Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/added_tokens.json +28 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/args.json +388 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/chat_template.jinja +120 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/config.json +69 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/generation_config.json +13 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/latest +1 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/merges.txt +0 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/model-00001-of-00004.safetensors +3 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/model-00002-of-00004.safetensors +3 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/model-00003-of-00004.safetensors +3 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/model-00004-of-00004.safetensors +3 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/model.safetensors.index.json +758 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/preprocessor_config.json +21 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/special_tokens_map.json +31 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/tokenizer.json +3 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/tokenizer_config.json +240 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/trainer_state.json +3114 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/training_args.bin +3 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/video_preprocessor_config.json +41 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/vocab.json +0 -0
- qwen3vl_8b_agentnetv1_fullsft_gb200/zero_to_fp32.py +760 -0
.gitattributes
CHANGED
|
@@ -38,3 +38,4 @@ qwen3vl_8b_click100k_fullsft_gb200/tokenizer.json filter=lfs diff=lfs merge=lfs
|
|
| 38 |
qwen3vl_8b_click100k_fullsft-lr1e-5_gb200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
AgentNet/agentnet_ubuntu_5k.train0107.openai.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 40 |
AgentNet/agentnet_win_mac_18k.train0107.openai.jsonl filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 38 |
qwen3vl_8b_click100k_fullsft-lr1e-5_gb200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
AgentNet/agentnet_ubuntu_5k.train0107.openai.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 40 |
AgentNet/agentnet_win_mac_18k.train0107.openai.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
qwen3vl_8b_agentnetv1_fullsft_gb200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
qwen3vl_8b_agentnetv1_fullsft_gb200/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/args.json
ADDED
|
@@ -0,0 +1,388 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/workspace/weixian/workplace/ms_swift_project/ms-swift/output/qwen3vl_8b_sft_full_agentnet_dist/v3-20260118-132920",
|
| 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": 8,
|
| 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": 3,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 2e-05,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"adam_beta1": 0.9,
|
| 20 |
+
"adam_beta2": 0.95,
|
| 21 |
+
"adam_epsilon": 1e-08,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"num_train_epochs": 2.0,
|
| 24 |
+
"max_steps": -1,
|
| 25 |
+
"lr_scheduler_type": "cosine",
|
| 26 |
+
"lr_scheduler_kwargs": null,
|
| 27 |
+
"warmup_ratio": 0.05,
|
| 28 |
+
"warmup_steps": 0,
|
| 29 |
+
"log_level": "passive",
|
| 30 |
+
"log_level_replica": "warning",
|
| 31 |
+
"log_on_each_node": true,
|
| 32 |
+
"logging_dir": "/workspace/weixian/workplace/ms_swift_project/ms-swift/output/qwen3vl_8b_sft_full_agentnet_dist/v3-20260118-132920/runs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 5,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 200.0,
|
| 39 |
+
"save_total_limit": 2,
|
| 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": 200.0,
|
| 64 |
+
"dataloader_num_workers": 8,
|
| 65 |
+
"dataloader_prefetch_factor": null,
|
| 66 |
+
"past_index": -1,
|
| 67 |
+
"run_name": "/workspace/weixian/workplace/ms_swift_project/ms-swift/output/qwen3vl_8b_sft_full_agentnet_dist/v3-20260118-132920",
|
| 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": 1,
|
| 97 |
+
"offload_optimizer": {
|
| 98 |
+
"device": "none",
|
| 99 |
+
"pin_memory": true
|
| 100 |
+
},
|
| 101 |
+
"allgather_partitions": true,
|
| 102 |
+
"allgather_bucket_size": 200000000.0,
|
| 103 |
+
"overlap_comm": false,
|
| 104 |
+
"reduce_scatter": true,
|
| 105 |
+
"reduce_bucket_size": 200000000.0,
|
| 106 |
+
"contiguous_gradients": true
|
| 107 |
+
},
|
| 108 |
+
"gradient_accumulation_steps": "auto",
|
| 109 |
+
"gradient_clipping": "auto",
|
| 110 |
+
"steps_per_print": 2000,
|
| 111 |
+
"train_batch_size": "auto",
|
| 112 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 113 |
+
"wall_clock_breakdown": false
|
| 114 |
+
},
|
| 115 |
+
"label_smoothing_factor": 0.0,
|
| 116 |
+
"optim": "adamw_torch_fused",
|
| 117 |
+
"optim_args": null,
|
| 118 |
+
"adafactor": false,
|
| 119 |
+
"group_by_length": false,
|
| 120 |
+
"length_column_name": "length",
|
| 121 |
+
"report_to": [
|
| 122 |
+
"tensorboard"
|
| 123 |
+
],
|
| 124 |
+
"project": "huggingface",
|
| 125 |
+
"trackio_space_id": "trackio",
|
| 126 |
+
"ddp_find_unused_parameters": null,
|
| 127 |
+
"ddp_bucket_cap_mb": null,
|
| 128 |
+
"ddp_broadcast_buffers": null,
|
| 129 |
+
"dataloader_pin_memory": true,
|
| 130 |
+
"dataloader_persistent_workers": false,
|
| 131 |
+
"skip_memory_metrics": true,
|
| 132 |
+
"use_legacy_prediction_loop": false,
|
| 133 |
+
"push_to_hub": false,
|
| 134 |
+
"resume_from_checkpoint": null,
|
| 135 |
+
"hub_model_id": null,
|
| 136 |
+
"hub_strategy": "every_save",
|
| 137 |
+
"hub_token": null,
|
| 138 |
+
"hub_private_repo": null,
|
| 139 |
+
"hub_always_push": false,
|
| 140 |
+
"hub_revision": null,
|
| 141 |
+
"gradient_checkpointing": true,
|
| 142 |
+
"gradient_checkpointing_kwargs": null,
|
| 143 |
+
"include_inputs_for_metrics": false,
|
| 144 |
+
"include_for_metrics": [],
|
| 145 |
+
"eval_do_concat_batches": true,
|
| 146 |
+
"fp16_backend": "auto",
|
| 147 |
+
"push_to_hub_model_id": null,
|
| 148 |
+
"push_to_hub_organization": null,
|
| 149 |
+
"push_to_hub_token": null,
|
| 150 |
+
"mp_parameters": "",
|
| 151 |
+
"auto_find_batch_size": false,
|
| 152 |
+
"full_determinism": false,
|
| 153 |
+
"torchdynamo": null,
|
| 154 |
+
"ray_scope": "last",
|
| 155 |
+
"ddp_timeout": 18000000,
|
| 156 |
+
"torch_compile": false,
|
| 157 |
+
"torch_compile_backend": null,
|
| 158 |
+
"torch_compile_mode": null,
|
| 159 |
+
"include_tokens_per_second": false,
|
| 160 |
+
"include_num_input_tokens_seen": false,
|
| 161 |
+
"neftune_noise_alpha": null,
|
| 162 |
+
"optim_target_modules": null,
|
| 163 |
+
"batch_eval_metrics": false,
|
| 164 |
+
"eval_on_start": false,
|
| 165 |
+
"use_liger_kernel": true,
|
| 166 |
+
"liger_kernel_config": null,
|
| 167 |
+
"eval_use_gather_object": false,
|
| 168 |
+
"average_tokens_across_devices": true,
|
| 169 |
+
"sortish_sampler": false,
|
| 170 |
+
"predict_with_generate": false,
|
| 171 |
+
"generation_max_length": null,
|
| 172 |
+
"generation_num_beams": null,
|
| 173 |
+
"generation_config": null,
|
| 174 |
+
"tuner_backend": "peft",
|
| 175 |
+
"vit_gradient_checkpointing": null,
|
| 176 |
+
"router_aux_loss_coef": 0.0,
|
| 177 |
+
"enable_dft_loss": false,
|
| 178 |
+
"enable_channel_loss": false,
|
| 179 |
+
"check_model": true,
|
| 180 |
+
"acc_strategy": "token",
|
| 181 |
+
"train_dataloader_shuffle": true,
|
| 182 |
+
"max_epochs": null,
|
| 183 |
+
"aligner_lr": 1e-05,
|
| 184 |
+
"vit_lr": 1e-05,
|
| 185 |
+
"use_logits_to_keep": null,
|
| 186 |
+
"ds3_gather_for_generation": true,
|
| 187 |
+
"resume_only_model": false,
|
| 188 |
+
"optimizer": null,
|
| 189 |
+
"loss_type": null,
|
| 190 |
+
"metric": null,
|
| 191 |
+
"eval_use_evalscope": false,
|
| 192 |
+
"eval_dataset": [],
|
| 193 |
+
"eval_dataset_args": null,
|
| 194 |
+
"eval_limit": null,
|
| 195 |
+
"eval_generation_config": null,
|
| 196 |
+
"extra_eval_args": null,
|
| 197 |
+
"use_flash_ckpt": false,
|
| 198 |
+
"use_ray": false,
|
| 199 |
+
"ray_exp_name": null,
|
| 200 |
+
"device_groups": null,
|
| 201 |
+
"model": "/workspace/weixian/ckpt/Qwen3-VL-8B-Instruct",
|
| 202 |
+
"model_type": "qwen3_vl",
|
| 203 |
+
"model_revision": null,
|
| 204 |
+
"task_type": "causal_lm",
|
| 205 |
+
"torch_dtype": "bfloat16",
|
| 206 |
+
"attn_impl": "flash_attn",
|
| 207 |
+
"new_special_tokens": [],
|
| 208 |
+
"num_labels": null,
|
| 209 |
+
"problem_type": null,
|
| 210 |
+
"rope_scaling": null,
|
| 211 |
+
"device_map": null,
|
| 212 |
+
"max_memory": {},
|
| 213 |
+
"max_model_len": null,
|
| 214 |
+
"local_repo_path": null,
|
| 215 |
+
"init_strategy": null,
|
| 216 |
+
"template": "qwen3_vl",
|
| 217 |
+
"system": null,
|
| 218 |
+
"max_length": 32768,
|
| 219 |
+
"truncation_strategy": "delete",
|
| 220 |
+
"max_pixels": null,
|
| 221 |
+
"agent_template": null,
|
| 222 |
+
"norm_bbox": null,
|
| 223 |
+
"use_chat_template": true,
|
| 224 |
+
"padding_side": "right",
|
| 225 |
+
"padding_free": true,
|
| 226 |
+
"loss_scale": "default",
|
| 227 |
+
"sequence_parallel_size": 1,
|
| 228 |
+
"template_backend": "swift",
|
| 229 |
+
"response_prefix": null,
|
| 230 |
+
"enable_thinking": null,
|
| 231 |
+
"add_non_thinking_prefix": true,
|
| 232 |
+
"dataset": [
|
| 233 |
+
"/workspace/data/processed/AgentNet/agentnet_win_mac_18k.swift.v1.jsonl",
|
| 234 |
+
"/workspace/data/processed/AgentNet/agentnet_ubuntu_5k.swift.v1.jsonl"
|
| 235 |
+
],
|
| 236 |
+
"val_dataset": [],
|
| 237 |
+
"cached_dataset": [],
|
| 238 |
+
"cached_val_dataset": [],
|
| 239 |
+
"split_dataset_ratio": 0.0,
|
| 240 |
+
"dataset_num_proc": 8,
|
| 241 |
+
"load_from_cache_file": false,
|
| 242 |
+
"dataset_shuffle": true,
|
| 243 |
+
"val_dataset_shuffle": false,
|
| 244 |
+
"streaming": false,
|
| 245 |
+
"interleave_prob": null,
|
| 246 |
+
"stopping_strategy": "first_exhausted",
|
| 247 |
+
"shuffle_buffer_size": 1000,
|
| 248 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 249 |
+
"columns": {},
|
| 250 |
+
"strict": false,
|
| 251 |
+
"model_name": null,
|
| 252 |
+
"model_author": null,
|
| 253 |
+
"custom_dataset_info": [],
|
| 254 |
+
"quant_method": null,
|
| 255 |
+
"quant_bits": null,
|
| 256 |
+
"hqq_axis": null,
|
| 257 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 258 |
+
"bnb_4bit_quant_type": "nf4",
|
| 259 |
+
"bnb_4bit_use_double_quant": true,
|
| 260 |
+
"bnb_4bit_quant_storage": null,
|
| 261 |
+
"max_new_tokens": 64,
|
| 262 |
+
"temperature": 0.0,
|
| 263 |
+
"top_k": null,
|
| 264 |
+
"top_p": null,
|
| 265 |
+
"repetition_penalty": null,
|
| 266 |
+
"num_beams": 1,
|
| 267 |
+
"stream": false,
|
| 268 |
+
"stop_words": [],
|
| 269 |
+
"logprobs": false,
|
| 270 |
+
"top_logprobs": null,
|
| 271 |
+
"structured_outputs_regex": null,
|
| 272 |
+
"ckpt_dir": null,
|
| 273 |
+
"lora_modules": [],
|
| 274 |
+
"train_type": "full",
|
| 275 |
+
"adapters": [],
|
| 276 |
+
"external_plugins": [],
|
| 277 |
+
"model_kwargs": {},
|
| 278 |
+
"load_args": false,
|
| 279 |
+
"load_data_args": false,
|
| 280 |
+
"packing": false,
|
| 281 |
+
"packing_length": null,
|
| 282 |
+
"packing_num_proc": 1,
|
| 283 |
+
"lazy_tokenize": true,
|
| 284 |
+
"custom_register_path": [],
|
| 285 |
+
"use_hf": false,
|
| 286 |
+
"ignore_args_error": false,
|
| 287 |
+
"use_swift_lora": false,
|
| 288 |
+
"freeze_parameters": [],
|
| 289 |
+
"freeze_parameters_regex": null,
|
| 290 |
+
"freeze_parameters_ratio": 0.0,
|
| 291 |
+
"trainable_parameters": [
|
| 292 |
+
"model.visual.merger",
|
| 293 |
+
"model.visual.deepstack_merger_list"
|
| 294 |
+
],
|
| 295 |
+
"trainable_parameters_regex": null,
|
| 296 |
+
"freeze_llm": false,
|
| 297 |
+
"freeze_vit": false,
|
| 298 |
+
"freeze_aligner": false,
|
| 299 |
+
"target_modules": [
|
| 300 |
+
"all-linear"
|
| 301 |
+
],
|
| 302 |
+
"target_regex": null,
|
| 303 |
+
"target_parameters": null,
|
| 304 |
+
"modules_to_save": [],
|
| 305 |
+
"lora_rank": 8,
|
| 306 |
+
"lora_alpha": 32,
|
| 307 |
+
"lora_dropout": 0.05,
|
| 308 |
+
"lora_bias": "none",
|
| 309 |
+
"lora_dtype": null,
|
| 310 |
+
"lorap_lr_ratio": null,
|
| 311 |
+
"use_rslora": false,
|
| 312 |
+
"use_dora": false,
|
| 313 |
+
"lora_ga_batch_size": 2,
|
| 314 |
+
"lora_ga_iters": 2,
|
| 315 |
+
"lora_ga_max_length": 1024,
|
| 316 |
+
"lora_ga_direction": "ArB2r",
|
| 317 |
+
"lora_ga_scale": "stable",
|
| 318 |
+
"lora_ga_stable_gamma": 16,
|
| 319 |
+
"init_weights": true,
|
| 320 |
+
"fourier_n_frequency": 2000,
|
| 321 |
+
"fourier_scaling": 300.0,
|
| 322 |
+
"boft_block_size": 4,
|
| 323 |
+
"boft_block_num": 0,
|
| 324 |
+
"boft_n_butterfly_factor": 1,
|
| 325 |
+
"boft_dropout": 0.0,
|
| 326 |
+
"vera_rank": 256,
|
| 327 |
+
"vera_projection_prng_key": 0,
|
| 328 |
+
"vera_dropout": 0.0,
|
| 329 |
+
"vera_d_initial": 0.1,
|
| 330 |
+
"adapter_act": "gelu",
|
| 331 |
+
"adapter_length": 128,
|
| 332 |
+
"use_galore": false,
|
| 333 |
+
"galore_target_modules": null,
|
| 334 |
+
"galore_rank": 128,
|
| 335 |
+
"galore_update_proj_gap": 50,
|
| 336 |
+
"galore_scale": 1.0,
|
| 337 |
+
"galore_proj_type": "std",
|
| 338 |
+
"galore_optim_per_parameter": false,
|
| 339 |
+
"galore_with_embedding": false,
|
| 340 |
+
"galore_quantization": false,
|
| 341 |
+
"galore_proj_quant": false,
|
| 342 |
+
"galore_proj_bits": 4,
|
| 343 |
+
"galore_proj_group_size": 256,
|
| 344 |
+
"galore_cos_threshold": 0.4,
|
| 345 |
+
"galore_gamma_proj": 2,
|
| 346 |
+
"galore_queue_size": 5,
|
| 347 |
+
"adalora_target_r": 8,
|
| 348 |
+
"adalora_init_r": 12,
|
| 349 |
+
"adalora_tinit": 0,
|
| 350 |
+
"adalora_tfinal": 0,
|
| 351 |
+
"adalora_deltaT": 1,
|
| 352 |
+
"adalora_beta1": 0.85,
|
| 353 |
+
"adalora_beta2": 0.85,
|
| 354 |
+
"adalora_orth_reg_weight": 0.5,
|
| 355 |
+
"llamapro_num_new_blocks": 4,
|
| 356 |
+
"llamapro_num_groups": null,
|
| 357 |
+
"lisa_activated_layers": 0,
|
| 358 |
+
"lisa_step_interval": 20,
|
| 359 |
+
"reft_layer_key": null,
|
| 360 |
+
"reft_layers": null,
|
| 361 |
+
"reft_rank": 4,
|
| 362 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 363 |
+
"reft_args": null,
|
| 364 |
+
"swanlab_token": null,
|
| 365 |
+
"swanlab_project": "ms-swift",
|
| 366 |
+
"swanlab_workspace": null,
|
| 367 |
+
"swanlab_exp_name": null,
|
| 368 |
+
"swanlab_notification_method": null,
|
| 369 |
+
"swanlab_webhook_url": null,
|
| 370 |
+
"swanlab_secret": null,
|
| 371 |
+
"swanlab_mode": "cloud",
|
| 372 |
+
"add_version": true,
|
| 373 |
+
"create_checkpoint_symlink": false,
|
| 374 |
+
"zero_hpz_partition_size": null,
|
| 375 |
+
"deepspeed_autotp_size": null,
|
| 376 |
+
"early_stop_interval": null,
|
| 377 |
+
"rank": 0,
|
| 378 |
+
"global_world_size": 16,
|
| 379 |
+
"local_world_size": 4,
|
| 380 |
+
"model_suffix": "Qwen3-VL-8B-Instruct",
|
| 381 |
+
"model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/workspace/weixian/ckpt/Qwen3-VL-8B-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)",
|
| 382 |
+
"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)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=<function get_model_tokenizer_qwen3_vl at 0xfffc20b36160>, 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=[]), architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])",
|
| 383 |
+
"model_dir": "/workspace/weixian/ckpt/Qwen3-VL-8B-Instruct",
|
| 384 |
+
"_val_dataset_exists": [],
|
| 385 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 386 |
+
"evaluation_strategy": "steps",
|
| 387 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/weixian/workplace/ms_swift_project/ms-swift/output/qwen3vl_8b_sft_full_agentnet_dist/v3-20260118-132920', 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=8, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=3, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/weixian/workplace/ms_swift_project/ms-swift/output/qwen3vl_8b_sft_full_agentnet_dist/v3-20260118-132920/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=200, save_total_limit=2, 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=200.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/workspace/weixian/workplace/ms_swift_project/ms-swift/output/qwen3vl_8b_sft_full_agentnet_dist/v3-20260118-132920', 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': 1, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, 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=True, 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=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=1e-05, vit_lr=1e-05, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
|
| 388 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_size": 4096,
|
| 8 |
+
"image_token_id": 151655,
|
| 9 |
+
"model_type": "qwen3_vl",
|
| 10 |
+
"pad_token_id": 151643,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bos_token_id": 151643,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"eos_token_id": 151645,
|
| 17 |
+
"head_dim": 128,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 4096,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 12288,
|
| 22 |
+
"max_position_embeddings": 262144,
|
| 23 |
+
"model_type": "qwen3_vl_text",
|
| 24 |
+
"num_attention_heads": 32,
|
| 25 |
+
"num_hidden_layers": 36,
|
| 26 |
+
"num_key_value_heads": 8,
|
| 27 |
+
"pad_token_id": 151643,
|
| 28 |
+
"rms_norm_eps": 1e-06,
|
| 29 |
+
"rope_scaling": {
|
| 30 |
+
"mrope_interleaved": true,
|
| 31 |
+
"mrope_section": [
|
| 32 |
+
24,
|
| 33 |
+
20,
|
| 34 |
+
20
|
| 35 |
+
],
|
| 36 |
+
"rope_type": "default"
|
| 37 |
+
},
|
| 38 |
+
"rope_theta": 5000000,
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 151936
|
| 41 |
+
},
|
| 42 |
+
"tie_word_embeddings": false,
|
| 43 |
+
"transformers_version": "4.57.3",
|
| 44 |
+
"video_token_id": 151656,
|
| 45 |
+
"vision_config": {
|
| 46 |
+
"deepstack_visual_indexes": [
|
| 47 |
+
8,
|
| 48 |
+
16,
|
| 49 |
+
24
|
| 50 |
+
],
|
| 51 |
+
"depth": 27,
|
| 52 |
+
"dtype": "bfloat16",
|
| 53 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 54 |
+
"hidden_size": 1152,
|
| 55 |
+
"in_channels": 3,
|
| 56 |
+
"initializer_range": 0.02,
|
| 57 |
+
"intermediate_size": 4304,
|
| 58 |
+
"model_type": "qwen3_vl",
|
| 59 |
+
"num_heads": 16,
|
| 60 |
+
"num_position_embeddings": 2304,
|
| 61 |
+
"out_hidden_size": 4096,
|
| 62 |
+
"pad_token_id": 151643,
|
| 63 |
+
"patch_size": 16,
|
| 64 |
+
"spatial_merge_size": 2,
|
| 65 |
+
"temporal_patch_size": 2
|
| 66 |
+
},
|
| 67 |
+
"vision_end_token_id": 151653,
|
| 68 |
+
"vision_start_token_id": 151652
|
| 69 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.3"
|
| 13 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step2196
|
qwen3vl_8b_agentnetv1_fullsft_gb200/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3vl_8b_agentnetv1_fullsft_gb200/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c5126fa717c00c356e35a32c1db42a079af3805557fa1a8e4bb5686863d9d64
|
| 3 |
+
size 4998056552
|
qwen3vl_8b_agentnetv1_fullsft_gb200/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d32d38b2efa518aa561523e8cd3e272817b9c86ee66020e1061e1d15a940af3f
|
| 3 |
+
size 4915962464
|
qwen3vl_8b_agentnetv1_fullsft_gb200/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f7f584474093d5ea8003ccbfed8d1ad7bc7ecc4f51083a4c0139f9114bfbf3f
|
| 3 |
+
size 4915962496
|
qwen3vl_8b_agentnetv1_fullsft_gb200/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a01f61fc3265c162770716c611d27873fe8719527c47956b15480209b1c15a49
|
| 3 |
+
size 2704357976
|
qwen3vl_8b_agentnetv1_fullsft_gb200/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,758 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8767123696,
|
| 4 |
+
"total_size": 17534247392
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 409 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 413 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
|
| 417 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 421 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 425 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
|
| 429 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 730 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 731 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 732 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 733 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 734 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
|
| 735 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
|
| 736 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 737 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 738 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 739 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 740 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
|
| 741 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
|
| 742 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 743 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 744 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 745 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 746 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
|
| 747 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
|
| 748 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 749 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 750 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 751 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 752 |
+
"model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
|
| 753 |
+
"model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
|
| 754 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
|
| 755 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
|
| 756 |
+
"model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
|
| 757 |
+
}
|
| 758 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/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 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
qwen3vl_8b_agentnetv1_fullsft_gb200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"processor_class": "Qwen3VLProcessor",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/trainer_state.json
ADDED
|
@@ -0,0 +1,3114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 200.0,
|
| 7 |
+
"global_step": 2196,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0009110233829334953,
|
| 14 |
+
"grad_norm": 17.559492111206055,
|
| 15 |
+
"learning_rate": 9.090909090909091e-08,
|
| 16 |
+
"loss": 1.2423300743103027,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.004555116914667477,
|
| 21 |
+
"grad_norm": 25.693878173828125,
|
| 22 |
+
"learning_rate": 4.5454545454545457e-07,
|
| 23 |
+
"loss": 1.2533537149429321,
|
| 24 |
+
"step": 5
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.009110233829334954,
|
| 28 |
+
"grad_norm": 13.45212459564209,
|
| 29 |
+
"learning_rate": 9.090909090909091e-07,
|
| 30 |
+
"loss": 1.1839993476867676,
|
| 31 |
+
"step": 10
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.013665350744002429,
|
| 35 |
+
"grad_norm": 4.8773298263549805,
|
| 36 |
+
"learning_rate": 1.3636363636363636e-06,
|
| 37 |
+
"loss": 0.942754077911377,
|
| 38 |
+
"step": 15
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.018220467658669907,
|
| 42 |
+
"grad_norm": 6.213735103607178,
|
| 43 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 44 |
+
"loss": 0.8017440795898437,
|
| 45 |
+
"step": 20
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.022775584573337383,
|
| 49 |
+
"grad_norm": 4.074641704559326,
|
| 50 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 51 |
+
"loss": 0.7369897842407227,
|
| 52 |
+
"step": 25
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.027330701488004858,
|
| 56 |
+
"grad_norm": 6.384721755981445,
|
| 57 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 58 |
+
"loss": 0.6929409027099609,
|
| 59 |
+
"step": 30
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.031885818402672336,
|
| 63 |
+
"grad_norm": 4.765110492706299,
|
| 64 |
+
"learning_rate": 3.181818181818182e-06,
|
| 65 |
+
"loss": 0.6680615425109864,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.036440935317339815,
|
| 70 |
+
"grad_norm": 5.50184440612793,
|
| 71 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 72 |
+
"loss": 0.6583371639251709,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.040996052232007286,
|
| 77 |
+
"grad_norm": 7.0187482833862305,
|
| 78 |
+
"learning_rate": 4.0909090909090915e-06,
|
| 79 |
+
"loss": 0.6485747337341309,
|
| 80 |
+
"step": 45
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.045551169146674765,
|
| 84 |
+
"grad_norm": 4.4937214851379395,
|
| 85 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 86 |
+
"loss": 0.6382402420043946,
|
| 87 |
+
"step": 50
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.050106286061342244,
|
| 91 |
+
"grad_norm": 6.880841255187988,
|
| 92 |
+
"learning_rate": 5e-06,
|
| 93 |
+
"loss": 0.6306743144989013,
|
| 94 |
+
"step": 55
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.054661402976009715,
|
| 98 |
+
"grad_norm": 4.950007915496826,
|
| 99 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 100 |
+
"loss": 0.6264668464660644,
|
| 101 |
+
"step": 60
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.059216519890677194,
|
| 105 |
+
"grad_norm": 13.052614212036133,
|
| 106 |
+
"learning_rate": 5.90909090909091e-06,
|
| 107 |
+
"loss": 0.6193904876708984,
|
| 108 |
+
"step": 65
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.06377163680534467,
|
| 112 |
+
"grad_norm": 16.394208908081055,
|
| 113 |
+
"learning_rate": 6.363636363636364e-06,
|
| 114 |
+
"loss": 0.6106473922729492,
|
| 115 |
+
"step": 70
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06832675372001215,
|
| 119 |
+
"grad_norm": 5.312663555145264,
|
| 120 |
+
"learning_rate": 6.818181818181818e-06,
|
| 121 |
+
"loss": 0.6170936584472656,
|
| 122 |
+
"step": 75
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.07288187063467963,
|
| 126 |
+
"grad_norm": 10.03520679473877,
|
| 127 |
+
"learning_rate": 7.272727272727273e-06,
|
| 128 |
+
"loss": 0.5990739345550538,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0774369875493471,
|
| 133 |
+
"grad_norm": 9.031923294067383,
|
| 134 |
+
"learning_rate": 7.727272727272727e-06,
|
| 135 |
+
"loss": 0.6070697784423829,
|
| 136 |
+
"step": 85
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.08199210446401457,
|
| 140 |
+
"grad_norm": 7.924659729003906,
|
| 141 |
+
"learning_rate": 8.181818181818183e-06,
|
| 142 |
+
"loss": 0.5944653511047363,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.08654722137868205,
|
| 147 |
+
"grad_norm": 9.117231369018555,
|
| 148 |
+
"learning_rate": 8.636363636363637e-06,
|
| 149 |
+
"loss": 0.5960843086242675,
|
| 150 |
+
"step": 95
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.09110233829334953,
|
| 154 |
+
"grad_norm": 34.10580825805664,
|
| 155 |
+
"learning_rate": 9.090909090909091e-06,
|
| 156 |
+
"loss": 0.5919606208801269,
|
| 157 |
+
"step": 100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.09565745520801701,
|
| 161 |
+
"grad_norm": 9.232901573181152,
|
| 162 |
+
"learning_rate": 9.545454545454547e-06,
|
| 163 |
+
"loss": 0.5938567638397216,
|
| 164 |
+
"step": 105
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.10021257212268449,
|
| 168 |
+
"grad_norm": 14.370579719543457,
|
| 169 |
+
"learning_rate": 1e-05,
|
| 170 |
+
"loss": 0.5873185157775879,
|
| 171 |
+
"step": 110
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.10476768903735195,
|
| 175 |
+
"grad_norm": 7.017094612121582,
|
| 176 |
+
"learning_rate": 9.999858241502208e-06,
|
| 177 |
+
"loss": 0.5942224025726318,
|
| 178 |
+
"step": 115
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.10932280595201943,
|
| 182 |
+
"grad_norm": 5.101506233215332,
|
| 183 |
+
"learning_rate": 9.999432974047014e-06,
|
| 184 |
+
"loss": 0.5906107902526856,
|
| 185 |
+
"step": 120
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.11387792286668691,
|
| 189 |
+
"grad_norm": 7.324491024017334,
|
| 190 |
+
"learning_rate": 9.99872422174853e-06,
|
| 191 |
+
"loss": 0.591792631149292,
|
| 192 |
+
"step": 125
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.11843303978135439,
|
| 196 |
+
"grad_norm": 8.754467964172363,
|
| 197 |
+
"learning_rate": 9.99773202479542e-06,
|
| 198 |
+
"loss": 0.5856371879577636,
|
| 199 |
+
"step": 130
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.12298815669602187,
|
| 203 |
+
"grad_norm": 5.618054389953613,
|
| 204 |
+
"learning_rate": 9.996456439448628e-06,
|
| 205 |
+
"loss": 0.5825910091400146,
|
| 206 |
+
"step": 135
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.12754327361068934,
|
| 210 |
+
"grad_norm": 5.029508590698242,
|
| 211 |
+
"learning_rate": 9.994897538038176e-06,
|
| 212 |
+
"loss": 0.580083179473877,
|
| 213 |
+
"step": 140
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.13209839052535682,
|
| 217 |
+
"grad_norm": 5.695907115936279,
|
| 218 |
+
"learning_rate": 9.99305540895907e-06,
|
| 219 |
+
"loss": 0.5816529750823974,
|
| 220 |
+
"step": 145
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.1366535074400243,
|
| 224 |
+
"grad_norm": 4.026976585388184,
|
| 225 |
+
"learning_rate": 9.990930156666294e-06,
|
| 226 |
+
"loss": 0.5851906299591064,
|
| 227 |
+
"step": 150
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.14120862435469178,
|
| 231 |
+
"grad_norm": 3.444056987762451,
|
| 232 |
+
"learning_rate": 9.988521901668878e-06,
|
| 233 |
+
"loss": 0.5782979011535645,
|
| 234 |
+
"step": 155
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.14576374126935926,
|
| 238 |
+
"grad_norm": 6.146154880523682,
|
| 239 |
+
"learning_rate": 9.985830780523062e-06,
|
| 240 |
+
"loss": 0.5769307613372803,
|
| 241 |
+
"step": 160
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.1503188581840267,
|
| 245 |
+
"grad_norm": 4.238720893859863,
|
| 246 |
+
"learning_rate": 9.982856945824567e-06,
|
| 247 |
+
"loss": 0.5825564861297607,
|
| 248 |
+
"step": 165
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.1548739750986942,
|
| 252 |
+
"grad_norm": 3.784989595413208,
|
| 253 |
+
"learning_rate": 9.979600566199926e-06,
|
| 254 |
+
"loss": 0.5774458885192871,
|
| 255 |
+
"step": 170
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.15942909201336167,
|
| 259 |
+
"grad_norm": 5.971307277679443,
|
| 260 |
+
"learning_rate": 9.976061826296933e-06,
|
| 261 |
+
"loss": 0.5697900295257569,
|
| 262 |
+
"step": 175
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.16398420892802915,
|
| 266 |
+
"grad_norm": 2.7221076488494873,
|
| 267 |
+
"learning_rate": 9.972240926774167e-06,
|
| 268 |
+
"loss": 0.574206018447876,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.16853932584269662,
|
| 273 |
+
"grad_norm": 3.3567593097686768,
|
| 274 |
+
"learning_rate": 9.968138084289625e-06,
|
| 275 |
+
"loss": 0.5786737918853759,
|
| 276 |
+
"step": 185
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.1730944427573641,
|
| 280 |
+
"grad_norm": 7.935139179229736,
|
| 281 |
+
"learning_rate": 9.963753531488416e-06,
|
| 282 |
+
"loss": 0.5722726345062256,
|
| 283 |
+
"step": 190
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.17764955967203158,
|
| 287 |
+
"grad_norm": 3.7399966716766357,
|
| 288 |
+
"learning_rate": 9.959087516989589e-06,
|
| 289 |
+
"loss": 0.5803302764892578,
|
| 290 |
+
"step": 195
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.18220467658669906,
|
| 294 |
+
"grad_norm": 3.1717324256896973,
|
| 295 |
+
"learning_rate": 9.954140305372026e-06,
|
| 296 |
+
"loss": 0.5747191429138183,
|
| 297 |
+
"step": 200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.18675979350136654,
|
| 301 |
+
"grad_norm": 4.224859714508057,
|
| 302 |
+
"learning_rate": 9.948912177159445e-06,
|
| 303 |
+
"loss": 0.5714075088500976,
|
| 304 |
+
"step": 205
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.19131491041603402,
|
| 308 |
+
"grad_norm": 2.968369722366333,
|
| 309 |
+
"learning_rate": 9.943403428804482e-06,
|
| 310 |
+
"loss": 0.5736642837524414,
|
| 311 |
+
"step": 210
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.1958700273307015,
|
| 315 |
+
"grad_norm": 4.710346698760986,
|
| 316 |
+
"learning_rate": 9.937614372671896e-06,
|
| 317 |
+
"loss": 0.568629264831543,
|
| 318 |
+
"step": 215
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.20042514424536897,
|
| 322 |
+
"grad_norm": 2.995421886444092,
|
| 323 |
+
"learning_rate": 9.93154533702085e-06,
|
| 324 |
+
"loss": 0.5707715034484864,
|
| 325 |
+
"step": 220
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.20498026116003645,
|
| 329 |
+
"grad_norm": 2.9990322589874268,
|
| 330 |
+
"learning_rate": 9.925196665986289e-06,
|
| 331 |
+
"loss": 0.5626624584197998,
|
| 332 |
+
"step": 225
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.2095353780747039,
|
| 336 |
+
"grad_norm": 3.209749221801758,
|
| 337 |
+
"learning_rate": 9.918568719559443e-06,
|
| 338 |
+
"loss": 0.5639097213745117,
|
| 339 |
+
"step": 230
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.21409049498937138,
|
| 343 |
+
"grad_norm": 3.255554437637329,
|
| 344 |
+
"learning_rate": 9.911661873567407e-06,
|
| 345 |
+
"loss": 0.5606301307678223,
|
| 346 |
+
"step": 235
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.21864561190403886,
|
| 350 |
+
"grad_norm": 3.2023773193359375,
|
| 351 |
+
"learning_rate": 9.904476519651822e-06,
|
| 352 |
+
"loss": 0.5634839534759521,
|
| 353 |
+
"step": 240
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.22320072881870634,
|
| 357 |
+
"grad_norm": 4.02494478225708,
|
| 358 |
+
"learning_rate": 9.89701306524668e-06,
|
| 359 |
+
"loss": 0.5576680183410645,
|
| 360 |
+
"step": 245
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.22775584573337382,
|
| 364 |
+
"grad_norm": 2.883610725402832,
|
| 365 |
+
"learning_rate": 9.889271933555214e-06,
|
| 366 |
+
"loss": 0.5645258903503418,
|
| 367 |
+
"step": 250
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2323109626480413,
|
| 371 |
+
"grad_norm": 4.670317649841309,
|
| 372 |
+
"learning_rate": 9.881253563525905e-06,
|
| 373 |
+
"loss": 0.56104736328125,
|
| 374 |
+
"step": 255
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.23686607956270878,
|
| 378 |
+
"grad_norm": 4.898850917816162,
|
| 379 |
+
"learning_rate": 9.872958409827588e-06,
|
| 380 |
+
"loss": 0.5592937469482422,
|
| 381 |
+
"step": 260
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.24142119647737625,
|
| 385 |
+
"grad_norm": 3.393101692199707,
|
| 386 |
+
"learning_rate": 9.864386942823678e-06,
|
| 387 |
+
"loss": 0.5690124034881592,
|
| 388 |
+
"step": 265
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.24597631339204373,
|
| 392 |
+
"grad_norm": 3.7247464656829834,
|
| 393 |
+
"learning_rate": 9.855539648545485e-06,
|
| 394 |
+
"loss": 0.560127067565918,
|
| 395 |
+
"step": 270
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.2505314303067112,
|
| 399 |
+
"grad_norm": 3.4709503650665283,
|
| 400 |
+
"learning_rate": 9.846417028664668e-06,
|
| 401 |
+
"loss": 0.5557423114776612,
|
| 402 |
+
"step": 275
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2550865472213787,
|
| 406 |
+
"grad_norm": 2.8535945415496826,
|
| 407 |
+
"learning_rate": 9.837019600464783e-06,
|
| 408 |
+
"loss": 0.5636860847473144,
|
| 409 |
+
"step": 280
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.25964166413604617,
|
| 413 |
+
"grad_norm": 3.1316518783569336,
|
| 414 |
+
"learning_rate": 9.827347896811954e-06,
|
| 415 |
+
"loss": 0.5631931304931641,
|
| 416 |
+
"step": 285
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.26419678105071365,
|
| 420 |
+
"grad_norm": 2.6706693172454834,
|
| 421 |
+
"learning_rate": 9.817402466124652e-06,
|
| 422 |
+
"loss": 0.5706257820129395,
|
| 423 |
+
"step": 290
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.2687518979653811,
|
| 427 |
+
"grad_norm": 2.1610724925994873,
|
| 428 |
+
"learning_rate": 9.807183872342603e-06,
|
| 429 |
+
"loss": 0.5647665023803711,
|
| 430 |
+
"step": 295
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.2733070148800486,
|
| 434 |
+
"grad_norm": 3.649000644683838,
|
| 435 |
+
"learning_rate": 9.796692694894809e-06,
|
| 436 |
+
"loss": 0.56468505859375,
|
| 437 |
+
"step": 300
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.2778621317947161,
|
| 441 |
+
"grad_norm": 4.748224258422852,
|
| 442 |
+
"learning_rate": 9.785929528666691e-06,
|
| 443 |
+
"loss": 0.561229133605957,
|
| 444 |
+
"step": 305
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.28241724870938356,
|
| 448 |
+
"grad_norm": 3.2732272148132324,
|
| 449 |
+
"learning_rate": 9.77489498396636e-06,
|
| 450 |
+
"loss": 0.5538298606872558,
|
| 451 |
+
"step": 310
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.28697236562405104,
|
| 455 |
+
"grad_norm": 2.783526659011841,
|
| 456 |
+
"learning_rate": 9.76358968649001e-06,
|
| 457 |
+
"loss": 0.5541868686676026,
|
| 458 |
+
"step": 315
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.2915274825387185,
|
| 462 |
+
"grad_norm": 3.165250062942505,
|
| 463 |
+
"learning_rate": 9.752014277286433e-06,
|
| 464 |
+
"loss": 0.5500054359436035,
|
| 465 |
+
"step": 320
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.296082599453386,
|
| 469 |
+
"grad_norm": 3.244180679321289,
|
| 470 |
+
"learning_rate": 9.740169412720677e-06,
|
| 471 |
+
"loss": 0.5560133934020997,
|
| 472 |
+
"step": 325
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.3006377163680534,
|
| 476 |
+
"grad_norm": 3.5502259731292725,
|
| 477 |
+
"learning_rate": 9.728055764436828e-06,
|
| 478 |
+
"loss": 0.5537430763244628,
|
| 479 |
+
"step": 330
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.3051928332827209,
|
| 483 |
+
"grad_norm": 2.9355859756469727,
|
| 484 |
+
"learning_rate": 9.715674019319917e-06,
|
| 485 |
+
"loss": 0.550521993637085,
|
| 486 |
+
"step": 335
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.3097479501973884,
|
| 490 |
+
"grad_norm": 3.7240347862243652,
|
| 491 |
+
"learning_rate": 9.703024879456978e-06,
|
| 492 |
+
"loss": 0.556462287902832,
|
| 493 |
+
"step": 340
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.31430306711205586,
|
| 497 |
+
"grad_norm": 2.31040096282959,
|
| 498 |
+
"learning_rate": 9.690109062097241e-06,
|
| 499 |
+
"loss": 0.5485388278961182,
|
| 500 |
+
"step": 345
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.31885818402672333,
|
| 504 |
+
"grad_norm": 2.3651797771453857,
|
| 505 |
+
"learning_rate": 9.67692729961145e-06,
|
| 506 |
+
"loss": 0.5521252632141114,
|
| 507 |
+
"step": 350
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3234133009413908,
|
| 511 |
+
"grad_norm": 3.3303847312927246,
|
| 512 |
+
"learning_rate": 9.663480339450344e-06,
|
| 513 |
+
"loss": 0.552528190612793,
|
| 514 |
+
"step": 355
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.3279684178560583,
|
| 518 |
+
"grad_norm": 2.7311720848083496,
|
| 519 |
+
"learning_rate": 9.649768944102272e-06,
|
| 520 |
+
"loss": 0.5484151363372802,
|
| 521 |
+
"step": 360
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.33252353477072577,
|
| 525 |
+
"grad_norm": 2.9131832122802734,
|
| 526 |
+
"learning_rate": 9.635793891049959e-06,
|
| 527 |
+
"loss": 0.5590497493743897,
|
| 528 |
+
"step": 365
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.33707865168539325,
|
| 532 |
+
"grad_norm": 5.8473687171936035,
|
| 533 |
+
"learning_rate": 9.621555972726416e-06,
|
| 534 |
+
"loss": 0.5552995204925537,
|
| 535 |
+
"step": 370
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.3416337686000607,
|
| 539 |
+
"grad_norm": 1.9673869609832764,
|
| 540 |
+
"learning_rate": 9.607055996470003e-06,
|
| 541 |
+
"loss": 0.5548224449157715,
|
| 542 |
+
"step": 375
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.3461888855147282,
|
| 546 |
+
"grad_norm": 2.8362224102020264,
|
| 547 |
+
"learning_rate": 9.592294784478668e-06,
|
| 548 |
+
"loss": 0.5551294326782227,
|
| 549 |
+
"step": 380
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3507440024293957,
|
| 553 |
+
"grad_norm": 5.5295257568359375,
|
| 554 |
+
"learning_rate": 9.577273173763302e-06,
|
| 555 |
+
"loss": 0.5563198089599609,
|
| 556 |
+
"step": 385
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.35529911934406316,
|
| 560 |
+
"grad_norm": 1.7222570180892944,
|
| 561 |
+
"learning_rate": 9.561992016100293e-06,
|
| 562 |
+
"loss": 0.5539894580841065,
|
| 563 |
+
"step": 390
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.35985423625873064,
|
| 567 |
+
"grad_norm": 1.6861451864242554,
|
| 568 |
+
"learning_rate": 9.546452177983223e-06,
|
| 569 |
+
"loss": 0.5516669273376464,
|
| 570 |
+
"step": 395
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3644093531733981,
|
| 574 |
+
"grad_norm": 2.1530921459198,
|
| 575 |
+
"learning_rate": 9.530654540573736e-06,
|
| 576 |
+
"loss": 0.5513467788696289,
|
| 577 |
+
"step": 400
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.3689644700880656,
|
| 581 |
+
"grad_norm": 4.1498517990112305,
|
| 582 |
+
"learning_rate": 9.514599999651572e-06,
|
| 583 |
+
"loss": 0.5544273853302002,
|
| 584 |
+
"step": 405
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.3735195870027331,
|
| 588 |
+
"grad_norm": 3.0634090900421143,
|
| 589 |
+
"learning_rate": 9.498289465563769e-06,
|
| 590 |
+
"loss": 0.5443705558776856,
|
| 591 |
+
"step": 410
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.37807470391740056,
|
| 595 |
+
"grad_norm": 2.7513556480407715,
|
| 596 |
+
"learning_rate": 9.481723863173054e-06,
|
| 597 |
+
"loss": 0.5389851093292236,
|
| 598 |
+
"step": 415
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.38262982083206803,
|
| 602 |
+
"grad_norm": 32.76044845581055,
|
| 603 |
+
"learning_rate": 9.46490413180539e-06,
|
| 604 |
+
"loss": 0.5442268371582031,
|
| 605 |
+
"step": 420
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.3871849377467355,
|
| 609 |
+
"grad_norm": 3.125256299972534,
|
| 610 |
+
"learning_rate": 9.44783122519672e-06,
|
| 611 |
+
"loss": 0.5439101219177246,
|
| 612 |
+
"step": 425
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.391740054661403,
|
| 616 |
+
"grad_norm": 2.8991496562957764,
|
| 617 |
+
"learning_rate": 9.430506111438877e-06,
|
| 618 |
+
"loss": 0.5462981224060058,
|
| 619 |
+
"step": 430
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.39629517157607047,
|
| 623 |
+
"grad_norm": 13.466605186462402,
|
| 624 |
+
"learning_rate": 9.412929772924707e-06,
|
| 625 |
+
"loss": 0.5357834815979003,
|
| 626 |
+
"step": 435
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.40085028849073795,
|
| 630 |
+
"grad_norm": 15.509262084960938,
|
| 631 |
+
"learning_rate": 9.395103206292342e-06,
|
| 632 |
+
"loss": 0.5422843933105469,
|
| 633 |
+
"step": 440
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.40540540540540543,
|
| 637 |
+
"grad_norm": 5.389743328094482,
|
| 638 |
+
"learning_rate": 9.377027422368707e-06,
|
| 639 |
+
"loss": 0.5465549468994141,
|
| 640 |
+
"step": 445
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.4099605223200729,
|
| 644 |
+
"grad_norm": 4.2232842445373535,
|
| 645 |
+
"learning_rate": 9.358703446112194e-06,
|
| 646 |
+
"loss": 0.5402978420257568,
|
| 647 |
+
"step": 450
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.4145156392347404,
|
| 651 |
+
"grad_norm": 4.203605651855469,
|
| 652 |
+
"learning_rate": 9.34013231655454e-06,
|
| 653 |
+
"loss": 0.5347804069519043,
|
| 654 |
+
"step": 455
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.4190707561494078,
|
| 658 |
+
"grad_norm": 8.337684631347656,
|
| 659 |
+
"learning_rate": 9.321315086741916e-06,
|
| 660 |
+
"loss": 0.5400158882141113,
|
| 661 |
+
"step": 460
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4236258730640753,
|
| 665 |
+
"grad_norm": 3.43294095993042,
|
| 666 |
+
"learning_rate": 9.302252823675217e-06,
|
| 667 |
+
"loss": 0.5414864540100097,
|
| 668 |
+
"step": 465
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.42818098997874277,
|
| 672 |
+
"grad_norm": 3.3577237129211426,
|
| 673 |
+
"learning_rate": 9.282946608249553e-06,
|
| 674 |
+
"loss": 0.5411586284637451,
|
| 675 |
+
"step": 470
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.43273610689341024,
|
| 679 |
+
"grad_norm": 2.9969730377197266,
|
| 680 |
+
"learning_rate": 9.263397535192959e-06,
|
| 681 |
+
"loss": 0.543182373046875,
|
| 682 |
+
"step": 475
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.4372912238080777,
|
| 686 |
+
"grad_norm": 3.317013740539551,
|
| 687 |
+
"learning_rate": 9.24360671300433e-06,
|
| 688 |
+
"loss": 0.54539794921875,
|
| 689 |
+
"step": 480
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.4418463407227452,
|
| 693 |
+
"grad_norm": 4.378854751586914,
|
| 694 |
+
"learning_rate": 9.223575263890556e-06,
|
| 695 |
+
"loss": 0.5474021434783936,
|
| 696 |
+
"step": 485
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.4464014576374127,
|
| 700 |
+
"grad_norm": 2.789015769958496,
|
| 701 |
+
"learning_rate": 9.20330432370289e-06,
|
| 702 |
+
"loss": 0.5468668460845947,
|
| 703 |
+
"step": 490
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.45095657455208016,
|
| 707 |
+
"grad_norm": 3.1256697177886963,
|
| 708 |
+
"learning_rate": 9.182795041872543e-06,
|
| 709 |
+
"loss": 0.5451174736022949,
|
| 710 |
+
"step": 495
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.45551169146674764,
|
| 714 |
+
"grad_norm": 19.11293601989746,
|
| 715 |
+
"learning_rate": 9.162048581345511e-06,
|
| 716 |
+
"loss": 0.5430747032165527,
|
| 717 |
+
"step": 500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.4600668083814151,
|
| 721 |
+
"grad_norm": 2.99991774559021,
|
| 722 |
+
"learning_rate": 9.141066118516625e-06,
|
| 723 |
+
"loss": 0.5492184638977051,
|
| 724 |
+
"step": 505
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.4646219252960826,
|
| 728 |
+
"grad_norm": 3.0613291263580322,
|
| 729 |
+
"learning_rate": 9.119848843162844e-06,
|
| 730 |
+
"loss": 0.5410381317138672,
|
| 731 |
+
"step": 510
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.4691770422107501,
|
| 735 |
+
"grad_norm": 3.8927035331726074,
|
| 736 |
+
"learning_rate": 9.098397958375807e-06,
|
| 737 |
+
"loss": 0.5446810722351074,
|
| 738 |
+
"step": 515
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.47373215912541755,
|
| 742 |
+
"grad_norm": 2.757336139678955,
|
| 743 |
+
"learning_rate": 9.076714680493594e-06,
|
| 744 |
+
"loss": 0.5469783306121826,
|
| 745 |
+
"step": 520
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.47828727604008503,
|
| 749 |
+
"grad_norm": 2.6528310775756836,
|
| 750 |
+
"learning_rate": 9.054800239031763e-06,
|
| 751 |
+
"loss": 0.5482687473297119,
|
| 752 |
+
"step": 525
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.4828423929547525,
|
| 756 |
+
"grad_norm": 2.5695135593414307,
|
| 757 |
+
"learning_rate": 9.032655876613636e-06,
|
| 758 |
+
"loss": 0.542782211303711,
|
| 759 |
+
"step": 530
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.48739750986942,
|
| 763 |
+
"grad_norm": 4.648599624633789,
|
| 764 |
+
"learning_rate": 9.010282848899833e-06,
|
| 765 |
+
"loss": 0.5455782890319825,
|
| 766 |
+
"step": 535
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.49195262678408747,
|
| 770 |
+
"grad_norm": 3.9627435207366943,
|
| 771 |
+
"learning_rate": 8.987682424517075e-06,
|
| 772 |
+
"loss": 0.5418254375457764,
|
| 773 |
+
"step": 540
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.49650774369875494,
|
| 777 |
+
"grad_norm": 7.180903434753418,
|
| 778 |
+
"learning_rate": 8.964855884986244e-06,
|
| 779 |
+
"loss": 0.5390671253204345,
|
| 780 |
+
"step": 545
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.5010628606134224,
|
| 784 |
+
"grad_norm": 2.5528030395507812,
|
| 785 |
+
"learning_rate": 8.941804524649721e-06,
|
| 786 |
+
"loss": 0.546663761138916,
|
| 787 |
+
"step": 550
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.5056179775280899,
|
| 791 |
+
"grad_norm": 3.286468029022217,
|
| 792 |
+
"learning_rate": 8.918529650597996e-06,
|
| 793 |
+
"loss": 0.5427966117858887,
|
| 794 |
+
"step": 555
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.5101730944427574,
|
| 798 |
+
"grad_norm": 3.3196663856506348,
|
| 799 |
+
"learning_rate": 8.895032582595537e-06,
|
| 800 |
+
"loss": 0.536742877960205,
|
| 801 |
+
"step": 560
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.5147282113574249,
|
| 805 |
+
"grad_norm": 2.7130608558654785,
|
| 806 |
+
"learning_rate": 8.871314653005972e-06,
|
| 807 |
+
"loss": 0.5361935138702393,
|
| 808 |
+
"step": 565
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.5192833282720923,
|
| 812 |
+
"grad_norm": 2.7196788787841797,
|
| 813 |
+
"learning_rate": 8.847377206716527e-06,
|
| 814 |
+
"loss": 0.5388089179992676,
|
| 815 |
+
"step": 570
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.5238384451867598,
|
| 819 |
+
"grad_norm": 3.419187307357788,
|
| 820 |
+
"learning_rate": 8.823221601061774e-06,
|
| 821 |
+
"loss": 0.5345405578613281,
|
| 822 |
+
"step": 575
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.5283935621014273,
|
| 826 |
+
"grad_norm": 2.363970994949341,
|
| 827 |
+
"learning_rate": 8.79884920574666e-06,
|
| 828 |
+
"loss": 0.536346435546875,
|
| 829 |
+
"step": 580
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.5329486790160948,
|
| 833 |
+
"grad_norm": 3.2918245792388916,
|
| 834 |
+
"learning_rate": 8.774261402768844e-06,
|
| 835 |
+
"loss": 0.5398552894592286,
|
| 836 |
+
"step": 585
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.5375037959307623,
|
| 840 |
+
"grad_norm": 5.764172077178955,
|
| 841 |
+
"learning_rate": 8.749459586340334e-06,
|
| 842 |
+
"loss": 0.5393971920013427,
|
| 843 |
+
"step": 590
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.5420589128454297,
|
| 847 |
+
"grad_norm": 2.588685989379883,
|
| 848 |
+
"learning_rate": 8.724445162808423e-06,
|
| 849 |
+
"loss": 0.5340259075164795,
|
| 850 |
+
"step": 595
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5466140297600972,
|
| 854 |
+
"grad_norm": 3.468891143798828,
|
| 855 |
+
"learning_rate": 8.699219550575954e-06,
|
| 856 |
+
"loss": 0.5304669857025146,
|
| 857 |
+
"step": 600
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5511691466747647,
|
| 861 |
+
"grad_norm": 4.80936336517334,
|
| 862 |
+
"learning_rate": 8.673784180020884e-06,
|
| 863 |
+
"loss": 0.529237174987793,
|
| 864 |
+
"step": 605
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5557242635894322,
|
| 868 |
+
"grad_norm": 4.984926223754883,
|
| 869 |
+
"learning_rate": 8.648140493415183e-06,
|
| 870 |
+
"loss": 0.5376770496368408,
|
| 871 |
+
"step": 610
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5602793805040996,
|
| 875 |
+
"grad_norm": 2.2710659503936768,
|
| 876 |
+
"learning_rate": 8.622289944843047e-06,
|
| 877 |
+
"loss": 0.5376224994659424,
|
| 878 |
+
"step": 615
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.5648344974187671,
|
| 882 |
+
"grad_norm": 2.312422513961792,
|
| 883 |
+
"learning_rate": 8.596234000118446e-06,
|
| 884 |
+
"loss": 0.532253646850586,
|
| 885 |
+
"step": 620
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.5693896143334346,
|
| 889 |
+
"grad_norm": 2.549513816833496,
|
| 890 |
+
"learning_rate": 8.569974136702019e-06,
|
| 891 |
+
"loss": 0.5293230533599853,
|
| 892 |
+
"step": 625
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.5739447312481021,
|
| 896 |
+
"grad_norm": 2.343762159347534,
|
| 897 |
+
"learning_rate": 8.543511843617277e-06,
|
| 898 |
+
"loss": 0.5317315101623535,
|
| 899 |
+
"step": 630
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.5784998481627696,
|
| 903 |
+
"grad_norm": 2.1737287044525146,
|
| 904 |
+
"learning_rate": 8.516848621366188e-06,
|
| 905 |
+
"loss": 0.5308964729309082,
|
| 906 |
+
"step": 635
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.583054965077437,
|
| 910 |
+
"grad_norm": 2.0589590072631836,
|
| 911 |
+
"learning_rate": 8.489985981844086e-06,
|
| 912 |
+
"loss": 0.5311801910400391,
|
| 913 |
+
"step": 640
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.5876100819921045,
|
| 917 |
+
"grad_norm": 4.078348159790039,
|
| 918 |
+
"learning_rate": 8.46292544825394e-06,
|
| 919 |
+
"loss": 0.5306229591369629,
|
| 920 |
+
"step": 645
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.592165198906772,
|
| 924 |
+
"grad_norm": 2.8249433040618896,
|
| 925 |
+
"learning_rate": 8.435668555019987e-06,
|
| 926 |
+
"loss": 0.5330135345458984,
|
| 927 |
+
"step": 650
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5967203158214394,
|
| 931 |
+
"grad_norm": 3.677963972091675,
|
| 932 |
+
"learning_rate": 8.408216847700725e-06,
|
| 933 |
+
"loss": 0.5320111274719238,
|
| 934 |
+
"step": 655
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.6012754327361068,
|
| 938 |
+
"grad_norm": 2.4316532611846924,
|
| 939 |
+
"learning_rate": 8.380571882901265e-06,
|
| 940 |
+
"loss": 0.5290947914123535,
|
| 941 |
+
"step": 660
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.6058305496507743,
|
| 945 |
+
"grad_norm": 3.219510555267334,
|
| 946 |
+
"learning_rate": 8.352735228185085e-06,
|
| 947 |
+
"loss": 0.529725456237793,
|
| 948 |
+
"step": 665
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.6103856665654418,
|
| 952 |
+
"grad_norm": 3.452469825744629,
|
| 953 |
+
"learning_rate": 8.324708461985124e-06,
|
| 954 |
+
"loss": 0.5379016399383545,
|
| 955 |
+
"step": 670
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.6149407834801093,
|
| 959 |
+
"grad_norm": 2.2365944385528564,
|
| 960 |
+
"learning_rate": 8.296493173514294e-06,
|
| 961 |
+
"loss": 0.5272422790527344,
|
| 962 |
+
"step": 675
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.6194959003947768,
|
| 966 |
+
"grad_norm": 4.5478339195251465,
|
| 967 |
+
"learning_rate": 8.268090962675358e-06,
|
| 968 |
+
"loss": 0.5276835441589356,
|
| 969 |
+
"step": 680
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.6240510173094442,
|
| 973 |
+
"grad_norm": 2.9637320041656494,
|
| 974 |
+
"learning_rate": 8.239503439970212e-06,
|
| 975 |
+
"loss": 0.5249893188476562,
|
| 976 |
+
"step": 685
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.6286061342241117,
|
| 980 |
+
"grad_norm": 3.1997034549713135,
|
| 981 |
+
"learning_rate": 8.210732226408566e-06,
|
| 982 |
+
"loss": 0.5261757850646973,
|
| 983 |
+
"step": 690
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.6331612511387792,
|
| 987 |
+
"grad_norm": 4.2955756187438965,
|
| 988 |
+
"learning_rate": 8.181778953416025e-06,
|
| 989 |
+
"loss": 0.525751781463623,
|
| 990 |
+
"step": 695
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.6377163680534467,
|
| 994 |
+
"grad_norm": 2.975689172744751,
|
| 995 |
+
"learning_rate": 8.152645262741586e-06,
|
| 996 |
+
"loss": 0.5300833702087402,
|
| 997 |
+
"step": 700
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.6422714849681141,
|
| 1001 |
+
"grad_norm": 2.491178512573242,
|
| 1002 |
+
"learning_rate": 8.123332806364537e-06,
|
| 1003 |
+
"loss": 0.5283273696899414,
|
| 1004 |
+
"step": 705
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.6468266018827816,
|
| 1008 |
+
"grad_norm": 5.0057549476623535,
|
| 1009 |
+
"learning_rate": 8.09384324640079e-06,
|
| 1010 |
+
"loss": 0.5246441841125489,
|
| 1011 |
+
"step": 710
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.6513817187974491,
|
| 1015 |
+
"grad_norm": 3.7425742149353027,
|
| 1016 |
+
"learning_rate": 8.064178255008637e-06,
|
| 1017 |
+
"loss": 0.5283780097961426,
|
| 1018 |
+
"step": 715
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.6559368357121166,
|
| 1022 |
+
"grad_norm": 5.3434906005859375,
|
| 1023 |
+
"learning_rate": 8.03433951429392e-06,
|
| 1024 |
+
"loss": 0.5267109394073486,
|
| 1025 |
+
"step": 720
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.6604919526267841,
|
| 1029 |
+
"grad_norm": 5.699710369110107,
|
| 1030 |
+
"learning_rate": 8.004328716214667e-06,
|
| 1031 |
+
"loss": 0.5268173217773438,
|
| 1032 |
+
"step": 725
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.6650470695414515,
|
| 1036 |
+
"grad_norm": 3.340369701385498,
|
| 1037 |
+
"learning_rate": 7.97414756248514e-06,
|
| 1038 |
+
"loss": 0.5249145030975342,
|
| 1039 |
+
"step": 730
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.669602186456119,
|
| 1043 |
+
"grad_norm": 2.61981201171875,
|
| 1044 |
+
"learning_rate": 7.943797764479338e-06,
|
| 1045 |
+
"loss": 0.5252110481262207,
|
| 1046 |
+
"step": 735
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.6741573033707865,
|
| 1050 |
+
"grad_norm": 1.742195963859558,
|
| 1051 |
+
"learning_rate": 7.913281043133978e-06,
|
| 1052 |
+
"loss": 0.5280135154724122,
|
| 1053 |
+
"step": 740
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.678712420285454,
|
| 1057 |
+
"grad_norm": 2.602257251739502,
|
| 1058 |
+
"learning_rate": 7.882599128850888e-06,
|
| 1059 |
+
"loss": 0.525156307220459,
|
| 1060 |
+
"step": 745
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.6832675372001215,
|
| 1064 |
+
"grad_norm": 2.2966225147247314,
|
| 1065 |
+
"learning_rate": 7.851753761398895e-06,
|
| 1066 |
+
"loss": 0.5265485286712647,
|
| 1067 |
+
"step": 750
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.6878226541147889,
|
| 1071 |
+
"grad_norm": 2.6013224124908447,
|
| 1072 |
+
"learning_rate": 7.820746689815188e-06,
|
| 1073 |
+
"loss": 0.5309466361999512,
|
| 1074 |
+
"step": 755
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.6923777710294564,
|
| 1078 |
+
"grad_norm": 6.142124176025391,
|
| 1079 |
+
"learning_rate": 7.789579672306117e-06,
|
| 1080 |
+
"loss": 0.5194272041320801,
|
| 1081 |
+
"step": 760
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.6969328879441239,
|
| 1085 |
+
"grad_norm": 2.3743906021118164,
|
| 1086 |
+
"learning_rate": 7.758254476147515e-06,
|
| 1087 |
+
"loss": 0.528320026397705,
|
| 1088 |
+
"step": 765
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.7014880048587914,
|
| 1092 |
+
"grad_norm": 1.3435266017913818,
|
| 1093 |
+
"learning_rate": 7.726772877584486e-06,
|
| 1094 |
+
"loss": 0.5290194988250733,
|
| 1095 |
+
"step": 770
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.7060431217734588,
|
| 1099 |
+
"grad_norm": 1.8624411821365356,
|
| 1100 |
+
"learning_rate": 7.695136661730677e-06,
|
| 1101 |
+
"loss": 0.5187951564788819,
|
| 1102 |
+
"step": 775
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.7105982386881263,
|
| 1106 |
+
"grad_norm": 1.8843101263046265,
|
| 1107 |
+
"learning_rate": 7.66334762246706e-06,
|
| 1108 |
+
"loss": 0.5258677005767822,
|
| 1109 |
+
"step": 780
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.7151533556027938,
|
| 1113 |
+
"grad_norm": 2.0883312225341797,
|
| 1114 |
+
"learning_rate": 7.631407562340215e-06,
|
| 1115 |
+
"loss": 0.5251790046691894,
|
| 1116 |
+
"step": 785
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.7197084725174613,
|
| 1120 |
+
"grad_norm": 2.7113304138183594,
|
| 1121 |
+
"learning_rate": 7.599318292460125e-06,
|
| 1122 |
+
"loss": 0.525829267501831,
|
| 1123 |
+
"step": 790
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.7242635894321288,
|
| 1127 |
+
"grad_norm": 2.360489845275879,
|
| 1128 |
+
"learning_rate": 7.567081632397462e-06,
|
| 1129 |
+
"loss": 0.517587947845459,
|
| 1130 |
+
"step": 795
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.7288187063467962,
|
| 1134 |
+
"grad_norm": 1.8589805364608765,
|
| 1135 |
+
"learning_rate": 7.534699410080429e-06,
|
| 1136 |
+
"loss": 0.5235529899597168,
|
| 1137 |
+
"step": 800
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.7333738232614637,
|
| 1141 |
+
"grad_norm": 2.6437175273895264,
|
| 1142 |
+
"learning_rate": 7.502173461691104e-06,
|
| 1143 |
+
"loss": 0.5219250202178956,
|
| 1144 |
+
"step": 805
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.7379289401761312,
|
| 1148 |
+
"grad_norm": 14.303297996520996,
|
| 1149 |
+
"learning_rate": 7.469505631561318e-06,
|
| 1150 |
+
"loss": 0.5251981258392334,
|
| 1151 |
+
"step": 810
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.7424840570907987,
|
| 1155 |
+
"grad_norm": 3.5786635875701904,
|
| 1156 |
+
"learning_rate": 7.436697772068083e-06,
|
| 1157 |
+
"loss": 0.522415018081665,
|
| 1158 |
+
"step": 815
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.7470391740054662,
|
| 1162 |
+
"grad_norm": 3.2803893089294434,
|
| 1163 |
+
"learning_rate": 7.40375174352855e-06,
|
| 1164 |
+
"loss": 0.519214677810669,
|
| 1165 |
+
"step": 820
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.7515942909201336,
|
| 1169 |
+
"grad_norm": 3.6064188480377197,
|
| 1170 |
+
"learning_rate": 7.370669414094522e-06,
|
| 1171 |
+
"loss": 0.5226556777954101,
|
| 1172 |
+
"step": 825
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.7561494078348011,
|
| 1176 |
+
"grad_norm": 3.3592140674591064,
|
| 1177 |
+
"learning_rate": 7.3374526596465334e-06,
|
| 1178 |
+
"loss": 0.5165884494781494,
|
| 1179 |
+
"step": 830
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.7607045247494686,
|
| 1183 |
+
"grad_norm": 5.043455600738525,
|
| 1184 |
+
"learning_rate": 7.3041033636874635e-06,
|
| 1185 |
+
"loss": 0.514227819442749,
|
| 1186 |
+
"step": 835
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.7652596416641361,
|
| 1190 |
+
"grad_norm": 4.375437259674072,
|
| 1191 |
+
"learning_rate": 7.2706234172357556e-06,
|
| 1192 |
+
"loss": 0.5168005943298339,
|
| 1193 |
+
"step": 840
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.7698147585788035,
|
| 1197 |
+
"grad_norm": 5.3485541343688965,
|
| 1198 |
+
"learning_rate": 7.2370147187181736e-06,
|
| 1199 |
+
"loss": 0.517771053314209,
|
| 1200 |
+
"step": 845
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.774369875493471,
|
| 1204 |
+
"grad_norm": 3.3749423027038574,
|
| 1205 |
+
"learning_rate": 7.203279173862164e-06,
|
| 1206 |
+
"loss": 0.517666244506836,
|
| 1207 |
+
"step": 850
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.7789249924081385,
|
| 1211 |
+
"grad_norm": 5.747758388519287,
|
| 1212 |
+
"learning_rate": 7.169418695587791e-06,
|
| 1213 |
+
"loss": 0.5237475395202636,
|
| 1214 |
+
"step": 855
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.783480109322806,
|
| 1218 |
+
"grad_norm": 2.7103781700134277,
|
| 1219 |
+
"learning_rate": 7.135435203899269e-06,
|
| 1220 |
+
"loss": 0.5126797676086425,
|
| 1221 |
+
"step": 860
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.7880352262374735,
|
| 1225 |
+
"grad_norm": 2.7993369102478027,
|
| 1226 |
+
"learning_rate": 7.10133062577609e-06,
|
| 1227 |
+
"loss": 0.5152403354644776,
|
| 1228 |
+
"step": 865
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.7925903431521409,
|
| 1232 |
+
"grad_norm": 2.4125592708587646,
|
| 1233 |
+
"learning_rate": 7.067106895063761e-06,
|
| 1234 |
+
"loss": 0.5169252395629883,
|
| 1235 |
+
"step": 870
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.7971454600668084,
|
| 1239 |
+
"grad_norm": 2.7944040298461914,
|
| 1240 |
+
"learning_rate": 7.032765952364142e-06,
|
| 1241 |
+
"loss": 0.5117922782897949,
|
| 1242 |
+
"step": 875
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.8017005769814759,
|
| 1246 |
+
"grad_norm": 5.195308685302734,
|
| 1247 |
+
"learning_rate": 6.998309744925411e-06,
|
| 1248 |
+
"loss": 0.516599178314209,
|
| 1249 |
+
"step": 880
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.8062556938961434,
|
| 1253 |
+
"grad_norm": 3.4537782669067383,
|
| 1254 |
+
"learning_rate": 6.9637402265316546e-06,
|
| 1255 |
+
"loss": 0.5194319725036621,
|
| 1256 |
+
"step": 885
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.8108108108108109,
|
| 1260 |
+
"grad_norm": 3.8817193508148193,
|
| 1261 |
+
"learning_rate": 6.9290593573920705e-06,
|
| 1262 |
+
"loss": 0.5188677787780762,
|
| 1263 |
+
"step": 890
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.8153659277254783,
|
| 1267 |
+
"grad_norm": 4.101870059967041,
|
| 1268 |
+
"learning_rate": 6.894269104029821e-06,
|
| 1269 |
+
"loss": 0.5178657531738281,
|
| 1270 |
+
"step": 895
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.8199210446401458,
|
| 1274 |
+
"grad_norm": 2.8397769927978516,
|
| 1275 |
+
"learning_rate": 6.85937143917053e-06,
|
| 1276 |
+
"loss": 0.5115979194641114,
|
| 1277 |
+
"step": 900
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.8244761615548133,
|
| 1281 |
+
"grad_norm": 5.299158573150635,
|
| 1282 |
+
"learning_rate": 6.824368341630417e-06,
|
| 1283 |
+
"loss": 0.5131528854370118,
|
| 1284 |
+
"step": 905
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.8290312784694808,
|
| 1288 |
+
"grad_norm": 5.552743434906006,
|
| 1289 |
+
"learning_rate": 6.7892617962040895e-06,
|
| 1290 |
+
"loss": 0.5187356472015381,
|
| 1291 |
+
"step": 910
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.8335863953841481,
|
| 1295 |
+
"grad_norm": 3.70224666595459,
|
| 1296 |
+
"learning_rate": 6.754053793552005e-06,
|
| 1297 |
+
"loss": 0.5094799995422363,
|
| 1298 |
+
"step": 915
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.8381415122988156,
|
| 1302 |
+
"grad_norm": 6.331211566925049,
|
| 1303 |
+
"learning_rate": 6.718746330087592e-06,
|
| 1304 |
+
"loss": 0.5205501556396485,
|
| 1305 |
+
"step": 920
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.8426966292134831,
|
| 1309 |
+
"grad_norm": 5.271122455596924,
|
| 1310 |
+
"learning_rate": 6.683341407864041e-06,
|
| 1311 |
+
"loss": 0.513223934173584,
|
| 1312 |
+
"step": 925
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.8472517461281506,
|
| 1316 |
+
"grad_norm": 5.599212646484375,
|
| 1317 |
+
"learning_rate": 6.64784103446079e-06,
|
| 1318 |
+
"loss": 0.5125411987304688,
|
| 1319 |
+
"step": 930
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.851806863042818,
|
| 1323 |
+
"grad_norm": 4.971273422241211,
|
| 1324 |
+
"learning_rate": 6.61224722286968e-06,
|
| 1325 |
+
"loss": 0.512675142288208,
|
| 1326 |
+
"step": 935
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.8563619799574855,
|
| 1330 |
+
"grad_norm": 19.01078987121582,
|
| 1331 |
+
"learning_rate": 6.576561991380813e-06,
|
| 1332 |
+
"loss": 0.5141432762145997,
|
| 1333 |
+
"step": 940
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.860917096872153,
|
| 1337 |
+
"grad_norm": 3.6665432453155518,
|
| 1338 |
+
"learning_rate": 6.540787363468117e-06,
|
| 1339 |
+
"loss": 0.5151987075805664,
|
| 1340 |
+
"step": 945
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.8654722137868205,
|
| 1344 |
+
"grad_norm": 11.245736122131348,
|
| 1345 |
+
"learning_rate": 6.504925367674595e-06,
|
| 1346 |
+
"loss": 0.5133233070373535,
|
| 1347 |
+
"step": 950
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.870027330701488,
|
| 1351 |
+
"grad_norm": 11.291261672973633,
|
| 1352 |
+
"learning_rate": 6.468978037497306e-06,
|
| 1353 |
+
"loss": 0.5141026496887207,
|
| 1354 |
+
"step": 955
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.8745824476161554,
|
| 1358 |
+
"grad_norm": 4.820343971252441,
|
| 1359 |
+
"learning_rate": 6.432947411272061e-06,
|
| 1360 |
+
"loss": 0.5152844429016114,
|
| 1361 |
+
"step": 960
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.8791375645308229,
|
| 1365 |
+
"grad_norm": 5.331433296203613,
|
| 1366 |
+
"learning_rate": 6.396835532057842e-06,
|
| 1367 |
+
"loss": 0.5164792537689209,
|
| 1368 |
+
"step": 965
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.8836926814454904,
|
| 1372 |
+
"grad_norm": 4.908500671386719,
|
| 1373 |
+
"learning_rate": 6.360644447520946e-06,
|
| 1374 |
+
"loss": 0.5097151756286621,
|
| 1375 |
+
"step": 970
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.8882477983601579,
|
| 1379 |
+
"grad_norm": 4.368012428283691,
|
| 1380 |
+
"learning_rate": 6.3243762098188856e-06,
|
| 1381 |
+
"loss": 0.513163948059082,
|
| 1382 |
+
"step": 975
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.8928029152748254,
|
| 1386 |
+
"grad_norm": 4.894745826721191,
|
| 1387 |
+
"learning_rate": 6.288032875484017e-06,
|
| 1388 |
+
"loss": 0.511021900177002,
|
| 1389 |
+
"step": 980
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.8973580321894928,
|
| 1393 |
+
"grad_norm": 4.908347129821777,
|
| 1394 |
+
"learning_rate": 6.251616505306933e-06,
|
| 1395 |
+
"loss": 0.5213098049163818,
|
| 1396 |
+
"step": 985
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.9019131491041603,
|
| 1400 |
+
"grad_norm": 7.74894905090332,
|
| 1401 |
+
"learning_rate": 6.215129164219609e-06,
|
| 1402 |
+
"loss": 0.5086194515228272,
|
| 1403 |
+
"step": 990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.9064682660188278,
|
| 1407 |
+
"grad_norm": 3.935709238052368,
|
| 1408 |
+
"learning_rate": 6.178572921178303e-06,
|
| 1409 |
+
"loss": 0.5145331859588623,
|
| 1410 |
+
"step": 995
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.9110233829334953,
|
| 1414 |
+
"grad_norm": 3.560208320617676,
|
| 1415 |
+
"learning_rate": 6.141949849046259e-06,
|
| 1416 |
+
"loss": 0.5098010540008545,
|
| 1417 |
+
"step": 1000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.9155784998481628,
|
| 1421 |
+
"grad_norm": 4.882101058959961,
|
| 1422 |
+
"learning_rate": 6.1052620244761554e-06,
|
| 1423 |
+
"loss": 0.504856538772583,
|
| 1424 |
+
"step": 1005
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.9201336167628302,
|
| 1428 |
+
"grad_norm": 3.6763391494750977,
|
| 1429 |
+
"learning_rate": 6.068511527792345e-06,
|
| 1430 |
+
"loss": 0.507168960571289,
|
| 1431 |
+
"step": 1010
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.9246887336774977,
|
| 1435 |
+
"grad_norm": 4.296417713165283,
|
| 1436 |
+
"learning_rate": 6.031700442872913e-06,
|
| 1437 |
+
"loss": 0.5144553184509277,
|
| 1438 |
+
"step": 1015
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.9292438505921652,
|
| 1442 |
+
"grad_norm": 4.9462995529174805,
|
| 1443 |
+
"learning_rate": 5.9948308570315e-06,
|
| 1444 |
+
"loss": 0.5141644954681397,
|
| 1445 |
+
"step": 1020
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.9337989675068327,
|
| 1449 |
+
"grad_norm": 5.650740623474121,
|
| 1450 |
+
"learning_rate": 5.957904860898945e-06,
|
| 1451 |
+
"loss": 0.5157180309295655,
|
| 1452 |
+
"step": 1025
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.9383540844215001,
|
| 1456 |
+
"grad_norm": 2.4969570636749268,
|
| 1457 |
+
"learning_rate": 5.920924548304745e-06,
|
| 1458 |
+
"loss": 0.5117298126220703,
|
| 1459 |
+
"step": 1030
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.9429092013361676,
|
| 1463 |
+
"grad_norm": 4.6982035636901855,
|
| 1464 |
+
"learning_rate": 5.883892016158327e-06,
|
| 1465 |
+
"loss": 0.5127541542053222,
|
| 1466 |
+
"step": 1035
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.9474643182508351,
|
| 1470 |
+
"grad_norm": 2.9895901679992676,
|
| 1471 |
+
"learning_rate": 5.84680936433014e-06,
|
| 1472 |
+
"loss": 0.5123614311218262,
|
| 1473 |
+
"step": 1040
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.9520194351655026,
|
| 1477 |
+
"grad_norm": 6.107245445251465,
|
| 1478 |
+
"learning_rate": 5.809678695532589e-06,
|
| 1479 |
+
"loss": 0.5081177711486816,
|
| 1480 |
+
"step": 1045
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.9565745520801701,
|
| 1484 |
+
"grad_norm": 2.194211006164551,
|
| 1485 |
+
"learning_rate": 5.77250211520081e-06,
|
| 1486 |
+
"loss": 0.5117453575134278,
|
| 1487 |
+
"step": 1050
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.9611296689948375,
|
| 1491 |
+
"grad_norm": 2.4194414615631104,
|
| 1492 |
+
"learning_rate": 5.735281731373271e-06,
|
| 1493 |
+
"loss": 0.5113804340362549,
|
| 1494 |
+
"step": 1055
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.965684785909505,
|
| 1498 |
+
"grad_norm": 3.714282989501953,
|
| 1499 |
+
"learning_rate": 5.698019654572257e-06,
|
| 1500 |
+
"loss": 0.5118466377258301,
|
| 1501 |
+
"step": 1060
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.9702399028241725,
|
| 1505 |
+
"grad_norm": 2.9563801288604736,
|
| 1506 |
+
"learning_rate": 5.660717997684176e-06,
|
| 1507 |
+
"loss": 0.505659818649292,
|
| 1508 |
+
"step": 1065
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.97479501973884,
|
| 1512 |
+
"grad_norm": 4.059390544891357,
|
| 1513 |
+
"learning_rate": 5.623378875839769e-06,
|
| 1514 |
+
"loss": 0.5077022075653076,
|
| 1515 |
+
"step": 1070
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.9793501366535075,
|
| 1519 |
+
"grad_norm": 8.951316833496094,
|
| 1520 |
+
"learning_rate": 5.586004406294163e-06,
|
| 1521 |
+
"loss": 0.5117686271667481,
|
| 1522 |
+
"step": 1075
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.9839052535681749,
|
| 1526 |
+
"grad_norm": 4.351177215576172,
|
| 1527 |
+
"learning_rate": 5.5485967083068225e-06,
|
| 1528 |
+
"loss": 0.5095709800720215,
|
| 1529 |
+
"step": 1080
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.9884603704828424,
|
| 1533 |
+
"grad_norm": 3.330329179763794,
|
| 1534 |
+
"learning_rate": 5.511157903021376e-06,
|
| 1535 |
+
"loss": 0.5055630207061768,
|
| 1536 |
+
"step": 1085
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.9930154873975099,
|
| 1540 |
+
"grad_norm": 163.6642303466797,
|
| 1541 |
+
"learning_rate": 5.473690113345343e-06,
|
| 1542 |
+
"loss": 0.5033265113830566,
|
| 1543 |
+
"step": 1090
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.9975706043121774,
|
| 1547 |
+
"grad_norm": 2.309828996658325,
|
| 1548 |
+
"learning_rate": 5.436195463829753e-06,
|
| 1549 |
+
"loss": 0.5086031913757324,
|
| 1550 |
+
"step": 1095
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.001822046765867,
|
| 1554 |
+
"grad_norm": 2.9510703086853027,
|
| 1555 |
+
"learning_rate": 5.398676080548686e-06,
|
| 1556 |
+
"loss": 0.4903547286987305,
|
| 1557 |
+
"step": 1100
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.0063771636805345,
|
| 1561 |
+
"grad_norm": 3.1362714767456055,
|
| 1562 |
+
"learning_rate": 5.361134090978706e-06,
|
| 1563 |
+
"loss": 0.4678180694580078,
|
| 1564 |
+
"step": 1105
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.010932280595202,
|
| 1568 |
+
"grad_norm": 7.239353656768799,
|
| 1569 |
+
"learning_rate": 5.323571623878228e-06,
|
| 1570 |
+
"loss": 0.46486196517944334,
|
| 1571 |
+
"step": 1110
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.0154873975098695,
|
| 1575 |
+
"grad_norm": 7.031823635101318,
|
| 1576 |
+
"learning_rate": 5.285990809166819e-06,
|
| 1577 |
+
"loss": 0.4655783653259277,
|
| 1578 |
+
"step": 1115
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.0200425144245369,
|
| 1582 |
+
"grad_norm": 2.0763893127441406,
|
| 1583 |
+
"learning_rate": 5.248393777804414e-06,
|
| 1584 |
+
"loss": 0.4618667125701904,
|
| 1585 |
+
"step": 1120
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.0245976313392045,
|
| 1589 |
+
"grad_norm": 2.655989646911621,
|
| 1590 |
+
"learning_rate": 5.210782661670486e-06,
|
| 1591 |
+
"loss": 0.46256508827209475,
|
| 1592 |
+
"step": 1125
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.0291527482538718,
|
| 1596 |
+
"grad_norm": 3.223036527633667,
|
| 1597 |
+
"learning_rate": 5.173159593443169e-06,
|
| 1598 |
+
"loss": 0.46468095779418944,
|
| 1599 |
+
"step": 1130
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.0337078651685394,
|
| 1603 |
+
"grad_norm": 1.3973139524459839,
|
| 1604 |
+
"learning_rate": 5.135526706478312e-06,
|
| 1605 |
+
"loss": 0.4647266387939453,
|
| 1606 |
+
"step": 1135
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.0382629820832068,
|
| 1610 |
+
"grad_norm": 1.9962592124938965,
|
| 1611 |
+
"learning_rate": 5.0978861346885275e-06,
|
| 1612 |
+
"loss": 0.46361312866210935,
|
| 1613 |
+
"step": 1140
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.0428180989978744,
|
| 1617 |
+
"grad_norm": 1.7671151161193848,
|
| 1618 |
+
"learning_rate": 5.060240012422179e-06,
|
| 1619 |
+
"loss": 0.46665177345275877,
|
| 1620 |
+
"step": 1145
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.0473732159125417,
|
| 1624 |
+
"grad_norm": 2.207895517349243,
|
| 1625 |
+
"learning_rate": 5.022590474342364e-06,
|
| 1626 |
+
"loss": 0.4580831527709961,
|
| 1627 |
+
"step": 1150
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.0519283328272093,
|
| 1631 |
+
"grad_norm": 2.9564528465270996,
|
| 1632 |
+
"learning_rate": 4.984939655305865e-06,
|
| 1633 |
+
"loss": 0.46053476333618165,
|
| 1634 |
+
"step": 1155
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.0564834497418767,
|
| 1638 |
+
"grad_norm": 1.5557438135147095,
|
| 1639 |
+
"learning_rate": 4.947289690242103e-06,
|
| 1640 |
+
"loss": 0.4670742988586426,
|
| 1641 |
+
"step": 1160
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.0610385666565443,
|
| 1645 |
+
"grad_norm": 1.9870871305465698,
|
| 1646 |
+
"learning_rate": 4.909642714032074e-06,
|
| 1647 |
+
"loss": 0.45641288757324217,
|
| 1648 |
+
"step": 1165
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.0655936835712116,
|
| 1652 |
+
"grad_norm": 1.6024967432022095,
|
| 1653 |
+
"learning_rate": 4.872000861387291e-06,
|
| 1654 |
+
"loss": 0.46791677474975585,
|
| 1655 |
+
"step": 1170
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.0701488004858792,
|
| 1659 |
+
"grad_norm": 1.6948623657226562,
|
| 1660 |
+
"learning_rate": 4.834366266728753e-06,
|
| 1661 |
+
"loss": 0.4647111415863037,
|
| 1662 |
+
"step": 1175
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.0747039174005466,
|
| 1666 |
+
"grad_norm": 1.7235485315322876,
|
| 1667 |
+
"learning_rate": 4.796741064065902e-06,
|
| 1668 |
+
"loss": 0.46364355087280273,
|
| 1669 |
+
"step": 1180
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.0792590343152142,
|
| 1673 |
+
"grad_norm": 3.3120858669281006,
|
| 1674 |
+
"learning_rate": 4.759127386875618e-06,
|
| 1675 |
+
"loss": 0.45574679374694826,
|
| 1676 |
+
"step": 1185
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.0838141512298816,
|
| 1680 |
+
"grad_norm": 1.5388199090957642,
|
| 1681 |
+
"learning_rate": 4.721527367981251e-06,
|
| 1682 |
+
"loss": 0.46392068862915037,
|
| 1683 |
+
"step": 1190
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.088369268144549,
|
| 1687 |
+
"grad_norm": 1.50483238697052,
|
| 1688 |
+
"learning_rate": 4.683943139431683e-06,
|
| 1689 |
+
"loss": 0.4626826286315918,
|
| 1690 |
+
"step": 1195
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.0929243850592165,
|
| 1694 |
+
"grad_norm": 1.2712243795394897,
|
| 1695 |
+
"learning_rate": 4.646376832380423e-06,
|
| 1696 |
+
"loss": 0.4646759986877441,
|
| 1697 |
+
"step": 1200
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.097479501973884,
|
| 1701 |
+
"grad_norm": 1.4449741840362549,
|
| 1702 |
+
"learning_rate": 4.608830576964772e-06,
|
| 1703 |
+
"loss": 0.46281089782714846,
|
| 1704 |
+
"step": 1205
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.1020346188885515,
|
| 1708 |
+
"grad_norm": 1.2682076692581177,
|
| 1709 |
+
"learning_rate": 4.571306502185043e-06,
|
| 1710 |
+
"loss": 0.4645559787750244,
|
| 1711 |
+
"step": 1210
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.1065897358032188,
|
| 1715 |
+
"grad_norm": 1.3985633850097656,
|
| 1716 |
+
"learning_rate": 4.533806735783815e-06,
|
| 1717 |
+
"loss": 0.46173458099365233,
|
| 1718 |
+
"step": 1215
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.1111448527178864,
|
| 1722 |
+
"grad_norm": 2.7544267177581787,
|
| 1723 |
+
"learning_rate": 4.496333404125314e-06,
|
| 1724 |
+
"loss": 0.4600971221923828,
|
| 1725 |
+
"step": 1220
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.1156999696325538,
|
| 1729 |
+
"grad_norm": 1.4135196208953857,
|
| 1730 |
+
"learning_rate": 4.4588886320748235e-06,
|
| 1731 |
+
"loss": 0.45669097900390626,
|
| 1732 |
+
"step": 1225
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.1202550865472214,
|
| 1736 |
+
"grad_norm": 1.51726233959198,
|
| 1737 |
+
"learning_rate": 4.4214745428781946e-06,
|
| 1738 |
+
"loss": 0.46077938079833985,
|
| 1739 |
+
"step": 1230
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.1248102034618888,
|
| 1743 |
+
"grad_norm": 1.4505730867385864,
|
| 1744 |
+
"learning_rate": 4.384093258041459e-06,
|
| 1745 |
+
"loss": 0.46395068168640136,
|
| 1746 |
+
"step": 1235
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.1293653203765563,
|
| 1750 |
+
"grad_norm": 1.9110316038131714,
|
| 1751 |
+
"learning_rate": 4.346746897210534e-06,
|
| 1752 |
+
"loss": 0.45387964248657225,
|
| 1753 |
+
"step": 1240
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.1339204372912237,
|
| 1757 |
+
"grad_norm": 1.3564186096191406,
|
| 1758 |
+
"learning_rate": 4.309437578051021e-06,
|
| 1759 |
+
"loss": 0.4566159248352051,
|
| 1760 |
+
"step": 1245
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.1384755542058913,
|
| 1764 |
+
"grad_norm": 1.4822899103164673,
|
| 1765 |
+
"learning_rate": 4.272167416128134e-06,
|
| 1766 |
+
"loss": 0.4583602428436279,
|
| 1767 |
+
"step": 1250
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.1430306711205587,
|
| 1771 |
+
"grad_norm": 1.3349090814590454,
|
| 1772 |
+
"learning_rate": 4.234938524786744e-06,
|
| 1773 |
+
"loss": 0.45874862670898436,
|
| 1774 |
+
"step": 1255
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.1475857880352263,
|
| 1778 |
+
"grad_norm": 2.713782787322998,
|
| 1779 |
+
"learning_rate": 4.19775301503153e-06,
|
| 1780 |
+
"loss": 0.46090211868286135,
|
| 1781 |
+
"step": 1260
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.1521409049498936,
|
| 1785 |
+
"grad_norm": 1.5619561672210693,
|
| 1786 |
+
"learning_rate": 4.160612995407296e-06,
|
| 1787 |
+
"loss": 0.4585545539855957,
|
| 1788 |
+
"step": 1265
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.1566960218645612,
|
| 1792 |
+
"grad_norm": 1.8272922039031982,
|
| 1793 |
+
"learning_rate": 4.1235205718793995e-06,
|
| 1794 |
+
"loss": 0.45654687881469724,
|
| 1795 |
+
"step": 1270
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.1612511387792286,
|
| 1799 |
+
"grad_norm": 2.169624090194702,
|
| 1800 |
+
"learning_rate": 4.086477847714331e-06,
|
| 1801 |
+
"loss": 0.4591087341308594,
|
| 1802 |
+
"step": 1275
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.1658062556938962,
|
| 1806 |
+
"grad_norm": 2.21856689453125,
|
| 1807 |
+
"learning_rate": 4.0494869233604685e-06,
|
| 1808 |
+
"loss": 0.4587860107421875,
|
| 1809 |
+
"step": 1280
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.1703613726085635,
|
| 1813 |
+
"grad_norm": 1.5166852474212646,
|
| 1814 |
+
"learning_rate": 4.012549896328957e-06,
|
| 1815 |
+
"loss": 0.4574915885925293,
|
| 1816 |
+
"step": 1285
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.1749164895232311,
|
| 1820 |
+
"grad_norm": 1.3856573104858398,
|
| 1821 |
+
"learning_rate": 3.975668861074783e-06,
|
| 1822 |
+
"loss": 0.4564501762390137,
|
| 1823 |
+
"step": 1290
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.1794716064378985,
|
| 1827 |
+
"grad_norm": 1.2893812656402588,
|
| 1828 |
+
"learning_rate": 3.938845908878006e-06,
|
| 1829 |
+
"loss": 0.45852975845336913,
|
| 1830 |
+
"step": 1295
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.184026723352566,
|
| 1834 |
+
"grad_norm": 1.315671682357788,
|
| 1835 |
+
"learning_rate": 3.902083127725186e-06,
|
| 1836 |
+
"loss": 0.45477943420410155,
|
| 1837 |
+
"step": 1300
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.1885818402672335,
|
| 1841 |
+
"grad_norm": 1.489163875579834,
|
| 1842 |
+
"learning_rate": 3.865382602190972e-06,
|
| 1843 |
+
"loss": 0.45960540771484376,
|
| 1844 |
+
"step": 1305
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.193136957181901,
|
| 1848 |
+
"grad_norm": 1.664601445198059,
|
| 1849 |
+
"learning_rate": 3.828746413319911e-06,
|
| 1850 |
+
"loss": 0.4604182720184326,
|
| 1851 |
+
"step": 1310
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.1976920740965684,
|
| 1855 |
+
"grad_norm": 2.8415708541870117,
|
| 1856 |
+
"learning_rate": 3.7921766385084447e-06,
|
| 1857 |
+
"loss": 0.4568796634674072,
|
| 1858 |
+
"step": 1315
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.202247191011236,
|
| 1862 |
+
"grad_norm": 1.8271973133087158,
|
| 1863 |
+
"learning_rate": 3.755675351387107e-06,
|
| 1864 |
+
"loss": 0.4560407638549805,
|
| 1865 |
+
"step": 1320
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.2068023079259034,
|
| 1869 |
+
"grad_norm": 1.6760120391845703,
|
| 1870 |
+
"learning_rate": 3.719244621702952e-06,
|
| 1871 |
+
"loss": 0.4565584182739258,
|
| 1872 |
+
"step": 1325
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.211357424840571,
|
| 1876 |
+
"grad_norm": 1.4044896364212036,
|
| 1877 |
+
"learning_rate": 3.6828865152021857e-06,
|
| 1878 |
+
"loss": 0.4525318145751953,
|
| 1879 |
+
"step": 1330
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.2159125417552383,
|
| 1883 |
+
"grad_norm": 1.3660306930541992,
|
| 1884 |
+
"learning_rate": 3.64660309351303e-06,
|
| 1885 |
+
"loss": 0.45788965225219724,
|
| 1886 |
+
"step": 1335
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.220467658669906,
|
| 1890 |
+
"grad_norm": 1.7708740234375,
|
| 1891 |
+
"learning_rate": 3.610396414028827e-06,
|
| 1892 |
+
"loss": 0.45180473327636717,
|
| 1893 |
+
"step": 1340
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.2250227755845733,
|
| 1897 |
+
"grad_norm": 1.551252007484436,
|
| 1898 |
+
"learning_rate": 3.5742685297913773e-06,
|
| 1899 |
+
"loss": 0.4559042930603027,
|
| 1900 |
+
"step": 1345
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.2295778924992409,
|
| 1904 |
+
"grad_norm": 1.6479007005691528,
|
| 1905 |
+
"learning_rate": 3.538221489374516e-06,
|
| 1906 |
+
"loss": 0.4566207408905029,
|
| 1907 |
+
"step": 1350
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.2341330094139082,
|
| 1911 |
+
"grad_norm": 1.4534903764724731,
|
| 1912 |
+
"learning_rate": 3.5022573367679626e-06,
|
| 1913 |
+
"loss": 0.45155649185180663,
|
| 1914 |
+
"step": 1355
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.2386881263285758,
|
| 1918 |
+
"grad_norm": 1.7879937887191772,
|
| 1919 |
+
"learning_rate": 3.4663781112614192e-06,
|
| 1920 |
+
"loss": 0.44574294090270994,
|
| 1921 |
+
"step": 1360
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.2432432432432432,
|
| 1925 |
+
"grad_norm": 1.3173577785491943,
|
| 1926 |
+
"learning_rate": 3.43058584732893e-06,
|
| 1927 |
+
"loss": 0.45929703712463377,
|
| 1928 |
+
"step": 1365
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.2477983601579108,
|
| 1932 |
+
"grad_norm": 1.5794878005981445,
|
| 1933 |
+
"learning_rate": 3.3948825745135196e-06,
|
| 1934 |
+
"loss": 0.456890869140625,
|
| 1935 |
+
"step": 1370
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.2523534770725782,
|
| 1939 |
+
"grad_norm": 1.5050439834594727,
|
| 1940 |
+
"learning_rate": 3.3592703173121155e-06,
|
| 1941 |
+
"loss": 0.45540714263916016,
|
| 1942 |
+
"step": 1375
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.2569085939872457,
|
| 1946 |
+
"grad_norm": 2.2978973388671875,
|
| 1947 |
+
"learning_rate": 3.323751095060756e-06,
|
| 1948 |
+
"loss": 0.45746870040893556,
|
| 1949 |
+
"step": 1380
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.2614637109019131,
|
| 1953 |
+
"grad_norm": 1.3030719757080078,
|
| 1954 |
+
"learning_rate": 3.288326921820072e-06,
|
| 1955 |
+
"loss": 0.4567601203918457,
|
| 1956 |
+
"step": 1385
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.2660188278165807,
|
| 1960 |
+
"grad_norm": 1.585959553718567,
|
| 1961 |
+
"learning_rate": 3.2529998062611e-06,
|
| 1962 |
+
"loss": 0.45557346343994143,
|
| 1963 |
+
"step": 1390
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.270573944731248,
|
| 1967 |
+
"grad_norm": 1.2981617450714111,
|
| 1968 |
+
"learning_rate": 3.2177717515513723e-06,
|
| 1969 |
+
"loss": 0.4497828960418701,
|
| 1970 |
+
"step": 1395
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.2751290616459157,
|
| 1974 |
+
"grad_norm": 2.575040102005005,
|
| 1975 |
+
"learning_rate": 3.1826447552413337e-06,
|
| 1976 |
+
"loss": 0.46262612342834475,
|
| 1977 |
+
"step": 1400
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.279684178560583,
|
| 1981 |
+
"grad_norm": 1.5246721506118774,
|
| 1982 |
+
"learning_rate": 3.147620809151078e-06,
|
| 1983 |
+
"loss": 0.45871772766113283,
|
| 1984 |
+
"step": 1405
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.2842392954752504,
|
| 1988 |
+
"grad_norm": 1.6146317720413208,
|
| 1989 |
+
"learning_rate": 3.1127018992573994e-06,
|
| 1990 |
+
"loss": 0.4530343055725098,
|
| 1991 |
+
"step": 1410
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.288794412389918,
|
| 1995 |
+
"grad_norm": 1.3936330080032349,
|
| 1996 |
+
"learning_rate": 3.07789000558118e-06,
|
| 1997 |
+
"loss": 0.44968690872192385,
|
| 1998 |
+
"step": 1415
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.2933495293045856,
|
| 2002 |
+
"grad_norm": 2.6830527782440186,
|
| 2003 |
+
"learning_rate": 3.043187102075121e-06,
|
| 2004 |
+
"loss": 0.45221376419067383,
|
| 2005 |
+
"step": 1420
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.297904646219253,
|
| 2009 |
+
"grad_norm": 1.5950199365615845,
|
| 2010 |
+
"learning_rate": 3.0085951565118142e-06,
|
| 2011 |
+
"loss": 0.45414228439331056,
|
| 2012 |
+
"step": 1425
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.3024597631339203,
|
| 2016 |
+
"grad_norm": 2.076038122177124,
|
| 2017 |
+
"learning_rate": 2.974116130372151e-06,
|
| 2018 |
+
"loss": 0.4510965347290039,
|
| 2019 |
+
"step": 1430
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.307014880048588,
|
| 2023 |
+
"grad_norm": 2.966803550720215,
|
| 2024 |
+
"learning_rate": 2.9397519787341144e-06,
|
| 2025 |
+
"loss": 0.45758919715881347,
|
| 2026 |
+
"step": 1435
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.3115699969632555,
|
| 2030 |
+
"grad_norm": 1.5716099739074707,
|
| 2031 |
+
"learning_rate": 2.9055046501619088e-06,
|
| 2032 |
+
"loss": 0.45397381782531737,
|
| 2033 |
+
"step": 1440
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.3161251138779229,
|
| 2037 |
+
"grad_norm": 1.8856912851333618,
|
| 2038 |
+
"learning_rate": 2.8713760865954743e-06,
|
| 2039 |
+
"loss": 0.4520057201385498,
|
| 2040 |
+
"step": 1445
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.3206802307925902,
|
| 2044 |
+
"grad_norm": 1.5396655797958374,
|
| 2045 |
+
"learning_rate": 2.837368223240372e-06,
|
| 2046 |
+
"loss": 0.4507561683654785,
|
| 2047 |
+
"step": 1450
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.3252353477072578,
|
| 2051 |
+
"grad_norm": 1.9894485473632812,
|
| 2052 |
+
"learning_rate": 2.803482988458054e-06,
|
| 2053 |
+
"loss": 0.4559630393981934,
|
| 2054 |
+
"step": 1455
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.3297904646219254,
|
| 2058 |
+
"grad_norm": 9.26878547668457,
|
| 2059 |
+
"learning_rate": 2.7697223036565103e-06,
|
| 2060 |
+
"loss": 0.44710407257080076,
|
| 2061 |
+
"step": 1460
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.3343455815365928,
|
| 2065 |
+
"grad_norm": 1.7867859601974487,
|
| 2066 |
+
"learning_rate": 2.736088083181324e-06,
|
| 2067 |
+
"loss": 0.4569823741912842,
|
| 2068 |
+
"step": 1465
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.3389006984512601,
|
| 2072 |
+
"grad_norm": 4.057967662811279,
|
| 2073 |
+
"learning_rate": 2.702582234207126e-06,
|
| 2074 |
+
"loss": 0.4553251266479492,
|
| 2075 |
+
"step": 1470
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.3434558153659277,
|
| 2079 |
+
"grad_norm": 1.4120380878448486,
|
| 2080 |
+
"learning_rate": 2.6692066566294393e-06,
|
| 2081 |
+
"loss": 0.45798654556274415,
|
| 2082 |
+
"step": 1475
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.3480109322805953,
|
| 2086 |
+
"grad_norm": 1.817967176437378,
|
| 2087 |
+
"learning_rate": 2.6359632429569652e-06,
|
| 2088 |
+
"loss": 0.4523132801055908,
|
| 2089 |
+
"step": 1480
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.3525660491952627,
|
| 2093 |
+
"grad_norm": 2.0179030895233154,
|
| 2094 |
+
"learning_rate": 2.6028538782042547e-06,
|
| 2095 |
+
"loss": 0.4514320373535156,
|
| 2096 |
+
"step": 1485
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.35712116610993,
|
| 2100 |
+
"grad_norm": 2.939159870147705,
|
| 2101 |
+
"learning_rate": 2.5698804397848294e-06,
|
| 2102 |
+
"loss": 0.45455131530761717,
|
| 2103 |
+
"step": 1490
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.3616762830245976,
|
| 2107 |
+
"grad_norm": 1.9223039150238037,
|
| 2108 |
+
"learning_rate": 2.5370447974047308e-06,
|
| 2109 |
+
"loss": 0.45690116882324217,
|
| 2110 |
+
"step": 1495
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.3662313999392652,
|
| 2114 |
+
"grad_norm": 2.0542290210723877,
|
| 2115 |
+
"learning_rate": 2.5043488129564954e-06,
|
| 2116 |
+
"loss": 0.4534407138824463,
|
| 2117 |
+
"step": 1500
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.3707865168539326,
|
| 2121 |
+
"grad_norm": 1.5204252004623413,
|
| 2122 |
+
"learning_rate": 2.471794340413578e-06,
|
| 2123 |
+
"loss": 0.453262996673584,
|
| 2124 |
+
"step": 1505
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.3753416337686,
|
| 2128 |
+
"grad_norm": 1.4880733489990234,
|
| 2129 |
+
"learning_rate": 2.4393832257252253e-06,
|
| 2130 |
+
"loss": 0.4536959171295166,
|
| 2131 |
+
"step": 1510
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.3798967506832676,
|
| 2135 |
+
"grad_norm": 1.7958362102508545,
|
| 2136 |
+
"learning_rate": 2.4071173067118136e-06,
|
| 2137 |
+
"loss": 0.4493096351623535,
|
| 2138 |
+
"step": 1515
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.3844518675979351,
|
| 2142 |
+
"grad_norm": 1.4270687103271484,
|
| 2143 |
+
"learning_rate": 2.374998412960623e-06,
|
| 2144 |
+
"loss": 0.4516870975494385,
|
| 2145 |
+
"step": 1520
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.3890069845126025,
|
| 2149 |
+
"grad_norm": 1.7491718530654907,
|
| 2150 |
+
"learning_rate": 2.343028365722109e-06,
|
| 2151 |
+
"loss": 0.45421199798583983,
|
| 2152 |
+
"step": 1525
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 1.3935621014272699,
|
| 2156 |
+
"grad_norm": 1.595752239227295,
|
| 2157 |
+
"learning_rate": 2.311208977806617e-06,
|
| 2158 |
+
"loss": 0.45371274948120116,
|
| 2159 |
+
"step": 1530
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.3981172183419375,
|
| 2163 |
+
"grad_norm": 1.572836995124817,
|
| 2164 |
+
"learning_rate": 2.279542053481599e-06,
|
| 2165 |
+
"loss": 0.45087580680847167,
|
| 2166 |
+
"step": 1535
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.4026723352566048,
|
| 2170 |
+
"grad_norm": 3.447502851486206,
|
| 2171 |
+
"learning_rate": 2.2480293883693053e-06,
|
| 2172 |
+
"loss": 0.4540461540222168,
|
| 2173 |
+
"step": 1540
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.4072274521712724,
|
| 2177 |
+
"grad_norm": 5.559060096740723,
|
| 2178 |
+
"learning_rate": 2.216672769344965e-06,
|
| 2179 |
+
"loss": 0.4529916763305664,
|
| 2180 |
+
"step": 1545
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.4117825690859398,
|
| 2184 |
+
"grad_norm": 2.572004795074463,
|
| 2185 |
+
"learning_rate": 2.185473974435459e-06,
|
| 2186 |
+
"loss": 0.45006046295166013,
|
| 2187 |
+
"step": 1550
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.4163376860006074,
|
| 2191 |
+
"grad_norm": 1.64500892162323,
|
| 2192 |
+
"learning_rate": 2.1544347727185067e-06,
|
| 2193 |
+
"loss": 0.4464961051940918,
|
| 2194 |
+
"step": 1555
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.4208928029152748,
|
| 2198 |
+
"grad_norm": 2.7676432132720947,
|
| 2199 |
+
"learning_rate": 2.1235569242223537e-06,
|
| 2200 |
+
"loss": 0.44682931900024414,
|
| 2201 |
+
"step": 1560
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.4254479198299423,
|
| 2205 |
+
"grad_norm": 1.6749385595321655,
|
| 2206 |
+
"learning_rate": 2.0928421798259633e-06,
|
| 2207 |
+
"loss": 0.45028390884399416,
|
| 2208 |
+
"step": 1565
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 1.4300030367446097,
|
| 2212 |
+
"grad_norm": 1.5821510553359985,
|
| 2213 |
+
"learning_rate": 2.0622922811597512e-06,
|
| 2214 |
+
"loss": 0.4520574569702148,
|
| 2215 |
+
"step": 1570
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 1.4345581536592773,
|
| 2219 |
+
"grad_norm": 2.120412826538086,
|
| 2220 |
+
"learning_rate": 2.031908960506811e-06,
|
| 2221 |
+
"loss": 0.44826512336730956,
|
| 2222 |
+
"step": 1575
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 1.4391132705739447,
|
| 2226 |
+
"grad_norm": 1.8699346780776978,
|
| 2227 |
+
"learning_rate": 2.0016939407046987e-06,
|
| 2228 |
+
"loss": 0.4471128463745117,
|
| 2229 |
+
"step": 1580
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.4436683874886123,
|
| 2233 |
+
"grad_norm": 2.077984571456909,
|
| 2234 |
+
"learning_rate": 1.971648935047744e-06,
|
| 2235 |
+
"loss": 0.44693751335144044,
|
| 2236 |
+
"step": 1585
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 1.4482235044032796,
|
| 2240 |
+
"grad_norm": 1.5535467863082886,
|
| 2241 |
+
"learning_rate": 1.941775647189895e-06,
|
| 2242 |
+
"loss": 0.44760980606079104,
|
| 2243 |
+
"step": 1590
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 1.4527786213179472,
|
| 2247 |
+
"grad_norm": 2.7341277599334717,
|
| 2248 |
+
"learning_rate": 1.9120757710481155e-06,
|
| 2249 |
+
"loss": 0.44966630935668944,
|
| 2250 |
+
"step": 1595
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.4573337382326146,
|
| 2254 |
+
"grad_norm": 1.7916532754898071,
|
| 2255 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 2256 |
+
"loss": 0.44744625091552737,
|
| 2257 |
+
"step": 1600
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 1.4618888551472822,
|
| 2261 |
+
"grad_norm": 2.4260597229003906,
|
| 2262 |
+
"learning_rate": 1.8532029803199537e-06,
|
| 2263 |
+
"loss": 0.4553190231323242,
|
| 2264 |
+
"step": 1605
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 1.4664439720619495,
|
| 2268 |
+
"grad_norm": 1.6395586729049683,
|
| 2269 |
+
"learning_rate": 1.8240334040209252e-06,
|
| 2270 |
+
"loss": 0.45157713890075685,
|
| 2271 |
+
"step": 1610
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.4709990889766171,
|
| 2275 |
+
"grad_norm": 2.9597060680389404,
|
| 2276 |
+
"learning_rate": 1.795043915823373e-06,
|
| 2277 |
+
"loss": 0.45125951766967776,
|
| 2278 |
+
"step": 1615
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 1.4755542058912845,
|
| 2282 |
+
"grad_norm": 1.5317883491516113,
|
| 2283 |
+
"learning_rate": 1.7662361595298144e-06,
|
| 2284 |
+
"loss": 0.44574918746948244,
|
| 2285 |
+
"step": 1620
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 1.480109322805952,
|
| 2289 |
+
"grad_norm": 2.6433119773864746,
|
| 2290 |
+
"learning_rate": 1.7376117686379562e-06,
|
| 2291 |
+
"loss": 0.4534473896026611,
|
| 2292 |
+
"step": 1625
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 1.4846644397206195,
|
| 2296 |
+
"grad_norm": 1.9677019119262695,
|
| 2297 |
+
"learning_rate": 1.7091723662480557e-06,
|
| 2298 |
+
"loss": 0.44940710067749023,
|
| 2299 |
+
"step": 1630
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 1.489219556635287,
|
| 2303 |
+
"grad_norm": 1.8388527631759644,
|
| 2304 |
+
"learning_rate": 1.6809195649708998e-06,
|
| 2305 |
+
"loss": 0.4490818977355957,
|
| 2306 |
+
"step": 1635
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.4937746735499544,
|
| 2310 |
+
"grad_norm": 2.5333993434906006,
|
| 2311 |
+
"learning_rate": 1.6528549668363586e-06,
|
| 2312 |
+
"loss": 0.44977474212646484,
|
| 2313 |
+
"step": 1640
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 1.498329790464622,
|
| 2317 |
+
"grad_norm": 1.6673647165298462,
|
| 2318 |
+
"learning_rate": 1.6249801632025337e-06,
|
| 2319 |
+
"loss": 0.447948694229126,
|
| 2320 |
+
"step": 1645
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 1.5028849073792894,
|
| 2324 |
+
"grad_norm": 3.8595633506774902,
|
| 2325 |
+
"learning_rate": 1.5972967346655449e-06,
|
| 2326 |
+
"loss": 0.4469724178314209,
|
| 2327 |
+
"step": 1650
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.507440024293957,
|
| 2331 |
+
"grad_norm": 1.906414270401001,
|
| 2332 |
+
"learning_rate": 1.5698062509698908e-06,
|
| 2333 |
+
"loss": 0.4501968860626221,
|
| 2334 |
+
"step": 1655
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.5119951412086243,
|
| 2338 |
+
"grad_norm": 1.8252265453338623,
|
| 2339 |
+
"learning_rate": 1.5425102709194374e-06,
|
| 2340 |
+
"loss": 0.44973297119140626,
|
| 2341 |
+
"step": 1660
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 1.5165502581232917,
|
| 2345 |
+
"grad_norm": 1.7581197023391724,
|
| 2346 |
+
"learning_rate": 1.5154103422890394e-06,
|
| 2347 |
+
"loss": 0.44851016998291016,
|
| 2348 |
+
"step": 1665
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 1.5211053750379593,
|
| 2352 |
+
"grad_norm": 2.9670493602752686,
|
| 2353 |
+
"learning_rate": 1.4885080017367632e-06,
|
| 2354 |
+
"loss": 0.4460925102233887,
|
| 2355 |
+
"step": 1670
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 1.5256604919526269,
|
| 2359 |
+
"grad_norm": 2.03843355178833,
|
| 2360 |
+
"learning_rate": 1.4618047747167613e-06,
|
| 2361 |
+
"loss": 0.4519230365753174,
|
| 2362 |
+
"step": 1675
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.5302156088672942,
|
| 2366 |
+
"grad_norm": 2.041097402572632,
|
| 2367 |
+
"learning_rate": 1.4353021753927753e-06,
|
| 2368 |
+
"loss": 0.4467913627624512,
|
| 2369 |
+
"step": 1680
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 1.5347707257819616,
|
| 2373 |
+
"grad_norm": 2.044473886489868,
|
| 2374 |
+
"learning_rate": 1.4090017065522731e-06,
|
| 2375 |
+
"loss": 0.4481149673461914,
|
| 2376 |
+
"step": 1685
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 1.5393258426966292,
|
| 2380 |
+
"grad_norm": 2.0631234645843506,
|
| 2381 |
+
"learning_rate": 1.3829048595212358e-06,
|
| 2382 |
+
"loss": 0.45535945892333984,
|
| 2383 |
+
"step": 1690
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 1.5438809596112968,
|
| 2387 |
+
"grad_norm": 3.0296971797943115,
|
| 2388 |
+
"learning_rate": 1.3570131140795934e-06,
|
| 2389 |
+
"loss": 0.4471914291381836,
|
| 2390 |
+
"step": 1695
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 1.5484360765259642,
|
| 2394 |
+
"grad_norm": 2.544480323791504,
|
| 2395 |
+
"learning_rate": 1.3313279383773258e-06,
|
| 2396 |
+
"loss": 0.44684619903564454,
|
| 2397 |
+
"step": 1700
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 1.5529911934406315,
|
| 2401 |
+
"grad_norm": 1.992871642112732,
|
| 2402 |
+
"learning_rate": 1.3058507888511985e-06,
|
| 2403 |
+
"loss": 0.44977169036865233,
|
| 2404 |
+
"step": 1705
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 1.5575463103552991,
|
| 2408 |
+
"grad_norm": 3.2738561630249023,
|
| 2409 |
+
"learning_rate": 1.2805831101421923e-06,
|
| 2410 |
+
"loss": 0.4530197620391846,
|
| 2411 |
+
"step": 1710
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 1.5621014272699667,
|
| 2415 |
+
"grad_norm": 2.0382983684539795,
|
| 2416 |
+
"learning_rate": 1.255526335013577e-06,
|
| 2417 |
+
"loss": 0.4496905326843262,
|
| 2418 |
+
"step": 1715
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 1.566656544184634,
|
| 2422 |
+
"grad_norm": 2.9439361095428467,
|
| 2423 |
+
"learning_rate": 1.2306818842696716e-06,
|
| 2424 |
+
"loss": 0.4521991729736328,
|
| 2425 |
+
"step": 1720
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 1.5712116610993014,
|
| 2429 |
+
"grad_norm": 23.51557159423828,
|
| 2430 |
+
"learning_rate": 1.206051166675284e-06,
|
| 2431 |
+
"loss": 0.44781079292297366,
|
| 2432 |
+
"step": 1725
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 1.575766778013969,
|
| 2436 |
+
"grad_norm": 2.009943723678589,
|
| 2437 |
+
"learning_rate": 1.181635578875826e-06,
|
| 2438 |
+
"loss": 0.4488945007324219,
|
| 2439 |
+
"step": 1730
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 1.5803218949286366,
|
| 2443 |
+
"grad_norm": 4.892741680145264,
|
| 2444 |
+
"learning_rate": 1.1574365053181152e-06,
|
| 2445 |
+
"loss": 0.448914098739624,
|
| 2446 |
+
"step": 1735
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 1.584877011843304,
|
| 2450 |
+
"grad_norm": 2.3487164974212646,
|
| 2451 |
+
"learning_rate": 1.1334553181718771e-06,
|
| 2452 |
+
"loss": 0.4451763153076172,
|
| 2453 |
+
"step": 1740
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 1.5894321287579714,
|
| 2457 |
+
"grad_norm": 2.0576467514038086,
|
| 2458 |
+
"learning_rate": 1.1096933772519408e-06,
|
| 2459 |
+
"loss": 0.4390605926513672,
|
| 2460 |
+
"step": 1745
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 1.593987245672639,
|
| 2464 |
+
"grad_norm": 5.04032564163208,
|
| 2465 |
+
"learning_rate": 1.086152029941122e-06,
|
| 2466 |
+
"loss": 0.4442657470703125,
|
| 2467 |
+
"step": 1750
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 1.5985423625873065,
|
| 2471 |
+
"grad_norm": 3.1288936138153076,
|
| 2472 |
+
"learning_rate": 1.0628326111138377e-06,
|
| 2473 |
+
"loss": 0.44927182197570803,
|
| 2474 |
+
"step": 1755
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.603097479501974,
|
| 2478 |
+
"grad_norm": 2.3182742595672607,
|
| 2479 |
+
"learning_rate": 1.0397364430603978e-06,
|
| 2480 |
+
"loss": 0.45226001739501953,
|
| 2481 |
+
"step": 1760
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 1.6076525964166413,
|
| 2485 |
+
"grad_norm": 2.4209063053131104,
|
| 2486 |
+
"learning_rate": 1.016864835412037e-06,
|
| 2487 |
+
"loss": 0.4492661476135254,
|
| 2488 |
+
"step": 1765
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 1.6122077133313089,
|
| 2492 |
+
"grad_norm": 1.9613839387893677,
|
| 2493 |
+
"learning_rate": 9.94219085066654e-07,
|
| 2494 |
+
"loss": 0.4481070518493652,
|
| 2495 |
+
"step": 1770
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 1.6167628302459764,
|
| 2499 |
+
"grad_norm": 3.977729082107544,
|
| 2500 |
+
"learning_rate": 9.718004761152689e-07,
|
| 2501 |
+
"loss": 0.4445545196533203,
|
| 2502 |
+
"step": 1775
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 1.6213179471606438,
|
| 2506 |
+
"grad_norm": 2.3831753730773926,
|
| 2507 |
+
"learning_rate": 9.496102797692125e-07,
|
| 2508 |
+
"loss": 0.4480759620666504,
|
| 2509 |
+
"step": 1780
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 1.6258730640753112,
|
| 2513 |
+
"grad_norm": 1.8846925497055054,
|
| 2514 |
+
"learning_rate": 9.276497542880431e-07,
|
| 2515 |
+
"loss": 0.4429009437561035,
|
| 2516 |
+
"step": 1785
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 1.6304281809899788,
|
| 2520 |
+
"grad_norm": 4.497838497161865,
|
| 2521 |
+
"learning_rate": 9.059201449082045e-07,
|
| 2522 |
+
"loss": 0.4449130058288574,
|
| 2523 |
+
"step": 1790
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 1.6349832979046464,
|
| 2527 |
+
"grad_norm": 2.514615535736084,
|
| 2528 |
+
"learning_rate": 8.844226837724079e-07,
|
| 2529 |
+
"loss": 0.4506368160247803,
|
| 2530 |
+
"step": 1795
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 1.6395384148193137,
|
| 2534 |
+
"grad_norm": 2.240323066711426,
|
| 2535 |
+
"learning_rate": 8.631585898597739e-07,
|
| 2536 |
+
"loss": 0.4447455883026123,
|
| 2537 |
+
"step": 1800
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 1.644093531733981,
|
| 2541 |
+
"grad_norm": 2.0742299556732178,
|
| 2542 |
+
"learning_rate": 8.421290689167056e-07,
|
| 2543 |
+
"loss": 0.44998984336853026,
|
| 2544 |
+
"step": 1805
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 1.6486486486486487,
|
| 2548 |
+
"grad_norm": 1.7966265678405762,
|
| 2549 |
+
"learning_rate": 8.213353133885211e-07,
|
| 2550 |
+
"loss": 0.4495072841644287,
|
| 2551 |
+
"step": 1810
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 1.6532037655633163,
|
| 2555 |
+
"grad_norm": 2.6778430938720703,
|
| 2556 |
+
"learning_rate": 8.0077850235184e-07,
|
| 2557 |
+
"loss": 0.44173946380615237,
|
| 2558 |
+
"step": 1815
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 1.6577588824779836,
|
| 2562 |
+
"grad_norm": 1.9878642559051514,
|
| 2563 |
+
"learning_rate": 7.804598014477255e-07,
|
| 2564 |
+
"loss": 0.4415739059448242,
|
| 2565 |
+
"step": 1820
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 1.662313999392651,
|
| 2569 |
+
"grad_norm": 2.5896787643432617,
|
| 2570 |
+
"learning_rate": 7.603803628155821e-07,
|
| 2571 |
+
"loss": 0.44545326232910154,
|
| 2572 |
+
"step": 1825
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 1.6668691163073186,
|
| 2576 |
+
"grad_norm": 1.7139712572097778,
|
| 2577 |
+
"learning_rate": 7.405413250278315e-07,
|
| 2578 |
+
"loss": 0.45055904388427737,
|
| 2579 |
+
"step": 1830
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 1.6714242332219862,
|
| 2583 |
+
"grad_norm": 1.7959189414978027,
|
| 2584 |
+
"learning_rate": 7.209438130253538e-07,
|
| 2585 |
+
"loss": 0.4413741111755371,
|
| 2586 |
+
"step": 1835
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 1.6759793501366536,
|
| 2590 |
+
"grad_norm": 5.144044876098633,
|
| 2591 |
+
"learning_rate": 7.015889380536939e-07,
|
| 2592 |
+
"loss": 0.44967002868652345,
|
| 2593 |
+
"step": 1840
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 1.680534467051321,
|
| 2597 |
+
"grad_norm": 2.06825852394104,
|
| 2598 |
+
"learning_rate": 6.824777976000513e-07,
|
| 2599 |
+
"loss": 0.44098854064941406,
|
| 2600 |
+
"step": 1845
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 1.6850895839659885,
|
| 2604 |
+
"grad_norm": 1.9740947484970093,
|
| 2605 |
+
"learning_rate": 6.636114753310496e-07,
|
| 2606 |
+
"loss": 0.45333032608032225,
|
| 2607 |
+
"step": 1850
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 1.689644700880656,
|
| 2611 |
+
"grad_norm": 20.434785842895508,
|
| 2612 |
+
"learning_rate": 6.449910410312927e-07,
|
| 2613 |
+
"loss": 0.44796323776245117,
|
| 2614 |
+
"step": 1855
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 1.6941998177953232,
|
| 2618 |
+
"grad_norm": 2.0130579471588135,
|
| 2619 |
+
"learning_rate": 6.266175505426958e-07,
|
| 2620 |
+
"loss": 0.451617431640625,
|
| 2621 |
+
"step": 1860
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 1.6987549347099908,
|
| 2625 |
+
"grad_norm": 3.6143994331359863,
|
| 2626 |
+
"learning_rate": 6.08492045704625e-07,
|
| 2627 |
+
"loss": 0.4540760040283203,
|
| 2628 |
+
"step": 1865
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 1.7033100516246584,
|
| 2632 |
+
"grad_norm": 1.749821424484253,
|
| 2633 |
+
"learning_rate": 5.906155542948172e-07,
|
| 2634 |
+
"loss": 0.4482609748840332,
|
| 2635 |
+
"step": 1870
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 1.7078651685393258,
|
| 2639 |
+
"grad_norm": 2.197422981262207,
|
| 2640 |
+
"learning_rate": 5.729890899710949e-07,
|
| 2641 |
+
"loss": 0.4451118469238281,
|
| 2642 |
+
"step": 1875
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 1.7124202854539932,
|
| 2646 |
+
"grad_norm": 1.8987295627593994,
|
| 2647 |
+
"learning_rate": 5.556136522139027e-07,
|
| 2648 |
+
"loss": 0.44547395706176757,
|
| 2649 |
+
"step": 1880
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 1.7169754023686608,
|
| 2653 |
+
"grad_norm": 2.9210968017578125,
|
| 2654 |
+
"learning_rate": 5.384902262696229e-07,
|
| 2655 |
+
"loss": 0.44892401695251466,
|
| 2656 |
+
"step": 1885
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 1.7215305192833283,
|
| 2660 |
+
"grad_norm": 2.459737777709961,
|
| 2661 |
+
"learning_rate": 5.216197830947095e-07,
|
| 2662 |
+
"loss": 0.45287532806396485,
|
| 2663 |
+
"step": 1890
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 1.7260856361979957,
|
| 2667 |
+
"grad_norm": 2.4369258880615234,
|
| 2668 |
+
"learning_rate": 5.05003279300637e-07,
|
| 2669 |
+
"loss": 0.4450559139251709,
|
| 2670 |
+
"step": 1895
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 1.730640753112663,
|
| 2674 |
+
"grad_norm": 2.977600336074829,
|
| 2675 |
+
"learning_rate": 4.886416570996505e-07,
|
| 2676 |
+
"loss": 0.4451436996459961,
|
| 2677 |
+
"step": 1900
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 1.7351958700273307,
|
| 2681 |
+
"grad_norm": 2.3304171562194824,
|
| 2682 |
+
"learning_rate": 4.7253584425134393e-07,
|
| 2683 |
+
"loss": 0.4494274139404297,
|
| 2684 |
+
"step": 1905
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 1.7397509869419983,
|
| 2688 |
+
"grad_norm": 1.9524421691894531,
|
| 2689 |
+
"learning_rate": 4.5668675401005113e-07,
|
| 2690 |
+
"loss": 0.449497127532959,
|
| 2691 |
+
"step": 1910
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 1.7443061038566656,
|
| 2695 |
+
"grad_norm": 1.9427039623260498,
|
| 2696 |
+
"learning_rate": 4.410952850730638e-07,
|
| 2697 |
+
"loss": 0.4483028411865234,
|
| 2698 |
+
"step": 1915
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 1.748861220771333,
|
| 2702 |
+
"grad_norm": 3.3043453693389893,
|
| 2703 |
+
"learning_rate": 4.2576232152966577e-07,
|
| 2704 |
+
"loss": 0.4501804828643799,
|
| 2705 |
+
"step": 1920
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 1.7534163376860006,
|
| 2709 |
+
"grad_norm": 2.155041456222534,
|
| 2710 |
+
"learning_rate": 4.106887328110082e-07,
|
| 2711 |
+
"loss": 0.4523191452026367,
|
| 2712 |
+
"step": 1925
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 1.7579714546006682,
|
| 2716 |
+
"grad_norm": 2.140929937362671,
|
| 2717 |
+
"learning_rate": 3.958753736408105e-07,
|
| 2718 |
+
"loss": 0.4435746192932129,
|
| 2719 |
+
"step": 1930
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 1.7625265715153355,
|
| 2723 |
+
"grad_norm": 2.4108352661132812,
|
| 2724 |
+
"learning_rate": 3.8132308398688813e-07,
|
| 2725 |
+
"loss": 0.4462573051452637,
|
| 2726 |
+
"step": 1935
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 1.767081688430003,
|
| 2730 |
+
"grad_norm": 4.496824741363525,
|
| 2731 |
+
"learning_rate": 3.6703268901353007e-07,
|
| 2732 |
+
"loss": 0.4435447692871094,
|
| 2733 |
+
"step": 1940
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 1.7716368053446705,
|
| 2737 |
+
"grad_norm": 3.001497507095337,
|
| 2738 |
+
"learning_rate": 3.530049990347068e-07,
|
| 2739 |
+
"loss": 0.4490827560424805,
|
| 2740 |
+
"step": 1945
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 1.776191922259338,
|
| 2744 |
+
"grad_norm": 1.8158936500549316,
|
| 2745 |
+
"learning_rate": 3.392408094681193e-07,
|
| 2746 |
+
"loss": 0.44419255256652834,
|
| 2747 |
+
"step": 1950
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 1.7807470391740055,
|
| 2751 |
+
"grad_norm": 1.8862253427505493,
|
| 2752 |
+
"learning_rate": 3.257409007901047e-07,
|
| 2753 |
+
"loss": 0.44574751853942873,
|
| 2754 |
+
"step": 1955
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 1.7853021560886728,
|
| 2758 |
+
"grad_norm": 3.064157247543335,
|
| 2759 |
+
"learning_rate": 3.125060384913725e-07,
|
| 2760 |
+
"loss": 0.4461554527282715,
|
| 2761 |
+
"step": 1960
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 1.7898572730033404,
|
| 2765 |
+
"grad_norm": 3.538055658340454,
|
| 2766 |
+
"learning_rate": 2.995369730336012e-07,
|
| 2767 |
+
"loss": 0.45227828025817873,
|
| 2768 |
+
"step": 1965
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 1.794412389918008,
|
| 2772 |
+
"grad_norm": 1.7463148832321167,
|
| 2773 |
+
"learning_rate": 2.8683443980688506e-07,
|
| 2774 |
+
"loss": 0.4456148147583008,
|
| 2775 |
+
"step": 1970
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 1.7989675068326754,
|
| 2779 |
+
"grad_norm": 2.07248854637146,
|
| 2780 |
+
"learning_rate": 2.7439915908803736e-07,
|
| 2781 |
+
"loss": 0.4530907154083252,
|
| 2782 |
+
"step": 1975
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 1.8035226237473427,
|
| 2786 |
+
"grad_norm": 1.6984100341796875,
|
| 2787 |
+
"learning_rate": 2.622318359997417e-07,
|
| 2788 |
+
"loss": 0.44570345878601075,
|
| 2789 |
+
"step": 1980
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 1.8080777406620103,
|
| 2793 |
+
"grad_norm": 2.3377933502197266,
|
| 2794 |
+
"learning_rate": 2.5033316047057664e-07,
|
| 2795 |
+
"loss": 0.4517060279846191,
|
| 2796 |
+
"step": 1985
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 1.812632857576678,
|
| 2800 |
+
"grad_norm": 4.431271076202393,
|
| 2801 |
+
"learning_rate": 2.387038071958897e-07,
|
| 2802 |
+
"loss": 0.444257926940918,
|
| 2803 |
+
"step": 1990
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 1.8171879744913453,
|
| 2807 |
+
"grad_norm": 5.051254749298096,
|
| 2808 |
+
"learning_rate": 2.2734443559954023e-07,
|
| 2809 |
+
"loss": 0.4467195510864258,
|
| 2810 |
+
"step": 1995
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 1.8217430914060126,
|
| 2814 |
+
"grad_norm": 2.7545220851898193,
|
| 2815 |
+
"learning_rate": 2.1625568979651012e-07,
|
| 2816 |
+
"loss": 0.4499521732330322,
|
| 2817 |
+
"step": 2000
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 1.8262982083206802,
|
| 2821 |
+
"grad_norm": 2.4163920879364014,
|
| 2822 |
+
"learning_rate": 2.054381985563786e-07,
|
| 2823 |
+
"loss": 0.44539585113525393,
|
| 2824 |
+
"step": 2005
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 1.8308533252353478,
|
| 2828 |
+
"grad_norm": 2.1222238540649414,
|
| 2829 |
+
"learning_rate": 1.9489257526766891e-07,
|
| 2830 |
+
"loss": 0.445588493347168,
|
| 2831 |
+
"step": 2010
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 1.8354084421500152,
|
| 2835 |
+
"grad_norm": 1.582443356513977,
|
| 2836 |
+
"learning_rate": 1.8461941790306637e-07,
|
| 2837 |
+
"loss": 0.446135950088501,
|
| 2838 |
+
"step": 2015
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 1.8399635590646826,
|
| 2842 |
+
"grad_norm": 2.354520797729492,
|
| 2843 |
+
"learning_rate": 1.7461930898551472e-07,
|
| 2844 |
+
"loss": 0.44951620101928713,
|
| 2845 |
+
"step": 2020
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 1.8445186759793502,
|
| 2849 |
+
"grad_norm": 2.66642689704895,
|
| 2850 |
+
"learning_rate": 1.6489281555517934e-07,
|
| 2851 |
+
"loss": 0.443574857711792,
|
| 2852 |
+
"step": 2025
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 1.8490737928940177,
|
| 2856 |
+
"grad_norm": 3.7442924976348877,
|
| 2857 |
+
"learning_rate": 1.5544048913730126e-07,
|
| 2858 |
+
"loss": 0.44850635528564453,
|
| 2859 |
+
"step": 2030
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 1.853628909808685,
|
| 2863 |
+
"grad_norm": 1.5329631567001343,
|
| 2864 |
+
"learning_rate": 1.4626286571091664e-07,
|
| 2865 |
+
"loss": 0.4458890914916992,
|
| 2866 |
+
"step": 2035
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 1.8581840267233525,
|
| 2870 |
+
"grad_norm": 2.335324764251709,
|
| 2871 |
+
"learning_rate": 1.373604656784694e-07,
|
| 2872 |
+
"loss": 0.4490960597991943,
|
| 2873 |
+
"step": 2040
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 1.86273914363802,
|
| 2877 |
+
"grad_norm": 2.4603464603424072,
|
| 2878 |
+
"learning_rate": 1.2873379383630203e-07,
|
| 2879 |
+
"loss": 0.44408578872680665,
|
| 2880 |
+
"step": 2045
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 1.8672942605526877,
|
| 2884 |
+
"grad_norm": 2.4164867401123047,
|
| 2885 |
+
"learning_rate": 1.2038333934603187e-07,
|
| 2886 |
+
"loss": 0.44702978134155275,
|
| 2887 |
+
"step": 2050
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 1.871849377467355,
|
| 2891 |
+
"grad_norm": 4.425102710723877,
|
| 2892 |
+
"learning_rate": 1.1230957570681211e-07,
|
| 2893 |
+
"loss": 0.4475153923034668,
|
| 2894 |
+
"step": 2055
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 1.8764044943820224,
|
| 2898 |
+
"grad_norm": 2.0736005306243896,
|
| 2899 |
+
"learning_rate": 1.0451296072848394e-07,
|
| 2900 |
+
"loss": 0.44957666397094725,
|
| 2901 |
+
"step": 2060
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 1.88095961129669,
|
| 2905 |
+
"grad_norm": 2.4189772605895996,
|
| 2906 |
+
"learning_rate": 9.699393650561883e-08,
|
| 2907 |
+
"loss": 0.44267587661743163,
|
| 2908 |
+
"step": 2065
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 1.8855147282113576,
|
| 2912 |
+
"grad_norm": 4.224188327789307,
|
| 2913 |
+
"learning_rate": 8.975292939244928e-08,
|
| 2914 |
+
"loss": 0.4467939853668213,
|
| 2915 |
+
"step": 2070
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 1.890069845126025,
|
| 2919 |
+
"grad_norm": 1.827042818069458,
|
| 2920 |
+
"learning_rate": 8.27903499786903e-08,
|
| 2921 |
+
"loss": 0.4426234722137451,
|
| 2922 |
+
"step": 2075
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 1.8946249620406923,
|
| 2926 |
+
"grad_norm": 1.7865091562271118,
|
| 2927 |
+
"learning_rate": 7.610659306626134e-08,
|
| 2928 |
+
"loss": 0.4465123176574707,
|
| 2929 |
+
"step": 2080
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 1.89918007895536,
|
| 2933 |
+
"grad_norm": 1.8325212001800537,
|
| 2934 |
+
"learning_rate": 6.970203764689931e-08,
|
| 2935 |
+
"loss": 0.44530882835388186,
|
| 2936 |
+
"step": 2085
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 1.9037351958700275,
|
| 2940 |
+
"grad_norm": 1.6083518266677856,
|
| 2941 |
+
"learning_rate": 6.357704688066457e-08,
|
| 2942 |
+
"loss": 0.44170894622802737,
|
| 2943 |
+
"step": 2090
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 1.9082903127846949,
|
| 2947 |
+
"grad_norm": 2.245140314102173,
|
| 2948 |
+
"learning_rate": 5.773196807535464e-08,
|
| 2949 |
+
"loss": 0.448030948638916,
|
| 2950 |
+
"step": 2095
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 1.9128454296993622,
|
| 2954 |
+
"grad_norm": 1.7852219343185425,
|
| 2955 |
+
"learning_rate": 5.2167132666806063e-08,
|
| 2956 |
+
"loss": 0.4466597557067871,
|
| 2957 |
+
"step": 2100
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 1.9174005466140298,
|
| 2961 |
+
"grad_norm": 1.8668675422668457,
|
| 2962 |
+
"learning_rate": 4.6882856200101135e-08,
|
| 2963 |
+
"loss": 0.4466597557067871,
|
| 2964 |
+
"step": 2105
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 1.9219556635286974,
|
| 2968 |
+
"grad_norm": 2.011796712875366,
|
| 2969 |
+
"learning_rate": 4.1879438311677176e-08,
|
| 2970 |
+
"loss": 0.4484766960144043,
|
| 2971 |
+
"step": 2110
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 1.9265107804433648,
|
| 2975 |
+
"grad_norm": 2.214890241622925,
|
| 2976 |
+
"learning_rate": 3.715716271233627e-08,
|
| 2977 |
+
"loss": 0.4424152374267578,
|
| 2978 |
+
"step": 2115
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 1.9310658973580321,
|
| 2982 |
+
"grad_norm": 2.4538991451263428,
|
| 2983 |
+
"learning_rate": 3.271629717115643e-08,
|
| 2984 |
+
"loss": 0.44472498893737794,
|
| 2985 |
+
"step": 2120
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 1.9356210142726997,
|
| 2989 |
+
"grad_norm": 2.28452467918396,
|
| 2990 |
+
"learning_rate": 2.8557093500308774e-08,
|
| 2991 |
+
"loss": 0.45107216835021974,
|
| 2992 |
+
"step": 2125
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 1.940176131187367,
|
| 2996 |
+
"grad_norm": 1.7527275085449219,
|
| 2997 |
+
"learning_rate": 2.4679787540779488e-08,
|
| 2998 |
+
"loss": 0.443121337890625,
|
| 2999 |
+
"step": 2130
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 1.9447312481020345,
|
| 3003 |
+
"grad_norm": 1.5625219345092773,
|
| 3004 |
+
"learning_rate": 2.1084599148994966e-08,
|
| 3005 |
+
"loss": 0.4465321063995361,
|
| 3006 |
+
"step": 2135
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 1.949286365016702,
|
| 3010 |
+
"grad_norm": 2.579392671585083,
|
| 3011 |
+
"learning_rate": 1.7771732184357905e-08,
|
| 3012 |
+
"loss": 0.4496023178100586,
|
| 3013 |
+
"step": 2140
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 1.9538414819313696,
|
| 3017 |
+
"grad_norm": 1.7549206018447876,
|
| 3018 |
+
"learning_rate": 1.4741374497686534e-08,
|
| 3019 |
+
"loss": 0.4448676109313965,
|
| 3020 |
+
"step": 2145
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 1.958396598846037,
|
| 3024 |
+
"grad_norm": 5.741093158721924,
|
| 3025 |
+
"learning_rate": 1.1993697920561486e-08,
|
| 3026 |
+
"loss": 0.44547858238220217,
|
| 3027 |
+
"step": 2150
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 1.9629517157607044,
|
| 3031 |
+
"grad_norm": 2.295653820037842,
|
| 3032 |
+
"learning_rate": 9.528858255584694e-09,
|
| 3033 |
+
"loss": 0.4428717136383057,
|
| 3034 |
+
"step": 2155
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 1.967506832675372,
|
| 3038 |
+
"grad_norm": 2.983132839202881,
|
| 3039 |
+
"learning_rate": 7.3469952675436774e-09,
|
| 3040 |
+
"loss": 0.4444404125213623,
|
| 3041 |
+
"step": 2160
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 1.9720619495900396,
|
| 3045 |
+
"grad_norm": 2.4041531085968018,
|
| 3046 |
+
"learning_rate": 5.448232675485665e-09,
|
| 3047 |
+
"loss": 0.44472641944885255,
|
| 3048 |
+
"step": 2165
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 1.976617066504707,
|
| 3052 |
+
"grad_norm": 1.7280186414718628,
|
| 3053 |
+
"learning_rate": 3.832678145704316e-09,
|
| 3054 |
+
"loss": 0.44418935775756835,
|
| 3055 |
+
"step": 2170
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 1.9811721834193743,
|
| 3059 |
+
"grad_norm": 2.51718807220459,
|
| 3060 |
+
"learning_rate": 2.500423285632381e-09,
|
| 3061 |
+
"loss": 0.44251017570495604,
|
| 3062 |
+
"step": 2175
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 1.9857273003340419,
|
| 3066 |
+
"grad_norm": 2.018040180206299,
|
| 3067 |
+
"learning_rate": 1.4515436386497439e-09,
|
| 3068 |
+
"loss": 0.44551925659179686,
|
| 3069 |
+
"step": 2180
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 1.9902824172487095,
|
| 3073 |
+
"grad_norm": 2.1868982315063477,
|
| 3074 |
+
"learning_rate": 6.860986797968538e-10,
|
| 3075 |
+
"loss": 0.44702887535095215,
|
| 3076 |
+
"step": 2185
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 1.9948375341633768,
|
| 3080 |
+
"grad_norm": 2.0124709606170654,
|
| 3081 |
+
"learning_rate": 2.0413181240519498e-10,
|
| 3082 |
+
"loss": 0.44887866973876955,
|
| 3083 |
+
"step": 2190
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 1.9993926510780442,
|
| 3087 |
+
"grad_norm": 2.1505117416381836,
|
| 3088 |
+
"learning_rate": 5.670365634258268e-12,
|
| 3089 |
+
"loss": 0.4479702949523926,
|
| 3090 |
+
"step": 2195
|
| 3091 |
+
}
|
| 3092 |
+
],
|
| 3093 |
+
"logging_steps": 5,
|
| 3094 |
+
"max_steps": 2196,
|
| 3095 |
+
"num_input_tokens_seen": 0,
|
| 3096 |
+
"num_train_epochs": 2,
|
| 3097 |
+
"save_steps": 200,
|
| 3098 |
+
"stateful_callbacks": {
|
| 3099 |
+
"TrainerControl": {
|
| 3100 |
+
"args": {
|
| 3101 |
+
"should_epoch_stop": false,
|
| 3102 |
+
"should_evaluate": false,
|
| 3103 |
+
"should_log": false,
|
| 3104 |
+
"should_save": true,
|
| 3105 |
+
"should_training_stop": true
|
| 3106 |
+
},
|
| 3107 |
+
"attributes": {}
|
| 3108 |
+
}
|
| 3109 |
+
},
|
| 3110 |
+
"total_flos": 2.3603289861491838e+20,
|
| 3111 |
+
"train_batch_size": 8,
|
| 3112 |
+
"trial_name": null,
|
| 3113 |
+
"trial_params": null
|
| 3114 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1b36131cc0286c12218ef134fa6916b868c8a2171f01c50266afdff7f461fdf
|
| 3 |
+
size 9169
|
qwen3vl_8b_agentnetv1_fullsft_gb200/video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
qwen3vl_8b_agentnetv1_fullsft_gb200/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3vl_8b_agentnetv1_fullsft_gb200/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)
|