Upload CamSFT-4B (checkpoint-1326)
Browse files- .gitattributes +1 -0
- README.md +24 -0
- args.json +382 -0
- chat_template.jinja +120 -0
- config.json +71 -0
- generation_config.json +14 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +722 -0
- preprocessor_config.json +21 -0
- processor_config.json +60 -0
- tokenizer.json +3 -0
- tokenizer_config.json +31 -0
- trainer_state.json +1098 -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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3-VL-4B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- camera-movement
|
| 6 |
+
- video-understanding
|
| 7 |
+
- qwen3-vl
|
| 8 |
+
- sft
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# CamSFT-4B
|
| 12 |
+
|
| 13 |
+
Camera-movement SFT 微调模型，基于 `Qwen/Qwen3-VL-4B-Instruct`。
|
| 14 |
+
|
| 15 |
+
- Checkpoint: `checkpoint-1326`
|
| 16 |
+
- 训练框架: [ms-swift](https://github.com/modelscope/ms-swift)
|
| 17 |
+
|
| 18 |
+
## 使用
|
| 19 |
+
|
| 20 |
+
```python
|
| 21 |
+
from transformers import AutoModelForCausalLM, AutoProcessor
|
| 22 |
+
model = AutoModelForCausalLM.from_pretrained("ddz16/CamSFT-4B", torch_dtype="bfloat16", device_map="auto")
|
| 23 |
+
processor = AutoProcessor.from_pretrained("ddz16/CamSFT-4B")
|
| 24 |
+
```
|
args.json
ADDED
|
@@ -0,0 +1,382 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/group/40009/dazhaodu/ms-swift/output/camera_sft_qwen3vl_4b/v7-20260707-101801",
|
| 3 |
+
"per_device_train_batch_size": 2,
|
| 4 |
+
"num_train_epochs": 2.0,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"learning_rate": 2e-05,
|
| 7 |
+
"lr_scheduler_type": "cosine",
|
| 8 |
+
"lr_scheduler_kwargs": null,
|
| 9 |
+
"warmup_steps": 0,
|
| 10 |
+
"optim": "adamw_torch_fused",
|
| 11 |
+
"optim_args": null,
|
| 12 |
+
"weight_decay": 0.01,
|
| 13 |
+
"adam_beta1": 0.9,
|
| 14 |
+
"adam_beta2": 0.95,
|
| 15 |
+
"adam_epsilon": 1e-08,
|
| 16 |
+
"optim_target_modules": null,
|
| 17 |
+
"gradient_accumulation_steps": 4,
|
| 18 |
+
"average_tokens_across_devices": true,
|
| 19 |
+
"max_grad_norm": 1.0,
|
| 20 |
+
"label_smoothing_factor": 0.0,
|
| 21 |
+
"bf16": true,
|
| 22 |
+
"fp16": false,
|
| 23 |
+
"bf16_full_eval": false,
|
| 24 |
+
"fp16_full_eval": false,
|
| 25 |
+
"tf32": null,
|
| 26 |
+
"gradient_checkpointing": true,
|
| 27 |
+
"gradient_checkpointing_kwargs": null,
|
| 28 |
+
"torch_compile": false,
|
| 29 |
+
"torch_compile_backend": null,
|
| 30 |
+
"torch_compile_mode": null,
|
| 31 |
+
"use_liger_kernel": false,
|
| 32 |
+
"liger_kernel_config": null,
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"neftune_noise_alpha": null,
|
| 35 |
+
"torch_empty_cache_steps": null,
|
| 36 |
+
"auto_find_batch_size": false,
|
| 37 |
+
"logging_strategy": "steps",
|
| 38 |
+
"logging_steps": 10,
|
| 39 |
+
"logging_first_step": true,
|
| 40 |
+
"log_on_each_node": true,
|
| 41 |
+
"logging_nan_inf_filter": true,
|
| 42 |
+
"include_num_input_tokens_seen": false,
|
| 43 |
+
"log_level": "passive",
|
| 44 |
+
"log_level_replica": "warning",
|
| 45 |
+
"disable_tqdm": null,
|
| 46 |
+
"report_to": [
|
| 47 |
+
"wandb"
|
| 48 |
+
],
|
| 49 |
+
"run_name": "/group/40009/dazhaodu/ms-swift/output/camera_sft_qwen3vl_4b/v7-20260707-101801",
|
| 50 |
+
"project": "huggingface",
|
| 51 |
+
"trackio_space_id": null,
|
| 52 |
+
"trackio_bucket_id": null,
|
| 53 |
+
"trackio_static_space_id": null,
|
| 54 |
+
"eval_strategy": "no",
|
| 55 |
+
"eval_steps": null,
|
| 56 |
+
"eval_delay": 0,
|
| 57 |
+
"per_device_eval_batch_size": 2,
|
| 58 |
+
"prediction_loss_only": false,
|
| 59 |
+
"eval_on_start": false,
|
| 60 |
+
"eval_do_concat_batches": true,
|
| 61 |
+
"eval_use_gather_object": false,
|
| 62 |
+
"eval_accumulation_steps": null,
|
| 63 |
+
"include_for_metrics": [],
|
| 64 |
+
"batch_eval_metrics": false,
|
| 65 |
+
"save_only_model": false,
|
| 66 |
+
"save_strategy": "epoch",
|
| 67 |
+
"save_steps": 500,
|
| 68 |
+
"save_on_each_node": false,
|
| 69 |
+
"save_total_limit": 1,
|
| 70 |
+
"enable_jit_checkpoint": false,
|
| 71 |
+
"push_to_hub": false,
|
| 72 |
+
"hub_token": null,
|
| 73 |
+
"hub_private_repo": null,
|
| 74 |
+
"hub_model_id": null,
|
| 75 |
+
"hub_strategy": "every_save",
|
| 76 |
+
"hub_always_push": false,
|
| 77 |
+
"hub_revision": null,
|
| 78 |
+
"load_best_model_at_end": false,
|
| 79 |
+
"metric_for_best_model": "loss",
|
| 80 |
+
"greater_is_better": false,
|
| 81 |
+
"ignore_data_skip": false,
|
| 82 |
+
"restore_callback_states_from_checkpoint": false,
|
| 83 |
+
"full_determinism": false,
|
| 84 |
+
"seed": 42,
|
| 85 |
+
"data_seed": 42,
|
| 86 |
+
"use_cpu": false,
|
| 87 |
+
"accelerator_config": {
|
| 88 |
+
"dispatch_batches": false
|
| 89 |
+
},
|
| 90 |
+
"parallelism_config": null,
|
| 91 |
+
"dataloader_drop_last": false,
|
| 92 |
+
"dataloader_num_workers": 8,
|
| 93 |
+
"dataloader_pin_memory": true,
|
| 94 |
+
"dataloader_persistent_workers": false,
|
| 95 |
+
"dataloader_prefetch_factor": null,
|
| 96 |
+
"remove_unused_columns": true,
|
| 97 |
+
"label_names": null,
|
| 98 |
+
"train_sampling_strategy": "random",
|
| 99 |
+
"length_column_name": "length",
|
| 100 |
+
"ddp_find_unused_parameters": null,
|
| 101 |
+
"ddp_bucket_cap_mb": null,
|
| 102 |
+
"ddp_broadcast_buffers": null,
|
| 103 |
+
"ddp_static_graph": null,
|
| 104 |
+
"ddp_backend": null,
|
| 105 |
+
"ddp_timeout": 18000000,
|
| 106 |
+
"fsdp": [],
|
| 107 |
+
"fsdp_config": null,
|
| 108 |
+
"deepspeed": {
|
| 109 |
+
"fp16": {
|
| 110 |
+
"enabled": "auto",
|
| 111 |
+
"loss_scale": 0,
|
| 112 |
+
"loss_scale_window": 1000,
|
| 113 |
+
"initial_scale_power": 16,
|
| 114 |
+
"hysteresis": 2,
|
| 115 |
+
"min_loss_scale": 1
|
| 116 |
+
},
|
| 117 |
+
"bf16": {
|
| 118 |
+
"enabled": "auto"
|
| 119 |
+
},
|
| 120 |
+
"zero_optimization": {
|
| 121 |
+
"stage": 2,
|
| 122 |
+
"offload_optimizer": {
|
| 123 |
+
"device": "none",
|
| 124 |
+
"pin_memory": true
|
| 125 |
+
},
|
| 126 |
+
"allgather_partitions": true,
|
| 127 |
+
"allgather_bucket_size": 200000000.0,
|
| 128 |
+
"overlap_comm": false,
|
| 129 |
+
"reduce_scatter": true,
|
| 130 |
+
"reduce_bucket_size": 200000000.0,
|
| 131 |
+
"contiguous_gradients": true
|
| 132 |
+
},
|
| 133 |
+
"gradient_accumulation_steps": "auto",
|
| 134 |
+
"gradient_clipping": "auto",
|
| 135 |
+
"steps_per_print": 2000,
|
| 136 |
+
"train_batch_size": "auto",
|
| 137 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 138 |
+
"wall_clock_breakdown": false
|
| 139 |
+
},
|
| 140 |
+
"debug": null,
|
| 141 |
+
"skip_memory_metrics": true,
|
| 142 |
+
"do_train": false,
|
| 143 |
+
"do_eval": false,
|
| 144 |
+
"do_predict": false,
|
| 145 |
+
"resume_from_checkpoint": null,
|
| 146 |
+
"warmup_ratio": 0.05,
|
| 147 |
+
"logging_dir": "/group/40009/dazhaodu/ms-swift/output/camera_sft_qwen3vl_4b/v7-20260707-101801/runs",
|
| 148 |
+
"local_rank": 0,
|
| 149 |
+
"sortish_sampler": false,
|
| 150 |
+
"predict_with_generate": false,
|
| 151 |
+
"generation_max_length": null,
|
| 152 |
+
"generation_num_beams": null,
|
| 153 |
+
"generation_config": null,
|
| 154 |
+
"tuner_backend": "peft",
|
| 155 |
+
"vit_gradient_checkpointing": false,
|
| 156 |
+
"router_aux_loss_coef": 0.0,
|
| 157 |
+
"enable_dft_loss": false,
|
| 158 |
+
"enable_channel_loss": false,
|
| 159 |
+
"safe_serialization": true,
|
| 160 |
+
"max_shard_size": "5GB",
|
| 161 |
+
"check_model": true,
|
| 162 |
+
"acc_strategy": "token",
|
| 163 |
+
"train_dataloader_shuffle": true,
|
| 164 |
+
"group_by_length": false,
|
| 165 |
+
"max_epochs": null,
|
| 166 |
+
"aligner_lr": null,
|
| 167 |
+
"vit_lr": null,
|
| 168 |
+
"use_logits_to_keep": null,
|
| 169 |
+
"ds3_gather_for_generation": true,
|
| 170 |
+
"resume_only_model": false,
|
| 171 |
+
"optimizer": null,
|
| 172 |
+
"loss_type": null,
|
| 173 |
+
"eval_metric": null,
|
| 174 |
+
"callbacks": [],
|
| 175 |
+
"early_stop_interval": null,
|
| 176 |
+
"eval_use_evalscope": false,
|
| 177 |
+
"eval_dataset": [],
|
| 178 |
+
"eval_dataset_args": null,
|
| 179 |
+
"eval_limit": null,
|
| 180 |
+
"eval_generation_config": null,
|
| 181 |
+
"extra_eval_args": null,
|
| 182 |
+
"tuner_type": "full",
|
| 183 |
+
"use_galore": false,
|
| 184 |
+
"galore_target_modules": null,
|
| 185 |
+
"galore_rank": 128,
|
| 186 |
+
"galore_update_proj_gap": 50,
|
| 187 |
+
"galore_scale": 1.0,
|
| 188 |
+
"galore_proj_type": "std",
|
| 189 |
+
"galore_optim_per_parameter": false,
|
| 190 |
+
"galore_with_embedding": false,
|
| 191 |
+
"galore_quantization": false,
|
| 192 |
+
"galore_proj_quant": false,
|
| 193 |
+
"galore_proj_bits": 4,
|
| 194 |
+
"galore_proj_group_size": 256,
|
| 195 |
+
"galore_cos_threshold": 0.4,
|
| 196 |
+
"galore_gamma_proj": 2,
|
| 197 |
+
"galore_queue_size": 5,
|
| 198 |
+
"lisa_activated_layers": 0,
|
| 199 |
+
"lisa_step_interval": 20,
|
| 200 |
+
"use_flash_ckpt": false,
|
| 201 |
+
"use_ray": false,
|
| 202 |
+
"ray_exp_name": null,
|
| 203 |
+
"device_groups": null,
|
| 204 |
+
"model": "Qwen/Qwen3-VL-4B-Instruct",
|
| 205 |
+
"model_type": "qwen3_vl",
|
| 206 |
+
"model_revision": null,
|
| 207 |
+
"task_type": "causal_lm",
|
| 208 |
+
"torch_dtype": "bfloat16",
|
| 209 |
+
"attn_impl": "flash_attention_2",
|
| 210 |
+
"experts_impl": null,
|
| 211 |
+
"new_special_tokens": [],
|
| 212 |
+
"num_labels": null,
|
| 213 |
+
"problem_type": null,
|
| 214 |
+
"rope_scaling": null,
|
| 215 |
+
"device_map": null,
|
| 216 |
+
"max_memory": {},
|
| 217 |
+
"max_model_len": null,
|
| 218 |
+
"local_repo_path": null,
|
| 219 |
+
"init_strategy": null,
|
| 220 |
+
"template": "qwen3_vl",
|
| 221 |
+
"system": null,
|
| 222 |
+
"max_length": 16384,
|
| 223 |
+
"truncation_strategy": "delete",
|
| 224 |
+
"max_pixels": null,
|
| 225 |
+
"agent_template": null,
|
| 226 |
+
"norm_bbox": null,
|
| 227 |
+
"use_chat_template": true,
|
| 228 |
+
"padding_side": "right",
|
| 229 |
+
"padding_free": false,
|
| 230 |
+
"loss_scale": "default",
|
| 231 |
+
"sequence_parallel_size": 1,
|
| 232 |
+
"template_backend": "swift",
|
| 233 |
+
"response_prefix": null,
|
| 234 |
+
"enable_thinking": null,
|
| 235 |
+
"preserve_thinking": null,
|
| 236 |
+
"add_non_thinking_prefix": true,
|
| 237 |
+
"dataset": [
|
| 238 |
+
"/group/40009/dazhaodu/ms-swift/camera_movement_sft/train_data/camera_movement_train_diverse_50k_en.jsonl"
|
| 239 |
+
],
|
| 240 |
+
"val_dataset": [],
|
| 241 |
+
"cached_dataset": [],
|
| 242 |
+
"cached_val_dataset": [],
|
| 243 |
+
"split_dataset_ratio": 0.0,
|
| 244 |
+
"dataset_num_proc": 8,
|
| 245 |
+
"load_from_cache_file": true,
|
| 246 |
+
"dataset_shuffle": true,
|
| 247 |
+
"val_dataset_shuffle": false,
|
| 248 |
+
"streaming": false,
|
| 249 |
+
"interleave_prob": null,
|
| 250 |
+
"stopping_strategy": "first_exhausted",
|
| 251 |
+
"shuffle_buffer_size": 1000,
|
| 252 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 253 |
+
"columns": {},
|
| 254 |
+
"strict": false,
|
| 255 |
+
"disable_auto_column_mapping": false,
|
| 256 |
+
"model_name": null,
|
| 257 |
+
"model_author": null,
|
| 258 |
+
"custom_dataset_info": [],
|
| 259 |
+
"quant_method": null,
|
| 260 |
+
"quant_bits": null,
|
| 261 |
+
"hqq_axis": null,
|
| 262 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 263 |
+
"bnb_4bit_quant_type": "nf4",
|
| 264 |
+
"bnb_4bit_use_double_quant": true,
|
| 265 |
+
"bnb_4bit_quant_storage": null,
|
| 266 |
+
"max_new_tokens": 64,
|
| 267 |
+
"temperature": 0.0,
|
| 268 |
+
"top_k": null,
|
| 269 |
+
"top_p": null,
|
| 270 |
+
"repetition_penalty": null,
|
| 271 |
+
"num_beams": 1,
|
| 272 |
+
"stream": false,
|
| 273 |
+
"stop_words": [],
|
| 274 |
+
"logprobs": false,
|
| 275 |
+
"top_logprobs": null,
|
| 276 |
+
"structured_outputs_regex": null,
|
| 277 |
+
"adapters": [],
|
| 278 |
+
"external_plugins": [],
|
| 279 |
+
"custom_register_path": [],
|
| 280 |
+
"model_kwargs": {},
|
| 281 |
+
"enable_npu_model_patch": true,
|
| 282 |
+
"load_args": false,
|
| 283 |
+
"load_data_args": false,
|
| 284 |
+
"packing": false,
|
| 285 |
+
"packing_length": null,
|
| 286 |
+
"packing_num_proc": 1,
|
| 287 |
+
"lazy_tokenize": true,
|
| 288 |
+
"use_hf": true,
|
| 289 |
+
"ignore_args_error": false,
|
| 290 |
+
"use_swift_lora": false,
|
| 291 |
+
"freeze_parameters": [
|
| 292 |
+
"model.visual",
|
| 293 |
+
"model.visual.merger",
|
| 294 |
+
"model.visual.deepstack_merger_list"
|
| 295 |
+
],
|
| 296 |
+
"freeze_parameters_regex": null,
|
| 297 |
+
"freeze_parameters_ratio": 0.0,
|
| 298 |
+
"trainable_parameters": [],
|
| 299 |
+
"trainable_parameters_regex": null,
|
| 300 |
+
"freeze_llm": false,
|
| 301 |
+
"freeze_vit": true,
|
| 302 |
+
"freeze_aligner": true,
|
| 303 |
+
"target_modules": [
|
| 304 |
+
"all-linear"
|
| 305 |
+
],
|
| 306 |
+
"target_regex": null,
|
| 307 |
+
"target_parameters": null,
|
| 308 |
+
"modules_to_save": [],
|
| 309 |
+
"lora_rank": 8,
|
| 310 |
+
"lora_alpha": 32,
|
| 311 |
+
"lora_dropout": 0.05,
|
| 312 |
+
"lora_bias": "none",
|
| 313 |
+
"lora_dtype": null,
|
| 314 |
+
"lorap_lr_ratio": null,
|
| 315 |
+
"use_rslora": false,
|
| 316 |
+
"use_dora": false,
|
| 317 |
+
"lora_ga_batch_size": 2,
|
| 318 |
+
"lora_ga_iters": 2,
|
| 319 |
+
"lora_ga_max_length": 1024,
|
| 320 |
+
"lora_ga_direction": "ArB2r",
|
| 321 |
+
"lora_ga_scale": "stable",
|
| 322 |
+
"lora_ga_stable_gamma": 16,
|
| 323 |
+
"init_weights": true,
|
| 324 |
+
"fourier_n_frequency": 2000,
|
| 325 |
+
"fourier_scaling": 300.0,
|
| 326 |
+
"boft_block_size": 4,
|
| 327 |
+
"boft_block_num": 0,
|
| 328 |
+
"boft_n_butterfly_factor": 1,
|
| 329 |
+
"boft_dropout": 0.0,
|
| 330 |
+
"vera_rank": 256,
|
| 331 |
+
"vera_projection_prng_key": 0,
|
| 332 |
+
"vera_dropout": 0.0,
|
| 333 |
+
"vera_d_initial": 0.1,
|
| 334 |
+
"adapter_act": "gelu",
|
| 335 |
+
"adapter_length": 128,
|
| 336 |
+
"adalora_target_r": 8,
|
| 337 |
+
"adalora_init_r": 12,
|
| 338 |
+
"adalora_tinit": 0,
|
| 339 |
+
"adalora_tfinal": 0,
|
| 340 |
+
"adalora_deltaT": 1,
|
| 341 |
+
"adalora_beta1": 0.85,
|
| 342 |
+
"adalora_beta2": 0.85,
|
| 343 |
+
"adalora_orth_reg_weight": 0.5,
|
| 344 |
+
"llamapro_num_new_blocks": 4,
|
| 345 |
+
"llamapro_num_groups": null,
|
| 346 |
+
"reft_layer_key": null,
|
| 347 |
+
"reft_layers": null,
|
| 348 |
+
"reft_rank": 4,
|
| 349 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 350 |
+
"reft_args": null,
|
| 351 |
+
"swanlab_token": null,
|
| 352 |
+
"swanlab_project": "ms-swift",
|
| 353 |
+
"swanlab_workspace": null,
|
| 354 |
+
"swanlab_exp_name": null,
|
| 355 |
+
"swanlab_notification_method": null,
|
| 356 |
+
"swanlab_webhook_url": null,
|
| 357 |
+
"swanlab_secret": null,
|
| 358 |
+
"swanlab_sender_email": null,
|
| 359 |
+
"swanlab_receiver_email": null,
|
| 360 |
+
"swanlab_smtp_server": null,
|
| 361 |
+
"swanlab_smtp_port": null,
|
| 362 |
+
"swanlab_email_language": "zh",
|
| 363 |
+
"swanlab_mode": "cloud",
|
| 364 |
+
"add_version": true,
|
| 365 |
+
"create_checkpoint_symlink": false,
|
| 366 |
+
"zero_hpz_partition_size": null,
|
| 367 |
+
"deepspeed_autotp_size": null,
|
| 368 |
+
"swift_version": "4.3.0.dev0",
|
| 369 |
+
"ckpt_dir": null,
|
| 370 |
+
"rank": 0,
|
| 371 |
+
"global_world_size": 8,
|
| 372 |
+
"local_world_size": 8,
|
| 373 |
+
"model_suffix": "Qwen3-VL-4B-Instruct",
|
| 374 |
+
"model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/apdcephfs_gy2/share_303094921/hunyuan/yujiazhang/dazhaodu/hf/hub/models--Qwen--Qwen3-VL-4B-Instruct/snapshots/ebb281ec70b05090aa6165b016eac8ec08e71b17', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
|
| 375 |
+
"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=[])",
|
| 376 |
+
"model_dir": "/apdcephfs_gy2/share_303094921/hunyuan/yujiazhang/dazhaodu/hf/hub/models--Qwen--Qwen3-VL-4B-Instruct/snapshots/ebb281ec70b05090aa6165b016eac8ec08e71b17",
|
| 377 |
+
"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='')",
|
| 378 |
+
"_val_dataset_exists": true,
|
| 379 |
+
"hub": "<class 'swift.hub.hub.HFHub'>",
|
| 380 |
+
"evaluation_strategy": "no",
|
| 381 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/group/40009/dazhaodu/ms-swift/output/camera_sft_qwen3vl_4b/v7-20260707-101801', per_device_train_batch_size=2, num_train_epochs=2.0, max_steps=-1, learning_rate=2e-05, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0.05, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=4, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=10, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['wandb'], run_name='/group/40009/dazhaodu/ms-swift/output/camera_sft_qwen3vl_4b/v7-20260707-101801', project='huggingface', trackio_space_id=None, trackio_bucket_id=None, trackio_static_space_id=None, eval_strategy=<IntervalStrategy.NO: 'no'>, eval_steps=None, eval_delay=0, per_device_eval_batch_size=2, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=False, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_on_each_node=False, save_total_limit=1, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, 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, dataloader_drop_last=False, dataloader_num_workers=8, dataloader_pin_memory=True, dataloader_persistent_workers=False, dataloader_prefetch_factor=2, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_static_graph=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=False, do_predict=False, resume_from_checkpoint=None, warmup_ratio=0.05, logging_dir='/group/40009/dazhaodu/ms-swift/output/camera_sft_qwen3vl_4b/v7-20260707-101801/runs', local_rank=0, 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, group_by_length=False, 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)"
|
| 382 |
+
}
|
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 %}
|
config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_size": 2560,
|
| 9 |
+
"image_token_id": 151655,
|
| 10 |
+
"model_type": "qwen3_vl",
|
| 11 |
+
"pad_token_id": 151643,
|
| 12 |
+
"text_config": {
|
| 13 |
+
"attention_bias": false,
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"bos_token_id": 151643,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 151645,
|
| 18 |
+
"head_dim": 128,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 2560,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 9728,
|
| 23 |
+
"max_position_embeddings": 262144,
|
| 24 |
+
"model_type": "qwen3_vl_text",
|
| 25 |
+
"num_attention_heads": 32,
|
| 26 |
+
"num_hidden_layers": 36,
|
| 27 |
+
"num_key_value_heads": 8,
|
| 28 |
+
"pad_token_id": 151643,
|
| 29 |
+
"rms_norm_eps": 1e-06,
|
| 30 |
+
"rope_parameters": {
|
| 31 |
+
"mrope_interleaved": true,
|
| 32 |
+
"mrope_section": [
|
| 33 |
+
24,
|
| 34 |
+
20,
|
| 35 |
+
20
|
| 36 |
+
],
|
| 37 |
+
"rope_theta": 5000000,
|
| 38 |
+
"rope_type": "default"
|
| 39 |
+
},
|
| 40 |
+
"tie_word_embeddings": true,
|
| 41 |
+
"use_cache": false,
|
| 42 |
+
"vocab_size": 151936
|
| 43 |
+
},
|
| 44 |
+
"tie_word_embeddings": true,
|
| 45 |
+
"transformers_version": "5.8.1",
|
| 46 |
+
"use_cache": false,
|
| 47 |
+
"video_token_id": 151656,
|
| 48 |
+
"vision_config": {
|
| 49 |
+
"deepstack_visual_indexes": [
|
| 50 |
+
5,
|
| 51 |
+
11,
|
| 52 |
+
17
|
| 53 |
+
],
|
| 54 |
+
"depth": 24,
|
| 55 |
+
"dtype": "bfloat16",
|
| 56 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 57 |
+
"hidden_size": 1024,
|
| 58 |
+
"in_channels": 3,
|
| 59 |
+
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 4096,
|
| 61 |
+
"model_type": "qwen3_vl_vision",
|
| 62 |
+
"num_heads": 16,
|
| 63 |
+
"num_position_embeddings": 2304,
|
| 64 |
+
"out_hidden_size": 2560,
|
| 65 |
+
"patch_size": 16,
|
| 66 |
+
"spatial_merge_size": 2,
|
| 67 |
+
"temporal_patch_size": 2
|
| 68 |
+
},
|
| 69 |
+
"vision_end_token_id": 151653,
|
| 70 |
+
"vision_start_token_id": 151652
|
| 71 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.0,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "5.8.1"
|
| 14 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:418087b9ecb3da146bf689be6236421467f588e3fa9f33950532fa8271a2ce1f
|
| 3 |
+
size 4987502200
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4671a46ba5ba73d703a7df4351113f73c21e0e7d741619b1f2d1342fc3099e54
|
| 3 |
+
size 4666129576
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,722 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4437815808,
|
| 4 |
+
"total_size": 9653543936
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 409 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 413 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 417 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 421 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 425 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 721 |
+
}
|
| 722 |
+
}
|
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 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
+
size 11422650
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": true,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 262144,
|
| 26 |
+
"pad_token": "<|endoftext|>",
|
| 27 |
+
"processor_class": "Qwen3VLProcessor",
|
| 28 |
+
"split_special_tokens": false,
|
| 29 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 30 |
+
"unk_token": null
|
| 31 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1098 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1326,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0015082956259426848,
|
| 14 |
+
"grad_norm": 30.968734741210938,
|
| 15 |
+
"learning_rate": 2.9850746268656716e-07,
|
| 16 |
+
"loss": 0.8261417150497437,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.8618925831202046
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.015082956259426848,
|
| 22 |
+
"grad_norm": 9.643964767456055,
|
| 23 |
+
"learning_rate": 2.9850746268656716e-06,
|
| 24 |
+
"loss": 0.6247194078233507,
|
| 25 |
+
"step": 10,
|
| 26 |
+
"token_acc": 0.8784715183458341
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.030165912518853696,
|
| 30 |
+
"grad_norm": 1.2653270959854126,
|
| 31 |
+
"learning_rate": 5.970149253731343e-06,
|
| 32 |
+
"loss": 0.21320788860321044,
|
| 33 |
+
"step": 20,
|
| 34 |
+
"token_acc": 0.9200478773370504
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.04524886877828054,
|
| 38 |
+
"grad_norm": 1.6828762292861938,
|
| 39 |
+
"learning_rate": 8.955223880597016e-06,
|
| 40 |
+
"loss": 0.1644657850265503,
|
| 41 |
+
"step": 30,
|
| 42 |
+
"token_acc": 0.9310746927198235
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.06033182503770739,
|
| 46 |
+
"grad_norm": 1.3016011714935303,
|
| 47 |
+
"learning_rate": 1.1940298507462686e-05,
|
| 48 |
+
"loss": 0.1581899881362915,
|
| 49 |
+
"step": 40,
|
| 50 |
+
"token_acc": 0.9363424769030858
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.07541478129713423,
|
| 54 |
+
"grad_norm": 1.772908329963684,
|
| 55 |
+
"learning_rate": 1.492537313432836e-05,
|
| 56 |
+
"loss": 0.14797013998031616,
|
| 57 |
+
"step": 50,
|
| 58 |
+
"token_acc": 0.9403096585489922
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09049773755656108,
|
| 62 |
+
"grad_norm": 1.0607707500457764,
|
| 63 |
+
"learning_rate": 1.791044776119403e-05,
|
| 64 |
+
"loss": 0.14336094856262208,
|
| 65 |
+
"step": 60,
|
| 66 |
+
"token_acc": 0.94302149950188
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.10558069381598793,
|
| 70 |
+
"grad_norm": 0.8757421970367432,
|
| 71 |
+
"learning_rate": 1.999971980603894e-05,
|
| 72 |
+
"loss": 0.14081008434295655,
|
| 73 |
+
"step": 70,
|
| 74 |
+
"token_acc": 0.9429653187944873
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.12066365007541478,
|
| 78 |
+
"grad_norm": 0.9281443357467651,
|
| 79 |
+
"learning_rate": 1.999473901685785e-05,
|
| 80 |
+
"loss": 0.1406252861022949,
|
| 81 |
+
"step": 80,
|
| 82 |
+
"token_acc": 0.9438380253798261
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.13574660633484162,
|
| 86 |
+
"grad_norm": 0.8397683501243591,
|
| 87 |
+
"learning_rate": 1.9983535264822027e-05,
|
| 88 |
+
"loss": 0.13869004249572753,
|
| 89 |
+
"step": 90,
|
| 90 |
+
"token_acc": 0.9443744563424218
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.15082956259426847,
|
| 94 |
+
"grad_norm": 0.9427488446235657,
|
| 95 |
+
"learning_rate": 1.9966115525654667e-05,
|
| 96 |
+
"loss": 0.13446314334869386,
|
| 97 |
+
"step": 100,
|
| 98 |
+
"token_acc": 0.9466490881125027
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.16591251885369532,
|
| 102 |
+
"grad_norm": 0.8245936036109924,
|
| 103 |
+
"learning_rate": 1.9942490645300782e-05,
|
| 104 |
+
"loss": 0.13205068111419677,
|
| 105 |
+
"step": 110,
|
| 106 |
+
"token_acc": 0.9481581044965068
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.18099547511312217,
|
| 110 |
+
"grad_norm": 1.0142247676849365,
|
| 111 |
+
"learning_rate": 1.9912675333174255e-05,
|
| 112 |
+
"loss": 0.1309139370918274,
|
| 113 |
+
"step": 120,
|
| 114 |
+
"token_acc": 0.9484835961342828
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.19607843137254902,
|
| 118 |
+
"grad_norm": 1.0399980545043945,
|
| 119 |
+
"learning_rate": 1.987668815299942e-05,
|
| 120 |
+
"loss": 0.13243772983551025,
|
| 121 |
+
"step": 130,
|
| 122 |
+
"token_acc": 0.9475406813257733
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.21116138763197587,
|
| 126 |
+
"grad_norm": 0.825975775718689,
|
| 127 |
+
"learning_rate": 1.9834551511252828e-05,
|
| 128 |
+
"loss": 0.13408410549163818,
|
| 129 |
+
"step": 140,
|
| 130 |
+
"token_acc": 0.9473418398419512
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.22624434389140272,
|
| 134 |
+
"grad_norm": 0.7565873265266418,
|
| 135 |
+
"learning_rate": 1.9786291643212466e-05,
|
| 136 |
+
"loss": 0.12777891159057617,
|
| 137 |
+
"step": 150,
|
| 138 |
+
"token_acc": 0.949374481295915
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.24132730015082957,
|
| 142 |
+
"grad_norm": 0.7258040904998779,
|
| 143 |
+
"learning_rate": 1.9731938596623012e-05,
|
| 144 |
+
"loss": 0.12959227561950684,
|
| 145 |
+
"step": 160,
|
| 146 |
+
"token_acc": 0.9500562361309542
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.2564102564102564,
|
| 150 |
+
"grad_norm": 0.5646476149559021,
|
| 151 |
+
"learning_rate": 1.9671526212987425e-05,
|
| 152 |
+
"loss": 0.12599967718124389,
|
| 153 |
+
"step": 170,
|
| 154 |
+
"token_acc": 0.9519809753197457
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.27149321266968324,
|
| 158 |
+
"grad_norm": 0.871751606464386,
|
| 159 |
+
"learning_rate": 1.9605092106496397e-05,
|
| 160 |
+
"loss": 0.1252290725708008,
|
| 161 |
+
"step": 180,
|
| 162 |
+
"token_acc": 0.9504295106136511
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.2865761689291101,
|
| 166 |
+
"grad_norm": 0.9698847532272339,
|
| 167 |
+
"learning_rate": 1.9532677640608874e-05,
|
| 168 |
+
"loss": 0.12251553535461426,
|
| 169 |
+
"step": 190,
|
| 170 |
+
"token_acc": 0.9512455846811675
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.30165912518853694,
|
| 174 |
+
"grad_norm": 0.7135357856750488,
|
| 175 |
+
"learning_rate": 1.9454327902298176e-05,
|
| 176 |
+
"loss": 0.1227449893951416,
|
| 177 |
+
"step": 200,
|
| 178 |
+
"token_acc": 0.9516792651420917
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3167420814479638,
|
| 182 |
+
"grad_norm": 1.152921199798584,
|
| 183 |
+
"learning_rate": 1.9370091673979764e-05,
|
| 184 |
+
"loss": 0.12003127336502076,
|
| 185 |
+
"step": 210,
|
| 186 |
+
"token_acc": 0.9536876879684603
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.33182503770739064,
|
| 190 |
+
"grad_norm": 0.7168576717376709,
|
| 191 |
+
"learning_rate": 1.9280021403138154e-05,
|
| 192 |
+
"loss": 0.13734824657440187,
|
| 193 |
+
"step": 220,
|
| 194 |
+
"token_acc": 0.9508574589710492
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.3469079939668175,
|
| 198 |
+
"grad_norm": 0.9696043729782104,
|
| 199 |
+
"learning_rate": 1.9184173169671868e-05,
|
| 200 |
+
"loss": 0.12161376476287841,
|
| 201 |
+
"step": 230,
|
| 202 |
+
"token_acc": 0.9523213065686307
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.36199095022624433,
|
| 206 |
+
"grad_norm": 0.6335675120353699,
|
| 207 |
+
"learning_rate": 1.9082606650976735e-05,
|
| 208 |
+
"loss": 0.1165058970451355,
|
| 209 |
+
"step": 240,
|
| 210 |
+
"token_acc": 0.9543600729984925
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.3770739064856712,
|
| 214 |
+
"grad_norm": 0.5023436546325684,
|
| 215 |
+
"learning_rate": 1.8975385084789333e-05,
|
| 216 |
+
"loss": 0.11858338117599487,
|
| 217 |
+
"step": 250,
|
| 218 |
+
"token_acc": 0.9543472601848236
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.39215686274509803,
|
| 222 |
+
"grad_norm": 0.8230804800987244,
|
| 223 |
+
"learning_rate": 1.886257522981367e-05,
|
| 224 |
+
"loss": 0.11891791820526124,
|
| 225 |
+
"step": 260,
|
| 226 |
+
"token_acc": 0.9533092044993767
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4072398190045249,
|
| 230 |
+
"grad_norm": 0.7313021421432495,
|
| 231 |
+
"learning_rate": 1.8744247324155604e-05,
|
| 232 |
+
"loss": 0.11976690292358398,
|
| 233 |
+
"step": 270,
|
| 234 |
+
"token_acc": 0.9534955965269256
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.42232277526395173,
|
| 238 |
+
"grad_norm": 0.6101995706558228,
|
| 239 |
+
"learning_rate": 1.8620475041590948e-05,
|
| 240 |
+
"loss": 0.11677769422531128,
|
| 241 |
+
"step": 280,
|
| 242 |
+
"token_acc": 0.9540437337788252
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.4374057315233786,
|
| 246 |
+
"grad_norm": 0.6487584114074707,
|
| 247 |
+
"learning_rate": 1.8491335445694404e-05,
|
| 248 |
+
"loss": 0.11501857042312622,
|
| 249 |
+
"step": 290,
|
| 250 |
+
"token_acc": 0.95502744006087
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.45248868778280543,
|
| 254 |
+
"grad_norm": 0.6374943256378174,
|
| 255 |
+
"learning_rate": 1.8356908941857942e-05,
|
| 256 |
+
"loss": 0.12021658420562745,
|
| 257 |
+
"step": 300,
|
| 258 |
+
"token_acc": 0.9528524628869934
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.4675716440422323,
|
| 262 |
+
"grad_norm": 0.744682788848877,
|
| 263 |
+
"learning_rate": 1.8217279227228503e-05,
|
| 264 |
+
"loss": 0.1173781156539917,
|
| 265 |
+
"step": 310,
|
| 266 |
+
"token_acc": 0.9543975427285445
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.48265460030165913,
|
| 270 |
+
"grad_norm": 0.7849182486534119,
|
| 271 |
+
"learning_rate": 1.8072533238596134e-05,
|
| 272 |
+
"loss": 0.11671500205993653,
|
| 273 |
+
"step": 320,
|
| 274 |
+
"token_acc": 0.9545516831864066
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.497737556561086,
|
| 278 |
+
"grad_norm": 0.42268458008766174,
|
| 279 |
+
"learning_rate": 1.7922761098265096e-05,
|
| 280 |
+
"loss": 0.11766018867492675,
|
| 281 |
+
"step": 330,
|
| 282 |
+
"token_acc": 0.9539052876838372
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5128205128205128,
|
| 286 |
+
"grad_norm": 0.6217177510261536,
|
| 287 |
+
"learning_rate": 1.7768056057941546e-05,
|
| 288 |
+
"loss": 0.11545138359069824,
|
| 289 |
+
"step": 340,
|
| 290 |
+
"token_acc": 0.9544162710572694
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5279034690799397,
|
| 294 |
+
"grad_norm": 0.688858151435852,
|
| 295 |
+
"learning_rate": 1.760851444067282e-05,
|
| 296 |
+
"loss": 0.11715751886367798,
|
| 297 |
+
"step": 350,
|
| 298 |
+
"token_acc": 0.9544157346702661
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.5429864253393665,
|
| 302 |
+
"grad_norm": 0.570622444152832,
|
| 303 |
+
"learning_rate": 1.7444235580874382e-05,
|
| 304 |
+
"loss": 0.11272256374359131,
|
| 305 |
+
"step": 360,
|
| 306 |
+
"token_acc": 0.9569494714351771
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.5580693815987934,
|
| 310 |
+
"grad_norm": 0.43587830662727356,
|
| 311 |
+
"learning_rate": 1.727532176248188e-05,
|
| 312 |
+
"loss": 0.1147916078567505,
|
| 313 |
+
"step": 370,
|
| 314 |
+
"token_acc": 0.9553941908713693
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.5731523378582202,
|
| 318 |
+
"grad_norm": 0.39815858006477356,
|
| 319 |
+
"learning_rate": 1.7101878155266702e-05,
|
| 320 |
+
"loss": 0.11624550819396973,
|
| 321 |
+
"step": 380,
|
| 322 |
+
"token_acc": 0.9544733044733045
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.5882352941176471,
|
| 326 |
+
"grad_norm": 0.5202909708023071,
|
| 327 |
+
"learning_rate": 1.692401274935478e-05,
|
| 328 |
+
"loss": 0.11601772308349609,
|
| 329 |
+
"step": 390,
|
| 330 |
+
"token_acc": 0.9548668395003536
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.6033182503770739,
|
| 334 |
+
"grad_norm": 0.6442638039588928,
|
| 335 |
+
"learning_rate": 1.674183628798936e-05,
|
| 336 |
+
"loss": 0.1141278862953186,
|
| 337 |
+
"step": 400,
|
| 338 |
+
"token_acc": 0.9565292910153166
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6184012066365008,
|
| 342 |
+
"grad_norm": 0.5705167651176453,
|
| 343 |
+
"learning_rate": 1.655546219857962e-05,
|
| 344 |
+
"loss": 0.11343185901641846,
|
| 345 |
+
"step": 410,
|
| 346 |
+
"token_acc": 0.955780920763412
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6334841628959276,
|
| 350 |
+
"grad_norm": 0.7077851295471191,
|
| 351 |
+
"learning_rate": 1.6365006522078057e-05,
|
| 352 |
+
"loss": 0.11292238235473633,
|
| 353 |
+
"step": 420,
|
| 354 |
+
"token_acc": 0.956367147389232
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.6485671191553545,
|
| 358 |
+
"grad_norm": 0.7096773386001587,
|
| 359 |
+
"learning_rate": 1.6170587840730627e-05,
|
| 360 |
+
"loss": 0.11361818313598633,
|
| 361 |
+
"step": 430,
|
| 362 |
+
"token_acc": 0.9554244309583136
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.6636500754147813,
|
| 366 |
+
"grad_norm": 0.6647536754608154,
|
| 367 |
+
"learning_rate": 1.59723272042446e-05,
|
| 368 |
+
"loss": 0.1104124665260315,
|
| 369 |
+
"step": 440,
|
| 370 |
+
"token_acc": 0.9571542325125567
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.6787330316742082,
|
| 374 |
+
"grad_norm": 0.532390296459198,
|
| 375 |
+
"learning_rate": 1.5770348054420147e-05,
|
| 376 |
+
"loss": 0.10935736894607544,
|
| 377 |
+
"step": 450,
|
| 378 |
+
"token_acc": 0.9568433662773286
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.693815987933635,
|
| 382 |
+
"grad_norm": 0.6258285045623779,
|
| 383 |
+
"learning_rate": 1.556477614829251e-05,
|
| 384 |
+
"loss": 0.10925512313842774,
|
| 385 |
+
"step": 460,
|
| 386 |
+
"token_acc": 0.9575476813907008
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.7088989441930619,
|
| 390 |
+
"grad_norm": 0.6589264273643494,
|
| 391 |
+
"learning_rate": 1.5355739479832675e-05,
|
| 392 |
+
"loss": 0.11245393753051758,
|
| 393 |
+
"step": 470,
|
| 394 |
+
"token_acc": 0.9563331882774868
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7239819004524887,
|
| 398 |
+
"grad_norm": 0.8117122650146484,
|
| 399 |
+
"learning_rate": 1.5143368200255294e-05,
|
| 400 |
+
"loss": 0.10972108840942382,
|
| 401 |
+
"step": 480,
|
| 402 |
+
"token_acc": 0.9572499104179975
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7390648567119156,
|
| 406 |
+
"grad_norm": 0.6422977447509766,
|
| 407 |
+
"learning_rate": 1.4927794536983411e-05,
|
| 408 |
+
"loss": 0.1119101881980896,
|
| 409 |
+
"step": 490,
|
| 410 |
+
"token_acc": 0.9557822601900805
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7541478129713424,
|
| 414 |
+
"grad_norm": 0.5782728791236877,
|
| 415 |
+
"learning_rate": 1.4709152711320529e-05,
|
| 416 |
+
"loss": 0.11008884906768798,
|
| 417 |
+
"step": 500,
|
| 418 |
+
"token_acc": 0.9574936263202622
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.7692307692307693,
|
| 422 |
+
"grad_norm": 0.6354721188545227,
|
| 423 |
+
"learning_rate": 1.4487578854881217e-05,
|
| 424 |
+
"loss": 0.10828690528869629,
|
| 425 |
+
"step": 510,
|
| 426 |
+
"token_acc": 0.9580254531430775
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.7843137254901961,
|
| 430 |
+
"grad_norm": 0.5012155771255493,
|
| 431 |
+
"learning_rate": 1.4263210924832332e-05,
|
| 432 |
+
"loss": 0.10970515012741089,
|
| 433 |
+
"step": 520,
|
| 434 |
+
"token_acc": 0.957624905926984
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.799396681749623,
|
| 438 |
+
"grad_norm": 0.5928862690925598,
|
| 439 |
+
"learning_rate": 1.4036188617997581e-05,
|
| 440 |
+
"loss": 0.1113357424736023,
|
| 441 |
+
"step": 530,
|
| 442 |
+
"token_acc": 0.9566905792375645
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.8144796380090498,
|
| 446 |
+
"grad_norm": 0.43102213740348816,
|
| 447 |
+
"learning_rate": 1.3806653283878963e-05,
|
| 448 |
+
"loss": 0.107137131690979,
|
| 449 |
+
"step": 540,
|
| 450 |
+
"token_acc": 0.9579867607981257
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.8295625942684767,
|
| 454 |
+
"grad_norm": 0.417781800031662,
|
| 455 |
+
"learning_rate": 1.3574747836649197e-05,
|
| 456 |
+
"loss": 0.10823215246200561,
|
| 457 |
+
"step": 550,
|
| 458 |
+
"token_acc": 0.9582748004901814
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8446455505279035,
|
| 462 |
+
"grad_norm": 0.8108027577400208,
|
| 463 |
+
"learning_rate": 1.3340616666169925e-05,
|
| 464 |
+
"loss": 0.10481956005096435,
|
| 465 |
+
"step": 560,
|
| 466 |
+
"token_acc": 0.959131087119606
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.8597285067873304,
|
| 470 |
+
"grad_norm": 0.5911276340484619,
|
| 471 |
+
"learning_rate": 1.3104405548091188e-05,
|
| 472 |
+
"loss": 0.108212411403656,
|
| 473 |
+
"step": 570,
|
| 474 |
+
"token_acc": 0.9576892430278885
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8748114630467572,
|
| 478 |
+
"grad_norm": 0.5372975468635559,
|
| 479 |
+
"learning_rate": 1.2866261553087977e-05,
|
| 480 |
+
"loss": 0.10410468578338623,
|
| 481 |
+
"step": 580,
|
| 482 |
+
"token_acc": 0.9592422768746237
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.889894419306184,
|
| 486 |
+
"grad_norm": 0.5496704578399658,
|
| 487 |
+
"learning_rate": 1.2626332955290564e-05,
|
| 488 |
+
"loss": 0.10734721422195434,
|
| 489 |
+
"step": 590,
|
| 490 |
+
"token_acc": 0.9583501505790307
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.9049773755656109,
|
| 494 |
+
"grad_norm": 0.4394945800304413,
|
| 495 |
+
"learning_rate": 1.2384769139965476e-05,
|
| 496 |
+
"loss": 0.10930960178375244,
|
| 497 |
+
"step": 600,
|
| 498 |
+
"token_acc": 0.9577309571799371
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.9200603318250377,
|
| 502 |
+
"grad_norm": 0.642622172832489,
|
| 503 |
+
"learning_rate": 1.2141720510504662e-05,
|
| 504 |
+
"loss": 0.10778934955596924,
|
| 505 |
+
"step": 610,
|
| 506 |
+
"token_acc": 0.9577198020406916
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9351432880844646,
|
| 510 |
+
"grad_norm": 0.5836299657821655,
|
| 511 |
+
"learning_rate": 1.1897338394780762e-05,
|
| 512 |
+
"loss": 0.10450876951217651,
|
| 513 |
+
"step": 620,
|
| 514 |
+
"token_acc": 0.9592342342342343
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9502262443438914,
|
| 518 |
+
"grad_norm": 0.37644606828689575,
|
| 519 |
+
"learning_rate": 1.165177495092677e-05,
|
| 520 |
+
"loss": 0.10912293195724487,
|
| 521 |
+
"step": 630,
|
| 522 |
+
"token_acc": 0.9573103488304603
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.9653092006033183,
|
| 526 |
+
"grad_norm": 0.5391575694084167,
|
| 527 |
+
"learning_rate": 1.1405183072598735e-05,
|
| 528 |
+
"loss": 0.10322842597961426,
|
| 529 |
+
"step": 640,
|
| 530 |
+
"token_acc": 0.9595477232115349
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.9803921568627451,
|
| 534 |
+
"grad_norm": 0.5731673240661621,
|
| 535 |
+
"learning_rate": 1.115771629378054e-05,
|
| 536 |
+
"loss": 0.10575449466705322,
|
| 537 |
+
"step": 650,
|
| 538 |
+
"token_acc": 0.9590387340944134
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.995475113122172,
|
| 542 |
+
"grad_norm": 0.4750414192676544,
|
| 543 |
+
"learning_rate": 1.0909528693189974e-05,
|
| 544 |
+
"loss": 0.10648643970489502,
|
| 545 |
+
"step": 660,
|
| 546 |
+
"token_acc": 0.9586862250888426
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.0105580693815988,
|
| 550 |
+
"grad_norm": 0.44234615564346313,
|
| 551 |
+
"learning_rate": 1.0660774798345655e-05,
|
| 552 |
+
"loss": 0.10033718347549439,
|
| 553 |
+
"step": 670,
|
| 554 |
+
"token_acc": 0.9616517345072387
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.0256410256410255,
|
| 558 |
+
"grad_norm": 0.4087628722190857,
|
| 559 |
+
"learning_rate": 1.0411609489354495e-05,
|
| 560 |
+
"loss": 0.09711532592773438,
|
| 561 |
+
"step": 680,
|
| 562 |
+
"token_acc": 0.9627995992882882
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.0407239819004526,
|
| 566 |
+
"grad_norm": 0.873450517654419,
|
| 567 |
+
"learning_rate": 1.016218790247969e-05,
|
| 568 |
+
"loss": 0.09997568130493165,
|
| 569 |
+
"step": 690,
|
| 570 |
+
"token_acc": 0.960326375237917
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0558069381598794,
|
| 574 |
+
"grad_norm": 0.6006814241409302,
|
| 575 |
+
"learning_rate": 9.91266533354913e-06,
|
| 576 |
+
"loss": 0.09607951045036316,
|
| 577 |
+
"step": 700,
|
| 578 |
+
"token_acc": 0.962045793927327
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.0708898944193062,
|
| 582 |
+
"grad_norm": 0.5565671324729919,
|
| 583 |
+
"learning_rate": 9.663197141264556e-06,
|
| 584 |
+
"loss": 0.09508470296859742,
|
| 585 |
+
"step": 710,
|
| 586 |
+
"token_acc": 0.9628928711804696
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.085972850678733,
|
| 590 |
+
"grad_norm": 0.4465359151363373,
|
| 591 |
+
"learning_rate": 9.413938650471515e-06,
|
| 592 |
+
"loss": 0.09565139412879944,
|
| 593 |
+
"step": 720,
|
| 594 |
+
"token_acc": 0.9632787942290643
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.10105580693816,
|
| 598 |
+
"grad_norm": 0.5148073434829712,
|
| 599 |
+
"learning_rate": 9.165045055450393e-06,
|
| 600 |
+
"loss": 0.09551175832748413,
|
| 601 |
+
"step": 730,
|
| 602 |
+
"token_acc": 0.9626595193859836
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.1161387631975868,
|
| 606 |
+
"grad_norm": 0.526919960975647,
|
| 607 |
+
"learning_rate": 8.916671323288777e-06,
|
| 608 |
+
"loss": 0.09376778602600097,
|
| 609 |
+
"step": 740,
|
| 610 |
+
"token_acc": 0.9630099437202928
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.1312217194570136,
|
| 614 |
+
"grad_norm": 0.515141487121582,
|
| 615 |
+
"learning_rate": 8.66897209739523e-06,
|
| 616 |
+
"loss": 0.0931336224079132,
|
| 617 |
+
"step": 750,
|
| 618 |
+
"token_acc": 0.9638066154589221
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.1463046757164403,
|
| 622 |
+
"grad_norm": 0.40961524844169617,
|
| 623 |
+
"learning_rate": 8.422101601214643e-06,
|
| 624 |
+
"loss": 0.09019145965576172,
|
| 625 |
+
"step": 760,
|
| 626 |
+
"token_acc": 0.9654217212723278
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1613876319758674,
|
| 630 |
+
"grad_norm": 0.498300701379776,
|
| 631 |
+
"learning_rate": 8.176213542205016e-06,
|
| 632 |
+
"loss": 0.09666601419448853,
|
| 633 |
+
"step": 770,
|
| 634 |
+
"token_acc": 0.9628490978048501
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.1764705882352942,
|
| 638 |
+
"grad_norm": 0.634801983833313,
|
| 639 |
+
"learning_rate": 7.931461016135534e-06,
|
| 640 |
+
"loss": 0.09509063959121704,
|
| 641 |
+
"step": 780,
|
| 642 |
+
"token_acc": 0.9631919905771495
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.191553544494721,
|
| 646 |
+
"grad_norm": 0.5501129627227783,
|
| 647 |
+
"learning_rate": 7.687996411765503e-06,
|
| 648 |
+
"loss": 0.09726064801216125,
|
| 649 |
+
"step": 790,
|
| 650 |
+
"token_acc": 0.9615822735429508
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.2066365007541477,
|
| 654 |
+
"grad_norm": 0.40932971239089966,
|
| 655 |
+
"learning_rate": 7.445971315963459e-06,
|
| 656 |
+
"loss": 0.09402073621749878,
|
| 657 |
+
"step": 800,
|
| 658 |
+
"token_acc": 0.9623268010364785
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.2217194570135748,
|
| 662 |
+
"grad_norm": 0.4873681962490082,
|
| 663 |
+
"learning_rate": 7.205536419325581e-06,
|
| 664 |
+
"loss": 0.0950639545917511,
|
| 665 |
+
"step": 810,
|
| 666 |
+
"token_acc": 0.9637483110183024
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.2368024132730016,
|
| 670 |
+
"grad_norm": 0.664931058883667,
|
| 671 |
+
"learning_rate": 6.966841422352127e-06,
|
| 672 |
+
"loss": 0.0921372652053833,
|
| 673 |
+
"step": 820,
|
| 674 |
+
"token_acc": 0.9640317224437807
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.2518853695324283,
|
| 678 |
+
"grad_norm": 0.43320387601852417,
|
| 679 |
+
"learning_rate": 6.7300349422403344e-06,
|
| 680 |
+
"loss": 0.09601188898086548,
|
| 681 |
+
"step": 830,
|
| 682 |
+
"token_acc": 0.9622773264928032
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2669683257918551,
|
| 686 |
+
"grad_norm": 0.48374417424201965,
|
| 687 |
+
"learning_rate": 6.495264420351799e-06,
|
| 688 |
+
"loss": 0.09131983518600464,
|
| 689 |
+
"step": 840,
|
| 690 |
+
"token_acc": 0.9639983480254632
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.282051282051282,
|
| 694 |
+
"grad_norm": 0.43359142541885376,
|
| 695 |
+
"learning_rate": 6.262676030411985e-06,
|
| 696 |
+
"loss": 0.09142310619354248,
|
| 697 |
+
"step": 850,
|
| 698 |
+
"token_acc": 0.9637676869338702
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.297134238310709,
|
| 702 |
+
"grad_norm": 0.6854210495948792,
|
| 703 |
+
"learning_rate": 6.0324145874989606e-06,
|
| 704 |
+
"loss": 0.0924448013305664,
|
| 705 |
+
"step": 860,
|
| 706 |
+
"token_acc": 0.9636747201305801
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.3122171945701357,
|
| 710 |
+
"grad_norm": 0.4733792841434479,
|
| 711 |
+
"learning_rate": 5.804623457878088e-06,
|
| 712 |
+
"loss": 0.09350036382675171,
|
| 713 |
+
"step": 870,
|
| 714 |
+
"token_acc": 0.9638449071188131
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.3273001508295625,
|
| 718 |
+
"grad_norm": 0.4248761832714081,
|
| 719 |
+
"learning_rate": 5.579444469738771e-06,
|
| 720 |
+
"loss": 0.09371748566627502,
|
| 721 |
+
"step": 880,
|
| 722 |
+
"token_acc": 0.963402983234714
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.3423831070889896,
|
| 726 |
+
"grad_norm": 0.3817572593688965,
|
| 727 |
+
"learning_rate": 5.357017824888831e-06,
|
| 728 |
+
"loss": 0.08855417370796204,
|
| 729 |
+
"step": 890,
|
| 730 |
+
"token_acc": 0.965276182349273
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.3574660633484164,
|
| 734 |
+
"grad_norm": 0.5116860270500183,
|
| 735 |
+
"learning_rate": 5.137482011461513e-06,
|
| 736 |
+
"loss": 0.09090266823768615,
|
| 737 |
+
"step": 900,
|
| 738 |
+
"token_acc": 0.964496366539577
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.3725490196078431,
|
| 742 |
+
"grad_norm": 0.4829014539718628,
|
| 743 |
+
"learning_rate": 4.920973717689495e-06,
|
| 744 |
+
"loss": 0.0917883038520813,
|
| 745 |
+
"step": 910,
|
| 746 |
+
"token_acc": 0.9649694993054297
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.38763197586727,
|
| 750 |
+
"grad_norm": 0.5397462248802185,
|
| 751 |
+
"learning_rate": 4.707627746799517e-06,
|
| 752 |
+
"loss": 0.09063017964363099,
|
| 753 |
+
"step": 920,
|
| 754 |
+
"token_acc": 0.9644550868409186
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.4027149321266967,
|
| 758 |
+
"grad_norm": 0.446719229221344,
|
| 759 |
+
"learning_rate": 4.497576933080677e-06,
|
| 760 |
+
"loss": 0.09249653816223144,
|
| 761 |
+
"step": 930,
|
| 762 |
+
"token_acc": 0.963393705372192
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.4177978883861238,
|
| 766 |
+
"grad_norm": 0.38629722595214844,
|
| 767 |
+
"learning_rate": 4.290952059178644e-06,
|
| 768 |
+
"loss": 0.09290457963943481,
|
| 769 |
+
"step": 940,
|
| 770 |
+
"token_acc": 0.9633827640695272
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.4328808446455505,
|
| 774 |
+
"grad_norm": 0.5298126339912415,
|
| 775 |
+
"learning_rate": 4.087881774667258e-06,
|
| 776 |
+
"loss": 0.09557251930236817,
|
| 777 |
+
"step": 950,
|
| 778 |
+
"token_acc": 0.9631715835624582
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.4479638009049773,
|
| 782 |
+
"grad_norm": 0.3959716856479645,
|
| 783 |
+
"learning_rate": 3.888492515948241e-06,
|
| 784 |
+
"loss": 0.09034661054611207,
|
| 785 |
+
"step": 960,
|
| 786 |
+
"token_acc": 0.964851074293794
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.4630467571644044,
|
| 790 |
+
"grad_norm": 0.39855247735977173,
|
| 791 |
+
"learning_rate": 3.692908427528866e-06,
|
| 792 |
+
"loss": 0.08885170221328735,
|
| 793 |
+
"step": 970,
|
| 794 |
+
"token_acc": 0.9658355310477104
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.4781297134238311,
|
| 798 |
+
"grad_norm": 0.38074812293052673,
|
| 799 |
+
"learning_rate": 3.5012512847266435e-06,
|
| 800 |
+
"loss": 0.08835339546203613,
|
| 801 |
+
"step": 980,
|
| 802 |
+
"token_acc": 0.9653404148161714
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.493212669683258,
|
| 806 |
+
"grad_norm": 0.46875646710395813,
|
| 807 |
+
"learning_rate": 3.313640417849107e-06,
|
| 808 |
+
"loss": 0.09411121010780335,
|
| 809 |
+
"step": 990,
|
| 810 |
+
"token_acc": 0.963810409758586
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.5082956259426847,
|
| 814 |
+
"grad_norm": 0.540631890296936,
|
| 815 |
+
"learning_rate": 3.130192637895888e-06,
|
| 816 |
+
"loss": 0.09138602018356323,
|
| 817 |
+
"step": 1000,
|
| 818 |
+
"token_acc": 0.9636740152724449
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.5233785822021115,
|
| 822 |
+
"grad_norm": 0.5243298411369324,
|
| 823 |
+
"learning_rate": 2.9510221638294378e-06,
|
| 824 |
+
"loss": 0.09415959119796753,
|
| 825 |
+
"step": 1010,
|
| 826 |
+
"token_acc": 0.9632957660676211
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.5384615384615383,
|
| 830 |
+
"grad_norm": 0.4213015139102936,
|
| 831 |
+
"learning_rate": 2.776240551459558e-06,
|
| 832 |
+
"loss": 0.08891291618347168,
|
| 833 |
+
"step": 1020,
|
| 834 |
+
"token_acc": 0.9648928840391611
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.5535444947209653,
|
| 838 |
+
"grad_norm": 0.46009889245033264,
|
| 839 |
+
"learning_rate": 2.6059566239861e-06,
|
| 840 |
+
"loss": 0.08925861120223999,
|
| 841 |
+
"step": 1030,
|
| 842 |
+
"token_acc": 0.9647288759601836
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.5686274509803921,
|
| 846 |
+
"grad_norm": 0.48863378167152405,
|
| 847 |
+
"learning_rate": 2.4402764042430317e-06,
|
| 848 |
+
"loss": 0.08919482231140137,
|
| 849 |
+
"step": 1040,
|
| 850 |
+
"token_acc": 0.9651635934592869
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.5837104072398192,
|
| 854 |
+
"grad_norm": 0.535592257976532,
|
| 855 |
+
"learning_rate": 2.2793030486861212e-06,
|
| 856 |
+
"loss": 0.08794163465499878,
|
| 857 |
+
"step": 1050,
|
| 858 |
+
"token_acc": 0.9659154613745936
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.598793363499246,
|
| 862 |
+
"grad_norm": 0.49713340401649475,
|
| 863 |
+
"learning_rate": 2.1231367831652415e-06,
|
| 864 |
+
"loss": 0.08887355327606201,
|
| 865 |
+
"step": 1060,
|
| 866 |
+
"token_acc": 0.9647955384444762
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.6138763197586727,
|
| 870 |
+
"grad_norm": 0.3400653898715973,
|
| 871 |
+
"learning_rate": 1.971874840521374e-06,
|
| 872 |
+
"loss": 0.09162210822105407,
|
| 873 |
+
"step": 1070,
|
| 874 |
+
"token_acc": 0.96406639508725
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.6289592760180995,
|
| 878 |
+
"grad_norm": 0.44764232635498047,
|
| 879 |
+
"learning_rate": 1.825611400047126e-06,
|
| 880 |
+
"loss": 0.09081205129623413,
|
| 881 |
+
"step": 1080,
|
| 882 |
+
"token_acc": 0.9648421603395152
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.6440422322775263,
|
| 886 |
+
"grad_norm": 0.3386666178703308,
|
| 887 |
+
"learning_rate": 1.684437528848456e-06,
|
| 888 |
+
"loss": 0.08757848739624023,
|
| 889 |
+
"step": 1090,
|
| 890 |
+
"token_acc": 0.965227225664633
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.6591251885369531,
|
| 894 |
+
"grad_norm": 0.41909298300743103,
|
| 895 |
+
"learning_rate": 1.5484411251441234e-06,
|
| 896 |
+
"loss": 0.08880707025527954,
|
| 897 |
+
"step": 1100,
|
| 898 |
+
"token_acc": 0.9646852985864911
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.6742081447963801,
|
| 902 |
+
"grad_norm": 0.4352640211582184,
|
| 903 |
+
"learning_rate": 1.4177068635381575e-06,
|
| 904 |
+
"loss": 0.08535876274108886,
|
| 905 |
+
"step": 1110,
|
| 906 |
+
"token_acc": 0.9665068649512442
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.689291101055807,
|
| 910 |
+
"grad_norm": 0.3794000744819641,
|
| 911 |
+
"learning_rate": 1.2923161422994302e-06,
|
| 912 |
+
"loss": 0.09240926504135132,
|
| 913 |
+
"step": 1120,
|
| 914 |
+
"token_acc": 0.9636572421712548
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.704374057315234,
|
| 918 |
+
"grad_norm": 0.35188183188438416,
|
| 919 |
+
"learning_rate": 1.1723470326811582e-06,
|
| 920 |
+
"loss": 0.08627489805221558,
|
| 921 |
+
"step": 1130,
|
| 922 |
+
"token_acc": 0.9659923592409344
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.7194570135746607,
|
| 926 |
+
"grad_norm": 0.446426123380661,
|
| 927 |
+
"learning_rate": 1.0578742303118695e-06,
|
| 928 |
+
"loss": 0.09179290533065795,
|
| 929 |
+
"step": 1140,
|
| 930 |
+
"token_acc": 0.9638420618865663
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.7345399698340875,
|
| 934 |
+
"grad_norm": 0.3761591613292694,
|
| 935 |
+
"learning_rate": 9.489690086881321e-07,
|
| 936 |
+
"loss": 0.08692222833633423,
|
| 937 |
+
"step": 1150,
|
| 938 |
+
"token_acc": 0.9657407263152975
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.7496229260935143,
|
| 942 |
+
"grad_norm": 0.49052301049232483,
|
| 943 |
+
"learning_rate": 8.456991747979782e-07,
|
| 944 |
+
"loss": 0.089877450466156,
|
| 945 |
+
"step": 1160,
|
| 946 |
+
"token_acc": 0.9652767450852096
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.7647058823529411,
|
| 950 |
+
"grad_norm": 0.41365307569503784,
|
| 951 |
+
"learning_rate": 7.48129026902642e-07,
|
| 952 |
+
"loss": 0.08901469707489014,
|
| 953 |
+
"step": 1170,
|
| 954 |
+
"token_acc": 0.9654412454281159
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.779788838612368,
|
| 958 |
+
"grad_norm": 0.4520035982131958,
|
| 959 |
+
"learning_rate": 6.563193145029423e-07,
|
| 960 |
+
"loss": 0.09040895104408264,
|
| 961 |
+
"step": 1180,
|
| 962 |
+
"token_acc": 0.9646702238499668
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7948717948717947,
|
| 966 |
+
"grad_norm": 0.4278804361820221,
|
| 967 |
+
"learning_rate": 5.703272005151905e-07,
|
| 968 |
+
"loss": 0.08340400457382202,
|
| 969 |
+
"step": 1190,
|
| 970 |
+
"token_acc": 0.9672215853126866
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.8099547511312217,
|
| 974 |
+
"grad_norm": 0.43313461542129517,
|
| 975 |
+
"learning_rate": 4.902062256801954e-07,
|
| 976 |
+
"loss": 0.08683132529258727,
|
| 977 |
+
"step": 1200,
|
| 978 |
+
"token_acc": 0.9662295699093391
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.8250377073906485,
|
| 982 |
+
"grad_norm": 0.32996904850006104,
|
| 983 |
+
"learning_rate": 4.1600627522751624e-07,
|
| 984 |
+
"loss": 0.08770017027854919,
|
| 985 |
+
"step": 1210,
|
| 986 |
+
"token_acc": 0.9661082315191905
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.8401206636500755,
|
| 990 |
+
"grad_norm": 0.4273052513599396,
|
| 991 |
+
"learning_rate": 3.477735478157429e-07,
|
| 992 |
+
"loss": 0.08336774706840515,
|
| 993 |
+
"step": 1220,
|
| 994 |
+
"token_acc": 0.9679050340734228
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.8552036199095023,
|
| 998 |
+
"grad_norm": 0.3404141068458557,
|
| 999 |
+
"learning_rate": 2.855505267680947e-07,
|
| 1000 |
+
"loss": 0.09096280932426452,
|
| 1001 |
+
"step": 1230,
|
| 1002 |
+
"token_acc": 0.9640440692174121
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.8702865761689291,
|
| 1006 |
+
"grad_norm": 0.4492412805557251,
|
| 1007 |
+
"learning_rate": 2.2937595362129805e-07,
|
| 1008 |
+
"loss": 0.08709906935691833,
|
| 1009 |
+
"step": 1240,
|
| 1010 |
+
"token_acc": 0.9661851711983888
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.885369532428356,
|
| 1014 |
+
"grad_norm": 0.39498382806777954,
|
| 1015 |
+
"learning_rate": 1.7928480400417837e-07,
|
| 1016 |
+
"loss": 0.08509960174560546,
|
| 1017 |
+
"step": 1250,
|
| 1018 |
+
"token_acc": 0.9664054460539856
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.9004524886877827,
|
| 1022 |
+
"grad_norm": 0.4895835518836975,
|
| 1023 |
+
"learning_rate": 1.3530826586100276e-07,
|
| 1024 |
+
"loss": 0.0855100154876709,
|
| 1025 |
+
"step": 1260,
|
| 1026 |
+
"token_acc": 0.9667
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.9155354449472095,
|
| 1030 |
+
"grad_norm": 0.37063419818878174,
|
| 1031 |
+
"learning_rate": 9.747372003312106e-08,
|
| 1032 |
+
"loss": 0.08988954424858094,
|
| 1033 |
+
"step": 1270,
|
| 1034 |
+
"token_acc": 0.9651437057744388
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.9306184012066365,
|
| 1038 |
+
"grad_norm": 0.37928536534309387,
|
| 1039 |
+
"learning_rate": 6.580472321099928e-08,
|
| 1040 |
+
"loss": 0.09078261852264405,
|
| 1041 |
+
"step": 1280,
|
| 1042 |
+
"token_acc": 0.9638408813108261
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.9457013574660633,
|
| 1046 |
+
"grad_norm": 0.4147525429725647,
|
| 1047 |
+
"learning_rate": 4.0320993267264354e-08,
|
| 1048 |
+
"loss": 0.08869935870170594,
|
| 1049 |
+
"step": 1290,
|
| 1050 |
+
"token_acc": 0.9655277072251242
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.9607843137254903,
|
| 1054 |
+
"grad_norm": 0.39682766795158386,
|
| 1055 |
+
"learning_rate": 2.1038396979884414e-08,
|
| 1056 |
+
"loss": 0.08754374980926513,
|
| 1057 |
+
"step": 1300,
|
| 1058 |
+
"token_acc": 0.9651909735342573
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.9758672699849171,
|
| 1062 |
+
"grad_norm": 0.39889928698539734,
|
| 1063 |
+
"learning_rate": 7.968940153136872e-09,
|
| 1064 |
+
"loss": 0.0862058699131012,
|
| 1065 |
+
"step": 1310,
|
| 1066 |
+
"token_acc": 0.9660498767487274
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.990950226244344,
|
| 1070 |
+
"grad_norm": 0.38509562611579895,
|
| 1071 |
+
"learning_rate": 1.1207601425078375e-09,
|
| 1072 |
+
"loss": 0.08868761658668518,
|
| 1073 |
+
"step": 1320,
|
| 1074 |
+
"token_acc": 0.9653918684468583
|
| 1075 |
+
}
|
| 1076 |
+
],
|
| 1077 |
+
"logging_steps": 10,
|
| 1078 |
+
"max_steps": 1326,
|
| 1079 |
+
"num_input_tokens_seen": 0,
|
| 1080 |
+
"num_train_epochs": 2,
|
| 1081 |
+
"save_steps": 500,
|
| 1082 |
+
"stateful_callbacks": {
|
| 1083 |
+
"TrainerControl": {
|
| 1084 |
+
"args": {
|
| 1085 |
+
"should_epoch_stop": false,
|
| 1086 |
+
"should_evaluate": false,
|
| 1087 |
+
"should_log": false,
|
| 1088 |
+
"should_save": true,
|
| 1089 |
+
"should_training_stop": true
|
| 1090 |
+
},
|
| 1091 |
+
"attributes": {}
|
| 1092 |
+
}
|
| 1093 |
+
},
|
| 1094 |
+
"total_flos": 7.840189747375899e+18,
|
| 1095 |
+
"train_batch_size": 2,
|
| 1096 |
+
"trial_name": null,
|
| 1097 |
+
"trial_params": null
|
| 1098 |
+
}
|