2510
+ },
2511
+ {
2512
+ "epoch": 0.0912799592044875,
2513
+ "grad_norm": 2.211289644241333,
2514
+ "learning_rate": 9.953977354567723e-06,
2515
+ "loss": 0.5680918097496033,
2516
+ "step": 358
2517
+ },
2518
+ {
2519
+ "epoch": 0.09153493115757266,
2520
+ "grad_norm": 2.4168450832366943,
2521
+ "learning_rate": 9.953404761567299e-06,
2522
+ "loss": 0.5729773044586182,
2523
+ "step": 359
2524
+ },
2525
+ {
2526
+ "epoch": 0.09178990311065782,
2527
+ "grad_norm": 2.44561767578125,
2528
+ "learning_rate": 9.952828645255849e-06,
2529
+ "loss": 0.5714361667633057,
2530
+ "step": 360
2531
+ },
2532
+ {
2533
+ "epoch": 0.09204487506374298,
2534
+ "grad_norm": 2.3818702697753906,
2535
+ "learning_rate": 9.952249006043163e-06,
2536
+ "loss": 0.5708685517311096,
2537
+ "step": 361
2538
+ },
2539
+ {
2540
+ "epoch": 0.09229984701682815,
2541
+ "grad_norm": 2.3030588626861572,
2542
+ "learning_rate": 9.95166584434153e-06,
2543
+ "loss": 0.5894932746887207,
2544
+ "step": 362
2545
+ },
2546
+ {
2547
+ "epoch": 0.09255481896991331,
2548
+ "grad_norm": 6.469595432281494,
2549
+ "learning_rate": 9.951079160565747e-06,
2550
+ "loss": 0.5663866400718689,
2551
+ "step": 363
2552
+ },
2553
+ {
2554
+ "epoch": 0.09280979092299847,
2555
+ "grad_norm": 3.4183993339538574,
2556
+ "learning_rate": 9.950488955133118e-06,
2557
+ "loss": 0.5638302564620972,
2558
+ "step": 364
2559
+ },
2560
+ {
2561
+ "epoch": 0.09306476287608363,
2562
+ "grad_norm": 2.77966570854187,
2563
+ "learning_rate": 9.94989522846345e-06,
2564
+ "loss": 0.5765042304992676,
2565
+ "step": 365
2566
+ },
2567
+ {
2568
+ "epoch": 0.09331973482916879,
2569
+ "grad_norm": 3.0297207832336426,
2570
+ "learning_rate": 9.949297980979056e-06,
2571
+ "loss": 0.5630312561988831,
2572
+ "step": 366
2573
+ },
2574
+ {
2575
+ "epoch": 0.09357470678225395,
2576
+ "grad_norm": 2.405850410461426,
2577
+ "learning_rate": 9.948697213104754e-06,
2578
+ "loss": 0.5837424993515015,
2579
+ "step": 367
2580
+ },
2581
+ {
2582
+ "epoch": 0.09382967873533911,
2583
+ "grad_norm": 3.138538122177124,
2584
+ "learning_rate": 9.94809292526786e-06,
2585
+ "loss": 0.5750604271888733,
2586
+ "step": 368
2587
+ },
2588
+ {
2589
+ "epoch": 0.09408465068842427,
2590
+ "grad_norm": 2.2397854328155518,
2591
+ "learning_rate": 9.947485117898204e-06,
2592
+ "loss": 0.5760766267776489,
2593
+ "step": 369
2594
+ },
2595
+ {
2596
+ "epoch": 0.09433962264150944,
2597
+ "grad_norm": 3.172715425491333,
2598
+ "learning_rate": 9.946873791428108e-06,
2599
+ "loss": 0.5685843229293823,
2600
+ "step": 370
2601
+ },
2602
+ {
2603
+ "epoch": 0.0945945945945946,
2604
+ "grad_norm": 1.991998553276062,
2605
+ "learning_rate": 9.94625894629241e-06,
2606
+ "loss": 0.5787516832351685,
2607
+ "step": 371
2608
+ },
2609
+ {
2610
+ "epoch": 0.09484956654767976,
2611
+ "grad_norm": 2.286336898803711,
2612
+ "learning_rate": 9.945640582928438e-06,
2613
+ "loss": 0.5736852884292603,
2614
+ "step": 372
2615
+ },
2616
+ {
2617
+ "epoch": 0.09510453850076492,
2618
+ "grad_norm": 3.257596492767334,
2619
+ "learning_rate": 9.945018701776027e-06,
2620
+ "loss": 0.5641451478004456,
2621
+ "step": 373
2622
+ },
2623
+ {
2624
+ "epoch": 0.09535951045385008,
2625
+ "grad_norm": 1.9430432319641113,
2626
+ "learning_rate": 9.944393303277523e-06,
2627
+ "loss": 0.5590602159500122,
2628
+ "step": 374
2629
+ },
2630
+ {
2631
+ "epoch": 0.09561448240693524,
2632
+ "grad_norm": 1.9836829900741577,
2633
+ "learning_rate": 9.943764387877758e-06,
2634
+ "loss": 0.5627750158309937,
2635
+ "step": 375
2636
+ },
2637
+ {
2638
+ "epoch": 0.0958694543600204,
2639
+ "grad_norm": 3.3282463550567627,
2640
+ "learning_rate": 9.943131956024078e-06,
2641
+ "loss": 0.5622991323471069,
2642
+ "step": 376
2643
+ },
2644
+ {
2645
+ "epoch": 0.09612442631310555,
2646
+ "grad_norm": 2.969663143157959,
2647
+ "learning_rate": 9.942496008166325e-06,
2648
+ "loss": 0.5768574476242065,
2649
+ "step": 377
2650
+ },
2651
+ {
2652
+ "epoch": 0.09637939826619071,
2653
+ "grad_norm": 4.455136775970459,
2654
+ "learning_rate": 9.941856544756843e-06,
2655
+ "loss": 0.5683542490005493,
2656
+ "step": 378
2657
+ },
2658
+ {
2659
+ "epoch": 0.09663437021927589,
2660
+ "grad_norm": 2.2980382442474365,
2661
+ "learning_rate": 9.941213566250475e-06,
2662
+ "loss": 0.5575302839279175,
2663
+ "step": 379
2664
+ },
2665
+ {
2666
+ "epoch": 0.09688934217236105,
2667
+ "grad_norm": 2.662888526916504,
2668
+ "learning_rate": 9.940567073104568e-06,
2669
+ "loss": 0.5679932236671448,
2670
+ "step": 380
2671
+ },
2672
+ {
2673
+ "epoch": 0.0971443141254462,
2674
+ "grad_norm": 5.441934585571289,
2675
+ "learning_rate": 9.939917065778965e-06,
2676
+ "loss": 0.5602290034294128,
2677
+ "step": 381
2678
+ },
2679
+ {
2680
+ "epoch": 0.09739928607853136,
2681
+ "grad_norm": 2.7203729152679443,
2682
+ "learning_rate": 9.93926354473601e-06,
2683
+ "loss": 0.5430388450622559,
2684
+ "step": 382
2685
+ },
2686
+ {
2687
+ "epoch": 0.09765425803161652,
2688
+ "grad_norm": 3.4668338298797607,
2689
+ "learning_rate": 9.938606510440548e-06,
2690
+ "loss": 0.5614120960235596,
2691
+ "step": 383
2692
+ },
2693
+ {
2694
+ "epoch": 0.09790922998470168,
2695
+ "grad_norm": 2.841843605041504,
2696
+ "learning_rate": 9.937945963359919e-06,
2697
+ "loss": 0.5806660056114197,
2698
+ "step": 384
2699
+ },
2700
+ {
2701
+ "epoch": 0.09816420193778684,
2702
+ "grad_norm": 2.8140835762023926,
2703
+ "learning_rate": 9.937281903963968e-06,
2704
+ "loss": 0.5649043321609497,
2705
+ "step": 385
2706
+ },
2707
+ {
2708
+ "epoch": 0.098419173890872,
2709
+ "grad_norm": 1.9643291234970093,
2710
+ "learning_rate": 9.93661433272503e-06,
2711
+ "loss": 0.5647992491722107,
2712
+ "step": 386
2713
+ },
2714
+ {
2715
+ "epoch": 0.09867414584395716,
2716
+ "grad_norm": 2.129157543182373,
2717
+ "learning_rate": 9.935943250117945e-06,
2718
+ "loss": 0.5809118151664734,
2719
+ "step": 387
2720
+ },
2721
+ {
2722
+ "epoch": 0.09892911779704233,
2723
+ "grad_norm": 3.388709545135498,
2724
+ "learning_rate": 9.935268656620048e-06,
2725
+ "loss": 0.5615958571434021,
2726
+ "step": 388
2727
+ },
2728
+ {
2729
+ "epoch": 0.09918408975012749,
2730
+ "grad_norm": 3.151108741760254,
2731
+ "learning_rate": 9.934590552711167e-06,
2732
+ "loss": 0.5755165815353394,
2733
+ "step": 389
2734
+ },
2735
+ {
2736
+ "epoch": 0.09943906170321265,
2737
+ "grad_norm": 3.6108310222625732,
2738
+ "learning_rate": 9.933908938873638e-06,
2739
+ "loss": 0.5648122429847717,
2740
+ "step": 390
2741
+ },
2742
+ {
2743
+ "epoch": 0.09969403365629781,
2744
+ "grad_norm": 4.878504753112793,
2745
+ "learning_rate": 9.933223815592278e-06,
2746
+ "loss": 0.5667652487754822,
2747
+ "step": 391
2748
+ },
2749
+ {
2750
+ "epoch": 0.09994900560938297,
2751
+ "grad_norm": 3.92559814453125,
2752
+ "learning_rate": 9.932535183354418e-06,
2753
+ "loss": 0.5649821162223816,
2754
+ "step": 392
2755
+ },
2756
+ {
2757
+ "epoch": 0.10020397756246813,
2758
+ "grad_norm": 4.201918601989746,
2759
+ "learning_rate": 9.93184304264987e-06,
2760
+ "loss": 0.5741337537765503,
2761
+ "step": 393
2762
+ },
2763
+ {
2764
+ "epoch": 0.10045894951555329,
2765
+ "grad_norm": 4.567728519439697,
2766
+ "learning_rate": 9.931147393970949e-06,
2767
+ "loss": 0.5604985952377319,
2768
+ "step": 394
2769
+ },
2770
+ {
2771
+ "epoch": 0.10071392146863845,
2772
+ "grad_norm": 4.432600498199463,
2773
+ "learning_rate": 9.930448237812462e-06,
2774
+ "loss": 0.5782884359359741,
2775
+ "step": 395
2776
+ },
2777
+ {
2778
+ "epoch": 0.1009688934217236,
2779
+ "grad_norm": 7.759515762329102,
2780
+ "learning_rate": 9.929745574671714e-06,
2781
+ "loss": 0.58075350522995,
2782
+ "step": 396
2783
+ },
2784
+ {
2785
+ "epoch": 0.10122386537480878,
2786
+ "grad_norm": 4.055099964141846,
2787
+ "learning_rate": 9.929039405048502e-06,
2788
+ "loss": 0.5670657157897949,
2789
+ "step": 397
2790
+ },
2791
+ {
2792
+ "epoch": 0.10147883732789394,
2793
+ "grad_norm": 5.6480326652526855,
2794
+ "learning_rate": 9.928329729445118e-06,
2795
+ "loss": 0.5497553944587708,
2796
+ "step": 398
2797
+ },
2798
+ {
2799
+ "epoch": 0.1017338092809791,
2800
+ "grad_norm": 5.648945331573486,
2801
+ "learning_rate": 9.92761654836635e-06,
2802
+ "loss": 0.5727936029434204,
2803
+ "step": 399
2804
+ },
2805
+ {
2806
+ "epoch": 0.10198878123406425,
2807
+ "grad_norm": 8.808309555053711,
2808
+ "learning_rate": 9.926899862319472e-06,
2809
+ "loss": 0.5711077451705933,
2810
+ "step": 400
2811
+ },
2812
+ {
2813
+ "epoch": 0.10224375318714941,
2814
+ "grad_norm": 4.987074375152588,
2815
+ "learning_rate": 9.92617967181426e-06,
2816
+ "loss": 0.5715692043304443,
2817
+ "step": 401
2818
+ },
2819
+ {
2820
+ "epoch": 0.10249872514023457,
2821
+ "grad_norm": 10.667113304138184,
2822
+ "learning_rate": 9.92545597736298e-06,
2823
+ "loss": 0.579121470451355,
2824
+ "step": 402
2825
+ },
2826
+ {
2827
+ "epoch": 0.10275369709331973,
2828
+ "grad_norm": 3.9461591243743896,
2829
+ "learning_rate": 9.924728779480386e-06,
2830
+ "loss": 0.5666054487228394,
2831
+ "step": 403
2832
+ },
2833
+ {
2834
+ "epoch": 0.10300866904640489,
2835
+ "grad_norm": 4.880352020263672,
2836
+ "learning_rate": 9.923998078683728e-06,
2837
+ "loss": 0.5608178377151489,
2838
+ "step": 404
2839
+ },
2840
+ {
2841
+ "epoch": 0.10326364099949005,
2842
+ "grad_norm": 2.8450400829315186,
2843
+ "learning_rate": 9.923263875492745e-06,
2844
+ "loss": 0.5613754987716675,
2845
+ "step": 405
2846
+ },
2847
+ {
2848
+ "epoch": 0.10351861295257522,
2849
+ "grad_norm": 2.3046202659606934,
2850
+ "learning_rate": 9.922526170429675e-06,
2851
+ "loss": 0.5492349863052368,
2852
+ "step": 406
2853
+ },
2854
+ {
2855
+ "epoch": 0.10377358490566038,
2856
+ "grad_norm": 3.4868693351745605,
2857
+ "learning_rate": 9.921784964019234e-06,
2858
+ "loss": 0.552125871181488,
2859
+ "step": 407
2860
+ },
2861
+ {
2862
+ "epoch": 0.10402855685874554,
2863
+ "grad_norm": 2.966796875,
2864
+ "learning_rate": 9.92104025678864e-06,
2865
+ "loss": 0.5744848251342773,
2866
+ "step": 408
2867
+ },
2868
+ {
2869
+ "epoch": 0.1042835288118307,
2870
+ "grad_norm": 3.2738051414489746,
2871
+ "learning_rate": 9.920292049267592e-06,
2872
+ "loss": 0.5550822615623474,
2873
+ "step": 409
2874
+ },
2875
+ {
2876
+ "epoch": 0.10453850076491586,
2877
+ "grad_norm": 2.2583632469177246,
2878
+ "learning_rate": 9.919540341988287e-06,
2879
+ "loss": 0.5528494119644165,
2880
+ "step": 410
2881
+ },
2882
+ {
2883
+ "epoch": 0.10479347271800102,
2884
+ "grad_norm": 1.9360980987548828,
2885
+ "learning_rate": 9.918785135485405e-06,
2886
+ "loss": 0.5590968728065491,
2887
+ "step": 411
2888
+ },
2889
+ {
2890
+ "epoch": 0.10504844467108618,
2891
+ "grad_norm": 1.826249599456787,
2892
+ "learning_rate": 9.918026430296119e-06,
2893
+ "loss": 0.5546989440917969,
2894
+ "step": 412
2895
+ },
2896
+ {
2897
+ "epoch": 0.10530341662417134,
2898
+ "grad_norm": 4.0869879722595215,
2899
+ "learning_rate": 9.917264226960088e-06,
2900
+ "loss": 0.5490781664848328,
2901
+ "step": 413
2902
+ },
2903
+ {
2904
+ "epoch": 0.1055583885772565,
2905
+ "grad_norm": 2.0648045539855957,
2906
+ "learning_rate": 9.916498526019461e-06,
2907
+ "loss": 0.5518783330917358,
2908
+ "step": 414
2909
+ },
2910
+ {
2911
+ "epoch": 0.10581336053034167,
2912
+ "grad_norm": 2.43099045753479,
2913
+ "learning_rate": 9.915729328018874e-06,
2914
+ "loss": 0.5636767745018005,
2915
+ "step": 415
2916
+ },
2917
+ {
2918
+ "epoch": 0.10606833248342683,
2919
+ "grad_norm": 11.354096412658691,
2920
+ "learning_rate": 9.914956633505449e-06,
2921
+ "loss": 0.5413601398468018,
2922
+ "step": 416
2923
+ },
2924
+ {
2925
+ "epoch": 0.10632330443651199,
2926
+ "grad_norm": 2.1528172492980957,
2927
+ "learning_rate": 9.914180443028798e-06,
2928
+ "loss": 0.5820633172988892,
2929
+ "step": 417
2930
+ },
2931
+ {
2932
+ "epoch": 0.10657827638959715,
2933
+ "grad_norm": 1.944624423980713,
2934
+ "learning_rate": 9.913400757141016e-06,
2935
+ "loss": 0.569353461265564,
2936
+ "step": 418
2937
+ },
2938
+ {
2939
+ "epoch": 0.1068332483426823,
2940
+ "grad_norm": 1.8753156661987305,
2941
+ "learning_rate": 9.91261757639669e-06,
2942
+ "loss": 0.5503973960876465,
2943
+ "step": 419
2944
+ },
2945
+ {
2946
+ "epoch": 0.10708822029576746,
2947
+ "grad_norm": 4.639176368713379,
2948
+ "learning_rate": 9.911830901352887e-06,
2949
+ "loss": 0.5602145195007324,
2950
+ "step": 420
2951
+ },
2952
+ {
2953
+ "epoch": 0.10734319224885262,
2954
+ "grad_norm": 2.0952956676483154,
2955
+ "learning_rate": 9.91104073256916e-06,
2956
+ "loss": 0.5641953945159912,
2957
+ "step": 421
2958
+ },
2959
+ {
2960
+ "epoch": 0.10759816420193778,
2961
+ "grad_norm": 2.922534465789795,
2962
+ "learning_rate": 9.91024707060755e-06,
2963
+ "loss": 0.5575719475746155,
2964
+ "step": 422
2965
+ },
2966
+ {
2967
+ "epoch": 0.10785313615502294,
2968
+ "grad_norm": 2.3282814025878906,
2969
+ "learning_rate": 9.909449916032586e-06,
2970
+ "loss": 0.5521407127380371,
2971
+ "step": 423
2972
+ },
2973
+ {
2974
+ "epoch": 0.10810810810810811,
2975
+ "grad_norm": 3.6761107444763184,
2976
+ "learning_rate": 9.90864926941127e-06,
2977
+ "loss": 0.545198917388916,
2978
+ "step": 424
2979
+ },
2980
+ {
2981
+ "epoch": 0.10836308006119327,
2982
+ "grad_norm": 3.0300190448760986,
2983
+ "learning_rate": 9.907845131313097e-06,
2984
+ "loss": 0.553956925868988,
2985
+ "step": 425
2986
+ },
2987
+ {
2988
+ "epoch": 0.10861805201427843,
2989
+ "grad_norm": 2.0869300365448,
2990
+ "learning_rate": 9.907037502310045e-06,
2991
+ "loss": 0.5557433366775513,
2992
+ "step": 426
2993
+ },
2994
+ {
2995
+ "epoch": 0.10887302396736359,
2996
+ "grad_norm": 8.301857948303223,
2997
+ "learning_rate": 9.906226382976568e-06,
2998
+ "loss": 0.5531321167945862,
2999
+ "step": 427
3000
+ },
3001
+ {
3002
+ "epoch": 0.10912799592044875,
3003
+ "grad_norm": 1.706969141960144,
3004
+ "learning_rate": 9.905411773889613e-06,
3005
+ "loss": 0.5832129716873169,
3006
+ "step": 428
3007
+ },
3008
+ {
3009
+ "epoch": 0.10938296787353391,
3010
+ "grad_norm": 4.29292106628418,
3011
+ "learning_rate": 9.904593675628603e-06,
3012
+ "loss": 0.5588259100914001,
3013
+ "step": 429
3014
+ },
3015
+ {
3016
+ "epoch": 0.10963793982661907,
3017
+ "grad_norm": 1.8968133926391602,
3018
+ "learning_rate": 9.903772088775441e-06,
3019
+ "loss": 0.5617460608482361,
3020
+ "step": 430
3021
+ },
3022
+ {
3023
+ "epoch": 0.10989291177970423,
3024
+ "grad_norm": 2.2897067070007324,
3025
+ "learning_rate": 9.902947013914515e-06,
3026
+ "loss": 0.56639564037323,
3027
+ "step": 431
3028
+ },
3029
+ {
3030
+ "epoch": 0.11014788373278939,
3031
+ "grad_norm": 1.9766414165496826,
3032
+ "learning_rate": 9.902118451632694e-06,
3033
+ "loss": 0.5575860738754272,
3034
+ "step": 432
3035
+ },
3036
+ {
3037
+ "epoch": 0.11040285568587456,
3038
+ "grad_norm": 1.9631874561309814,
3039
+ "learning_rate": 9.901286402519328e-06,
3040
+ "loss": 0.5484806895256042,
3041
+ "step": 433
3042
+ },
3043
+ {
3044
+ "epoch": 0.11065782763895972,
3045
+ "grad_norm": 1.556809425354004,
3046
+ "learning_rate": 9.900450867166244e-06,
3047
+ "loss": 0.5607021450996399,
3048
+ "step": 434
3049
+ },
3050
+ {
3051
+ "epoch": 0.11091279959204488,
3052
+ "grad_norm": 2.1358542442321777,
3053
+ "learning_rate": 9.89961184616775e-06,
3054
+ "loss": 0.5543813109397888,
3055
+ "step": 435
3056
+ },
3057
+ {
3058
+ "epoch": 0.11116777154513004,
3059
+ "grad_norm": 1.9221220016479492,
3060
+ "learning_rate": 9.898769340120635e-06,
3061
+ "loss": 0.5601315498352051,
3062
+ "step": 436
3063
+ },
3064
+ {
3065
+ "epoch": 0.1114227434982152,
3066
+ "grad_norm": 1.6563795804977417,
3067
+ "learning_rate": 9.897923349624165e-06,
3068
+ "loss": 0.5403985977172852,
3069
+ "step": 437
3070
+ },
3071
+ {
3072
+ "epoch": 0.11167771545130036,
3073
+ "grad_norm": 1.8465486764907837,
3074
+ "learning_rate": 9.897073875280088e-06,
3075
+ "loss": 0.5579530000686646,
3076
+ "step": 438
3077
+ },
3078
+ {
3079
+ "epoch": 0.11193268740438551,
3080
+ "grad_norm": 1.7812130451202393,
3081
+ "learning_rate": 9.896220917692624e-06,
3082
+ "loss": 0.5482833385467529,
3083
+ "step": 439
3084
+ },
3085
+ {
3086
+ "epoch": 0.11218765935747067,
3087
+ "grad_norm": 1.6004902124404907,
3088
+ "learning_rate": 9.895364477468474e-06,
3089
+ "loss": 0.5627224445343018,
3090
+ "step": 440
3091
+ },
3092
+ {
3093
+ "epoch": 0.11244263131055583,
3094
+ "grad_norm": 2.030223846435547,
3095
+ "learning_rate": 9.894504555216818e-06,
3096
+ "loss": 0.5554012656211853,
3097
+ "step": 441
3098
+ },
3099
+ {
3100
+ "epoch": 0.112697603263641,
3101
+ "grad_norm": 2.268024444580078,
3102
+ "learning_rate": 9.893641151549309e-06,
3103
+ "loss": 0.5493656992912292,
3104
+ "step": 442
3105
+ },
3106
+ {
3107
+ "epoch": 0.11295257521672616,
3108
+ "grad_norm": 17.941709518432617,
3109
+ "learning_rate": 9.89277426708008e-06,
3110
+ "loss": 0.5542835593223572,
3111
+ "step": 443
3112
+ },
3113
+ {
3114
+ "epoch": 0.11320754716981132,
3115
+ "grad_norm": 1.722589373588562,
3116
+ "learning_rate": 9.891903902425735e-06,
3117
+ "loss": 0.5496931076049805,
3118
+ "step": 444
3119
+ },
3120
+ {
3121
+ "epoch": 0.11346251912289648,
3122
+ "grad_norm": 2.5744998455047607,
3123
+ "learning_rate": 9.891030058205359e-06,
3124
+ "loss": 0.5635861158370972,
3125
+ "step": 445
3126
+ },
3127
+ {
3128
+ "epoch": 0.11371749107598164,
3129
+ "grad_norm": 4.437044143676758,
3130
+ "learning_rate": 9.890152735040508e-06,
3131
+ "loss": 0.5610167980194092,
3132
+ "step": 446
3133
+ },
3134
+ {
3135
+ "epoch": 0.1139724630290668,
3136
+ "grad_norm": 2.3134236335754395,
3137
+ "learning_rate": 9.889271933555214e-06,
3138
+ "loss": 0.5595861077308655,
3139
+ "step": 447
3140
+ },
3141
+ {
3142
+ "epoch": 0.11422743498215196,
3143
+ "grad_norm": 2.3492934703826904,
3144
+ "learning_rate": 9.888387654375982e-06,
3145
+ "loss": 0.5650231242179871,
3146
+ "step": 448
3147
+ },
3148
+ {
3149
+ "epoch": 0.11448240693523712,
3150
+ "grad_norm": 2.3988776206970215,
3151
+ "learning_rate": 9.887499898131794e-06,
3152
+ "loss": 0.5635617971420288,
3153
+ "step": 449
3154
+ },
3155
+ {
3156
+ "epoch": 0.11473737888832228,
3157
+ "grad_norm": 1.8519774675369263,
3158
+ "learning_rate": 9.886608665454103e-06,
3159
+ "loss": 0.5491594076156616,
3160
+ "step": 450
3161
+ },
3162
+ {
3163
+ "epoch": 0.11499235084140745,
3164
+ "grad_norm": 3.4155073165893555,
3165
+ "learning_rate": 9.885713956976831e-06,
3166
+ "loss": 0.5530607104301453,
3167
+ "step": 451
3168
+ },
3169
+ {
3170
+ "epoch": 0.11524732279449261,
3171
+ "grad_norm": 2.399628162384033,
3172
+ "learning_rate": 9.884815773336378e-06,
3173
+ "loss": 0.556371808052063,
3174
+ "step": 452
3175
+ },
3176
+ {
3177
+ "epoch": 0.11550229474757777,
3178
+ "grad_norm": 2.0557265281677246,
3179
+ "learning_rate": 9.883914115171614e-06,
3180
+ "loss": 0.5491721034049988,
3181
+ "step": 453
3182
+ },
3183
+ {
3184
+ "epoch": 0.11575726670066293,
3185
+ "grad_norm": 1.9038746356964111,
3186
+ "learning_rate": 9.883008983123881e-06,
3187
+ "loss": 0.5566811561584473,
3188
+ "step": 454
3189
+ },
3190
+ {
3191
+ "epoch": 0.11601223865374809,
3192
+ "grad_norm": 2.2605245113372803,
3193
+ "learning_rate": 9.882100377836988e-06,
3194
+ "loss": 0.5654865503311157,
3195
+ "step": 455
3196
+ },
3197
+ {
3198
+ "epoch": 0.11626721060683325,
3199
+ "grad_norm": 1.8456274271011353,
3200
+ "learning_rate": 9.88118829995722e-06,
3201
+ "loss": 0.5562974214553833,
3202
+ "step": 456
3203
+ },
3204
+ {
3205
+ "epoch": 0.1165221825599184,
3206
+ "grad_norm": 1.7836940288543701,
3207
+ "learning_rate": 9.880272750133328e-06,
3208
+ "loss": 0.566531777381897,
3209
+ "step": 457
3210
+ },
3211
+ {
3212
+ "epoch": 0.11677715451300356,
3213
+ "grad_norm": 2.3698477745056152,
3214
+ "learning_rate": 9.879353729016537e-06,
3215
+ "loss": 0.557073175907135,
3216
+ "step": 458
3217
+ },
3218
+ {
3219
+ "epoch": 0.11703212646608872,
3220
+ "grad_norm": 3.380236864089966,
3221
+ "learning_rate": 9.878431237260535e-06,
3222
+ "loss": 0.5533016920089722,
3223
+ "step": 459
3224
+ },
3225
+ {
3226
+ "epoch": 0.1172870984191739,
3227
+ "grad_norm": 2.136101245880127,
3228
+ "learning_rate": 9.877505275521485e-06,
3229
+ "loss": 0.555318295955658,
3230
+ "step": 460
3231
+ },
3232
+ {
3233
+ "epoch": 0.11754207037225906,
3234
+ "grad_norm": 4.435114860534668,
3235
+ "learning_rate": 9.876575844458012e-06,
3236
+ "loss": 0.5532917976379395,
3237
+ "step": 461
3238
+ },
3239
+ {
3240
+ "epoch": 0.11779704232534421,
3241
+ "grad_norm": 2.546670913696289,
3242
+ "learning_rate": 9.875642944731212e-06,
3243
+ "loss": 0.5604023337364197,
3244
+ "step": 462
3245
+ },
3246
+ {
3247
+ "epoch": 0.11805201427842937,
3248
+ "grad_norm": 3.9529716968536377,
3249
+ "learning_rate": 9.87470657700465e-06,
3250
+ "loss": 0.5603578090667725,
3251
+ "step": 463
3252
+ },
3253
+ {
3254
+ "epoch": 0.11830698623151453,
3255
+ "grad_norm": 2.1415586471557617,
3256
+ "learning_rate": 9.873766741944353e-06,
3257
+ "loss": 0.5529968738555908,
3258
+ "step": 464
3259
+ },
3260
+ {
3261
+ "epoch": 0.11856195818459969,
3262
+ "grad_norm": 2.085867166519165,
3263
+ "learning_rate": 9.872823440218821e-06,
3264
+ "loss": 0.5548291206359863,
3265
+ "step": 465
3266
+ },
3267
+ {
3268
+ "epoch": 0.11881693013768485,
3269
+ "grad_norm": 3.555215358734131,
3270
+ "learning_rate": 9.871876672499012e-06,
3271
+ "loss": 0.5481231212615967,
3272
+ "step": 466
3273
+ },
3274
+ {
3275
+ "epoch": 0.11907190209077001,
3276
+ "grad_norm": 2.137446641921997,
3277
+ "learning_rate": 9.870926439458355e-06,
3278
+ "loss": 0.5487592220306396,
3279
+ "step": 467
3280
+ },
3281
+ {
3282
+ "epoch": 0.11932687404385518,
3283
+ "grad_norm": 2.8710625171661377,
3284
+ "learning_rate": 9.86997274177274e-06,
3285
+ "loss": 0.5602512955665588,
3286
+ "step": 468
3287
+ },
3288
+ {
3289
+ "epoch": 0.11958184599694034,
3290
+ "grad_norm": 2.24103045463562,
3291
+ "learning_rate": 9.869015580120527e-06,
3292
+ "loss": 0.5430268049240112,
3293
+ "step": 469
3294
+ },
3295
+ {
3296
+ "epoch": 0.1198368179500255,
3297
+ "grad_norm": 2.0165767669677734,
3298
+ "learning_rate": 9.868054955182533e-06,
3299
+ "loss": 0.5526243448257446,
3300
+ "step": 470
3301
+ },
3302
+ {
3303
+ "epoch": 0.12009178990311066,
3304
+ "grad_norm": 2.7446656227111816,
3305
+ "learning_rate": 9.867090867642042e-06,
3306
+ "loss": 0.5715802311897278,
3307
+ "step": 471
3308
+ },
3309
+ {
3310
+ "epoch": 0.12034676185619582,
3311
+ "grad_norm": 4.814818382263184,
3312
+ "learning_rate": 9.866123318184803e-06,
3313
+ "loss": 0.5400905609130859,
3314
+ "step": 472
3315
+ },
3316
+ {
3317
+ "epoch": 0.12060173380928098,
3318
+ "grad_norm": 2.0347468852996826,
3319
+ "learning_rate": 9.865152307499022e-06,
3320
+ "loss": 0.5547370314598083,
3321
+ "step": 473
3322
+ },
3323
+ {
3324
+ "epoch": 0.12085670576236614,
3325
+ "grad_norm": 1.9471986293792725,
3326
+ "learning_rate": 9.864177836275371e-06,
3327
+ "loss": 0.5558183193206787,
3328
+ "step": 474
3329
+ },
3330
+ {
3331
+ "epoch": 0.1211116777154513,
3332
+ "grad_norm": 2.60526180267334,
3333
+ "learning_rate": 9.863199905206983e-06,
3334
+ "loss": 0.5537914037704468,
3335
+ "step": 475
3336
+ },
3337
+ {
3338
+ "epoch": 0.12136664966853646,
3339
+ "grad_norm": 2.1302649974823,
3340
+ "learning_rate": 9.862218514989452e-06,
3341
+ "loss": 0.5470219850540161,
3342
+ "step": 476
3343
+ },
3344
+ {
3345
+ "epoch": 0.12162162162162163,
3346
+ "grad_norm": 2.58955717086792,
3347
+ "learning_rate": 9.861233666320828e-06,
3348
+ "loss": 0.5556906461715698,
3349
+ "step": 477
3350
+ },
3351
+ {
3352
+ "epoch": 0.12187659357470679,
3353
+ "grad_norm": 2.096116304397583,
3354
+ "learning_rate": 9.86024535990163e-06,
3355
+ "loss": 0.5494530200958252,
3356
+ "step": 478
3357
+ },
3358
+ {
3359
+ "epoch": 0.12213156552779195,
3360
+ "grad_norm": 2.0807015895843506,
3361
+ "learning_rate": 9.859253596434828e-06,
3362
+ "loss": 0.5564595460891724,
3363
+ "step": 479
3364
+ },
3365
+ {
3366
+ "epoch": 0.1223865374808771,
3367
+ "grad_norm": 3.05375599861145,
3368
+ "learning_rate": 9.858258376625855e-06,
3369
+ "loss": 0.5492424964904785,
3370
+ "step": 480
3371
+ },
3372
+ {
3373
+ "epoch": 0.12264150943396226,
3374
+ "grad_norm": 2.2253363132476807,
3375
+ "learning_rate": 9.8572597011826e-06,
3376
+ "loss": 0.5405623912811279,
3377
+ "step": 481
3378
+ },
3379
+ {
3380
+ "epoch": 0.12289648138704742,
3381
+ "grad_norm": 5.153561115264893,
3382
+ "learning_rate": 9.856257570815415e-06,
3383
+ "loss": 0.5545088052749634,
3384
+ "step": 482
3385
+ },
3386
+ {
3387
+ "epoch": 0.12315145334013258,
3388
+ "grad_norm": 1.9642194509506226,
3389
+ "learning_rate": 9.855251986237103e-06,
3390
+ "loss": 0.5469231009483337,
3391
+ "step": 483
3392
+ },
3393
+ {
3394
+ "epoch": 0.12340642529321774,
3395
+ "grad_norm": 4.149758815765381,
3396
+ "learning_rate": 9.85424294816293e-06,
3397
+ "loss": 0.5515980124473572,
3398
+ "step": 484
3399
+ },
3400
+ {
3401
+ "epoch": 0.1236613972463029,
3402
+ "grad_norm": 3.9454345703125,
3403
+ "learning_rate": 9.853230457310613e-06,
3404
+ "loss": 0.5524808168411255,
3405
+ "step": 485
3406
+ },
3407
+ {
3408
+ "epoch": 0.12391636919938807,
3409
+ "grad_norm": 1.893150806427002,
3410
+ "learning_rate": 9.852214514400326e-06,
3411
+ "loss": 0.5513901710510254,
3412
+ "step": 486
3413
+ },
3414
+ {
3415
+ "epoch": 0.12417134115247323,
3416
+ "grad_norm": 2.6218254566192627,
3417
+ "learning_rate": 9.851195120154701e-06,
3418
+ "loss": 0.5557699799537659,
3419
+ "step": 487
3420
+ },
3421
+ {
3422
+ "epoch": 0.12442631310555839,
3423
+ "grad_norm": 4.718894958496094,
3424
+ "learning_rate": 9.850172275298828e-06,
3425
+ "loss": 0.5626286268234253,
3426
+ "step": 488
3427
+ },
3428
+ {
3429
+ "epoch": 0.12468128505864355,
3430
+ "grad_norm": 2.0461502075195312,
3431
+ "learning_rate": 9.849145980560243e-06,
3432
+ "loss": 0.5560814738273621,
3433
+ "step": 489
3434
+ },
3435
+ {
3436
+ "epoch": 0.12493625701172871,
3437
+ "grad_norm": 4.197045803070068,
3438
+ "learning_rate": 9.848116236668939e-06,
3439
+ "loss": 0.5595450401306152,
3440
+ "step": 490
3441
+ },
3442
+ {
3443
+ "epoch": 0.12519122896481388,
3444
+ "grad_norm": 2.1661648750305176,
3445
+ "learning_rate": 9.847083044357367e-06,
3446
+ "loss": 0.5466753840446472,
3447
+ "step": 491
3448
+ },
3449
+ {
3450
+ "epoch": 0.12544620091789904,
3451
+ "grad_norm": 2.64660382270813,
3452
+ "learning_rate": 9.846046404360423e-06,
3453
+ "loss": 0.5495432615280151,
3454
+ "step": 492
3455
+ },
3456
+ {
3457
+ "epoch": 0.1257011728709842,
3458
+ "grad_norm": 2.2083492279052734,
3459
+ "learning_rate": 9.845006317415463e-06,
3460
+ "loss": 0.5645055770874023,
3461
+ "step": 493
3462
+ },
3463
+ {
3464
+ "epoch": 0.12595614482406936,
3465
+ "grad_norm": 2.4461467266082764,
3466
+ "learning_rate": 9.843962784262289e-06,
3467
+ "loss": 0.5569705963134766,
3468
+ "step": 494
3469
+ },
3470
+ {
3471
+ "epoch": 0.12621111677715452,
3472
+ "grad_norm": 2.076951026916504,
3473
+ "learning_rate": 9.842915805643156e-06,
3474
+ "loss": 0.5476626753807068,
3475
+ "step": 495
3476
+ },
3477
+ {
3478
+ "epoch": 0.12646608873023968,
3479
+ "grad_norm": 2.278542995452881,
3480
+ "learning_rate": 9.841865382302773e-06,
3481
+ "loss": 0.5460015535354614,
3482
+ "step": 496
3483
+ },
3484
+ {
3485
+ "epoch": 0.12672106068332484,
3486
+ "grad_norm": 2.187434673309326,
3487
+ "learning_rate": 9.840811514988294e-06,
3488
+ "loss": 0.5466282367706299,
3489
+ "step": 497
3490
+ },
3491
+ {
3492
+ "epoch": 0.12697603263641,
3493
+ "grad_norm": 2.5430383682250977,
3494
+ "learning_rate": 9.839754204449328e-06,
3495
+ "loss": 0.5423339605331421,
3496
+ "step": 498
3497
+ },
3498
+ {
3499
+ "epoch": 0.12723100458949516,
3500
+ "grad_norm": 3.8312206268310547,
3501
+ "learning_rate": 9.838693451437926e-06,
3502
+ "loss": 0.5447465777397156,
3503
+ "step": 499
3504
+ },
3505
+ {
3506
+ "epoch": 0.12748597654258031,
3507
+ "grad_norm": 2.2003931999206543,
3508
+ "learning_rate": 9.837629256708595e-06,
3509
+ "loss": 0.5435498952865601,
3510
+ "step": 500
3511
+ }
3512
+ ],
3513
+ "logging_steps": 1,
3514
+ "max_steps": 3922,
3515
+ "num_input_tokens_seen": 0,
3516
+ "num_train_epochs": 1,
3517
+ "save_steps": 500,
3518
+ "stateful_callbacks": {
3519
+ "TrainerControl": {
3520
+ "args": {
3521
+ "should_epoch_stop": false,
3522
+ "should_evaluate": false,
3523
+ "should_log": false,
3524
+ "should_save": true,
3525
+ "should_training_stop": false
3526
+ },
3527
+ "attributes": {}
3528
+ }
3529
+ },
3530
+ "total_flos": 3.709996150610408e+19,
3531
+ "train_batch_size": 4,
3532
+ "trial_name": null,
3533
+ "trial_params": null
3534
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb2b71716b815c69acae19745e5f5d002f10f9854295fcea3ac09170daa4d99b
3
+ size 9297
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/video_preprocessor_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": true,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "merge_size": 2,
26
+ "min_frames": 4,
27
+ "num_frames": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_metadata": false,
34
+ "size": {
35
+ "longest_edge": 25165824,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2,
39
+ "video_metadata": null,
40
+ "video_processor_type": "Qwen3VLVideoProcessor"
41
+ }
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/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 ZERO_STAGE not 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("Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info("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)