Upload CamSFT-8B (checkpoint-1326)
Browse files- .gitattributes +1 -0
- README.md +24 -0
- args.json +382 -0
- chat_template.jinja +120 -0
- config.json +70 -0
- generation_config.json +14 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +758 -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-8B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- camera-movement
|
| 6 |
+
- video-understanding
|
| 7 |
+
- qwen3-vl
|
| 8 |
+
- sft
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# CamSFT-8B
|
| 12 |
+
|
| 13 |
+
Camera-movement SFT 微调模型，基于 `Qwen/Qwen3-VL-8B-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-8B", torch_dtype="bfloat16", device_map="auto")
|
| 23 |
+
processor = AutoProcessor.from_pretrained("ddz16/CamSFT-8B")
|
| 24 |
+
```
|
args.json
ADDED
|
@@ -0,0 +1,382 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/group/40009/dazhaodu/ms-swift/output/camera_sft_qwen3vl_8b/v0-20260708-112218",
|
| 3 |
+
"per_device_train_batch_size": 2,
|
| 4 |
+
"num_train_epochs": 2.0,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"learning_rate": 1.5e-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_8b/v0-20260708-112218",
|
| 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_8b/v0-20260708-112218/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-8B-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-8B-Instruct",
|
| 374 |
+
"model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/apdcephfs_gy2/share_303094921/hunyuan/yujiazhang/dazhaodu/hf/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=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-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
|
| 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_8b/v0-20260708-112218', per_device_train_batch_size=2, num_train_epochs=2.0, max_steps=-1, learning_rate=1.5e-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_8b/v0-20260708-112218', 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_8b/v0-20260708-112218/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 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_size": 4096,
|
| 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": 4096,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 12288,
|
| 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 |
+
"use_cache": false,
|
| 41 |
+
"vocab_size": 151936
|
| 42 |
+
},
|
| 43 |
+
"tie_word_embeddings": false,
|
| 44 |
+
"transformers_version": "5.8.1",
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"video_token_id": 151656,
|
| 47 |
+
"vision_config": {
|
| 48 |
+
"deepstack_visual_indexes": [
|
| 49 |
+
8,
|
| 50 |
+
16,
|
| 51 |
+
24
|
| 52 |
+
],
|
| 53 |
+
"depth": 27,
|
| 54 |
+
"dtype": "bfloat16",
|
| 55 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 56 |
+
"hidden_size": 1152,
|
| 57 |
+
"in_channels": 3,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 4304,
|
| 60 |
+
"model_type": "qwen3_vl_vision",
|
| 61 |
+
"num_heads": 16,
|
| 62 |
+
"num_position_embeddings": 2304,
|
| 63 |
+
"out_hidden_size": 4096,
|
| 64 |
+
"patch_size": 16,
|
| 65 |
+
"spatial_merge_size": 2,
|
| 66 |
+
"temporal_patch_size": 2
|
| 67 |
+
},
|
| 68 |
+
"vision_end_token_id": 151653,
|
| 69 |
+
"vision_start_token_id": 151652
|
| 70 |
+
}
|
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-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27e17af7a636836b1ce8c050ec5858e5a5948e4c34c091f3df2fd6f893e06409
|
| 3 |
+
size 4905357176
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dee986b69dc8219eeeced7744bb9cbc9dcd6c5e9cdb1d339e65018fbb3b32ef1
|
| 3 |
+
size 4915962456
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b679e30779cbde18bb576ac3db8376cac572e36d71085f1db13034cf444a76e
|
| 3 |
+
size 4974674312
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81ac099ee6595407433c820d98e46172de89285ba2d4e4fc1746be2fc1f8c638
|
| 3 |
+
size 2738345504
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,758 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8767123696,
|
| 4 |
+
"total_size": 17534247392
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 409 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 413 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 417 |
+
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 421 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 425 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 429 |
+
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
| 730 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 731 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 732 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 733 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 734 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00004-of-00004.safetensors",
|
| 735 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00004-of-00004.safetensors",
|
| 736 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 737 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 738 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 739 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 740 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00004-of-00004.safetensors",
|
| 741 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00004-of-00004.safetensors",
|
| 742 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 743 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 744 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 745 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 746 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00004-of-00004.safetensors",
|
| 747 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00004-of-00004.safetensors",
|
| 748 |
+
"model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 749 |
+
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 750 |
+
"model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 751 |
+
"model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 752 |
+
"model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
|
| 753 |
+
"model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
|
| 754 |
+
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
| 755 |
+
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
| 756 |
+
"model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
|
| 757 |
+
}
|
| 758 |
+
}
|
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": 29.815479278564453,
|
| 15 |
+
"learning_rate": 2.2388059701492537e-07,
|
| 16 |
+
"loss": 0.9120703339576721,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.8818734015345269
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.015082956259426848,
|
| 22 |
+
"grad_norm": 12.396344184875488,
|
| 23 |
+
"learning_rate": 2.2388059701492535e-06,
|
| 24 |
+
"loss": 0.7334412468804253,
|
| 25 |
+
"step": 10,
|
| 26 |
+
"token_acc": 0.8877795797013311
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.030165912518853696,
|
| 30 |
+
"grad_norm": 2.1095762252807617,
|
| 31 |
+
"learning_rate": 4.477611940298507e-06,
|
| 32 |
+
"loss": 0.22399492263793946,
|
| 33 |
+
"step": 20,
|
| 34 |
+
"token_acc": 0.9162146601618133
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.04524886877828054,
|
| 38 |
+
"grad_norm": 1.1608413457870483,
|
| 39 |
+
"learning_rate": 6.716417910447762e-06,
|
| 40 |
+
"loss": 0.16365647315979004,
|
| 41 |
+
"step": 30,
|
| 42 |
+
"token_acc": 0.9324771509612354
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.06033182503770739,
|
| 46 |
+
"grad_norm": 0.7096361517906189,
|
| 47 |
+
"learning_rate": 8.955223880597014e-06,
|
| 48 |
+
"loss": 0.1502757787704468,
|
| 49 |
+
"step": 40,
|
| 50 |
+
"token_acc": 0.9384272679242049
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.07541478129713423,
|
| 54 |
+
"grad_norm": 0.8093337416648865,
|
| 55 |
+
"learning_rate": 1.119402985074627e-05,
|
| 56 |
+
"loss": 0.1409849166870117,
|
| 57 |
+
"step": 50,
|
| 58 |
+
"token_acc": 0.943997583773129
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09049773755656108,
|
| 62 |
+
"grad_norm": 0.8115042448043823,
|
| 63 |
+
"learning_rate": 1.3432835820895523e-05,
|
| 64 |
+
"loss": 0.13948071002960205,
|
| 65 |
+
"step": 60,
|
| 66 |
+
"token_acc": 0.9437285085323135
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.10558069381598793,
|
| 70 |
+
"grad_norm": 0.9792377948760986,
|
| 71 |
+
"learning_rate": 1.4999789854529206e-05,
|
| 72 |
+
"loss": 0.13599691390991211,
|
| 73 |
+
"step": 70,
|
| 74 |
+
"token_acc": 0.9456004846281993
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.12066365007541478,
|
| 78 |
+
"grad_norm": 0.9598162174224854,
|
| 79 |
+
"learning_rate": 1.4996054262643387e-05,
|
| 80 |
+
"loss": 0.13396866321563722,
|
| 81 |
+
"step": 80,
|
| 82 |
+
"token_acc": 0.9470223855769079
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.13574660633484162,
|
| 86 |
+
"grad_norm": 0.8766047358512878,
|
| 87 |
+
"learning_rate": 1.498765144861652e-05,
|
| 88 |
+
"loss": 0.13383805751800537,
|
| 89 |
+
"step": 90,
|
| 90 |
+
"token_acc": 0.9467140586100363
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.15082956259426847,
|
| 94 |
+
"grad_norm": 0.6658370494842529,
|
| 95 |
+
"learning_rate": 1.4974586644241e-05,
|
| 96 |
+
"loss": 0.1294718623161316,
|
| 97 |
+
"step": 100,
|
| 98 |
+
"token_acc": 0.9488610561781293
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.16591251885369532,
|
| 102 |
+
"grad_norm": 0.7449970245361328,
|
| 103 |
+
"learning_rate": 1.4956867983975587e-05,
|
| 104 |
+
"loss": 0.1265101194381714,
|
| 105 |
+
"step": 110,
|
| 106 |
+
"token_acc": 0.9505024772205117
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.18099547511312217,
|
| 110 |
+
"grad_norm": 0.9009830355644226,
|
| 111 |
+
"learning_rate": 1.493450649988069e-05,
|
| 112 |
+
"loss": 0.12676594257354737,
|
| 113 |
+
"step": 120,
|
| 114 |
+
"token_acc": 0.9508201932858596
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.19607843137254902,
|
| 118 |
+
"grad_norm": 0.6432599425315857,
|
| 119 |
+
"learning_rate": 1.4907516114749562e-05,
|
| 120 |
+
"loss": 0.1273956298828125,
|
| 121 |
+
"step": 130,
|
| 122 |
+
"token_acc": 0.9494921556877026
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.21116138763197587,
|
| 126 |
+
"grad_norm": 0.698387861251831,
|
| 127 |
+
"learning_rate": 1.487591363343962e-05,
|
| 128 |
+
"loss": 0.12959996461868287,
|
| 129 |
+
"step": 140,
|
| 130 |
+
"token_acc": 0.9489460940865406
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.22624434389140272,
|
| 134 |
+
"grad_norm": 0.7407552599906921,
|
| 135 |
+
"learning_rate": 1.4839718732409347e-05,
|
| 136 |
+
"loss": 0.12531228065490724,
|
| 137 |
+
"step": 150,
|
| 138 |
+
"token_acc": 0.9505425260504718
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.24132730015082957,
|
| 142 |
+
"grad_norm": 0.6289209127426147,
|
| 143 |
+
"learning_rate": 1.4798953947467258e-05,
|
| 144 |
+
"loss": 0.1264174222946167,
|
| 145 |
+
"step": 160,
|
| 146 |
+
"token_acc": 0.9510897650241663
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.2564102564102564,
|
| 150 |
+
"grad_norm": 0.5078371167182922,
|
| 151 |
+
"learning_rate": 1.4753644659740567e-05,
|
| 152 |
+
"loss": 0.12367002964019776,
|
| 153 |
+
"step": 170,
|
| 154 |
+
"token_acc": 0.9527126937910639
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.27149321266968324,
|
| 158 |
+
"grad_norm": 0.6037768721580505,
|
| 159 |
+
"learning_rate": 1.4703819079872297e-05,
|
| 160 |
+
"loss": 0.12230026721954346,
|
| 161 |
+
"step": 180,
|
| 162 |
+
"token_acc": 0.9514374689714311
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.2865761689291101,
|
| 166 |
+
"grad_norm": 1.126369595527649,
|
| 167 |
+
"learning_rate": 1.4649508230456655e-05,
|
| 168 |
+
"loss": 0.12020505666732788,
|
| 169 |
+
"step": 190,
|
| 170 |
+
"token_acc": 0.9517103550845882
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.30165912518853694,
|
| 174 |
+
"grad_norm": 0.706250786781311,
|
| 175 |
+
"learning_rate": 1.459074592672363e-05,
|
| 176 |
+
"loss": 0.12032895088195801,
|
| 177 |
+
"step": 200,
|
| 178 |
+
"token_acc": 0.9516314228303512
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3167420814479638,
|
| 182 |
+
"grad_norm": 17.569059371948242,
|
| 183 |
+
"learning_rate": 1.4527568755484822e-05,
|
| 184 |
+
"loss": 0.12428458929061889,
|
| 185 |
+
"step": 210,
|
| 186 |
+
"token_acc": 0.9539214311314728
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.33182503770739064,
|
| 190 |
+
"grad_norm": 0.7467140555381775,
|
| 191 |
+
"learning_rate": 1.4460016052353615e-05,
|
| 192 |
+
"loss": 0.11901211738586426,
|
| 193 |
+
"step": 220,
|
| 194 |
+
"token_acc": 0.9542842215256009
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.3469079939668175,
|
| 198 |
+
"grad_norm": 0.8222630620002747,
|
| 199 |
+
"learning_rate": 1.43881298772539e-05,
|
| 200 |
+
"loss": 0.11689404249191285,
|
| 201 |
+
"step": 230,
|
| 202 |
+
"token_acc": 0.9536877379054559
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.36199095022624433,
|
| 206 |
+
"grad_norm": 0.5848267674446106,
|
| 207 |
+
"learning_rate": 1.4311954988232549e-05,
|
| 208 |
+
"loss": 0.1140936017036438,
|
| 209 |
+
"step": 240,
|
| 210 |
+
"token_acc": 0.9551059271601999
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.3770739064856712,
|
| 214 |
+
"grad_norm": 0.4587470591068268,
|
| 215 |
+
"learning_rate": 1.4231538813591998e-05,
|
| 216 |
+
"loss": 0.11686046123504638,
|
| 217 |
+
"step": 250,
|
| 218 |
+
"token_acc": 0.9549980476376415
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.39215686274509803,
|
| 222 |
+
"grad_norm": 0.8135445713996887,
|
| 223 |
+
"learning_rate": 1.4146931422360251e-05,
|
| 224 |
+
"loss": 0.1165614128112793,
|
| 225 |
+
"step": 260,
|
| 226 |
+
"token_acc": 0.9541351915539069
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4072398190045249,
|
| 230 |
+
"grad_norm": 0.6098634004592896,
|
| 231 |
+
"learning_rate": 1.4058185493116703e-05,
|
| 232 |
+
"loss": 0.11796810626983642,
|
| 233 |
+
"step": 270,
|
| 234 |
+
"token_acc": 0.9544430810332241
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.42232277526395173,
|
| 238 |
+
"grad_norm": 0.6988653540611267,
|
| 239 |
+
"learning_rate": 1.396535628119321e-05,
|
| 240 |
+
"loss": 0.11589565277099609,
|
| 241 |
+
"step": 280,
|
| 242 |
+
"token_acc": 0.9535664210494914
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.4374057315233786,
|
| 246 |
+
"grad_norm": 0.5857917070388794,
|
| 247 |
+
"learning_rate": 1.3868501584270802e-05,
|
| 248 |
+
"loss": 0.1144603967666626,
|
| 249 |
+
"step": 290,
|
| 250 |
+
"token_acc": 0.9557559372521086
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.45248868778280543,
|
| 254 |
+
"grad_norm": 0.5581201910972595,
|
| 255 |
+
"learning_rate": 1.3767681706393457e-05,
|
| 256 |
+
"loss": 0.11729376316070557,
|
| 257 |
+
"step": 300,
|
| 258 |
+
"token_acc": 0.9539887259097483
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.4675716440422323,
|
| 262 |
+
"grad_norm": 0.634107232093811,
|
| 263 |
+
"learning_rate": 1.3662959420421375e-05,
|
| 264 |
+
"loss": 0.1152184247970581,
|
| 265 |
+
"step": 310,
|
| 266 |
+
"token_acc": 0.9554923666443647
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.48265460030165913,
|
| 270 |
+
"grad_norm": 0.7922980785369873,
|
| 271 |
+
"learning_rate": 1.35543999289471e-05,
|
| 272 |
+
"loss": 0.11476943492889405,
|
| 273 |
+
"step": 320,
|
| 274 |
+
"token_acc": 0.955084578023417
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.497737556561086,
|
| 278 |
+
"grad_norm": 0.49707281589508057,
|
| 279 |
+
"learning_rate": 1.3442070823698822e-05,
|
| 280 |
+
"loss": 0.11693618297576905,
|
| 281 |
+
"step": 330,
|
| 282 |
+
"token_acc": 0.954469228143597
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5128205128205128,
|
| 286 |
+
"grad_norm": 0.5565932989120483,
|
| 287 |
+
"learning_rate": 1.332604204345616e-05,
|
| 288 |
+
"loss": 0.11409028768539428,
|
| 289 |
+
"step": 340,
|
| 290 |
+
"token_acc": 0.9557340869758506
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5279034690799397,
|
| 294 |
+
"grad_norm": 0.7205259799957275,
|
| 295 |
+
"learning_rate": 1.3206385830504614e-05,
|
| 296 |
+
"loss": 0.11583917140960694,
|
| 297 |
+
"step": 350,
|
| 298 |
+
"token_acc": 0.9547551099112996
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.5429864253393665,
|
| 302 |
+
"grad_norm": 0.6330074071884155,
|
| 303 |
+
"learning_rate": 1.3083176685655786e-05,
|
| 304 |
+
"loss": 0.11165814399719239,
|
| 305 |
+
"step": 360,
|
| 306 |
+
"token_acc": 0.9570610839166415
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.5580693815987934,
|
| 310 |
+
"grad_norm": 0.5063838958740234,
|
| 311 |
+
"learning_rate": 1.295649132186141e-05,
|
| 312 |
+
"loss": 0.11352043151855469,
|
| 313 |
+
"step": 370,
|
| 314 |
+
"token_acc": 0.9562457422431412
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.5731523378582202,
|
| 318 |
+
"grad_norm": 0.4470171332359314,
|
| 319 |
+
"learning_rate": 1.2826408616450027e-05,
|
| 320 |
+
"loss": 0.11494969129562378,
|
| 321 |
+
"step": 380,
|
| 322 |
+
"token_acc": 0.9556565656565656
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.5882352941176471,
|
| 326 |
+
"grad_norm": 0.5665348768234253,
|
| 327 |
+
"learning_rate": 1.2693009562016084e-05,
|
| 328 |
+
"loss": 0.11389807462692261,
|
| 329 |
+
"step": 390,
|
| 330 |
+
"token_acc": 0.9554707753947679
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.6033182503770739,
|
| 334 |
+
"grad_norm": 0.5819860696792603,
|
| 335 |
+
"learning_rate": 1.2556377215992019e-05,
|
| 336 |
+
"loss": 0.11242160797119141,
|
| 337 |
+
"step": 400,
|
| 338 |
+
"token_acc": 0.9572872256434549
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6184012066365008,
|
| 342 |
+
"grad_norm": 0.6842740178108215,
|
| 343 |
+
"learning_rate": 1.2416596648934716e-05,
|
| 344 |
+
"loss": 0.11078722476959228,
|
| 345 |
+
"step": 410,
|
| 346 |
+
"token_acc": 0.9570846029075144
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6334841628959276,
|
| 350 |
+
"grad_norm": 0.6340636014938354,
|
| 351 |
+
"learning_rate": 1.2273754891558542e-05,
|
| 352 |
+
"loss": 0.11188424825668335,
|
| 353 |
+
"step": 420,
|
| 354 |
+
"token_acc": 0.9564591028214992
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.6485671191553545,
|
| 358 |
+
"grad_norm": 0.7150080800056458,
|
| 359 |
+
"learning_rate": 1.212794088054797e-05,
|
| 360 |
+
"loss": 0.11114382743835449,
|
| 361 |
+
"step": 430,
|
| 362 |
+
"token_acc": 0.9571518106914105
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.6636500754147813,
|
| 366 |
+
"grad_norm": 0.6401362419128418,
|
| 367 |
+
"learning_rate": 1.1979245403183451e-05,
|
| 368 |
+
"loss": 0.10850663185119629,
|
| 369 |
+
"step": 440,
|
| 370 |
+
"token_acc": 0.9578280044101434
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.6787330316742082,
|
| 374 |
+
"grad_norm": 0.3908592164516449,
|
| 375 |
+
"learning_rate": 1.182776104081511e-05,
|
| 376 |
+
"loss": 0.10802350044250489,
|
| 377 |
+
"step": 450,
|
| 378 |
+
"token_acc": 0.9573075771188979
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.693815987933635,
|
| 382 |
+
"grad_norm": 0.5129520893096924,
|
| 383 |
+
"learning_rate": 1.167358211121938e-05,
|
| 384 |
+
"loss": 0.10646429061889648,
|
| 385 |
+
"step": 460,
|
| 386 |
+
"token_acc": 0.9588181522395922
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.7088989441930619,
|
| 390 |
+
"grad_norm": 0.5238049626350403,
|
| 391 |
+
"learning_rate": 1.1516804609874507e-05,
|
| 392 |
+
"loss": 0.11202960014343262,
|
| 393 |
+
"step": 470,
|
| 394 |
+
"token_acc": 0.9568884020347834
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7239819004524887,
|
| 398 |
+
"grad_norm": 0.6929338574409485,
|
| 399 |
+
"learning_rate": 1.1357526150191471e-05,
|
| 400 |
+
"loss": 0.10924453735351562,
|
| 401 |
+
"step": 480,
|
| 402 |
+
"token_acc": 0.9574212846838145
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7390648567119156,
|
| 406 |
+
"grad_norm": 0.47621390223503113,
|
| 407 |
+
"learning_rate": 1.1195845902737558e-05,
|
| 408 |
+
"loss": 0.11051700115203858,
|
| 409 |
+
"step": 490,
|
| 410 |
+
"token_acc": 0.9569450689157971
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.7541478129713424,
|
| 414 |
+
"grad_norm": 0.5051868557929993,
|
| 415 |
+
"learning_rate": 1.1031864533490397e-05,
|
| 416 |
+
"loss": 0.10972610712051392,
|
| 417 |
+
"step": 500,
|
| 418 |
+
"token_acc": 0.957463275464368
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.7692307692307693,
|
| 422 |
+
"grad_norm": 0.5780250430107117,
|
| 423 |
+
"learning_rate": 1.0865684141160912e-05,
|
| 424 |
+
"loss": 0.10704238414764404,
|
| 425 |
+
"step": 510,
|
| 426 |
+
"token_acc": 0.9587042036251446
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.7843137254901961,
|
| 430 |
+
"grad_norm": 0.5643448233604431,
|
| 431 |
+
"learning_rate": 1.0697408193624248e-05,
|
| 432 |
+
"loss": 0.10957627296447754,
|
| 433 |
+
"step": 520,
|
| 434 |
+
"token_acc": 0.9574098818903685
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.799396681749623,
|
| 438 |
+
"grad_norm": 0.5077806115150452,
|
| 439 |
+
"learning_rate": 1.0527141463498186e-05,
|
| 440 |
+
"loss": 0.10917415618896484,
|
| 441 |
+
"step": 530,
|
| 442 |
+
"token_acc": 0.9577429299816209
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.8144796380090498,
|
| 446 |
+
"grad_norm": 0.3003750145435333,
|
| 447 |
+
"learning_rate": 1.0354989962909223e-05,
|
| 448 |
+
"loss": 0.1055147409439087,
|
| 449 |
+
"step": 540,
|
| 450 |
+
"token_acc": 0.9590716835170364
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.8295625942684767,
|
| 454 |
+
"grad_norm": 0.3721616566181183,
|
| 455 |
+
"learning_rate": 1.0181060877486896e-05,
|
| 456 |
+
"loss": 0.1066395878791809,
|
| 457 |
+
"step": 550,
|
| 458 |
+
"token_acc": 0.9577666855964372
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8446455505279035,
|
| 462 |
+
"grad_norm": 0.6667331457138062,
|
| 463 |
+
"learning_rate": 1.0005462499627443e-05,
|
| 464 |
+
"loss": 0.10366250276565551,
|
| 465 |
+
"step": 560,
|
| 466 |
+
"token_acc": 0.9599628167911544
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.8597285067873304,
|
| 470 |
+
"grad_norm": 0.5545596480369568,
|
| 471 |
+
"learning_rate": 9.82830416106839e-06,
|
| 472 |
+
"loss": 0.10734113454818725,
|
| 473 |
+
"step": 570,
|
| 474 |
+
"token_acc": 0.9578964143426295
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8748114630467572,
|
| 478 |
+
"grad_norm": 0.43999919295310974,
|
| 479 |
+
"learning_rate": 9.649696164815983e-06,
|
| 480 |
+
"loss": 0.1027806282043457,
|
| 481 |
+
"step": 580,
|
| 482 |
+
"token_acc": 0.9604619208620876
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.889894419306184,
|
| 486 |
+
"grad_norm": 0.4688698649406433,
|
| 487 |
+
"learning_rate": 9.469749716467922e-06,
|
| 488 |
+
"loss": 0.10514171123504638,
|
| 489 |
+
"step": 590,
|
| 490 |
+
"token_acc": 0.9594212797665249
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.9049773755656109,
|
| 494 |
+
"grad_norm": 0.40809348225593567,
|
| 495 |
+
"learning_rate": 9.288576854974107e-06,
|
| 496 |
+
"loss": 0.10727782249450683,
|
| 497 |
+
"step": 600,
|
| 498 |
+
"token_acc": 0.9590070037556371
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.9200603318250377,
|
| 502 |
+
"grad_norm": 0.49828872084617615,
|
| 503 |
+
"learning_rate": 9.106290382878496e-06,
|
| 504 |
+
"loss": 0.10498321056365967,
|
| 505 |
+
"step": 610,
|
| 506 |
+
"token_acc": 0.9591861672878352
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9351432880844646,
|
| 510 |
+
"grad_norm": 0.4879675805568695,
|
| 511 |
+
"learning_rate": 8.923003796085571e-06,
|
| 512 |
+
"loss": 0.10296416282653809,
|
| 513 |
+
"step": 620,
|
| 514 |
+
"token_acc": 0.9602477477477478
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9502262443438914,
|
| 518 |
+
"grad_norm": 0.3828055262565613,
|
| 519 |
+
"learning_rate": 8.738831213195076e-06,
|
| 520 |
+
"loss": 0.1069521188735962,
|
| 521 |
+
"step": 630,
|
| 522 |
+
"token_acc": 0.9581954843577689
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.9653092006033183,
|
| 526 |
+
"grad_norm": 0.6066528558731079,
|
| 527 |
+
"learning_rate": 8.553887304449051e-06,
|
| 528 |
+
"loss": 0.10204867124557496,
|
| 529 |
+
"step": 640,
|
| 530 |
+
"token_acc": 0.960210117690554
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.9803921568627451,
|
| 534 |
+
"grad_norm": 0.5788474082946777,
|
| 535 |
+
"learning_rate": 8.368287220335405e-06,
|
| 536 |
+
"loss": 0.10363715887069702,
|
| 537 |
+
"step": 650,
|
| 538 |
+
"token_acc": 0.959661719127198
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.995475113122172,
|
| 542 |
+
"grad_norm": 0.45377716422080994,
|
| 543 |
+
"learning_rate": 8.18214651989248e-06,
|
| 544 |
+
"loss": 0.10440789461135865,
|
| 545 |
+
"step": 660,
|
| 546 |
+
"token_acc": 0.9594376692706295
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.0105580693815988,
|
| 550 |
+
"grad_norm": 0.39804208278656006,
|
| 551 |
+
"learning_rate": 7.99558109875924e-06,
|
| 552 |
+
"loss": 0.09972409009933472,
|
| 553 |
+
"step": 670,
|
| 554 |
+
"token_acc": 0.96149672939207
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.0256410256410255,
|
| 558 |
+
"grad_norm": 0.4112270176410675,
|
| 559 |
+
"learning_rate": 7.808707117015871e-06,
|
| 560 |
+
"loss": 0.09616597890853881,
|
| 561 |
+
"step": 680,
|
| 562 |
+
"token_acc": 0.9632930129633229
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.0407239819004526,
|
| 566 |
+
"grad_norm": 0.8032577633857727,
|
| 567 |
+
"learning_rate": 7.621640926859767e-06,
|
| 568 |
+
"loss": 0.09788082242012024,
|
| 569 |
+
"step": 690,
|
| 570 |
+
"token_acc": 0.9619020874286249
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0558069381598794,
|
| 574 |
+
"grad_norm": 0.5775718092918396,
|
| 575 |
+
"learning_rate": 7.434499000161847e-06,
|
| 576 |
+
"loss": 0.09358711242675781,
|
| 577 |
+
"step": 700,
|
| 578 |
+
"token_acc": 0.9633524141363863
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.0708898944193062,
|
| 582 |
+
"grad_norm": 0.5401419401168823,
|
| 583 |
+
"learning_rate": 7.247397855948417e-06,
|
| 584 |
+
"loss": 0.09408066868782043,
|
| 585 |
+
"step": 710,
|
| 586 |
+
"token_acc": 0.9634460570946094
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.085972850678733,
|
| 590 |
+
"grad_norm": 0.3692776560783386,
|
| 591 |
+
"learning_rate": 7.060453987853635e-06,
|
| 592 |
+
"loss": 0.09346169233322144,
|
| 593 |
+
"step": 720,
|
| 594 |
+
"token_acc": 0.9638752317240268
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.10105580693816,
|
| 598 |
+
"grad_norm": 0.4132152199745178,
|
| 599 |
+
"learning_rate": 6.873783791587794e-06,
|
| 600 |
+
"loss": 0.09388680458068847,
|
| 601 |
+
"step": 730,
|
| 602 |
+
"token_acc": 0.9637559772180428
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.1161387631975868,
|
| 606 |
+
"grad_norm": 0.4544770419597626,
|
| 607 |
+
"learning_rate": 6.6875034924665825e-06,
|
| 608 |
+
"loss": 0.09155543446540833,
|
| 609 |
+
"step": 740,
|
| 610 |
+
"token_acc": 0.9647887323943662
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.1312217194570136,
|
| 614 |
+
"grad_norm": 0.4763709008693695,
|
| 615 |
+
"learning_rate": 6.501729073046421e-06,
|
| 616 |
+
"loss": 0.09151909351348878,
|
| 617 |
+
"step": 750,
|
| 618 |
+
"token_acc": 0.9641338049016095
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.1463046757164403,
|
| 622 |
+
"grad_norm": 0.3512129783630371,
|
| 623 |
+
"learning_rate": 6.316576200910982e-06,
|
| 624 |
+
"loss": 0.08871339559555054,
|
| 625 |
+
"step": 760,
|
| 626 |
+
"token_acc": 0.9654217212723278
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1613876319758674,
|
| 630 |
+
"grad_norm": 0.4989905059337616,
|
| 631 |
+
"learning_rate": 6.1321601566537614e-06,
|
| 632 |
+
"loss": 0.09526662230491638,
|
| 633 |
+
"step": 770,
|
| 634 |
+
"token_acc": 0.9631938857602574
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.1764705882352942,
|
| 638 |
+
"grad_norm": 0.6301065683364868,
|
| 639 |
+
"learning_rate": 5.94859576210165e-06,
|
| 640 |
+
"loss": 0.09378224611282349,
|
| 641 |
+
"step": 780,
|
| 642 |
+
"token_acc": 0.9638894054925299
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.191553544494721,
|
| 646 |
+
"grad_norm": 0.5111472606658936,
|
| 647 |
+
"learning_rate": 5.765997308824127e-06,
|
| 648 |
+
"loss": 0.09456103444099426,
|
| 649 |
+
"step": 790,
|
| 650 |
+
"token_acc": 0.9630646797222439
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.2066365007541477,
|
| 654 |
+
"grad_norm": 0.4381602704524994,
|
| 655 |
+
"learning_rate": 5.584478486972594e-06,
|
| 656 |
+
"loss": 0.09292151927947997,
|
| 657 |
+
"step": 800,
|
| 658 |
+
"token_acc": 0.9635370603112539
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.2217194570135748,
|
| 662 |
+
"grad_norm": 0.46196287870407104,
|
| 663 |
+
"learning_rate": 5.404152314494185e-06,
|
| 664 |
+
"loss": 0.09235544800758362,
|
| 665 |
+
"step": 810,
|
| 666 |
+
"token_acc": 0.9644699668345412
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.2368024132730016,
|
| 670 |
+
"grad_norm": 0.4581727683544159,
|
| 671 |
+
"learning_rate": 5.225131066764096e-06,
|
| 672 |
+
"loss": 0.0894450843334198,
|
| 673 |
+
"step": 820,
|
| 674 |
+
"token_acc": 0.9649870350432923
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.2518853695324283,
|
| 678 |
+
"grad_norm": 0.4270052909851074,
|
| 679 |
+
"learning_rate": 5.04752620668025e-06,
|
| 680 |
+
"loss": 0.0947738230228424,
|
| 681 |
+
"step": 830,
|
| 682 |
+
"token_acc": 0.9627476129400029
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2669683257918551,
|
| 686 |
+
"grad_norm": 0.45762163400650024,
|
| 687 |
+
"learning_rate": 4.871448315263849e-06,
|
| 688 |
+
"loss": 0.09065256118774415,
|
| 689 |
+
"step": 840,
|
| 690 |
+
"token_acc": 0.9639841068656632
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.282051282051282,
|
| 694 |
+
"grad_norm": 0.46436837315559387,
|
| 695 |
+
"learning_rate": 4.697007022808989e-06,
|
| 696 |
+
"loss": 0.08982598781585693,
|
| 697 |
+
"step": 850,
|
| 698 |
+
"token_acc": 0.9650109525782962
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.297134238310709,
|
| 702 |
+
"grad_norm": 0.6739473342895508,
|
| 703 |
+
"learning_rate": 4.52431094062422e-06,
|
| 704 |
+
"loss": 0.09014194011688233,
|
| 705 |
+
"step": 860,
|
| 706 |
+
"token_acc": 0.9642136708704825
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.3122171945701357,
|
| 710 |
+
"grad_norm": 0.45681968331336975,
|
| 711 |
+
"learning_rate": 4.353467593408566e-06,
|
| 712 |
+
"loss": 0.09165002107620239,
|
| 713 |
+
"step": 870,
|
| 714 |
+
"token_acc": 0.964421518513901
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.3273001508295625,
|
| 718 |
+
"grad_norm": 0.42422786355018616,
|
| 719 |
+
"learning_rate": 4.1845833523040775e-06,
|
| 720 |
+
"loss": 0.09196000099182129,
|
| 721 |
+
"step": 880,
|
| 722 |
+
"token_acc": 0.9632488905325444
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.3423831070889896,
|
| 726 |
+
"grad_norm": 0.41552069783210754,
|
| 727 |
+
"learning_rate": 4.0177633686666225e-06,
|
| 728 |
+
"loss": 0.0871020257472992,
|
| 729 |
+
"step": 890,
|
| 730 |
+
"token_acc": 0.9665725819685582
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.3574660633484164,
|
| 734 |
+
"grad_norm": 0.5335479378700256,
|
| 735 |
+
"learning_rate": 3.853111508596134e-06,
|
| 736 |
+
"loss": 0.0898630142211914,
|
| 737 |
+
"step": 900,
|
| 738 |
+
"token_acc": 0.9652458695864699
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.3725490196078431,
|
| 742 |
+
"grad_norm": 0.44376763701438904,
|
| 743 |
+
"learning_rate": 3.6907302882671214e-06,
|
| 744 |
+
"loss": 0.09012840986251831,
|
| 745 |
+
"step": 910,
|
| 746 |
+
"token_acc": 0.9647732077067102
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.38763197586727,
|
| 750 |
+
"grad_norm": 0.5066686272621155,
|
| 751 |
+
"learning_rate": 3.5307208100996376e-06,
|
| 752 |
+
"loss": 0.09017069339752197,
|
| 753 |
+
"step": 920,
|
| 754 |
+
"token_acc": 0.964361793105593
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.4027149321266967,
|
| 758 |
+
"grad_norm": 0.3902303874492645,
|
| 759 |
+
"learning_rate": 3.373182699810508e-06,
|
| 760 |
+
"loss": 0.09142625331878662,
|
| 761 |
+
"step": 930,
|
| 762 |
+
"token_acc": 0.9647421163923876
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.4177978883861238,
|
| 766 |
+
"grad_norm": 0.41397470235824585,
|
| 767 |
+
"learning_rate": 3.2182140443839834e-06,
|
| 768 |
+
"loss": 0.09144071340560914,
|
| 769 |
+
"step": 940,
|
| 770 |
+
"token_acc": 0.9640816822657104
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.4328808446455505,
|
| 774 |
+
"grad_norm": 0.5350260734558105,
|
| 775 |
+
"learning_rate": 3.0659113310004437e-06,
|
| 776 |
+
"loss": 0.09406846761703491,
|
| 777 |
+
"step": 950,
|
| 778 |
+
"token_acc": 0.9636620346288177
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.4479638009049773,
|
| 782 |
+
"grad_norm": 0.3802923858165741,
|
| 783 |
+
"learning_rate": 2.9163693869611806e-06,
|
| 784 |
+
"loss": 0.08901124000549317,
|
| 785 |
+
"step": 960,
|
| 786 |
+
"token_acc": 0.9656810008299266
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.4630467571644044,
|
| 790 |
+
"grad_norm": 0.35188332200050354,
|
| 791 |
+
"learning_rate": 2.7696813206466494e-06,
|
| 792 |
+
"loss": 0.08718435764312744,
|
| 793 |
+
"step": 970,
|
| 794 |
+
"token_acc": 0.966524814193239
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.4781297134238311,
|
| 798 |
+
"grad_norm": 0.4129849672317505,
|
| 799 |
+
"learning_rate": 2.6259384635449823e-06,
|
| 800 |
+
"loss": 0.08675562143325806,
|
| 801 |
+
"step": 980,
|
| 802 |
+
"token_acc": 0.9662713856203166
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.493212669683258,
|
| 806 |
+
"grad_norm": 0.45535895228385925,
|
| 807 |
+
"learning_rate": 2.48523031338683e-06,
|
| 808 |
+
"loss": 0.09237306118011475,
|
| 809 |
+
"step": 990,
|
| 810 |
+
"token_acc": 0.9645306006091614
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.5082956259426847,
|
| 814 |
+
"grad_norm": 0.4584350287914276,
|
| 815 |
+
"learning_rate": 2.347644478421916e-06,
|
| 816 |
+
"loss": 0.09014174342155457,
|
| 817 |
+
"step": 1000,
|
| 818 |
+
"token_acc": 0.9647957202640322
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.5233785822021115,
|
| 822 |
+
"grad_norm": 0.4994698762893677,
|
| 823 |
+
"learning_rate": 2.2132666228720783e-06,
|
| 824 |
+
"loss": 0.09264277219772339,
|
| 825 |
+
"step": 1010,
|
| 826 |
+
"token_acc": 0.9640724946695096
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.5384615384615383,
|
| 830 |
+
"grad_norm": 0.39258939027786255,
|
| 831 |
+
"learning_rate": 2.0821804135946685e-06,
|
| 832 |
+
"loss": 0.0883907675743103,
|
| 833 |
+
"step": 1020,
|
| 834 |
+
"token_acc": 0.9648448140492557
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.5535444947209653,
|
| 838 |
+
"grad_norm": 0.3761826753616333,
|
| 839 |
+
"learning_rate": 1.954467467989575e-06,
|
| 840 |
+
"loss": 0.08799158334732056,
|
| 841 |
+
"step": 1030,
|
| 842 |
+
"token_acc": 0.9661682044755542
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.5686274509803921,
|
| 846 |
+
"grad_norm": 0.4628184139728546,
|
| 847 |
+
"learning_rate": 1.8302073031822736e-06,
|
| 848 |
+
"loss": 0.08756601214408874,
|
| 849 |
+
"step": 1040,
|
| 850 |
+
"token_acc": 0.9655115037286905
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.5837104072398192,
|
| 854 |
+
"grad_norm": 0.5046730041503906,
|
| 855 |
+
"learning_rate": 1.7094772865145908e-06,
|
| 856 |
+
"loss": 0.08718575239181518,
|
| 857 |
+
"step": 1050,
|
| 858 |
+
"token_acc": 0.966780388576554
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.598793363499246,
|
| 862 |
+
"grad_norm": 0.45518726110458374,
|
| 863 |
+
"learning_rate": 1.5923525873739312e-06,
|
| 864 |
+
"loss": 0.08757206201553344,
|
| 865 |
+
"step": 1060,
|
| 866 |
+
"token_acc": 0.9656194052315541
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.6138763197586727,
|
| 870 |
+
"grad_norm": 0.3528100252151489,
|
| 871 |
+
"learning_rate": 1.4789061303910304e-06,
|
| 872 |
+
"loss": 0.09095115661621093,
|
| 873 |
+
"step": 1070,
|
| 874 |
+
"token_acc": 0.9643856022374901
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.6289592760180995,
|
| 878 |
+
"grad_norm": 0.3653790056705475,
|
| 879 |
+
"learning_rate": 1.3692085500353444e-06,
|
| 880 |
+
"loss": 0.09028034210205078,
|
| 881 |
+
"step": 1080,
|
| 882 |
+
"token_acc": 0.9654089878495437
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.6440422322775263,
|
| 886 |
+
"grad_norm": 0.3657921254634857,
|
| 887 |
+
"learning_rate": 1.263328146636342e-06,
|
| 888 |
+
"loss": 0.08679715394973755,
|
| 889 |
+
"step": 1090,
|
| 890 |
+
"token_acc": 0.9662785326303381
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.6591251885369531,
|
| 894 |
+
"grad_norm": 0.3641863465309143,
|
| 895 |
+
"learning_rate": 1.1613308438580924e-06,
|
| 896 |
+
"loss": 0.08758020401000977,
|
| 897 |
+
"step": 1100,
|
| 898 |
+
"token_acc": 0.9654987184799791
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.6742081447963801,
|
| 902 |
+
"grad_norm": 0.4320993721485138,
|
| 903 |
+
"learning_rate": 1.063280147653618e-06,
|
| 904 |
+
"loss": 0.08432935476303101,
|
| 905 |
+
"step": 1110,
|
| 906 |
+
"token_acc": 0.9675015490982618
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.689291101055807,
|
| 910 |
+
"grad_norm": 0.34107470512390137,
|
| 911 |
+
"learning_rate": 9.692371067245726e-07,
|
| 912 |
+
"loss": 0.09100235104560853,
|
| 913 |
+
"step": 1120,
|
| 914 |
+
"token_acc": 0.964681418950374
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.704374057315234,
|
| 918 |
+
"grad_norm": 0.32863467931747437,
|
| 919 |
+
"learning_rate": 8.792602745108685e-07,
|
| 920 |
+
"loss": 0.08523865342140198,
|
| 921 |
+
"step": 1130,
|
| 922 |
+
"token_acc": 0.9660080165341016
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.7194570135746607,
|
| 926 |
+
"grad_norm": 0.44436898827552795,
|
| 927 |
+
"learning_rate": 7.93405672733902e-07,
|
| 928 |
+
"loss": 0.09061864614486695,
|
| 929 |
+
"step": 1140,
|
| 930 |
+
"token_acc": 0.9646512324867011
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.7345399698340875,
|
| 934 |
+
"grad_norm": 0.365710586309433,
|
| 935 |
+
"learning_rate": 7.117267565160989e-07,
|
| 936 |
+
"loss": 0.0857430338859558,
|
| 937 |
+
"step": 1150,
|
| 938 |
+
"token_acc": 0.9665197002508296
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.7496229260935143,
|
| 942 |
+
"grad_norm": 0.4832117557525635,
|
| 943 |
+
"learning_rate": 6.342743810984836e-07,
|
| 944 |
+
"loss": 0.08890118002891541,
|
| 945 |
+
"step": 1160,
|
| 946 |
+
"token_acc": 0.9660351545073312
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.7647058823529411,
|
| 950 |
+
"grad_norm": 0.3681408762931824,
|
| 951 |
+
"learning_rate": 5.610967701769814e-07,
|
| 952 |
+
"loss": 0.08722085952758789,
|
| 953 |
+
"step": 1170,
|
| 954 |
+
"token_acc": 0.9660664603457438
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.779788838612368,
|
| 958 |
+
"grad_norm": 0.4544508457183838,
|
| 959 |
+
"learning_rate": 4.922394858772067e-07,
|
| 960 |
+
"loss": 0.08912365436553955,
|
| 961 |
+
"step": 1180,
|
| 962 |
+
"token_acc": 0.9653174628232248
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7948717948717947,
|
| 966 |
+
"grad_norm": 0.4088412821292877,
|
| 967 |
+
"learning_rate": 4.2774540038639286e-07,
|
| 968 |
+
"loss": 0.08246009349822998,
|
| 969 |
+
"step": 1190,
|
| 970 |
+
"token_acc": 0.9678997594096655
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.8099547511312217,
|
| 974 |
+
"grad_norm": 0.4180281162261963,
|
| 975 |
+
"learning_rate": 3.676546692601465e-07,
|
| 976 |
+
"loss": 0.08530747294425964,
|
| 977 |
+
"step": 1200,
|
| 978 |
+
"token_acc": 0.966511905135364
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.8250377073906485,
|
| 982 |
+
"grad_norm": 0.3279511332511902,
|
| 983 |
+
"learning_rate": 3.1200470642063716e-07,
|
| 984 |
+
"loss": 0.08611878156661987,
|
| 985 |
+
"step": 1210,
|
| 986 |
+
"token_acc": 0.9662316426015056
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.8401206636500755,
|
| 990 |
+
"grad_norm": 0.4073133170604706,
|
| 991 |
+
"learning_rate": 2.6083016086180715e-07,
|
| 992 |
+
"loss": 0.08319737315177918,
|
| 993 |
+
"step": 1220,
|
| 994 |
+
"token_acc": 0.9677166096159282
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.8552036199095023,
|
| 998 |
+
"grad_norm": 0.3561563789844513,
|
| 999 |
+
"learning_rate": 2.14162895076071e-07,
|
| 1000 |
+
"loss": 0.0903146207332611,
|
| 1001 |
+
"step": 1230,
|
| 1002 |
+
"token_acc": 0.9648374348841386
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.8702865761689291,
|
| 1006 |
+
"grad_norm": 0.42073923349380493,
|
| 1007 |
+
"learning_rate": 1.7203196521597354e-07,
|
| 1008 |
+
"loss": 0.08666027188301087,
|
| 1009 |
+
"step": 1240,
|
| 1010 |
+
"token_acc": 0.9662166414904331
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.885369532428356,
|
| 1014 |
+
"grad_norm": 0.3711903691291809,
|
| 1015 |
+
"learning_rate": 1.3446360300313375e-07,
|
| 1016 |
+
"loss": 0.0845598578453064,
|
| 1017 |
+
"step": 1250,
|
| 1018 |
+
"token_acc": 0.9672128552204544
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.9004524886877827,
|
| 1022 |
+
"grad_norm": 0.4648366868495941,
|
| 1023 |
+
"learning_rate": 1.0148119939575207e-07,
|
| 1024 |
+
"loss": 0.08463501334190368,
|
| 1025 |
+
"step": 1260,
|
| 1026 |
+
"token_acc": 0.9671166666666666
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.9155354449472095,
|
| 1030 |
+
"grad_norm": 0.34604692459106445,
|
| 1031 |
+
"learning_rate": 7.310529002484079e-08,
|
| 1032 |
+
"loss": 0.0892053484916687,
|
| 1033 |
+
"step": 1270,
|
| 1034 |
+
"token_acc": 0.9649981072187764
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.9306184012066365,
|
| 1038 |
+
"grad_norm": 0.38359424471855164,
|
| 1039 |
+
"learning_rate": 4.9353542408249465e-08,
|
| 1040 |
+
"loss": 0.08901722431182861,
|
| 1041 |
+
"step": 1280,
|
| 1042 |
+
"token_acc": 0.9650786774148629
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.9457013574660633,
|
| 1046 |
+
"grad_norm": 0.42977797985076904,
|
| 1047 |
+
"learning_rate": 3.024074495044826e-08,
|
| 1048 |
+
"loss": 0.08712854385375976,
|
| 1049 |
+
"step": 1290,
|
| 1050 |
+
"token_acc": 0.9666139518538043
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.9607843137254903,
|
| 1054 |
+
"grad_norm": 0.3914060592651367,
|
| 1055 |
+
"learning_rate": 1.5778797734913307e-08,
|
| 1056 |
+
"loss": 0.08645588755607606,
|
| 1057 |
+
"step": 1300,
|
| 1058 |
+
"token_acc": 0.96584090325116
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.9758672699849171,
|
| 1062 |
+
"grad_norm": 0.3837912380695343,
|
| 1063 |
+
"learning_rate": 5.976705114852654e-09,
|
| 1064 |
+
"loss": 0.08520195484161378,
|
| 1065 |
+
"step": 1310,
|
| 1066 |
+
"token_acc": 0.966562089829369
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.990950226244344,
|
| 1070 |
+
"grad_norm": 0.38043421506881714,
|
| 1071 |
+
"learning_rate": 8.40570106880878e-10,
|
| 1072 |
+
"loss": 0.08780958652496337,
|
| 1073 |
+
"step": 1320,
|
| 1074 |
+
"token_acc": 0.9663121369842348
|
| 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": 1.5775587374832026e+19,
|
| 1095 |
+
"train_batch_size": 2,
|
| 1096 |
+
"trial_name": null,
|
| 1097 |
+
"trial_params": null
|
| 1098 |
+
}
|