shulin16 commited on
Commit
2f7e43b
·
verified ·
1 Parent(s): 47f3f5f

Upload final checkpoint-939

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-939/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-939/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
+ }
checkpoint-939/args.json ADDED
@@ -0,0 +1,409 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_resume500_20260503_143601_constlr",
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": 2,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 8,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 2.3e-06,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 1.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "constant",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.0,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_resume500_20260503_143601_constlr/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 5,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 100.0,
39
+ "save_total_limit": 2,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": true,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "bf16": true,
51
+ "fp16": false,
52
+ "fp16_opt_level": "O1",
53
+ "half_precision_backend": "auto",
54
+ "bf16_full_eval": false,
55
+ "fp16_full_eval": false,
56
+ "tf32": null,
57
+ "local_rank": 0,
58
+ "ddp_backend": null,
59
+ "tpu_num_cores": null,
60
+ "tpu_metrics_debug": false,
61
+ "debug": null,
62
+ "dataloader_drop_last": false,
63
+ "eval_steps": 100.0,
64
+ "dataloader_num_workers": 2,
65
+ "dataloader_prefetch_factor": null,
66
+ "past_index": -1,
67
+ "run_name": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_resume500_20260503_143601_constlr",
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": 3,
97
+ "offload_optimizer": {
98
+ "device": "none",
99
+ "pin_memory": true
100
+ },
101
+ "offload_param": {
102
+ "device": "none",
103
+ "pin_memory": true
104
+ },
105
+ "overlap_comm": false,
106
+ "contiguous_gradients": true,
107
+ "sub_group_size": 1000000000.0,
108
+ "reduce_bucket_size": "auto",
109
+ "zero_quantized_weights": false,
110
+ "zero_quantized_gradients": false,
111
+ "stage3_prefetch_bucket_size": "auto",
112
+ "stage3_param_persistence_threshold": "auto",
113
+ "stage3_max_live_parameters": 1000000000.0,
114
+ "stage3_max_reuse_distance": 1000000000.0,
115
+ "stage3_gather_16bit_weights_on_model_save": true
116
+ },
117
+ "gradient_accumulation_steps": "auto",
118
+ "gradient_clipping": "auto",
119
+ "steps_per_print": 2000,
120
+ "train_batch_size": "auto",
121
+ "train_micro_batch_size_per_gpu": "auto",
122
+ "wall_clock_breakdown": false
123
+ },
124
+ "label_smoothing_factor": 0.0,
125
+ "optim": "adamw_torch",
126
+ "optim_args": null,
127
+ "adafactor": false,
128
+ "group_by_length": false,
129
+ "length_column_name": "length",
130
+ "report_to": [
131
+ "tensorboard"
132
+ ],
133
+ "project": "huggingface",
134
+ "trackio_space_id": "trackio",
135
+ "ddp_find_unused_parameters": null,
136
+ "ddp_bucket_cap_mb": null,
137
+ "ddp_broadcast_buffers": null,
138
+ "dataloader_pin_memory": true,
139
+ "dataloader_persistent_workers": false,
140
+ "skip_memory_metrics": true,
141
+ "use_legacy_prediction_loop": false,
142
+ "push_to_hub": false,
143
+ "resume_from_checkpoint": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_20260502_001938/v0-20260502-002006/checkpoint-500",
144
+ "hub_model_id": null,
145
+ "hub_strategy": "every_save",
146
+ "hub_token": null,
147
+ "hub_private_repo": null,
148
+ "hub_always_push": false,
149
+ "hub_revision": null,
150
+ "gradient_checkpointing": true,
151
+ "gradient_checkpointing_kwargs": null,
152
+ "include_inputs_for_metrics": false,
153
+ "include_for_metrics": [],
154
+ "eval_do_concat_batches": true,
155
+ "fp16_backend": "auto",
156
+ "push_to_hub_model_id": null,
157
+ "push_to_hub_organization": null,
158
+ "push_to_hub_token": null,
159
+ "mp_parameters": "",
160
+ "auto_find_batch_size": false,
161
+ "full_determinism": false,
162
+ "torchdynamo": null,
163
+ "ray_scope": "last",
164
+ "ddp_timeout": 18000000,
165
+ "torch_compile": false,
166
+ "torch_compile_backend": null,
167
+ "torch_compile_mode": null,
168
+ "include_tokens_per_second": false,
169
+ "include_num_input_tokens_seen": false,
170
+ "neftune_noise_alpha": null,
171
+ "optim_target_modules": null,
172
+ "batch_eval_metrics": false,
173
+ "eval_on_start": false,
174
+ "use_liger_kernel": false,
175
+ "liger_kernel_config": null,
176
+ "eval_use_gather_object": false,
177
+ "average_tokens_across_devices": true,
178
+ "sortish_sampler": false,
179
+ "predict_with_generate": false,
180
+ "generation_max_length": null,
181
+ "generation_num_beams": null,
182
+ "generation_config": null,
183
+ "tuner_backend": "peft",
184
+ "vit_gradient_checkpointing": false,
185
+ "router_aux_loss_coef": 0.0,
186
+ "enable_dft_loss": false,
187
+ "enable_channel_loss": false,
188
+ "safe_serialization": true,
189
+ "max_shard_size": "5GB",
190
+ "check_model": true,
191
+ "acc_strategy": "token",
192
+ "train_dataloader_shuffle": true,
193
+ "max_epochs": null,
194
+ "aligner_lr": null,
195
+ "vit_lr": null,
196
+ "use_logits_to_keep": null,
197
+ "ds3_gather_for_generation": true,
198
+ "resume_only_model": true,
199
+ "optimizer": null,
200
+ "loss_type": null,
201
+ "eval_metric": null,
202
+ "callbacks": [],
203
+ "early_stop_interval": null,
204
+ "eval_use_evalscope": false,
205
+ "eval_dataset": [],
206
+ "eval_dataset_args": null,
207
+ "eval_limit": null,
208
+ "eval_generation_config": null,
209
+ "extra_eval_args": null,
210
+ "tuner_type": "full",
211
+ "use_galore": false,
212
+ "galore_target_modules": null,
213
+ "galore_rank": 128,
214
+ "galore_update_proj_gap": 50,
215
+ "galore_scale": 1.0,
216
+ "galore_proj_type": "std",
217
+ "galore_optim_per_parameter": false,
218
+ "galore_with_embedding": false,
219
+ "galore_quantization": false,
220
+ "galore_proj_quant": false,
221
+ "galore_proj_bits": 4,
222
+ "galore_proj_group_size": 256,
223
+ "galore_cos_threshold": 0.4,
224
+ "galore_gamma_proj": 2,
225
+ "galore_queue_size": 5,
226
+ "lisa_activated_layers": 0,
227
+ "lisa_step_interval": 20,
228
+ "use_flash_ckpt": false,
229
+ "use_ray": false,
230
+ "ray_exp_name": null,
231
+ "device_groups": null,
232
+ "model": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_20260502_001938/v0-20260502-002006/checkpoint-500",
233
+ "model_type": "qwen3_vl",
234
+ "model_revision": null,
235
+ "task_type": "causal_lm",
236
+ "torch_dtype": "bfloat16",
237
+ "attn_impl": "flash_attn",
238
+ "experts_impl": null,
239
+ "new_special_tokens": [],
240
+ "num_labels": null,
241
+ "problem_type": null,
242
+ "rope_scaling": null,
243
+ "device_map": null,
244
+ "max_memory": {},
245
+ "max_model_len": null,
246
+ "local_repo_path": null,
247
+ "init_strategy": null,
248
+ "template": "qwen3_vl",
249
+ "system": null,
250
+ "max_length": 4096,
251
+ "truncation_strategy": "delete",
252
+ "max_pixels": null,
253
+ "agent_template": null,
254
+ "norm_bbox": null,
255
+ "use_chat_template": true,
256
+ "padding_side": "right",
257
+ "padding_free": false,
258
+ "loss_scale": "default",
259
+ "sequence_parallel_size": 1,
260
+ "template_backend": "swift",
261
+ "response_prefix": null,
262
+ "enable_thinking": null,
263
+ "add_non_thinking_prefix": true,
264
+ "dataset": [
265
+ "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/data_v2/egotools_v2_sft_final_clips.letter_balanced.swift.jsonl"
266
+ ],
267
+ "val_dataset": [],
268
+ "cached_dataset": [],
269
+ "cached_val_dataset": [],
270
+ "split_dataset_ratio": 0.0,
271
+ "dataset_num_proc": 16,
272
+ "load_from_cache_file": false,
273
+ "dataset_shuffle": true,
274
+ "val_dataset_shuffle": false,
275
+ "streaming": false,
276
+ "interleave_prob": null,
277
+ "stopping_strategy": "first_exhausted",
278
+ "shuffle_buffer_size": 1000,
279
+ "download_mode": "reuse_dataset_if_exists",
280
+ "columns": {},
281
+ "strict": false,
282
+ "disable_auto_column_mapping": false,
283
+ "model_name": null,
284
+ "model_author": null,
285
+ "custom_dataset_info": [],
286
+ "quant_method": null,
287
+ "quant_bits": null,
288
+ "hqq_axis": null,
289
+ "bnb_4bit_compute_dtype": "bfloat16",
290
+ "bnb_4bit_quant_type": "nf4",
291
+ "bnb_4bit_use_double_quant": true,
292
+ "bnb_4bit_quant_storage": null,
293
+ "max_new_tokens": 64,
294
+ "temperature": 0.0,
295
+ "top_k": null,
296
+ "top_p": null,
297
+ "repetition_penalty": null,
298
+ "num_beams": 1,
299
+ "stream": false,
300
+ "stop_words": [],
301
+ "logprobs": false,
302
+ "top_logprobs": null,
303
+ "structured_outputs_regex": null,
304
+ "adapters": [],
305
+ "external_plugins": [],
306
+ "custom_register_path": [],
307
+ "model_kwargs": {},
308
+ "enable_npu_model_patch": true,
309
+ "load_args": false,
310
+ "load_data_args": false,
311
+ "packing": false,
312
+ "packing_length": null,
313
+ "packing_num_proc": 1,
314
+ "lazy_tokenize": true,
315
+ "use_hf": false,
316
+ "ignore_args_error": false,
317
+ "use_swift_lora": false,
318
+ "freeze_parameters": [
319
+ "model.visual",
320
+ "model.visual.merger",
321
+ "model.visual.deepstack_merger_list"
322
+ ],
323
+ "freeze_parameters_regex": null,
324
+ "freeze_parameters_ratio": 0.0,
325
+ "trainable_parameters": [],
326
+ "trainable_parameters_regex": null,
327
+ "freeze_llm": false,
328
+ "freeze_vit": true,
329
+ "freeze_aligner": true,
330
+ "target_modules": [
331
+ "all-linear"
332
+ ],
333
+ "target_regex": null,
334
+ "target_parameters": null,
335
+ "modules_to_save": [],
336
+ "lora_rank": 8,
337
+ "lora_alpha": 32,
338
+ "lora_dropout": 0.05,
339
+ "lora_bias": "none",
340
+ "lora_dtype": null,
341
+ "lorap_lr_ratio": null,
342
+ "use_rslora": false,
343
+ "use_dora": false,
344
+ "lora_ga_batch_size": 2,
345
+ "lora_ga_iters": 2,
346
+ "lora_ga_max_length": 1024,
347
+ "lora_ga_direction": "ArB2r",
348
+ "lora_ga_scale": "stable",
349
+ "lora_ga_stable_gamma": 16,
350
+ "init_weights": true,
351
+ "fourier_n_frequency": 2000,
352
+ "fourier_scaling": 300.0,
353
+ "boft_block_size": 4,
354
+ "boft_block_num": 0,
355
+ "boft_n_butterfly_factor": 1,
356
+ "boft_dropout": 0.0,
357
+ "vera_rank": 256,
358
+ "vera_projection_prng_key": 0,
359
+ "vera_dropout": 0.0,
360
+ "vera_d_initial": 0.1,
361
+ "adapter_act": "gelu",
362
+ "adapter_length": 128,
363
+ "adalora_target_r": 8,
364
+ "adalora_init_r": 12,
365
+ "adalora_tinit": 0,
366
+ "adalora_tfinal": 0,
367
+ "adalora_deltaT": 1,
368
+ "adalora_beta1": 0.85,
369
+ "adalora_beta2": 0.85,
370
+ "adalora_orth_reg_weight": 0.5,
371
+ "llamapro_num_new_blocks": 4,
372
+ "llamapro_num_groups": null,
373
+ "reft_layer_key": null,
374
+ "reft_layers": null,
375
+ "reft_rank": 4,
376
+ "reft_intervention_type": "LoreftIntervention",
377
+ "reft_args": null,
378
+ "swanlab_token": null,
379
+ "swanlab_project": "ms-swift",
380
+ "swanlab_workspace": null,
381
+ "swanlab_exp_name": null,
382
+ "swanlab_notification_method": null,
383
+ "swanlab_webhook_url": null,
384
+ "swanlab_secret": null,
385
+ "swanlab_sender_email": null,
386
+ "swanlab_receiver_email": null,
387
+ "swanlab_smtp_server": null,
388
+ "swanlab_smtp_port": null,
389
+ "swanlab_email_language": "zh",
390
+ "swanlab_mode": "cloud",
391
+ "add_version": false,
392
+ "create_checkpoint_symlink": false,
393
+ "zero_hpz_partition_size": null,
394
+ "deepspeed_autotp_size": null,
395
+ "swift_version": "4.2.0.dev0",
396
+ "ckpt_dir": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_20260502_001938/v0-20260502-002006/checkpoint-500",
397
+ "rank": 0,
398
+ "global_world_size": 8,
399
+ "local_world_size": 8,
400
+ "model_suffix": "checkpoint-500",
401
+ "model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_20260502_001938/v0-20260502-002006/checkpoint-500', 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)",
402
+ "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)], template='qwen3_vl', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3VLLoader'>, template=None, 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=[]), mcore_model_type=None, architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])",
403
+ "model_dir": "/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_20260502_001938/v0-20260502-002006/checkpoint-500",
404
+ "template_meta": "QwenTemplateMeta(template_type='qwen3_vl', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3VLTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='<think>\\n', non_thinking_prefix='', history_thinking_prefix='')",
405
+ "_val_dataset_exists": false,
406
+ "hub": "<class 'swift.hub.hub.MSHub'>",
407
+ "evaluation_strategy": "steps",
408
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_resume500_20260503_143601_constlr', 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=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2.3e-06, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.CONSTANT: 'constant'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_resume500_20260503_143601_constlr/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=100, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=True, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=100.0, dataloader_num_workers=2, dataloader_prefetch_factor=2, past_index=-1, run_name='/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_resume500_20260503_143601_constlr', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], 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='/mnt/raid10/sltian/egotools_dev_data/workspace/ms-swift/output/egotools_qwen3vl8b_v2_full_direct_8gpu_32f_bs2_acc8_20260502_001938/v0-20260502-002006/checkpoint-500', hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=False, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=True, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
409
+ }
checkpoint-939/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 %}
checkpoint-939/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 151645,
7
+ "hidden_size": 4096,
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": 4096,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 12288,
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
+ "use_cache": false,
40
+ "vocab_size": 151936
41
+ },
42
+ "tie_word_embeddings": false,
43
+ "transformers_version": "4.57.6",
44
+ "video_token_id": 151656,
45
+ "vision_config": {
46
+ "deepstack_visual_indexes": [
47
+ 8,
48
+ 16,
49
+ 24
50
+ ],
51
+ "depth": 27,
52
+ "dtype": "bfloat16",
53
+ "hidden_act": "gelu_pytorch_tanh",
54
+ "hidden_size": 1152,
55
+ "in_channels": 3,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4304,
58
+ "model_type": "qwen3_vl",
59
+ "num_heads": 16,
60
+ "num_position_embeddings": 2304,
61
+ "out_hidden_size": 4096,
62
+ "patch_size": 16,
63
+ "spatial_merge_size": 2,
64
+ "temporal_patch_size": 2
65
+ },
66
+ "vision_end_token_id": 151653,
67
+ "vision_start_token_id": 151652
68
+ }
checkpoint-939/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": "4.57.6"
13
+ }
checkpoint-939/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-939/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52bb9be98487dc597e783ccd42ca8935a2f62ca1694ceda3d43a39359bd3de1
3
+ size 4998056552
checkpoint-939/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb91aebfb2f00a002123727a765e7ecccd57d650f0109a6aeee55db29ccc82fd
3
+ size 4915962464
checkpoint-939/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f5e9915bb931a0530e48e83c3677d864837f0f53f622d547026730f4cce071e
3
+ size 4915962496
checkpoint-939/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c36516859c05fa9081dfaa53baf24e87cdbaa4f66ee79a0e2b8482bf40f7a24
3
+ size 2704357976
checkpoint-939/model.safetensors.index.json ADDED
@@ -0,0 +1,758 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 770288,
4
+ "total_size": 17534247392
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
15
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
18
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
26
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
29
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
37
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
40
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
43
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
48
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
51
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
59
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
62
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
70
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
73
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
81
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
84
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
87
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
92
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
95
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
103
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
106
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
114
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
117
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
120
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
122
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
124
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
125
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
128
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
130
+ "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
136
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
139
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
142
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
143
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
144
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
145
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
146
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
147
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
148
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
149
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
150
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
151
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
152
+ "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
158
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
161
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
164
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
168
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
169
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
172
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
180
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
183
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
186
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
191
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
194
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
202
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
205
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
213
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
216
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
219
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
223
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
224
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
227
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
235
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
238
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
245
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
246
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
249
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
252
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
254
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
256
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
257
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
260
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
262
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
263
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
268
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
271
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
274
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
276
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
277
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
278
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
279
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
280
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
281
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
282
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
283
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
284
+ "model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
285
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
286
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
287
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
288
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
289
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
290
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
291
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
292
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
293
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
294
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
295
+ "model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
296
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
297
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
298
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
299
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
300
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
301
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
302
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
303
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
304
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
305
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
306
+ "model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
307
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
308
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
309
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
310
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
311
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
312
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
313
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
314
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
315
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
316
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
317
+ "model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
318
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
319
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
320
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
321
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
322
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
323
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
324
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
325
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
326
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
327
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
328
+ "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
329
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
331
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
332
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
333
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
334
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
335
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
336
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
337
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
338
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
339
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
340
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
341
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
342
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
343
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
344
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
345
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
346
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
347
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
348
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
349
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
350
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
351
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
354
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
355
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
356
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
357
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
358
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
359
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
360
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
361
+ "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
362
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
363
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
364
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
365
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
366
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
367
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
368
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
369
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
370
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
371
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
372
+ "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
373
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
374
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
375
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
376
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
377
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
378
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
379
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
380
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
381
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
382
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
383
+ "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
384
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
385
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
386
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
387
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
388
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
389
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
390
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
391
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
392
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
393
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
394
+ "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
395
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
396
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
397
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
398
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
399
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
400
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
401
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
402
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
403
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
404
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
405
+ "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
406
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
407
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
408
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
409
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
410
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
411
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
412
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
413
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
414
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
415
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
416
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
417
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
418
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
419
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
420
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
421
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
422
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
423
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
424
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
425
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
426
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
427
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
428
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
429
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
430
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
431
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
432
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
433
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
434
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
435
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
436
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
437
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
438
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
439
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
440
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
441
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
442
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
443
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
444
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
445
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
446
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
447
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
448
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
449
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
450
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
451
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
452
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
453
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
454
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
455
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
456
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
457
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
458
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
459
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
460
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
461
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
462
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
463
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
464
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
465
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
466
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
467
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
468
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
469
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
470
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
471
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
472
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
473
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
474
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
475
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
476
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
477
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
478
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
479
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
480
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
481
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
482
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
483
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
484
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
485
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
486
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
487
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
488
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
489
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
490
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
491
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
492
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
493
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
494
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
495
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
496
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
497
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
498
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
499
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
500
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
501
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
502
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
503
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
504
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
505
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
506
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
507
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
508
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
509
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
510
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
511
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
512
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
513
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
514
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
515
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
516
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
517
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
518
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
519
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
520
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
521
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
522
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
523
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
524
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
525
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
526
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
527
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
528
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
529
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
530
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
531
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
532
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
533
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
534
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
535
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
536
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
537
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
538
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
539
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
540
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
541
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
542
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
543
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
544
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
545
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
546
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
547
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
548
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
549
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
550
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
551
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
552
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
553
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
554
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
555
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
556
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
557
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
558
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
559
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
560
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
561
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
562
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
563
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
564
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
565
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
566
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
567
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
568
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
569
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
570
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
571
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
572
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
573
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
574
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
575
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
576
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
577
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
578
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
579
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
580
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
581
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
582
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
583
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
584
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
585
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
586
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
587
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
588
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
589
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
590
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
591
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
592
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
593
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
594
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
595
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
596
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
597
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
598
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
599
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
600
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
601
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
602
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
603
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
604
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
605
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
606
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
607
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
608
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
609
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
610
+ "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
611
+ "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
612
+ "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
613
+ "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
614
+ "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
615
+ "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
616
+ "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
617
+ "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
618
+ "model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
619
+ "model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
620
+ "model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
621
+ "model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
622
+ "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
623
+ "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
624
+ "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
625
+ "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
626
+ "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
627
+ "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
628
+ "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
629
+ "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
630
+ "model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
631
+ "model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
632
+ "model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
633
+ "model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
634
+ "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
635
+ "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
636
+ "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
637
+ "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
638
+ "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
639
+ "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
640
+ "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
641
+ "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
642
+ "model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
643
+ "model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
644
+ "model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
645
+ "model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
646
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
647
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
648
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
649
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
650
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
651
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
652
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
653
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
654
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
655
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
656
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
657
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
658
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
659
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
660
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
661
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
662
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
663
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
664
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
665
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
666
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
667
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
668
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
669
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
670
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
671
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
672
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
673
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
674
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
675
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
676
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
677
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
678
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
679
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
680
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
681
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
682
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
683
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
684
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
685
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
686
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
687
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
688
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
689
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
690
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
691
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
692
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
693
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
694
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
695
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
696
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
697
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
698
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
699
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
700
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
701
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
702
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
703
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
704
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
705
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
706
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
707
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
708
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
709
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
710
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
711
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
712
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
713
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
714
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
715
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
716
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
717
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
718
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
719
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
720
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
721
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
722
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
723
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
724
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
725
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
726
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
727
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
728
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
729
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
730
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
731
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
732
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
733
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
734
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
735
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
736
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
737
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
738
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
739
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
740
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
741
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
742
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
743
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
744
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
745
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
746
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
747
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
748
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
749
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
750
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
751
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
752
+ "model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
753
+ "model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
754
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
755
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
756
+ "model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
757
+ }
758
+ }
checkpoint-939/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
+ }
checkpoint-939/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
+ }
checkpoint-939/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
checkpoint-939/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
+ }
checkpoint-939/trainer_state.json ADDED
@@ -0,0 +1,1538 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500.0,
7
+ "global_step": 939,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0010659560293137908,
14
+ "grad_norm": 65.16799013627562,
15
+ "learning_rate": 1.7241379310344828e-07,
16
+ "loss": 1.7501227855682373,
17
+ "step": 1,
18
+ "token_acc": 0.5974304068522484
19
+ },
20
+ {
21
+ "epoch": 0.005329780146568954,
22
+ "grad_norm": 49.60785562728193,
23
+ "learning_rate": 8.620689655172415e-07,
24
+ "loss": 1.9290522336959839,
25
+ "step": 5,
26
+ "token_acc": 0.6
27
+ },
28
+ {
29
+ "epoch": 0.010659560293137908,
30
+ "grad_norm": 19.615574554346505,
31
+ "learning_rate": 1.724137931034483e-06,
32
+ "loss": 1.787750244140625,
33
+ "step": 10,
34
+ "token_acc": 0.6390234811777861
35
+ },
36
+ {
37
+ "epoch": 0.015989340439706862,
38
+ "grad_norm": 11.065195164896805,
39
+ "learning_rate": 2.5862068965517246e-06,
40
+ "loss": 1.4807558059692383,
41
+ "step": 15,
42
+ "token_acc": 0.6601166054847765
43
+ },
44
+ {
45
+ "epoch": 0.021319120586275817,
46
+ "grad_norm": 6.817900936636832,
47
+ "learning_rate": 3.448275862068966e-06,
48
+ "loss": 1.398179054260254,
49
+ "step": 20,
50
+ "token_acc": 0.6557256131292643
51
+ },
52
+ {
53
+ "epoch": 0.02664890073284477,
54
+ "grad_norm": 6.32783528737025,
55
+ "learning_rate": 4.310344827586207e-06,
56
+ "loss": 1.3023101806640625,
57
+ "step": 25,
58
+ "token_acc": 0.6763397175469142
59
+ },
60
+ {
61
+ "epoch": 0.031978680879413725,
62
+ "grad_norm": 6.367128597932351,
63
+ "learning_rate": 4.9999851020489695e-06,
64
+ "loss": 1.2105424880981446,
65
+ "step": 30,
66
+ "token_acc": 0.6806692125841062
67
+ },
68
+ {
69
+ "epoch": 0.037308461025982675,
70
+ "grad_norm": 5.745679317649865,
71
+ "learning_rate": 4.99946369240638e-06,
72
+ "loss": 1.0424203872680664,
73
+ "step": 35,
74
+ "token_acc": 0.720532319391635
75
+ },
76
+ {
77
+ "epoch": 0.04263824117255163,
78
+ "grad_norm": 5.84995920075286,
79
+ "learning_rate": 4.998197562761914e-06,
80
+ "loss": 1.0592132568359376,
81
+ "step": 40,
82
+ "token_acc": 0.7028319235012872
83
+ },
84
+ {
85
+ "epoch": 0.047968021319120584,
86
+ "grad_norm": 6.027890463744797,
87
+ "learning_rate": 4.9961870903613266e-06,
88
+ "loss": 0.9895943641662598,
89
+ "step": 45,
90
+ "token_acc": 0.7256235827664399
91
+ },
92
+ {
93
+ "epoch": 0.05329780146568954,
94
+ "grad_norm": 5.138993659750872,
95
+ "learning_rate": 4.9934328742287285e-06,
96
+ "loss": 1.0118780136108398,
97
+ "step": 50,
98
+ "token_acc": 0.7169505271695052
99
+ },
100
+ {
101
+ "epoch": 0.05862758161225849,
102
+ "grad_norm": 5.517701738242315,
103
+ "learning_rate": 4.989935734988098e-06,
104
+ "loss": 1.1720707893371582,
105
+ "step": 55,
106
+ "token_acc": 0.6896987191051777
107
+ },
108
+ {
109
+ "epoch": 0.06395736175882745,
110
+ "grad_norm": 6.246846876317293,
111
+ "learning_rate": 4.985696714618781e-06,
112
+ "loss": 1.0461352348327637,
113
+ "step": 60,
114
+ "token_acc": 0.7217303822937626
115
+ },
116
+ {
117
+ "epoch": 0.06928714190539641,
118
+ "grad_norm": 5.1838327118545795,
119
+ "learning_rate": 4.98071707614503e-06,
120
+ "loss": 1.0784454345703125,
121
+ "step": 65,
122
+ "token_acc": 0.7065761258041459
123
+ },
124
+ {
125
+ "epoch": 0.07461692205196535,
126
+ "grad_norm": 5.207457333274206,
127
+ "learning_rate": 4.9749983032596775e-06,
128
+ "loss": 1.0711910247802734,
129
+ "step": 70,
130
+ "token_acc": 0.7140947288006112
131
+ },
132
+ {
133
+ "epoch": 0.07994670219853431,
134
+ "grad_norm": 5.076819409823014,
135
+ "learning_rate": 4.968542099882077e-06,
136
+ "loss": 0.9525423049926758,
137
+ "step": 75,
138
+ "token_acc": 0.7458682120626744
139
+ },
140
+ {
141
+ "epoch": 0.08527648234510327,
142
+ "grad_norm": 5.145333113069056,
143
+ "learning_rate": 4.961350389650409e-06,
144
+ "loss": 1.0395957946777343,
145
+ "step": 80,
146
+ "token_acc": 0.7181391712275215
147
+ },
148
+ {
149
+ "epoch": 0.09060626249167222,
150
+ "grad_norm": 5.708204831944594,
151
+ "learning_rate": 4.953425315348534e-06,
152
+ "loss": 1.015221405029297,
153
+ "step": 85,
154
+ "token_acc": 0.7219031993437244
155
+ },
156
+ {
157
+ "epoch": 0.09593604263824117,
158
+ "grad_norm": 5.356494906382105,
159
+ "learning_rate": 4.944769238267542e-06,
160
+ "loss": 1.065409278869629,
161
+ "step": 90,
162
+ "token_acc": 0.7133068878470971
163
+ },
164
+ {
165
+ "epoch": 0.10126582278481013,
166
+ "grad_norm": 5.561086978061129,
167
+ "learning_rate": 4.935384737502204e-06,
168
+ "loss": 0.8904417037963868,
169
+ "step": 95,
170
+ "token_acc": 0.7561363636363636
171
+ },
172
+ {
173
+ "epoch": 0.10659560293137908,
174
+ "grad_norm": 5.007929386757231,
175
+ "learning_rate": 4.925274609182527e-06,
176
+ "loss": 0.9963092803955078,
177
+ "step": 100,
178
+ "token_acc": 0.7157873859579532
179
+ },
180
+ {
181
+ "epoch": 0.11192538307794804,
182
+ "grad_norm": 4.729475065378666,
183
+ "learning_rate": 4.914441865640636e-06,
184
+ "loss": 1.0125768661499024,
185
+ "step": 105,
186
+ "token_acc": 0.7199248120300752
187
+ },
188
+ {
189
+ "epoch": 0.11725516322451698,
190
+ "grad_norm": 5.352763340267538,
191
+ "learning_rate": 4.902889734513251e-06,
192
+ "loss": 0.977642822265625,
193
+ "step": 110,
194
+ "token_acc": 0.7219261890665087
195
+ },
196
+ {
197
+ "epoch": 0.12258494337108594,
198
+ "grad_norm": 5.01951337624599,
199
+ "learning_rate": 4.890621657780002e-06,
200
+ "loss": 0.9350076675415039,
201
+ "step": 115,
202
+ "token_acc": 0.7369072164948454
203
+ },
204
+ {
205
+ "epoch": 0.1279147235176549,
206
+ "grad_norm": 5.682732846054211,
207
+ "learning_rate": 4.8776412907378845e-06,
208
+ "loss": 0.9863363265991211,
209
+ "step": 120,
210
+ "token_acc": 0.7295660948536832
211
+ },
212
+ {
213
+ "epoch": 0.13324450366422386,
214
+ "grad_norm": 5.009947806421316,
215
+ "learning_rate": 4.86395250091216e-06,
216
+ "loss": 0.9168167114257812,
217
+ "step": 125,
218
+ "token_acc": 0.7459949409780776
219
+ },
220
+ {
221
+ "epoch": 0.13857428381079281,
222
+ "grad_norm": 5.16090001119418,
223
+ "learning_rate": 4.849559366904016e-06,
224
+ "loss": 0.9731523513793945,
225
+ "step": 130,
226
+ "token_acc": 0.7264408099688473
227
+ },
228
+ {
229
+ "epoch": 0.14390406395736177,
230
+ "grad_norm": 5.393302939264074,
231
+ "learning_rate": 4.83446617717534e-06,
232
+ "loss": 0.9265727996826172,
233
+ "step": 135,
234
+ "token_acc": 0.7382675211908207
235
+ },
236
+ {
237
+ "epoch": 0.1492338441039307,
238
+ "grad_norm": 5.1348529508995915,
239
+ "learning_rate": 4.818677428770965e-06,
240
+ "loss": 0.9645535469055175,
241
+ "step": 140,
242
+ "token_acc": 0.7365953109072375
243
+ },
244
+ {
245
+ "epoch": 0.15456362425049966,
246
+ "grad_norm": 5.274944058378017,
247
+ "learning_rate": 4.802197825978766e-06,
248
+ "loss": 0.9219735145568848,
249
+ "step": 145,
250
+ "token_acc": 0.7424147311152961
251
+ },
252
+ {
253
+ "epoch": 0.15989340439706862,
254
+ "grad_norm": 4.9265099733335225,
255
+ "learning_rate": 4.785032278928009e-06,
256
+ "loss": 0.9755061149597168,
257
+ "step": 150,
258
+ "token_acc": 0.7261881478584001
259
+ },
260
+ {
261
+ "epoch": 0.16522318454363757,
262
+ "grad_norm": 5.186158859969355,
263
+ "learning_rate": 4.7671859021263635e-06,
264
+ "loss": 0.8955172538757324,
265
+ "step": 155,
266
+ "token_acc": 0.7485970819304153
267
+ },
268
+ {
269
+ "epoch": 0.17055296469020653,
270
+ "grad_norm": 4.8553098725317,
271
+ "learning_rate": 4.748664012936035e-06,
272
+ "loss": 0.9992611885070801,
273
+ "step": 160,
274
+ "token_acc": 0.7210042432814711
275
+ },
276
+ {
277
+ "epoch": 0.1758827448367755,
278
+ "grad_norm": 5.607452928309844,
279
+ "learning_rate": 4.729472129989439e-06,
280
+ "loss": 0.8785256385803223,
281
+ "step": 165,
282
+ "token_acc": 0.7405417024935511
283
+ },
284
+ {
285
+ "epoch": 0.18121252498334445,
286
+ "grad_norm": 5.063309155216159,
287
+ "learning_rate": 4.709615971544912e-06,
288
+ "loss": 0.958376121520996,
289
+ "step": 170,
290
+ "token_acc": 0.7236842105263158
291
+ },
292
+ {
293
+ "epoch": 0.18654230512991338,
294
+ "grad_norm": 4.958090896706627,
295
+ "learning_rate": 4.689101453782954e-06,
296
+ "loss": 0.9511463165283203,
297
+ "step": 175,
298
+ "token_acc": 0.7302402347331745
299
+ },
300
+ {
301
+ "epoch": 0.19187208527648233,
302
+ "grad_norm": 5.554535034316316,
303
+ "learning_rate": 4.6679346890434864e-06,
304
+ "loss": 0.9487571716308594,
305
+ "step": 180,
306
+ "token_acc": 0.7357374546842206
307
+ },
308
+ {
309
+ "epoch": 0.1972018654230513,
310
+ "grad_norm": 5.0455487989596985,
311
+ "learning_rate": 4.646121984004666e-06,
312
+ "loss": 0.9357378005981445,
313
+ "step": 185,
314
+ "token_acc": 0.7466236645837533
315
+ },
316
+ {
317
+ "epoch": 0.20253164556962025,
318
+ "grad_norm": 5.102368295977931,
319
+ "learning_rate": 4.623669837803803e-06,
320
+ "loss": 0.9165685653686524,
321
+ "step": 190,
322
+ "token_acc": 0.7344439983942191
323
+ },
324
+ {
325
+ "epoch": 0.2078614257161892,
326
+ "grad_norm": 6.03242586164789,
327
+ "learning_rate": 4.600584940100929e-06,
328
+ "loss": 0.8400386810302735,
329
+ "step": 195,
330
+ "token_acc": 0.7588924387646432
331
+ },
332
+ {
333
+ "epoch": 0.21319120586275817,
334
+ "grad_norm": 6.046048176929514,
335
+ "learning_rate": 4.576874169085596e-06,
336
+ "loss": 1.0382144927978516,
337
+ "step": 200,
338
+ "token_acc": 0.7164823773324119
339
+ },
340
+ {
341
+ "epoch": 0.21852098600932712,
342
+ "grad_norm": 5.3128952327016306,
343
+ "learning_rate": 4.552544589427514e-06,
344
+ "loss": 0.9587564468383789,
345
+ "step": 205,
346
+ "token_acc": 0.7335751713018944
347
+ },
348
+ {
349
+ "epoch": 0.22385076615589608,
350
+ "grad_norm": 4.856245265355434,
351
+ "learning_rate": 4.527603450171614e-06,
352
+ "loss": 1.0106466293334961,
353
+ "step": 210,
354
+ "token_acc": 0.7285714285714285
355
+ },
356
+ {
357
+ "epoch": 0.229180546302465,
358
+ "grad_norm": 4.364039021197141,
359
+ "learning_rate": 4.502058182578181e-06,
360
+ "loss": 0.8945587158203125,
361
+ "step": 215,
362
+ "token_acc": 0.7414500683994528
363
+ },
364
+ {
365
+ "epoch": 0.23451032644903397,
366
+ "grad_norm": 5.794013669019053,
367
+ "learning_rate": 4.4759163979086985e-06,
368
+ "loss": 0.9250093460083008,
369
+ "step": 220,
370
+ "token_acc": 0.7438412408759124
371
+ },
372
+ {
373
+ "epoch": 0.23984010659560293,
374
+ "grad_norm": 4.9248548258612574,
375
+ "learning_rate": 4.449185885158056e-06,
376
+ "loss": 0.9222723007202148,
377
+ "step": 225,
378
+ "token_acc": 0.7404455344369507
379
+ },
380
+ {
381
+ "epoch": 0.24516988674217188,
382
+ "grad_norm": 5.088119921434173,
383
+ "learning_rate": 4.421874608733806e-06,
384
+ "loss": 0.927369213104248,
385
+ "step": 230,
386
+ "token_acc": 0.7411545623836127
387
+ },
388
+ {
389
+ "epoch": 0.2504996668887408,
390
+ "grad_norm": 5.261396967134003,
391
+ "learning_rate": 4.393990706083149e-06,
392
+ "loss": 0.9975498199462891,
393
+ "step": 235,
394
+ "token_acc": 0.7302452316076294
395
+ },
396
+ {
397
+ "epoch": 0.2558294470353098,
398
+ "grad_norm": 4.270065742658553,
399
+ "learning_rate": 4.3655424852683695e-06,
400
+ "loss": 0.9474044799804687,
401
+ "step": 240,
402
+ "token_acc": 0.7366733466933868
403
+ },
404
+ {
405
+ "epoch": 0.26115922718187873,
406
+ "grad_norm": 4.0368542213252745,
407
+ "learning_rate": 4.336538422491432e-06,
408
+ "loss": 0.9614317893981934,
409
+ "step": 245,
410
+ "token_acc": 0.7291335803776249
411
+ },
412
+ {
413
+ "epoch": 0.2664890073284477,
414
+ "grad_norm": 5.940590055777755,
415
+ "learning_rate": 4.3069871595684795e-06,
416
+ "loss": 0.9075183868408203,
417
+ "step": 250,
418
+ "token_acc": 0.7441300421432872
419
+ },
420
+ {
421
+ "epoch": 0.27181878747501664,
422
+ "grad_norm": 6.020932164981831,
423
+ "learning_rate": 4.276897501354987e-06,
424
+ "loss": 0.9187180519104003,
425
+ "step": 255,
426
+ "token_acc": 0.7450124688279302
427
+ },
428
+ {
429
+ "epoch": 0.27714856762158563,
430
+ "grad_norm": 5.007173976721824,
431
+ "learning_rate": 4.246278413122344e-06,
432
+ "loss": 0.9306771278381347,
433
+ "step": 260,
434
+ "token_acc": 0.7377112881290072
435
+ },
436
+ {
437
+ "epoch": 0.28247834776815456,
438
+ "grad_norm": 5.037382296205618,
439
+ "learning_rate": 4.21513901788662e-06,
440
+ "loss": 0.9223703384399414,
441
+ "step": 265,
442
+ "token_acc": 0.7390941348361512
443
+ },
444
+ {
445
+ "epoch": 0.28780812791472354,
446
+ "grad_norm": 4.579320525829714,
447
+ "learning_rate": 4.183488593690365e-06,
448
+ "loss": 0.8956701278686523,
449
+ "step": 270,
450
+ "token_acc": 0.7352545629202689
451
+ },
452
+ {
453
+ "epoch": 0.2931379080612925,
454
+ "grad_norm": 4.422357549054009,
455
+ "learning_rate": 4.151336570838182e-06,
456
+ "loss": 0.9767134666442872,
457
+ "step": 275,
458
+ "token_acc": 0.729864575908767
459
+ },
460
+ {
461
+ "epoch": 0.2984676882078614,
462
+ "grad_norm": 5.387070334048114,
463
+ "learning_rate": 4.118692529086956e-06,
464
+ "loss": 0.8453518867492675,
465
+ "step": 280,
466
+ "token_acc": 0.7639063153492263
467
+ },
468
+ {
469
+ "epoch": 0.3037974683544304,
470
+ "grad_norm": 5.218152944895714,
471
+ "learning_rate": 4.08556619479155e-06,
472
+ "loss": 0.9285115242004395,
473
+ "step": 285,
474
+ "token_acc": 0.7405669997960432
475
+ },
476
+ {
477
+ "epoch": 0.3091272485009993,
478
+ "grad_norm": 4.473635157614191,
479
+ "learning_rate": 4.051967438006812e-06,
480
+ "loss": 0.9505875587463379,
481
+ "step": 290,
482
+ "token_acc": 0.7344601962922573
483
+ },
484
+ {
485
+ "epoch": 0.3144570286475683,
486
+ "grad_norm": 4.630841152213125,
487
+ "learning_rate": 4.017906269546778e-06,
488
+ "loss": 0.9147586822509766,
489
+ "step": 295,
490
+ "token_acc": 0.7461659457333858
491
+ },
492
+ {
493
+ "epoch": 0.31978680879413723,
494
+ "grad_norm": 4.4381854725202805,
495
+ "learning_rate": 3.983392838001932e-06,
496
+ "loss": 0.8980813980102539,
497
+ "step": 300,
498
+ "token_acc": 0.7419038272816487
499
+ },
500
+ {
501
+ "epoch": 0.3251165889407062,
502
+ "grad_norm": 4.3925972764182735,
503
+ "learning_rate": 3.948437426715409e-06,
504
+ "loss": 0.9489370346069336,
505
+ "step": 305,
506
+ "token_acc": 0.7271723122238586
507
+ },
508
+ {
509
+ "epoch": 0.33044636908727515,
510
+ "grad_norm": 4.777819792705776,
511
+ "learning_rate": 3.913050450719057e-06,
512
+ "loss": 0.9575244903564453,
513
+ "step": 310,
514
+ "token_acc": 0.7353364519611371
515
+ },
516
+ {
517
+ "epoch": 0.3357761492338441,
518
+ "grad_norm": 4.690307974879278,
519
+ "learning_rate": 3.8772424536302565e-06,
520
+ "loss": 0.8590595245361328,
521
+ "step": 315,
522
+ "token_acc": 0.7531313131313131
523
+ },
524
+ {
525
+ "epoch": 0.34110592938041306,
526
+ "grad_norm": 5.548729734061873,
527
+ "learning_rate": 3.841024104510431e-06,
528
+ "loss": 0.78990797996521,
529
+ "step": 320,
530
+ "token_acc": 0.7674789341835573
531
+ },
532
+ {
533
+ "epoch": 0.346435709526982,
534
+ "grad_norm": 4.989871534387572,
535
+ "learning_rate": 3.8044061946861795e-06,
536
+ "loss": 0.9506110191345215,
537
+ "step": 325,
538
+ "token_acc": 0.7373412059402398
539
+ },
540
+ {
541
+ "epoch": 0.351765489673551,
542
+ "grad_norm": 4.676259945487118,
543
+ "learning_rate": 3.767399634533976e-06,
544
+ "loss": 0.9495532035827636,
545
+ "step": 330,
546
+ "token_acc": 0.7358214416392242
547
+ },
548
+ {
549
+ "epoch": 0.3570952698201199,
550
+ "grad_norm": 4.980936255741834,
551
+ "learning_rate": 3.7300154502294093e-06,
552
+ "loss": 0.9292638778686524,
553
+ "step": 335,
554
+ "token_acc": 0.7407978415879746
555
+ },
556
+ {
557
+ "epoch": 0.3624250499666889,
558
+ "grad_norm": 4.965729215770431,
559
+ "learning_rate": 3.6922647804619073e-06,
560
+ "loss": 0.9855228424072265,
561
+ "step": 340,
562
+ "token_acc": 0.7225995961079493
563
+ },
564
+ {
565
+ "epoch": 0.3677548301132578,
566
+ "grad_norm": 4.936075061330924,
567
+ "learning_rate": 3.654158873115944e-06,
568
+ "loss": 0.9076862335205078,
569
+ "step": 345,
570
+ "token_acc": 0.7436141822340832
571
+ },
572
+ {
573
+ "epoch": 0.37308461025982675,
574
+ "grad_norm": 5.231662158108306,
575
+ "learning_rate": 3.61570908191971e-06,
576
+ "loss": 0.8928030014038086,
577
+ "step": 350,
578
+ "token_acc": 0.7541051756391602
579
+ },
580
+ {
581
+ "epoch": 0.37841439040639574,
582
+ "grad_norm": 4.522556964501456,
583
+ "learning_rate": 3.5769268630622533e-06,
584
+ "loss": 0.9126054763793945,
585
+ "step": 355,
586
+ "token_acc": 0.7474881516587678
587
+ },
588
+ {
589
+ "epoch": 0.38374417055296467,
590
+ "grad_norm": 5.1995597965754685,
591
+ "learning_rate": 3.537823771780077e-06,
592
+ "loss": 0.8765750885009765,
593
+ "step": 360,
594
+ "token_acc": 0.7457895779671092
595
+ },
596
+ {
597
+ "epoch": 0.38907395069953365,
598
+ "grad_norm": 5.281242833316695,
599
+ "learning_rate": 3.4984114589142388e-06,
600
+ "loss": 0.9568130493164062,
601
+ "step": 365,
602
+ "token_acc": 0.737781383086595
603
+ },
604
+ {
605
+ "epoch": 0.3944037308461026,
606
+ "grad_norm": 4.5694389026717435,
607
+ "learning_rate": 3.458701667438965e-06,
608
+ "loss": 0.8665159225463868,
609
+ "step": 370,
610
+ "token_acc": 0.7548999797938978
611
+ },
612
+ {
613
+ "epoch": 0.39973351099267157,
614
+ "grad_norm": 4.332384453495391,
615
+ "learning_rate": 3.4187062289627983e-06,
616
+ "loss": 0.882652759552002,
617
+ "step": 375,
618
+ "token_acc": 0.7516012810248198
619
+ },
620
+ {
621
+ "epoch": 0.4050632911392405,
622
+ "grad_norm": 5.463888132443461,
623
+ "learning_rate": 3.3784370602033572e-06,
624
+ "loss": 0.7812636852264404,
625
+ "step": 380,
626
+ "token_acc": 0.769391062746006
627
+ },
628
+ {
629
+ "epoch": 0.4103930712858095,
630
+ "grad_norm": 4.6396298492906505,
631
+ "learning_rate": 3.337906159436721e-06,
632
+ "loss": 0.891010856628418,
633
+ "step": 385,
634
+ "token_acc": 0.752018908804412
635
+ },
636
+ {
637
+ "epoch": 0.4157228514323784,
638
+ "grad_norm": 5.11189175613832,
639
+ "learning_rate": 3.2971256029225253e-06,
640
+ "loss": 0.8738397598266602,
641
+ "step": 390,
642
+ "token_acc": 0.7532467532467533
643
+ },
644
+ {
645
+ "epoch": 0.42105263157894735,
646
+ "grad_norm": 4.9436874254737075,
647
+ "learning_rate": 3.2561075413058113e-06,
648
+ "loss": 0.8521583557128907,
649
+ "step": 395,
650
+ "token_acc": 0.7503179313268334
651
+ },
652
+ {
653
+ "epoch": 0.42638241172551633,
654
+ "grad_norm": 4.666360407842893,
655
+ "learning_rate": 3.214864195996723e-06,
656
+ "loss": 0.9074520111083985,
657
+ "step": 400,
658
+ "token_acc": 0.7434575733544806
659
+ },
660
+ {
661
+ "epoch": 0.43171219187208526,
662
+ "grad_norm": 4.750112035885002,
663
+ "learning_rate": 3.1734078555291137e-06,
664
+ "loss": 0.9123194694519043,
665
+ "step": 405,
666
+ "token_acc": 0.7403057419835943
667
+ },
668
+ {
669
+ "epoch": 0.43704197201865425,
670
+ "grad_norm": 4.771140489181497,
671
+ "learning_rate": 3.1317508718991496e-06,
672
+ "loss": 0.8552797317504883,
673
+ "step": 410,
674
+ "token_acc": 0.7574031890660592
675
+ },
676
+ {
677
+ "epoch": 0.4423717521652232,
678
+ "grad_norm": 4.692545746773149,
679
+ "learning_rate": 3.0899056568850148e-06,
680
+ "loss": 0.9358634948730469,
681
+ "step": 415,
682
+ "token_acc": 0.7455585052072697
683
+ },
684
+ {
685
+ "epoch": 0.44770153231179216,
686
+ "grad_norm": 5.0036012753115235,
687
+ "learning_rate": 3.047884678348795e-06,
688
+ "loss": 0.9225390434265137,
689
+ "step": 420,
690
+ "token_acc": 0.739247795573151
691
+ },
692
+ {
693
+ "epoch": 0.4530313124583611,
694
+ "grad_norm": 4.741320422434045,
695
+ "learning_rate": 3.0057004565216523e-06,
696
+ "loss": 0.8901847839355469,
697
+ "step": 425,
698
+ "token_acc": 0.7495299770210988
699
+ },
700
+ {
701
+ "epoch": 0.45836109260493,
702
+ "grad_norm": 4.703918003843587,
703
+ "learning_rate": 2.9633655602734035e-06,
704
+ "loss": 0.9226030349731446,
705
+ "step": 430,
706
+ "token_acc": 0.7433257055682685
707
+ },
708
+ {
709
+ "epoch": 0.463690872751499,
710
+ "grad_norm": 5.477224800396244,
711
+ "learning_rate": 2.920892603367596e-06,
712
+ "loss": 0.8314413070678711,
713
+ "step": 435,
714
+ "token_acc": 0.7559628975265018
715
+ },
716
+ {
717
+ "epoch": 0.46902065289806794,
718
+ "grad_norm": 4.8329386010913264,
719
+ "learning_rate": 2.8782942407032177e-06,
720
+ "loss": 0.8740703582763671,
721
+ "step": 440,
722
+ "token_acc": 0.7501027538018906
723
+ },
724
+ {
725
+ "epoch": 0.4743504330446369,
726
+ "grad_norm": 5.087948549401884,
727
+ "learning_rate": 2.835583164544139e-06,
728
+ "loss": 0.8511223793029785,
729
+ "step": 445,
730
+ "token_acc": 0.7644836272040302
731
+ },
732
+ {
733
+ "epoch": 0.47968021319120585,
734
+ "grad_norm": 4.99727487177206,
735
+ "learning_rate": 2.7927721007374347e-06,
736
+ "loss": 0.815243911743164,
737
+ "step": 450,
738
+ "token_acc": 0.766592647421663
739
+ },
740
+ {
741
+ "epoch": 0.48500999333777484,
742
+ "grad_norm": 5.576288110570715,
743
+ "learning_rate": 2.7498738049216904e-06,
744
+ "loss": 0.9731996536254883,
745
+ "step": 455,
746
+ "token_acc": 0.7280547752808989
747
+ },
748
+ {
749
+ "epoch": 0.49033977348434377,
750
+ "grad_norm": 4.652800298925416,
751
+ "learning_rate": 2.706901058726437e-06,
752
+ "loss": 0.8669706344604492,
753
+ "step": 460,
754
+ "token_acc": 0.7513238289205703
755
+ },
756
+ {
757
+ "epoch": 0.49566955363091275,
758
+ "grad_norm": 4.67527794119894,
759
+ "learning_rate": 2.6638666659638372e-06,
760
+ "loss": 0.8978883743286132,
761
+ "step": 465,
762
+ "token_acc": 0.7504095004095004
763
+ },
764
+ {
765
+ "epoch": 0.5009993337774816,
766
+ "grad_norm": 4.500058654431643,
767
+ "learning_rate": 2.620783448813768e-06,
768
+ "loss": 0.803309440612793,
769
+ "step": 470,
770
+ "token_acc": 0.7682926829268293
771
+ },
772
+ {
773
+ "epoch": 0.5063291139240507,
774
+ "grad_norm": 5.549718692193634,
775
+ "learning_rate": 2.577664244003426e-06,
776
+ "loss": 0.8737884521484375,
777
+ "step": 475,
778
+ "token_acc": 0.7512740101920815
779
+ },
780
+ {
781
+ "epoch": 0.5116588940706196,
782
+ "grad_norm": 4.633775513369992,
783
+ "learning_rate": 2.5345218989825985e-06,
784
+ "loss": 0.8945508003234863,
785
+ "step": 480,
786
+ "token_acc": 0.7538946953263657
787
+ },
788
+ {
789
+ "epoch": 0.5169886742171885,
790
+ "grad_norm": 4.457350960855039,
791
+ "learning_rate": 2.4913692680957472e-06,
792
+ "loss": 0.8398324012756347,
793
+ "step": 485,
794
+ "token_acc": 0.763268931823229
795
+ },
796
+ {
797
+ "epoch": 0.5223184543637575,
798
+ "grad_norm": 4.9918603168538365,
799
+ "learning_rate": 2.4482192087520225e-06,
800
+ "loss": 0.8864654541015625,
801
+ "step": 490,
802
+ "token_acc": 0.7518545994065282
803
+ },
804
+ {
805
+ "epoch": 0.5276482345103265,
806
+ "grad_norm": 4.279486984922963,
807
+ "learning_rate": 2.4050845775943816e-06,
808
+ "loss": 0.951543140411377,
809
+ "step": 495,
810
+ "token_acc": 0.7330591811192562
811
+ },
812
+ {
813
+ "epoch": 0.5329780146568954,
814
+ "grad_norm": 4.9236086215774115,
815
+ "learning_rate": 2.361978226668922e-06,
816
+ "loss": 0.9079221725463867,
817
+ "step": 500,
818
+ "token_acc": 0.7499020759890325
819
+ },
820
+ {
821
+ "epoch": 0.5383077948034644,
822
+ "grad_norm": 5.043401669503223,
823
+ "learning_rate": 2.3e-06,
824
+ "loss": 0.9313335418701172,
825
+ "step": 505,
826
+ "token_acc": 0.7324805339265851
827
+ },
828
+ {
829
+ "epoch": 0.5436375749500333,
830
+ "grad_norm": 4.437011955068131,
831
+ "learning_rate": 2.3e-06,
832
+ "loss": 0.8004268646240235,
833
+ "step": 510,
834
+ "token_acc": 0.769280205655527
835
+ },
836
+ {
837
+ "epoch": 0.5489673550966022,
838
+ "grad_norm": 4.9461921832529905,
839
+ "learning_rate": 2.3e-06,
840
+ "loss": 0.843082332611084,
841
+ "step": 515,
842
+ "token_acc": 0.7563573136274723
843
+ },
844
+ {
845
+ "epoch": 0.5542971352431713,
846
+ "grad_norm": 4.791111901160093,
847
+ "learning_rate": 2.3e-06,
848
+ "loss": 0.8652103424072266,
849
+ "step": 520,
850
+ "token_acc": 0.7534468775344688
851
+ },
852
+ {
853
+ "epoch": 0.5596269153897402,
854
+ "grad_norm": 4.694299929140503,
855
+ "learning_rate": 2.3e-06,
856
+ "loss": 0.9284069061279296,
857
+ "step": 525,
858
+ "token_acc": 0.7399468556244464
859
+ },
860
+ {
861
+ "epoch": 0.5649566955363091,
862
+ "grad_norm": 4.590405768531116,
863
+ "learning_rate": 2.3e-06,
864
+ "loss": 0.8198009490966797,
865
+ "step": 530,
866
+ "token_acc": 0.7667011375387798
867
+ },
868
+ {
869
+ "epoch": 0.570286475682878,
870
+ "grad_norm": 5.139293375181794,
871
+ "learning_rate": 2.3e-06,
872
+ "loss": 0.9579063415527344,
873
+ "step": 535,
874
+ "token_acc": 0.7357558652319633
875
+ },
876
+ {
877
+ "epoch": 0.5756162558294471,
878
+ "grad_norm": 4.634359261863655,
879
+ "learning_rate": 2.3e-06,
880
+ "loss": 0.8792430877685546,
881
+ "step": 540,
882
+ "token_acc": 0.7548282171173003
883
+ },
884
+ {
885
+ "epoch": 0.580946035976016,
886
+ "grad_norm": 4.447120583644974,
887
+ "learning_rate": 2.3e-06,
888
+ "loss": 0.8046426773071289,
889
+ "step": 545,
890
+ "token_acc": 0.7633396107972379
891
+ },
892
+ {
893
+ "epoch": 0.586275816122585,
894
+ "grad_norm": 4.8496735934946855,
895
+ "learning_rate": 2.3e-06,
896
+ "loss": 0.8646127700805664,
897
+ "step": 550,
898
+ "token_acc": 0.7555690562980963
899
+ },
900
+ {
901
+ "epoch": 0.5916055962691539,
902
+ "grad_norm": 5.354316180442001,
903
+ "learning_rate": 2.3e-06,
904
+ "loss": 0.7959212303161621,
905
+ "step": 555,
906
+ "token_acc": 0.774977497749775
907
+ },
908
+ {
909
+ "epoch": 0.5969353764157228,
910
+ "grad_norm": 4.713142485275984,
911
+ "learning_rate": 2.3e-06,
912
+ "loss": 0.8876336097717286,
913
+ "step": 560,
914
+ "token_acc": 0.7479958890030832
915
+ },
916
+ {
917
+ "epoch": 0.6022651565622918,
918
+ "grad_norm": 4.497831071746374,
919
+ "learning_rate": 2.3e-06,
920
+ "loss": 0.7969367980957032,
921
+ "step": 565,
922
+ "token_acc": 0.7759058389106854
923
+ },
924
+ {
925
+ "epoch": 0.6075949367088608,
926
+ "grad_norm": 5.074530731396222,
927
+ "learning_rate": 2.3e-06,
928
+ "loss": 0.8135330200195312,
929
+ "step": 570,
930
+ "token_acc": 0.7633975852573607
931
+ },
932
+ {
933
+ "epoch": 0.6129247168554297,
934
+ "grad_norm": 5.439750380693716,
935
+ "learning_rate": 2.3e-06,
936
+ "loss": 0.8008811950683594,
937
+ "step": 575,
938
+ "token_acc": 0.7757837837837838
939
+ },
940
+ {
941
+ "epoch": 0.6182544970019986,
942
+ "grad_norm": 4.828635110227898,
943
+ "learning_rate": 2.3e-06,
944
+ "loss": 0.8349386215209961,
945
+ "step": 580,
946
+ "token_acc": 0.7681311751103637
947
+ },
948
+ {
949
+ "epoch": 0.6235842771485676,
950
+ "grad_norm": 4.665942163731842,
951
+ "learning_rate": 2.3e-06,
952
+ "loss": 0.8878559112548828,
953
+ "step": 585,
954
+ "token_acc": 0.7523170972194834
955
+ },
956
+ {
957
+ "epoch": 0.6289140572951366,
958
+ "grad_norm": 4.972690493936675,
959
+ "learning_rate": 2.3e-06,
960
+ "loss": 0.8758079528808593,
961
+ "step": 590,
962
+ "token_acc": 0.7523239000206569
963
+ },
964
+ {
965
+ "epoch": 0.6342438374417055,
966
+ "grad_norm": 5.350060088758041,
967
+ "learning_rate": 2.3e-06,
968
+ "loss": 0.8282616615295411,
969
+ "step": 595,
970
+ "token_acc": 0.7597730138713745
971
+ },
972
+ {
973
+ "epoch": 0.6395736175882745,
974
+ "grad_norm": 4.675665480589392,
975
+ "learning_rate": 2.3e-06,
976
+ "loss": 0.818998146057129,
977
+ "step": 600,
978
+ "token_acc": 0.7656360632523012
979
+ },
980
+ {
981
+ "epoch": 0.6449033977348434,
982
+ "grad_norm": 4.447533140940443,
983
+ "learning_rate": 2.3e-06,
984
+ "loss": 0.8747160911560059,
985
+ "step": 605,
986
+ "token_acc": 0.7465790914066777
987
+ },
988
+ {
989
+ "epoch": 0.6502331778814124,
990
+ "grad_norm": 5.130789428783895,
991
+ "learning_rate": 2.3e-06,
992
+ "loss": 0.8581184387207031,
993
+ "step": 610,
994
+ "token_acc": 0.7551923076923077
995
+ },
996
+ {
997
+ "epoch": 0.6555629580279814,
998
+ "grad_norm": 5.216571173791328,
999
+ "learning_rate": 2.3e-06,
1000
+ "loss": 0.8216348648071289,
1001
+ "step": 615,
1002
+ "token_acc": 0.7595803896381931
1003
+ },
1004
+ {
1005
+ "epoch": 0.6608927381745503,
1006
+ "grad_norm": 4.541713854990473,
1007
+ "learning_rate": 2.3e-06,
1008
+ "loss": 0.8405349731445313,
1009
+ "step": 620,
1010
+ "token_acc": 0.7559499798305769
1011
+ },
1012
+ {
1013
+ "epoch": 0.6662225183211192,
1014
+ "grad_norm": 5.23891265693261,
1015
+ "learning_rate": 2.3e-06,
1016
+ "loss": 0.9148238182067872,
1017
+ "step": 625,
1018
+ "token_acc": 0.7366863905325444
1019
+ },
1020
+ {
1021
+ "epoch": 0.6715522984676882,
1022
+ "grad_norm": 5.162967835973132,
1023
+ "learning_rate": 2.3e-06,
1024
+ "loss": 0.9344933509826661,
1025
+ "step": 630,
1026
+ "token_acc": 0.7420375865479722
1027
+ },
1028
+ {
1029
+ "epoch": 0.6768820786142572,
1030
+ "grad_norm": 4.883300468904484,
1031
+ "learning_rate": 2.3e-06,
1032
+ "loss": 0.8580543518066406,
1033
+ "step": 635,
1034
+ "token_acc": 0.7618649383232281
1035
+ },
1036
+ {
1037
+ "epoch": 0.6822118587608261,
1038
+ "grad_norm": 5.135683049076609,
1039
+ "learning_rate": 2.3e-06,
1040
+ "loss": 0.7567629814147949,
1041
+ "step": 640,
1042
+ "token_acc": 0.7874684415882488
1043
+ },
1044
+ {
1045
+ "epoch": 0.6875416389073951,
1046
+ "grad_norm": 4.69251131886331,
1047
+ "learning_rate": 2.3e-06,
1048
+ "loss": 0.8729320526123047,
1049
+ "step": 645,
1050
+ "token_acc": 0.7532595811932042
1051
+ },
1052
+ {
1053
+ "epoch": 0.692871419053964,
1054
+ "grad_norm": 4.537917652494429,
1055
+ "learning_rate": 2.3e-06,
1056
+ "loss": 0.7952337265014648,
1057
+ "step": 650,
1058
+ "token_acc": 0.7685081637217624
1059
+ },
1060
+ {
1061
+ "epoch": 0.698201199200533,
1062
+ "grad_norm": 4.589779554748045,
1063
+ "learning_rate": 2.3e-06,
1064
+ "loss": 0.8533817291259765,
1065
+ "step": 655,
1066
+ "token_acc": 0.7492307692307693
1067
+ },
1068
+ {
1069
+ "epoch": 0.703530979347102,
1070
+ "grad_norm": 5.241045198399743,
1071
+ "learning_rate": 2.3e-06,
1072
+ "loss": 0.8691547393798829,
1073
+ "step": 660,
1074
+ "token_acc": 0.7476708074534162
1075
+ },
1076
+ {
1077
+ "epoch": 0.7088607594936709,
1078
+ "grad_norm": 4.4294360348908475,
1079
+ "learning_rate": 2.3e-06,
1080
+ "loss": 0.8178191184997559,
1081
+ "step": 665,
1082
+ "token_acc": 0.7612659819744289
1083
+ },
1084
+ {
1085
+ "epoch": 0.7141905396402398,
1086
+ "grad_norm": 5.0125004541858695,
1087
+ "learning_rate": 2.3e-06,
1088
+ "loss": 0.8978594779968262,
1089
+ "step": 670,
1090
+ "token_acc": 0.7502776749352091
1091
+ },
1092
+ {
1093
+ "epoch": 0.7195203197868087,
1094
+ "grad_norm": 4.89456621393514,
1095
+ "learning_rate": 2.3e-06,
1096
+ "loss": 0.8966169357299805,
1097
+ "step": 675,
1098
+ "token_acc": 0.7424985291233576
1099
+ },
1100
+ {
1101
+ "epoch": 0.7248500999333778,
1102
+ "grad_norm": 4.723699518324189,
1103
+ "learning_rate": 2.3e-06,
1104
+ "loss": 0.8785926818847656,
1105
+ "step": 680,
1106
+ "token_acc": 0.7525147086733726
1107
+ },
1108
+ {
1109
+ "epoch": 0.7301798800799467,
1110
+ "grad_norm": 4.749141256391105,
1111
+ "learning_rate": 2.3e-06,
1112
+ "loss": 0.8269707679748535,
1113
+ "step": 685,
1114
+ "token_acc": 0.7698035160289556
1115
+ },
1116
+ {
1117
+ "epoch": 0.7355096602265156,
1118
+ "grad_norm": 4.357558582129155,
1119
+ "learning_rate": 2.3e-06,
1120
+ "loss": 0.7781161308288574,
1121
+ "step": 690,
1122
+ "token_acc": 0.7590879759087976
1123
+ },
1124
+ {
1125
+ "epoch": 0.7408394403730846,
1126
+ "grad_norm": 4.715021183358473,
1127
+ "learning_rate": 2.3e-06,
1128
+ "loss": 0.8154525756835938,
1129
+ "step": 695,
1130
+ "token_acc": 0.7670259114881908
1131
+ },
1132
+ {
1133
+ "epoch": 0.7461692205196535,
1134
+ "grad_norm": 4.845394913724092,
1135
+ "learning_rate": 2.3e-06,
1136
+ "loss": 0.9302475929260254,
1137
+ "step": 700,
1138
+ "token_acc": 0.7333573876961934
1139
+ },
1140
+ {
1141
+ "epoch": 0.7514990006662225,
1142
+ "grad_norm": 4.458085929920139,
1143
+ "learning_rate": 2.3e-06,
1144
+ "loss": 0.8405391693115234,
1145
+ "step": 705,
1146
+ "token_acc": 0.7585416666666667
1147
+ },
1148
+ {
1149
+ "epoch": 0.7568287808127915,
1150
+ "grad_norm": 5.104919361304955,
1151
+ "learning_rate": 2.3e-06,
1152
+ "loss": 0.8558987617492676,
1153
+ "step": 710,
1154
+ "token_acc": 0.7531428571428571
1155
+ },
1156
+ {
1157
+ "epoch": 0.7621585609593604,
1158
+ "grad_norm": 4.50702112491344,
1159
+ "learning_rate": 2.3e-06,
1160
+ "loss": 0.8234317779541016,
1161
+ "step": 715,
1162
+ "token_acc": 0.7599072105161415
1163
+ },
1164
+ {
1165
+ "epoch": 0.7674883411059293,
1166
+ "grad_norm": 4.613405541301498,
1167
+ "learning_rate": 2.3e-06,
1168
+ "loss": 0.9495395660400391,
1169
+ "step": 720,
1170
+ "token_acc": 0.7383750638732755
1171
+ },
1172
+ {
1173
+ "epoch": 0.7728181212524984,
1174
+ "grad_norm": 5.0274346973418345,
1175
+ "learning_rate": 2.3e-06,
1176
+ "loss": 0.8480627059936523,
1177
+ "step": 725,
1178
+ "token_acc": 0.7663193706145014
1179
+ },
1180
+ {
1181
+ "epoch": 0.7781479013990673,
1182
+ "grad_norm": 4.868595479556196,
1183
+ "learning_rate": 2.3e-06,
1184
+ "loss": 0.8753684997558594,
1185
+ "step": 730,
1186
+ "token_acc": 0.74125
1187
+ },
1188
+ {
1189
+ "epoch": 0.7834776815456362,
1190
+ "grad_norm": 4.564850676362406,
1191
+ "learning_rate": 2.3e-06,
1192
+ "loss": 0.843782615661621,
1193
+ "step": 735,
1194
+ "token_acc": 0.765643924101736
1195
+ },
1196
+ {
1197
+ "epoch": 0.7888074616922052,
1198
+ "grad_norm": 5.05324907708148,
1199
+ "learning_rate": 2.3e-06,
1200
+ "loss": 0.8115653991699219,
1201
+ "step": 740,
1202
+ "token_acc": 0.7754152823920266
1203
+ },
1204
+ {
1205
+ "epoch": 0.7941372418387741,
1206
+ "grad_norm": 5.480865823369537,
1207
+ "learning_rate": 2.3e-06,
1208
+ "loss": 0.8137409210205078,
1209
+ "step": 745,
1210
+ "token_acc": 0.7597292724196277
1211
+ },
1212
+ {
1213
+ "epoch": 0.7994670219853431,
1214
+ "grad_norm": 5.369323266878849,
1215
+ "learning_rate": 2.3e-06,
1216
+ "loss": 0.8155117034912109,
1217
+ "step": 750,
1218
+ "token_acc": 0.7665171288743883
1219
+ },
1220
+ {
1221
+ "epoch": 0.8047968021319121,
1222
+ "grad_norm": 4.853665943115109,
1223
+ "learning_rate": 2.3e-06,
1224
+ "loss": 0.8802165985107422,
1225
+ "step": 755,
1226
+ "token_acc": 0.7480860371855632
1227
+ },
1228
+ {
1229
+ "epoch": 0.810126582278481,
1230
+ "grad_norm": 4.808224943607436,
1231
+ "learning_rate": 2.3e-06,
1232
+ "loss": 0.82237548828125,
1233
+ "step": 760,
1234
+ "token_acc": 0.764473957252542
1235
+ },
1236
+ {
1237
+ "epoch": 0.8154563624250499,
1238
+ "grad_norm": 4.622557273028215,
1239
+ "learning_rate": 2.3e-06,
1240
+ "loss": 0.8893803596496582,
1241
+ "step": 765,
1242
+ "token_acc": 0.7448350851757883
1243
+ },
1244
+ {
1245
+ "epoch": 0.820786142571619,
1246
+ "grad_norm": 4.769533656387771,
1247
+ "learning_rate": 2.3e-06,
1248
+ "loss": 0.8182163238525391,
1249
+ "step": 770,
1250
+ "token_acc": 0.7690664387951293
1251
+ },
1252
+ {
1253
+ "epoch": 0.8261159227181879,
1254
+ "grad_norm": 4.781990293335522,
1255
+ "learning_rate": 2.3e-06,
1256
+ "loss": 0.8312844276428223,
1257
+ "step": 775,
1258
+ "token_acc": 0.761876127480457
1259
+ },
1260
+ {
1261
+ "epoch": 0.8314457028647568,
1262
+ "grad_norm": 4.988959771776016,
1263
+ "learning_rate": 2.3e-06,
1264
+ "loss": 0.814521312713623,
1265
+ "step": 780,
1266
+ "token_acc": 0.7755408010280574
1267
+ },
1268
+ {
1269
+ "epoch": 0.8367754830113258,
1270
+ "grad_norm": 4.087547272283349,
1271
+ "learning_rate": 2.3e-06,
1272
+ "loss": 0.8847762107849121,
1273
+ "step": 785,
1274
+ "token_acc": 0.7430968192939532
1275
+ },
1276
+ {
1277
+ "epoch": 0.8421052631578947,
1278
+ "grad_norm": 4.599551127627647,
1279
+ "learning_rate": 2.3e-06,
1280
+ "loss": 0.6787426471710205,
1281
+ "step": 790,
1282
+ "token_acc": 0.7971876690102758
1283
+ },
1284
+ {
1285
+ "epoch": 0.8474350433044637,
1286
+ "grad_norm": 4.776471715784441,
1287
+ "learning_rate": 2.3e-06,
1288
+ "loss": 0.8404502868652344,
1289
+ "step": 795,
1290
+ "token_acc": 0.7615946319321097
1291
+ },
1292
+ {
1293
+ "epoch": 0.8527648234510327,
1294
+ "grad_norm": 4.77324194182284,
1295
+ "learning_rate": 2.3e-06,
1296
+ "loss": 0.8979682922363281,
1297
+ "step": 800,
1298
+ "token_acc": 0.7428789906327662
1299
+ },
1300
+ {
1301
+ "epoch": 0.8580946035976016,
1302
+ "grad_norm": 4.186841899763308,
1303
+ "learning_rate": 2.3e-06,
1304
+ "loss": 0.8490333557128906,
1305
+ "step": 805,
1306
+ "token_acc": 0.7513409961685824
1307
+ },
1308
+ {
1309
+ "epoch": 0.8634243837441705,
1310
+ "grad_norm": 5.00996163860295,
1311
+ "learning_rate": 2.3e-06,
1312
+ "loss": 0.8072927474975586,
1313
+ "step": 810,
1314
+ "token_acc": 0.7662141779788839
1315
+ },
1316
+ {
1317
+ "epoch": 0.8687541638907396,
1318
+ "grad_norm": 4.818424223620723,
1319
+ "learning_rate": 2.3e-06,
1320
+ "loss": 0.7880621910095215,
1321
+ "step": 815,
1322
+ "token_acc": 0.7660944206008584
1323
+ },
1324
+ {
1325
+ "epoch": 0.8740839440373085,
1326
+ "grad_norm": 4.6356713282207975,
1327
+ "learning_rate": 2.3e-06,
1328
+ "loss": 0.8073809623718262,
1329
+ "step": 820,
1330
+ "token_acc": 0.7698314837648993
1331
+ },
1332
+ {
1333
+ "epoch": 0.8794137241838774,
1334
+ "grad_norm": 5.03662108299368,
1335
+ "learning_rate": 2.3e-06,
1336
+ "loss": 0.7883618354797364,
1337
+ "step": 825,
1338
+ "token_acc": 0.7801530153015301
1339
+ },
1340
+ {
1341
+ "epoch": 0.8847435043304464,
1342
+ "grad_norm": 4.494987433874659,
1343
+ "learning_rate": 2.3e-06,
1344
+ "loss": 0.8354556083679199,
1345
+ "step": 830,
1346
+ "token_acc": 0.7542094058447842
1347
+ },
1348
+ {
1349
+ "epoch": 0.8900732844770153,
1350
+ "grad_norm": 4.571643128763884,
1351
+ "learning_rate": 2.3e-06,
1352
+ "loss": 0.7755649089813232,
1353
+ "step": 835,
1354
+ "token_acc": 0.7809482943574341
1355
+ },
1356
+ {
1357
+ "epoch": 0.8954030646235843,
1358
+ "grad_norm": 4.515732991917952,
1359
+ "learning_rate": 2.3e-06,
1360
+ "loss": 0.8827999114990235,
1361
+ "step": 840,
1362
+ "token_acc": 0.7483820356932732
1363
+ },
1364
+ {
1365
+ "epoch": 0.9007328447701533,
1366
+ "grad_norm": 4.965366676519157,
1367
+ "learning_rate": 2.3e-06,
1368
+ "loss": 0.8320845603942871,
1369
+ "step": 845,
1370
+ "token_acc": 0.7568418980114195
1371
+ },
1372
+ {
1373
+ "epoch": 0.9060626249167222,
1374
+ "grad_norm": 5.153213542890202,
1375
+ "learning_rate": 2.3e-06,
1376
+ "loss": 0.8549650192260743,
1377
+ "step": 850,
1378
+ "token_acc": 0.7493156042236997
1379
+ },
1380
+ {
1381
+ "epoch": 0.9113924050632911,
1382
+ "grad_norm": 4.685348919973664,
1383
+ "learning_rate": 2.3e-06,
1384
+ "loss": 0.8040557861328125,
1385
+ "step": 855,
1386
+ "token_acc": 0.7747043918918919
1387
+ },
1388
+ {
1389
+ "epoch": 0.91672218520986,
1390
+ "grad_norm": 5.631387602760864,
1391
+ "learning_rate": 2.3e-06,
1392
+ "loss": 0.7609379768371582,
1393
+ "step": 860,
1394
+ "token_acc": 0.7761161681837885
1395
+ },
1396
+ {
1397
+ "epoch": 0.9220519653564291,
1398
+ "grad_norm": 4.29732725735809,
1399
+ "learning_rate": 2.3e-06,
1400
+ "loss": 0.8553963661193847,
1401
+ "step": 865,
1402
+ "token_acc": 0.7378821774794929
1403
+ },
1404
+ {
1405
+ "epoch": 0.927381745502998,
1406
+ "grad_norm": 4.4689622483360365,
1407
+ "learning_rate": 2.3e-06,
1408
+ "loss": 0.8411100387573243,
1409
+ "step": 870,
1410
+ "token_acc": 0.758266584514274
1411
+ },
1412
+ {
1413
+ "epoch": 0.9327115256495669,
1414
+ "grad_norm": 4.271516958949675,
1415
+ "learning_rate": 2.3e-06,
1416
+ "loss": 0.8458847045898438,
1417
+ "step": 875,
1418
+ "token_acc": 0.7636141138078727
1419
+ },
1420
+ {
1421
+ "epoch": 0.9380413057961359,
1422
+ "grad_norm": 5.280065922587605,
1423
+ "learning_rate": 2.3e-06,
1424
+ "loss": 0.7837121963500977,
1425
+ "step": 880,
1426
+ "token_acc": 0.7722984562607204
1427
+ },
1428
+ {
1429
+ "epoch": 0.9433710859427049,
1430
+ "grad_norm": 4.490709801842713,
1431
+ "learning_rate": 2.3e-06,
1432
+ "loss": 0.9280232429504395,
1433
+ "step": 885,
1434
+ "token_acc": 0.7421804375338998
1435
+ },
1436
+ {
1437
+ "epoch": 0.9487008660892738,
1438
+ "grad_norm": 5.2839081660696054,
1439
+ "learning_rate": 2.3e-06,
1440
+ "loss": 0.9062253952026367,
1441
+ "step": 890,
1442
+ "token_acc": 0.7496486649267216
1443
+ },
1444
+ {
1445
+ "epoch": 0.9540306462358428,
1446
+ "grad_norm": 4.659524061077068,
1447
+ "learning_rate": 2.3e-06,
1448
+ "loss": 0.7646889686584473,
1449
+ "step": 895,
1450
+ "token_acc": 0.7716500553709856
1451
+ },
1452
+ {
1453
+ "epoch": 0.9593604263824117,
1454
+ "grad_norm": 4.658005621045716,
1455
+ "learning_rate": 2.3e-06,
1456
+ "loss": 0.7846517562866211,
1457
+ "step": 900,
1458
+ "token_acc": 0.7760330578512397
1459
+ },
1460
+ {
1461
+ "epoch": 0.9646902065289806,
1462
+ "grad_norm": 4.827339570974992,
1463
+ "learning_rate": 2.3e-06,
1464
+ "loss": 0.8194332122802734,
1465
+ "step": 905,
1466
+ "token_acc": 0.7632450331125827
1467
+ },
1468
+ {
1469
+ "epoch": 0.9700199866755497,
1470
+ "grad_norm": 4.616508722821306,
1471
+ "learning_rate": 2.3e-06,
1472
+ "loss": 0.8886819839477539,
1473
+ "step": 910,
1474
+ "token_acc": 0.7549358843883575
1475
+ },
1476
+ {
1477
+ "epoch": 0.9753497668221186,
1478
+ "grad_norm": 4.587147736616801,
1479
+ "learning_rate": 2.3e-06,
1480
+ "loss": 0.82857666015625,
1481
+ "step": 915,
1482
+ "token_acc": 0.7579642579642579
1483
+ },
1484
+ {
1485
+ "epoch": 0.9806795469686875,
1486
+ "grad_norm": 4.385315976477473,
1487
+ "learning_rate": 2.3e-06,
1488
+ "loss": 0.8632021903991699,
1489
+ "step": 920,
1490
+ "token_acc": 0.7554684275691291
1491
+ },
1492
+ {
1493
+ "epoch": 0.9860093271152565,
1494
+ "grad_norm": 5.3105288038094605,
1495
+ "learning_rate": 2.3e-06,
1496
+ "loss": 0.7477989196777344,
1497
+ "step": 925,
1498
+ "token_acc": 0.7832802157391517
1499
+ },
1500
+ {
1501
+ "epoch": 0.9913391072618255,
1502
+ "grad_norm": 4.244619714135519,
1503
+ "learning_rate": 2.3e-06,
1504
+ "loss": 0.8497745513916015,
1505
+ "step": 930,
1506
+ "token_acc": 0.7574374885928089
1507
+ },
1508
+ {
1509
+ "epoch": 0.9966688874083944,
1510
+ "grad_norm": 4.693628875486247,
1511
+ "learning_rate": 2.3e-06,
1512
+ "loss": 0.7646096229553223,
1513
+ "step": 935,
1514
+ "token_acc": 0.7749592739120317
1515
+ }
1516
+ ],
1517
+ "logging_steps": 5,
1518
+ "max_steps": 939,
1519
+ "num_input_tokens_seen": 0,
1520
+ "num_train_epochs": 1,
1521
+ "save_steps": 500,
1522
+ "stateful_callbacks": {
1523
+ "TrainerControl": {
1524
+ "args": {
1525
+ "should_epoch_stop": false,
1526
+ "should_evaluate": false,
1527
+ "should_log": false,
1528
+ "should_save": true,
1529
+ "should_training_stop": true
1530
+ },
1531
+ "attributes": {}
1532
+ }
1533
+ },
1534
+ "total_flos": 1231477221752832.0,
1535
+ "train_batch_size": 2,
1536
+ "trial_name": null,
1537
+ "trial_params": null
1538
+ }
checkpoint-939/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a199edd71f4a74af9d5275f20743e1250d6d6696e66162173bfcda8c9de8cc4
3
+ size 9848
checkpoint-939/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
+ }
checkpoint-939/vocab.json ADDED
The diff for this file is too large to render. See raw diff