Upload fp16/args.json
Browse files- fp16/args.json +476 -0
fp16/args.json
ADDED
|
@@ -0,0 +1,476 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/mnt/data/ws/project/ms-swift/output/v3_sft_4b_20260430/v3-20260501-125351",
|
| 3 |
+
"overwrite_output_dir": false,
|
| 4 |
+
"do_train": false,
|
| 5 |
+
"do_eval": false,
|
| 6 |
+
"do_predict": false,
|
| 7 |
+
"eval_strategy": "no",
|
| 8 |
+
"prediction_loss_only": false,
|
| 9 |
+
"per_device_train_batch_size": 1,
|
| 10 |
+
"per_device_eval_batch_size": 1,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 2,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 1e-05,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"adam_beta1": 0.9,
|
| 20 |
+
"adam_beta2": 0.95,
|
| 21 |
+
"adam_epsilon": 1e-08,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"num_train_epochs": 3.0,
|
| 24 |
+
"max_steps": -1,
|
| 25 |
+
"lr_scheduler_type": "cosine",
|
| 26 |
+
"lr_scheduler_kwargs": null,
|
| 27 |
+
"warmup_ratio": 0.1,
|
| 28 |
+
"warmup_steps": 0,
|
| 29 |
+
"log_level": "passive",
|
| 30 |
+
"log_level_replica": "warning",
|
| 31 |
+
"log_on_each_node": true,
|
| 32 |
+
"logging_dir": "/mnt/data/ws/project/ms-swift/output/v3_sft_4b_20260430/v3-20260501-125351/runs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 10,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 2000.0,
|
| 39 |
+
"save_total_limit": 12,
|
| 40 |
+
"save_safetensors": true,
|
| 41 |
+
"save_on_each_node": false,
|
| 42 |
+
"save_only_model": false,
|
| 43 |
+
"restore_callback_states_from_checkpoint": false,
|
| 44 |
+
"no_cuda": false,
|
| 45 |
+
"use_cpu": false,
|
| 46 |
+
"use_mps_device": false,
|
| 47 |
+
"seed": 42,
|
| 48 |
+
"data_seed": 42,
|
| 49 |
+
"jit_mode_eval": false,
|
| 50 |
+
"bf16": true,
|
| 51 |
+
"fp16": false,
|
| 52 |
+
"fp16_opt_level": "O1",
|
| 53 |
+
"half_precision_backend": "auto",
|
| 54 |
+
"bf16_full_eval": false,
|
| 55 |
+
"fp16_full_eval": false,
|
| 56 |
+
"tf32": null,
|
| 57 |
+
"local_rank": 0,
|
| 58 |
+
"ddp_backend": null,
|
| 59 |
+
"tpu_num_cores": null,
|
| 60 |
+
"tpu_metrics_debug": false,
|
| 61 |
+
"debug": null,
|
| 62 |
+
"dataloader_drop_last": false,
|
| 63 |
+
"eval_steps": 2000.0,
|
| 64 |
+
"dataloader_num_workers": 16,
|
| 65 |
+
"dataloader_prefetch_factor": null,
|
| 66 |
+
"past_index": -1,
|
| 67 |
+
"run_name": "/mnt/data/ws/project/ms-swift/output/v3_sft_4b_20260430/v3-20260501-125351",
|
| 68 |
+
"disable_tqdm": null,
|
| 69 |
+
"remove_unused_columns": true,
|
| 70 |
+
"label_names": null,
|
| 71 |
+
"load_best_model_at_end": false,
|
| 72 |
+
"metric_for_best_model": "loss",
|
| 73 |
+
"greater_is_better": false,
|
| 74 |
+
"ignore_data_skip": false,
|
| 75 |
+
"fsdp": [],
|
| 76 |
+
"fsdp_min_num_params": 0,
|
| 77 |
+
"fsdp_config": null,
|
| 78 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 79 |
+
"accelerator_config": {
|
| 80 |
+
"dispatch_batches": false
|
| 81 |
+
},
|
| 82 |
+
"parallelism_config": null,
|
| 83 |
+
"deepspeed": {
|
| 84 |
+
"fp16": {
|
| 85 |
+
"enabled": "auto",
|
| 86 |
+
"loss_scale": 0,
|
| 87 |
+
"loss_scale_window": 1000,
|
| 88 |
+
"initial_scale_power": 16,
|
| 89 |
+
"hysteresis": 2,
|
| 90 |
+
"min_loss_scale": 1
|
| 91 |
+
},
|
| 92 |
+
"bf16": {
|
| 93 |
+
"enabled": "auto"
|
| 94 |
+
},
|
| 95 |
+
"zero_optimization": {
|
| 96 |
+
"stage": 3,
|
| 97 |
+
"offload_optimizer": {
|
| 98 |
+
"device": "none",
|
| 99 |
+
"pin_memory": true
|
| 100 |
+
},
|
| 101 |
+
"offload_param": {
|
| 102 |
+
"device": "none",
|
| 103 |
+
"pin_memory": true
|
| 104 |
+
},
|
| 105 |
+
"overlap_comm": false,
|
| 106 |
+
"contiguous_gradients": true,
|
| 107 |
+
"sub_group_size": 1000000000.0,
|
| 108 |
+
"reduce_bucket_size": "auto",
|
| 109 |
+
"zero_quantized_weights": false,
|
| 110 |
+
"zero_quantized_gradients": false,
|
| 111 |
+
"stage3_prefetch_bucket_size": "auto",
|
| 112 |
+
"stage3_param_persistence_threshold": "auto",
|
| 113 |
+
"stage3_max_live_parameters": 1000000000.0,
|
| 114 |
+
"stage3_max_reuse_distance": 1000000000.0,
|
| 115 |
+
"stage3_gather_16bit_weights_on_model_save": true
|
| 116 |
+
},
|
| 117 |
+
"gradient_accumulation_steps": "auto",
|
| 118 |
+
"gradient_clipping": "auto",
|
| 119 |
+
"steps_per_print": 2000,
|
| 120 |
+
"train_batch_size": "auto",
|
| 121 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 122 |
+
"wall_clock_breakdown": false
|
| 123 |
+
},
|
| 124 |
+
"label_smoothing_factor": 0.0,
|
| 125 |
+
"optim": "adamw_torch_fused",
|
| 126 |
+
"optim_args": null,
|
| 127 |
+
"adafactor": false,
|
| 128 |
+
"group_by_length": false,
|
| 129 |
+
"length_column_name": "length",
|
| 130 |
+
"report_to": [
|
| 131 |
+
"tensorboard"
|
| 132 |
+
],
|
| 133 |
+
"project": "huggingface",
|
| 134 |
+
"trackio_space_id": "trackio",
|
| 135 |
+
"ddp_find_unused_parameters": null,
|
| 136 |
+
"ddp_bucket_cap_mb": null,
|
| 137 |
+
"ddp_broadcast_buffers": null,
|
| 138 |
+
"dataloader_pin_memory": true,
|
| 139 |
+
"dataloader_persistent_workers": false,
|
| 140 |
+
"skip_memory_metrics": true,
|
| 141 |
+
"use_legacy_prediction_loop": false,
|
| 142 |
+
"push_to_hub": false,
|
| 143 |
+
"resume_from_checkpoint": null,
|
| 144 |
+
"hub_model_id": null,
|
| 145 |
+
"hub_strategy": "every_save",
|
| 146 |
+
"hub_token": null,
|
| 147 |
+
"hub_private_repo": null,
|
| 148 |
+
"hub_always_push": false,
|
| 149 |
+
"hub_revision": null,
|
| 150 |
+
"gradient_checkpointing": true,
|
| 151 |
+
"gradient_checkpointing_kwargs": null,
|
| 152 |
+
"include_inputs_for_metrics": false,
|
| 153 |
+
"include_for_metrics": [],
|
| 154 |
+
"eval_do_concat_batches": true,
|
| 155 |
+
"fp16_backend": "auto",
|
| 156 |
+
"push_to_hub_model_id": null,
|
| 157 |
+
"push_to_hub_organization": null,
|
| 158 |
+
"push_to_hub_token": null,
|
| 159 |
+
"mp_parameters": "",
|
| 160 |
+
"auto_find_batch_size": false,
|
| 161 |
+
"full_determinism": false,
|
| 162 |
+
"torchdynamo": null,
|
| 163 |
+
"ray_scope": "last",
|
| 164 |
+
"ddp_timeout": 18000000,
|
| 165 |
+
"torch_compile": false,
|
| 166 |
+
"torch_compile_backend": null,
|
| 167 |
+
"torch_compile_mode": null,
|
| 168 |
+
"include_tokens_per_second": false,
|
| 169 |
+
"include_num_input_tokens_seen": false,
|
| 170 |
+
"neftune_noise_alpha": null,
|
| 171 |
+
"optim_target_modules": null,
|
| 172 |
+
"batch_eval_metrics": false,
|
| 173 |
+
"eval_on_start": false,
|
| 174 |
+
"use_liger_kernel": false,
|
| 175 |
+
"liger_kernel_config": null,
|
| 176 |
+
"eval_use_gather_object": false,
|
| 177 |
+
"average_tokens_across_devices": true,
|
| 178 |
+
"sortish_sampler": false,
|
| 179 |
+
"predict_with_generate": false,
|
| 180 |
+
"generation_max_length": null,
|
| 181 |
+
"generation_num_beams": null,
|
| 182 |
+
"generation_config": null,
|
| 183 |
+
"tuner_backend": "peft",
|
| 184 |
+
"vit_gradient_checkpointing": false,
|
| 185 |
+
"router_aux_loss_coef": 0.0,
|
| 186 |
+
"enable_dft_loss": false,
|
| 187 |
+
"enable_channel_loss": false,
|
| 188 |
+
"safe_serialization": true,
|
| 189 |
+
"max_shard_size": "5GB",
|
| 190 |
+
"check_model": true,
|
| 191 |
+
"acc_strategy": "token",
|
| 192 |
+
"train_dataloader_shuffle": true,
|
| 193 |
+
"max_epochs": null,
|
| 194 |
+
"aligner_lr": null,
|
| 195 |
+
"vit_lr": null,
|
| 196 |
+
"use_logits_to_keep": null,
|
| 197 |
+
"ds3_gather_for_generation": true,
|
| 198 |
+
"resume_only_model": false,
|
| 199 |
+
"optimizer": null,
|
| 200 |
+
"loss_type": null,
|
| 201 |
+
"eval_metric": null,
|
| 202 |
+
"callbacks": [],
|
| 203 |
+
"early_stop_interval": null,
|
| 204 |
+
"eval_use_evalscope": false,
|
| 205 |
+
"eval_dataset": [],
|
| 206 |
+
"eval_dataset_args": null,
|
| 207 |
+
"eval_limit": null,
|
| 208 |
+
"eval_generation_config": null,
|
| 209 |
+
"extra_eval_args": null,
|
| 210 |
+
"tuner_type": "full",
|
| 211 |
+
"use_galore": false,
|
| 212 |
+
"galore_target_modules": null,
|
| 213 |
+
"galore_rank": 128,
|
| 214 |
+
"galore_update_proj_gap": 50,
|
| 215 |
+
"galore_scale": 1.0,
|
| 216 |
+
"galore_proj_type": "std",
|
| 217 |
+
"galore_optim_per_parameter": false,
|
| 218 |
+
"galore_with_embedding": false,
|
| 219 |
+
"galore_quantization": false,
|
| 220 |
+
"galore_proj_quant": false,
|
| 221 |
+
"galore_proj_bits": 4,
|
| 222 |
+
"galore_proj_group_size": 256,
|
| 223 |
+
"galore_cos_threshold": 0.4,
|
| 224 |
+
"galore_gamma_proj": 2,
|
| 225 |
+
"galore_queue_size": 5,
|
| 226 |
+
"lisa_activated_layers": 0,
|
| 227 |
+
"lisa_step_interval": 20,
|
| 228 |
+
"use_flash_ckpt": false,
|
| 229 |
+
"use_ray": false,
|
| 230 |
+
"ray_exp_name": null,
|
| 231 |
+
"device_groups": null,
|
| 232 |
+
"model": "/mnt/data/weights/Qwen3-VL-4B-Instruct",
|
| 233 |
+
"model_type": "qwen3_vl",
|
| 234 |
+
"model_revision": null,
|
| 235 |
+
"task_type": "causal_lm",
|
| 236 |
+
"torch_dtype": "bfloat16",
|
| 237 |
+
"attn_impl": null,
|
| 238 |
+
"experts_impl": null,
|
| 239 |
+
"new_special_tokens": [],
|
| 240 |
+
"num_labels": null,
|
| 241 |
+
"problem_type": null,
|
| 242 |
+
"rope_scaling": null,
|
| 243 |
+
"device_map": null,
|
| 244 |
+
"max_memory": {},
|
| 245 |
+
"max_model_len": null,
|
| 246 |
+
"local_repo_path": null,
|
| 247 |
+
"init_strategy": null,
|
| 248 |
+
"template": "qwen3_vl",
|
| 249 |
+
"system": null,
|
| 250 |
+
"max_length": 32768,
|
| 251 |
+
"truncation_strategy": "delete",
|
| 252 |
+
"max_pixels": null,
|
| 253 |
+
"agent_template": null,
|
| 254 |
+
"norm_bbox": null,
|
| 255 |
+
"use_chat_template": true,
|
| 256 |
+
"padding_side": "right",
|
| 257 |
+
"padding_free": false,
|
| 258 |
+
"loss_scale": "default",
|
| 259 |
+
"sequence_parallel_size": 1,
|
| 260 |
+
"template_backend": "swift",
|
| 261 |
+
"response_prefix": null,
|
| 262 |
+
"enable_thinking": null,
|
| 263 |
+
"add_non_thinking_prefix": true,
|
| 264 |
+
"dataset": [
|
| 265 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_v1.0_qwen3vl_single_pos_cua_v2/train_benchmark_aug_sft_qa_point_addthink_history_img_positive_v3.0_fix.json",
|
| 266 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_v1.0_qwen3vl_single_pos_cua_v2/train_benchmark_aug_sft_qa_point_addthink_history_img_positive_v3.0_fix_mask.json",
|
| 267 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_v1.0_qwen3vl_single_pos_cua_v2/train_ete_think_regen_2history.json",
|
| 268 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_v1.0_qwen3vl_single_pos_cua_v2/train_mind2webonline_aug_sft_qa_point_addthink_history_img_positive_v4.0_fix.json",
|
| 269 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_v1.0_qwen3vl_single_pos_cua_v2/train_scalecua_data_20250328_web_navigation_20250428_aug_sft_qa_point_addthink_history_img.json",
|
| 270 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_v1.0_qwen3vl_single_pos_cua_v2/train_scalecua_data_20250421_web_navigation_20250601_aug_sft_qa_point_addthink_history_img.json",
|
| 271 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_v1.0_qwen3vl_single_pos_cua_v2/train_scalecua_data_20250612_web_planning_20250720_boost_instruction_aug_sft_qa_point_addthink_history_img.json",
|
| 272 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_v1.0_qwen3vl_single_pos_cua_v2/train_scalecua_data_20250624_web_planning_20250720_boost_instruction_aug_sft_qa_point_addthink_history_img.json",
|
| 273 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_v1.0_qwen3vl_single_pos_cua_v2/train_scalecua_data_20250630_web_planning_20250720_boost_instruction_aug_sft_qa_point_addthink_history_img.json",
|
| 274 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250326_aug_sft_qa_point_addthink_history_img.json",
|
| 275 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250401_aug_sft_qa_point_addthink_history_img.json",
|
| 276 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250417_aug_sft_qa_point_addthink_history_img.json",
|
| 277 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250418_aug_sft_qa_point_addthink_history_img.json",
|
| 278 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250514_aug_sft_qa_point_addthink_history_img.json",
|
| 279 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250515_aug_sft_qa_point_addthink_history_img.json",
|
| 280 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250613_aug_sft_qa_point_addthink_history_img.json",
|
| 281 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250630_aug_sft_qa_point_addthink_history_img.json",
|
| 282 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250707_aug_sft_qa_point_addthink_history_img.json",
|
| 283 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250722_aug_sft_qa_point_addthink_history_img.json",
|
| 284 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250730_aug_sft_qa_point_addthink_history_img.json",
|
| 285 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250805_aug_sft_qa_point_addthink_history_img.json",
|
| 286 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250825_aug_sft_qa_point_addthink_history_img.json",
|
| 287 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_20250904_aug_sft_qa_point_addthink_history_img.json",
|
| 288 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_mind2web_aug_sft_qa_point_addthink_history_img_with_scroll_ch.json",
|
| 289 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_mind2web_aug_sft_qa_point_with_scroll_ch.json",
|
| 290 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_mind2webonline1_aug_sft_qa_point.json",
|
| 291 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_mind2webonline1_aug_sft_qa_point_addthink_history_img.json",
|
| 292 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_mind2webonline2_aug_sft_qa_point.json",
|
| 293 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_mind2webonline2_aug_sft_qa_point_addthink_history_img.json",
|
| 294 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250326_aug_fty_sft_qa_point.json",
|
| 295 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250401_aug_fty_sft_qa_point.json",
|
| 296 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250417_aug_fty_sft_qa_point.json",
|
| 297 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250418_aug_fty_sft_qa_point.json",
|
| 298 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250514_aug_fty_sft_qa_point.json",
|
| 299 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250515_aug_fty_sft_qa_point.json",
|
| 300 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250613_aug_fty_sft_qa_point.json",
|
| 301 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250630_aug_fty_sft_qa_point.json",
|
| 302 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250702_aug_fty_sft_qa_point_call_user.json",
|
| 303 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250702_aug_fty_sft_qa_point_call_user_addthink_history_img.json",
|
| 304 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250702_aug_fty_sft_qa_point_wait.json",
|
| 305 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250702_aug_fty_sft_qa_point_wait_addthink_history_img.json",
|
| 306 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250707_aug_fty_sft_qa_point.json",
|
| 307 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250722_aug_fty_sft_qa_point.json",
|
| 308 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250730_aug_fty_sft_qa_point.json",
|
| 309 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250805_aug_fty_sft_qa_point.json",
|
| 310 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250825_aug_fty_sft_qa_point.json",
|
| 311 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_v0.4_20250904_aug_fty_sft_qa_point.json",
|
| 312 |
+
"/mnt/data/mind2web_auto_explore/aartificial_dataset_v1.0_qwen3vl_single_pos_cua_v2/computer_use_train_uitar1.5_webretriever1_aug_sft_qa_point_addthink_history_img.json",
|
| 313 |
+
"/mnt/data/hufei/experiments/CUA_dataset_qwen3vl/sft_data_v2/sft_agentnet.jsonl",
|
| 314 |
+
"/mnt/data/hufei/experiments/CUA_dataset_qwen3vl/sft_data_v2/sft_opencua.json",
|
| 315 |
+
"/mnt/data/hufei/experiments/CUA_dataset_qwen3vl/sft_data_v2/sft_osworld.json",
|
| 316 |
+
"/mnt/data/hufei/experiments/CUA_dataset_qwen3vl/sft_data_v2/sft_zicai.json",
|
| 317 |
+
"/mnt/data/CUA/action_SFT_data_vepfs/merged_data_internVL_grounding_sr_only_bbox_norm_turbodata.json",
|
| 318 |
+
"/mnt/data/CUA/action_SFT_data_vepfs/merged_data_internVL_grounding_sr_only_point_turbodata.json",
|
| 319 |
+
"/mnt/data/CUA/action_SFT_data_new_vepfs_third/action_SFT_data_new/internVL_grounding_only_bbox_ref_0_100000_verified_new_norm_turbodata.json",
|
| 320 |
+
"/mnt/data/CUA/action_SFT_data_new_vepfs_third/action_SFT_data_new/internVL_grounding_only_bbox_ref_100000_200000_verified_new_norm_turbodata.json",
|
| 321 |
+
"/mnt/data/CUA/action_SFT_data_new_vepfs_third/action_SFT_data_new/internVL_grounding_only_bbox_ref_200000_675145_verified_new_norm_turbodata.json",
|
| 322 |
+
"/mnt/data/CUA/action_SFT_data_new_vepfs_third/action_SFT_data_new/merged_data_action_grounding_fix1127_sr_id_norm_turbodata.json",
|
| 323 |
+
"/mnt/data/CUA/action_SFT_data_new/merged_data_forward.json",
|
| 324 |
+
"/mnt/data/CUA/action_SFT_data_new_vepfs_third/action_SFT_data_new_en/internVL_grounding_only_bbox_ref_0_100000_verified_new_norm_turbodata.json",
|
| 325 |
+
"/mnt/data/CUA/action_SFT_data_new_vepfs_third/action_SFT_data_new_en/internVL_grounding_only_bbox_ref_100000_200000_verified_new_norm_turbodata.json",
|
| 326 |
+
"/mnt/data/CUA/action_SFT_data_new_vepfs_third/action_SFT_data_new_en/internVL_grounding_only_bbox_ref_200000_675145_verified_new_norm_turbodata.json",
|
| 327 |
+
"/mnt/data/CUA/action_SFT_data_new_vepfs_third/action_SFT_data_new_en/merged_data_action_grounding_fix1127_sr_id_norm_turbodata.json",
|
| 328 |
+
"/mnt/data/CUA/action_SFT_data_new_en/merged_data_forward.json",
|
| 329 |
+
"/mnt/data/wanghanning/trajactory/sft_qa_tos_sessions_select_batch1_aug3.json",
|
| 330 |
+
"/mnt/data/wanghanning/trajactory/sft_qa_tos_sessions_select_batch2_aug3.json",
|
| 331 |
+
"/mnt/data/wanghanning/trajactory/sft_qa_tos_sessions_select_batch3_aug3.json",
|
| 332 |
+
"/mnt/data/dw/experiments/Online-Mind2Web-main/train_data_open_url_qa_v1.0/train_open_url_aug_sft_qa_point_addthink_history_img.json"
|
| 333 |
+
],
|
| 334 |
+
"val_dataset": [],
|
| 335 |
+
"cached_dataset": [],
|
| 336 |
+
"cached_val_dataset": [],
|
| 337 |
+
"split_dataset_ratio": 0.0,
|
| 338 |
+
"dataset_num_proc": 1,
|
| 339 |
+
"load_from_cache_file": false,
|
| 340 |
+
"dataset_shuffle": true,
|
| 341 |
+
"val_dataset_shuffle": false,
|
| 342 |
+
"streaming": false,
|
| 343 |
+
"interleave_prob": null,
|
| 344 |
+
"stopping_strategy": "first_exhausted",
|
| 345 |
+
"shuffle_buffer_size": 1000,
|
| 346 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 347 |
+
"columns": {},
|
| 348 |
+
"strict": false,
|
| 349 |
+
"disable_auto_column_mapping": false,
|
| 350 |
+
"model_name": null,
|
| 351 |
+
"model_author": null,
|
| 352 |
+
"custom_dataset_info": [],
|
| 353 |
+
"quant_method": null,
|
| 354 |
+
"quant_bits": null,
|
| 355 |
+
"hqq_axis": null,
|
| 356 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 357 |
+
"bnb_4bit_quant_type": "nf4",
|
| 358 |
+
"bnb_4bit_use_double_quant": true,
|
| 359 |
+
"bnb_4bit_quant_storage": null,
|
| 360 |
+
"max_new_tokens": 64,
|
| 361 |
+
"temperature": 0.0,
|
| 362 |
+
"top_k": null,
|
| 363 |
+
"top_p": null,
|
| 364 |
+
"repetition_penalty": null,
|
| 365 |
+
"num_beams": 1,
|
| 366 |
+
"stream": false,
|
| 367 |
+
"stop_words": [],
|
| 368 |
+
"logprobs": false,
|
| 369 |
+
"top_logprobs": null,
|
| 370 |
+
"structured_outputs_regex": null,
|
| 371 |
+
"adapters": [],
|
| 372 |
+
"external_plugins": [],
|
| 373 |
+
"custom_register_path": [],
|
| 374 |
+
"model_kwargs": {},
|
| 375 |
+
"load_args": false,
|
| 376 |
+
"load_data_args": false,
|
| 377 |
+
"packing": false,
|
| 378 |
+
"packing_length": null,
|
| 379 |
+
"packing_num_proc": 1,
|
| 380 |
+
"lazy_tokenize": true,
|
| 381 |
+
"use_hf": false,
|
| 382 |
+
"ignore_args_error": false,
|
| 383 |
+
"use_swift_lora": false,
|
| 384 |
+
"freeze_parameters": [
|
| 385 |
+
"model.visual"
|
| 386 |
+
],
|
| 387 |
+
"freeze_parameters_regex": null,
|
| 388 |
+
"freeze_parameters_ratio": 0.0,
|
| 389 |
+
"trainable_parameters": [
|
| 390 |
+
"model.visual.merger",
|
| 391 |
+
"model.visual.deepstack_merger_list"
|
| 392 |
+
],
|
| 393 |
+
"trainable_parameters_regex": null,
|
| 394 |
+
"freeze_llm": false,
|
| 395 |
+
"freeze_vit": true,
|
| 396 |
+
"freeze_aligner": false,
|
| 397 |
+
"target_modules": [
|
| 398 |
+
"all-linear"
|
| 399 |
+
],
|
| 400 |
+
"target_regex": null,
|
| 401 |
+
"target_parameters": null,
|
| 402 |
+
"modules_to_save": [],
|
| 403 |
+
"lora_rank": 8,
|
| 404 |
+
"lora_alpha": 32,
|
| 405 |
+
"lora_dropout": 0.05,
|
| 406 |
+
"lora_bias": "none",
|
| 407 |
+
"lora_dtype": null,
|
| 408 |
+
"lorap_lr_ratio": null,
|
| 409 |
+
"use_rslora": false,
|
| 410 |
+
"use_dora": false,
|
| 411 |
+
"lora_ga_batch_size": 2,
|
| 412 |
+
"lora_ga_iters": 2,
|
| 413 |
+
"lora_ga_max_length": 1024,
|
| 414 |
+
"lora_ga_direction": "ArB2r",
|
| 415 |
+
"lora_ga_scale": "stable",
|
| 416 |
+
"lora_ga_stable_gamma": 16,
|
| 417 |
+
"init_weights": true,
|
| 418 |
+
"fourier_n_frequency": 2000,
|
| 419 |
+
"fourier_scaling": 300.0,
|
| 420 |
+
"boft_block_size": 4,
|
| 421 |
+
"boft_block_num": 0,
|
| 422 |
+
"boft_n_butterfly_factor": 1,
|
| 423 |
+
"boft_dropout": 0.0,
|
| 424 |
+
"vera_rank": 256,
|
| 425 |
+
"vera_projection_prng_key": 0,
|
| 426 |
+
"vera_dropout": 0.0,
|
| 427 |
+
"vera_d_initial": 0.1,
|
| 428 |
+
"adapter_act": "gelu",
|
| 429 |
+
"adapter_length": 128,
|
| 430 |
+
"adalora_target_r": 8,
|
| 431 |
+
"adalora_init_r": 12,
|
| 432 |
+
"adalora_tinit": 0,
|
| 433 |
+
"adalora_tfinal": 0,
|
| 434 |
+
"adalora_deltaT": 1,
|
| 435 |
+
"adalora_beta1": 0.85,
|
| 436 |
+
"adalora_beta2": 0.85,
|
| 437 |
+
"adalora_orth_reg_weight": 0.5,
|
| 438 |
+
"llamapro_num_new_blocks": 4,
|
| 439 |
+
"llamapro_num_groups": null,
|
| 440 |
+
"reft_layer_key": null,
|
| 441 |
+
"reft_layers": null,
|
| 442 |
+
"reft_rank": 4,
|
| 443 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 444 |
+
"reft_args": null,
|
| 445 |
+
"swanlab_token": null,
|
| 446 |
+
"swanlab_project": "ms-swift",
|
| 447 |
+
"swanlab_workspace": null,
|
| 448 |
+
"swanlab_exp_name": null,
|
| 449 |
+
"swanlab_notification_method": null,
|
| 450 |
+
"swanlab_webhook_url": null,
|
| 451 |
+
"swanlab_secret": null,
|
| 452 |
+
"swanlab_sender_email": null,
|
| 453 |
+
"swanlab_receiver_email": null,
|
| 454 |
+
"swanlab_smtp_server": null,
|
| 455 |
+
"swanlab_smtp_port": null,
|
| 456 |
+
"swanlab_email_language": "zh",
|
| 457 |
+
"swanlab_mode": "cloud",
|
| 458 |
+
"add_version": true,
|
| 459 |
+
"create_checkpoint_symlink": false,
|
| 460 |
+
"zero_hpz_partition_size": null,
|
| 461 |
+
"deepspeed_autotp_size": null,
|
| 462 |
+
"swift_version": "4.2.0.dev0",
|
| 463 |
+
"ckpt_dir": null,
|
| 464 |
+
"rank": 0,
|
| 465 |
+
"global_world_size": 72,
|
| 466 |
+
"local_world_size": 8,
|
| 467 |
+
"model_suffix": "Qwen3-VL-4B-Instruct",
|
| 468 |
+
"model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/mnt/data/weights/Qwen3-VL-4B-Instruct', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
|
| 469 |
+
"model_meta": "ModelMeta(model_type='qwen3_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct', hf_model_id='Qwen/Qwen3-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking', hf_model_id='Qwen/Qwen3-VL-2B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct', hf_model_id='Qwen/Qwen3-VL-4B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking', hf_model_id='Qwen/Qwen3-VL-4B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct', hf_model_id='Qwen/Qwen3-VL-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking', hf_model_id='Qwen/Qwen3-VL-8B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct', hf_model_id='Qwen/Qwen3-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking', hf_model_id='Qwen/Qwen3-VL-32B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_vl', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3VLLoader'>, template='qwen3_vl', model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), mcore_model_type=None, architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=[])",
|
| 470 |
+
"model_dir": "/mnt/data/weights/Qwen3-VL-4B-Instruct",
|
| 471 |
+
"template_meta": "QwenTemplateMeta(template_type='qwen3_vl', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3VLTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='<think>\\n', non_thinking_prefix='', history_thinking_prefix='')",
|
| 472 |
+
"_val_dataset_exists": false,
|
| 473 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 474 |
+
"evaluation_strategy": "steps",
|
| 475 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/data/ws/project/ms-swift/output/v3_sft_4b_20260430/v3-20260501-125351', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=3.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mnt/data/ws/project/ms-swift/output/v3_sft_4b_20260430/v3-20260501-125351/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=2000, save_total_limit=12, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000.0, dataloader_num_workers=16, dataloader_prefetch_factor=2, past_index=-1, run_name='/mnt/data/ws/project/ms-swift/output/v3_sft_4b_20260430/v3-20260501-125351', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=False, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
|
| 476 |
+
}
|