Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- args.json +382 -0
- chat_template.jinja +154 -0
- config.json +113 -0
- generation_config.json +9 -0
- latest +1 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +731 -0
- preprocessor_config.json +21 -0
- processor_config.json +60 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
- trainer_state.json +2175 -0
- training_args.bin +3 -0
- zero_to_fp32.py +760 -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
|
args.json
ADDED
|
@@ -0,0 +1,382 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/NHNHOME/data/sanghyeok/qwen-cua/runs/probe2000_idm_code_full/v1-20260621-231848",
|
| 3 |
+
"per_device_train_batch_size": 1,
|
| 4 |
+
"num_train_epochs": 3.0,
|
| 5 |
+
"max_steps": 2000,
|
| 6 |
+
"learning_rate": 1e-05,
|
| 7 |
+
"lr_scheduler_type": "cosine",
|
| 8 |
+
"lr_scheduler_kwargs": null,
|
| 9 |
+
"warmup_steps": 100.0,
|
| 10 |
+
"optim": "adamw_torch_fused",
|
| 11 |
+
"optim_args": null,
|
| 12 |
+
"weight_decay": 0.0,
|
| 13 |
+
"adam_beta1": 0.9,
|
| 14 |
+
"adam_beta2": 0.95,
|
| 15 |
+
"adam_epsilon": 1e-08,
|
| 16 |
+
"optim_target_modules": null,
|
| 17 |
+
"gradient_accumulation_steps": 32,
|
| 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": true,
|
| 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": "probe2000_idm_code_full",
|
| 50 |
+
"project": "huggingface",
|
| 51 |
+
"trackio_space_id": null,
|
| 52 |
+
"trackio_bucket_id": null,
|
| 53 |
+
"trackio_static_space_id": null,
|
| 54 |
+
"eval_strategy": "steps",
|
| 55 |
+
"eval_steps": 500.0,
|
| 56 |
+
"eval_delay": 0,
|
| 57 |
+
"per_device_eval_batch_size": 1,
|
| 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": "steps",
|
| 67 |
+
"save_steps": 500.0,
|
| 68 |
+
"save_on_each_node": false,
|
| 69 |
+
"save_total_limit": 6,
|
| 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": true,
|
| 95 |
+
"dataloader_prefetch_factor": 4,
|
| 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 |
+
"bf16": {
|
| 110 |
+
"enabled": true
|
| 111 |
+
},
|
| 112 |
+
"fp16": {
|
| 113 |
+
"enabled": false
|
| 114 |
+
},
|
| 115 |
+
"zero_optimization": {
|
| 116 |
+
"stage": 2,
|
| 117 |
+
"overlap_comm": true,
|
| 118 |
+
"contiguous_gradients": true,
|
| 119 |
+
"reduce_bucket_size": 500000000.0,
|
| 120 |
+
"allgather_bucket_size": 500000000.0,
|
| 121 |
+
"reduce_scatter": true,
|
| 122 |
+
"round_robin_gradients": true
|
| 123 |
+
},
|
| 124 |
+
"gradient_clipping": "auto",
|
| 125 |
+
"gradient_accumulation_steps": "auto",
|
| 126 |
+
"train_batch_size": "auto",
|
| 127 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 128 |
+
"steps_per_print": 100,
|
| 129 |
+
"wall_clock_breakdown": false,
|
| 130 |
+
"_comment_bf16_safety": "DeepSpeed 0.19 BF16_Optimizer keeps fp32 master grad partitions (fp32_groups_flat_partition + accumulate_hp_grads_and_remove_lp hook), so gradient accumulation across many micro-batches is done in fp32. bf16 is only used for the param master copy and forward/backward activations. This is safe at grad_accum=16+; no need to force fp32 collectives."
|
| 131 |
+
},
|
| 132 |
+
"debug": null,
|
| 133 |
+
"skip_memory_metrics": true,
|
| 134 |
+
"do_train": false,
|
| 135 |
+
"do_eval": false,
|
| 136 |
+
"do_predict": false,
|
| 137 |
+
"resume_from_checkpoint": "/NHNHOME/data/sanghyeok/qwen-cua/runs/probe2000_idm_code_full/v0-20260621-113102/checkpoint-1000",
|
| 138 |
+
"warmup_ratio": null,
|
| 139 |
+
"logging_dir": "/NHNHOME/data/sanghyeok/qwen-cua/runs/probe2000_idm_code_full/v1-20260621-231848/runs",
|
| 140 |
+
"local_rank": 0,
|
| 141 |
+
"sortish_sampler": false,
|
| 142 |
+
"predict_with_generate": false,
|
| 143 |
+
"generation_max_length": null,
|
| 144 |
+
"generation_num_beams": null,
|
| 145 |
+
"generation_config": null,
|
| 146 |
+
"tuner_backend": "peft",
|
| 147 |
+
"vit_gradient_checkpointing": false,
|
| 148 |
+
"router_aux_loss_coef": 0.0,
|
| 149 |
+
"enable_dft_loss": false,
|
| 150 |
+
"enable_channel_loss": false,
|
| 151 |
+
"safe_serialization": true,
|
| 152 |
+
"max_shard_size": "5GB",
|
| 153 |
+
"check_model": true,
|
| 154 |
+
"acc_strategy": "token",
|
| 155 |
+
"train_dataloader_shuffle": true,
|
| 156 |
+
"group_by_length": false,
|
| 157 |
+
"max_epochs": null,
|
| 158 |
+
"aligner_lr": null,
|
| 159 |
+
"vit_lr": null,
|
| 160 |
+
"use_logits_to_keep": null,
|
| 161 |
+
"ds3_gather_for_generation": true,
|
| 162 |
+
"resume_only_model": false,
|
| 163 |
+
"optimizer": null,
|
| 164 |
+
"loss_type": null,
|
| 165 |
+
"eval_metric": null,
|
| 166 |
+
"callbacks": [],
|
| 167 |
+
"early_stop_interval": null,
|
| 168 |
+
"eval_use_evalscope": false,
|
| 169 |
+
"eval_dataset": [],
|
| 170 |
+
"eval_dataset_args": null,
|
| 171 |
+
"eval_limit": null,
|
| 172 |
+
"eval_generation_config": null,
|
| 173 |
+
"extra_eval_args": null,
|
| 174 |
+
"tuner_type": "full",
|
| 175 |
+
"use_galore": false,
|
| 176 |
+
"galore_target_modules": null,
|
| 177 |
+
"galore_rank": 128,
|
| 178 |
+
"galore_update_proj_gap": 50,
|
| 179 |
+
"galore_scale": 1.0,
|
| 180 |
+
"galore_proj_type": "std",
|
| 181 |
+
"galore_optim_per_parameter": false,
|
| 182 |
+
"galore_with_embedding": false,
|
| 183 |
+
"galore_quantization": false,
|
| 184 |
+
"galore_proj_quant": false,
|
| 185 |
+
"galore_proj_bits": 4,
|
| 186 |
+
"galore_proj_group_size": 256,
|
| 187 |
+
"galore_cos_threshold": 0.4,
|
| 188 |
+
"galore_gamma_proj": 2,
|
| 189 |
+
"galore_queue_size": 5,
|
| 190 |
+
"lisa_activated_layers": 0,
|
| 191 |
+
"lisa_step_interval": 20,
|
| 192 |
+
"use_flash_ckpt": false,
|
| 193 |
+
"use_ray": false,
|
| 194 |
+
"ray_exp_name": null,
|
| 195 |
+
"device_groups": null,
|
| 196 |
+
"model": "/NHNHOME/data/sanghyeok/qwen-cua/runs/ocu_ex_base_exact_all_12k_nopack/v0-20260612-174123/checkpoint-4336",
|
| 197 |
+
"model_type": "qwen3_5",
|
| 198 |
+
"model_revision": null,
|
| 199 |
+
"task_type": "causal_lm",
|
| 200 |
+
"torch_dtype": "bfloat16",
|
| 201 |
+
"attn_impl": "flash_attention_2",
|
| 202 |
+
"experts_impl": null,
|
| 203 |
+
"new_special_tokens": [],
|
| 204 |
+
"num_labels": null,
|
| 205 |
+
"problem_type": null,
|
| 206 |
+
"rope_scaling": null,
|
| 207 |
+
"device_map": null,
|
| 208 |
+
"max_memory": {},
|
| 209 |
+
"max_model_len": null,
|
| 210 |
+
"local_repo_path": null,
|
| 211 |
+
"init_strategy": null,
|
| 212 |
+
"template": "qwen3_5",
|
| 213 |
+
"system": null,
|
| 214 |
+
"max_length": 12288,
|
| 215 |
+
"truncation_strategy": "delete",
|
| 216 |
+
"max_pixels": 16777216,
|
| 217 |
+
"agent_template": null,
|
| 218 |
+
"norm_bbox": null,
|
| 219 |
+
"use_chat_template": true,
|
| 220 |
+
"padding_side": "right",
|
| 221 |
+
"padding_free": false,
|
| 222 |
+
"loss_scale": "default",
|
| 223 |
+
"sequence_parallel_size": 1,
|
| 224 |
+
"template_backend": "swift",
|
| 225 |
+
"response_prefix": null,
|
| 226 |
+
"enable_thinking": null,
|
| 227 |
+
"add_non_thinking_prefix": true,
|
| 228 |
+
"dataset": [
|
| 229 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/AgentNet/l1/ubuntu/train_wm.jsonl#35000",
|
| 230 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/AgentNet/l2/ubuntu/train_wm.jsonl#35000",
|
| 231 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/AgentNet/l3/ubuntu/train_wm.jsonl#35000",
|
| 232 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/AgentNet/l1/win_mac/train_wm.jsonl#100000",
|
| 233 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/AgentNet/l2/win_mac/train_wm.jsonl#100000",
|
| 234 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/AgentNet/l3/win_mac/train_wm.jsonl#100000",
|
| 235 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/GUI-360/l1/train_wm.jsonl#50000",
|
| 236 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/GUI-360/l2/train_wm.jsonl#50000",
|
| 237 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/GUI-360/l3/train_wm.jsonl#50000"
|
| 238 |
+
],
|
| 239 |
+
"val_dataset": [
|
| 240 |
+
"/NHNHOME/data/sanghyeok/qwen-cua/data/AgentNet/l2/ubuntu/val_wm.jsonl"
|
| 241 |
+
],
|
| 242 |
+
"cached_dataset": [],
|
| 243 |
+
"cached_val_dataset": [],
|
| 244 |
+
"split_dataset_ratio": 0.0,
|
| 245 |
+
"dataset_num_proc": 4,
|
| 246 |
+
"load_from_cache_file": false,
|
| 247 |
+
"dataset_shuffle": true,
|
| 248 |
+
"val_dataset_shuffle": false,
|
| 249 |
+
"streaming": false,
|
| 250 |
+
"interleave_prob": null,
|
| 251 |
+
"stopping_strategy": "first_exhausted",
|
| 252 |
+
"shuffle_buffer_size": 1000,
|
| 253 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 254 |
+
"columns": {},
|
| 255 |
+
"strict": false,
|
| 256 |
+
"disable_auto_column_mapping": false,
|
| 257 |
+
"model_name": null,
|
| 258 |
+
"model_author": null,
|
| 259 |
+
"custom_dataset_info": [],
|
| 260 |
+
"quant_method": null,
|
| 261 |
+
"quant_bits": null,
|
| 262 |
+
"hqq_axis": null,
|
| 263 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 264 |
+
"bnb_4bit_quant_type": "nf4",
|
| 265 |
+
"bnb_4bit_use_double_quant": true,
|
| 266 |
+
"bnb_4bit_quant_storage": null,
|
| 267 |
+
"max_new_tokens": 64,
|
| 268 |
+
"temperature": 0.0,
|
| 269 |
+
"top_k": null,
|
| 270 |
+
"top_p": null,
|
| 271 |
+
"repetition_penalty": null,
|
| 272 |
+
"num_beams": 1,
|
| 273 |
+
"stream": false,
|
| 274 |
+
"stop_words": [],
|
| 275 |
+
"logprobs": false,
|
| 276 |
+
"top_logprobs": null,
|
| 277 |
+
"structured_outputs_regex": null,
|
| 278 |
+
"adapters": [],
|
| 279 |
+
"external_plugins": [],
|
| 280 |
+
"custom_register_path": [],
|
| 281 |
+
"model_kwargs": {},
|
| 282 |
+
"enable_npu_model_patch": true,
|
| 283 |
+
"load_args": false,
|
| 284 |
+
"load_data_args": false,
|
| 285 |
+
"packing": false,
|
| 286 |
+
"packing_length": null,
|
| 287 |
+
"packing_num_proc": 1,
|
| 288 |
+
"lazy_tokenize": true,
|
| 289 |
+
"use_hf": false,
|
| 290 |
+
"ignore_args_error": false,
|
| 291 |
+
"use_swift_lora": false,
|
| 292 |
+
"freeze_parameters": [
|
| 293 |
+
"model.visual",
|
| 294 |
+
"model.visual.merger"
|
| 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": "4.2.1",
|
| 369 |
+
"ckpt_dir": "/NHNHOME/data/sanghyeok/qwen-cua/runs/ocu_ex_base_exact_all_12k_nopack/v0-20260612-174123/checkpoint-4336",
|
| 370 |
+
"rank": 0,
|
| 371 |
+
"global_world_size": 4,
|
| 372 |
+
"local_world_size": 4,
|
| 373 |
+
"model_suffix": "checkpoint-4336",
|
| 374 |
+
"model_info": "ModelInfo(model_type='qwen3_5', model_dir='/NHNHOME/data/sanghyeok/qwen-cua/runs/ocu_ex_base_exact_all_12k_nopack/v0-20260612-174123/checkpoint-4336', 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_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.5-0.8B', hf_model_id='Qwen/Qwen3.5-0.8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B', hf_model_id='Qwen/Qwen3.5-2B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B', hf_model_id='Qwen/Qwen3.5-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B', hf_model_id='Qwen/Qwen3.5-9B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B', hf_model_id='Qwen/Qwen3.5-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B-FP8', hf_model_id='Qwen/Qwen3.5-27B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-0.8B-Base', hf_model_id='Qwen/Qwen3.5-0.8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B-Base', hf_model_id='Qwen/Qwen3.5-2B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B-Base', hf_model_id='Qwen/Qwen3.5-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B-Base', hf_model_id='Qwen/Qwen3.5-9B-Base', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.6-27B', hf_model_id='Qwen/Qwen3.6-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.6-27B-FP8', hf_model_id='Qwen/Qwen3.6-27B-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3_5Loader'>, template=None, model_arch=MultiModelKeys(arch_name='qwen2_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'], vision_tower=['model.visual'], generator=[]), mcore_model_type=None, architectures=['Qwen3_5ForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=5.0.0.dev', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])",
|
| 376 |
+
"model_dir": "/NHNHOME/data/sanghyeok/qwen-cua/runs/ocu_ex_base_exact_all_12k_nopack/v0-20260612-174123/checkpoint-4336",
|
| 377 |
+
"template_meta": "QwenTemplateMeta(template_type='qwen3_5', 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.Qwen3_5Template'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='qwen3_5', is_thinking=True, thinking_prefix='<think>\\n', non_thinking_prefix='<think>\\n\\n</think>\\n\\n', history_thinking_prefix='')",
|
| 378 |
+
"_val_dataset_exists": true,
|
| 379 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 380 |
+
"evaluation_strategy": "steps",
|
| 381 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/NHNHOME/data/sanghyeok/qwen-cua/runs/probe2000_idm_code_full/v1-20260621-231848', per_device_train_batch_size=1, num_train_epochs=3.0, max_steps=2000, learning_rate=1e-05, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=100.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, weight_decay=0.0, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=32, 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=True, 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='probe2000_idm_code_full', project='huggingface', trackio_space_id=None, trackio_bucket_id=None, trackio_static_space_id=None, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, eval_steps=500, eval_delay=0, per_device_eval_batch_size=1, 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.STEPS: 'steps'>, save_steps=500, save_on_each_node=False, save_total_limit=6, 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=True, dataloader_prefetch_factor=4, 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={'bf16': {'enabled': True}, 'fp16': {'enabled': False}, 'zero_optimization': {'stage': 2, 'overlap_comm': True, 'contiguous_gradients': True, 'reduce_bucket_size': 500000000.0, 'allgather_bucket_size': 500000000.0, 'reduce_scatter': True, 'round_robin_gradients': True}, 'gradient_clipping': 'auto', 'gradient_accumulation_steps': 'auto', 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'steps_per_print': 100, 'wall_clock_breakdown': False, '_comment_bf16_safety': 'DeepSpeed 0.19 BF16_Optimizer keeps fp32 master grad partitions (fp32_groups_flat_partition + accumulate_hp_grads_and_remove_lp hook), so gradient accumulation across many micro-batches is done in fp32. bf16 is only used for the param master copy and forward/backward activations. This is safe at grad_accum=16+; no need to force fp32 collectives.'}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=True, do_predict=False, resume_from_checkpoint='/NHNHOME/data/sanghyeok/qwen-cua/runs/probe2000_idm_code_full/v0-20260621-113102/checkpoint-1000', warmup_ratio=None, logging_dir='/NHNHOME/data/sanghyeok/qwen-cua/runs/probe2000_idm_code_full/v1-20260621-231848/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 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"hidden_size": 2560,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_type": "qwen3_5",
|
| 10 |
+
"pad_token_id": 248044,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_output_gate": true,
|
| 15 |
+
"bos_token_id": null,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 248044,
|
| 18 |
+
"full_attention_interval": 4,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 2560,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 9216,
|
| 24 |
+
"layer_types": [
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention"
|
| 57 |
+
],
|
| 58 |
+
"linear_conv_kernel_dim": 4,
|
| 59 |
+
"linear_key_head_dim": 128,
|
| 60 |
+
"linear_num_key_heads": 16,
|
| 61 |
+
"linear_num_value_heads": 32,
|
| 62 |
+
"linear_value_head_dim": 128,
|
| 63 |
+
"mamba_ssm_dtype": "float32",
|
| 64 |
+
"max_position_embeddings": 262144,
|
| 65 |
+
"mlp_only_layers": [],
|
| 66 |
+
"model_type": "qwen3_5_text",
|
| 67 |
+
"mtp_num_hidden_layers": 1,
|
| 68 |
+
"mtp_use_dedicated_embeddings": false,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_hidden_layers": 32,
|
| 71 |
+
"num_key_value_heads": 4,
|
| 72 |
+
"pad_token_id": 248044,
|
| 73 |
+
"partial_rotary_factor": 0.25,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_parameters": {
|
| 76 |
+
"mrope_interleaved": true,
|
| 77 |
+
"mrope_section": [
|
| 78 |
+
11,
|
| 79 |
+
11,
|
| 80 |
+
10
|
| 81 |
+
],
|
| 82 |
+
"partial_rotary_factor": 0.25,
|
| 83 |
+
"rope_theta": 10000000,
|
| 84 |
+
"rope_type": "default"
|
| 85 |
+
},
|
| 86 |
+
"tie_word_embeddings": true,
|
| 87 |
+
"use_cache": false,
|
| 88 |
+
"vocab_size": 248320
|
| 89 |
+
},
|
| 90 |
+
"tie_word_embeddings": true,
|
| 91 |
+
"transformers_version": "5.8.1",
|
| 92 |
+
"use_cache": false,
|
| 93 |
+
"video_token_id": 248057,
|
| 94 |
+
"vision_config": {
|
| 95 |
+
"deepstack_visual_indexes": [],
|
| 96 |
+
"depth": 24,
|
| 97 |
+
"dtype": "bfloat16",
|
| 98 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
+
"hidden_size": 1024,
|
| 100 |
+
"in_channels": 3,
|
| 101 |
+
"initializer_range": 0.02,
|
| 102 |
+
"intermediate_size": 4096,
|
| 103 |
+
"model_type": "qwen3_5_vision",
|
| 104 |
+
"num_heads": 16,
|
| 105 |
+
"num_position_embeddings": 2304,
|
| 106 |
+
"out_hidden_size": 2560,
|
| 107 |
+
"patch_size": 16,
|
| 108 |
+
"spatial_merge_size": 2,
|
| 109 |
+
"temporal_patch_size": 2
|
| 110 |
+
},
|
| 111 |
+
"vision_end_token_id": 248054,
|
| 112 |
+
"vision_start_token_id": 248053
|
| 113 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248044,
|
| 5 |
+
248046
|
| 6 |
+
],
|
| 7 |
+
"transformers_version": "5.8.1",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step1500
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56f8fc3bb6aa4c91c7aabe2373bb9c422f1945ed3ae3961a72df7c9846f2ca5
|
| 3 |
+
size 4958192864
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ed72f0815fb91bd3a50a9e608e9047cf608e3aa2253ce1637ec9e51cfdef97
|
| 3 |
+
size 4993498424
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9132529e66cac3079a828b70ff720888e735b62dcc8a839f7c42730ef896d42c
|
| 3 |
+
size 398327248
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,731 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 10350018536
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00001-of-00003.safetensors",
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 58 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 59 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 60 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 61 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 62 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 70 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 71 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 72 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 73 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 74 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 75 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 76 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 77 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 78 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 79 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 80 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 81 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 82 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 83 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 84 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 85 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 86 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 87 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 88 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 89 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 90 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 91 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 92 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 93 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 94 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 95 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 96 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 97 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 98 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 99 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 100 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 101 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 102 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 103 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 104 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 105 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 106 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 107 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 108 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 109 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 110 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 111 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 112 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 113 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 114 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 115 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 116 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 117 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 118 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 119 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 120 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 121 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 122 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 123 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 124 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 125 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 126 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 127 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 128 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 129 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 130 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 131 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 132 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 133 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 134 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 135 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 136 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 137 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 138 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 139 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 140 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 141 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 142 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 143 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 144 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 145 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 146 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 147 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 148 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 149 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 150 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 151 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 152 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 153 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 154 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 157 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 162 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 163 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 165 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 262 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 263 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 264 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 265 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 266 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 274 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 275 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 276 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 277 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 278 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 279 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 280 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 281 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 282 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 283 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 284 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 285 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 286 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 287 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 288 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 289 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 290 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 291 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 292 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 293 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 294 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 295 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 296 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 297 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 298 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 299 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 300 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 301 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 302 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 303 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 304 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 305 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 306 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 307 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 308 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 309 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 310 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 311 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 312 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 313 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 314 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 315 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 316 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 317 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 318 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 319 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 320 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 333 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 335 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 337 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 339 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 341 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 342 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 347 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 348 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 349 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 350 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 351 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 352 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 353 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 354 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 355 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 356 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 357 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 358 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 359 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 360 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 361 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 362 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 363 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 364 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 365 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 366 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 367 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 368 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 369 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 370 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 371 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 372 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 373 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 374 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 375 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 376 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 377 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 378 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 379 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 380 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 381 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 382 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 383 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 384 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 385 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 386 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 387 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 388 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 389 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 390 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 391 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 392 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 393 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 394 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 395 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 396 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 397 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 398 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 399 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 400 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 401 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 402 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 403 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 404 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 405 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 406 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 407 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 408 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 409 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 410 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 411 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 412 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 413 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 414 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 415 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 416 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 417 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 418 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 419 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 420 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 421 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 422 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 423 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 424 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 425 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 426 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 427 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 428 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 429 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 430 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 431 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 432 |
+
"model.language_model.norm.weight": "model-00002-of-00003.safetensors",
|
| 433 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 436 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 437 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 440 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 441 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00003.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00003.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00003.safetensors",
|
| 444 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00003.safetensors",
|
| 445 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 448 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 449 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 452 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 453 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00003.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00003.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00003.safetensors",
|
| 456 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00003.safetensors",
|
| 457 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 460 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 461 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 464 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 465 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 466 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 467 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 468 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 469 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 470 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 471 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 472 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00003.safetensors",
|
| 473 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00003.safetensors",
|
| 474 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00003.safetensors",
|
| 475 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00003.safetensors",
|
| 476 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 477 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 478 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 479 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 480 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 481 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 482 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 483 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 484 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00003.safetensors",
|
| 485 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00003.safetensors",
|
| 486 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00003.safetensors",
|
| 487 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00003.safetensors",
|
| 488 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 489 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 490 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 491 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 492 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 493 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 494 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 495 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 496 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00003.safetensors",
|
| 497 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00003.safetensors",
|
| 498 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00003.safetensors",
|
| 499 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00003.safetensors",
|
| 500 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 501 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 502 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 503 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 504 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 505 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 506 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 507 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 508 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00003.safetensors",
|
| 509 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00003.safetensors",
|
| 510 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00003.safetensors",
|
| 511 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00003.safetensors",
|
| 512 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 513 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 514 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 515 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 516 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 517 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 518 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 519 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 520 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00003.safetensors",
|
| 521 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00003.safetensors",
|
| 522 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00003.safetensors",
|
| 523 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00003.safetensors",
|
| 524 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 525 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 526 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 527 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 529 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 531 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00003.safetensors",
|
| 533 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00003.safetensors",
|
| 535 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00003.safetensors",
|
| 536 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 537 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 538 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 539 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 540 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 541 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 542 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 543 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 544 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00003.safetensors",
|
| 545 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00003.safetensors",
|
| 546 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00003.safetensors",
|
| 547 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00003.safetensors",
|
| 548 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 549 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 550 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 551 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 552 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 553 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 554 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 555 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 556 |
+
"model.visual.blocks.9.norm1.bias": "model-00002-of-00003.safetensors",
|
| 557 |
+
"model.visual.blocks.9.norm1.weight": "model-00002-of-00003.safetensors",
|
| 558 |
+
"model.visual.blocks.9.norm2.bias": "model-00002-of-00003.safetensors",
|
| 559 |
+
"model.visual.blocks.9.norm2.weight": "model-00002-of-00003.safetensors",
|
| 560 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 561 |
+
"model.visual.blocks.10.norm1.bias": "model-00003-of-00003.safetensors",
|
| 562 |
+
"model.visual.blocks.10.norm1.weight": "model-00003-of-00003.safetensors",
|
| 563 |
+
"model.visual.blocks.10.norm2.bias": "model-00003-of-00003.safetensors",
|
| 564 |
+
"model.visual.blocks.10.norm2.weight": "model-00003-of-00003.safetensors",
|
| 565 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 566 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 567 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 568 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 569 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 570 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 571 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 572 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 573 |
+
"model.visual.blocks.11.norm1.bias": "model-00003-of-00003.safetensors",
|
| 574 |
+
"model.visual.blocks.11.norm1.weight": "model-00003-of-00003.safetensors",
|
| 575 |
+
"model.visual.blocks.11.norm2.bias": "model-00003-of-00003.safetensors",
|
| 576 |
+
"model.visual.blocks.11.norm2.weight": "model-00003-of-00003.safetensors",
|
| 577 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 578 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 579 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 580 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 581 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 582 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 583 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 584 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 585 |
+
"model.visual.blocks.12.norm1.bias": "model-00003-of-00003.safetensors",
|
| 586 |
+
"model.visual.blocks.12.norm1.weight": "model-00003-of-00003.safetensors",
|
| 587 |
+
"model.visual.blocks.12.norm2.bias": "model-00003-of-00003.safetensors",
|
| 588 |
+
"model.visual.blocks.12.norm2.weight": "model-00003-of-00003.safetensors",
|
| 589 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 590 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 591 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 592 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 593 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 594 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 595 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 596 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 597 |
+
"model.visual.blocks.13.norm1.bias": "model-00003-of-00003.safetensors",
|
| 598 |
+
"model.visual.blocks.13.norm1.weight": "model-00003-of-00003.safetensors",
|
| 599 |
+
"model.visual.blocks.13.norm2.bias": "model-00003-of-00003.safetensors",
|
| 600 |
+
"model.visual.blocks.13.norm2.weight": "model-00003-of-00003.safetensors",
|
| 601 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 602 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 603 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 604 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 605 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 606 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 607 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 608 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 609 |
+
"model.visual.blocks.14.norm1.bias": "model-00003-of-00003.safetensors",
|
| 610 |
+
"model.visual.blocks.14.norm1.weight": "model-00003-of-00003.safetensors",
|
| 611 |
+
"model.visual.blocks.14.norm2.bias": "model-00003-of-00003.safetensors",
|
| 612 |
+
"model.visual.blocks.14.norm2.weight": "model-00003-of-00003.safetensors",
|
| 613 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 614 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 615 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 616 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 617 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 618 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 619 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 620 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 621 |
+
"model.visual.blocks.15.norm1.bias": "model-00003-of-00003.safetensors",
|
| 622 |
+
"model.visual.blocks.15.norm1.weight": "model-00003-of-00003.safetensors",
|
| 623 |
+
"model.visual.blocks.15.norm2.bias": "model-00003-of-00003.safetensors",
|
| 624 |
+
"model.visual.blocks.15.norm2.weight": "model-00003-of-00003.safetensors",
|
| 625 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 626 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 627 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 628 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 629 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 630 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 631 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 632 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 633 |
+
"model.visual.blocks.16.norm1.bias": "model-00003-of-00003.safetensors",
|
| 634 |
+
"model.visual.blocks.16.norm1.weight": "model-00003-of-00003.safetensors",
|
| 635 |
+
"model.visual.blocks.16.norm2.bias": "model-00003-of-00003.safetensors",
|
| 636 |
+
"model.visual.blocks.16.norm2.weight": "model-00003-of-00003.safetensors",
|
| 637 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 638 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 639 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 640 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 641 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 642 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 643 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 644 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 645 |
+
"model.visual.blocks.17.norm1.bias": "model-00003-of-00003.safetensors",
|
| 646 |
+
"model.visual.blocks.17.norm1.weight": "model-00003-of-00003.safetensors",
|
| 647 |
+
"model.visual.blocks.17.norm2.bias": "model-00003-of-00003.safetensors",
|
| 648 |
+
"model.visual.blocks.17.norm2.weight": "model-00003-of-00003.safetensors",
|
| 649 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 650 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 651 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 652 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 653 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 654 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 655 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 656 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 657 |
+
"model.visual.blocks.18.norm1.bias": "model-00003-of-00003.safetensors",
|
| 658 |
+
"model.visual.blocks.18.norm1.weight": "model-00003-of-00003.safetensors",
|
| 659 |
+
"model.visual.blocks.18.norm2.bias": "model-00003-of-00003.safetensors",
|
| 660 |
+
"model.visual.blocks.18.norm2.weight": "model-00003-of-00003.safetensors",
|
| 661 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 662 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 663 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 664 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 665 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 666 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 667 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 668 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 669 |
+
"model.visual.blocks.19.norm1.bias": "model-00003-of-00003.safetensors",
|
| 670 |
+
"model.visual.blocks.19.norm1.weight": "model-00003-of-00003.safetensors",
|
| 671 |
+
"model.visual.blocks.19.norm2.bias": "model-00003-of-00003.safetensors",
|
| 672 |
+
"model.visual.blocks.19.norm2.weight": "model-00003-of-00003.safetensors",
|
| 673 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 674 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 675 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 676 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 677 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 678 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 679 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 680 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 681 |
+
"model.visual.blocks.20.norm1.bias": "model-00003-of-00003.safetensors",
|
| 682 |
+
"model.visual.blocks.20.norm1.weight": "model-00003-of-00003.safetensors",
|
| 683 |
+
"model.visual.blocks.20.norm2.bias": "model-00003-of-00003.safetensors",
|
| 684 |
+
"model.visual.blocks.20.norm2.weight": "model-00003-of-00003.safetensors",
|
| 685 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 686 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 687 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 688 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 689 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 690 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 691 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 692 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 693 |
+
"model.visual.blocks.21.norm1.bias": "model-00003-of-00003.safetensors",
|
| 694 |
+
"model.visual.blocks.21.norm1.weight": "model-00003-of-00003.safetensors",
|
| 695 |
+
"model.visual.blocks.21.norm2.bias": "model-00003-of-00003.safetensors",
|
| 696 |
+
"model.visual.blocks.21.norm2.weight": "model-00003-of-00003.safetensors",
|
| 697 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 698 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 699 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 700 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 701 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 702 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 703 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 704 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 705 |
+
"model.visual.blocks.22.norm1.bias": "model-00003-of-00003.safetensors",
|
| 706 |
+
"model.visual.blocks.22.norm1.weight": "model-00003-of-00003.safetensors",
|
| 707 |
+
"model.visual.blocks.22.norm2.bias": "model-00003-of-00003.safetensors",
|
| 708 |
+
"model.visual.blocks.22.norm2.weight": "model-00003-of-00003.safetensors",
|
| 709 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 710 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 711 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 712 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 713 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 714 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 715 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 716 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 717 |
+
"model.visual.blocks.23.norm1.bias": "model-00003-of-00003.safetensors",
|
| 718 |
+
"model.visual.blocks.23.norm1.weight": "model-00003-of-00003.safetensors",
|
| 719 |
+
"model.visual.blocks.23.norm2.bias": "model-00003-of-00003.safetensors",
|
| 720 |
+
"model.visual.blocks.23.norm2.weight": "model-00003-of-00003.safetensors",
|
| 721 |
+
"model.visual.merger.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 722 |
+
"model.visual.merger.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 723 |
+
"model.visual.merger.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 724 |
+
"model.visual.merger.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 725 |
+
"model.visual.merger.norm.bias": "model-00003-of-00003.safetensors",
|
| 726 |
+
"model.visual.merger.norm.weight": "model-00003-of-00003.safetensors",
|
| 727 |
+
"model.visual.patch_embed.proj.bias": "model-00003-of-00003.safetensors",
|
| 728 |
+
"model.visual.patch_embed.proj.weight": "model-00003-of-00003.safetensors",
|
| 729 |
+
"model.visual.pos_embed.weight": "model-00003-of-00003.safetensors"
|
| 730 |
+
}
|
| 731 |
+
}
|
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 |
+
}
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2ab3e814502b356f072924a54278393c2c87c5474a1d996601ff9e21a569a48
|
| 3 |
+
size 15429
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f76c79aa5910dadeae53e2b400cc9b4e45feb7084ef176b72e8864510a7ec13
|
| 3 |
+
size 15429
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:205c8c4ec2a8cada34770494c342700561ff7a5bb88b22e15205539bba9c1343
|
| 3 |
+
size 15429
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9430290c5da4b68b98bc18a348f463c62d8803969955be6302d0be44686246a
|
| 3 |
+
size 15429
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f192e5dca08cc67abfd9e6da26065c3078f7122a02d6a55de0d22a45d7aec26c
|
| 3 |
+
size 1465
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1500,
|
| 3 |
+
"best_metric": 1.14039981,
|
| 4 |
+
"best_model_checkpoint": "/NHNHOME/data/sanghyeok/qwen-cua/runs/probe2000_idm_code_full/v1-20260621-231848/checkpoint-1500",
|
| 5 |
+
"epoch": 0.34594594594594597,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00023063063063063062,
|
| 14 |
+
"grad_norm": 1592.4940185546875,
|
| 15 |
+
"learning_rate": 1.0000000000000001e-07,
|
| 16 |
+
"loss": 79.31526184082031,
|
| 17 |
+
"loss_idm": 4.953125,
|
| 18 |
+
"loss_idm_anl": 0.0,
|
| 19 |
+
"loss_idm_coord": 0.0621337890625,
|
| 20 |
+
"loss_idm_text": 1.8660085201263428,
|
| 21 |
+
"loss_idm_type": 3.003211200237274,
|
| 22 |
+
"loss_sft": 0.013178251218050718,
|
| 23 |
+
"step": 1,
|
| 24 |
+
"token_acc": 0.855064946292334
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0023063063063063064,
|
| 28 |
+
"grad_norm": 1613.28076171875,
|
| 29 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 30 |
+
"loss": 76.10415310329861,
|
| 31 |
+
"loss_idm": 4.284722222222222,
|
| 32 |
+
"loss_idm_anl": 0.0,
|
| 33 |
+
"loss_idm_coord": 0.05967881944444445,
|
| 34 |
+
"loss_idm_text": 1.7714627848731146,
|
| 35 |
+
"loss_idm_type": 2.89741759830051,
|
| 36 |
+
"loss_sft": 0.013162603808773888,
|
| 37 |
+
"step": 10,
|
| 38 |
+
"token_acc": 0.8557915694044088
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.004612612612612613,
|
| 42 |
+
"grad_norm": 348.3831481933594,
|
| 43 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 44 |
+
"loss": 50.42054443359375,
|
| 45 |
+
"loss_idm": 2.9625,
|
| 46 |
+
"loss_idm_anl": 0.0,
|
| 47 |
+
"loss_idm_coord": 0.0595703125,
|
| 48 |
+
"loss_idm_text": 1.6456905126571655,
|
| 49 |
+
"loss_idm_type": 1.4186124086380005,
|
| 50 |
+
"loss_sft": 0.013041298277676106,
|
| 51 |
+
"step": 20,
|
| 52 |
+
"token_acc": 0.8575046262325297
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.006918918918918919,
|
| 56 |
+
"grad_norm": 126.2293930053711,
|
| 57 |
+
"learning_rate": 3e-06,
|
| 58 |
+
"loss": 44.00212707519531,
|
| 59 |
+
"loss_idm": 2.5375,
|
| 60 |
+
"loss_idm_anl": 0.0,
|
| 61 |
+
"loss_idm_coord": 0.052490234375,
|
| 62 |
+
"loss_idm_text": 1.6745069742202758,
|
| 63 |
+
"loss_idm_type": 0.9961585998535156,
|
| 64 |
+
"loss_sft": 0.013043427839875221,
|
| 65 |
+
"step": 30,
|
| 66 |
+
"token_acc": 0.8575169162329329
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.009225225225225226,
|
| 70 |
+
"grad_norm": 161.60565185546875,
|
| 71 |
+
"learning_rate": 4.000000000000001e-06,
|
| 72 |
+
"loss": 40.35985412597656,
|
| 73 |
+
"loss_idm": 2.340625,
|
| 74 |
+
"loss_idm_anl": 0.0,
|
| 75 |
+
"loss_idm_coord": 0.0490234375,
|
| 76 |
+
"loss_idm_text": 1.5050048112869263,
|
| 77 |
+
"loss_idm_type": 0.9409058809280395,
|
| 78 |
+
"loss_sft": 0.013070817664265632,
|
| 79 |
+
"step": 40,
|
| 80 |
+
"token_acc": 0.8573629929949759
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.011531531531531532,
|
| 84 |
+
"grad_norm": 366.02923583984375,
|
| 85 |
+
"learning_rate": 5e-06,
|
| 86 |
+
"loss": 36.85423583984375,
|
| 87 |
+
"loss_idm": 2.15625,
|
| 88 |
+
"loss_idm_anl": 0.0,
|
| 89 |
+
"loss_idm_coord": 0.045751953125,
|
| 90 |
+
"loss_idm_text": 1.454877495765686,
|
| 91 |
+
"loss_idm_type": 0.7732545018196106,
|
| 92 |
+
"loss_sft": 0.014006125554442406,
|
| 93 |
+
"step": 50,
|
| 94 |
+
"token_acc": 0.8500105439434349
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.013837837837837838,
|
| 98 |
+
"grad_norm": 334.4949951171875,
|
| 99 |
+
"learning_rate": 6e-06,
|
| 100 |
+
"loss": 27.9380615234375,
|
| 101 |
+
"loss_idm": 1.6390625,
|
| 102 |
+
"loss_idm_anl": 0.0,
|
| 103 |
+
"loss_idm_coord": 0.04501953125,
|
| 104 |
+
"loss_idm_text": 1.0883261203765868,
|
| 105 |
+
"loss_idm_type": 0.5830961108207703,
|
| 106 |
+
"loss_sft": 0.014523161575198174,
|
| 107 |
+
"step": 60,
|
| 108 |
+
"token_acc": 0.8460712220110717
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.016144144144144144,
|
| 112 |
+
"grad_norm": 287.8810729980469,
|
| 113 |
+
"learning_rate": 7e-06,
|
| 114 |
+
"loss": 28.939056396484375,
|
| 115 |
+
"loss_idm": 1.696875,
|
| 116 |
+
"loss_idm_anl": 0.0,
|
| 117 |
+
"loss_idm_coord": 0.04052734375,
|
| 118 |
+
"loss_idm_text": 1.0840964794158936,
|
| 119 |
+
"loss_idm_type": 0.6544631838798523,
|
| 120 |
+
"loss_sft": 0.01408173404633999,
|
| 121 |
+
"step": 70,
|
| 122 |
+
"token_acc": 0.8500501916749074
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.01845045045045045,
|
| 126 |
+
"grad_norm": 164.0933380126953,
|
| 127 |
+
"learning_rate": 8.000000000000001e-06,
|
| 128 |
+
"loss": 24.88965606689453,
|
| 129 |
+
"loss_idm": 1.4421875,
|
| 130 |
+
"loss_idm_anl": 0.0,
|
| 131 |
+
"loss_idm_coord": 0.0427734375,
|
| 132 |
+
"loss_idm_text": 0.8765177607536316,
|
| 133 |
+
"loss_idm_type": 0.607001006603241,
|
| 134 |
+
"loss_sft": 0.013972016051411629,
|
| 135 |
+
"step": 80,
|
| 136 |
+
"token_acc": 0.850499639034801
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.020756756756756756,
|
| 140 |
+
"grad_norm": 271.42523193359375,
|
| 141 |
+
"learning_rate": 9e-06,
|
| 142 |
+
"loss": 24.212254333496094,
|
| 143 |
+
"loss_idm": 1.409375,
|
| 144 |
+
"loss_idm_anl": 0.0,
|
| 145 |
+
"loss_idm_coord": 0.03955078125,
|
| 146 |
+
"loss_idm_text": 0.8325042963027954,
|
| 147 |
+
"loss_idm_type": 0.6114315390586853,
|
| 148 |
+
"loss_sft": 0.014018873870372772,
|
| 149 |
+
"step": 90,
|
| 150 |
+
"token_acc": 0.8487399360383294
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.023063063063063063,
|
| 154 |
+
"grad_norm": 229.35255432128906,
|
| 155 |
+
"learning_rate": 1e-05,
|
| 156 |
+
"loss": 25.997027587890624,
|
| 157 |
+
"loss_idm": 1.5015625,
|
| 158 |
+
"loss_idm_anl": 0.0,
|
| 159 |
+
"loss_idm_coord": 0.039697265625,
|
| 160 |
+
"loss_idm_text": 0.9402544498443604,
|
| 161 |
+
"loss_idm_type": 0.6157279968261719,
|
| 162 |
+
"loss_sft": 0.014289245754480363,
|
| 163 |
+
"step": 100,
|
| 164 |
+
"token_acc": 0.8460278937791673
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.025369369369369368,
|
| 168 |
+
"grad_norm": 294.6478576660156,
|
| 169 |
+
"learning_rate": 9.999316524962347e-06,
|
| 170 |
+
"loss": 25.035136413574218,
|
| 171 |
+
"loss_idm": 1.45625,
|
| 172 |
+
"loss_idm_anl": 0.0,
|
| 173 |
+
"loss_idm_coord": 0.034033203125,
|
| 174 |
+
"loss_idm_text": 0.9034677743911743,
|
| 175 |
+
"loss_idm_type": 0.5977115869522095,
|
| 176 |
+
"loss_sft": 0.014173812046647073,
|
| 177 |
+
"step": 110,
|
| 178 |
+
"token_acc": 0.8471177587505733
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.027675675675675675,
|
| 182 |
+
"grad_norm": 233.29827880859375,
|
| 183 |
+
"learning_rate": 9.99726628670463e-06,
|
| 184 |
+
"loss": 26.405145263671876,
|
| 185 |
+
"loss_idm": 1.553125,
|
| 186 |
+
"loss_idm_anl": 0.0,
|
| 187 |
+
"loss_idm_coord": 0.035498046875,
|
| 188 |
+
"loss_idm_text": 0.968865442276001,
|
| 189 |
+
"loss_idm_type": 0.6166337251663208,
|
| 190 |
+
"loss_sft": 0.013977998867630959,
|
| 191 |
+
"step": 120,
|
| 192 |
+
"token_acc": 0.8493716829225565
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.029981981981981983,
|
| 196 |
+
"grad_norm": 314.5971374511719,
|
| 197 |
+
"learning_rate": 9.993849845741525e-06,
|
| 198 |
+
"loss": 25.430509948730467,
|
| 199 |
+
"loss_idm": 1.471875,
|
| 200 |
+
"loss_idm_anl": 0.0,
|
| 201 |
+
"loss_idm_coord": 0.03779296875,
|
| 202 |
+
"loss_idm_text": 0.9332091808319092,
|
| 203 |
+
"loss_idm_type": 0.5891867876052856,
|
| 204 |
+
"loss_sft": 0.014243610203266144,
|
| 205 |
+
"step": 130,
|
| 206 |
+
"token_acc": 0.8470191198367073
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.03228828828828829,
|
| 210 |
+
"grad_norm": 199.4022674560547,
|
| 211 |
+
"learning_rate": 9.989068136093873e-06,
|
| 212 |
+
"loss": 23.130665588378907,
|
| 213 |
+
"loss_idm": 1.3390625,
|
| 214 |
+
"loss_idm_anl": 0.0,
|
| 215 |
+
"loss_idm_coord": 0.03154296875,
|
| 216 |
+
"loss_idm_text": 0.7847968459129333,
|
| 217 |
+
"loss_idm_type": 0.6001523256301879,
|
| 218 |
+
"loss_sft": 0.014024525508284568,
|
| 219 |
+
"step": 140,
|
| 220 |
+
"token_acc": 0.8488714086911894
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.034594594594594595,
|
| 224 |
+
"grad_norm": 250.71766662597656,
|
| 225 |
+
"learning_rate": 9.98292246503335e-06,
|
| 226 |
+
"loss": 26.04180908203125,
|
| 227 |
+
"loss_idm": 1.5328125,
|
| 228 |
+
"loss_idm_anl": 0.0,
|
| 229 |
+
"loss_idm_coord": 0.0306640625,
|
| 230 |
+
"loss_idm_text": 0.9394279241561889,
|
| 231 |
+
"loss_idm_type": 0.6282362818717957,
|
| 232 |
+
"loss_sft": 0.014096884429454804,
|
| 233 |
+
"step": 150,
|
| 234 |
+
"token_acc": 0.8478837080550887
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.0369009009009009,
|
| 238 |
+
"grad_norm": 166.97149658203125,
|
| 239 |
+
"learning_rate": 9.975414512725058e-06,
|
| 240 |
+
"loss": 21.466415405273438,
|
| 241 |
+
"loss_idm": 1.246875,
|
| 242 |
+
"loss_idm_anl": 0.0,
|
| 243 |
+
"loss_idm_coord": 0.032177734375,
|
| 244 |
+
"loss_idm_text": 0.7001996755599975,
|
| 245 |
+
"loss_idm_type": 0.5806768774986267,
|
| 246 |
+
"loss_sft": 0.013779866695404052,
|
| 247 |
+
"step": 160,
|
| 248 |
+
"token_acc": 0.8516435390217498
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.03920720720720721,
|
| 252 |
+
"grad_norm": 166.47470092773438,
|
| 253 |
+
"learning_rate": 9.966546331768192e-06,
|
| 254 |
+
"loss": 21.78998565673828,
|
| 255 |
+
"loss_idm": 1.2703125,
|
| 256 |
+
"loss_idm_anl": 0.0,
|
| 257 |
+
"loss_idm_coord": 0.0283203125,
|
| 258 |
+
"loss_idm_text": 0.6905548334121704,
|
| 259 |
+
"loss_idm_type": 0.6141234040260315,
|
| 260 |
+
"loss_sft": 0.014114163070917129,
|
| 261 |
+
"step": 170,
|
| 262 |
+
"token_acc": 0.8484753365377703
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.04151351351351351,
|
| 266 |
+
"grad_norm": 218.82046508789062,
|
| 267 |
+
"learning_rate": 9.956320346634877e-06,
|
| 268 |
+
"loss": 22.165342712402342,
|
| 269 |
+
"loss_idm": 1.2859375,
|
| 270 |
+
"loss_idm_anl": 0.0,
|
| 271 |
+
"loss_idm_coord": 0.02763671875,
|
| 272 |
+
"loss_idm_text": 0.7303984642028809,
|
| 273 |
+
"loss_idm_type": 0.5983686685562134,
|
| 274 |
+
"loss_sft": 0.013757656514644622,
|
| 275 |
+
"step": 180,
|
| 276 |
+
"token_acc": 0.8512506835204802
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.04381981981981982,
|
| 280 |
+
"grad_norm": 219.92880249023438,
|
| 281 |
+
"learning_rate": 9.944739353007344e-06,
|
| 282 |
+
"loss": 21.063986206054686,
|
| 283 |
+
"loss_idm": 1.209375,
|
| 284 |
+
"loss_idm_anl": 0.0,
|
| 285 |
+
"loss_idm_coord": 0.02802734375,
|
| 286 |
+
"loss_idm_text": 0.6704511880874634,
|
| 287 |
+
"loss_idm_type": 0.589215099811554,
|
| 288 |
+
"loss_sft": 0.014041738212108612,
|
| 289 |
+
"step": 190,
|
| 290 |
+
"token_acc": 0.8489764234034295
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.04612612612612613,
|
| 294 |
+
"grad_norm": 160.0710906982422,
|
| 295 |
+
"learning_rate": 9.931806517013612e-06,
|
| 296 |
+
"loss": 22.00762023925781,
|
| 297 |
+
"loss_idm": 1.26875,
|
| 298 |
+
"loss_idm_anl": 0.0,
|
| 299 |
+
"loss_idm_coord": 0.028125,
|
| 300 |
+
"loss_idm_text": 0.649952232837677,
|
| 301 |
+
"loss_idm_type": 0.6678654789924622,
|
| 302 |
+
"loss_sft": 0.014099276438355447,
|
| 303 |
+
"step": 200,
|
| 304 |
+
"token_acc": 0.8480138468195586
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.048432432432432435,
|
| 308 |
+
"grad_norm": 231.97708129882812,
|
| 309 |
+
"learning_rate": 9.917525374361913e-06,
|
| 310 |
+
"loss": 22.615927124023436,
|
| 311 |
+
"loss_idm": 1.3203125,
|
| 312 |
+
"loss_idm_anl": 0.0,
|
| 313 |
+
"loss_idm_coord": 0.0266357421875,
|
| 314 |
+
"loss_idm_text": 0.7614493370056152,
|
| 315 |
+
"loss_idm_type": 0.5959304571151733,
|
| 316 |
+
"loss_sft": 0.014167248830199241,
|
| 317 |
+
"step": 210,
|
| 318 |
+
"token_acc": 0.8475955923181496
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.050738738738738735,
|
| 322 |
+
"grad_norm": 199.168212890625,
|
| 323 |
+
"learning_rate": 9.901899829374048e-06,
|
| 324 |
+
"loss": 20.7582763671875,
|
| 325 |
+
"loss_idm": 1.1828125,
|
| 326 |
+
"loss_idm_anl": 0.0,
|
| 327 |
+
"loss_idm_coord": 0.030615234375,
|
| 328 |
+
"loss_idm_text": 0.6515186548233032,
|
| 329 |
+
"loss_idm_type": 0.5868193507194519,
|
| 330 |
+
"loss_sft": 0.013925193250179291,
|
| 331 |
+
"step": 220,
|
| 332 |
+
"token_acc": 0.8496626268588034
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.05304504504504504,
|
| 336 |
+
"grad_norm": 160.00375366210938,
|
| 337 |
+
"learning_rate": 9.884934153917998e-06,
|
| 338 |
+
"loss": 22.84142608642578,
|
| 339 |
+
"loss_idm": 1.34375,
|
| 340 |
+
"loss_idm_anl": 0.0,
|
| 341 |
+
"loss_idm_coord": 0.028173828125,
|
| 342 |
+
"loss_idm_text": 0.7582223653793335,
|
| 343 |
+
"loss_idm_type": 0.6115516662597656,
|
| 344 |
+
"loss_sft": 0.014063675329089165,
|
| 345 |
+
"step": 230,
|
| 346 |
+
"token_acc": 0.8490615719208343
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.05535135135135135,
|
| 350 |
+
"grad_norm": 185.79376220703125,
|
| 351 |
+
"learning_rate": 9.86663298624003e-06,
|
| 352 |
+
"loss": 21.26628875732422,
|
| 353 |
+
"loss_idm": 1.225,
|
| 354 |
+
"loss_idm_anl": 0.0,
|
| 355 |
+
"loss_idm_coord": 0.02509765625,
|
| 356 |
+
"loss_idm_text": 0.7225316286087036,
|
| 357 |
+
"loss_idm_type": 0.5519452333450318,
|
| 358 |
+
"loss_sft": 0.014292314276099205,
|
| 359 |
+
"step": 240,
|
| 360 |
+
"token_acc": 0.8462079420660857
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.05765765765765766,
|
| 364 |
+
"grad_norm": 165.556884765625,
|
| 365 |
+
"learning_rate": 9.847001329696653e-06,
|
| 366 |
+
"loss": 20.54603271484375,
|
| 367 |
+
"loss_idm": 1.1765625,
|
| 368 |
+
"loss_idm_anl": 0.0,
|
| 369 |
+
"loss_idm_coord": 0.02568359375,
|
| 370 |
+
"loss_idm_text": 0.6419167995452881,
|
| 371 |
+
"loss_idm_type": 0.586991822719574,
|
| 372 |
+
"loss_sft": 0.014299248531460761,
|
| 373 |
+
"step": 250,
|
| 374 |
+
"token_acc": 0.846426558505606
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.059963963963963966,
|
| 378 |
+
"grad_norm": 181.50538635253906,
|
| 379 |
+
"learning_rate": 9.826044551386743e-06,
|
| 380 |
+
"loss": 21.09702911376953,
|
| 381 |
+
"loss_idm": 1.2109375,
|
| 382 |
+
"loss_idm_anl": 0.0,
|
| 383 |
+
"loss_idm_coord": 0.023583984375,
|
| 384 |
+
"loss_idm_text": 0.6792068004608154,
|
| 385 |
+
"loss_idm_type": 0.5862257599830627,
|
| 386 |
+
"loss_sft": 0.014360376074910164,
|
| 387 |
+
"step": 260,
|
| 388 |
+
"token_acc": 0.8455009827053707
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.06227027027027027,
|
| 392 |
+
"grad_norm": 159.72378540039062,
|
| 393 |
+
"learning_rate": 9.803768380684242e-06,
|
| 394 |
+
"loss": 20.137149047851562,
|
| 395 |
+
"loss_idm": 1.1671875,
|
| 396 |
+
"loss_idm_anl": 0.0,
|
| 397 |
+
"loss_idm_coord": 0.02783203125,
|
| 398 |
+
"loss_idm_text": 0.6360970735549927,
|
| 399 |
+
"loss_idm_type": 0.5649659037590027,
|
| 400 |
+
"loss_sft": 0.014287288114428521,
|
| 401 |
+
"step": 270,
|
| 402 |
+
"token_acc": 0.8466014645893744
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.06457657657657657,
|
| 406 |
+
"grad_norm": 142.44703674316406,
|
| 407 |
+
"learning_rate": 9.780178907671788e-06,
|
| 408 |
+
"loss": 21.38773193359375,
|
| 409 |
+
"loss_idm": 1.2390625,
|
| 410 |
+
"loss_idm_anl": 0.0,
|
| 411 |
+
"loss_idm_coord": 0.027734375,
|
| 412 |
+
"loss_idm_text": 0.679478108882904,
|
| 413 |
+
"loss_idm_type": 0.5993240475654602,
|
| 414 |
+
"loss_sft": 0.014427094906568527,
|
| 415 |
+
"step": 280,
|
| 416 |
+
"token_acc": 0.845819646334507
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.06688288288288288,
|
| 420 |
+
"grad_norm": 167.3060302734375,
|
| 421 |
+
"learning_rate": 9.755282581475769e-06,
|
| 422 |
+
"loss": 18.871426391601563,
|
| 423 |
+
"loss_idm": 1.0859375,
|
| 424 |
+
"loss_idm_anl": 0.0,
|
| 425 |
+
"loss_idm_coord": 0.026220703125,
|
| 426 |
+
"loss_idm_text": 0.5865870356559754,
|
| 427 |
+
"loss_idm_type": 0.536228609085083,
|
| 428 |
+
"loss_sft": 0.014549480751156807,
|
| 429 |
+
"step": 290,
|
| 430 |
+
"token_acc": 0.8449012068675806
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.06918918918918919,
|
| 434 |
+
"grad_norm": 138.20761108398438,
|
| 435 |
+
"learning_rate": 9.729086208503174e-06,
|
| 436 |
+
"loss": 20.88959197998047,
|
| 437 |
+
"loss_idm": 1.221875,
|
| 438 |
+
"loss_idm_anl": 0.0,
|
| 439 |
+
"loss_idm_coord": 0.026416015625,
|
| 440 |
+
"loss_idm_text": 0.7052467823028564,
|
| 441 |
+
"loss_idm_type": 0.5426920533180237,
|
| 442 |
+
"loss_sft": 0.014955276995897293,
|
| 443 |
+
"step": 300,
|
| 444 |
+
"token_acc": 0.8407353983815368
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.0714954954954955,
|
| 448 |
+
"grad_norm": 183.0985565185547,
|
| 449 |
+
"learning_rate": 9.701596950580807e-06,
|
| 450 |
+
"loss": 20.191453552246095,
|
| 451 |
+
"loss_idm": 1.153125,
|
| 452 |
+
"loss_idm_anl": 0.0,
|
| 453 |
+
"loss_idm_coord": 0.0275390625,
|
| 454 |
+
"loss_idm_text": 0.6399867296218872,
|
| 455 |
+
"loss_idm_type": 0.5646127104759217,
|
| 456 |
+
"loss_sft": 0.01429852657020092,
|
| 457 |
+
"step": 310,
|
| 458 |
+
"token_acc": 0.8468957501589651
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.0738018018018018,
|
| 462 |
+
"grad_norm": 139.37664794921875,
|
| 463 |
+
"learning_rate": 9.672822322997305e-06,
|
| 464 |
+
"loss": 18.14356384277344,
|
| 465 |
+
"loss_idm": 1.053125,
|
| 466 |
+
"loss_idm_anl": 0.0,
|
| 467 |
+
"loss_idm_coord": 0.024609375,
|
| 468 |
+
"loss_idm_text": 0.5447785139083863,
|
| 469 |
+
"loss_idm_type": 0.534551739692688,
|
| 470 |
+
"loss_sft": 0.01457935906946659,
|
| 471 |
+
"step": 320,
|
| 472 |
+
"token_acc": 0.8441828406914472
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.07610810810810811,
|
| 476 |
+
"grad_norm": 165.80722045898438,
|
| 477 |
+
"learning_rate": 9.642770192448537e-06,
|
| 478 |
+
"loss": 21.30792236328125,
|
| 479 |
+
"loss_idm": 1.2375,
|
| 480 |
+
"loss_idm_anl": 0.0,
|
| 481 |
+
"loss_idm_coord": 0.0251953125,
|
| 482 |
+
"loss_idm_text": 0.7330950379371644,
|
| 483 |
+
"loss_idm_type": 0.5434134244918823,
|
| 484 |
+
"loss_sft": 0.014491663500666618,
|
| 485 |
+
"step": 330,
|
| 486 |
+
"token_acc": 0.844535425337065
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.07841441441441442,
|
| 490 |
+
"grad_norm": 135.9119415283203,
|
| 491 |
+
"learning_rate": 9.611448774886925e-06,
|
| 492 |
+
"loss": 21.87939910888672,
|
| 493 |
+
"loss_idm": 1.271875,
|
| 494 |
+
"loss_idm_anl": 0.0,
|
| 495 |
+
"loss_idm_coord": 0.02431640625,
|
| 496 |
+
"loss_idm_text": 0.7017751932144165,
|
| 497 |
+
"loss_idm_type": 0.6117419362068176,
|
| 498 |
+
"loss_sft": 0.01456201747059822,
|
| 499 |
+
"step": 340,
|
| 500 |
+
"token_acc": 0.8440950452721977
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.08072072072072072,
|
| 504 |
+
"grad_norm": 168.16905212402344,
|
| 505 |
+
"learning_rate": 9.578866633275289e-06,
|
| 506 |
+
"loss": 20.681498718261718,
|
| 507 |
+
"loss_idm": 1.18125,
|
| 508 |
+
"loss_idm_anl": 0.0,
|
| 509 |
+
"loss_idm_coord": 0.023046875,
|
| 510 |
+
"loss_idm_text": 0.6695239424705506,
|
| 511 |
+
"loss_idm_type": 0.5692394852638245,
|
| 512 |
+
"loss_sft": 0.014816844463348388,
|
| 513 |
+
"step": 350,
|
| 514 |
+
"token_acc": 0.8415710439552528
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.08302702702702702,
|
| 518 |
+
"grad_norm": 166.8290252685547,
|
| 519 |
+
"learning_rate": 9.545032675245814e-06,
|
| 520 |
+
"loss": 18.921286010742186,
|
| 521 |
+
"loss_idm": 1.1046875,
|
| 522 |
+
"loss_idm_anl": 0.0,
|
| 523 |
+
"loss_idm_coord": 0.0237548828125,
|
| 524 |
+
"loss_idm_text": 0.6103208661079407,
|
| 525 |
+
"loss_idm_type": 0.519065773487091,
|
| 526 |
+
"loss_sft": 0.014447029307484626,
|
| 527 |
+
"step": 360,
|
| 528 |
+
"token_acc": 0.8450666103171796
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.08533333333333333,
|
| 532 |
+
"grad_norm": 126.34339904785156,
|
| 533 |
+
"learning_rate": 9.509956150664796e-06,
|
| 534 |
+
"loss": 18.619956970214844,
|
| 535 |
+
"loss_idm": 1.084375,
|
| 536 |
+
"loss_idm_anl": 0.0,
|
| 537 |
+
"loss_idm_coord": 0.02314453125,
|
| 538 |
+
"loss_idm_text": 0.6043006479740143,
|
| 539 |
+
"loss_idm_type": 0.5059460878372193,
|
| 540 |
+
"loss_sft": 0.014802501350641251,
|
| 541 |
+
"step": 370,
|
| 542 |
+
"token_acc": 0.8417970844912486
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.08763963963963964,
|
| 546 |
+
"grad_norm": 196.3380584716797,
|
| 547 |
+
"learning_rate": 9.473646649103819e-06,
|
| 548 |
+
"loss": 20.677947998046875,
|
| 549 |
+
"loss_idm": 1.1921875,
|
| 550 |
+
"loss_idm_anl": 0.0,
|
| 551 |
+
"loss_idm_coord": 0.0225830078125,
|
| 552 |
+
"loss_idm_text": 0.6596546173095703,
|
| 553 |
+
"loss_idm_type": 0.5795348882675171,
|
| 554 |
+
"loss_sft": 0.014789283275604248,
|
| 555 |
+
"step": 380,
|
| 556 |
+
"token_acc": 0.8423334299504732
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.08994594594594595,
|
| 560 |
+
"grad_norm": 134.393798828125,
|
| 561 |
+
"learning_rate": 9.43611409721806e-06,
|
| 562 |
+
"loss": 18.679299926757814,
|
| 563 |
+
"loss_idm": 1.0765625,
|
| 564 |
+
"loss_idm_anl": 0.0,
|
| 565 |
+
"loss_idm_coord": 0.023193359375,
|
| 566 |
+
"loss_idm_text": 0.5959227085113525,
|
| 567 |
+
"loss_idm_type": 0.5186289191246033,
|
| 568 |
+
"loss_sft": 0.01440901979804039,
|
| 569 |
+
"step": 390,
|
| 570 |
+
"token_acc": 0.845818279940636
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.09225225225225225,
|
| 574 |
+
"grad_norm": 152.67922973632812,
|
| 575 |
+
"learning_rate": 9.397368756032445e-06,
|
| 576 |
+
"loss": 19.257763671875,
|
| 577 |
+
"loss_idm": 1.109375,
|
| 578 |
+
"loss_idm_anl": 0.0,
|
| 579 |
+
"loss_idm_coord": 0.0220703125,
|
| 580 |
+
"loss_idm_text": 0.628661286830902,
|
| 581 |
+
"loss_idm_type": 0.5230772495269775,
|
| 582 |
+
"loss_sft": 0.014480241760611533,
|
| 583 |
+
"step": 400,
|
| 584 |
+
"token_acc": 0.8448503815357494
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.09455855855855856,
|
| 588 |
+
"grad_norm": 122.16210174560547,
|
| 589 |
+
"learning_rate": 9.357421218136387e-06,
|
| 590 |
+
"loss": 19.842500305175783,
|
| 591 |
+
"loss_idm": 1.14375,
|
| 592 |
+
"loss_idm_anl": 0.0,
|
| 593 |
+
"loss_idm_coord": 0.023193359375,
|
| 594 |
+
"loss_idm_text": 0.6230831980705261,
|
| 595 |
+
"loss_idm_type": 0.5645471215248108,
|
| 596 |
+
"loss_sft": 0.014090249687433243,
|
| 597 |
+
"step": 410,
|
| 598 |
+
"token_acc": 0.8484338211188269
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.09686486486486487,
|
| 602 |
+
"grad_norm": 167.9059295654297,
|
| 603 |
+
"learning_rate": 9.31628240478787e-06,
|
| 604 |
+
"loss": 20.216983032226562,
|
| 605 |
+
"loss_idm": 1.1921875,
|
| 606 |
+
"loss_idm_anl": 0.0,
|
| 607 |
+
"loss_idm_coord": 0.0225830078125,
|
| 608 |
+
"loss_idm_text": 0.6476395845413208,
|
| 609 |
+
"loss_idm_type": 0.5624619722366333,
|
| 610 |
+
"loss_sft": 0.01480226032435894,
|
| 611 |
+
"step": 420,
|
| 612 |
+
"token_acc": 0.8419641120404591
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.09917117117117118,
|
| 616 |
+
"grad_norm": 168.45751953125,
|
| 617 |
+
"learning_rate": 9.273963562927695e-06,
|
| 618 |
+
"loss": 19.274252319335936,
|
| 619 |
+
"loss_idm": 1.1203125,
|
| 620 |
+
"loss_idm_anl": 0.0,
|
| 621 |
+
"loss_idm_coord": 0.0229736328125,
|
| 622 |
+
"loss_idm_text": 0.5932227373123169,
|
| 623 |
+
"loss_idm_type": 0.5581031084060669,
|
| 624 |
+
"loss_sft": 0.014671726524829865,
|
| 625 |
+
"step": 430,
|
| 626 |
+
"token_acc": 0.8432967886740331
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.10147747747747747,
|
| 630 |
+
"grad_norm": 185.98695373535156,
|
| 631 |
+
"learning_rate": 9.230476262104678e-06,
|
| 632 |
+
"loss": 20.714811706542967,
|
| 633 |
+
"loss_idm": 1.2,
|
| 634 |
+
"loss_idm_anl": 0.0,
|
| 635 |
+
"loss_idm_coord": 0.0226806640625,
|
| 636 |
+
"loss_idm_text": 0.697117555141449,
|
| 637 |
+
"loss_idm_type": 0.5450912117958069,
|
| 638 |
+
"loss_sft": 0.014781413972377777,
|
| 639 |
+
"step": 440,
|
| 640 |
+
"token_acc": 0.841088699598131
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.10378378378378378,
|
| 644 |
+
"grad_norm": 86.4629135131836,
|
| 645 |
+
"learning_rate": 9.185832391312644e-06,
|
| 646 |
+
"loss": 20.035540771484374,
|
| 647 |
+
"loss_idm": 1.1671875,
|
| 648 |
+
"loss_idm_anl": 0.0,
|
| 649 |
+
"loss_idm_coord": 0.0203857421875,
|
| 650 |
+
"loss_idm_text": 0.7159459352493286,
|
| 651 |
+
"loss_idm_type": 0.48527697324752805,
|
| 652 |
+
"loss_sft": 0.014686542749404907,
|
| 653 |
+
"step": 450,
|
| 654 |
+
"token_acc": 0.8427634581544566
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.10609009009009009,
|
| 658 |
+
"grad_norm": 187.40481567382812,
|
| 659 |
+
"learning_rate": 9.140044155740102e-06,
|
| 660 |
+
"loss": 19.649851989746093,
|
| 661 |
+
"loss_idm": 1.1328125,
|
| 662 |
+
"loss_idm_anl": 0.0,
|
| 663 |
+
"loss_idm_coord": 0.0243408203125,
|
| 664 |
+
"loss_idm_text": 0.6601190686225891,
|
| 665 |
+
"loss_idm_type": 0.5130853056907654,
|
| 666 |
+
"loss_sft": 0.014707070216536522,
|
| 667 |
+
"step": 460,
|
| 668 |
+
"token_acc": 0.8420556576404618
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.1083963963963964,
|
| 672 |
+
"grad_norm": 182.9649200439453,
|
| 673 |
+
"learning_rate": 9.093124073433464e-06,
|
| 674 |
+
"loss": 20.768836975097656,
|
| 675 |
+
"loss_idm": 1.2015625,
|
| 676 |
+
"loss_idm_anl": 0.0,
|
| 677 |
+
"loss_idm_coord": 0.0226806640625,
|
| 678 |
+
"loss_idm_text": 0.7002580642700196,
|
| 679 |
+
"loss_idm_type": 0.5446828842163086,
|
| 680 |
+
"loss_sft": 0.014763540402054787,
|
| 681 |
+
"step": 470,
|
| 682 |
+
"token_acc": 0.8420311073517537
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.1107027027027027,
|
| 686 |
+
"grad_norm": 149.92550659179688,
|
| 687 |
+
"learning_rate": 9.045084971874738e-06,
|
| 688 |
+
"loss": 18.808259582519533,
|
| 689 |
+
"loss_idm": 1.084375,
|
| 690 |
+
"loss_idm_anl": 0.0,
|
| 691 |
+
"loss_idm_coord": 0.0229736328125,
|
| 692 |
+
"loss_idm_text": 0.602880334854126,
|
| 693 |
+
"loss_idm_type": 0.5190148711204529,
|
| 694 |
+
"loss_sft": 0.014968127384781838,
|
| 695 |
+
"step": 480,
|
| 696 |
+
"token_acc": 0.8410174126994425
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.11300900900900901,
|
| 700 |
+
"grad_norm": 137.2638702392578,
|
| 701 |
+
"learning_rate": 8.995939984474624e-06,
|
| 702 |
+
"loss": 20.157275390625,
|
| 703 |
+
"loss_idm": 1.1765625,
|
| 704 |
+
"loss_idm_anl": 0.0,
|
| 705 |
+
"loss_idm_coord": 0.0243408203125,
|
| 706 |
+
"loss_idm_text": 0.6711506247520447,
|
| 707 |
+
"loss_idm_type": 0.5331731677055359,
|
| 708 |
+
"loss_sft": 0.014955581724643707,
|
| 709 |
+
"step": 490,
|
| 710 |
+
"token_acc": 0.840715306484563
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.11531531531531532,
|
| 714 |
+
"grad_norm": 142.88665771484375,
|
| 715 |
+
"learning_rate": 8.94570254698197e-06,
|
| 716 |
+
"loss": 19.9982666015625,
|
| 717 |
+
"loss_idm": 1.1578125,
|
| 718 |
+
"loss_idm_anl": 0.0,
|
| 719 |
+
"loss_idm_coord": 0.0236328125,
|
| 720 |
+
"loss_idm_text": 0.6669049620628357,
|
| 721 |
+
"loss_idm_type": 0.5289612531661987,
|
| 722 |
+
"loss_sft": 0.014832272753119468,
|
| 723 |
+
"step": 500,
|
| 724 |
+
"token_acc": 0.8413044197474939
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.11531531531531532,
|
| 728 |
+
"eval_loss": 1.343860387802124,
|
| 729 |
+
"eval_runtime": 169.0406,
|
| 730 |
+
"eval_samples_per_second": 10.323,
|
| 731 |
+
"eval_steps_per_second": 2.585,
|
| 732 |
+
"eval_token_acc": 0.8296746896271974,
|
| 733 |
+
"step": 500
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.11762162162162162,
|
| 737 |
+
"grad_norm": 121.90780639648438,
|
| 738 |
+
"learning_rate": 8.894386393810563e-06,
|
| 739 |
+
"loss": 19.183363342285155,
|
| 740 |
+
"loss_idm": 1.10703125,
|
| 741 |
+
"loss_idm_anl": 0.0,
|
| 742 |
+
"loss_idm_coord": 0.02314453125,
|
| 743 |
+
"loss_idm_text": 0.6232369840145111,
|
| 744 |
+
"loss_idm_type": 0.5219475150108337,
|
| 745 |
+
"loss_sft": 0.014694250002503396,
|
| 746 |
+
"step": 510,
|
| 747 |
+
"token_acc": 0.8422317950328234
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.11992792792792793,
|
| 751 |
+
"grad_norm": 130.7283477783203,
|
| 752 |
+
"learning_rate": 8.842005554284296e-06,
|
| 753 |
+
"loss": 21.542631530761717,
|
| 754 |
+
"loss_idm": 1.275,
|
| 755 |
+
"loss_idm_anl": 0.0,
|
| 756 |
+
"loss_idm_coord": 0.023486328125,
|
| 757 |
+
"loss_idm_text": 0.7642043590545654,
|
| 758 |
+
"loss_idm_type": 0.527753472328186,
|
| 759 |
+
"loss_sft": 0.014815109595656396,
|
| 760 |
+
"step": 520,
|
| 761 |
+
"token_acc": 0.8421332755567278
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.12223423423423424,
|
| 765 |
+
"grad_norm": 139.00326538085938,
|
| 766 |
+
"learning_rate": 8.788574348801676e-06,
|
| 767 |
+
"loss": 19.373654174804688,
|
| 768 |
+
"loss_idm": 1.1203125,
|
| 769 |
+
"loss_idm_anl": 0.0,
|
| 770 |
+
"loss_idm_coord": 0.0209228515625,
|
| 771 |
+
"loss_idm_text": 0.632088041305542,
|
| 772 |
+
"loss_idm_type": 0.5272146463394165,
|
| 773 |
+
"loss_sft": 0.014772192761301994,
|
| 774 |
+
"step": 530,
|
| 775 |
+
"token_acc": 0.8428789749734085
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.12454054054054053,
|
| 779 |
+
"grad_norm": 139.85838317871094,
|
| 780 |
+
"learning_rate": 8.734107384920771e-06,
|
| 781 |
+
"loss": 19.69678649902344,
|
| 782 |
+
"loss_idm": 1.1359375,
|
| 783 |
+
"loss_idm_anl": 0.0,
|
| 784 |
+
"loss_idm_coord": 0.0214111328125,
|
| 785 |
+
"loss_idm_text": 0.6562704801559448,
|
| 786 |
+
"loss_idm_type": 0.5232262134552002,
|
| 787 |
+
"loss_sft": 0.014777998626232147,
|
| 788 |
+
"step": 540,
|
| 789 |
+
"token_acc": 0.8425625030223899
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.12684684684684686,
|
| 793 |
+
"grad_norm": 148.52243041992188,
|
| 794 |
+
"learning_rate": 8.67861955336566e-06,
|
| 795 |
+
"loss": 18.976077270507812,
|
| 796 |
+
"loss_idm": 1.0984375,
|
| 797 |
+
"loss_idm_anl": 0.0,
|
| 798 |
+
"loss_idm_coord": 0.021044921875,
|
| 799 |
+
"loss_idm_text": 0.6217063784599304,
|
| 800 |
+
"loss_idm_type": 0.5128381371498107,
|
| 801 |
+
"loss_sft": 0.014830715954303741,
|
| 802 |
+
"step": 550,
|
| 803 |
+
"token_acc": 0.8408637973317883
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.12915315315315315,
|
| 807 |
+
"grad_norm": 146.99465942382812,
|
| 808 |
+
"learning_rate": 8.622126023955446e-06,
|
| 809 |
+
"loss": 17.574090576171876,
|
| 810 |
+
"loss_idm": 1.021875,
|
| 811 |
+
"loss_idm_anl": 0.0,
|
| 812 |
+
"loss_idm_coord": 0.0211181640625,
|
| 813 |
+
"loss_idm_text": 0.5682262539863586,
|
| 814 |
+
"loss_idm_type": 0.4789894104003906,
|
| 815 |
+
"loss_sft": 0.014643288403749465,
|
| 816 |
+
"step": 560,
|
| 817 |
+
"token_acc": 0.8428118655908181
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.13145945945945947,
|
| 821 |
+
"grad_norm": 152.93589782714844,
|
| 822 |
+
"learning_rate": 8.564642241456986e-06,
|
| 823 |
+
"loss": 19.4894775390625,
|
| 824 |
+
"loss_idm": 1.1359375,
|
| 825 |
+
"loss_idm_anl": 0.0,
|
| 826 |
+
"loss_idm_coord": 0.0201904296875,
|
| 827 |
+
"loss_idm_text": 0.6324522256851196,
|
| 828 |
+
"loss_idm_type": 0.5348370909690857,
|
| 829 |
+
"loss_sft": 0.014856469631195069,
|
| 830 |
+
"step": 570,
|
| 831 |
+
"token_acc": 0.8417346370130199
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.13376576576576577,
|
| 835 |
+
"grad_norm": 123.00813293457031,
|
| 836 |
+
"learning_rate": 8.506183921362443e-06,
|
| 837 |
+
"loss": 18.439350891113282,
|
| 838 |
+
"loss_idm": 1.046875,
|
| 839 |
+
"loss_idm_anl": 0.0,
|
| 840 |
+
"loss_idm_coord": 0.0206298828125,
|
| 841 |
+
"loss_idm_text": 0.5719715774059295,
|
| 842 |
+
"loss_idm_type": 0.5290378570556641,
|
| 843 |
+
"loss_sft": 0.01490309163928032,
|
| 844 |
+
"step": 580,
|
| 845 |
+
"token_acc": 0.8404926826479667
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.13607207207207206,
|
| 849 |
+
"grad_norm": 123.43096923828125,
|
| 850 |
+
"learning_rate": 8.446767045592829e-06,
|
| 851 |
+
"loss": 19.559785461425783,
|
| 852 |
+
"loss_idm": 1.1203125,
|
| 853 |
+
"loss_idm_anl": 0.0,
|
| 854 |
+
"loss_idm_coord": 0.022509765625,
|
| 855 |
+
"loss_idm_text": 0.6619894862174988,
|
| 856 |
+
"loss_idm_type": 0.5079665780067444,
|
| 857 |
+
"loss_sft": 0.014454486221075058,
|
| 858 |
+
"step": 590,
|
| 859 |
+
"token_acc": 0.8448515319710282
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.13837837837837838,
|
| 863 |
+
"grad_norm": 132.0702667236328,
|
| 864 |
+
"learning_rate": 8.386407858128707e-06,
|
| 865 |
+
"loss": 17.04791717529297,
|
| 866 |
+
"loss_idm": 0.971875,
|
| 867 |
+
"loss_idm_anl": 0.0,
|
| 868 |
+
"loss_idm_coord": 0.0239501953125,
|
| 869 |
+
"loss_idm_text": 0.5366034507751465,
|
| 870 |
+
"loss_idm_type": 0.4742018222808838,
|
| 871 |
+
"loss_sft": 0.014516119658946992,
|
| 872 |
+
"step": 600,
|
| 873 |
+
"token_acc": 0.8445947126557285
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.14068468468468467,
|
| 877 |
+
"grad_norm": 115.69120025634766,
|
| 878 |
+
"learning_rate": 8.325122860569241e-06,
|
| 879 |
+
"loss": 16.37723388671875,
|
| 880 |
+
"loss_idm": 0.9421875,
|
| 881 |
+
"loss_idm_anl": 0.0,
|
| 882 |
+
"loss_idm_coord": 0.0227783203125,
|
| 883 |
+
"loss_idm_text": 0.500444620847702,
|
| 884 |
+
"loss_idm_type": 0.4702631950378418,
|
| 885 |
+
"loss_sft": 0.014540355652570724,
|
| 886 |
+
"step": 610,
|
| 887 |
+
"token_acc": 0.8434274898223862
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.142990990990991,
|
| 891 |
+
"grad_norm": 130.52622985839844,
|
| 892 |
+
"learning_rate": 8.262928807620843e-06,
|
| 893 |
+
"loss": 17.805007934570312,
|
| 894 |
+
"loss_idm": 1.028125,
|
| 895 |
+
"loss_idm_anl": 0.0,
|
| 896 |
+
"loss_idm_coord": 0.02314453125,
|
| 897 |
+
"loss_idm_text": 0.5241958260536194,
|
| 898 |
+
"loss_idm_type": 0.5350467205047608,
|
| 899 |
+
"loss_sft": 0.014786705374717712,
|
| 900 |
+
"step": 620,
|
| 901 |
+
"token_acc": 0.8413365725890637
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.1452972972972973,
|
| 905 |
+
"grad_norm": 164.35609436035156,
|
| 906 |
+
"learning_rate": 8.199842702516584e-06,
|
| 907 |
+
"loss": 17.97591552734375,
|
| 908 |
+
"loss_idm": 1.0296875,
|
| 909 |
+
"loss_idm_anl": 0.0,
|
| 910 |
+
"loss_idm_coord": 0.0201904296875,
|
| 911 |
+
"loss_idm_text": 0.5606541872024536,
|
| 912 |
+
"loss_idm_type": 0.511587917804718,
|
| 913 |
+
"loss_sft": 0.01503448113799095,
|
| 914 |
+
"step": 630,
|
| 915 |
+
"token_acc": 0.8400106109751245
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.1476036036036036,
|
| 919 |
+
"grad_norm": 156.69053649902344,
|
| 920 |
+
"learning_rate": 8.135881792367686e-06,
|
| 921 |
+
"loss": 19.665069580078125,
|
| 922 |
+
"loss_idm": 1.153125,
|
| 923 |
+
"loss_idm_anl": 0.0,
|
| 924 |
+
"loss_idm_coord": 0.0185546875,
|
| 925 |
+
"loss_idm_text": 0.6834821462631225,
|
| 926 |
+
"loss_idm_type": 0.4970504879951477,
|
| 927 |
+
"loss_sft": 0.014596361666917801,
|
| 928 |
+
"step": 640,
|
| 929 |
+
"token_acc": 0.843500234929801
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.1499099099099099,
|
| 933 |
+
"grad_norm": 135.3104705810547,
|
| 934 |
+
"learning_rate": 8.071063563448341e-06,
|
| 935 |
+
"loss": 18.526170349121095,
|
| 936 |
+
"loss_idm": 1.0796875,
|
| 937 |
+
"loss_idm_anl": 0.0,
|
| 938 |
+
"loss_idm_coord": 0.020263671875,
|
| 939 |
+
"loss_idm_text": 0.6125914216041565,
|
| 940 |
+
"loss_idm_type": 0.4950984835624695,
|
| 941 |
+
"loss_sft": 0.014367320761084556,
|
| 942 |
+
"step": 650,
|
| 943 |
+
"token_acc": 0.8459901142882337
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.15221621621621623,
|
| 947 |
+
"grad_norm": 123.56324005126953,
|
| 948 |
+
"learning_rate": 8.005405736415127e-06,
|
| 949 |
+
"loss": 17.6597412109375,
|
| 950 |
+
"loss_idm": 1.015625,
|
| 951 |
+
"loss_idm_anl": 0.0,
|
| 952 |
+
"loss_idm_coord": 0.0221435546875,
|
| 953 |
+
"loss_idm_text": 0.5704326272010803,
|
| 954 |
+
"loss_idm_type": 0.4809408187866211,
|
| 955 |
+
"loss_sft": 0.014742322266101837,
|
| 956 |
+
"step": 660,
|
| 957 |
+
"token_acc": 0.8423076448143437
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.15452252252252252,
|
| 961 |
+
"grad_norm": 127.19869995117188,
|
| 962 |
+
"learning_rate": 7.938926261462366e-06,
|
| 963 |
+
"loss": 16.650668334960937,
|
| 964 |
+
"loss_idm": 0.9515625,
|
| 965 |
+
"loss_idm_anl": 0.0,
|
| 966 |
+
"loss_idm_coord": 0.019775390625,
|
| 967 |
+
"loss_idm_text": 0.5215044260025025,
|
| 968 |
+
"loss_idm_type": 0.46839267015457153,
|
| 969 |
+
"loss_sft": 0.014879125729203224,
|
| 970 |
+
"step": 670,
|
| 971 |
+
"token_acc": 0.8405719579176686
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.15682882882882884,
|
| 975 |
+
"grad_norm": 165.220458984375,
|
| 976 |
+
"learning_rate": 7.871643313414718e-06,
|
| 977 |
+
"loss": 17.50257110595703,
|
| 978 |
+
"loss_idm": 1.0015625,
|
| 979 |
+
"loss_idm_anl": 0.0,
|
| 980 |
+
"loss_idm_coord": 0.022314453125,
|
| 981 |
+
"loss_idm_text": 0.5456109881401062,
|
| 982 |
+
"loss_idm_type": 0.4950627326965332,
|
| 983 |
+
"loss_sft": 0.01498027853667736,
|
| 984 |
+
"step": 680,
|
| 985 |
+
"token_acc": 0.8399575879479895
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.15913513513513514,
|
| 989 |
+
"grad_norm": 161.6404266357422,
|
| 990 |
+
"learning_rate": 7.803575286758365e-06,
|
| 991 |
+
"loss": 17.011473083496092,
|
| 992 |
+
"loss_idm": 0.9921875,
|
| 993 |
+
"loss_idm_anl": 0.0,
|
| 994 |
+
"loss_idm_coord": 0.0203857421875,
|
| 995 |
+
"loss_idm_text": 0.5609789371490479,
|
| 996 |
+
"loss_idm_type": 0.45157656669616697,
|
| 997 |
+
"loss_sft": 0.014758187159895898,
|
| 998 |
+
"step": 690,
|
| 999 |
+
"token_acc": 0.8414021280985645
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.16144144144144143,
|
| 1003 |
+
"grad_norm": 120.51724243164062,
|
| 1004 |
+
"learning_rate": 7.734740790612137e-06,
|
| 1005 |
+
"loss": 17.647825622558592,
|
| 1006 |
+
"loss_idm": 1.01875,
|
| 1007 |
+
"loss_idm_anl": 0.0,
|
| 1008 |
+
"loss_idm_coord": 0.0201904296875,
|
| 1009 |
+
"loss_idm_text": 0.5838465094566345,
|
| 1010 |
+
"loss_idm_type": 0.46862274408340454,
|
| 1011 |
+
"loss_sft": 0.014633599296212196,
|
| 1012 |
+
"step": 700,
|
| 1013 |
+
"token_acc": 0.8431996616079811
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.16374774774774775,
|
| 1017 |
+
"grad_norm": 170.06082153320312,
|
| 1018 |
+
"learning_rate": 7.66515864363997e-06,
|
| 1019 |
+
"loss": 19.361347961425782,
|
| 1020 |
+
"loss_idm": 1.1140625,
|
| 1021 |
+
"loss_idm_anl": 0.0,
|
| 1022 |
+
"loss_idm_coord": 0.0193115234375,
|
| 1023 |
+
"loss_idm_text": 0.682057511806488,
|
| 1024 |
+
"loss_idm_type": 0.4779606580734253,
|
| 1025 |
+
"loss_sft": 0.014754829555749893,
|
| 1026 |
+
"step": 710,
|
| 1027 |
+
"token_acc": 0.8426819048755804
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.16605405405405405,
|
| 1031 |
+
"grad_norm": 140.20143127441406,
|
| 1032 |
+
"learning_rate": 7.594847868906076e-06,
|
| 1033 |
+
"loss": 18.635955810546875,
|
| 1034 |
+
"loss_idm": 1.0734375,
|
| 1035 |
+
"loss_idm_anl": 0.0,
|
| 1036 |
+
"loss_idm_coord": 0.0216064453125,
|
| 1037 |
+
"loss_idm_text": 0.6446984887123108,
|
| 1038 |
+
"loss_idm_type": 0.46787831783294676,
|
| 1039 |
+
"loss_sft": 0.014802397787570953,
|
| 1040 |
+
"step": 720,
|
| 1041 |
+
"token_acc": 0.8416590932420016
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.16836036036036037,
|
| 1045 |
+
"grad_norm": 130.18458557128906,
|
| 1046 |
+
"learning_rate": 7.52382768867422e-06,
|
| 1047 |
+
"loss": 18.703033447265625,
|
| 1048 |
+
"loss_idm": 1.078125,
|
| 1049 |
+
"loss_idm_anl": 0.0,
|
| 1050 |
+
"loss_idm_coord": 0.0206298828125,
|
| 1051 |
+
"loss_idm_text": 0.6053381562232971,
|
| 1052 |
+
"loss_idm_type": 0.5120768785476685,
|
| 1053 |
+
"loss_sft": 0.015017282590270043,
|
| 1054 |
+
"step": 730,
|
| 1055 |
+
"token_acc": 0.8400633789067389
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.17066666666666666,
|
| 1059 |
+
"grad_norm": 141.50216674804688,
|
| 1060 |
+
"learning_rate": 7.452117519152542e-06,
|
| 1061 |
+
"loss": 17.169430541992188,
|
| 1062 |
+
"loss_idm": 0.9890625,
|
| 1063 |
+
"loss_idm_anl": 0.0,
|
| 1064 |
+
"loss_idm_coord": 0.02119140625,
|
| 1065 |
+
"loss_idm_text": 0.5741037368774414,
|
| 1066 |
+
"loss_idm_type": 0.44670088291168214,
|
| 1067 |
+
"loss_sft": 0.014911935850977897,
|
| 1068 |
+
"step": 740,
|
| 1069 |
+
"token_acc": 0.8413064777939722
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.17297297297297298,
|
| 1073 |
+
"grad_norm": 381.0265197753906,
|
| 1074 |
+
"learning_rate": 7.379736965185369e-06,
|
| 1075 |
+
"loss": 17.39481201171875,
|
| 1076 |
+
"loss_idm": 1.0078125,
|
| 1077 |
+
"loss_idm_anl": 0.0,
|
| 1078 |
+
"loss_idm_coord": 0.0203125,
|
| 1079 |
+
"loss_idm_text": 0.5736348688602447,
|
| 1080 |
+
"loss_idm_type": 0.4622136473655701,
|
| 1081 |
+
"loss_sft": 0.014967407658696174,
|
| 1082 |
+
"step": 750,
|
| 1083 |
+
"token_acc": 0.8404096603119668
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.17527927927927928,
|
| 1087 |
+
"grad_norm": 99.33075714111328,
|
| 1088 |
+
"learning_rate": 7.30670581489344e-06,
|
| 1089 |
+
"loss": 17.591326904296874,
|
| 1090 |
+
"loss_idm": 1.015625,
|
| 1091 |
+
"loss_idm_anl": 0.0,
|
| 1092 |
+
"loss_idm_coord": 0.01943359375,
|
| 1093 |
+
"loss_idm_text": 0.5623904466629028,
|
| 1094 |
+
"loss_idm_type": 0.48672530651092527,
|
| 1095 |
+
"loss_sft": 0.014822157844901086,
|
| 1096 |
+
"step": 760,
|
| 1097 |
+
"token_acc": 0.8409873327517785
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.1775855855855856,
|
| 1101 |
+
"grad_norm": 167.3463897705078,
|
| 1102 |
+
"learning_rate": 7.233044034264034e-06,
|
| 1103 |
+
"loss": 17.634791564941406,
|
| 1104 |
+
"loss_idm": 1.0203125,
|
| 1105 |
+
"loss_idm_anl": 0.0,
|
| 1106 |
+
"loss_idm_coord": 0.019189453125,
|
| 1107 |
+
"loss_idm_text": 0.5990640759468079,
|
| 1108 |
+
"loss_idm_type": 0.4531928539276123,
|
| 1109 |
+
"loss_sft": 0.01482548825442791,
|
| 1110 |
+
"step": 770,
|
| 1111 |
+
"token_acc": 0.842217710493471
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.1798918918918919,
|
| 1115 |
+
"grad_norm": 180.26498413085938,
|
| 1116 |
+
"learning_rate": 7.158771761692464e-06,
|
| 1117 |
+
"loss": 16.831851196289062,
|
| 1118 |
+
"loss_idm": 0.9734375,
|
| 1119 |
+
"loss_idm_anl": 0.0,
|
| 1120 |
+
"loss_idm_coord": 0.0206787109375,
|
| 1121 |
+
"loss_idm_text": 0.5070213794708252,
|
| 1122 |
+
"loss_idm_type": 0.49378237724304197,
|
| 1123 |
+
"loss_sft": 0.0149398323148489,
|
| 1124 |
+
"step": 780,
|
| 1125 |
+
"token_acc": 0.8399789433151118
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.18219819819819819,
|
| 1129 |
+
"grad_norm": 146.3783416748047,
|
| 1130 |
+
"learning_rate": 7.083909302476453e-06,
|
| 1131 |
+
"loss": 20.254476928710936,
|
| 1132 |
+
"loss_idm": 1.1703125,
|
| 1133 |
+
"loss_idm_anl": 0.0,
|
| 1134 |
+
"loss_idm_coord": 0.0190673828125,
|
| 1135 |
+
"loss_idm_text": 0.6638812899589539,
|
| 1136 |
+
"loss_idm_type": 0.5520286917686462,
|
| 1137 |
+
"loss_sft": 0.014968634769320487,
|
| 1138 |
+
"step": 790,
|
| 1139 |
+
"token_acc": 0.8404702738415722
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.1845045045045045,
|
| 1143 |
+
"grad_norm": 131.1219482421875,
|
| 1144 |
+
"learning_rate": 7.008477123264849e-06,
|
| 1145 |
+
"loss": 17.661578369140624,
|
| 1146 |
+
"loss_idm": 1.028125,
|
| 1147 |
+
"loss_idm_anl": 0.0,
|
| 1148 |
+
"loss_idm_coord": 0.0191650390625,
|
| 1149 |
+
"loss_idm_text": 0.6021960020065308,
|
| 1150 |
+
"loss_idm_type": 0.45235241651535035,
|
| 1151 |
+
"loss_sft": 0.014716891944408417,
|
| 1152 |
+
"step": 800,
|
| 1153 |
+
"token_acc": 0.8420775256235287
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.1868108108108108,
|
| 1157 |
+
"grad_norm": 103.17658233642578,
|
| 1158 |
+
"learning_rate": 6.932495846462262e-06,
|
| 1159 |
+
"loss": 20.432151794433594,
|
| 1160 |
+
"loss_idm": 1.184375,
|
| 1161 |
+
"loss_idm_anl": 0.0,
|
| 1162 |
+
"loss_idm_coord": 0.0184814453125,
|
| 1163 |
+
"loss_idm_text": 0.733825957775116,
|
| 1164 |
+
"loss_idm_type": 0.49434599876403806,
|
| 1165 |
+
"loss_sft": 0.014786238595843316,
|
| 1166 |
+
"step": 810,
|
| 1167 |
+
"token_acc": 0.8414228227929852
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.18911711711711712,
|
| 1171 |
+
"grad_norm": 165.00164794921875,
|
| 1172 |
+
"learning_rate": 6.855986244591104e-06,
|
| 1173 |
+
"loss": 16.781680297851562,
|
| 1174 |
+
"loss_idm": 0.96875,
|
| 1175 |
+
"loss_idm_anl": 0.0,
|
| 1176 |
+
"loss_idm_coord": 0.0200927734375,
|
| 1177 |
+
"loss_idm_text": 0.574801790714264,
|
| 1178 |
+
"loss_idm_type": 0.4236711263656616,
|
| 1179 |
+
"loss_sft": 0.014908399060368538,
|
| 1180 |
+
"step": 820,
|
| 1181 |
+
"token_acc": 0.8403310689620388
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.19142342342342342,
|
| 1185 |
+
"grad_norm": 148.9649200439453,
|
| 1186 |
+
"learning_rate": 6.778969234612583e-06,
|
| 1187 |
+
"loss": 18.193667602539062,
|
| 1188 |
+
"loss_idm": 1.0484375,
|
| 1189 |
+
"loss_idm_anl": 0.0,
|
| 1190 |
+
"loss_idm_coord": 0.01845703125,
|
| 1191 |
+
"loss_idm_text": 0.6122974157333374,
|
| 1192 |
+
"loss_idm_type": 0.47533333897590635,
|
| 1193 |
+
"loss_sft": 0.014953377842903137,
|
| 1194 |
+
"step": 830,
|
| 1195 |
+
"token_acc": 0.8400144278851671
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.19372972972972974,
|
| 1199 |
+
"grad_norm": 182.86627197265625,
|
| 1200 |
+
"learning_rate": 6.701465872208216e-06,
|
| 1201 |
+
"loss": 17.96783905029297,
|
| 1202 |
+
"loss_idm": 1.040625,
|
| 1203 |
+
"loss_idm_anl": 0.0,
|
| 1204 |
+
"loss_idm_coord": 0.020166015625,
|
| 1205 |
+
"loss_idm_text": 0.6057761192321778,
|
| 1206 |
+
"loss_idm_type": 0.46598526239395144,
|
| 1207 |
+
"loss_sft": 0.015001512691378593,
|
| 1208 |
+
"step": 840,
|
| 1209 |
+
"token_acc": 0.8398306158449229
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.19603603603603603,
|
| 1213 |
+
"grad_norm": 162.88619995117188,
|
| 1214 |
+
"learning_rate": 6.6234973460234184e-06,
|
| 1215 |
+
"loss": 14.121282958984375,
|
| 1216 |
+
"loss_idm": 0.809375,
|
| 1217 |
+
"loss_idm_anl": 0.0,
|
| 1218 |
+
"loss_idm_coord": 0.0208984375,
|
| 1219 |
+
"loss_idm_text": 0.45296228528022764,
|
| 1220 |
+
"loss_idm_type": 0.3782169342041016,
|
| 1221 |
+
"loss_sft": 0.01484096460044384,
|
| 1222 |
+
"step": 850,
|
| 1223 |
+
"token_acc": 0.8408548948297047
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.19834234234234235,
|
| 1227 |
+
"grad_norm": 138.98036193847656,
|
| 1228 |
+
"learning_rate": 6.545084971874738e-06,
|
| 1229 |
+
"loss": 19.859603881835938,
|
| 1230 |
+
"loss_idm": 1.1203125,
|
| 1231 |
+
"loss_idm_anl": 0.0,
|
| 1232 |
+
"loss_idm_coord": 0.0204345703125,
|
| 1233 |
+
"loss_idm_text": 0.6227663040161133,
|
| 1234 |
+
"loss_idm_type": 0.5677083492279053,
|
| 1235 |
+
"loss_sft": 0.014872971922159195,
|
| 1236 |
+
"step": 860,
|
| 1237 |
+
"token_acc": 0.8419059541128763
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.20064864864864865,
|
| 1241 |
+
"grad_norm": 114.0866470336914,
|
| 1242 |
+
"learning_rate": 6.466250186922325e-06,
|
| 1243 |
+
"loss": 17.332069396972656,
|
| 1244 |
+
"loss_idm": 1.0171875,
|
| 1245 |
+
"loss_idm_anl": 0.0,
|
| 1246 |
+
"loss_idm_coord": 0.019140625,
|
| 1247 |
+
"loss_idm_text": 0.5944822430610657,
|
| 1248 |
+
"loss_idm_type": 0.4399122357368469,
|
| 1249 |
+
"loss_sft": 0.01457468681037426,
|
| 1250 |
+
"step": 870,
|
| 1251 |
+
"token_acc": 0.8431677371323297
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.20295495495495494,
|
| 1255 |
+
"grad_norm": 120.35962677001953,
|
| 1256 |
+
"learning_rate": 6.387014543809224e-06,
|
| 1257 |
+
"loss": 18.15101318359375,
|
| 1258 |
+
"loss_idm": 1.04375,
|
| 1259 |
+
"loss_idm_anl": 0.0,
|
| 1260 |
+
"loss_idm_coord": 0.020361328125,
|
| 1261 |
+
"loss_idm_text": 0.6401098132133484,
|
| 1262 |
+
"loss_idm_type": 0.4436539769172668,
|
| 1263 |
+
"loss_sft": 0.0147173710167408,
|
| 1264 |
+
"step": 880,
|
| 1265 |
+
"token_acc": 0.8424536391896238
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.20526126126126126,
|
| 1269 |
+
"grad_norm": 174.99981689453125,
|
| 1270 |
+
"learning_rate": 6.3073997047691e-06,
|
| 1271 |
+
"loss": 16.543356323242186,
|
| 1272 |
+
"loss_idm": 0.9515625,
|
| 1273 |
+
"loss_idm_anl": 0.0,
|
| 1274 |
+
"loss_idm_coord": 0.019189453125,
|
| 1275 |
+
"loss_idm_text": 0.5327290534973145,
|
| 1276 |
+
"loss_idm_type": 0.4514281630516052,
|
| 1277 |
+
"loss_sft": 0.014785801619291305,
|
| 1278 |
+
"step": 890,
|
| 1279 |
+
"token_acc": 0.8419114203024312
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.20756756756756756,
|
| 1283 |
+
"grad_norm": 151.06468200683594,
|
| 1284 |
+
"learning_rate": 6.227427435703997e-06,
|
| 1285 |
+
"loss": 16.995733642578124,
|
| 1286 |
+
"loss_idm": 0.9875,
|
| 1287 |
+
"loss_idm_anl": 0.0,
|
| 1288 |
+
"loss_idm_coord": 0.018994140625,
|
| 1289 |
+
"loss_idm_text": 0.5460891246795654,
|
| 1290 |
+
"loss_idm_type": 0.4672634840011597,
|
| 1291 |
+
"loss_sft": 0.014472068846225738,
|
| 1292 |
+
"step": 900,
|
| 1293 |
+
"token_acc": 0.8442095221030661
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.20987387387387388,
|
| 1297 |
+
"grad_norm": 133.1666259765625,
|
| 1298 |
+
"learning_rate": 6.147119600233758e-06,
|
| 1299 |
+
"loss": 17.9807861328125,
|
| 1300 |
+
"loss_idm": 1.0484375,
|
| 1301 |
+
"loss_idm_anl": 0.0,
|
| 1302 |
+
"loss_idm_coord": 0.020166015625,
|
| 1303 |
+
"loss_idm_text": 0.5863479137420654,
|
| 1304 |
+
"loss_idm_type": 0.48693227767944336,
|
| 1305 |
+
"loss_sft": 0.014701117947697639,
|
| 1306 |
+
"step": 910,
|
| 1307 |
+
"token_acc": 0.8430407477028895
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.21218018018018017,
|
| 1311 |
+
"grad_norm": 184.44479370117188,
|
| 1312 |
+
"learning_rate": 6.066498153718735e-06,
|
| 1313 |
+
"loss": 16.594337463378906,
|
| 1314 |
+
"loss_idm": 0.9578125,
|
| 1315 |
+
"loss_idm_anl": 0.0,
|
| 1316 |
+
"loss_idm_coord": 0.0224365234375,
|
| 1317 |
+
"loss_idm_text": 0.551909339427948,
|
| 1318 |
+
"loss_idm_type": 0.4326519906520844,
|
| 1319 |
+
"loss_sft": 0.014737406745553017,
|
| 1320 |
+
"step": 920,
|
| 1321 |
+
"token_acc": 0.8421604346747479
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.2144864864864865,
|
| 1325 |
+
"grad_norm": 169.61996459960938,
|
| 1326 |
+
"learning_rate": 5.985585137257401e-06,
|
| 1327 |
+
"loss": 17.667451477050783,
|
| 1328 |
+
"loss_idm": 1.0171875,
|
| 1329 |
+
"loss_idm_anl": 0.0,
|
| 1330 |
+
"loss_idm_coord": 0.0206298828125,
|
| 1331 |
+
"loss_idm_text": 0.6201748490333557,
|
| 1332 |
+
"loss_idm_type": 0.43307361006736755,
|
| 1333 |
+
"loss_sft": 0.014662803709506988,
|
| 1334 |
+
"step": 930,
|
| 1335 |
+
"token_acc": 0.8420754680619393
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.2167927927927928,
|
| 1339 |
+
"grad_norm": 137.0713653564453,
|
| 1340 |
+
"learning_rate": 5.904402671660551e-06,
|
| 1341 |
+
"loss": 17.701638793945314,
|
| 1342 |
+
"loss_idm": 1.0296875,
|
| 1343 |
+
"loss_idm_anl": 0.0,
|
| 1344 |
+
"loss_idm_coord": 0.0200439453125,
|
| 1345 |
+
"loss_idm_text": 0.6406922459602356,
|
| 1346 |
+
"loss_idm_type": 0.41507343053817747,
|
| 1347 |
+
"loss_sft": 0.014637062698602677,
|
| 1348 |
+
"step": 940,
|
| 1349 |
+
"token_acc": 0.8429834188591938
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.2190990990990991,
|
| 1353 |
+
"grad_norm": 122.10049438476562,
|
| 1354 |
+
"learning_rate": 5.82297295140367e-06,
|
| 1355 |
+
"loss": 15.998197937011719,
|
| 1356 |
+
"loss_idm": 0.92890625,
|
| 1357 |
+
"loss_idm_anl": 0.0,
|
| 1358 |
+
"loss_idm_coord": 0.0203857421875,
|
| 1359 |
+
"loss_idm_text": 0.5469140887260437,
|
| 1360 |
+
"loss_idm_type": 0.4025842845439911,
|
| 1361 |
+
"loss_sft": 0.014529398083686829,
|
| 1362 |
+
"step": 950,
|
| 1363 |
+
"token_acc": 0.8437657098716236
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.2214054054054054,
|
| 1367 |
+
"grad_norm": 149.300537109375,
|
| 1368 |
+
"learning_rate": 5.74131823855921e-06,
|
| 1369 |
+
"loss": 18.87696990966797,
|
| 1370 |
+
"loss_idm": 1.103125,
|
| 1371 |
+
"loss_idm_anl": 0.0,
|
| 1372 |
+
"loss_idm_coord": 0.01923828125,
|
| 1373 |
+
"loss_idm_text": 0.6745636343955994,
|
| 1374 |
+
"loss_idm_type": 0.456106698513031,
|
| 1375 |
+
"loss_sft": 0.014411784335970878,
|
| 1376 |
+
"step": 960,
|
| 1377 |
+
"token_acc": 0.8451125206797825
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.22371171171171172,
|
| 1381 |
+
"grad_norm": 124.75553131103516,
|
| 1382 |
+
"learning_rate": 5.659460856710346e-06,
|
| 1383 |
+
"loss": 19.086871337890624,
|
| 1384 |
+
"loss_idm": 1.1125,
|
| 1385 |
+
"loss_idm_anl": 0.0,
|
| 1386 |
+
"loss_idm_coord": 0.0179443359375,
|
| 1387 |
+
"loss_idm_text": 0.7104646563529968,
|
| 1388 |
+
"loss_idm_type": 0.43523850440979006,
|
| 1389 |
+
"loss_sft": 0.014291927590966225,
|
| 1390 |
+
"step": 970,
|
| 1391 |
+
"token_acc": 0.8462941753717098
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.22601801801801802,
|
| 1395 |
+
"grad_norm": 144.1509246826172,
|
| 1396 |
+
"learning_rate": 5.577423184847932e-06,
|
| 1397 |
+
"loss": 19.0544921875,
|
| 1398 |
+
"loss_idm": 1.103125,
|
| 1399 |
+
"loss_idm_anl": 0.0,
|
| 1400 |
+
"loss_idm_coord": 0.0209716796875,
|
| 1401 |
+
"loss_idm_text": 0.6754696369171143,
|
| 1402 |
+
"loss_idm_type": 0.4647406220436096,
|
| 1403 |
+
"loss_sft": 0.014486004412174226,
|
| 1404 |
+
"step": 980,
|
| 1405 |
+
"token_acc": 0.8444574023769905
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.2283243243243243,
|
| 1409 |
+
"grad_norm": 148.3787841796875,
|
| 1410 |
+
"learning_rate": 5.495227651252315e-06,
|
| 1411 |
+
"loss": 17.188890075683595,
|
| 1412 |
+
"loss_idm": 0.990625,
|
| 1413 |
+
"loss_idm_anl": 0.0,
|
| 1414 |
+
"loss_idm_coord": 0.0214111328125,
|
| 1415 |
+
"loss_idm_text": 0.5891213119029999,
|
| 1416 |
+
"loss_idm_type": 0.4334494173526764,
|
| 1417 |
+
"loss_sft": 0.01478007510304451,
|
| 1418 |
+
"step": 990,
|
| 1419 |
+
"token_acc": 0.8416261870377664
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.23063063063063063,
|
| 1423 |
+
"grad_norm": 134.9239044189453,
|
| 1424 |
+
"learning_rate": 5.412896727361663e-06,
|
| 1425 |
+
"loss": 15.146394348144531,
|
| 1426 |
+
"loss_idm": 0.87578125,
|
| 1427 |
+
"loss_idm_anl": 0.0,
|
| 1428 |
+
"loss_idm_coord": 0.0206298828125,
|
| 1429 |
+
"loss_idm_text": 0.5002685964107514,
|
| 1430 |
+
"loss_idm_type": 0.3955659091472626,
|
| 1431 |
+
"loss_sft": 0.014745334535837174,
|
| 1432 |
+
"step": 1000,
|
| 1433 |
+
"token_acc": 0.8416804747692777
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.23063063063063063,
|
| 1437 |
+
"eval_loss": 1.2327880859375,
|
| 1438 |
+
"eval_runtime": 166.9771,
|
| 1439 |
+
"eval_samples_per_second": 10.451,
|
| 1440 |
+
"eval_steps_per_second": 2.617,
|
| 1441 |
+
"eval_token_acc": 0.8295414506468012,
|
| 1442 |
+
"step": 1000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.23293693693693693,
|
| 1446 |
+
"grad_norm": 124.12373352050781,
|
| 1447 |
+
"learning_rate": 5.3304529216284974e-06,
|
| 1448 |
+
"loss": 17.167878723144533,
|
| 1449 |
+
"loss_idm": 0.98125,
|
| 1450 |
+
"loss_idm_anl": 0.0,
|
| 1451 |
+
"loss_idm_coord": 0.0199951171875,
|
| 1452 |
+
"loss_idm_text": 0.5918982982635498,
|
| 1453 |
+
"loss_idm_type": 0.43085501790046693,
|
| 1454 |
+
"loss_sft": 0.014523088186979293,
|
| 1455 |
+
"step": 1010,
|
| 1456 |
+
"token_acc": 0.8444175480975747
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.23524324324324325,
|
| 1460 |
+
"grad_norm": 131.99546813964844,
|
| 1461 |
+
"learning_rate": 5.247918773366112e-06,
|
| 1462 |
+
"loss": 14.159613037109375,
|
| 1463 |
+
"loss_idm": 0.81484375,
|
| 1464 |
+
"loss_idm_anl": 0.0,
|
| 1465 |
+
"loss_idm_coord": 0.01875,
|
| 1466 |
+
"loss_idm_text": 0.4083675146102905,
|
| 1467 |
+
"loss_idm_type": 0.4275529682636261,
|
| 1468 |
+
"loss_sft": 0.0146888118237257,
|
| 1469 |
+
"step": 1020,
|
| 1470 |
+
"token_acc": 0.8415360933638757
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.23754954954954954,
|
| 1474 |
+
"grad_norm": 116.93572235107422,
|
| 1475 |
+
"learning_rate": 5.165316846586541e-06,
|
| 1476 |
+
"loss": 15.603080749511719,
|
| 1477 |
+
"loss_idm": 0.90625,
|
| 1478 |
+
"loss_idm_anl": 0.0,
|
| 1479 |
+
"loss_idm_coord": 0.0185791015625,
|
| 1480 |
+
"loss_idm_text": 0.52706378698349,
|
| 1481 |
+
"loss_idm_type": 0.3998319745063782,
|
| 1482 |
+
"loss_sft": 0.01447979360818863,
|
| 1483 |
+
"step": 1030,
|
| 1484 |
+
"token_acc": 0.8434217713051085
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.23985585585585587,
|
| 1488 |
+
"grad_norm": 186.3677215576172,
|
| 1489 |
+
"learning_rate": 5.082669723831793e-06,
|
| 1490 |
+
"loss": 17.206391906738283,
|
| 1491 |
+
"loss_idm": 0.9890625,
|
| 1492 |
+
"loss_idm_anl": 0.0,
|
| 1493 |
+
"loss_idm_coord": 0.0183837890625,
|
| 1494 |
+
"loss_idm_text": 0.5997193098068238,
|
| 1495 |
+
"loss_idm_type": 0.4266417622566223,
|
| 1496 |
+
"loss_sft": 0.014923496916890145,
|
| 1497 |
+
"step": 1040,
|
| 1498 |
+
"token_acc": 0.8400955159770253
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.24216216216216216,
|
| 1502 |
+
"grad_norm": 134.91090393066406,
|
| 1503 |
+
"learning_rate": 5e-06,
|
| 1504 |
+
"loss": 14.17005615234375,
|
| 1505 |
+
"loss_idm": 0.81796875,
|
| 1506 |
+
"loss_idm_anl": 0.0,
|
| 1507 |
+
"loss_idm_coord": 0.019482421875,
|
| 1508 |
+
"loss_idm_text": 0.45228556394577024,
|
| 1509 |
+
"loss_idm_type": 0.3835588574409485,
|
| 1510 |
+
"loss_sft": 0.014760823175311088,
|
| 1511 |
+
"step": 1050,
|
| 1512 |
+
"token_acc": 0.8408674793872597
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.24446846846846848,
|
| 1516 |
+
"grad_norm": 156.60739135742188,
|
| 1517 |
+
"learning_rate": 4.917330276168208e-06,
|
| 1518 |
+
"loss": 15.966705322265625,
|
| 1519 |
+
"loss_idm": 0.9203125,
|
| 1520 |
+
"loss_idm_anl": 0.0,
|
| 1521 |
+
"loss_idm_coord": 0.0190185546875,
|
| 1522 |
+
"loss_idm_text": 0.5112396121025086,
|
| 1523 |
+
"loss_idm_type": 0.43749035596847535,
|
| 1524 |
+
"loss_sft": 0.014795352146029473,
|
| 1525 |
+
"step": 1060,
|
| 1526 |
+
"token_acc": 0.8414434859351285
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.24677477477477477,
|
| 1530 |
+
"grad_norm": 109.64134979248047,
|
| 1531 |
+
"learning_rate": 4.8346831534134595e-06,
|
| 1532 |
+
"loss": 17.60172119140625,
|
| 1533 |
+
"loss_idm": 1.02109375,
|
| 1534 |
+
"loss_idm_anl": 0.0,
|
| 1535 |
+
"loss_idm_coord": 0.0205810546875,
|
| 1536 |
+
"loss_idm_text": 0.5611821413040161,
|
| 1537 |
+
"loss_idm_type": 0.4880287885665894,
|
| 1538 |
+
"loss_sft": 0.014694352447986603,
|
| 1539 |
+
"step": 1070,
|
| 1540 |
+
"token_acc": 0.8420225056411745
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.24908108108108107,
|
| 1544 |
+
"grad_norm": 144.90110778808594,
|
| 1545 |
+
"learning_rate": 4.752081226633888e-06,
|
| 1546 |
+
"loss": 16.909609985351562,
|
| 1547 |
+
"loss_idm": 0.9734375,
|
| 1548 |
+
"loss_idm_anl": 0.0,
|
| 1549 |
+
"loss_idm_coord": 0.0178955078125,
|
| 1550 |
+
"loss_idm_text": 0.5911481857299805,
|
| 1551 |
+
"loss_idm_type": 0.4173463821411133,
|
| 1552 |
+
"loss_sft": 0.01456589177250862,
|
| 1553 |
+
"step": 1080,
|
| 1554 |
+
"token_acc": 0.8422988826546816
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.25138738738738736,
|
| 1558 |
+
"grad_norm": 156.7343292236328,
|
| 1559 |
+
"learning_rate": 4.669547078371503e-06,
|
| 1560 |
+
"loss": 17.835157775878905,
|
| 1561 |
+
"loss_idm": 1.03125,
|
| 1562 |
+
"loss_idm_anl": 0.0,
|
| 1563 |
+
"loss_idm_coord": 0.018505859375,
|
| 1564 |
+
"loss_idm_text": 0.602037787437439,
|
| 1565 |
+
"loss_idm_type": 0.4644427180290222,
|
| 1566 |
+
"loss_sft": 0.014457069337368011,
|
| 1567 |
+
"step": 1090,
|
| 1568 |
+
"token_acc": 0.8447727688647594
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.2536936936936937,
|
| 1572 |
+
"grad_norm": 151.3989715576172,
|
| 1573 |
+
"learning_rate": 4.587103272638339e-06,
|
| 1574 |
+
"loss": 15.797918701171875,
|
| 1575 |
+
"loss_idm": 0.9109375,
|
| 1576 |
+
"loss_idm_anl": 0.0,
|
| 1577 |
+
"loss_idm_coord": 0.0177490234375,
|
| 1578 |
+
"loss_idm_text": 0.5759642958641052,
|
| 1579 |
+
"loss_idm_type": 0.3644200384616852,
|
| 1580 |
+
"loss_sft": 0.014347700774669648,
|
| 1581 |
+
"step": 1100,
|
| 1582 |
+
"token_acc": 0.8458367433542481
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.256,
|
| 1586 |
+
"grad_norm": 154.04307556152344,
|
| 1587 |
+
"learning_rate": 4.504772348747687e-06,
|
| 1588 |
+
"loss": 16.6408203125,
|
| 1589 |
+
"loss_idm": 0.9640625,
|
| 1590 |
+
"loss_idm_anl": 0.0,
|
| 1591 |
+
"loss_idm_coord": 0.017138671875,
|
| 1592 |
+
"loss_idm_text": 0.5653828263282776,
|
| 1593 |
+
"loss_idm_type": 0.42803622484207154,
|
| 1594 |
+
"loss_sft": 0.014483000338077544,
|
| 1595 |
+
"step": 1110,
|
| 1596 |
+
"token_acc": 0.8437569514130214
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.2583063063063063,
|
| 1600 |
+
"grad_norm": 136.6959228515625,
|
| 1601 |
+
"learning_rate": 4.42257681515207e-06,
|
| 1602 |
+
"loss": 17.77167510986328,
|
| 1603 |
+
"loss_idm": 1.0453125,
|
| 1604 |
+
"loss_idm_anl": 0.0,
|
| 1605 |
+
"loss_idm_coord": 0.0193115234375,
|
| 1606 |
+
"loss_idm_text": 0.6610914945602417,
|
| 1607 |
+
"loss_idm_type": 0.400143039226532,
|
| 1608 |
+
"loss_sft": 0.01451752446591854,
|
| 1609 |
+
"step": 1120,
|
| 1610 |
+
"token_acc": 0.8445543010340107
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.2606126126126126,
|
| 1614 |
+
"grad_norm": 135.94491577148438,
|
| 1615 |
+
"learning_rate": 4.340539143289655e-06,
|
| 1616 |
+
"loss": 17.628460693359376,
|
| 1617 |
+
"loss_idm": 1.0203125,
|
| 1618 |
+
"loss_idm_anl": 0.0,
|
| 1619 |
+
"loss_idm_coord": 0.01865234375,
|
| 1620 |
+
"loss_idm_text": 0.6353346109390259,
|
| 1621 |
+
"loss_idm_type": 0.41818714141845703,
|
| 1622 |
+
"loss_sft": 0.014454802125692367,
|
| 1623 |
+
"step": 1130,
|
| 1624 |
+
"token_acc": 0.8443907936562738
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.26291891891891894,
|
| 1628 |
+
"grad_norm": 160.8830108642578,
|
| 1629 |
+
"learning_rate": 4.25868176144079e-06,
|
| 1630 |
+
"loss": 16.29990234375,
|
| 1631 |
+
"loss_idm": 0.94375,
|
| 1632 |
+
"loss_idm_anl": 0.0,
|
| 1633 |
+
"loss_idm_coord": 0.0177001953125,
|
| 1634 |
+
"loss_idm_text": 0.541166114807129,
|
| 1635 |
+
"loss_idm_type": 0.4297985553741455,
|
| 1636 |
+
"loss_sft": 0.014698965847492218,
|
| 1637 |
+
"step": 1140,
|
| 1638 |
+
"token_acc": 0.842613082682653
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.26522522522522524,
|
| 1642 |
+
"grad_norm": 135.12367248535156,
|
| 1643 |
+
"learning_rate": 4.17702704859633e-06,
|
| 1644 |
+
"loss": 16.195712280273437,
|
| 1645 |
+
"loss_idm": 0.9375,
|
| 1646 |
+
"loss_idm_anl": 0.0,
|
| 1647 |
+
"loss_idm_coord": 0.020068359375,
|
| 1648 |
+
"loss_idm_text": 0.5394660949707031,
|
| 1649 |
+
"loss_idm_type": 0.42227545380592346,
|
| 1650 |
+
"loss_sft": 0.0147840466350317,
|
| 1651 |
+
"step": 1150,
|
| 1652 |
+
"token_acc": 0.8406737136218165
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.26753153153153153,
|
| 1656 |
+
"grad_norm": 216.79522705078125,
|
| 1657 |
+
"learning_rate": 4.0955973283394525e-06,
|
| 1658 |
+
"loss": 15.386363220214843,
|
| 1659 |
+
"loss_idm": 0.88125,
|
| 1660 |
+
"loss_idm_anl": 0.0,
|
| 1661 |
+
"loss_idm_coord": 0.01923828125,
|
| 1662 |
+
"loss_idm_text": 0.5185725450515747,
|
| 1663 |
+
"loss_idm_type": 0.3934124231338501,
|
| 1664 |
+
"loss_sft": 0.014546865224838256,
|
| 1665 |
+
"step": 1160,
|
| 1666 |
+
"token_acc": 0.8429609969438807
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.2698378378378378,
|
| 1670 |
+
"grad_norm": 192.94996643066406,
|
| 1671 |
+
"learning_rate": 4.0144148627426e-06,
|
| 1672 |
+
"loss": 15.84566650390625,
|
| 1673 |
+
"loss_idm": 0.9125,
|
| 1674 |
+
"loss_idm_anl": 0.0,
|
| 1675 |
+
"loss_idm_coord": 0.018603515625,
|
| 1676 |
+
"loss_idm_text": 0.5233206033706665,
|
| 1677 |
+
"loss_idm_type": 0.41824811697006226,
|
| 1678 |
+
"loss_sft": 0.014757906273007392,
|
| 1679 |
+
"step": 1170,
|
| 1680 |
+
"token_acc": 0.8413835079300053
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.2721441441441441,
|
| 1684 |
+
"grad_norm": 136.8788604736328,
|
| 1685 |
+
"learning_rate": 3.9335018462812664e-06,
|
| 1686 |
+
"loss": 15.686166381835937,
|
| 1687 |
+
"loss_idm": 0.903125,
|
| 1688 |
+
"loss_idm_anl": 0.0,
|
| 1689 |
+
"loss_idm_coord": 0.0183349609375,
|
| 1690 |
+
"loss_idm_text": 0.45666194558143614,
|
| 1691 |
+
"loss_idm_type": 0.47452101707458494,
|
| 1692 |
+
"loss_sft": 0.014861632883548737,
|
| 1693 |
+
"step": 1180,
|
| 1694 |
+
"token_acc": 0.8401439821611449
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.27445045045045047,
|
| 1698 |
+
"grad_norm": 144.01904296875,
|
| 1699 |
+
"learning_rate": 3.852880399766243e-06,
|
| 1700 |
+
"loss": 17.8814697265625,
|
| 1701 |
+
"loss_idm": 1.03125,
|
| 1702 |
+
"loss_idm_anl": 0.0,
|
| 1703 |
+
"loss_idm_coord": 0.018603515625,
|
| 1704 |
+
"loss_idm_text": 0.6181171536445618,
|
| 1705 |
+
"loss_idm_type": 0.45043269991874696,
|
| 1706 |
+
"loss_sft": 0.014725609496235848,
|
| 1707 |
+
"step": 1190,
|
| 1708 |
+
"token_acc": 0.8415764879488441
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.27675675675675676,
|
| 1712 |
+
"grad_norm": 142.98623657226562,
|
| 1713 |
+
"learning_rate": 3.7725725642960047e-06,
|
| 1714 |
+
"loss": 15.80457000732422,
|
| 1715 |
+
"loss_idm": 0.91484375,
|
| 1716 |
+
"loss_idm_anl": 0.0,
|
| 1717 |
+
"loss_idm_coord": 0.0194580078125,
|
| 1718 |
+
"loss_idm_text": 0.5567480087280273,
|
| 1719 |
+
"loss_idm_type": 0.38129279017448425,
|
| 1720 |
+
"loss_sft": 0.014737585186958313,
|
| 1721 |
+
"step": 1200,
|
| 1722 |
+
"token_acc": 0.8415397949338522
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.27906306306306305,
|
| 1726 |
+
"grad_norm": 114.70137023925781,
|
| 1727 |
+
"learning_rate": 3.6926002952309015e-06,
|
| 1728 |
+
"loss": 15.290737915039063,
|
| 1729 |
+
"loss_idm": 0.88671875,
|
| 1730 |
+
"loss_idm_anl": 0.0,
|
| 1731 |
+
"loss_idm_coord": 0.0188232421875,
|
| 1732 |
+
"loss_idm_text": 0.515410315990448,
|
| 1733 |
+
"loss_idm_type": 0.3913223624229431,
|
| 1734 |
+
"loss_sft": 0.014572849497199059,
|
| 1735 |
+
"step": 1210,
|
| 1736 |
+
"token_acc": 0.8432653274893042
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.28136936936936935,
|
| 1740 |
+
"grad_norm": 144.1276092529297,
|
| 1741 |
+
"learning_rate": 3.6129854561907786e-06,
|
| 1742 |
+
"loss": 12.707015991210938,
|
| 1743 |
+
"loss_idm": 0.73203125,
|
| 1744 |
+
"loss_idm_anl": 0.0,
|
| 1745 |
+
"loss_idm_coord": 0.0183349609375,
|
| 1746 |
+
"loss_idm_text": 0.3691279649734497,
|
| 1747 |
+
"loss_idm_type": 0.3762137830257416,
|
| 1748 |
+
"loss_sft": 0.014775990322232247,
|
| 1749 |
+
"step": 1220,
|
| 1750 |
+
"token_acc": 0.8407985566363351
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 0.2836756756756757,
|
| 1754 |
+
"grad_norm": 162.1075897216797,
|
| 1755 |
+
"learning_rate": 3.533749813077677e-06,
|
| 1756 |
+
"loss": 17.085980224609376,
|
| 1757 |
+
"loss_idm": 0.98515625,
|
| 1758 |
+
"loss_idm_anl": 0.0,
|
| 1759 |
+
"loss_idm_coord": 0.0185546875,
|
| 1760 |
+
"loss_idm_text": 0.6291376233100892,
|
| 1761 |
+
"loss_idm_type": 0.390378075838089,
|
| 1762 |
+
"loss_sft": 0.014458349719643594,
|
| 1763 |
+
"step": 1230,
|
| 1764 |
+
"token_acc": 0.8444264451798582
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.285981981981982,
|
| 1768 |
+
"grad_norm": 210.1119842529297,
|
| 1769 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 1770 |
+
"loss": 15.181900024414062,
|
| 1771 |
+
"loss_idm": 0.8828125,
|
| 1772 |
+
"loss_idm_anl": 0.0,
|
| 1773 |
+
"loss_idm_coord": 0.0185791015625,
|
| 1774 |
+
"loss_idm_text": 0.5205450057983398,
|
| 1775 |
+
"loss_idm_type": 0.3800136804580688,
|
| 1776 |
+
"loss_sft": 0.014402059838175774,
|
| 1777 |
+
"step": 1240,
|
| 1778 |
+
"token_acc": 0.8441134821036184
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 0.2882882882882883,
|
| 1782 |
+
"grad_norm": 138.51524353027344,
|
| 1783 |
+
"learning_rate": 3.3765026539765832e-06,
|
| 1784 |
+
"loss": 16.950105285644533,
|
| 1785 |
+
"loss_idm": 0.9875,
|
| 1786 |
+
"loss_idm_anl": 0.0,
|
| 1787 |
+
"loss_idm_coord": 0.0195556640625,
|
| 1788 |
+
"loss_idm_text": 0.6216296911239624,
|
| 1789 |
+
"loss_idm_type": 0.3894159376621246,
|
| 1790 |
+
"loss_sft": 0.014125967025756836,
|
| 1791 |
+
"step": 1250,
|
| 1792 |
+
"token_acc": 0.847919528627195
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 0.2905945945945946,
|
| 1796 |
+
"grad_norm": 154.9911346435547,
|
| 1797 |
+
"learning_rate": 3.298534127791785e-06,
|
| 1798 |
+
"loss": 16.449783325195312,
|
| 1799 |
+
"loss_idm": 0.959375,
|
| 1800 |
+
"loss_idm_anl": 0.0,
|
| 1801 |
+
"loss_idm_coord": 0.0198974609375,
|
| 1802 |
+
"loss_idm_text": 0.557077956199646,
|
| 1803 |
+
"loss_idm_type": 0.42165766954421996,
|
| 1804 |
+
"loss_sft": 0.014437104761600494,
|
| 1805 |
+
"step": 1260,
|
| 1806 |
+
"token_acc": 0.8440432417820339
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 0.2929009009009009,
|
| 1810 |
+
"grad_norm": 126.49798583984375,
|
| 1811 |
+
"learning_rate": 3.2210307653874175e-06,
|
| 1812 |
+
"loss": 14.849807739257812,
|
| 1813 |
+
"loss_idm": 0.85703125,
|
| 1814 |
+
"loss_idm_anl": 0.0,
|
| 1815 |
+
"loss_idm_coord": 0.016943359375,
|
| 1816 |
+
"loss_idm_text": 0.5337203025817872,
|
| 1817 |
+
"loss_idm_type": 0.3474113941192627,
|
| 1818 |
+
"loss_sft": 0.014366917312145233,
|
| 1819 |
+
"step": 1270,
|
| 1820 |
+
"token_acc": 0.8457429629704389
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 0.2952072072072072,
|
| 1824 |
+
"grad_norm": 162.35890197753906,
|
| 1825 |
+
"learning_rate": 3.1440137554088957e-06,
|
| 1826 |
+
"loss": 15.314067077636718,
|
| 1827 |
+
"loss_idm": 0.88125,
|
| 1828 |
+
"loss_idm_anl": 0.0,
|
| 1829 |
+
"loss_idm_coord": 0.0182373046875,
|
| 1830 |
+
"loss_idm_text": 0.5182104647159577,
|
| 1831 |
+
"loss_idm_type": 0.39087520241737367,
|
| 1832 |
+
"loss_sft": 0.014491885155439376,
|
| 1833 |
+
"step": 1280,
|
| 1834 |
+
"token_acc": 0.84312589885166
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 0.2975135135135135,
|
| 1838 |
+
"grad_norm": 156.34283447265625,
|
| 1839 |
+
"learning_rate": 3.06750415353774e-06,
|
| 1840 |
+
"loss": 15.587838745117187,
|
| 1841 |
+
"loss_idm": 0.903125,
|
| 1842 |
+
"loss_idm_anl": 0.0,
|
| 1843 |
+
"loss_idm_coord": 0.017919921875,
|
| 1844 |
+
"loss_idm_text": 0.5396368145942688,
|
| 1845 |
+
"loss_idm_type": 0.3871441423892975,
|
| 1846 |
+
"loss_sft": 0.014515075832605362,
|
| 1847 |
+
"step": 1290,
|
| 1848 |
+
"token_acc": 0.8436580424785217
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 0.2998198198198198,
|
| 1852 |
+
"grad_norm": 169.38795471191406,
|
| 1853 |
+
"learning_rate": 2.991522876735154e-06,
|
| 1854 |
+
"loss": 15.711705017089844,
|
| 1855 |
+
"loss_idm": 0.909375,
|
| 1856 |
+
"loss_idm_anl": 0.0,
|
| 1857 |
+
"loss_idm_coord": 0.018310546875,
|
| 1858 |
+
"loss_idm_text": 0.5583156704902649,
|
| 1859 |
+
"loss_idm_type": 0.3756734192371368,
|
| 1860 |
+
"loss_sft": 0.014504583552479744,
|
| 1861 |
+
"step": 1300,
|
| 1862 |
+
"token_acc": 0.8438711647805225
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 0.3021261261261261,
|
| 1866 |
+
"grad_norm": 165.150146484375,
|
| 1867 |
+
"learning_rate": 2.9160906975235493e-06,
|
| 1868 |
+
"loss": 13.628689575195313,
|
| 1869 |
+
"loss_idm": 0.78671875,
|
| 1870 |
+
"loss_idm_anl": 0.0,
|
| 1871 |
+
"loss_idm_coord": 0.0202880859375,
|
| 1872 |
+
"loss_idm_text": 0.4506654143333435,
|
| 1873 |
+
"loss_idm_type": 0.35060195326805116,
|
| 1874 |
+
"loss_sft": 0.014570535719394683,
|
| 1875 |
+
"step": 1310,
|
| 1876 |
+
"token_acc": 0.8431417376648077
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 0.30443243243243245,
|
| 1880 |
+
"grad_norm": 199.06549072265625,
|
| 1881 |
+
"learning_rate": 2.8412282383075362e-06,
|
| 1882 |
+
"loss": 16.37169647216797,
|
| 1883 |
+
"loss_idm": 0.9515625,
|
| 1884 |
+
"loss_idm_anl": 0.0,
|
| 1885 |
+
"loss_idm_coord": 0.0171875,
|
| 1886 |
+
"loss_idm_text": 0.6052956461906434,
|
| 1887 |
+
"loss_idm_type": 0.37099899649620055,
|
| 1888 |
+
"loss_sft": 0.01451174020767212,
|
| 1889 |
+
"step": 1320,
|
| 1890 |
+
"token_acc": 0.8432796170522042
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 0.30673873873873875,
|
| 1894 |
+
"grad_norm": 162.7277374267578,
|
| 1895 |
+
"learning_rate": 2.766955965735968e-06,
|
| 1896 |
+
"loss": 14.637554931640626,
|
| 1897 |
+
"loss_idm": 0.85078125,
|
| 1898 |
+
"loss_idm_anl": 0.0,
|
| 1899 |
+
"loss_idm_coord": 0.0188232421875,
|
| 1900 |
+
"loss_idm_text": 0.5082914412021637,
|
| 1901 |
+
"loss_idm_type": 0.3572277069091797,
|
| 1902 |
+
"loss_sft": 0.014705703407526017,
|
| 1903 |
+
"step": 1330,
|
| 1904 |
+
"token_acc": 0.8422121601269894
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 0.30904504504504504,
|
| 1908 |
+
"grad_norm": 143.47894287109375,
|
| 1909 |
+
"learning_rate": 2.693294185106562e-06,
|
| 1910 |
+
"loss": 13.652301025390624,
|
| 1911 |
+
"loss_idm": 0.7828125,
|
| 1912 |
+
"loss_idm_anl": 0.0,
|
| 1913 |
+
"loss_idm_coord": 0.0198486328125,
|
| 1914 |
+
"loss_idm_text": 0.4210363507270813,
|
| 1915 |
+
"loss_idm_type": 0.3825237274169922,
|
| 1916 |
+
"loss_sft": 0.014496737718582153,
|
| 1917 |
+
"step": 1340,
|
| 1918 |
+
"token_acc": 0.8437972852010349
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 0.31135135135135134,
|
| 1922 |
+
"grad_norm": 132.78858947753906,
|
| 1923 |
+
"learning_rate": 2.6202630348146323e-06,
|
| 1924 |
+
"loss": 15.083595275878906,
|
| 1925 |
+
"loss_idm": 0.8796875,
|
| 1926 |
+
"loss_idm_anl": 0.0,
|
| 1927 |
+
"loss_idm_coord": 0.0176025390625,
|
| 1928 |
+
"loss_idm_text": 0.5048262238502502,
|
| 1929 |
+
"loss_idm_type": 0.39085535407066346,
|
| 1930 |
+
"loss_sft": 0.01434645541012287,
|
| 1931 |
+
"step": 1350,
|
| 1932 |
+
"token_acc": 0.8459678060808526
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 0.3136576576576577,
|
| 1936 |
+
"grad_norm": 165.5104217529297,
|
| 1937 |
+
"learning_rate": 2.5478824808474613e-06,
|
| 1938 |
+
"loss": 15.311534118652343,
|
| 1939 |
+
"loss_idm": 0.87421875,
|
| 1940 |
+
"loss_idm_anl": 0.0,
|
| 1941 |
+
"loss_idm_coord": 0.0175537109375,
|
| 1942 |
+
"loss_idm_text": 0.5322446703910828,
|
| 1943 |
+
"loss_idm_type": 0.37764355540275574,
|
| 1944 |
+
"loss_sft": 0.014268488809466361,
|
| 1945 |
+
"step": 1360,
|
| 1946 |
+
"token_acc": 0.8452123559853058
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 0.315963963963964,
|
| 1950 |
+
"grad_norm": 141.0616455078125,
|
| 1951 |
+
"learning_rate": 2.476172311325783e-06,
|
| 1952 |
+
"loss": 15.717620849609375,
|
| 1953 |
+
"loss_idm": 0.915625,
|
| 1954 |
+
"loss_idm_anl": 0.0,
|
| 1955 |
+
"loss_idm_coord": 0.0179931640625,
|
| 1956 |
+
"loss_idm_text": 0.5490303754806518,
|
| 1957 |
+
"loss_idm_type": 0.38535616993904115,
|
| 1958 |
+
"loss_sft": 0.014547385275363922,
|
| 1959 |
+
"step": 1370,
|
| 1960 |
+
"token_acc": 0.8435834472048124
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 0.3182702702702703,
|
| 1964 |
+
"grad_norm": 202.39620971679688,
|
| 1965 |
+
"learning_rate": 2.4051521310939258e-06,
|
| 1966 |
+
"loss": 16.194735717773437,
|
| 1967 |
+
"loss_idm": 0.9453125,
|
| 1968 |
+
"loss_idm_anl": 0.0,
|
| 1969 |
+
"loss_idm_coord": 0.016943359375,
|
| 1970 |
+
"loss_idm_text": 0.5614462852478027,
|
| 1971 |
+
"loss_idm_type": 0.40362446904182436,
|
| 1972 |
+
"loss_sft": 0.014665166661143304,
|
| 1973 |
+
"step": 1380,
|
| 1974 |
+
"token_acc": 0.8426359432769256
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 0.32057657657657657,
|
| 1978 |
+
"grad_norm": 186.8247833251953,
|
| 1979 |
+
"learning_rate": 2.3348413563600324e-06,
|
| 1980 |
+
"loss": 14.730172729492187,
|
| 1981 |
+
"loss_idm": 0.8421875,
|
| 1982 |
+
"loss_idm_anl": 0.0,
|
| 1983 |
+
"loss_idm_coord": 0.0188720703125,
|
| 1984 |
+
"loss_idm_text": 0.4475443482398987,
|
| 1985 |
+
"loss_idm_type": 0.42451398968696596,
|
| 1986 |
+
"loss_sft": 0.014449363574385643,
|
| 1987 |
+
"step": 1390,
|
| 1988 |
+
"token_acc": 0.8445057561070892
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 0.32288288288288286,
|
| 1992 |
+
"grad_norm": 114.01448822021484,
|
| 1993 |
+
"learning_rate": 2.265259209387867e-06,
|
| 1994 |
+
"loss": 14.568830871582032,
|
| 1995 |
+
"loss_idm": 0.8296875,
|
| 1996 |
+
"loss_idm_anl": 0.0,
|
| 1997 |
+
"loss_idm_coord": 0.0177490234375,
|
| 1998 |
+
"loss_idm_text": 0.4782296776771545,
|
| 1999 |
+
"loss_idm_type": 0.38517374396324155,
|
| 2000 |
+
"loss_sft": 0.014272304996848107,
|
| 2001 |
+
"step": 1400,
|
| 2002 |
+
"token_acc": 0.8455116168894466
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 0.3251891891891892,
|
| 2006 |
+
"grad_norm": 152.14208984375,
|
| 2007 |
+
"learning_rate": 2.1964247132416373e-06,
|
| 2008 |
+
"loss": 15.284608459472656,
|
| 2009 |
+
"loss_idm": 0.8859375,
|
| 2010 |
+
"loss_idm_anl": 0.0,
|
| 2011 |
+
"loss_idm_coord": 0.0169677734375,
|
| 2012 |
+
"loss_idm_text": 0.5515658617019653,
|
| 2013 |
+
"loss_idm_type": 0.35711957812309264,
|
| 2014 |
+
"loss_sft": 0.014497144892811776,
|
| 2015 |
+
"step": 1410,
|
| 2016 |
+
"token_acc": 0.8435979398066908
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 0.3274954954954955,
|
| 2020 |
+
"grad_norm": 137.8850555419922,
|
| 2021 |
+
"learning_rate": 2.1283566865852824e-06,
|
| 2022 |
+
"loss": 14.024693298339844,
|
| 2023 |
+
"loss_idm": 0.80703125,
|
| 2024 |
+
"loss_idm_anl": 0.0,
|
| 2025 |
+
"loss_idm_coord": 0.018408203125,
|
| 2026 |
+
"loss_idm_text": 0.48794840574264525,
|
| 2027 |
+
"loss_idm_type": 0.34030611515045167,
|
| 2028 |
+
"loss_sft": 0.014438638836145401,
|
| 2029 |
+
"step": 1420,
|
| 2030 |
+
"token_acc": 0.8444949198905822
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.3298018018018018,
|
| 2034 |
+
"grad_norm": 193.08645629882812,
|
| 2035 |
+
"learning_rate": 2.061073738537635e-06,
|
| 2036 |
+
"loss": 14.654190063476562,
|
| 2037 |
+
"loss_idm": 0.84921875,
|
| 2038 |
+
"loss_idm_anl": 0.0,
|
| 2039 |
+
"loss_idm_coord": 0.02021484375,
|
| 2040 |
+
"loss_idm_text": 0.5063535213470459,
|
| 2041 |
+
"loss_idm_type": 0.35956308245658875,
|
| 2042 |
+
"loss_sft": 0.014374737441539765,
|
| 2043 |
+
"step": 1430,
|
| 2044 |
+
"token_acc": 0.8457109989803655
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 0.3321081081081081,
|
| 2048 |
+
"grad_norm": 179.3224639892578,
|
| 2049 |
+
"learning_rate": 1.9945942635848745e-06,
|
| 2050 |
+
"loss": 15.624932861328125,
|
| 2051 |
+
"loss_idm": 0.90234375,
|
| 2052 |
+
"loss_idm_anl": 0.0,
|
| 2053 |
+
"loss_idm_coord": 0.019384765625,
|
| 2054 |
+
"loss_idm_text": 0.5428369641304016,
|
| 2055 |
+
"loss_idm_type": 0.38439915180206297,
|
| 2056 |
+
"loss_sft": 0.014417222514748574,
|
| 2057 |
+
"step": 1440,
|
| 2058 |
+
"token_acc": 0.845333890181186
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 0.33441441441441444,
|
| 2062 |
+
"grad_norm": 154.86846923828125,
|
| 2063 |
+
"learning_rate": 1.928936436551661e-06,
|
| 2064 |
+
"loss": 17.012544250488283,
|
| 2065 |
+
"loss_idm": 0.9953125,
|
| 2066 |
+
"loss_idm_anl": 0.0,
|
| 2067 |
+
"loss_idm_coord": 0.018603515625,
|
| 2068 |
+
"loss_idm_text": 0.63501957654953,
|
| 2069 |
+
"loss_idm_type": 0.38010231852531434,
|
| 2070 |
+
"loss_sft": 0.014432965219020844,
|
| 2071 |
+
"step": 1450,
|
| 2072 |
+
"token_acc": 0.8441891544960063
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 0.33672072072072073,
|
| 2076 |
+
"grad_norm": 135.02999877929688,
|
| 2077 |
+
"learning_rate": 1.864118207632315e-06,
|
| 2078 |
+
"loss": 14.688017272949219,
|
| 2079 |
+
"loss_idm": 0.8484375,
|
| 2080 |
+
"loss_idm_anl": 0.0,
|
| 2081 |
+
"loss_idm_coord": 0.0168701171875,
|
| 2082 |
+
"loss_idm_text": 0.5101109147071838,
|
| 2083 |
+
"loss_idm_type": 0.36122512221336367,
|
| 2084 |
+
"loss_sft": 0.014461452886462212,
|
| 2085 |
+
"step": 1460,
|
| 2086 |
+
"token_acc": 0.8441797287309384
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 0.33902702702702703,
|
| 2090 |
+
"grad_norm": 161.4497833251953,
|
| 2091 |
+
"learning_rate": 1.8001572974834169e-06,
|
| 2092 |
+
"loss": 14.854217529296875,
|
| 2093 |
+
"loss_idm": 0.8578125,
|
| 2094 |
+
"loss_idm_anl": 0.0,
|
| 2095 |
+
"loss_idm_coord": 0.019482421875,
|
| 2096 |
+
"loss_idm_text": 0.5380716323852539,
|
| 2097 |
+
"loss_idm_type": 0.341589891910553,
|
| 2098 |
+
"loss_sft": 0.014205808565020562,
|
| 2099 |
+
"step": 1470,
|
| 2100 |
+
"token_acc": 0.8471874874954983
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 0.3413333333333333,
|
| 2104 |
+
"grad_norm": 133.96571350097656,
|
| 2105 |
+
"learning_rate": 1.7370711923791567e-06,
|
| 2106 |
+
"loss": 13.000572204589844,
|
| 2107 |
+
"loss_idm": 0.7375,
|
| 2108 |
+
"loss_idm_anl": 0.0,
|
| 2109 |
+
"loss_idm_coord": 0.019384765625,
|
| 2110 |
+
"loss_idm_text": 0.4172104477882385,
|
| 2111 |
+
"loss_idm_type": 0.34592602252960203,
|
| 2112 |
+
"loss_sft": 0.014315107464790344,
|
| 2113 |
+
"step": 1480,
|
| 2114 |
+
"token_acc": 0.8460156840421251
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 0.3436396396396396,
|
| 2118 |
+
"grad_norm": 120.62774658203125,
|
| 2119 |
+
"learning_rate": 1.6748771394307584e-06,
|
| 2120 |
+
"loss": 14.395199584960938,
|
| 2121 |
+
"loss_idm": 0.83671875,
|
| 2122 |
+
"loss_idm_anl": 0.0,
|
| 2123 |
+
"loss_idm_coord": 0.0180419921875,
|
| 2124 |
+
"loss_idm_text": 0.4689497768878937,
|
| 2125 |
+
"loss_idm_type": 0.3827894330024719,
|
| 2126 |
+
"loss_sft": 0.014493611082434655,
|
| 2127 |
+
"step": 1490,
|
| 2128 |
+
"token_acc": 0.8434915816796925
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 0.34594594594594597,
|
| 2132 |
+
"grad_norm": 160.82275390625,
|
| 2133 |
+
"learning_rate": 1.6135921418712959e-06,
|
| 2134 |
+
"loss": 14.267446899414063,
|
| 2135 |
+
"loss_idm": 0.8265625,
|
| 2136 |
+
"loss_idm_anl": 0.0,
|
| 2137 |
+
"loss_idm_coord": 0.0183837890625,
|
| 2138 |
+
"loss_idm_text": 0.486546927690506,
|
| 2139 |
+
"loss_idm_type": 0.357412725687027,
|
| 2140 |
+
"loss_sft": 0.014240951836109161,
|
| 2141 |
+
"step": 1500,
|
| 2142 |
+
"token_acc": 0.8465638485857505
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 0.34594594594594597,
|
| 2146 |
+
"eval_loss": 1.1403998136520386,
|
| 2147 |
+
"eval_runtime": 168.4218,
|
| 2148 |
+
"eval_samples_per_second": 10.361,
|
| 2149 |
+
"eval_steps_per_second": 2.595,
|
| 2150 |
+
"eval_token_acc": 0.8319841652873965,
|
| 2151 |
+
"step": 1500
|
| 2152 |
+
}
|
| 2153 |
+
],
|
| 2154 |
+
"logging_steps": 10,
|
| 2155 |
+
"max_steps": 2000,
|
| 2156 |
+
"num_input_tokens_seen": 0,
|
| 2157 |
+
"num_train_epochs": 1,
|
| 2158 |
+
"save_steps": 500,
|
| 2159 |
+
"stateful_callbacks": {
|
| 2160 |
+
"TrainerControl": {
|
| 2161 |
+
"args": {
|
| 2162 |
+
"should_epoch_stop": false,
|
| 2163 |
+
"should_evaluate": false,
|
| 2164 |
+
"should_log": false,
|
| 2165 |
+
"should_save": true,
|
| 2166 |
+
"should_training_stop": false
|
| 2167 |
+
},
|
| 2168 |
+
"attributes": {}
|
| 2169 |
+
}
|
| 2170 |
+
},
|
| 2171 |
+
"total_flos": 1.8759920794589987e+19,
|
| 2172 |
+
"train_batch_size": 1,
|
| 2173 |
+
"trial_name": null,
|
| 2174 |
+
"trial_params": null
|
| 2175 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:480d2a033203336cd344021860b1a6676cd1dd4de3ddc5dda1f2a33f47fcd0cf
|
| 3 |
+
size 8977
|
zero_to_fp32.py
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import gc
|
| 25 |
+
import json
|
| 26 |
+
import numpy as np
|
| 27 |
+
from tqdm import tqdm
|
| 28 |
+
from collections import OrderedDict
|
| 29 |
+
from dataclasses import dataclass
|
| 30 |
+
|
| 31 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
+
from deepspeed.utils import logger
|
| 34 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
@dataclass
|
| 40 |
+
class zero_model_state:
|
| 41 |
+
buffers: dict()
|
| 42 |
+
param_shapes: dict()
|
| 43 |
+
shared_params: list
|
| 44 |
+
ds_version: int
|
| 45 |
+
frozen_param_shapes: dict()
|
| 46 |
+
frozen_param_fragments: dict()
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
debug = 0
|
| 50 |
+
|
| 51 |
+
# load to cpu
|
| 52 |
+
device = torch.device('cpu')
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def atoi(text):
|
| 56 |
+
return int(text) if text.isdigit() else text
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def natural_keys(text):
|
| 60 |
+
'''
|
| 61 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
+
(See Toothy's implementation in the comments)
|
| 64 |
+
'''
|
| 65 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
+
if not os.path.isdir(checkpoint_dir):
|
| 70 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
+
|
| 72 |
+
# there should be only one file
|
| 73 |
+
if zero_stage <= 2:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
+
elif zero_stage == 3:
|
| 76 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
+
|
| 78 |
+
if not os.path.exists(file):
|
| 79 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
+
|
| 81 |
+
return file
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
+
|
| 88 |
+
if len(ckpt_files) == 0:
|
| 89 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
+
|
| 91 |
+
return ckpt_files
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def get_optim_files(checkpoint_dir):
|
| 95 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def get_model_state_files(checkpoint_dir):
|
| 99 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def parse_model_states(files):
|
| 103 |
+
zero_model_states = []
|
| 104 |
+
for file in files:
|
| 105 |
+
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
+
|
| 107 |
+
if BUFFER_NAMES not in state_dict:
|
| 108 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
+
if debug:
|
| 111 |
+
print("Found buffers:", buffer_names)
|
| 112 |
+
|
| 113 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
+
|
| 117 |
+
# collect parameters that are included in param_shapes
|
| 118 |
+
param_names = []
|
| 119 |
+
for s in param_shapes:
|
| 120 |
+
for name in s.keys():
|
| 121 |
+
param_names.append(name)
|
| 122 |
+
|
| 123 |
+
# update with frozen parameters
|
| 124 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
+
if frozen_param_shapes is not None:
|
| 126 |
+
if debug:
|
| 127 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
+
param_names += list(frozen_param_shapes.keys())
|
| 129 |
+
|
| 130 |
+
# handle shared params
|
| 131 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
+
|
| 133 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
+
|
| 135 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
+
|
| 137 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
+
param_shapes=param_shapes,
|
| 139 |
+
shared_params=shared_params,
|
| 140 |
+
ds_version=ds_version,
|
| 141 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
+
zero_model_states.append(z_model_state)
|
| 144 |
+
|
| 145 |
+
return zero_model_states
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
+
total_files = len(files)
|
| 150 |
+
state_dicts = []
|
| 151 |
+
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
+
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
+
# and also handle the case where it was already removed by another helper script
|
| 155 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
+
state_dicts.append(state_dict)
|
| 157 |
+
|
| 158 |
+
if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
+
|
| 163 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
+
# use the max of the partition_count to get the dp world_size.
|
| 166 |
+
|
| 167 |
+
if type(world_size) is list:
|
| 168 |
+
world_size = max(world_size)
|
| 169 |
+
|
| 170 |
+
if world_size != total_files:
|
| 171 |
+
raise ValueError(
|
| 172 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
# the groups are named differently in each stage
|
| 177 |
+
if zero_stage <= 2:
|
| 178 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
+
elif zero_stage == 3:
|
| 180 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
+
else:
|
| 182 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
+
|
| 184 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
+
"""
|
| 190 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
+
|
| 192 |
+
Args:
|
| 193 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
+
|
| 195 |
+
"""
|
| 196 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
+
|
| 198 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
+
|
| 202 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
+
|
| 204 |
+
zero_model_states = parse_model_states(model_files)
|
| 205 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
+
|
| 207 |
+
if zero_stage <= 2:
|
| 208 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
+
exclude_frozen_parameters)
|
| 210 |
+
elif zero_stage == 3:
|
| 211 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
+
exclude_frozen_parameters)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _has_callable(obj, fn):
|
| 248 |
+
attr = getattr(obj, fn, None)
|
| 249 |
+
return callable(attr)
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
+
|
| 255 |
+
# Reconstruction protocol:
|
| 256 |
+
#
|
| 257 |
+
# XXX: document this
|
| 258 |
+
|
| 259 |
+
if debug:
|
| 260 |
+
for i in range(world_size):
|
| 261 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
+
|
| 264 |
+
# XXX: memory usage doubles here (zero2)
|
| 265 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
+
merged_single_partition_of_fp32_groups = []
|
| 267 |
+
for i in range(num_param_groups):
|
| 268 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
+
avail_numel = sum(
|
| 272 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
+
|
| 274 |
+
if debug:
|
| 275 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
+
# not asserting if there is a mismatch due to possible padding
|
| 278 |
+
print(f"Have {avail_numel} numels to process.")
|
| 279 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
+
|
| 281 |
+
# params
|
| 282 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
+
# out-of-core computing solution
|
| 284 |
+
total_numel = 0
|
| 285 |
+
total_params = 0
|
| 286 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
+
offset = 0
|
| 288 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
+
for name, shape in shapes.items():
|
| 290 |
+
|
| 291 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
+
total_numel += unpartitioned_numel
|
| 293 |
+
total_params += 1
|
| 294 |
+
|
| 295 |
+
if debug:
|
| 296 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
+
offset += unpartitioned_numel
|
| 299 |
+
|
| 300 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
+
align_to = 2 * world_size
|
| 305 |
+
|
| 306 |
+
def zero2_align(x):
|
| 307 |
+
return align_to * math.ceil(x / align_to)
|
| 308 |
+
|
| 309 |
+
if debug:
|
| 310 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
+
|
| 312 |
+
offset = zero2_align(offset)
|
| 313 |
+
avail_numel = zero2_align(avail_numel)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
# Sanity check
|
| 319 |
+
if offset != avail_numel:
|
| 320 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
+
|
| 322 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
+
exclude_frozen_parameters):
|
| 327 |
+
state_dict = OrderedDict()
|
| 328 |
+
|
| 329 |
+
# buffers
|
| 330 |
+
buffers = zero_model_states[0].buffers
|
| 331 |
+
state_dict.update(buffers)
|
| 332 |
+
if debug:
|
| 333 |
+
print(f"added {len(buffers)} buffers")
|
| 334 |
+
|
| 335 |
+
if not exclude_frozen_parameters:
|
| 336 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
+
|
| 338 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
+
|
| 340 |
+
# recover shared parameters
|
| 341 |
+
for pair in zero_model_states[0].shared_params:
|
| 342 |
+
if pair[1] in state_dict:
|
| 343 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
+
|
| 345 |
+
return state_dict
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
+
remainder = unpartitioned_numel % world_size
|
| 350 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
+
return partitioned_numel, padding_numel
|
| 353 |
+
|
| 354 |
+
|
| 355 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
+
return
|
| 358 |
+
|
| 359 |
+
if debug:
|
| 360 |
+
for i in range(world_size):
|
| 361 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
+
|
| 364 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
+
wanted_params = len(frozen_param_shapes)
|
| 366 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
+
|
| 371 |
+
total_params = 0
|
| 372 |
+
total_numel = 0
|
| 373 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
+
total_params += 1
|
| 375 |
+
unpartitioned_numel = shape.numel()
|
| 376 |
+
total_numel += unpartitioned_numel
|
| 377 |
+
|
| 378 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
+
|
| 381 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
+
|
| 383 |
+
if debug:
|
| 384 |
+
print(
|
| 385 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
class GatheredTensor:
|
| 392 |
+
"""
|
| 393 |
+
A pseudo tensor that collects partitioned weights.
|
| 394 |
+
It is more memory efficient when there are multiple groups.
|
| 395 |
+
"""
|
| 396 |
+
|
| 397 |
+
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
+
self.flat_groups = flat_groups
|
| 399 |
+
self.flat_groups_offset = flat_groups_offset
|
| 400 |
+
self.offset = offset
|
| 401 |
+
self.partitioned_numel = partitioned_numel
|
| 402 |
+
self.shape = shape
|
| 403 |
+
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
+
|
| 405 |
+
def contiguous(self):
|
| 406 |
+
"""
|
| 407 |
+
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
+
"""
|
| 409 |
+
end_idx = self.offset + self.partitioned_numel
|
| 410 |
+
world_size = len(self.flat_groups)
|
| 411 |
+
pad_flat_param_chunks = []
|
| 412 |
+
|
| 413 |
+
for rank_i in range(world_size):
|
| 414 |
+
# for each rank, we need to collect weights from related group/groups
|
| 415 |
+
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
+
start_group_id = None
|
| 417 |
+
end_group_id = None
|
| 418 |
+
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
+
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
+
start_group_id = group_id
|
| 421 |
+
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
+
end_group_id = group_id
|
| 423 |
+
break
|
| 424 |
+
# collect weights from related group/groups
|
| 425 |
+
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
+
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
+
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
+
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
+
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
+
|
| 431 |
+
# collect weights from all ranks
|
| 432 |
+
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
+
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
+
return param
|
| 435 |
+
|
| 436 |
+
|
| 437 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
+
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
+
|
| 441 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
+
|
| 444 |
+
# merge list of dicts, preserving order
|
| 445 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
+
|
| 447 |
+
if debug:
|
| 448 |
+
for i in range(world_size):
|
| 449 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
+
|
| 451 |
+
wanted_params = len(param_shapes)
|
| 452 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
+
# not asserting if there is a mismatch due to possible padding
|
| 454 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
+
|
| 458 |
+
# params
|
| 459 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
+
# out-of-core computing solution
|
| 461 |
+
offset = 0
|
| 462 |
+
total_numel = 0
|
| 463 |
+
total_params = 0
|
| 464 |
+
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
+
unpartitioned_numel = shape.numel()
|
| 467 |
+
total_numel += unpartitioned_numel
|
| 468 |
+
total_params += 1
|
| 469 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
+
|
| 471 |
+
if debug:
|
| 472 |
+
print(
|
| 473 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
+
)
|
| 475 |
+
|
| 476 |
+
# memory efficient tensor
|
| 477 |
+
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
+
state_dict[name] = tensor
|
| 479 |
+
offset += partitioned_numel
|
| 480 |
+
|
| 481 |
+
offset *= world_size
|
| 482 |
+
|
| 483 |
+
# Sanity check
|
| 484 |
+
if offset != avail_numel:
|
| 485 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
+
|
| 487 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
+
exclude_frozen_parameters):
|
| 492 |
+
state_dict = OrderedDict()
|
| 493 |
+
|
| 494 |
+
# buffers
|
| 495 |
+
buffers = zero_model_states[0].buffers
|
| 496 |
+
state_dict.update(buffers)
|
| 497 |
+
if debug:
|
| 498 |
+
print(f"added {len(buffers)} buffers")
|
| 499 |
+
|
| 500 |
+
if not exclude_frozen_parameters:
|
| 501 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
+
|
| 503 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
+
|
| 505 |
+
# recover shared parameters
|
| 506 |
+
for pair in zero_model_states[0].shared_params:
|
| 507 |
+
if pair[1] in state_dict:
|
| 508 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
+
|
| 510 |
+
return state_dict
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
+
"""
|
| 515 |
+
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
+
"""
|
| 517 |
+
torch_state_dict = {}
|
| 518 |
+
converted_tensors = {}
|
| 519 |
+
for name, tensor in state_dict.items():
|
| 520 |
+
tensor_id = id(tensor)
|
| 521 |
+
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
+
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
+
torch_state_dict[name] = shared_tensor
|
| 524 |
+
else:
|
| 525 |
+
converted_tensors[tensor_id] = name
|
| 526 |
+
if return_empty_tensor:
|
| 527 |
+
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
+
else:
|
| 529 |
+
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
+
return torch_state_dict
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
+
tag=None,
|
| 535 |
+
exclude_frozen_parameters=False,
|
| 536 |
+
lazy_mode=False):
|
| 537 |
+
"""
|
| 538 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
+
via a model hub.
|
| 541 |
+
|
| 542 |
+
Args:
|
| 543 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
+
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
+
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
+
|
| 549 |
+
Returns:
|
| 550 |
+
- pytorch ``state_dict``
|
| 551 |
+
|
| 552 |
+
A typical usage might be ::
|
| 553 |
+
|
| 554 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
+
# do the training and checkpoint saving
|
| 556 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
+
model = model.cpu() # move to cpu
|
| 558 |
+
model.load_state_dict(state_dict)
|
| 559 |
+
# submit to model hub or save the model to share with others
|
| 560 |
+
|
| 561 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
+
|
| 565 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
+
|
| 567 |
+
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
+
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
+
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
+
|
| 571 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
+
for name, lazy_tensor in state_dict.item():
|
| 574 |
+
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
+
print(name, tensor)
|
| 576 |
+
# del tensor to release memory if it no longer in use
|
| 577 |
+
"""
|
| 578 |
+
if tag is None:
|
| 579 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
+
if os.path.isfile(latest_path):
|
| 581 |
+
with open(latest_path, 'r') as fd:
|
| 582 |
+
tag = fd.read().strip()
|
| 583 |
+
else:
|
| 584 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
+
|
| 586 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
+
|
| 588 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
+
|
| 591 |
+
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
+
if lazy_mode:
|
| 593 |
+
return state_dict
|
| 594 |
+
else:
|
| 595 |
+
return to_torch_tensor(state_dict)
|
| 596 |
+
|
| 597 |
+
|
| 598 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
+
output_dir,
|
| 600 |
+
max_shard_size="5GB",
|
| 601 |
+
safe_serialization=False,
|
| 602 |
+
tag=None,
|
| 603 |
+
exclude_frozen_parameters=False):
|
| 604 |
+
"""
|
| 605 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
+
|
| 608 |
+
Args:
|
| 609 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
+
"""
|
| 616 |
+
|
| 617 |
+
# Dependency pre-check
|
| 618 |
+
if safe_serialization:
|
| 619 |
+
try:
|
| 620 |
+
from safetensors.torch import save_file
|
| 621 |
+
except ImportError:
|
| 622 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
+
raise
|
| 624 |
+
if max_shard_size is not None:
|
| 625 |
+
try:
|
| 626 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
+
except ImportError:
|
| 628 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
+
raise
|
| 630 |
+
|
| 631 |
+
# Convert zero checkpoint to state_dict
|
| 632 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
+
tag,
|
| 634 |
+
exclude_frozen_parameters,
|
| 635 |
+
lazy_mode=True)
|
| 636 |
+
|
| 637 |
+
# Shard the model if it is too big.
|
| 638 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
+
if max_shard_size is not None:
|
| 640 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
+
# an memory-efficient approach for sharding
|
| 642 |
+
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
+
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
+
filename_pattern=filename_pattern,
|
| 645 |
+
max_shard_size=max_shard_size)
|
| 646 |
+
else:
|
| 647 |
+
from collections import namedtuple
|
| 648 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
+
|
| 652 |
+
# Save the model by shard
|
| 653 |
+
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
+
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
+
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
+
if safe_serialization:
|
| 660 |
+
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
+
else:
|
| 662 |
+
torch.save(shard_state_dict, output_path)
|
| 663 |
+
# release the memory of current shard
|
| 664 |
+
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
+
del state_dict[tensor_name]
|
| 666 |
+
del shard_state_dict[tensor_name]
|
| 667 |
+
del shard_state_dict
|
| 668 |
+
gc.collect()
|
| 669 |
+
|
| 670 |
+
# Save index if sharded
|
| 671 |
+
if state_dict_split.is_sharded:
|
| 672 |
+
index = {
|
| 673 |
+
"metadata": state_dict_split.metadata,
|
| 674 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
+
}
|
| 676 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
+
f.write(content)
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
+
"""
|
| 685 |
+
1. Put the provided model to cpu
|
| 686 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
+
3. Load it into the provided model
|
| 688 |
+
|
| 689 |
+
Args:
|
| 690 |
+
- ``model``: the model object to update
|
| 691 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
+
|
| 694 |
+
Returns:
|
| 695 |
+
- ``model`: modified model
|
| 696 |
+
|
| 697 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
+
conveniently placed for you in the checkpoint folder.
|
| 700 |
+
|
| 701 |
+
A typical usage might be ::
|
| 702 |
+
|
| 703 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
+
# submit to model hub or save the model to share with others
|
| 706 |
+
|
| 707 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
+
|
| 711 |
+
"""
|
| 712 |
+
logger.info("Extracting fp32 weights")
|
| 713 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
+
|
| 715 |
+
logger.info("Overwriting model with fp32 weights")
|
| 716 |
+
model = model.cpu()
|
| 717 |
+
model.load_state_dict(state_dict, strict=False)
|
| 718 |
+
|
| 719 |
+
return model
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
if __name__ == "__main__":
|
| 723 |
+
parser = argparse.ArgumentParser()
|
| 724 |
+
parser.add_argument("checkpoint_dir",
|
| 725 |
+
type=str,
|
| 726 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
+
parser.add_argument("output_dir",
|
| 728 |
+
type=str,
|
| 729 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
+
parser.add_argument(
|
| 732 |
+
"--max_shard_size",
|
| 733 |
+
type=str,
|
| 734 |
+
default="5GB",
|
| 735 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
+
"without CPU OOM issues.")
|
| 739 |
+
parser.add_argument(
|
| 740 |
+
"--safe_serialization",
|
| 741 |
+
default=False,
|
| 742 |
+
action='store_true',
|
| 743 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
+
parser.add_argument("-t",
|
| 745 |
+
"--tag",
|
| 746 |
+
type=str,
|
| 747 |
+
default=None,
|
| 748 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
+
args = parser.parse_args()
|
| 752 |
+
|
| 753 |
+
debug = args.debug
|
| 754 |
+
|
| 755 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
+
args.output_dir,
|
| 757 |
+
max_shard_size=args.max_shard_size,
|
| 758 |
+
safe_serialization=args.safe_serialization,
|
| 759 |
+
tag=args.tag,
|
| 760 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|