add sft-mvtec (weights only)
Browse files- .gitattributes +1 -0
- sft-mvtec/added_tokens.json +28 -0
- sft-mvtec/args.json +412 -0
- sft-mvtec/chat_template.jinja +120 -0
- sft-mvtec/config.json +68 -0
- sft-mvtec/generation_config.json +13 -0
- sft-mvtec/merges.txt +0 -0
- sft-mvtec/model-00001-of-00004.safetensors +3 -0
- sft-mvtec/model-00002-of-00004.safetensors +3 -0
- sft-mvtec/model-00003-of-00004.safetensors +3 -0
- sft-mvtec/model-00004-of-00004.safetensors +3 -0
- sft-mvtec/model.safetensors.index.json +758 -0
- sft-mvtec/preprocessor_config.json +21 -0
- sft-mvtec/special_tokens_map.json +31 -0
- sft-mvtec/tokenizer.json +3 -0
- sft-mvtec/tokenizer_config.json +240 -0
- sft-mvtec/trainer_state.json +1442 -0
- sft-mvtec/video_preprocessor_config.json +41 -0
- sft-mvtec/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
sft-mvtec/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
sft-mvtec/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 |
+
}
|
sft-mvtec/args.json
ADDED
|
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/work/s111062218/IRPO/mvtec/runs/sft_mvtec_full/v0-20260710-011618",
|
| 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": 1,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 1e-05,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"adam_beta1": 0.9,
|
| 20 |
+
"adam_beta2": 0.95,
|
| 21 |
+
"adam_epsilon": 1e-08,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"num_train_epochs": 2.0,
|
| 24 |
+
"max_steps": -1,
|
| 25 |
+
"lr_scheduler_type": "cosine",
|
| 26 |
+
"lr_scheduler_kwargs": null,
|
| 27 |
+
"warmup_ratio": 0.05,
|
| 28 |
+
"warmup_steps": 0,
|
| 29 |
+
"log_level": "passive",
|
| 30 |
+
"log_level_replica": "warning",
|
| 31 |
+
"log_on_each_node": true,
|
| 32 |
+
"logging_dir": "/work/s111062218/IRPO/mvtec/runs/sft_mvtec_full/v0-20260710-011618/runs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 1,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 88.0,
|
| 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": 88.0,
|
| 64 |
+
"dataloader_num_workers": null,
|
| 65 |
+
"dataloader_prefetch_factor": null,
|
| 66 |
+
"past_index": -1,
|
| 67 |
+
"run_name": "/work/s111062218/IRPO/mvtec/runs/sft_mvtec_full/v0-20260710-011618",
|
| 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_fused",
|
| 126 |
+
"optim_args": null,
|
| 127 |
+
"adafactor": false,
|
| 128 |
+
"group_by_length": false,
|
| 129 |
+
"length_column_name": "length",
|
| 130 |
+
"report_to": [
|
| 131 |
+
"tensorboard"
|
| 132 |
+
],
|
| 133 |
+
"project": "huggingface",
|
| 134 |
+
"trackio_space_id": "trackio",
|
| 135 |
+
"ddp_find_unused_parameters": null,
|
| 136 |
+
"ddp_bucket_cap_mb": null,
|
| 137 |
+
"ddp_broadcast_buffers": null,
|
| 138 |
+
"dataloader_pin_memory": true,
|
| 139 |
+
"dataloader_persistent_workers": false,
|
| 140 |
+
"skip_memory_metrics": true,
|
| 141 |
+
"use_legacy_prediction_loop": false,
|
| 142 |
+
"push_to_hub": false,
|
| 143 |
+
"resume_from_checkpoint": null,
|
| 144 |
+
"hub_model_id": null,
|
| 145 |
+
"hub_strategy": "every_save",
|
| 146 |
+
"hub_token": null,
|
| 147 |
+
"hub_private_repo": null,
|
| 148 |
+
"hub_always_push": false,
|
| 149 |
+
"hub_revision": null,
|
| 150 |
+
"gradient_checkpointing": true,
|
| 151 |
+
"gradient_checkpointing_kwargs": null,
|
| 152 |
+
"include_inputs_for_metrics": false,
|
| 153 |
+
"include_for_metrics": [],
|
| 154 |
+
"eval_do_concat_batches": true,
|
| 155 |
+
"fp16_backend": "auto",
|
| 156 |
+
"push_to_hub_model_id": null,
|
| 157 |
+
"push_to_hub_organization": null,
|
| 158 |
+
"push_to_hub_token": null,
|
| 159 |
+
"mp_parameters": "",
|
| 160 |
+
"auto_find_batch_size": false,
|
| 161 |
+
"full_determinism": false,
|
| 162 |
+
"torchdynamo": null,
|
| 163 |
+
"ray_scope": "last",
|
| 164 |
+
"ddp_timeout": 18000000,
|
| 165 |
+
"torch_compile": false,
|
| 166 |
+
"torch_compile_backend": null,
|
| 167 |
+
"torch_compile_mode": null,
|
| 168 |
+
"include_tokens_per_second": false,
|
| 169 |
+
"include_num_input_tokens_seen": false,
|
| 170 |
+
"neftune_noise_alpha": null,
|
| 171 |
+
"optim_target_modules": null,
|
| 172 |
+
"batch_eval_metrics": false,
|
| 173 |
+
"eval_on_start": false,
|
| 174 |
+
"use_liger_kernel": false,
|
| 175 |
+
"liger_kernel_config": null,
|
| 176 |
+
"eval_use_gather_object": false,
|
| 177 |
+
"average_tokens_across_devices": true,
|
| 178 |
+
"sortish_sampler": false,
|
| 179 |
+
"predict_with_generate": false,
|
| 180 |
+
"generation_max_length": null,
|
| 181 |
+
"generation_num_beams": null,
|
| 182 |
+
"generation_config": null,
|
| 183 |
+
"tuner_backend": "peft",
|
| 184 |
+
"vit_gradient_checkpointing": 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": false,
|
| 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": "Qwen/Qwen3-VL-8B-Instruct",
|
| 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": 8192,
|
| 251 |
+
"truncation_strategy": "delete",
|
| 252 |
+
"max_pixels": 200704,
|
| 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 |
+
"is_binary_loss_scale": null,
|
| 261 |
+
"template_backend": "swift",
|
| 262 |
+
"response_prefix": null,
|
| 263 |
+
"enable_thinking": null,
|
| 264 |
+
"preserve_thinking": null,
|
| 265 |
+
"add_non_thinking_prefix": true,
|
| 266 |
+
"disable_ignore_empty_think": false,
|
| 267 |
+
"dataset": [
|
| 268 |
+
"/work/s111062218/IRPO/mvtec/train_direct/mvtec_sft.jsonl"
|
| 269 |
+
],
|
| 270 |
+
"val_dataset": [],
|
| 271 |
+
"cached_dataset": [],
|
| 272 |
+
"cached_val_dataset": [],
|
| 273 |
+
"split_dataset_ratio": 0.0,
|
| 274 |
+
"dataset_num_proc": 2,
|
| 275 |
+
"load_from_cache_file": false,
|
| 276 |
+
"dataset_shuffle": true,
|
| 277 |
+
"val_dataset_shuffle": false,
|
| 278 |
+
"streaming": false,
|
| 279 |
+
"interleave_prob": null,
|
| 280 |
+
"stopping_strategy": "first_exhausted",
|
| 281 |
+
"shuffle_buffer_size": 1000,
|
| 282 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 283 |
+
"columns": {},
|
| 284 |
+
"strict": false,
|
| 285 |
+
"disable_auto_column_mapping": false,
|
| 286 |
+
"model_name": null,
|
| 287 |
+
"model_author": null,
|
| 288 |
+
"custom_dataset_info": [],
|
| 289 |
+
"quant_method": null,
|
| 290 |
+
"quant_bits": null,
|
| 291 |
+
"hqq_axis": null,
|
| 292 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 293 |
+
"bnb_4bit_quant_type": "nf4",
|
| 294 |
+
"bnb_4bit_use_double_quant": true,
|
| 295 |
+
"bnb_4bit_quant_storage": null,
|
| 296 |
+
"max_new_tokens": 64,
|
| 297 |
+
"temperature": 0.0,
|
| 298 |
+
"top_k": null,
|
| 299 |
+
"top_p": null,
|
| 300 |
+
"repetition_penalty": null,
|
| 301 |
+
"num_beams": 1,
|
| 302 |
+
"stream": false,
|
| 303 |
+
"stop_words": [],
|
| 304 |
+
"logprobs": false,
|
| 305 |
+
"top_logprobs": null,
|
| 306 |
+
"structured_outputs_regex": null,
|
| 307 |
+
"adapters": [],
|
| 308 |
+
"external_plugins": [],
|
| 309 |
+
"custom_register_path": [],
|
| 310 |
+
"model_kwargs": {},
|
| 311 |
+
"enable_npu_model_patch": true,
|
| 312 |
+
"load_args": false,
|
| 313 |
+
"load_data_args": false,
|
| 314 |
+
"packing": false,
|
| 315 |
+
"packing_length": null,
|
| 316 |
+
"packing_num_proc": 1,
|
| 317 |
+
"lazy_tokenize": true,
|
| 318 |
+
"use_hf": true,
|
| 319 |
+
"ignore_args_error": false,
|
| 320 |
+
"use_swift_lora": false,
|
| 321 |
+
"freeze_parameters": [
|
| 322 |
+
"model.visual",
|
| 323 |
+
"model.visual.merger",
|
| 324 |
+
"model.visual.deepstack_merger_list"
|
| 325 |
+
],
|
| 326 |
+
"freeze_parameters_regex": null,
|
| 327 |
+
"freeze_parameters_ratio": 0.0,
|
| 328 |
+
"trainable_parameters": [],
|
| 329 |
+
"trainable_parameters_regex": null,
|
| 330 |
+
"freeze_llm": false,
|
| 331 |
+
"freeze_vit": true,
|
| 332 |
+
"freeze_aligner": true,
|
| 333 |
+
"target_modules": [
|
| 334 |
+
"all-linear"
|
| 335 |
+
],
|
| 336 |
+
"target_regex": null,
|
| 337 |
+
"target_parameters": null,
|
| 338 |
+
"modules_to_save": [],
|
| 339 |
+
"lora_rank": 8,
|
| 340 |
+
"lora_alpha": 32,
|
| 341 |
+
"lora_dropout": 0.05,
|
| 342 |
+
"lora_bias": "none",
|
| 343 |
+
"lora_dtype": null,
|
| 344 |
+
"lorap_lr_ratio": null,
|
| 345 |
+
"use_rslora": false,
|
| 346 |
+
"use_dora": false,
|
| 347 |
+
"lora_ga_batch_size": 2,
|
| 348 |
+
"lora_ga_iters": 2,
|
| 349 |
+
"lora_ga_max_length": 1024,
|
| 350 |
+
"lora_ga_direction": "ArB2r",
|
| 351 |
+
"lora_ga_scale": "stable",
|
| 352 |
+
"lora_ga_stable_gamma": 16,
|
| 353 |
+
"init_weights": true,
|
| 354 |
+
"fourier_n_frequency": 2000,
|
| 355 |
+
"fourier_scaling": 300.0,
|
| 356 |
+
"boft_block_size": 4,
|
| 357 |
+
"boft_block_num": 0,
|
| 358 |
+
"boft_n_butterfly_factor": 1,
|
| 359 |
+
"boft_dropout": 0.0,
|
| 360 |
+
"vera_rank": 256,
|
| 361 |
+
"vera_projection_prng_key": 0,
|
| 362 |
+
"vera_dropout": 0.0,
|
| 363 |
+
"vera_d_initial": 0.1,
|
| 364 |
+
"adapter_act": "gelu",
|
| 365 |
+
"adapter_length": 128,
|
| 366 |
+
"adalora_target_r": 8,
|
| 367 |
+
"adalora_init_r": 12,
|
| 368 |
+
"adalora_tinit": 0,
|
| 369 |
+
"adalora_tfinal": 0,
|
| 370 |
+
"adalora_deltaT": 1,
|
| 371 |
+
"adalora_beta1": 0.85,
|
| 372 |
+
"adalora_beta2": 0.85,
|
| 373 |
+
"adalora_orth_reg_weight": 0.5,
|
| 374 |
+
"llamapro_num_new_blocks": 4,
|
| 375 |
+
"llamapro_num_groups": null,
|
| 376 |
+
"reft_layer_key": null,
|
| 377 |
+
"reft_layers": null,
|
| 378 |
+
"reft_rank": 4,
|
| 379 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 380 |
+
"reft_args": null,
|
| 381 |
+
"swanlab_token": null,
|
| 382 |
+
"swanlab_project": "ms-swift",
|
| 383 |
+
"swanlab_workspace": null,
|
| 384 |
+
"swanlab_exp_name": null,
|
| 385 |
+
"swanlab_notification_method": null,
|
| 386 |
+
"swanlab_webhook_url": null,
|
| 387 |
+
"swanlab_secret": null,
|
| 388 |
+
"swanlab_sender_email": null,
|
| 389 |
+
"swanlab_receiver_email": null,
|
| 390 |
+
"swanlab_smtp_server": null,
|
| 391 |
+
"swanlab_smtp_port": null,
|
| 392 |
+
"swanlab_email_language": "zh",
|
| 393 |
+
"swanlab_mode": "cloud",
|
| 394 |
+
"add_version": true,
|
| 395 |
+
"create_checkpoint_symlink": false,
|
| 396 |
+
"zero_hpz_partition_size": null,
|
| 397 |
+
"deepspeed_autotp_size": null,
|
| 398 |
+
"swift_version": "4.3.1",
|
| 399 |
+
"ckpt_dir": null,
|
| 400 |
+
"rank": 0,
|
| 401 |
+
"global_world_size": 2,
|
| 402 |
+
"local_world_size": 2,
|
| 403 |
+
"model_suffix": "Qwen3-VL-8B-Instruct",
|
| 404 |
+
"model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/work/s111062218/hf/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b', 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)",
|
| 405 |
+
"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='qwen3_vl', 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=[])",
|
| 406 |
+
"model_dir": "/work/s111062218/hf/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
|
| 407 |
+
"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='')",
|
| 408 |
+
"_val_dataset_exists": false,
|
| 409 |
+
"hub": "<class 'swift.hub.hub.HFHub'>",
|
| 410 |
+
"evaluation_strategy": "steps",
|
| 411 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/work/s111062218/IRPO/mvtec/runs/sft_mvtec_full/v0-20260710-011618', 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=1, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/work/s111062218/IRPO/mvtec/runs/sft_mvtec_full/v0-20260710-011618/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=88, 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=88.0, dataloader_num_workers=1, dataloader_prefetch_factor=2, past_index=-1, run_name='/work/s111062218/IRPO/mvtec/runs/sft_mvtec_full/v0-20260710-011618', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['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=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=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=False, 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)"
|
| 412 |
+
}
|
sft-mvtec/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 %}
|
sft-mvtec/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": "4.57.1",
|
| 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 |
+
}
|
sft-mvtec/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.1"
|
| 13 |
+
}
|
sft-mvtec/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft-mvtec/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7091cf5dab7bf8af9ccfb240a86e7f14d0da092e94b186ef1bef4d2cd83795b6
|
| 3 |
+
size 4998056552
|
sft-mvtec/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f0aebf6043400129ef42aff13b6e30cd8dfe7ceb233124c271101a632ccbe04
|
| 3 |
+
size 4915962464
|
sft-mvtec/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d0b85b594f1585c04b48872dbfa81820030f0c96e8192dab4a53341880731c1
|
| 3 |
+
size 4915962496
|
sft-mvtec/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c209b714eb1df5423e0722664621af91c32451dcaf1d31aa73ecae1671759a67
|
| 3 |
+
size 2704357976
|
sft-mvtec/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 |
+
}
|
sft-mvtec/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 |
+
}
|
sft-mvtec/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 |
+
}
|
sft-mvtec/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
sft-mvtec/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 |
+
}
|
sft-mvtec/trainer_state.json
ADDED
|
@@ -0,0 +1,1442 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 88.0,
|
| 7 |
+
"global_step": 176,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.011363636363636364,
|
| 14 |
+
"grad_norm": 195.9052499197566,
|
| 15 |
+
"learning_rate": 1.111111111111111e-06,
|
| 16 |
+
"loss": 1.6436803340911865,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.7368421052631579
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.022727272727272728,
|
| 22 |
+
"grad_norm": 197.8529757812739,
|
| 23 |
+
"learning_rate": 2.222222222222222e-06,
|
| 24 |
+
"loss": 2.2848076820373535,
|
| 25 |
+
"step": 2,
|
| 26 |
+
"token_acc": 0.6666666666666666
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.03409090909090909,
|
| 30 |
+
"grad_norm": 200.12115706482385,
|
| 31 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 32 |
+
"loss": 1.9579904079437256,
|
| 33 |
+
"step": 3,
|
| 34 |
+
"token_acc": 0.7027027027027027
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.045454545454545456,
|
| 38 |
+
"grad_norm": 156.1490927498441,
|
| 39 |
+
"learning_rate": 4.444444444444444e-06,
|
| 40 |
+
"loss": 1.67714524269104,
|
| 41 |
+
"step": 4,
|
| 42 |
+
"token_acc": 0.7894736842105263
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.056818181818181816,
|
| 46 |
+
"grad_norm": 128.56892038276865,
|
| 47 |
+
"learning_rate": 5.555555555555557e-06,
|
| 48 |
+
"loss": 0.5448644757270813,
|
| 49 |
+
"step": 5,
|
| 50 |
+
"token_acc": 0.8055555555555556
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06818181818181818,
|
| 54 |
+
"grad_norm": 53.96240527920626,
|
| 55 |
+
"learning_rate": 6.666666666666667e-06,
|
| 56 |
+
"loss": 0.5201314687728882,
|
| 57 |
+
"step": 6,
|
| 58 |
+
"token_acc": 0.9210526315789473
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.07954545454545454,
|
| 62 |
+
"grad_norm": 58.79727047532702,
|
| 63 |
+
"learning_rate": 7.77777777777778e-06,
|
| 64 |
+
"loss": 0.21907192468643188,
|
| 65 |
+
"step": 7,
|
| 66 |
+
"token_acc": 0.9523809523809523
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09090909090909091,
|
| 70 |
+
"grad_norm": 21.610610913212,
|
| 71 |
+
"learning_rate": 8.888888888888888e-06,
|
| 72 |
+
"loss": 0.23302510380744934,
|
| 73 |
+
"step": 8,
|
| 74 |
+
"token_acc": 0.9210526315789473
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.10227272727272728,
|
| 78 |
+
"grad_norm": 48.00136565721641,
|
| 79 |
+
"learning_rate": 1e-05,
|
| 80 |
+
"loss": 0.35925620794296265,
|
| 81 |
+
"step": 9,
|
| 82 |
+
"token_acc": 0.8947368421052632
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.11363636363636363,
|
| 86 |
+
"grad_norm": 11.165394060812915,
|
| 87 |
+
"learning_rate": 9.999115304121459e-06,
|
| 88 |
+
"loss": 0.16875913739204407,
|
| 89 |
+
"step": 10,
|
| 90 |
+
"token_acc": 0.918918918918919
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.125,
|
| 94 |
+
"grad_norm": 20.67801478310866,
|
| 95 |
+
"learning_rate": 9.996461529560553e-06,
|
| 96 |
+
"loss": 0.4627538323402405,
|
| 97 |
+
"step": 11,
|
| 98 |
+
"token_acc": 0.8947368421052632
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.13636363636363635,
|
| 102 |
+
"grad_norm": 14.547090071423504,
|
| 103 |
+
"learning_rate": 9.992039615430648e-06,
|
| 104 |
+
"loss": 0.2966996729373932,
|
| 105 |
+
"step": 12,
|
| 106 |
+
"token_acc": 0.8378378378378378
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.14772727272727273,
|
| 110 |
+
"grad_norm": 8.68950614952946,
|
| 111 |
+
"learning_rate": 9.985851126551428e-06,
|
| 112 |
+
"loss": 0.17632704973220825,
|
| 113 |
+
"step": 13,
|
| 114 |
+
"token_acc": 0.8974358974358975
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1590909090909091,
|
| 118 |
+
"grad_norm": 4.809531150727445,
|
| 119 |
+
"learning_rate": 9.977898252895133e-06,
|
| 120 |
+
"loss": 0.09936656802892685,
|
| 121 |
+
"step": 14,
|
| 122 |
+
"token_acc": 0.95
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.17045454545454544,
|
| 126 |
+
"grad_norm": 14.570648679905538,
|
| 127 |
+
"learning_rate": 9.968183808811586e-06,
|
| 128 |
+
"loss": 0.3718123435974121,
|
| 129 |
+
"step": 15,
|
| 130 |
+
"token_acc": 0.9210526315789473
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.18181818181818182,
|
| 134 |
+
"grad_norm": 13.903576246289267,
|
| 135 |
+
"learning_rate": 9.95671123203224e-06,
|
| 136 |
+
"loss": 0.46726879477500916,
|
| 137 |
+
"step": 16,
|
| 138 |
+
"token_acc": 0.8888888888888888
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.19318181818181818,
|
| 142 |
+
"grad_norm": 10.425063032585191,
|
| 143 |
+
"learning_rate": 9.943484582453653e-06,
|
| 144 |
+
"loss": 0.3023732304573059,
|
| 145 |
+
"step": 17,
|
| 146 |
+
"token_acc": 0.8947368421052632
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.20454545454545456,
|
| 150 |
+
"grad_norm": 13.968698952157565,
|
| 151 |
+
"learning_rate": 9.928508540700775e-06,
|
| 152 |
+
"loss": 0.4589124619960785,
|
| 153 |
+
"step": 18,
|
| 154 |
+
"token_acc": 0.8863636363636364
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.2159090909090909,
|
| 158 |
+
"grad_norm": 9.835347726071497,
|
| 159 |
+
"learning_rate": 9.91178840647057e-06,
|
| 160 |
+
"loss": 0.22297608852386475,
|
| 161 |
+
"step": 19,
|
| 162 |
+
"token_acc": 0.918918918918919
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.22727272727272727,
|
| 166 |
+
"grad_norm": 9.579424829686822,
|
| 167 |
+
"learning_rate": 9.893330096656576e-06,
|
| 168 |
+
"loss": 0.28242772817611694,
|
| 169 |
+
"step": 20,
|
| 170 |
+
"token_acc": 0.9
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.23863636363636365,
|
| 174 |
+
"grad_norm": 7.881240704755622,
|
| 175 |
+
"learning_rate": 9.873140143255035e-06,
|
| 176 |
+
"loss": 0.23008175194263458,
|
| 177 |
+
"step": 21,
|
| 178 |
+
"token_acc": 0.918918918918919
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.25,
|
| 182 |
+
"grad_norm": 10.872886421097451,
|
| 183 |
+
"learning_rate": 9.851225691053382e-06,
|
| 184 |
+
"loss": 0.33348631858825684,
|
| 185 |
+
"step": 22,
|
| 186 |
+
"token_acc": 0.9024390243902439
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.26136363636363635,
|
| 190 |
+
"grad_norm": 14.264270357002637,
|
| 191 |
+
"learning_rate": 9.827594495101824e-06,
|
| 192 |
+
"loss": 0.5246642827987671,
|
| 193 |
+
"step": 23,
|
| 194 |
+
"token_acc": 0.868421052631579
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.2727272727272727,
|
| 198 |
+
"grad_norm": 9.618701211682444,
|
| 199 |
+
"learning_rate": 9.802254917969033e-06,
|
| 200 |
+
"loss": 0.21203476190567017,
|
| 201 |
+
"step": 24,
|
| 202 |
+
"token_acc": 0.9210526315789473
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.2840909090909091,
|
| 206 |
+
"grad_norm": 12.947332773482199,
|
| 207 |
+
"learning_rate": 9.775215926782788e-06,
|
| 208 |
+
"loss": 0.4625626802444458,
|
| 209 |
+
"step": 25,
|
| 210 |
+
"token_acc": 0.9069767441860465
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.29545454545454547,
|
| 214 |
+
"grad_norm": 12.458809644831751,
|
| 215 |
+
"learning_rate": 9.746487090056712e-06,
|
| 216 |
+
"loss": 0.3603699803352356,
|
| 217 |
+
"step": 26,
|
| 218 |
+
"token_acc": 0.875
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.3068181818181818,
|
| 222 |
+
"grad_norm": 8.931946298485734,
|
| 223 |
+
"learning_rate": 9.71607857430419e-06,
|
| 224 |
+
"loss": 0.2773553729057312,
|
| 225 |
+
"step": 27,
|
| 226 |
+
"token_acc": 0.9512195121951219
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3181818181818182,
|
| 230 |
+
"grad_norm": 11.945759677616323,
|
| 231 |
+
"learning_rate": 9.68400114044064e-06,
|
| 232 |
+
"loss": 0.2876451909542084,
|
| 233 |
+
"step": 28,
|
| 234 |
+
"token_acc": 0.8918918918918919
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.32954545454545453,
|
| 238 |
+
"grad_norm": 8.563275162731655,
|
| 239 |
+
"learning_rate": 9.650266139975474e-06,
|
| 240 |
+
"loss": 0.23299528658390045,
|
| 241 |
+
"step": 29,
|
| 242 |
+
"token_acc": 0.9
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.3409090909090909,
|
| 246 |
+
"grad_norm": 7.639203814648641,
|
| 247 |
+
"learning_rate": 9.614885510995047e-06,
|
| 248 |
+
"loss": 0.2409423291683197,
|
| 249 |
+
"step": 30,
|
| 250 |
+
"token_acc": 0.9285714285714286
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.3522727272727273,
|
| 254 |
+
"grad_norm": 7.594291994556256,
|
| 255 |
+
"learning_rate": 9.577871773938013e-06,
|
| 256 |
+
"loss": 0.19314445555210114,
|
| 257 |
+
"step": 31,
|
| 258 |
+
"token_acc": 0.9210526315789473
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.36363636363636365,
|
| 262 |
+
"grad_norm": 10.22139388599444,
|
| 263 |
+
"learning_rate": 9.539238027164618e-06,
|
| 264 |
+
"loss": 0.2277001440525055,
|
| 265 |
+
"step": 32,
|
| 266 |
+
"token_acc": 0.925
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.375,
|
| 270 |
+
"grad_norm": 9.825388651759896,
|
| 271 |
+
"learning_rate": 9.498997942321484e-06,
|
| 272 |
+
"loss": 0.21605941653251648,
|
| 273 |
+
"step": 33,
|
| 274 |
+
"token_acc": 0.8918918918918919
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.38636363636363635,
|
| 278 |
+
"grad_norm": 8.071349735769445,
|
| 279 |
+
"learning_rate": 9.457165759503492e-06,
|
| 280 |
+
"loss": 0.20501622557640076,
|
| 281 |
+
"step": 34,
|
| 282 |
+
"token_acc": 0.9
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.3977272727272727,
|
| 286 |
+
"grad_norm": 4.498644705505135,
|
| 287 |
+
"learning_rate": 9.413756282214538e-06,
|
| 288 |
+
"loss": 0.11810928583145142,
|
| 289 |
+
"step": 35,
|
| 290 |
+
"token_acc": 0.9545454545454546
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.4090909090909091,
|
| 294 |
+
"grad_norm": 8.914258150643857,
|
| 295 |
+
"learning_rate": 9.368784872128877e-06,
|
| 296 |
+
"loss": 0.18691639602184296,
|
| 297 |
+
"step": 36,
|
| 298 |
+
"token_acc": 0.8974358974358975
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.42045454545454547,
|
| 302 |
+
"grad_norm": 9.393728864095808,
|
| 303 |
+
"learning_rate": 9.322267443654974e-06,
|
| 304 |
+
"loss": 0.2205682396888733,
|
| 305 |
+
"step": 37,
|
| 306 |
+
"token_acc": 0.918918918918919
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.4318181818181818,
|
| 310 |
+
"grad_norm": 10.426207266539826,
|
| 311 |
+
"learning_rate": 9.274220458303727e-06,
|
| 312 |
+
"loss": 0.3519130349159241,
|
| 313 |
+
"step": 38,
|
| 314 |
+
"token_acc": 0.8717948717948718
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.4431818181818182,
|
| 318 |
+
"grad_norm": 14.34736799438511,
|
| 319 |
+
"learning_rate": 9.224660918863104e-06,
|
| 320 |
+
"loss": 0.47112351655960083,
|
| 321 |
+
"step": 39,
|
| 322 |
+
"token_acc": 0.8648648648648649
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.45454545454545453,
|
| 326 |
+
"grad_norm": 15.21652321877103,
|
| 327 |
+
"learning_rate": 9.173606363381218e-06,
|
| 328 |
+
"loss": 0.4981301426887512,
|
| 329 |
+
"step": 40,
|
| 330 |
+
"token_acc": 0.85
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.4659090909090909,
|
| 334 |
+
"grad_norm": 8.101928185799775,
|
| 335 |
+
"learning_rate": 9.121074858959997e-06,
|
| 336 |
+
"loss": 0.2851291298866272,
|
| 337 |
+
"step": 41,
|
| 338 |
+
"token_acc": 0.918918918918919
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4772727272727273,
|
| 342 |
+
"grad_norm": 7.246952073824331,
|
| 343 |
+
"learning_rate": 9.067084995361623e-06,
|
| 344 |
+
"loss": 0.23519396781921387,
|
| 345 |
+
"step": 42,
|
| 346 |
+
"token_acc": 0.9736842105263158
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.48863636363636365,
|
| 350 |
+
"grad_norm": 6.858716885736816,
|
| 351 |
+
"learning_rate": 9.011655878430018e-06,
|
| 352 |
+
"loss": 0.2327650487422943,
|
| 353 |
+
"step": 43,
|
| 354 |
+
"token_acc": 0.9210526315789473
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.5,
|
| 358 |
+
"grad_norm": 5.963237806929174,
|
| 359 |
+
"learning_rate": 8.954807123329703e-06,
|
| 360 |
+
"loss": 0.17163364589214325,
|
| 361 |
+
"step": 44,
|
| 362 |
+
"token_acc": 0.972972972972973
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.5113636363636364,
|
| 366 |
+
"grad_norm": 8.927579293527703,
|
| 367 |
+
"learning_rate": 8.896558847604414e-06,
|
| 368 |
+
"loss": 0.29938608407974243,
|
| 369 |
+
"step": 45,
|
| 370 |
+
"token_acc": 0.918918918918919
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.5227272727272727,
|
| 374 |
+
"grad_norm": 9.90580188343264,
|
| 375 |
+
"learning_rate": 8.836931664057935e-06,
|
| 376 |
+
"loss": 0.26813453435897827,
|
| 377 |
+
"step": 46,
|
| 378 |
+
"token_acc": 0.918918918918919
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.5340909090909091,
|
| 382 |
+
"grad_norm": 9.069170357073718,
|
| 383 |
+
"learning_rate": 8.775946673459682e-06,
|
| 384 |
+
"loss": 0.3316657841205597,
|
| 385 |
+
"step": 47,
|
| 386 |
+
"token_acc": 0.926829268292683
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.5454545454545454,
|
| 390 |
+
"grad_norm": 9.467364120777885,
|
| 391 |
+
"learning_rate": 8.713625457077585e-06,
|
| 392 |
+
"loss": 0.3275446593761444,
|
| 393 |
+
"step": 48,
|
| 394 |
+
"token_acc": 0.8604651162790697
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5568181818181818,
|
| 398 |
+
"grad_norm": 6.527486895359135,
|
| 399 |
+
"learning_rate": 8.64999006904096e-06,
|
| 400 |
+
"loss": 0.10486947745084763,
|
| 401 |
+
"step": 49,
|
| 402 |
+
"token_acc": 0.9473684210526315
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5681818181818182,
|
| 406 |
+
"grad_norm": 8.03171901804604,
|
| 407 |
+
"learning_rate": 8.585063028536015e-06,
|
| 408 |
+
"loss": 0.1567389965057373,
|
| 409 |
+
"step": 50,
|
| 410 |
+
"token_acc": 0.9736842105263158
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.5795454545454546,
|
| 414 |
+
"grad_norm": 9.54100355711753,
|
| 415 |
+
"learning_rate": 8.518867311836808e-06,
|
| 416 |
+
"loss": 0.18998514115810394,
|
| 417 |
+
"step": 51,
|
| 418 |
+
"token_acc": 0.9743589743589743
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.5909090909090909,
|
| 422 |
+
"grad_norm": 14.315562799137096,
|
| 423 |
+
"learning_rate": 8.451426344174433e-06,
|
| 424 |
+
"loss": 0.41271671652793884,
|
| 425 |
+
"step": 52,
|
| 426 |
+
"token_acc": 0.8888888888888888
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.6022727272727273,
|
| 430 |
+
"grad_norm": 7.6591623398110364,
|
| 431 |
+
"learning_rate": 8.382763991447344e-06,
|
| 432 |
+
"loss": 0.1697944849729538,
|
| 433 |
+
"step": 53,
|
| 434 |
+
"token_acc": 0.972972972972973
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.6136363636363636,
|
| 438 |
+
"grad_norm": 7.728658786307115,
|
| 439 |
+
"learning_rate": 8.312904551775731e-06,
|
| 440 |
+
"loss": 0.12445592880249023,
|
| 441 |
+
"step": 54,
|
| 442 |
+
"token_acc": 0.9722222222222222
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.625,
|
| 446 |
+
"grad_norm": 6.928973081487085,
|
| 447 |
+
"learning_rate": 8.241872746902934e-06,
|
| 448 |
+
"loss": 0.18071499466896057,
|
| 449 |
+
"step": 55,
|
| 450 |
+
"token_acc": 0.95
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6363636363636364,
|
| 454 |
+
"grad_norm": 10.93589823580153,
|
| 455 |
+
"learning_rate": 8.16969371344696e-06,
|
| 456 |
+
"loss": 0.27051395177841187,
|
| 457 |
+
"step": 56,
|
| 458 |
+
"token_acc": 0.9047619047619048
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6477272727272727,
|
| 462 |
+
"grad_norm": 6.347167386694028,
|
| 463 |
+
"learning_rate": 8.096392994005177e-06,
|
| 464 |
+
"loss": 0.1373193860054016,
|
| 465 |
+
"step": 57,
|
| 466 |
+
"token_acc": 0.9512195121951219
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.6590909090909091,
|
| 470 |
+
"grad_norm": 9.945237728537498,
|
| 471 |
+
"learning_rate": 8.021996528115335e-06,
|
| 472 |
+
"loss": 0.5271890163421631,
|
| 473 |
+
"step": 58,
|
| 474 |
+
"token_acc": 0.9210526315789473
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.6704545454545454,
|
| 478 |
+
"grad_norm": 14.74078839957054,
|
| 479 |
+
"learning_rate": 7.946530643076138e-06,
|
| 480 |
+
"loss": 0.493736207485199,
|
| 481 |
+
"step": 59,
|
| 482 |
+
"token_acc": 0.8947368421052632
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.6818181818181818,
|
| 486 |
+
"grad_norm": 11.065972717032892,
|
| 487 |
+
"learning_rate": 7.870022044630569e-06,
|
| 488 |
+
"loss": 0.32494378089904785,
|
| 489 |
+
"step": 60,
|
| 490 |
+
"token_acc": 0.925
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.6931818181818182,
|
| 494 |
+
"grad_norm": 11.44327848116244,
|
| 495 |
+
"learning_rate": 7.792497807515317e-06,
|
| 496 |
+
"loss": 0.31102028489112854,
|
| 497 |
+
"step": 61,
|
| 498 |
+
"token_acc": 0.9210526315789473
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.7045454545454546,
|
| 502 |
+
"grad_norm": 8.66805616454484,
|
| 503 |
+
"learning_rate": 7.713985365879607e-06,
|
| 504 |
+
"loss": 0.16446304321289062,
|
| 505 |
+
"step": 62,
|
| 506 |
+
"token_acc": 0.9
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7159090909090909,
|
| 510 |
+
"grad_norm": 9.211547349947377,
|
| 511 |
+
"learning_rate": 7.63451250357685e-06,
|
| 512 |
+
"loss": 0.19309315085411072,
|
| 513 |
+
"step": 63,
|
| 514 |
+
"token_acc": 0.9
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.7272727272727273,
|
| 518 |
+
"grad_norm": 6.570773561644991,
|
| 519 |
+
"learning_rate": 7.55410734433254e-06,
|
| 520 |
+
"loss": 0.15972477197647095,
|
| 521 |
+
"step": 64,
|
| 522 |
+
"token_acc": 0.9473684210526315
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.7386363636363636,
|
| 526 |
+
"grad_norm": 11.004459112406472,
|
| 527 |
+
"learning_rate": 7.472798341791877e-06,
|
| 528 |
+
"loss": 0.33975672721862793,
|
| 529 |
+
"step": 65,
|
| 530 |
+
"token_acc": 0.8947368421052632
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.75,
|
| 534 |
+
"grad_norm": 7.056423289090194,
|
| 535 |
+
"learning_rate": 7.390614269450633e-06,
|
| 536 |
+
"loss": 0.19755582511425018,
|
| 537 |
+
"step": 66,
|
| 538 |
+
"token_acc": 0.9459459459459459
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.7613636363636364,
|
| 542 |
+
"grad_norm": 8.873371196309954,
|
| 543 |
+
"learning_rate": 7.3075842104728445e-06,
|
| 544 |
+
"loss": 0.29561012983322144,
|
| 545 |
+
"step": 67,
|
| 546 |
+
"token_acc": 0.9230769230769231
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.7727272727272727,
|
| 550 |
+
"grad_norm": 7.651685537791527,
|
| 551 |
+
"learning_rate": 7.223737547398898e-06,
|
| 552 |
+
"loss": 0.239907369017601,
|
| 553 |
+
"step": 68,
|
| 554 |
+
"token_acc": 0.925
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.7840909090909091,
|
| 558 |
+
"grad_norm": 7.502542695671493,
|
| 559 |
+
"learning_rate": 7.139103951747694e-06,
|
| 560 |
+
"loss": 0.17635251581668854,
|
| 561 |
+
"step": 69,
|
| 562 |
+
"token_acc": 0.9459459459459459
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7954545454545454,
|
| 566 |
+
"grad_norm": 8.741695509084057,
|
| 567 |
+
"learning_rate": 7.053713373516538e-06,
|
| 568 |
+
"loss": 0.21274474263191223,
|
| 569 |
+
"step": 70,
|
| 570 |
+
"token_acc": 0.95
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.8068181818181818,
|
| 574 |
+
"grad_norm": 6.790076837073194,
|
| 575 |
+
"learning_rate": 6.9675960305824785e-06,
|
| 576 |
+
"loss": 0.22346122562885284,
|
| 577 |
+
"step": 71,
|
| 578 |
+
"token_acc": 0.8947368421052632
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.8181818181818182,
|
| 582 |
+
"grad_norm": 7.431039250490218,
|
| 583 |
+
"learning_rate": 6.880782398008862e-06,
|
| 584 |
+
"loss": 0.1527853161096573,
|
| 585 |
+
"step": 72,
|
| 586 |
+
"token_acc": 0.9487179487179487
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.8295454545454546,
|
| 590 |
+
"grad_norm": 8.164971968902563,
|
| 591 |
+
"learning_rate": 6.7933031972608644e-06,
|
| 592 |
+
"loss": 0.1806386411190033,
|
| 593 |
+
"step": 73,
|
| 594 |
+
"token_acc": 0.9512195121951219
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.8409090909090909,
|
| 598 |
+
"grad_norm": 10.66558090913365,
|
| 599 |
+
"learning_rate": 6.70518938533383e-06,
|
| 600 |
+
"loss": 0.13778291642665863,
|
| 601 |
+
"step": 74,
|
| 602 |
+
"token_acc": 0.9473684210526315
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.8522727272727273,
|
| 606 |
+
"grad_norm": 9.529132284960879,
|
| 607 |
+
"learning_rate": 6.61647214379826e-06,
|
| 608 |
+
"loss": 0.2421799749135971,
|
| 609 |
+
"step": 75,
|
| 610 |
+
"token_acc": 0.925
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.8636363636363636,
|
| 614 |
+
"grad_norm": 9.227761599729329,
|
| 615 |
+
"learning_rate": 6.527182867765333e-06,
|
| 616 |
+
"loss": 0.14697305858135223,
|
| 617 |
+
"step": 76,
|
| 618 |
+
"token_acc": 0.9459459459459459
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.875,
|
| 622 |
+
"grad_norm": 9.81449017329525,
|
| 623 |
+
"learning_rate": 6.437353154776848e-06,
|
| 624 |
+
"loss": 0.29360121488571167,
|
| 625 |
+
"step": 77,
|
| 626 |
+
"token_acc": 0.8974358974358975
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.8863636363636364,
|
| 630 |
+
"grad_norm": 9.389854827380821,
|
| 631 |
+
"learning_rate": 6.3470147936235485e-06,
|
| 632 |
+
"loss": 0.31358498334884644,
|
| 633 |
+
"step": 78,
|
| 634 |
+
"token_acc": 0.926829268292683
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.8977272727272727,
|
| 638 |
+
"grad_norm": 6.1997657994467446,
|
| 639 |
+
"learning_rate": 6.256199753095745e-06,
|
| 640 |
+
"loss": 0.11065918952226639,
|
| 641 |
+
"step": 79,
|
| 642 |
+
"token_acc": 0.9736842105263158
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.9090909090909091,
|
| 646 |
+
"grad_norm": 7.145552043992015,
|
| 647 |
+
"learning_rate": 6.164940170670266e-06,
|
| 648 |
+
"loss": 0.16367042064666748,
|
| 649 |
+
"step": 80,
|
| 650 |
+
"token_acc": 0.9285714285714286
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.9204545454545454,
|
| 654 |
+
"grad_norm": 7.93747744022566,
|
| 655 |
+
"learning_rate": 6.073268341137694e-06,
|
| 656 |
+
"loss": 0.22145897150039673,
|
| 657 |
+
"step": 81,
|
| 658 |
+
"token_acc": 0.9459459459459459
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.9318181818181818,
|
| 662 |
+
"grad_norm": 6.472591335113881,
|
| 663 |
+
"learning_rate": 5.98121670517393e-06,
|
| 664 |
+
"loss": 0.15611425042152405,
|
| 665 |
+
"step": 82,
|
| 666 |
+
"token_acc": 0.9534883720930233
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.9431818181818182,
|
| 670 |
+
"grad_norm": 9.728846060957679,
|
| 671 |
+
"learning_rate": 5.8888178378601565e-06,
|
| 672 |
+
"loss": 0.33416748046875,
|
| 673 |
+
"step": 83,
|
| 674 |
+
"token_acc": 0.8974358974358975
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.9545454545454546,
|
| 678 |
+
"grad_norm": 5.949524265644311,
|
| 679 |
+
"learning_rate": 5.796104437155213e-06,
|
| 680 |
+
"loss": 0.23228313028812408,
|
| 681 |
+
"step": 84,
|
| 682 |
+
"token_acc": 0.925
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9659090909090909,
|
| 686 |
+
"grad_norm": 8.506133041858282,
|
| 687 |
+
"learning_rate": 5.703109312324493e-06,
|
| 688 |
+
"loss": 0.20393462479114532,
|
| 689 |
+
"step": 85,
|
| 690 |
+
"token_acc": 0.95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.9772727272727273,
|
| 694 |
+
"grad_norm": 7.684069112631382,
|
| 695 |
+
"learning_rate": 5.609865372329461e-06,
|
| 696 |
+
"loss": 0.23599931597709656,
|
| 697 |
+
"step": 86,
|
| 698 |
+
"token_acc": 0.8918918918918919
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.9886363636363636,
|
| 702 |
+
"grad_norm": 5.561375344471036,
|
| 703 |
+
"learning_rate": 5.516405614181883e-06,
|
| 704 |
+
"loss": 0.10231108218431473,
|
| 705 |
+
"step": 87,
|
| 706 |
+
"token_acc": 0.975
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.0,
|
| 710 |
+
"grad_norm": 6.402313033196499,
|
| 711 |
+
"learning_rate": 5.4227631112668955e-06,
|
| 712 |
+
"loss": 0.1993713080883026,
|
| 713 |
+
"step": 88,
|
| 714 |
+
"token_acc": 0.918918918918919
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.0113636363636365,
|
| 718 |
+
"grad_norm": 7.199893764507934,
|
| 719 |
+
"learning_rate": 5.328971001639054e-06,
|
| 720 |
+
"loss": 0.18095773458480835,
|
| 721 |
+
"step": 89,
|
| 722 |
+
"token_acc": 0.95
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.0227272727272727,
|
| 726 |
+
"grad_norm": 2.47366012333541,
|
| 727 |
+
"learning_rate": 5.235062476295488e-06,
|
| 728 |
+
"loss": 0.0230905469506979,
|
| 729 |
+
"step": 90,
|
| 730 |
+
"token_acc": 1.0
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.0340909090909092,
|
| 734 |
+
"grad_norm": 7.279321402429015,
|
| 735 |
+
"learning_rate": 5.141070767430331e-06,
|
| 736 |
+
"loss": 0.1365898996591568,
|
| 737 |
+
"step": 91,
|
| 738 |
+
"token_acc": 0.9459459459459459
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.0454545454545454,
|
| 742 |
+
"grad_norm": 5.350657202009064,
|
| 743 |
+
"learning_rate": 5.047029136674563e-06,
|
| 744 |
+
"loss": 0.11321850121021271,
|
| 745 |
+
"step": 92,
|
| 746 |
+
"token_acc": 0.9545454545454546
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.0568181818181819,
|
| 750 |
+
"grad_norm": 13.953533805140324,
|
| 751 |
+
"learning_rate": 4.95297086332544e-06,
|
| 752 |
+
"loss": 0.27081143856048584,
|
| 753 |
+
"step": 93,
|
| 754 |
+
"token_acc": 0.9210526315789473
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.0681818181818181,
|
| 758 |
+
"grad_norm": 9.411721345338792,
|
| 759 |
+
"learning_rate": 4.858929232569671e-06,
|
| 760 |
+
"loss": 0.13699771463871002,
|
| 761 |
+
"step": 94,
|
| 762 |
+
"token_acc": 0.9473684210526315
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.0795454545454546,
|
| 766 |
+
"grad_norm": 6.675002235100726,
|
| 767 |
+
"learning_rate": 4.7649375237045135e-06,
|
| 768 |
+
"loss": 0.10652704536914825,
|
| 769 |
+
"step": 95,
|
| 770 |
+
"token_acc": 0.9487179487179487
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.0909090909090908,
|
| 774 |
+
"grad_norm": 8.181756584986672,
|
| 775 |
+
"learning_rate": 4.671028998360947e-06,
|
| 776 |
+
"loss": 0.1227627545595169,
|
| 777 |
+
"step": 96,
|
| 778 |
+
"token_acc": 0.9487179487179487
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.1022727272727273,
|
| 782 |
+
"grad_norm": 13.821525224054058,
|
| 783 |
+
"learning_rate": 4.5772368887331044e-06,
|
| 784 |
+
"loss": 0.3747377395629883,
|
| 785 |
+
"step": 97,
|
| 786 |
+
"token_acc": 0.925
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.1136363636363635,
|
| 790 |
+
"grad_norm": 9.008201950815346,
|
| 791 |
+
"learning_rate": 4.483594385818119e-06,
|
| 792 |
+
"loss": 0.09657552093267441,
|
| 793 |
+
"step": 98,
|
| 794 |
+
"token_acc": 0.9444444444444444
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.125,
|
| 798 |
+
"grad_norm": 0.3399503581431662,
|
| 799 |
+
"learning_rate": 4.39013462767054e-06,
|
| 800 |
+
"loss": 0.0029641843866556883,
|
| 801 |
+
"step": 99,
|
| 802 |
+
"token_acc": 1.0
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.1363636363636362,
|
| 806 |
+
"grad_norm": 8.404769260512008,
|
| 807 |
+
"learning_rate": 4.29689068767551e-06,
|
| 808 |
+
"loss": 0.1632961481809616,
|
| 809 |
+
"step": 100,
|
| 810 |
+
"token_acc": 0.9230769230769231
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.1477272727272727,
|
| 814 |
+
"grad_norm": 6.156169046008191,
|
| 815 |
+
"learning_rate": 4.203895562844789e-06,
|
| 816 |
+
"loss": 0.11006340384483337,
|
| 817 |
+
"step": 101,
|
| 818 |
+
"token_acc": 0.9444444444444444
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.1590909090909092,
|
| 822 |
+
"grad_norm": 9.581907369768807,
|
| 823 |
+
"learning_rate": 4.111182162139844e-06,
|
| 824 |
+
"loss": 0.15489846467971802,
|
| 825 |
+
"step": 102,
|
| 826 |
+
"token_acc": 0.9545454545454546
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.1704545454545454,
|
| 830 |
+
"grad_norm": 2.1476395609705206,
|
| 831 |
+
"learning_rate": 4.018783294826071e-06,
|
| 832 |
+
"loss": 0.025181613862514496,
|
| 833 |
+
"step": 103,
|
| 834 |
+
"token_acc": 1.0
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.1818181818181819,
|
| 838 |
+
"grad_norm": 8.653026525644153,
|
| 839 |
+
"learning_rate": 3.926731658862307e-06,
|
| 840 |
+
"loss": 0.1841011792421341,
|
| 841 |
+
"step": 104,
|
| 842 |
+
"token_acc": 0.9285714285714286
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.1931818181818181,
|
| 846 |
+
"grad_norm": 7.504232851195428,
|
| 847 |
+
"learning_rate": 3.8350598293297345e-06,
|
| 848 |
+
"loss": 0.12672147154808044,
|
| 849 |
+
"step": 105,
|
| 850 |
+
"token_acc": 0.926829268292683
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.2045454545454546,
|
| 854 |
+
"grad_norm": 9.885762505275693,
|
| 855 |
+
"learning_rate": 3.7438002469042567e-06,
|
| 856 |
+
"loss": 0.276999294757843,
|
| 857 |
+
"step": 106,
|
| 858 |
+
"token_acc": 0.875
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.2159090909090908,
|
| 862 |
+
"grad_norm": 12.477323997898832,
|
| 863 |
+
"learning_rate": 3.652985206376455e-06,
|
| 864 |
+
"loss": 0.11598174273967743,
|
| 865 |
+
"step": 107,
|
| 866 |
+
"token_acc": 0.9166666666666666
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.2272727272727273,
|
| 870 |
+
"grad_norm": 6.978502854316774,
|
| 871 |
+
"learning_rate": 3.5626468452231534e-06,
|
| 872 |
+
"loss": 0.14181096851825714,
|
| 873 |
+
"step": 108,
|
| 874 |
+
"token_acc": 0.9512195121951219
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.2386363636363638,
|
| 878 |
+
"grad_norm": 10.418438484418086,
|
| 879 |
+
"learning_rate": 3.472817132234669e-06,
|
| 880 |
+
"loss": 0.24340537190437317,
|
| 881 |
+
"step": 109,
|
| 882 |
+
"token_acc": 0.95
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.25,
|
| 886 |
+
"grad_norm": 9.635231513627847,
|
| 887 |
+
"learning_rate": 3.3835278562017405e-06,
|
| 888 |
+
"loss": 0.1451936662197113,
|
| 889 |
+
"step": 110,
|
| 890 |
+
"token_acc": 0.95
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.2613636363636362,
|
| 894 |
+
"grad_norm": 6.495559629271991,
|
| 895 |
+
"learning_rate": 3.29481061466617e-06,
|
| 896 |
+
"loss": 0.13670389354228973,
|
| 897 |
+
"step": 111,
|
| 898 |
+
"token_acc": 0.9285714285714286
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.2727272727272727,
|
| 902 |
+
"grad_norm": 7.599787807019207,
|
| 903 |
+
"learning_rate": 3.2066968027391377e-06,
|
| 904 |
+
"loss": 0.1283184140920639,
|
| 905 |
+
"step": 112,
|
| 906 |
+
"token_acc": 0.975
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.2840909090909092,
|
| 910 |
+
"grad_norm": 7.8214885017197995,
|
| 911 |
+
"learning_rate": 3.119217601991139e-06,
|
| 912 |
+
"loss": 0.12655146420001984,
|
| 913 |
+
"step": 113,
|
| 914 |
+
"token_acc": 0.9459459459459459
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.2954545454545454,
|
| 918 |
+
"grad_norm": 1.33376059820044,
|
| 919 |
+
"learning_rate": 3.032403969417523e-06,
|
| 920 |
+
"loss": 0.012109911069273949,
|
| 921 |
+
"step": 114,
|
| 922 |
+
"token_acc": 1.0
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.3068181818181819,
|
| 926 |
+
"grad_norm": 1.855469756126943,
|
| 927 |
+
"learning_rate": 2.946286626483463e-06,
|
| 928 |
+
"loss": 0.016417205333709717,
|
| 929 |
+
"step": 115,
|
| 930 |
+
"token_acc": 1.0
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.3181818181818181,
|
| 934 |
+
"grad_norm": 14.519179269847893,
|
| 935 |
+
"learning_rate": 2.8608960482523058e-06,
|
| 936 |
+
"loss": 0.4724964499473572,
|
| 937 |
+
"step": 116,
|
| 938 |
+
"token_acc": 0.8648648648648649
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.3295454545454546,
|
| 942 |
+
"grad_norm": 8.04566880478037,
|
| 943 |
+
"learning_rate": 2.776262452601104e-06,
|
| 944 |
+
"loss": 0.17560063302516937,
|
| 945 |
+
"step": 117,
|
| 946 |
+
"token_acc": 0.9459459459459459
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.3409090909090908,
|
| 950 |
+
"grad_norm": 12.657358483238154,
|
| 951 |
+
"learning_rate": 2.6924157895271563e-06,
|
| 952 |
+
"loss": 0.3591260313987732,
|
| 953 |
+
"step": 118,
|
| 954 |
+
"token_acc": 0.8780487804878049
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.3522727272727273,
|
| 958 |
+
"grad_norm": 4.27840695352133,
|
| 959 |
+
"learning_rate": 2.6093857305493666e-06,
|
| 960 |
+
"loss": 0.06306027621030807,
|
| 961 |
+
"step": 119,
|
| 962 |
+
"token_acc": 0.9736842105263158
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.3636363636363638,
|
| 966 |
+
"grad_norm": 9.075217088447092,
|
| 967 |
+
"learning_rate": 2.5272016582081236e-06,
|
| 968 |
+
"loss": 0.2458903044462204,
|
| 969 |
+
"step": 120,
|
| 970 |
+
"token_acc": 0.9473684210526315
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.375,
|
| 974 |
+
"grad_norm": 1.7685033476767302,
|
| 975 |
+
"learning_rate": 2.445892655667462e-06,
|
| 976 |
+
"loss": 0.01817174255847931,
|
| 977 |
+
"step": 121,
|
| 978 |
+
"token_acc": 1.0
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.3863636363636362,
|
| 982 |
+
"grad_norm": 7.4739153510813185,
|
| 983 |
+
"learning_rate": 2.365487496423152e-06,
|
| 984 |
+
"loss": 0.17428866028785706,
|
| 985 |
+
"step": 122,
|
| 986 |
+
"token_acc": 0.95
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.3977272727272727,
|
| 990 |
+
"grad_norm": 7.659624146496388,
|
| 991 |
+
"learning_rate": 2.2860146341203936e-06,
|
| 992 |
+
"loss": 0.12651793658733368,
|
| 993 |
+
"step": 123,
|
| 994 |
+
"token_acc": 0.918918918918919
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.4090909090909092,
|
| 998 |
+
"grad_norm": 7.85241582131157,
|
| 999 |
+
"learning_rate": 2.207502192484685e-06,
|
| 1000 |
+
"loss": 0.16867241263389587,
|
| 1001 |
+
"step": 124,
|
| 1002 |
+
"token_acc": 0.9459459459459459
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.4204545454545454,
|
| 1006 |
+
"grad_norm": 5.969979957166302,
|
| 1007 |
+
"learning_rate": 2.1299779553694323e-06,
|
| 1008 |
+
"loss": 0.07473576813936234,
|
| 1009 |
+
"step": 125,
|
| 1010 |
+
"token_acc": 0.975
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.4318181818181819,
|
| 1014 |
+
"grad_norm": 1.8255317910915432,
|
| 1015 |
+
"learning_rate": 2.053469356923865e-06,
|
| 1016 |
+
"loss": 0.016128040850162506,
|
| 1017 |
+
"step": 126,
|
| 1018 |
+
"token_acc": 1.0
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.4431818181818181,
|
| 1022 |
+
"grad_norm": 5.5394567300337005,
|
| 1023 |
+
"learning_rate": 1.9780034718846653e-06,
|
| 1024 |
+
"loss": 0.055757757276296616,
|
| 1025 |
+
"step": 127,
|
| 1026 |
+
"token_acc": 0.9736842105263158
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.4545454545454546,
|
| 1030 |
+
"grad_norm": 6.583725345555674,
|
| 1031 |
+
"learning_rate": 1.9036070059948253e-06,
|
| 1032 |
+
"loss": 0.1242956891655922,
|
| 1033 |
+
"step": 128,
|
| 1034 |
+
"token_acc": 0.9210526315789473
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.4659090909090908,
|
| 1038 |
+
"grad_norm": 5.9848420129991835,
|
| 1039 |
+
"learning_rate": 1.8303062865530407e-06,
|
| 1040 |
+
"loss": 0.15906336903572083,
|
| 1041 |
+
"step": 129,
|
| 1042 |
+
"token_acc": 0.975
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.4772727272727273,
|
| 1046 |
+
"grad_norm": 6.110563378659318,
|
| 1047 |
+
"learning_rate": 1.7581272530970666e-06,
|
| 1048 |
+
"loss": 0.13482968509197235,
|
| 1049 |
+
"step": 130,
|
| 1050 |
+
"token_acc": 0.9722222222222222
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.4886363636363638,
|
| 1054 |
+
"grad_norm": 2.433994954138156,
|
| 1055 |
+
"learning_rate": 1.6870954482242707e-06,
|
| 1056 |
+
"loss": 0.01966552808880806,
|
| 1057 |
+
"step": 131,
|
| 1058 |
+
"token_acc": 1.0
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.5,
|
| 1062 |
+
"grad_norm": 7.238276976507611,
|
| 1063 |
+
"learning_rate": 1.6172360085526567e-06,
|
| 1064 |
+
"loss": 0.15612998604774475,
|
| 1065 |
+
"step": 132,
|
| 1066 |
+
"token_acc": 0.9487179487179487
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.5113636363636362,
|
| 1070 |
+
"grad_norm": 3.269861711718459,
|
| 1071 |
+
"learning_rate": 1.54857365582557e-06,
|
| 1072 |
+
"loss": 0.0246112123131752,
|
| 1073 |
+
"step": 133,
|
| 1074 |
+
"token_acc": 1.0
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.5227272727272727,
|
| 1078 |
+
"grad_norm": 9.569596217425156,
|
| 1079 |
+
"learning_rate": 1.4811326881631937e-06,
|
| 1080 |
+
"loss": 0.29205116629600525,
|
| 1081 |
+
"step": 134,
|
| 1082 |
+
"token_acc": 0.8974358974358975
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 1.5340909090909092,
|
| 1086 |
+
"grad_norm": 5.934444868229808,
|
| 1087 |
+
"learning_rate": 1.4149369714639856e-06,
|
| 1088 |
+
"loss": 0.1366189867258072,
|
| 1089 |
+
"step": 135,
|
| 1090 |
+
"token_acc": 0.9285714285714286
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.5454545454545454,
|
| 1094 |
+
"grad_norm": 4.946059819569902,
|
| 1095 |
+
"learning_rate": 1.3500099309590397e-06,
|
| 1096 |
+
"loss": 0.05375118553638458,
|
| 1097 |
+
"step": 136,
|
| 1098 |
+
"token_acc": 0.9743589743589743
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.5568181818181817,
|
| 1102 |
+
"grad_norm": 5.420651409348639,
|
| 1103 |
+
"learning_rate": 1.2863745429224145e-06,
|
| 1104 |
+
"loss": 0.07174789160490036,
|
| 1105 |
+
"step": 137,
|
| 1106 |
+
"token_acc": 0.9487179487179487
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.5681818181818183,
|
| 1110 |
+
"grad_norm": 4.022143313508885,
|
| 1111 |
+
"learning_rate": 1.22405332654032e-06,
|
| 1112 |
+
"loss": 0.028939109295606613,
|
| 1113 |
+
"step": 138,
|
| 1114 |
+
"token_acc": 1.0
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.5795454545454546,
|
| 1118 |
+
"grad_norm": 9.697441443288636,
|
| 1119 |
+
"learning_rate": 1.1630683359420653e-06,
|
| 1120 |
+
"loss": 0.16048294305801392,
|
| 1121 |
+
"step": 139,
|
| 1122 |
+
"token_acc": 0.918918918918919
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.5909090909090908,
|
| 1126 |
+
"grad_norm": 8.229479639223838,
|
| 1127 |
+
"learning_rate": 1.103441152395588e-06,
|
| 1128 |
+
"loss": 0.1701526790857315,
|
| 1129 |
+
"step": 140,
|
| 1130 |
+
"token_acc": 0.9459459459459459
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.6022727272727273,
|
| 1134 |
+
"grad_norm": 6.954228918415347,
|
| 1135 |
+
"learning_rate": 1.045192876670298e-06,
|
| 1136 |
+
"loss": 0.1258842945098877,
|
| 1137 |
+
"step": 141,
|
| 1138 |
+
"token_acc": 0.9743589743589743
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.6136363636363638,
|
| 1142 |
+
"grad_norm": 2.4947934548232165,
|
| 1143 |
+
"learning_rate": 9.883441215699824e-07,
|
| 1144 |
+
"loss": 0.018796103075146675,
|
| 1145 |
+
"step": 142,
|
| 1146 |
+
"token_acc": 1.0
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.625,
|
| 1150 |
+
"grad_norm": 7.6826017807589695,
|
| 1151 |
+
"learning_rate": 9.329150046383773e-07,
|
| 1152 |
+
"loss": 0.14171677827835083,
|
| 1153 |
+
"step": 143,
|
| 1154 |
+
"token_acc": 0.9487179487179487
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.6363636363636362,
|
| 1158 |
+
"grad_norm": 1.981506306155957,
|
| 1159 |
+
"learning_rate": 8.789251410400024e-07,
|
| 1160 |
+
"loss": 0.021310359239578247,
|
| 1161 |
+
"step": 144,
|
| 1162 |
+
"token_acc": 1.0
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.6477272727272727,
|
| 1166 |
+
"grad_norm": 9.316889291597604,
|
| 1167 |
+
"learning_rate": 8.263936366187825e-07,
|
| 1168 |
+
"loss": 0.21884095668792725,
|
| 1169 |
+
"step": 145,
|
| 1170 |
+
"token_acc": 0.95
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.6590909090909092,
|
| 1174 |
+
"grad_norm": 7.099583247790577,
|
| 1175 |
+
"learning_rate": 7.753390811368972e-07,
|
| 1176 |
+
"loss": 0.14693105220794678,
|
| 1177 |
+
"step": 146,
|
| 1178 |
+
"token_acc": 0.926829268292683
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.6704545454545454,
|
| 1182 |
+
"grad_norm": 7.061561118746622,
|
| 1183 |
+
"learning_rate": 7.257795416962754e-07,
|
| 1184 |
+
"loss": 0.09787449985742569,
|
| 1185 |
+
"step": 147,
|
| 1186 |
+
"token_acc": 0.95
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.6818181818181817,
|
| 1190 |
+
"grad_norm": 8.540582560750158,
|
| 1191 |
+
"learning_rate": 6.777325563450282e-07,
|
| 1192 |
+
"loss": 0.1575159877538681,
|
| 1193 |
+
"step": 148,
|
| 1194 |
+
"token_acc": 0.9230769230769231
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.6931818181818183,
|
| 1198 |
+
"grad_norm": 2.181121101987422,
|
| 1199 |
+
"learning_rate": 6.312151278711237e-07,
|
| 1200 |
+
"loss": 0.02192770503461361,
|
| 1201 |
+
"step": 149,
|
| 1202 |
+
"token_acc": 1.0
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.7045454545454546,
|
| 1206 |
+
"grad_norm": 7.3305693576878195,
|
| 1207 |
+
"learning_rate": 5.862437177854629e-07,
|
| 1208 |
+
"loss": 0.10576251894235611,
|
| 1209 |
+
"step": 150,
|
| 1210 |
+
"token_acc": 0.95
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.7159090909090908,
|
| 1214 |
+
"grad_norm": 7.275408392352814,
|
| 1215 |
+
"learning_rate": 5.428342404965076e-07,
|
| 1216 |
+
"loss": 0.09697937965393066,
|
| 1217 |
+
"step": 151,
|
| 1218 |
+
"token_acc": 0.9523809523809523
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.7272727272727273,
|
| 1222 |
+
"grad_norm": 7.7167780665745545,
|
| 1223 |
+
"learning_rate": 5.010020576785174e-07,
|
| 1224 |
+
"loss": 0.11863157898187637,
|
| 1225 |
+
"step": 152,
|
| 1226 |
+
"token_acc": 0.972972972972973
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.7386363636363638,
|
| 1230 |
+
"grad_norm": 6.854566961260753,
|
| 1231 |
+
"learning_rate": 4.607619728353818e-07,
|
| 1232 |
+
"loss": 0.08705897629261017,
|
| 1233 |
+
"step": 153,
|
| 1234 |
+
"token_acc": 0.9459459459459459
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.75,
|
| 1238 |
+
"grad_norm": 1.4950103182848966,
|
| 1239 |
+
"learning_rate": 4.221282260619891e-07,
|
| 1240 |
+
"loss": 0.016769861802458763,
|
| 1241 |
+
"step": 154,
|
| 1242 |
+
"token_acc": 1.0
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.7613636363636362,
|
| 1246 |
+
"grad_norm": 5.335402155261971,
|
| 1247 |
+
"learning_rate": 3.851144890049535e-07,
|
| 1248 |
+
"loss": 0.07611395418643951,
|
| 1249 |
+
"step": 155,
|
| 1250 |
+
"token_acc": 0.9444444444444444
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.7727272727272727,
|
| 1254 |
+
"grad_norm": 3.997548118257428,
|
| 1255 |
+
"learning_rate": 3.497338600245254e-07,
|
| 1256 |
+
"loss": 0.03954974189400673,
|
| 1257 |
+
"step": 156,
|
| 1258 |
+
"token_acc": 1.0
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 1.7840909090909092,
|
| 1262 |
+
"grad_norm": 6.029329008445983,
|
| 1263 |
+
"learning_rate": 3.159988595593616e-07,
|
| 1264 |
+
"loss": 0.10782109200954437,
|
| 1265 |
+
"step": 157,
|
| 1266 |
+
"token_acc": 0.975
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.7954545454545454,
|
| 1270 |
+
"grad_norm": 2.113198810909374,
|
| 1271 |
+
"learning_rate": 2.839214256958106e-07,
|
| 1272 |
+
"loss": 0.01702558435499668,
|
| 1273 |
+
"step": 158,
|
| 1274 |
+
"token_acc": 1.0
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.8068181818181817,
|
| 1278 |
+
"grad_norm": 6.085772397449453,
|
| 1279 |
+
"learning_rate": 2.5351290994328703e-07,
|
| 1280 |
+
"loss": 0.10801274329423904,
|
| 1281 |
+
"step": 159,
|
| 1282 |
+
"token_acc": 0.9736842105263158
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.8181818181818183,
|
| 1286 |
+
"grad_norm": 4.822542333419725,
|
| 1287 |
+
"learning_rate": 2.2478407321721295e-07,
|
| 1288 |
+
"loss": 0.07818000018596649,
|
| 1289 |
+
"step": 160,
|
| 1290 |
+
"token_acc": 0.9473684210526315
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.8295454545454546,
|
| 1294 |
+
"grad_norm": 6.90692198121901,
|
| 1295 |
+
"learning_rate": 1.9774508203096843e-07,
|
| 1296 |
+
"loss": 0.10510721802711487,
|
| 1297 |
+
"step": 161,
|
| 1298 |
+
"token_acc": 0.8974358974358975
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.8409090909090908,
|
| 1302 |
+
"grad_norm": 9.424366100232511,
|
| 1303 |
+
"learning_rate": 1.7240550489817652e-07,
|
| 1304 |
+
"loss": 0.31693142652511597,
|
| 1305 |
+
"step": 162,
|
| 1306 |
+
"token_acc": 0.9210526315789473
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.8522727272727273,
|
| 1310 |
+
"grad_norm": 5.9906515122333275,
|
| 1311 |
+
"learning_rate": 1.4877430894662037e-07,
|
| 1312 |
+
"loss": 0.0935223400592804,
|
| 1313 |
+
"step": 163,
|
| 1314 |
+
"token_acc": 0.9512195121951219
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.8636363636363638,
|
| 1318 |
+
"grad_norm": 0.7001975036371686,
|
| 1319 |
+
"learning_rate": 1.268598567449647e-07,
|
| 1320 |
+
"loss": 0.005389641970396042,
|
| 1321 |
+
"step": 164,
|
| 1322 |
+
"token_acc": 1.0
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.875,
|
| 1326 |
+
"grad_norm": 5.440457762197436,
|
| 1327 |
+
"learning_rate": 1.0666990334342708e-07,
|
| 1328 |
+
"loss": 0.09289371967315674,
|
| 1329 |
+
"step": 165,
|
| 1330 |
+
"token_acc": 0.9459459459459459
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.8863636363636362,
|
| 1334 |
+
"grad_norm": 4.629011735151434,
|
| 1335 |
+
"learning_rate": 8.821159352943142e-08,
|
| 1336 |
+
"loss": 0.05701345205307007,
|
| 1337 |
+
"step": 166,
|
| 1338 |
+
"token_acc": 0.95
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 1.8977272727272727,
|
| 1342 |
+
"grad_norm": 9.266170148953467,
|
| 1343 |
+
"learning_rate": 7.149145929922607e-08,
|
| 1344 |
+
"loss": 0.2318773865699768,
|
| 1345 |
+
"step": 167,
|
| 1346 |
+
"token_acc": 0.926829268292683
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.9090909090909092,
|
| 1350 |
+
"grad_norm": 7.325295151739083,
|
| 1351 |
+
"learning_rate": 5.651541754634726e-08,
|
| 1352 |
+
"loss": 0.11617127805948257,
|
| 1353 |
+
"step": 168,
|
| 1354 |
+
"token_acc": 0.9459459459459459
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.9204545454545454,
|
| 1358 |
+
"grad_norm": 4.679409964801964,
|
| 1359 |
+
"learning_rate": 4.328876796776071e-08,
|
| 1360 |
+
"loss": 0.048571497201919556,
|
| 1361 |
+
"step": 169,
|
| 1362 |
+
"token_acc": 0.972972972972973
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.9318181818181817,
|
| 1366 |
+
"grad_norm": 5.203562284759042,
|
| 1367 |
+
"learning_rate": 3.181619118841517e-08,
|
| 1368 |
+
"loss": 0.10277199745178223,
|
| 1369 |
+
"step": 170,
|
| 1370 |
+
"token_acc": 0.9761904761904762
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.9431818181818183,
|
| 1374 |
+
"grad_norm": 6.026296193559956,
|
| 1375 |
+
"learning_rate": 2.210174710486679e-08,
|
| 1376 |
+
"loss": 0.09030674397945404,
|
| 1377 |
+
"step": 171,
|
| 1378 |
+
"token_acc": 0.9512195121951219
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.9545454545454546,
|
| 1382 |
+
"grad_norm": 8.383579125272592,
|
| 1383 |
+
"learning_rate": 1.4148873448573408e-08,
|
| 1384 |
+
"loss": 0.1585637778043747,
|
| 1385 |
+
"step": 172,
|
| 1386 |
+
"token_acc": 0.925
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 1.9659090909090908,
|
| 1390 |
+
"grad_norm": 5.941814331196659,
|
| 1391 |
+
"learning_rate": 7.96038456935322e-09,
|
| 1392 |
+
"loss": 0.09052297472953796,
|
| 1393 |
+
"step": 173,
|
| 1394 |
+
"token_acc": 0.9473684210526315
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 1.9772727272727273,
|
| 1398 |
+
"grad_norm": 5.31219068311242,
|
| 1399 |
+
"learning_rate": 3.538470439448105e-09,
|
| 1400 |
+
"loss": 0.08900852501392365,
|
| 1401 |
+
"step": 174,
|
| 1402 |
+
"token_acc": 0.9534883720930233
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.9886363636363638,
|
| 1406 |
+
"grad_norm": 6.436701396284728,
|
| 1407 |
+
"learning_rate": 8.846958785418969e-10,
|
| 1408 |
+
"loss": 0.09907500445842743,
|
| 1409 |
+
"step": 175,
|
| 1410 |
+
"token_acc": 0.9459459459459459
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.0,
|
| 1414 |
+
"grad_norm": 6.805455894721991,
|
| 1415 |
+
"learning_rate": 0.0,
|
| 1416 |
+
"loss": 0.10433489084243774,
|
| 1417 |
+
"step": 176,
|
| 1418 |
+
"token_acc": 0.972972972972973
|
| 1419 |
+
}
|
| 1420 |
+
],
|
| 1421 |
+
"logging_steps": 1,
|
| 1422 |
+
"max_steps": 176,
|
| 1423 |
+
"num_input_tokens_seen": 0,
|
| 1424 |
+
"num_train_epochs": 2,
|
| 1425 |
+
"save_steps": 88,
|
| 1426 |
+
"stateful_callbacks": {
|
| 1427 |
+
"TrainerControl": {
|
| 1428 |
+
"args": {
|
| 1429 |
+
"should_epoch_stop": false,
|
| 1430 |
+
"should_evaluate": false,
|
| 1431 |
+
"should_log": false,
|
| 1432 |
+
"should_save": true,
|
| 1433 |
+
"should_training_stop": true
|
| 1434 |
+
},
|
| 1435 |
+
"attributes": {}
|
| 1436 |
+
}
|
| 1437 |
+
},
|
| 1438 |
+
"total_flos": 1241146570240.0,
|
| 1439 |
+
"train_batch_size": 2,
|
| 1440 |
+
"trial_name": null,
|
| 1441 |
+
"trial_params": null
|
| 1442 |
+
}
|
sft-mvtec/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 |
+
}
|
sft-mvtec/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|