Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/added_tokens.json +28 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/args.json +388 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/chat_template.jinja +120 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/config.json +70 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/generation_config.json +13 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/latest +1 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/merges.txt +0 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/model-00001-of-00002.safetensors +3 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/model-00002-of-00002.safetensors +3 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/model.safetensors.index.json +722 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/preprocessor_config.json +21 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/special_tokens_map.json +31 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/tokenizer.json +3 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/tokenizer_config.json +240 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/trainer_state.json +2066 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/training_args.bin +3 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/video_preprocessor_config.json +41 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/vocab.json +0 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/zero_to_fp32.py +760 -0
.gitattributes
CHANGED
|
@@ -89,3 +89,4 @@ vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_h800/step-254/toke
|
|
| 89 |
qwen3-vl-4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384_ep2/step-7844/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 90 |
qwen3-vl-4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384_ep2/step-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 91 |
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hactfunc/step-254/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 89 |
qwen3-vl-4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384_ep2/step-7844/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 90 |
qwen3-vl-4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384_ep2/step-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 91 |
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hactfunc/step-254/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/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 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/args.json
ADDED
|
@@ -0,0 +1,388 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/apdcephfs_wzj/share_304937439/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/v0-20260205-180314",
|
| 3 |
+
"overwrite_output_dir": false,
|
| 4 |
+
"do_train": false,
|
| 5 |
+
"do_eval": false,
|
| 6 |
+
"do_predict": false,
|
| 7 |
+
"eval_strategy": "no",
|
| 8 |
+
"prediction_loss_only": false,
|
| 9 |
+
"per_device_train_batch_size": 1,
|
| 10 |
+
"per_device_eval_batch_size": 1,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 4,
|
| 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": "/apdcephfs_wzj/share_304937439/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/v0-20260205-180314/runs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 1,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 100.0,
|
| 39 |
+
"save_total_limit": null,
|
| 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": 10000.0,
|
| 64 |
+
"dataloader_num_workers": 8,
|
| 65 |
+
"dataloader_prefetch_factor": null,
|
| 66 |
+
"past_index": -1,
|
| 67 |
+
"run_name": "/apdcephfs_wzj/share_304937439/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/v0-20260205-180314",
|
| 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": 2,
|
| 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 |
+
"wandb"
|
| 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": "/apdcephfs_wzj/share_304937439/mclan/checkpoints/Qwen3-VL-4B-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": 65536,
|
| 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": "last_round+config@hermes",
|
| 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 |
+
"/apdcephfs_wzj/share_304937439/weixian/workspace/data_preprocess/qwen3-vl_Agentnet_traj_preprocess/rollout_train_l1.ws4.jsonl#24250",
|
| 234 |
+
"/apdcephfs_wzj/share_304937439/weixian/workspace/data_preprocess/qwen3-vl_Agentnet_traj_preprocess/rollout_train_l2.ws4.jsonl#24250"
|
| 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": 96,
|
| 379 |
+
"local_world_size": 8,
|
| 380 |
+
"model_suffix": "Qwen3-VL-4B-Instruct",
|
| 381 |
+
"model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/apdcephfs_wzj/share_304937439/mclan/checkpoints/Qwen3-VL-4B-Instruct', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
|
| 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 0x7fa30ea7fd80>, 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": "/apdcephfs_wzj/share_304937439/mclan/checkpoints/Qwen3-VL-4B-Instruct",
|
| 384 |
+
"_val_dataset_exists": [],
|
| 385 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 386 |
+
"evaluation_strategy": "steps",
|
| 387 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/apdcephfs_wzj/share_304937439/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/v0-20260205-180314', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=4, 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='/apdcephfs_wzj/share_304937439/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/v0-20260205-180314/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=100, save_total_limit=None, 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=10000.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/apdcephfs_wzj/share_304937439/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/v0-20260205-180314', 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': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, 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=['wandb'], 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 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/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 %}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_size": 2560,
|
| 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": 2560,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 9728,
|
| 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 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"use_cache": false,
|
| 41 |
+
"vocab_size": 151936
|
| 42 |
+
},
|
| 43 |
+
"tie_word_embeddings": true,
|
| 44 |
+
"transformers_version": "4.57.6",
|
| 45 |
+
"video_token_id": 151656,
|
| 46 |
+
"vision_config": {
|
| 47 |
+
"deepstack_visual_indexes": [
|
| 48 |
+
5,
|
| 49 |
+
11,
|
| 50 |
+
17
|
| 51 |
+
],
|
| 52 |
+
"depth": 24,
|
| 53 |
+
"dtype": "bfloat16",
|
| 54 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 55 |
+
"hidden_size": 1024,
|
| 56 |
+
"in_channels": 3,
|
| 57 |
+
"initializer_range": 0.02,
|
| 58 |
+
"intermediate_size": 4096,
|
| 59 |
+
"model_type": "qwen3_vl",
|
| 60 |
+
"num_heads": 16,
|
| 61 |
+
"num_position_embeddings": 2304,
|
| 62 |
+
"out_hidden_size": 2560,
|
| 63 |
+
"pad_token_id": 151643,
|
| 64 |
+
"patch_size": 16,
|
| 65 |
+
"spatial_merge_size": 2,
|
| 66 |
+
"temporal_patch_size": 2
|
| 67 |
+
},
|
| 68 |
+
"vision_end_token_id": 151653,
|
| 69 |
+
"vision_start_token_id": 151652
|
| 70 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/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": "4.57.6"
|
| 13 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step254
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96ecab7c948a7adcb38eb1c5c7a121b8954bf8afec63850887dfba9287bac6af
|
| 3 |
+
size 4990497880
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b81f4af4e6a1f23de0f25e3091f8f2dde5f713826612235193ebd4ed722630aa
|
| 3 |
+
size 4663133960
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,722 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4437815808,
|
| 4 |
+
"total_size": 9653543936
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
|
| 721 |
+
}
|
| 722 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/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 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/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 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/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 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/trainer_state.json
ADDED
|
@@ -0,0 +1,2066 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 10000.0,
|
| 7 |
+
"global_step": 254,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007920792079207921,
|
| 14 |
+
"grad_norm": 5.960568428039551,
|
| 15 |
+
"learning_rate": 7.692307692307694e-07,
|
| 16 |
+
"loss": 1.2558643817901611,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.7386546272756495
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.015841584158415842,
|
| 22 |
+
"grad_norm": 6.14252233505249,
|
| 23 |
+
"learning_rate": 1.5384615384615387e-06,
|
| 24 |
+
"loss": 1.2524197101593018,
|
| 25 |
+
"step": 2,
|
| 26 |
+
"token_acc": 0.7413778372682482
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.023762376237623763,
|
| 30 |
+
"grad_norm": 6.316536903381348,
|
| 31 |
+
"learning_rate": 2.307692307692308e-06,
|
| 32 |
+
"loss": 1.2424075603485107,
|
| 33 |
+
"step": 3,
|
| 34 |
+
"token_acc": 0.7407693850075907
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.031683168316831684,
|
| 38 |
+
"grad_norm": 5.770832538604736,
|
| 39 |
+
"learning_rate": 3.0769230769230774e-06,
|
| 40 |
+
"loss": 1.1299089193344116,
|
| 41 |
+
"step": 4,
|
| 42 |
+
"token_acc": 0.7453882333061087
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.039603960396039604,
|
| 46 |
+
"grad_norm": 3.327702045440674,
|
| 47 |
+
"learning_rate": 3.846153846153847e-06,
|
| 48 |
+
"loss": 0.9353134036064148,
|
| 49 |
+
"step": 5,
|
| 50 |
+
"token_acc": 0.7549944385861008
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.047524752475247525,
|
| 54 |
+
"grad_norm": 2.5832724571228027,
|
| 55 |
+
"learning_rate": 4.615384615384616e-06,
|
| 56 |
+
"loss": 0.8535332679748535,
|
| 57 |
+
"step": 6,
|
| 58 |
+
"token_acc": 0.7627749721818026
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.055445544554455446,
|
| 62 |
+
"grad_norm": 3.3800265789031982,
|
| 63 |
+
"learning_rate": 5.384615384615385e-06,
|
| 64 |
+
"loss": 0.8232876062393188,
|
| 65 |
+
"step": 7,
|
| 66 |
+
"token_acc": 0.7667698503335938
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06336633663366337,
|
| 70 |
+
"grad_norm": 1.811529517173767,
|
| 71 |
+
"learning_rate": 6.153846153846155e-06,
|
| 72 |
+
"loss": 0.7926408052444458,
|
| 73 |
+
"step": 8,
|
| 74 |
+
"token_acc": 0.7734015345268542
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.07128712871287128,
|
| 78 |
+
"grad_norm": 2.7483937740325928,
|
| 79 |
+
"learning_rate": 6.923076923076923e-06,
|
| 80 |
+
"loss": 0.8098694682121277,
|
| 81 |
+
"step": 9,
|
| 82 |
+
"token_acc": 0.7737813330252975
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.07920792079207921,
|
| 86 |
+
"grad_norm": 5.573540210723877,
|
| 87 |
+
"learning_rate": 7.692307692307694e-06,
|
| 88 |
+
"loss": 0.7738057971000671,
|
| 89 |
+
"step": 10,
|
| 90 |
+
"token_acc": 0.77996206496008
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.08712871287128712,
|
| 94 |
+
"grad_norm": 2.0974764823913574,
|
| 95 |
+
"learning_rate": 8.461538461538462e-06,
|
| 96 |
+
"loss": 0.7609673738479614,
|
| 97 |
+
"step": 11,
|
| 98 |
+
"token_acc": 0.777332538373012
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.09504950495049505,
|
| 102 |
+
"grad_norm": 1.4482393264770508,
|
| 103 |
+
"learning_rate": 9.230769230769232e-06,
|
| 104 |
+
"loss": 0.7127729654312134,
|
| 105 |
+
"step": 12,
|
| 106 |
+
"token_acc": 0.7884159731853907
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.10297029702970296,
|
| 110 |
+
"grad_norm": 1.5792897939682007,
|
| 111 |
+
"learning_rate": 1e-05,
|
| 112 |
+
"loss": 0.7032858729362488,
|
| 113 |
+
"step": 13,
|
| 114 |
+
"token_acc": 0.7914226194070406
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.11089108910891089,
|
| 118 |
+
"grad_norm": 2.3364925384521484,
|
| 119 |
+
"learning_rate": 9.999575185316994e-06,
|
| 120 |
+
"loss": 0.6996965408325195,
|
| 121 |
+
"step": 14,
|
| 122 |
+
"token_acc": 0.7945679465980771
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.1188118811881188,
|
| 126 |
+
"grad_norm": 1.8159290552139282,
|
| 127 |
+
"learning_rate": 9.998300813454981e-06,
|
| 128 |
+
"loss": 0.6904325485229492,
|
| 129 |
+
"step": 15,
|
| 130 |
+
"token_acc": 0.7913668045560152
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.12673267326732673,
|
| 134 |
+
"grad_norm": 1.3460859060287476,
|
| 135 |
+
"learning_rate": 9.996177100962714e-06,
|
| 136 |
+
"loss": 0.6715091466903687,
|
| 137 |
+
"step": 16,
|
| 138 |
+
"token_acc": 0.7991728137125315
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.13465346534653466,
|
| 142 |
+
"grad_norm": 1.55337655544281,
|
| 143 |
+
"learning_rate": 9.99320440871389e-06,
|
| 144 |
+
"loss": 0.6560345888137817,
|
| 145 |
+
"step": 17,
|
| 146 |
+
"token_acc": 0.8022841037535047
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.14257425742574256,
|
| 150 |
+
"grad_norm": 1.3816040754318237,
|
| 151 |
+
"learning_rate": 9.98938324184584e-06,
|
| 152 |
+
"loss": 0.6276627779006958,
|
| 153 |
+
"step": 18,
|
| 154 |
+
"token_acc": 0.8103071704075469
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.1504950495049505,
|
| 158 |
+
"grad_norm": 1.112221360206604,
|
| 159 |
+
"learning_rate": 9.984714249673676e-06,
|
| 160 |
+
"loss": 0.6257315278053284,
|
| 161 |
+
"step": 19,
|
| 162 |
+
"token_acc": 0.8093213285919649
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.15841584158415842,
|
| 166 |
+
"grad_norm": 1.7343868017196655,
|
| 167 |
+
"learning_rate": 9.979198225579968e-06,
|
| 168 |
+
"loss": 0.6175891160964966,
|
| 169 |
+
"step": 20,
|
| 170 |
+
"token_acc": 0.8109397407006351
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.16633663366336635,
|
| 174 |
+
"grad_norm": 1.431488037109375,
|
| 175 |
+
"learning_rate": 9.972836106879936e-06,
|
| 176 |
+
"loss": 0.6148459911346436,
|
| 177 |
+
"step": 21,
|
| 178 |
+
"token_acc": 0.8126391553358632
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.17425742574257425,
|
| 182 |
+
"grad_norm": 1.841714859008789,
|
| 183 |
+
"learning_rate": 9.965628974662145e-06,
|
| 184 |
+
"loss": 0.5987235903739929,
|
| 185 |
+
"step": 22,
|
| 186 |
+
"token_acc": 0.8183481560358145
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.18217821782178217,
|
| 190 |
+
"grad_norm": 1.3867981433868408,
|
| 191 |
+
"learning_rate": 9.957578053604837e-06,
|
| 192 |
+
"loss": 0.5920147895812988,
|
| 193 |
+
"step": 23,
|
| 194 |
+
"token_acc": 0.8203578898442947
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.1900990099009901,
|
| 198 |
+
"grad_norm": 2.757582664489746,
|
| 199 |
+
"learning_rate": 9.9486847117678e-06,
|
| 200 |
+
"loss": 0.6163027286529541,
|
| 201 |
+
"step": 24,
|
| 202 |
+
"token_acc": 0.8111146056967824
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.19801980198019803,
|
| 206 |
+
"grad_norm": 5.330894947052002,
|
| 207 |
+
"learning_rate": 9.938950460359912e-06,
|
| 208 |
+
"loss": 0.558630108833313,
|
| 209 |
+
"step": 25,
|
| 210 |
+
"token_acc": 0.8286211937420298
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.20594059405940593,
|
| 214 |
+
"grad_norm": 2.2089269161224365,
|
| 215 |
+
"learning_rate": 9.928376953482343e-06,
|
| 216 |
+
"loss": 0.5832911729812622,
|
| 217 |
+
"step": 26,
|
| 218 |
+
"token_acc": 0.821839169868853
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.21386138613861386,
|
| 222 |
+
"grad_norm": 1.8307454586029053,
|
| 223 |
+
"learning_rate": 9.916965987847485e-06,
|
| 224 |
+
"loss": 0.5874606966972351,
|
| 225 |
+
"step": 27,
|
| 226 |
+
"token_acc": 0.8193906138861067
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.22178217821782178,
|
| 230 |
+
"grad_norm": 1.5963761806488037,
|
| 231 |
+
"learning_rate": 9.904719502473635e-06,
|
| 232 |
+
"loss": 0.5765716433525085,
|
| 233 |
+
"step": 28,
|
| 234 |
+
"token_acc": 0.8225516815354337
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2297029702970297,
|
| 238 |
+
"grad_norm": 1.3358356952667236,
|
| 239 |
+
"learning_rate": 9.891639578355511e-06,
|
| 240 |
+
"loss": 0.5653841495513916,
|
| 241 |
+
"step": 29,
|
| 242 |
+
"token_acc": 0.8259562841530055
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.2376237623762376,
|
| 246 |
+
"grad_norm": 1.527860403060913,
|
| 247 |
+
"learning_rate": 9.877728438110645e-06,
|
| 248 |
+
"loss": 0.5407878756523132,
|
| 249 |
+
"step": 30,
|
| 250 |
+
"token_acc": 0.8330158002549815
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.24554455445544554,
|
| 254 |
+
"grad_norm": 1.4003489017486572,
|
| 255 |
+
"learning_rate": 9.86298844560169e-06,
|
| 256 |
+
"loss": 0.5771046876907349,
|
| 257 |
+
"step": 31,
|
| 258 |
+
"token_acc": 0.8241231021267882
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.25346534653465347,
|
| 262 |
+
"grad_norm": 2.6539056301116943,
|
| 263 |
+
"learning_rate": 9.847422105534739e-06,
|
| 264 |
+
"loss": 0.5552494525909424,
|
| 265 |
+
"step": 32,
|
| 266 |
+
"token_acc": 0.8297435042841868
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.2613861386138614,
|
| 270 |
+
"grad_norm": 20.025283813476562,
|
| 271 |
+
"learning_rate": 9.831032063033726e-06,
|
| 272 |
+
"loss": 0.5467867255210876,
|
| 273 |
+
"step": 33,
|
| 274 |
+
"token_acc": 0.8331711991636781
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.2693069306930693,
|
| 278 |
+
"grad_norm": 1.5512030124664307,
|
| 279 |
+
"learning_rate": 9.813821103190932e-06,
|
| 280 |
+
"loss": 0.5362657904624939,
|
| 281 |
+
"step": 34,
|
| 282 |
+
"token_acc": 0.8353897539920997
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.27722772277227725,
|
| 286 |
+
"grad_norm": 1.3089414834976196,
|
| 287 |
+
"learning_rate": 9.795792150593739e-06,
|
| 288 |
+
"loss": 0.5507494211196899,
|
| 289 |
+
"step": 35,
|
| 290 |
+
"token_acc": 0.8289508558037022
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.2851485148514851,
|
| 294 |
+
"grad_norm": 1.8894169330596924,
|
| 295 |
+
"learning_rate": 9.776948268827658e-06,
|
| 296 |
+
"loss": 0.5392261743545532,
|
| 297 |
+
"step": 36,
|
| 298 |
+
"token_acc": 0.834827125463526
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.29306930693069305,
|
| 302 |
+
"grad_norm": 1.2781617641448975,
|
| 303 |
+
"learning_rate": 9.757292659955755e-06,
|
| 304 |
+
"loss": 0.5375286340713501,
|
| 305 |
+
"step": 37,
|
| 306 |
+
"token_acc": 0.8332741351140158
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.300990099009901,
|
| 310 |
+
"grad_norm": 6.748410701751709,
|
| 311 |
+
"learning_rate": 9.736828663974527e-06,
|
| 312 |
+
"loss": 0.5679943561553955,
|
| 313 |
+
"step": 38,
|
| 314 |
+
"token_acc": 0.8265700880730924
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3089108910891089,
|
| 318 |
+
"grad_norm": 2.126310110092163,
|
| 319 |
+
"learning_rate": 9.715559758246363e-06,
|
| 320 |
+
"loss": 0.5328996181488037,
|
| 321 |
+
"step": 39,
|
| 322 |
+
"token_acc": 0.8369150674980326
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.31683168316831684,
|
| 326 |
+
"grad_norm": 2.2901999950408936,
|
| 327 |
+
"learning_rate": 9.693489556908641e-06,
|
| 328 |
+
"loss": 0.5465728044509888,
|
| 329 |
+
"step": 40,
|
| 330 |
+
"token_acc": 0.8328036874803172
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.32475247524752476,
|
| 334 |
+
"grad_norm": 1.3399120569229126,
|
| 335 |
+
"learning_rate": 9.670621810259596e-06,
|
| 336 |
+
"loss": 0.4948033094406128,
|
| 337 |
+
"step": 41,
|
| 338 |
+
"token_acc": 0.8450985462276619
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.3326732673267327,
|
| 342 |
+
"grad_norm": 0.8025302290916443,
|
| 343 |
+
"learning_rate": 9.646960404121042e-06,
|
| 344 |
+
"loss": 0.5127119421958923,
|
| 345 |
+
"step": 42,
|
| 346 |
+
"token_acc": 0.8409398217479173
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3405940594059406,
|
| 350 |
+
"grad_norm": 1.3023853302001953,
|
| 351 |
+
"learning_rate": 9.62250935917808e-06,
|
| 352 |
+
"loss": 0.5001162886619568,
|
| 353 |
+
"step": 43,
|
| 354 |
+
"token_acc": 0.8428799535491363
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.3485148514851485,
|
| 358 |
+
"grad_norm": 2.22157883644104,
|
| 359 |
+
"learning_rate": 9.597272830295877e-06,
|
| 360 |
+
"loss": 0.49750232696533203,
|
| 361 |
+
"step": 44,
|
| 362 |
+
"token_acc": 0.8461594160922203
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.3564356435643564,
|
| 366 |
+
"grad_norm": 1.6608836650848389,
|
| 367 |
+
"learning_rate": 9.571255105813632e-06,
|
| 368 |
+
"loss": 0.5338799357414246,
|
| 369 |
+
"step": 45,
|
| 370 |
+
"token_acc": 0.8335051682660534
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.36435643564356435,
|
| 374 |
+
"grad_norm": 1.5023269653320312,
|
| 375 |
+
"learning_rate": 9.544460606815901e-06,
|
| 376 |
+
"loss": 0.4970719814300537,
|
| 377 |
+
"step": 46,
|
| 378 |
+
"token_acc": 0.8455046866994184
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.3722772277227723,
|
| 382 |
+
"grad_norm": 1.8531087636947632,
|
| 383 |
+
"learning_rate": 9.516893886381324e-06,
|
| 384 |
+
"loss": 0.474180668592453,
|
| 385 |
+
"step": 47,
|
| 386 |
+
"token_acc": 0.8515375828870659
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.3801980198019802,
|
| 390 |
+
"grad_norm": 1.1473661661148071,
|
| 391 |
+
"learning_rate": 9.488559628808939e-06,
|
| 392 |
+
"loss": 0.4969606101512909,
|
| 393 |
+
"step": 48,
|
| 394 |
+
"token_acc": 0.8458665517489047
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.38811881188118813,
|
| 398 |
+
"grad_norm": 6.623279571533203,
|
| 399 |
+
"learning_rate": 9.459462648822209e-06,
|
| 400 |
+
"loss": 0.4908920228481293,
|
| 401 |
+
"step": 49,
|
| 402 |
+
"token_acc": 0.8464699024709261
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.39603960396039606,
|
| 406 |
+
"grad_norm": 1.2542166709899902,
|
| 407 |
+
"learning_rate": 9.429607890750863e-06,
|
| 408 |
+
"loss": 0.48166391253471375,
|
| 409 |
+
"step": 50,
|
| 410 |
+
"token_acc": 0.8489055840497002
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.403960396039604,
|
| 414 |
+
"grad_norm": 1.5071438550949097,
|
| 415 |
+
"learning_rate": 9.399000427690736e-06,
|
| 416 |
+
"loss": 0.46615561842918396,
|
| 417 |
+
"step": 51,
|
| 418 |
+
"token_acc": 0.8543085578916197
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.41188118811881186,
|
| 422 |
+
"grad_norm": 1.1024000644683838,
|
| 423 |
+
"learning_rate": 9.367645460641716e-06,
|
| 424 |
+
"loss": 0.45957133173942566,
|
| 425 |
+
"step": 52,
|
| 426 |
+
"token_acc": 0.8549688758696449
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.4198019801980198,
|
| 430 |
+
"grad_norm": 1.1873629093170166,
|
| 431 |
+
"learning_rate": 9.335548317623957e-06,
|
| 432 |
+
"loss": 0.4486757516860962,
|
| 433 |
+
"step": 53,
|
| 434 |
+
"token_acc": 0.8588329772130842
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.4277227722772277,
|
| 438 |
+
"grad_norm": 1.5009210109710693,
|
| 439 |
+
"learning_rate": 9.302714452772515e-06,
|
| 440 |
+
"loss": 0.4693172872066498,
|
| 441 |
+
"step": 54,
|
| 442 |
+
"token_acc": 0.8534068377095475
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.43564356435643564,
|
| 446 |
+
"grad_norm": 5.657164573669434,
|
| 447 |
+
"learning_rate": 9.269149445410545e-06,
|
| 448 |
+
"loss": 0.4662116467952728,
|
| 449 |
+
"step": 55,
|
| 450 |
+
"token_acc": 0.8526032315978456
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.44356435643564357,
|
| 454 |
+
"grad_norm": 1.5517561435699463,
|
| 455 |
+
"learning_rate": 9.234858999101232e-06,
|
| 456 |
+
"loss": 0.48375004529953003,
|
| 457 |
+
"step": 56,
|
| 458 |
+
"token_acc": 0.8503732554365466
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.4514851485148515,
|
| 462 |
+
"grad_norm": 1.8860888481140137,
|
| 463 |
+
"learning_rate": 9.199848940678607e-06,
|
| 464 |
+
"loss": 0.44309550523757935,
|
| 465 |
+
"step": 57,
|
| 466 |
+
"token_acc": 0.8621422630233203
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.4594059405940594,
|
| 470 |
+
"grad_norm": 1.5281152725219727,
|
| 471 |
+
"learning_rate": 9.164125219257419e-06,
|
| 472 |
+
"loss": 0.44173678755760193,
|
| 473 |
+
"step": 58,
|
| 474 |
+
"token_acc": 0.8598130841121495
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.46732673267326735,
|
| 478 |
+
"grad_norm": 1.4732654094696045,
|
| 479 |
+
"learning_rate": 9.127693905222223e-06,
|
| 480 |
+
"loss": 0.44947731494903564,
|
| 481 |
+
"step": 59,
|
| 482 |
+
"token_acc": 0.8610026932438466
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.4752475247524752,
|
| 486 |
+
"grad_norm": 1.2622164487838745,
|
| 487 |
+
"learning_rate": 9.09056118919587e-06,
|
| 488 |
+
"loss": 0.45059236884117126,
|
| 489 |
+
"step": 60,
|
| 490 |
+
"token_acc": 0.8593911324817841
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.48316831683168315,
|
| 494 |
+
"grad_norm": 2.948002576828003,
|
| 495 |
+
"learning_rate": 9.052733380987555e-06,
|
| 496 |
+
"loss": 0.4473412036895752,
|
| 497 |
+
"step": 61,
|
| 498 |
+
"token_acc": 0.8587826132952486
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.4910891089108911,
|
| 502 |
+
"grad_norm": 1.3104896545410156,
|
| 503 |
+
"learning_rate": 9.014216908520619e-06,
|
| 504 |
+
"loss": 0.44685980677604675,
|
| 505 |
+
"step": 62,
|
| 506 |
+
"token_acc": 0.8593717056715159
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.499009900990099,
|
| 510 |
+
"grad_norm": 1.4617886543273926,
|
| 511 |
+
"learning_rate": 8.975018316740278e-06,
|
| 512 |
+
"loss": 0.4381181001663208,
|
| 513 |
+
"step": 63,
|
| 514 |
+
"token_acc": 0.8622589904679376
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5069306930693069,
|
| 518 |
+
"grad_norm": 1.521251916885376,
|
| 519 |
+
"learning_rate": 8.93514426650147e-06,
|
| 520 |
+
"loss": 0.4409676790237427,
|
| 521 |
+
"step": 64,
|
| 522 |
+
"token_acc": 0.8632225918169001
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.5148514851485149,
|
| 526 |
+
"grad_norm": 1.4733784198760986,
|
| 527 |
+
"learning_rate": 8.894601533437e-06,
|
| 528 |
+
"loss": 0.43711358308792114,
|
| 529 |
+
"step": 65,
|
| 530 |
+
"token_acc": 0.8639908720644732
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.5227722772277228,
|
| 534 |
+
"grad_norm": 1.0516679286956787,
|
| 535 |
+
"learning_rate": 8.853397006806183e-06,
|
| 536 |
+
"loss": 0.41722390055656433,
|
| 537 |
+
"step": 66,
|
| 538 |
+
"token_acc": 0.869306676553632
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.5306930693069307,
|
| 542 |
+
"grad_norm": 1.4391487836837769,
|
| 543 |
+
"learning_rate": 8.811537688324187e-06,
|
| 544 |
+
"loss": 0.4030117988586426,
|
| 545 |
+
"step": 67,
|
| 546 |
+
"token_acc": 0.8744586791771923
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.5386138613861386,
|
| 550 |
+
"grad_norm": 1.7863852977752686,
|
| 551 |
+
"learning_rate": 8.769030690972262e-06,
|
| 552 |
+
"loss": 0.4123440682888031,
|
| 553 |
+
"step": 68,
|
| 554 |
+
"token_acc": 0.8683172376737412
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.5465346534653466,
|
| 558 |
+
"grad_norm": 1.0948330163955688,
|
| 559 |
+
"learning_rate": 8.725883237789046e-06,
|
| 560 |
+
"loss": 0.4182654321193695,
|
| 561 |
+
"step": 69,
|
| 562 |
+
"token_acc": 0.8694254835039817
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.5544554455445545,
|
| 566 |
+
"grad_norm": 1.2923771142959595,
|
| 567 |
+
"learning_rate": 8.682102660643196e-06,
|
| 568 |
+
"loss": 0.415341854095459,
|
| 569 |
+
"step": 70,
|
| 570 |
+
"token_acc": 0.8695776828464119
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5623762376237624,
|
| 574 |
+
"grad_norm": 1.5113823413848877,
|
| 575 |
+
"learning_rate": 8.637696398987517e-06,
|
| 576 |
+
"loss": 0.4067484736442566,
|
| 577 |
+
"step": 71,
|
| 578 |
+
"token_acc": 0.8721385499128347
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.5702970297029702,
|
| 582 |
+
"grad_norm": 1.514534831047058,
|
| 583 |
+
"learning_rate": 8.592671998594794e-06,
|
| 584 |
+
"loss": 0.40408486127853394,
|
| 585 |
+
"step": 72,
|
| 586 |
+
"token_acc": 0.8719885915407488
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.5782178217821782,
|
| 590 |
+
"grad_norm": 1.318404197692871,
|
| 591 |
+
"learning_rate": 8.54703711027558e-06,
|
| 592 |
+
"loss": 0.39713895320892334,
|
| 593 |
+
"step": 73,
|
| 594 |
+
"token_acc": 0.8755292801789566
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.5861386138613861,
|
| 598 |
+
"grad_norm": 4.664387226104736,
|
| 599 |
+
"learning_rate": 8.50079948857812e-06,
|
| 600 |
+
"loss": 0.4010247588157654,
|
| 601 |
+
"step": 74,
|
| 602 |
+
"token_acc": 0.8738483119201709
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.594059405940594,
|
| 606 |
+
"grad_norm": 1.237453818321228,
|
| 607 |
+
"learning_rate": 8.453966990470656e-06,
|
| 608 |
+
"loss": 0.40040701627731323,
|
| 609 |
+
"step": 75,
|
| 610 |
+
"token_acc": 0.8726851851851852
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.601980198019802,
|
| 614 |
+
"grad_norm": 1.709481120109558,
|
| 615 |
+
"learning_rate": 8.406547574006326e-06,
|
| 616 |
+
"loss": 0.40477174520492554,
|
| 617 |
+
"step": 76,
|
| 618 |
+
"token_acc": 0.872207928897205
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.6099009900990099,
|
| 622 |
+
"grad_norm": 1.2701815366744995,
|
| 623 |
+
"learning_rate": 8.358549296970877e-06,
|
| 624 |
+
"loss": 0.3868257701396942,
|
| 625 |
+
"step": 77,
|
| 626 |
+
"token_acc": 0.876107152033103
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.6178217821782178,
|
| 630 |
+
"grad_norm": 2.213597059249878,
|
| 631 |
+
"learning_rate": 8.309980315513444e-06,
|
| 632 |
+
"loss": 0.3782214820384979,
|
| 633 |
+
"step": 78,
|
| 634 |
+
"token_acc": 0.8794976987663035
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.6257425742574257,
|
| 638 |
+
"grad_norm": 1.2918709516525269,
|
| 639 |
+
"learning_rate": 8.260848882760616e-06,
|
| 640 |
+
"loss": 0.39098963141441345,
|
| 641 |
+
"step": 79,
|
| 642 |
+
"token_acc": 0.8769130668477184
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.6336633663366337,
|
| 646 |
+
"grad_norm": 0.9354566931724548,
|
| 647 |
+
"learning_rate": 8.211163347414005e-06,
|
| 648 |
+
"loss": 0.3714665174484253,
|
| 649 |
+
"step": 80,
|
| 650 |
+
"token_acc": 0.8821628058635061
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.6415841584158416,
|
| 654 |
+
"grad_norm": 0.9066284894943237,
|
| 655 |
+
"learning_rate": 8.160932152331587e-06,
|
| 656 |
+
"loss": 0.35299476981163025,
|
| 657 |
+
"step": 81,
|
| 658 |
+
"token_acc": 0.8869762140880093
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.6495049504950495,
|
| 662 |
+
"grad_norm": 1.408962607383728,
|
| 663 |
+
"learning_rate": 8.11016383309305e-06,
|
| 664 |
+
"loss": 0.37095969915390015,
|
| 665 |
+
"step": 82,
|
| 666 |
+
"token_acc": 0.8819219167947185
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.6574257425742575,
|
| 670 |
+
"grad_norm": 1.824783444404602,
|
| 671 |
+
"learning_rate": 8.058867016549372e-06,
|
| 672 |
+
"loss": 0.36718663573265076,
|
| 673 |
+
"step": 83,
|
| 674 |
+
"token_acc": 0.8850464157157638
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6653465346534654,
|
| 678 |
+
"grad_norm": 1.1574032306671143,
|
| 679 |
+
"learning_rate": 8.007050419356898e-06,
|
| 680 |
+
"loss": 0.3503732681274414,
|
| 681 |
+
"step": 84,
|
| 682 |
+
"token_acc": 0.8894026568665844
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.6732673267326733,
|
| 686 |
+
"grad_norm": 0.7640724182128906,
|
| 687 |
+
"learning_rate": 7.95472284649615e-06,
|
| 688 |
+
"loss": 0.29962730407714844,
|
| 689 |
+
"step": 85,
|
| 690 |
+
"token_acc": 0.903403793540893
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.6811881188118812,
|
| 694 |
+
"grad_norm": 1.5607885122299194,
|
| 695 |
+
"learning_rate": 7.90189318977564e-06,
|
| 696 |
+
"loss": 0.36279821395874023,
|
| 697 |
+
"step": 86,
|
| 698 |
+
"token_acc": 0.8843451847292289
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.689108910891089,
|
| 702 |
+
"grad_norm": 1.2023508548736572,
|
| 703 |
+
"learning_rate": 7.848570426320918e-06,
|
| 704 |
+
"loss": 0.3537951409816742,
|
| 705 |
+
"step": 87,
|
| 706 |
+
"token_acc": 0.8888186169524658
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.697029702970297,
|
| 710 |
+
"grad_norm": 1.155798316001892,
|
| 711 |
+
"learning_rate": 7.794763617049124e-06,
|
| 712 |
+
"loss": 0.3468039929866791,
|
| 713 |
+
"step": 88,
|
| 714 |
+
"token_acc": 0.8892519346517627
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.7049504950495049,
|
| 718 |
+
"grad_norm": 0.999951958656311,
|
| 719 |
+
"learning_rate": 7.740481905129307e-06,
|
| 720 |
+
"loss": 0.3418969511985779,
|
| 721 |
+
"step": 89,
|
| 722 |
+
"token_acc": 0.8911494825716044
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.7128712871287128,
|
| 726 |
+
"grad_norm": 0.9334421753883362,
|
| 727 |
+
"learning_rate": 7.685734514428767e-06,
|
| 728 |
+
"loss": 0.32303059101104736,
|
| 729 |
+
"step": 90,
|
| 730 |
+
"token_acc": 0.8964737154653168
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.7207920792079208,
|
| 734 |
+
"grad_norm": 0.8004977107048035,
|
| 735 |
+
"learning_rate": 7.630530747945672e-06,
|
| 736 |
+
"loss": 0.3548615872859955,
|
| 737 |
+
"step": 91,
|
| 738 |
+
"token_acc": 0.8876648891383665
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7287128712871287,
|
| 742 |
+
"grad_norm": 0.90343177318573,
|
| 743 |
+
"learning_rate": 7.574879986228245e-06,
|
| 744 |
+
"loss": 0.33844494819641113,
|
| 745 |
+
"step": 92,
|
| 746 |
+
"token_acc": 0.8911179625797188
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.7366336633663366,
|
| 750 |
+
"grad_norm": 0.8163031935691833,
|
| 751 |
+
"learning_rate": 7.518791685780769e-06,
|
| 752 |
+
"loss": 0.34940439462661743,
|
| 753 |
+
"step": 93,
|
| 754 |
+
"token_acc": 0.8894498307612874
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.7445544554455445,
|
| 758 |
+
"grad_norm": 0.750158429145813,
|
| 759 |
+
"learning_rate": 7.462275377456671e-06,
|
| 760 |
+
"loss": 0.3375096917152405,
|
| 761 |
+
"step": 94,
|
| 762 |
+
"token_acc": 0.8929643707571029
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.7524752475247525,
|
| 766 |
+
"grad_norm": 0.9101679921150208,
|
| 767 |
+
"learning_rate": 7.405340664838994e-06,
|
| 768 |
+
"loss": 0.3067246377468109,
|
| 769 |
+
"step": 95,
|
| 770 |
+
"token_acc": 0.9026260133944307
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.7603960396039604,
|
| 774 |
+
"grad_norm": 0.8767592906951904,
|
| 775 |
+
"learning_rate": 7.3479972226084925e-06,
|
| 776 |
+
"loss": 0.29967474937438965,
|
| 777 |
+
"step": 96,
|
| 778 |
+
"token_acc": 0.9035729919845427
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.7683168316831683,
|
| 782 |
+
"grad_norm": 0.6261852383613586,
|
| 783 |
+
"learning_rate": 7.290254794899665e-06,
|
| 784 |
+
"loss": 0.32232388854026794,
|
| 785 |
+
"step": 97,
|
| 786 |
+
"token_acc": 0.8971666135527421
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7762376237623763,
|
| 790 |
+
"grad_norm": 1.7380542755126953,
|
| 791 |
+
"learning_rate": 7.232123193644957e-06,
|
| 792 |
+
"loss": 0.2845991551876068,
|
| 793 |
+
"step": 98,
|
| 794 |
+
"token_acc": 0.9085841363973314
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.7841584158415842,
|
| 798 |
+
"grad_norm": 0.8367014527320862,
|
| 799 |
+
"learning_rate": 7.173612296907473e-06,
|
| 800 |
+
"loss": 0.3244517147541046,
|
| 801 |
+
"step": 99,
|
| 802 |
+
"token_acc": 0.8966588527692264
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.7920792079207921,
|
| 806 |
+
"grad_norm": 0.6920971274375916,
|
| 807 |
+
"learning_rate": 7.114732047202433e-06,
|
| 808 |
+
"loss": 0.32402101159095764,
|
| 809 |
+
"step": 100,
|
| 810 |
+
"token_acc": 0.8972666219896482
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.8,
|
| 814 |
+
"grad_norm": 0.7598916888237,
|
| 815 |
+
"learning_rate": 7.055492449807684e-06,
|
| 816 |
+
"loss": 0.30883947014808655,
|
| 817 |
+
"step": 101,
|
| 818 |
+
"token_acc": 0.9022454202391452
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.807920792079208,
|
| 822 |
+
"grad_norm": 0.7116982936859131,
|
| 823 |
+
"learning_rate": 6.995903571063541e-06,
|
| 824 |
+
"loss": 0.34429144859313965,
|
| 825 |
+
"step": 102,
|
| 826 |
+
"token_acc": 0.8886749799460366
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.8158415841584158,
|
| 830 |
+
"grad_norm": 0.7116209268569946,
|
| 831 |
+
"learning_rate": 6.935975536662254e-06,
|
| 832 |
+
"loss": 0.3111732006072998,
|
| 833 |
+
"step": 103,
|
| 834 |
+
"token_acc": 0.9011823697835536
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.8237623762376237,
|
| 838 |
+
"grad_norm": 0.6527470946311951,
|
| 839 |
+
"learning_rate": 6.875718529927404e-06,
|
| 840 |
+
"loss": 0.29423317313194275,
|
| 841 |
+
"step": 104,
|
| 842 |
+
"token_acc": 0.9066821143226855
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.8316831683168316,
|
| 846 |
+
"grad_norm": 0.9359377026557922,
|
| 847 |
+
"learning_rate": 6.815142790083473e-06,
|
| 848 |
+
"loss": 0.32366448640823364,
|
| 849 |
+
"step": 105,
|
| 850 |
+
"token_acc": 0.8962439239946973
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.8396039603960396,
|
| 854 |
+
"grad_norm": 0.8654837012290955,
|
| 855 |
+
"learning_rate": 6.754258610515949e-06,
|
| 856 |
+
"loss": 0.32372117042541504,
|
| 857 |
+
"step": 106,
|
| 858 |
+
"token_acc": 0.8958815627768727
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.8475247524752475,
|
| 862 |
+
"grad_norm": 0.5636533498764038,
|
| 863 |
+
"learning_rate": 6.6930763370222104e-06,
|
| 864 |
+
"loss": 0.30436110496520996,
|
| 865 |
+
"step": 107,
|
| 866 |
+
"token_acc": 0.9025933813645083
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.8554455445544554,
|
| 870 |
+
"grad_norm": 0.6814311742782593,
|
| 871 |
+
"learning_rate": 6.631606366053507e-06,
|
| 872 |
+
"loss": 0.29518792033195496,
|
| 873 |
+
"step": 108,
|
| 874 |
+
"token_acc": 0.9051456354387071
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.8633663366336634,
|
| 878 |
+
"grad_norm": 0.738795280456543,
|
| 879 |
+
"learning_rate": 6.5698591429483286e-06,
|
| 880 |
+
"loss": 0.30844032764434814,
|
| 881 |
+
"step": 109,
|
| 882 |
+
"token_acc": 0.9014858159079827
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.8712871287128713,
|
| 886 |
+
"grad_norm": 0.7482790350914001,
|
| 887 |
+
"learning_rate": 6.507845160157476e-06,
|
| 888 |
+
"loss": 0.29798924922943115,
|
| 889 |
+
"step": 110,
|
| 890 |
+
"token_acc": 0.9047746894826831
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.8792079207920792,
|
| 894 |
+
"grad_norm": 0.6508976817131042,
|
| 895 |
+
"learning_rate": 6.445574955461134e-06,
|
| 896 |
+
"loss": 0.2793390154838562,
|
| 897 |
+
"step": 111,
|
| 898 |
+
"token_acc": 0.9102146945178815
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.8871287128712871,
|
| 902 |
+
"grad_norm": 1.243903398513794,
|
| 903 |
+
"learning_rate": 6.383059110178205e-06,
|
| 904 |
+
"loss": 0.2904765009880066,
|
| 905 |
+
"step": 112,
|
| 906 |
+
"token_acc": 0.9068011510955353
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.8950495049504951,
|
| 910 |
+
"grad_norm": 1.5983164310455322,
|
| 911 |
+
"learning_rate": 6.320308247368285e-06,
|
| 912 |
+
"loss": 0.28193169832229614,
|
| 913 |
+
"step": 113,
|
| 914 |
+
"token_acc": 0.9090690265486726
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.902970297029703,
|
| 918 |
+
"grad_norm": 0.5773327946662903,
|
| 919 |
+
"learning_rate": 6.2573330300265375e-06,
|
| 920 |
+
"loss": 0.26436686515808105,
|
| 921 |
+
"step": 114,
|
| 922 |
+
"token_acc": 0.9147169478572689
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.9108910891089109,
|
| 926 |
+
"grad_norm": 0.7900571227073669,
|
| 927 |
+
"learning_rate": 6.1941441592717564e-06,
|
| 928 |
+
"loss": 0.2797958254814148,
|
| 929 |
+
"step": 115,
|
| 930 |
+
"token_acc": 0.9092729851029926
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.9188118811881189,
|
| 934 |
+
"grad_norm": 0.8661277890205383,
|
| 935 |
+
"learning_rate": 6.130752372527981e-06,
|
| 936 |
+
"loss": 0.3126858174800873,
|
| 937 |
+
"step": 116,
|
| 938 |
+
"token_acc": 0.9007685352622061
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.9267326732673268,
|
| 942 |
+
"grad_norm": 0.6899728775024414,
|
| 943 |
+
"learning_rate": 6.067168441699927e-06,
|
| 944 |
+
"loss": 0.2807978093624115,
|
| 945 |
+
"step": 117,
|
| 946 |
+
"token_acc": 0.909438218086981
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.9346534653465347,
|
| 950 |
+
"grad_norm": 0.6866120100021362,
|
| 951 |
+
"learning_rate": 6.0034031713425636e-06,
|
| 952 |
+
"loss": 0.2751157879829407,
|
| 953 |
+
"step": 118,
|
| 954 |
+
"token_acc": 0.9142034235491485
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.9425742574257425,
|
| 958 |
+
"grad_norm": 0.5951712727546692,
|
| 959 |
+
"learning_rate": 5.939467396825137e-06,
|
| 960 |
+
"loss": 0.250967800617218,
|
| 961 |
+
"step": 119,
|
| 962 |
+
"token_acc": 0.91848387292717
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.9504950495049505,
|
| 966 |
+
"grad_norm": 0.6632791757583618,
|
| 967 |
+
"learning_rate": 5.875371982489959e-06,
|
| 968 |
+
"loss": 0.2624204158782959,
|
| 969 |
+
"step": 120,
|
| 970 |
+
"token_acc": 0.9153584744713344
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.9584158415841584,
|
| 974 |
+
"grad_norm": 0.6091061234474182,
|
| 975 |
+
"learning_rate": 5.811127819806277e-06,
|
| 976 |
+
"loss": 0.2638539671897888,
|
| 977 |
+
"step": 121,
|
| 978 |
+
"token_acc": 0.9172968344049813
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.9663366336633663,
|
| 982 |
+
"grad_norm": 0.8761502504348755,
|
| 983 |
+
"learning_rate": 5.746745825519539e-06,
|
| 984 |
+
"loss": 0.2673248052597046,
|
| 985 |
+
"step": 122,
|
| 986 |
+
"token_acc": 0.9151488099523405
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.9742574257425742,
|
| 990 |
+
"grad_norm": 0.5463993549346924,
|
| 991 |
+
"learning_rate": 5.682236939796337e-06,
|
| 992 |
+
"loss": 0.26560917496681213,
|
| 993 |
+
"step": 123,
|
| 994 |
+
"token_acc": 0.9139921066348946
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.9821782178217822,
|
| 998 |
+
"grad_norm": 0.7903063297271729,
|
| 999 |
+
"learning_rate": 5.617612124365411e-06,
|
| 1000 |
+
"loss": 0.26465660333633423,
|
| 1001 |
+
"step": 124,
|
| 1002 |
+
"token_acc": 0.9153518449134784
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.9900990099009901,
|
| 1006 |
+
"grad_norm": 0.5582003593444824,
|
| 1007 |
+
"learning_rate": 5.55288236065495e-06,
|
| 1008 |
+
"loss": 0.2597087025642395,
|
| 1009 |
+
"step": 125,
|
| 1010 |
+
"token_acc": 0.917374494319963
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.998019801980198,
|
| 1014 |
+
"grad_norm": 0.6030694246292114,
|
| 1015 |
+
"learning_rate": 5.4880586479265774e-06,
|
| 1016 |
+
"loss": 0.24883608520030975,
|
| 1017 |
+
"step": 126,
|
| 1018 |
+
"token_acc": 0.9199949319330452
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.0,
|
| 1022 |
+
"grad_norm": 10.117758750915527,
|
| 1023 |
+
"learning_rate": 5.423152001406282e-06,
|
| 1024 |
+
"loss": 0.25060826539993286,
|
| 1025 |
+
"step": 127,
|
| 1026 |
+
"token_acc": 0.918856002660459
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.007920792079208,
|
| 1030 |
+
"grad_norm": 1.1302499771118164,
|
| 1031 |
+
"learning_rate": 5.358173450412649e-06,
|
| 1032 |
+
"loss": 0.23308783769607544,
|
| 1033 |
+
"step": 128,
|
| 1034 |
+
"token_acc": 0.9244967917728751
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.0158415841584159,
|
| 1038 |
+
"grad_norm": 0.8070893883705139,
|
| 1039 |
+
"learning_rate": 5.293134036482697e-06,
|
| 1040 |
+
"loss": 0.2316235601902008,
|
| 1041 |
+
"step": 129,
|
| 1042 |
+
"token_acc": 0.9244842406876791
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.0237623762376238,
|
| 1046 |
+
"grad_norm": 0.7636346220970154,
|
| 1047 |
+
"learning_rate": 5.228044811495632e-06,
|
| 1048 |
+
"loss": 0.20030717551708221,
|
| 1049 |
+
"step": 130,
|
| 1050 |
+
"token_acc": 0.9340715266104282
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.0316831683168317,
|
| 1054 |
+
"grad_norm": 0.5981131196022034,
|
| 1055 |
+
"learning_rate": 5.162916835794843e-06,
|
| 1056 |
+
"loss": 0.20466125011444092,
|
| 1057 |
+
"step": 131,
|
| 1058 |
+
"token_acc": 0.9346894617716979
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.0396039603960396,
|
| 1062 |
+
"grad_norm": 9.42473316192627,
|
| 1063 |
+
"learning_rate": 5.097761176308471e-06,
|
| 1064 |
+
"loss": 0.21566234529018402,
|
| 1065 |
+
"step": 132,
|
| 1066 |
+
"token_acc": 0.9316123393161234
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.0475247524752476,
|
| 1070 |
+
"grad_norm": 0.7520480751991272,
|
| 1071 |
+
"learning_rate": 5.032588904668851e-06,
|
| 1072 |
+
"loss": 0.229787677526474,
|
| 1073 |
+
"step": 133,
|
| 1074 |
+
"token_acc": 0.9270069998906267
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.0554455445544555,
|
| 1078 |
+
"grad_norm": 0.6280667185783386,
|
| 1079 |
+
"learning_rate": 4.967411095331149e-06,
|
| 1080 |
+
"loss": 0.21739636361598969,
|
| 1081 |
+
"step": 134,
|
| 1082 |
+
"token_acc": 0.9297372100322424
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 1.0633663366336634,
|
| 1086 |
+
"grad_norm": 0.8191630840301514,
|
| 1087 |
+
"learning_rate": 4.9022388236915306e-06,
|
| 1088 |
+
"loss": 0.21421432495117188,
|
| 1089 |
+
"step": 135,
|
| 1090 |
+
"token_acc": 0.9307117565396434
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.0712871287128714,
|
| 1094 |
+
"grad_norm": 0.7555252909660339,
|
| 1095 |
+
"learning_rate": 4.837083164205159e-06,
|
| 1096 |
+
"loss": 0.2009151428937912,
|
| 1097 |
+
"step": 136,
|
| 1098 |
+
"token_acc": 0.9351036890014373
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.0792079207920793,
|
| 1102 |
+
"grad_norm": 0.5066846609115601,
|
| 1103 |
+
"learning_rate": 4.771955188504371e-06,
|
| 1104 |
+
"loss": 0.19109581410884857,
|
| 1105 |
+
"step": 137,
|
| 1106 |
+
"token_acc": 0.9368649273686492
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.0871287128712872,
|
| 1110 |
+
"grad_norm": 0.5917500257492065,
|
| 1111 |
+
"learning_rate": 4.7068659635173034e-06,
|
| 1112 |
+
"loss": 0.21460139751434326,
|
| 1113 |
+
"step": 138,
|
| 1114 |
+
"token_acc": 0.9313176239148099
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.0950495049504951,
|
| 1118 |
+
"grad_norm": 0.6032508611679077,
|
| 1119 |
+
"learning_rate": 4.641826549587352e-06,
|
| 1120 |
+
"loss": 0.1933349072933197,
|
| 1121 |
+
"step": 139,
|
| 1122 |
+
"token_acc": 0.9372593902819686
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.102970297029703,
|
| 1126 |
+
"grad_norm": 0.5786173343658447,
|
| 1127 |
+
"learning_rate": 4.57684799859372e-06,
|
| 1128 |
+
"loss": 0.18810829520225525,
|
| 1129 |
+
"step": 140,
|
| 1130 |
+
"token_acc": 0.9387748948423766
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.110891089108911,
|
| 1134 |
+
"grad_norm": 0.4901808798313141,
|
| 1135 |
+
"learning_rate": 4.511941352073424e-06,
|
| 1136 |
+
"loss": 0.22162280976772308,
|
| 1137 |
+
"step": 141,
|
| 1138 |
+
"token_acc": 0.9282359081419624
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.118811881188119,
|
| 1142 |
+
"grad_norm": 0.5518633127212524,
|
| 1143 |
+
"learning_rate": 4.447117639345052e-06,
|
| 1144 |
+
"loss": 0.19585859775543213,
|
| 1145 |
+
"step": 142,
|
| 1146 |
+
"token_acc": 0.9376085524345691
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.1267326732673268,
|
| 1150 |
+
"grad_norm": 0.5814948081970215,
|
| 1151 |
+
"learning_rate": 4.382387875634592e-06,
|
| 1152 |
+
"loss": 0.20231780409812927,
|
| 1153 |
+
"step": 143,
|
| 1154 |
+
"token_acc": 0.9355734598527476
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.1346534653465348,
|
| 1158 |
+
"grad_norm": 0.5113416910171509,
|
| 1159 |
+
"learning_rate": 4.317763060203665e-06,
|
| 1160 |
+
"loss": 0.1921614110469818,
|
| 1161 |
+
"step": 144,
|
| 1162 |
+
"token_acc": 0.9382995059904096
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.1425742574257425,
|
| 1166 |
+
"grad_norm": 0.5202580094337463,
|
| 1167 |
+
"learning_rate": 4.253254174480462e-06,
|
| 1168 |
+
"loss": 0.1873549073934555,
|
| 1169 |
+
"step": 145,
|
| 1170 |
+
"token_acc": 0.9390001188212928
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.1504950495049504,
|
| 1174 |
+
"grad_norm": 0.7925094366073608,
|
| 1175 |
+
"learning_rate": 4.188872180193723e-06,
|
| 1176 |
+
"loss": 0.18910908699035645,
|
| 1177 |
+
"step": 146,
|
| 1178 |
+
"token_acc": 0.9402803751074953
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.1584158415841583,
|
| 1182 |
+
"grad_norm": 0.5719192624092102,
|
| 1183 |
+
"learning_rate": 4.124628017510043e-06,
|
| 1184 |
+
"loss": 0.19358497858047485,
|
| 1185 |
+
"step": 147,
|
| 1186 |
+
"token_acc": 0.9383788072464407
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.1663366336633663,
|
| 1190 |
+
"grad_norm": 0.46902480721473694,
|
| 1191 |
+
"learning_rate": 4.060532603174865e-06,
|
| 1192 |
+
"loss": 0.16876821219921112,
|
| 1193 |
+
"step": 148,
|
| 1194 |
+
"token_acc": 0.945307392996109
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.1742574257425742,
|
| 1198 |
+
"grad_norm": 0.5391806960105896,
|
| 1199 |
+
"learning_rate": 3.996596828657437e-06,
|
| 1200 |
+
"loss": 0.1931639313697815,
|
| 1201 |
+
"step": 149,
|
| 1202 |
+
"token_acc": 0.9369311473449806
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.1821782178217821,
|
| 1206 |
+
"grad_norm": 0.5993138551712036,
|
| 1207 |
+
"learning_rate": 3.932831558300074e-06,
|
| 1208 |
+
"loss": 0.19623082876205444,
|
| 1209 |
+
"step": 150,
|
| 1210 |
+
"token_acc": 0.9373652145783912
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.19009900990099,
|
| 1214 |
+
"grad_norm": 0.5345911979675293,
|
| 1215 |
+
"learning_rate": 3.869247627472021e-06,
|
| 1216 |
+
"loss": 0.17675134539604187,
|
| 1217 |
+
"step": 151,
|
| 1218 |
+
"token_acc": 0.9421671340763452
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.198019801980198,
|
| 1222 |
+
"grad_norm": 0.6444203853607178,
|
| 1223 |
+
"learning_rate": 3.8058558407282465e-06,
|
| 1224 |
+
"loss": 0.17611345648765564,
|
| 1225 |
+
"step": 152,
|
| 1226 |
+
"token_acc": 0.9430135903696073
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.205940594059406,
|
| 1230 |
+
"grad_norm": 0.6985074877738953,
|
| 1231 |
+
"learning_rate": 3.742666969973463e-06,
|
| 1232 |
+
"loss": 0.1692647784948349,
|
| 1233 |
+
"step": 153,
|
| 1234 |
+
"token_acc": 0.9448539256169229
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.2138613861386138,
|
| 1238 |
+
"grad_norm": 0.5238531231880188,
|
| 1239 |
+
"learning_rate": 3.6796917526317153e-06,
|
| 1240 |
+
"loss": 0.15838640928268433,
|
| 1241 |
+
"step": 154,
|
| 1242 |
+
"token_acc": 0.9486795280014985
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.2217821782178218,
|
| 1246 |
+
"grad_norm": 0.5229592323303223,
|
| 1247 |
+
"learning_rate": 3.6169408898217973e-06,
|
| 1248 |
+
"loss": 0.18458889424800873,
|
| 1249 |
+
"step": 155,
|
| 1250 |
+
"token_acc": 0.9419533423306801
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.2297029702970297,
|
| 1254 |
+
"grad_norm": 0.5905978679656982,
|
| 1255 |
+
"learning_rate": 3.554425044538868e-06,
|
| 1256 |
+
"loss": 0.18788447976112366,
|
| 1257 |
+
"step": 156,
|
| 1258 |
+
"token_acc": 0.9408686551543695
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 1.2376237623762376,
|
| 1262 |
+
"grad_norm": 0.6504817605018616,
|
| 1263 |
+
"learning_rate": 3.4921548398425246e-06,
|
| 1264 |
+
"loss": 0.1664404571056366,
|
| 1265 |
+
"step": 157,
|
| 1266 |
+
"token_acc": 0.9465228840863283
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.2455445544554455,
|
| 1270 |
+
"grad_norm": 0.7393201589584351,
|
| 1271 |
+
"learning_rate": 3.430140857051675e-06,
|
| 1272 |
+
"loss": 0.14970415830612183,
|
| 1273 |
+
"step": 158,
|
| 1274 |
+
"token_acc": 0.9510341223026955
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.2534653465346535,
|
| 1278 |
+
"grad_norm": 0.5273522138595581,
|
| 1279 |
+
"learning_rate": 3.3683936339464957e-06,
|
| 1280 |
+
"loss": 0.16940216720104218,
|
| 1281 |
+
"step": 159,
|
| 1282 |
+
"token_acc": 0.9463269066806018
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.2613861386138614,
|
| 1286 |
+
"grad_norm": 0.665668785572052,
|
| 1287 |
+
"learning_rate": 3.306923662977789e-06,
|
| 1288 |
+
"loss": 0.17547041177749634,
|
| 1289 |
+
"step": 160,
|
| 1290 |
+
"token_acc": 0.9447421806400823
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.2693069306930693,
|
| 1294 |
+
"grad_norm": 0.600463330745697,
|
| 1295 |
+
"learning_rate": 3.2457413894840516e-06,
|
| 1296 |
+
"loss": 0.1802273392677307,
|
| 1297 |
+
"step": 161,
|
| 1298 |
+
"token_acc": 0.9430067541929119
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.2772277227722773,
|
| 1302 |
+
"grad_norm": 0.5325738191604614,
|
| 1303 |
+
"learning_rate": 3.184857209916528e-06,
|
| 1304 |
+
"loss": 0.15212231874465942,
|
| 1305 |
+
"step": 162,
|
| 1306 |
+
"token_acc": 0.9513644708591343
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.2851485148514852,
|
| 1310 |
+
"grad_norm": 0.6550883054733276,
|
| 1311 |
+
"learning_rate": 3.1242814700725977e-06,
|
| 1312 |
+
"loss": 0.1453072875738144,
|
| 1313 |
+
"step": 163,
|
| 1314 |
+
"token_acc": 0.9526897082257267
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.293069306930693,
|
| 1318 |
+
"grad_norm": 0.6055379509925842,
|
| 1319 |
+
"learning_rate": 3.064024463337747e-06,
|
| 1320 |
+
"loss": 0.1680273711681366,
|
| 1321 |
+
"step": 164,
|
| 1322 |
+
"token_acc": 0.9460150859548591
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.300990099009901,
|
| 1326 |
+
"grad_norm": 0.5471304059028625,
|
| 1327 |
+
"learning_rate": 3.0040964289364618e-06,
|
| 1328 |
+
"loss": 0.1544535607099533,
|
| 1329 |
+
"step": 165,
|
| 1330 |
+
"token_acc": 0.9517046657725701
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.308910891089109,
|
| 1334 |
+
"grad_norm": 0.7713163495063782,
|
| 1335 |
+
"learning_rate": 2.944507550192318e-06,
|
| 1336 |
+
"loss": 0.155064657330513,
|
| 1337 |
+
"step": 166,
|
| 1338 |
+
"token_acc": 0.9509043186414423
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 1.316831683168317,
|
| 1342 |
+
"grad_norm": 0.8327575325965881,
|
| 1343 |
+
"learning_rate": 2.885267952797569e-06,
|
| 1344 |
+
"loss": 0.16020247340202332,
|
| 1345 |
+
"step": 167,
|
| 1346 |
+
"token_acc": 0.9485959583436647
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.3247524752475248,
|
| 1350 |
+
"grad_norm": 0.5169234275817871,
|
| 1351 |
+
"learning_rate": 2.826387703092528e-06,
|
| 1352 |
+
"loss": 0.16192591190338135,
|
| 1353 |
+
"step": 168,
|
| 1354 |
+
"token_acc": 0.9488239403819283
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.3326732673267327,
|
| 1358 |
+
"grad_norm": 0.9723333120346069,
|
| 1359 |
+
"learning_rate": 2.7678768063550454e-06,
|
| 1360 |
+
"loss": 0.15419939160346985,
|
| 1361 |
+
"step": 169,
|
| 1362 |
+
"token_acc": 0.9512765023209133
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.3405940594059407,
|
| 1366 |
+
"grad_norm": 0.6089004278182983,
|
| 1367 |
+
"learning_rate": 2.7097452051003375e-06,
|
| 1368 |
+
"loss": 0.16952668130397797,
|
| 1369 |
+
"step": 170,
|
| 1370 |
+
"token_acc": 0.9462165620257684
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.3485148514851484,
|
| 1374 |
+
"grad_norm": 0.47285744547843933,
|
| 1375 |
+
"learning_rate": 2.6520027773915075e-06,
|
| 1376 |
+
"loss": 0.14173272252082825,
|
| 1377 |
+
"step": 171,
|
| 1378 |
+
"token_acc": 0.9558022622538752
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.3564356435643563,
|
| 1382 |
+
"grad_norm": 0.7607588171958923,
|
| 1383 |
+
"learning_rate": 2.594659335161008e-06,
|
| 1384 |
+
"loss": 0.14981427788734436,
|
| 1385 |
+
"step": 172,
|
| 1386 |
+
"token_acc": 0.9522860722425999
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 1.3643564356435642,
|
| 1390 |
+
"grad_norm": 0.6954582333564758,
|
| 1391 |
+
"learning_rate": 2.5377246225433306e-06,
|
| 1392 |
+
"loss": 0.15238721668720245,
|
| 1393 |
+
"step": 173,
|
| 1394 |
+
"token_acc": 0.9514182800540297
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 1.3722772277227722,
|
| 1398 |
+
"grad_norm": 0.44258734583854675,
|
| 1399 |
+
"learning_rate": 2.481208314219233e-06,
|
| 1400 |
+
"loss": 0.12909170985221863,
|
| 1401 |
+
"step": 174,
|
| 1402 |
+
"token_acc": 0.9590912443755993
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.38019801980198,
|
| 1406 |
+
"grad_norm": 0.4488363564014435,
|
| 1407 |
+
"learning_rate": 2.4251200137717545e-06,
|
| 1408 |
+
"loss": 0.14320072531700134,
|
| 1409 |
+
"step": 175,
|
| 1410 |
+
"token_acc": 0.9541365102390396
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.388118811881188,
|
| 1414 |
+
"grad_norm": 0.5396542549133301,
|
| 1415 |
+
"learning_rate": 2.3694692520543293e-06,
|
| 1416 |
+
"loss": 0.1328102946281433,
|
| 1417 |
+
"step": 176,
|
| 1418 |
+
"token_acc": 0.957649883694755
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.396039603960396,
|
| 1422 |
+
"grad_norm": 0.5702061653137207,
|
| 1423 |
+
"learning_rate": 2.3142654855712353e-06,
|
| 1424 |
+
"loss": 0.15418201684951782,
|
| 1425 |
+
"step": 177,
|
| 1426 |
+
"token_acc": 0.9516512042950486
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 1.4039603960396039,
|
| 1430 |
+
"grad_norm": 0.50037682056427,
|
| 1431 |
+
"learning_rate": 2.259518094870693e-06,
|
| 1432 |
+
"loss": 0.13242614269256592,
|
| 1433 |
+
"step": 178,
|
| 1434 |
+
"token_acc": 0.956668874744391
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.4118811881188118,
|
| 1438 |
+
"grad_norm": 0.619013249874115,
|
| 1439 |
+
"learning_rate": 2.2052363829508776e-06,
|
| 1440 |
+
"loss": 0.13758519291877747,
|
| 1441 |
+
"step": 179,
|
| 1442 |
+
"token_acc": 0.9562362930889051
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.4198019801980197,
|
| 1446 |
+
"grad_norm": 0.6710831522941589,
|
| 1447 |
+
"learning_rate": 2.151429573679084e-06,
|
| 1448 |
+
"loss": 0.13403016328811646,
|
| 1449 |
+
"step": 180,
|
| 1450 |
+
"token_acc": 0.95760710508396
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.4277227722772277,
|
| 1454 |
+
"grad_norm": 0.7688338160514832,
|
| 1455 |
+
"learning_rate": 2.098106810224362e-06,
|
| 1456 |
+
"loss": 0.14811764657497406,
|
| 1457 |
+
"step": 181,
|
| 1458 |
+
"token_acc": 0.9531458574352585
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.4356435643564356,
|
| 1462 |
+
"grad_norm": 0.5376871228218079,
|
| 1463 |
+
"learning_rate": 2.0452771535038518e-06,
|
| 1464 |
+
"loss": 0.14322683215141296,
|
| 1465 |
+
"step": 182,
|
| 1466 |
+
"token_acc": 0.9543201588367209
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.4435643564356435,
|
| 1470 |
+
"grad_norm": 0.5330381393432617,
|
| 1471 |
+
"learning_rate": 1.9929495806431024e-06,
|
| 1472 |
+
"loss": 0.13567030429840088,
|
| 1473 |
+
"step": 183,
|
| 1474 |
+
"token_acc": 0.9577093548909602
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.4514851485148514,
|
| 1478 |
+
"grad_norm": 0.555989682674408,
|
| 1479 |
+
"learning_rate": 1.9411329834506286e-06,
|
| 1480 |
+
"loss": 0.13676701486110687,
|
| 1481 |
+
"step": 184,
|
| 1482 |
+
"token_acc": 0.9566704675028507
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 1.4594059405940594,
|
| 1486 |
+
"grad_norm": 0.4395022988319397,
|
| 1487 |
+
"learning_rate": 1.8898361669069497e-06,
|
| 1488 |
+
"loss": 0.14137856662273407,
|
| 1489 |
+
"step": 185,
|
| 1490 |
+
"token_acc": 0.9553027224705404
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.4673267326732673,
|
| 1494 |
+
"grad_norm": 0.5565665364265442,
|
| 1495 |
+
"learning_rate": 1.8390678476684143e-06,
|
| 1496 |
+
"loss": 0.11843089759349823,
|
| 1497 |
+
"step": 186,
|
| 1498 |
+
"token_acc": 0.9634671645521236
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.4752475247524752,
|
| 1502 |
+
"grad_norm": 0.48320114612579346,
|
| 1503 |
+
"learning_rate": 1.7888366525859968e-06,
|
| 1504 |
+
"loss": 0.15879571437835693,
|
| 1505 |
+
"step": 187,
|
| 1506 |
+
"token_acc": 0.9498863271824484
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.4831683168316832,
|
| 1510 |
+
"grad_norm": 0.4197307527065277,
|
| 1511 |
+
"learning_rate": 1.7391511172393849e-06,
|
| 1512 |
+
"loss": 0.11339066922664642,
|
| 1513 |
+
"step": 188,
|
| 1514 |
+
"token_acc": 0.9634443770882382
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.491089108910891,
|
| 1518 |
+
"grad_norm": 0.49137404561042786,
|
| 1519 |
+
"learning_rate": 1.6900196844865575e-06,
|
| 1520 |
+
"loss": 0.10974431037902832,
|
| 1521 |
+
"step": 189,
|
| 1522 |
+
"token_acc": 0.9648260700892279
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.499009900990099,
|
| 1526 |
+
"grad_norm": 0.5384393930435181,
|
| 1527 |
+
"learning_rate": 1.6414507030291249e-06,
|
| 1528 |
+
"loss": 0.12600228190422058,
|
| 1529 |
+
"step": 190,
|
| 1530 |
+
"token_acc": 0.9595004851178367
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.506930693069307,
|
| 1534 |
+
"grad_norm": 0.5459060668945312,
|
| 1535 |
+
"learning_rate": 1.5934524259936757e-06,
|
| 1536 |
+
"loss": 0.13144095242023468,
|
| 1537 |
+
"step": 191,
|
| 1538 |
+
"token_acc": 0.9584661354581673
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.5148514851485149,
|
| 1542 |
+
"grad_norm": 0.4256502389907837,
|
| 1543 |
+
"learning_rate": 1.5460330095293447e-06,
|
| 1544 |
+
"loss": 0.12027375400066376,
|
| 1545 |
+
"step": 192,
|
| 1546 |
+
"token_acc": 0.9606931038492847
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.5227722772277228,
|
| 1550 |
+
"grad_norm": 0.45994868874549866,
|
| 1551 |
+
"learning_rate": 1.4992005114218805e-06,
|
| 1552 |
+
"loss": 0.1223437711596489,
|
| 1553 |
+
"step": 193,
|
| 1554 |
+
"token_acc": 0.9615836269082368
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.5306930693069307,
|
| 1558 |
+
"grad_norm": 0.36966246366500854,
|
| 1559 |
+
"learning_rate": 1.4529628897244214e-06,
|
| 1560 |
+
"loss": 0.0998164638876915,
|
| 1561 |
+
"step": 194,
|
| 1562 |
+
"token_acc": 0.9675614881463285
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.5386138613861386,
|
| 1566 |
+
"grad_norm": 0.5190201997756958,
|
| 1567 |
+
"learning_rate": 1.4073280014052077e-06,
|
| 1568 |
+
"loss": 0.10250329971313477,
|
| 1569 |
+
"step": 195,
|
| 1570 |
+
"token_acc": 0.966889336261591
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.5465346534653466,
|
| 1574 |
+
"grad_norm": 0.5622069239616394,
|
| 1575 |
+
"learning_rate": 1.3623036010124845e-06,
|
| 1576 |
+
"loss": 0.12284793704748154,
|
| 1577 |
+
"step": 196,
|
| 1578 |
+
"token_acc": 0.9612569828370167
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.5544554455445545,
|
| 1582 |
+
"grad_norm": 0.428867906332016,
|
| 1583 |
+
"learning_rate": 1.3178973393568055e-06,
|
| 1584 |
+
"loss": 0.1283891499042511,
|
| 1585 |
+
"step": 197,
|
| 1586 |
+
"token_acc": 0.9587091339520427
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.5623762376237624,
|
| 1590 |
+
"grad_norm": 0.4701291620731354,
|
| 1591 |
+
"learning_rate": 1.2741167622109557e-06,
|
| 1592 |
+
"loss": 0.12027464807033539,
|
| 1593 |
+
"step": 198,
|
| 1594 |
+
"token_acc": 0.9621139269148093
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 1.5702970297029704,
|
| 1598 |
+
"grad_norm": 0.6337451338768005,
|
| 1599 |
+
"learning_rate": 1.2309693090277392e-06,
|
| 1600 |
+
"loss": 0.11269824206829071,
|
| 1601 |
+
"step": 199,
|
| 1602 |
+
"token_acc": 0.9639051872609977
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 1.5782178217821783,
|
| 1606 |
+
"grad_norm": 0.9049360156059265,
|
| 1607 |
+
"learning_rate": 1.1884623116758121e-06,
|
| 1608 |
+
"loss": 0.12734943628311157,
|
| 1609 |
+
"step": 200,
|
| 1610 |
+
"token_acc": 0.9601251328413837
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.5861386138613862,
|
| 1614 |
+
"grad_norm": 0.5399721264839172,
|
| 1615 |
+
"learning_rate": 1.1466029931938182e-06,
|
| 1616 |
+
"loss": 0.12347307056188583,
|
| 1617 |
+
"step": 201,
|
| 1618 |
+
"token_acc": 0.961113178063844
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 1.5940594059405941,
|
| 1622 |
+
"grad_norm": 0.4135936498641968,
|
| 1623 |
+
"learning_rate": 1.1053984665630025e-06,
|
| 1624 |
+
"loss": 0.11961033195257187,
|
| 1625 |
+
"step": 202,
|
| 1626 |
+
"token_acc": 0.962127463183363
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.601980198019802,
|
| 1630 |
+
"grad_norm": 0.4108199179172516,
|
| 1631 |
+
"learning_rate": 1.064855733498531e-06,
|
| 1632 |
+
"loss": 0.11237754672765732,
|
| 1633 |
+
"step": 203,
|
| 1634 |
+
"token_acc": 0.9641947353523918
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.60990099009901,
|
| 1638 |
+
"grad_norm": 0.3836463987827301,
|
| 1639 |
+
"learning_rate": 1.024981683259723e-06,
|
| 1640 |
+
"loss": 0.11228284239768982,
|
| 1641 |
+
"step": 204,
|
| 1642 |
+
"token_acc": 0.9655187808798142
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.617821782178218,
|
| 1646 |
+
"grad_norm": 0.4256911277770996,
|
| 1647 |
+
"learning_rate": 9.857830914793827e-07,
|
| 1648 |
+
"loss": 0.12447601556777954,
|
| 1649 |
+
"step": 205,
|
| 1650 |
+
"token_acc": 0.959564361024215
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.6257425742574259,
|
| 1654 |
+
"grad_norm": 0.4444533586502075,
|
| 1655 |
+
"learning_rate": 9.472666190124457e-07,
|
| 1656 |
+
"loss": 0.1171032041311264,
|
| 1657 |
+
"step": 206,
|
| 1658 |
+
"token_acc": 0.9628257093225246
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 1.6336633663366338,
|
| 1662 |
+
"grad_norm": 0.4453146457672119,
|
| 1663 |
+
"learning_rate": 9.094388108041302e-07,
|
| 1664 |
+
"loss": 0.11630374193191528,
|
| 1665 |
+
"step": 207,
|
| 1666 |
+
"token_acc": 0.9627691971327285
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.6415841584158417,
|
| 1670 |
+
"grad_norm": 0.6507600545883179,
|
| 1671 |
+
"learning_rate": 8.723060947777778e-07,
|
| 1672 |
+
"loss": 0.10998623073101044,
|
| 1673 |
+
"step": 208,
|
| 1674 |
+
"token_acc": 0.9651977966950426
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.6495049504950496,
|
| 1678 |
+
"grad_norm": 0.419282466173172,
|
| 1679 |
+
"learning_rate": 8.358747807425827e-07,
|
| 1680 |
+
"loss": 0.09935610741376877,
|
| 1681 |
+
"step": 209,
|
| 1682 |
+
"token_acc": 0.9689518973056849
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.6574257425742576,
|
| 1686 |
+
"grad_norm": 0.4113824963569641,
|
| 1687 |
+
"learning_rate": 8.001510593213946e-07,
|
| 1688 |
+
"loss": 0.09419016540050507,
|
| 1689 |
+
"step": 210,
|
| 1690 |
+
"token_acc": 0.9706665872933192
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.6653465346534655,
|
| 1694 |
+
"grad_norm": 0.5601107478141785,
|
| 1695 |
+
"learning_rate": 7.651410008987698e-07,
|
| 1696 |
+
"loss": 0.11026152223348618,
|
| 1697 |
+
"step": 211,
|
| 1698 |
+
"token_acc": 0.9650260397564733
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.6732673267326734,
|
| 1702 |
+
"grad_norm": 0.38922393321990967,
|
| 1703 |
+
"learning_rate": 7.308505545894567e-07,
|
| 1704 |
+
"loss": 0.11773674190044403,
|
| 1705 |
+
"step": 212,
|
| 1706 |
+
"token_acc": 0.9628206154749512
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.6811881188118813,
|
| 1710 |
+
"grad_norm": 0.515808641910553,
|
| 1711 |
+
"learning_rate": 6.972855472274853e-07,
|
| 1712 |
+
"loss": 0.09375099837779999,
|
| 1713 |
+
"step": 213,
|
| 1714 |
+
"token_acc": 0.9702981734170818
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.689108910891089,
|
| 1718 |
+
"grad_norm": 0.3917420208454132,
|
| 1719 |
+
"learning_rate": 6.644516823760439e-07,
|
| 1720 |
+
"loss": 0.09479185193777084,
|
| 1721 |
+
"step": 214,
|
| 1722 |
+
"token_acc": 0.97002828854314
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.697029702970297,
|
| 1726 |
+
"grad_norm": 0.42259907722473145,
|
| 1727 |
+
"learning_rate": 6.323545393582847e-07,
|
| 1728 |
+
"loss": 0.10449820756912231,
|
| 1729 |
+
"step": 215,
|
| 1730 |
+
"token_acc": 0.9670323350538438
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 1.704950495049505,
|
| 1734 |
+
"grad_norm": 0.7351343631744385,
|
| 1735 |
+
"learning_rate": 6.009995723092655e-07,
|
| 1736 |
+
"loss": 0.09121552109718323,
|
| 1737 |
+
"step": 216,
|
| 1738 |
+
"token_acc": 0.9714563078661779
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.7128712871287128,
|
| 1742 |
+
"grad_norm": 0.43367230892181396,
|
| 1743 |
+
"learning_rate": 5.703921092491393e-07,
|
| 1744 |
+
"loss": 0.10226999968290329,
|
| 1745 |
+
"step": 217,
|
| 1746 |
+
"token_acc": 0.9678272768739546
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.7207920792079208,
|
| 1750 |
+
"grad_norm": 0.4525696933269501,
|
| 1751 |
+
"learning_rate": 5.405373511777939e-07,
|
| 1752 |
+
"loss": 0.10495859384536743,
|
| 1753 |
+
"step": 218,
|
| 1754 |
+
"token_acc": 0.9671123359023667
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.7287128712871287,
|
| 1758 |
+
"grad_norm": 0.3771766424179077,
|
| 1759 |
+
"learning_rate": 5.114403711910631e-07,
|
| 1760 |
+
"loss": 0.1022784560918808,
|
| 1761 |
+
"step": 219,
|
| 1762 |
+
"token_acc": 0.967561701690839
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 1.7366336633663366,
|
| 1766 |
+
"grad_norm": 0.48617279529571533,
|
| 1767 |
+
"learning_rate": 4.831061136186787e-07,
|
| 1768 |
+
"loss": 0.09722768515348434,
|
| 1769 |
+
"step": 220,
|
| 1770 |
+
"token_acc": 0.9686085644655913
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 1.7445544554455445,
|
| 1774 |
+
"grad_norm": 0.6091553568840027,
|
| 1775 |
+
"learning_rate": 4.555393931841001e-07,
|
| 1776 |
+
"loss": 0.11038898676633835,
|
| 1777 |
+
"step": 221,
|
| 1778 |
+
"token_acc": 0.9653706370431324
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.7524752475247525,
|
| 1782 |
+
"grad_norm": 0.6056889295578003,
|
| 1783 |
+
"learning_rate": 4.287448941863692e-07,
|
| 1784 |
+
"loss": 0.11534392833709717,
|
| 1785 |
+
"step": 222,
|
| 1786 |
+
"token_acc": 0.9629515599343186
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.7603960396039604,
|
| 1790 |
+
"grad_norm": 0.38846179842948914,
|
| 1791 |
+
"learning_rate": 4.0272716970412516e-07,
|
| 1792 |
+
"loss": 0.09573670476675034,
|
| 1793 |
+
"step": 223,
|
| 1794 |
+
"token_acc": 0.9695268301045774
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.7683168316831683,
|
| 1798 |
+
"grad_norm": 0.42757096886634827,
|
| 1799 |
+
"learning_rate": 3.7749064082191976e-07,
|
| 1800 |
+
"loss": 0.09938608109951019,
|
| 1801 |
+
"step": 224,
|
| 1802 |
+
"token_acc": 0.9691973907706362
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.7762376237623763,
|
| 1806 |
+
"grad_norm": 0.3813166618347168,
|
| 1807 |
+
"learning_rate": 3.53039595878959e-07,
|
| 1808 |
+
"loss": 0.1071573793888092,
|
| 1809 |
+
"step": 225,
|
| 1810 |
+
"token_acc": 0.9660217917017634
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.7841584158415842,
|
| 1814 |
+
"grad_norm": 0.4348575174808502,
|
| 1815 |
+
"learning_rate": 3.2937818974040637e-07,
|
| 1816 |
+
"loss": 0.10645346343517303,
|
| 1817 |
+
"step": 226,
|
| 1818 |
+
"token_acc": 0.9663214301148068
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.7920792079207921,
|
| 1822 |
+
"grad_norm": 0.6349267363548279,
|
| 1823 |
+
"learning_rate": 3.0651044309136016e-07,
|
| 1824 |
+
"loss": 0.11275631189346313,
|
| 1825 |
+
"step": 227,
|
| 1826 |
+
"token_acc": 0.9635372097408154
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 1.8,
|
| 1830 |
+
"grad_norm": 0.5375218391418457,
|
| 1831 |
+
"learning_rate": 2.844402417536374e-07,
|
| 1832 |
+
"loss": 0.09979911893606186,
|
| 1833 |
+
"step": 228,
|
| 1834 |
+
"token_acc": 0.9682528558413344
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.807920792079208,
|
| 1838 |
+
"grad_norm": 0.48544204235076904,
|
| 1839 |
+
"learning_rate": 2.631713360254734e-07,
|
| 1840 |
+
"loss": 0.09213175624608994,
|
| 1841 |
+
"step": 229,
|
| 1842 |
+
"token_acc": 0.9706900762920073
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.8158415841584157,
|
| 1846 |
+
"grad_norm": 0.3997177183628082,
|
| 1847 |
+
"learning_rate": 2.4270734004424643e-07,
|
| 1848 |
+
"loss": 0.09869547933340073,
|
| 1849 |
+
"step": 230,
|
| 1850 |
+
"token_acc": 0.9679887967861488
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.8237623762376236,
|
| 1854 |
+
"grad_norm": 0.35521507263183594,
|
| 1855 |
+
"learning_rate": 2.2305173117234236e-07,
|
| 1856 |
+
"loss": 0.10183179378509521,
|
| 1857 |
+
"step": 231,
|
| 1858 |
+
"token_acc": 0.9688890815559794
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.8316831683168315,
|
| 1862 |
+
"grad_norm": 0.43961137533187866,
|
| 1863 |
+
"learning_rate": 2.042078494062616e-07,
|
| 1864 |
+
"loss": 0.08839896321296692,
|
| 1865 |
+
"step": 232,
|
| 1866 |
+
"token_acc": 0.9725255726840513
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 1.8396039603960395,
|
| 1870 |
+
"grad_norm": 0.4296596944332123,
|
| 1871 |
+
"learning_rate": 1.861788968090683e-07,
|
| 1872 |
+
"loss": 0.09201016277074814,
|
| 1873 |
+
"step": 233,
|
| 1874 |
+
"token_acc": 0.9706376682516197
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.8475247524752474,
|
| 1878 |
+
"grad_norm": 0.5303926467895508,
|
| 1879 |
+
"learning_rate": 1.68967936966275e-07,
|
| 1880 |
+
"loss": 0.09831856936216354,
|
| 1881 |
+
"step": 234,
|
| 1882 |
+
"token_acc": 0.9690057098400967
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 1.8554455445544553,
|
| 1886 |
+
"grad_norm": 0.3820088505744934,
|
| 1887 |
+
"learning_rate": 1.5257789446526172e-07,
|
| 1888 |
+
"loss": 0.10098826885223389,
|
| 1889 |
+
"step": 235,
|
| 1890 |
+
"token_acc": 0.9689033199353464
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 1.8633663366336632,
|
| 1894 |
+
"grad_norm": 0.3905301094055176,
|
| 1895 |
+
"learning_rate": 1.3701155439831249e-07,
|
| 1896 |
+
"loss": 0.10082507133483887,
|
| 1897 |
+
"step": 236,
|
| 1898 |
+
"token_acc": 0.9685121304558543
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.8712871287128712,
|
| 1902 |
+
"grad_norm": 0.49219226837158203,
|
| 1903 |
+
"learning_rate": 1.2227156188935552e-07,
|
| 1904 |
+
"loss": 0.09544937312602997,
|
| 1905 |
+
"step": 237,
|
| 1906 |
+
"token_acc": 0.9699410057121454
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.879207920792079,
|
| 1910 |
+
"grad_norm": 0.502971351146698,
|
| 1911 |
+
"learning_rate": 1.0836042164448945e-07,
|
| 1912 |
+
"loss": 0.10350553691387177,
|
| 1913 |
+
"step": 238,
|
| 1914 |
+
"token_acc": 0.967554724092256
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.887128712871287,
|
| 1918 |
+
"grad_norm": 0.4445388913154602,
|
| 1919 |
+
"learning_rate": 9.528049752636714e-08,
|
| 1920 |
+
"loss": 0.09501008689403534,
|
| 1921 |
+
"step": 239,
|
| 1922 |
+
"token_acc": 0.9707895034498359
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.895049504950495,
|
| 1926 |
+
"grad_norm": 0.3258512318134308,
|
| 1927 |
+
"learning_rate": 8.303401215251583e-08,
|
| 1928 |
+
"loss": 0.09649574756622314,
|
| 1929 |
+
"step": 240,
|
| 1930 |
+
"token_acc": 0.9699121075723799
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 1.9029702970297029,
|
| 1934 |
+
"grad_norm": 0.4464386999607086,
|
| 1935 |
+
"learning_rate": 7.16230465176565e-08,
|
| 1936 |
+
"loss": 0.09789906442165375,
|
| 1937 |
+
"step": 241,
|
| 1938 |
+
"token_acc": 0.9689483723693674
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 1.9108910891089108,
|
| 1942 |
+
"grad_norm": 0.5163915157318115,
|
| 1943 |
+
"learning_rate": 6.104953964008897e-08,
|
| 1944 |
+
"loss": 0.09997884929180145,
|
| 1945 |
+
"step": 242,
|
| 1946 |
+
"token_acc": 0.968834388419142
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.9188118811881187,
|
| 1950 |
+
"grad_norm": 0.4559917747974396,
|
| 1951 |
+
"learning_rate": 5.1315288232201e-08,
|
| 1952 |
+
"loss": 0.08326887339353561,
|
| 1953 |
+
"step": 243,
|
| 1954 |
+
"token_acc": 0.9744464851263214
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 1.9267326732673267,
|
| 1958 |
+
"grad_norm": 0.9722307920455933,
|
| 1959 |
+
"learning_rate": 4.2421946395164174e-08,
|
| 1960 |
+
"loss": 0.09816071391105652,
|
| 1961 |
+
"step": 244,
|
| 1962 |
+
"token_acc": 0.9689419744455517
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.9346534653465346,
|
| 1966 |
+
"grad_norm": 0.4705962836742401,
|
| 1967 |
+
"learning_rate": 3.437102533785541e-08,
|
| 1968 |
+
"loss": 0.09553688019514084,
|
| 1969 |
+
"step": 245,
|
| 1970 |
+
"token_acc": 0.9703259532595326
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.9425742574257425,
|
| 1974 |
+
"grad_norm": 0.42266544699668884,
|
| 1975 |
+
"learning_rate": 2.7163893120066288e-08,
|
| 1976 |
+
"loss": 0.09367343783378601,
|
| 1977 |
+
"step": 246,
|
| 1978 |
+
"token_acc": 0.9703372044214356
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 1.9504950495049505,
|
| 1982 |
+
"grad_norm": 0.37436920404434204,
|
| 1983 |
+
"learning_rate": 2.0801774420031172e-08,
|
| 1984 |
+
"loss": 0.10248593986034393,
|
| 1985 |
+
"step": 247,
|
| 1986 |
+
"token_acc": 0.9682605172032712
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 1.9584158415841584,
|
| 1990 |
+
"grad_norm": 0.387408971786499,
|
| 1991 |
+
"learning_rate": 1.5285750326325953e-08,
|
| 1992 |
+
"loss": 0.09087318181991577,
|
| 1993 |
+
"step": 248,
|
| 1994 |
+
"token_acc": 0.9710745636759285
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.9663366336633663,
|
| 1998 |
+
"grad_norm": 0.38171303272247314,
|
| 1999 |
+
"learning_rate": 1.0616758154161633e-08,
|
| 2000 |
+
"loss": 0.08435317128896713,
|
| 2001 |
+
"step": 249,
|
| 2002 |
+
"token_acc": 0.9737835938872299
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.9742574257425742,
|
| 2006 |
+
"grad_norm": 0.4201211631298065,
|
| 2007 |
+
"learning_rate": 6.7955912861095155e-09,
|
| 2008 |
+
"loss": 0.09462376683950424,
|
| 2009 |
+
"step": 250,
|
| 2010 |
+
"token_acc": 0.9701571918212977
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 1.9821782178217822,
|
| 2014 |
+
"grad_norm": 0.5204740166664124,
|
| 2015 |
+
"learning_rate": 3.822899037286276e-09,
|
| 2016 |
+
"loss": 0.09324952214956284,
|
| 2017 |
+
"step": 251,
|
| 2018 |
+
"token_acc": 0.9703798285369516
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.99009900990099,
|
| 2022 |
+
"grad_norm": 0.4454892873764038,
|
| 2023 |
+
"learning_rate": 1.6991865450188827e-09,
|
| 2024 |
+
"loss": 0.0900895819067955,
|
| 2025 |
+
"step": 252,
|
| 2026 |
+
"token_acc": 0.9715137865968714
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.998019801980198,
|
| 2030 |
+
"grad_norm": 0.4123733937740326,
|
| 2031 |
+
"learning_rate": 4.2481468300603625e-10,
|
| 2032 |
+
"loss": 0.10531582683324814,
|
| 2033 |
+
"step": 253,
|
| 2034 |
+
"token_acc": 0.9668541721107429
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 2.0,
|
| 2038 |
+
"grad_norm": 1.6710283756256104,
|
| 2039 |
+
"learning_rate": 0.0,
|
| 2040 |
+
"loss": 0.10527525842189789,
|
| 2041 |
+
"step": 254,
|
| 2042 |
+
"token_acc": 0.9683964104564963
|
| 2043 |
+
}
|
| 2044 |
+
],
|
| 2045 |
+
"logging_steps": 1,
|
| 2046 |
+
"max_steps": 254,
|
| 2047 |
+
"num_input_tokens_seen": 0,
|
| 2048 |
+
"num_train_epochs": 2,
|
| 2049 |
+
"save_steps": 100,
|
| 2050 |
+
"stateful_callbacks": {
|
| 2051 |
+
"TrainerControl": {
|
| 2052 |
+
"args": {
|
| 2053 |
+
"should_epoch_stop": false,
|
| 2054 |
+
"should_evaluate": false,
|
| 2055 |
+
"should_log": false,
|
| 2056 |
+
"should_save": true,
|
| 2057 |
+
"should_training_stop": true
|
| 2058 |
+
},
|
| 2059 |
+
"attributes": {}
|
| 2060 |
+
}
|
| 2061 |
+
},
|
| 2062 |
+
"total_flos": 2.318078735384838e+19,
|
| 2063 |
+
"train_batch_size": 1,
|
| 2064 |
+
"trial_name": null,
|
| 2065 |
+
"trial_params": null
|
| 2066 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7a69dded37aa902e6c8711863821baf93a0505e240211fea7ffa88092efbd1a
|
| 3 |
+
size 9297
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/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 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5_bs384_hfunc/step-254/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)
|