Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/added_tokens.json +28 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/args.json +388 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/chat_template.jinja +120 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/config.json +70 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/generation_config.json +13 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/latest +1 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/merges.txt +0 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/model-00001-of-00002.safetensors +3 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/model-00002-of-00002.safetensors +3 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/model.safetensors.index.json +722 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/preprocessor_config.json +21 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/special_tokens_map.json +31 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/tokenizer.json +3 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/tokenizer_config.json +240 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/trainer_state.json +1812 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/training_args.bin +3 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/video_preprocessor_config.json +41 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/vocab.json +0 -0
- qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/zero_to_fp32.py +760 -0
.gitattributes
CHANGED
|
@@ -76,3 +76,4 @@ qwen3-vl-4b-agentnet_filter_failure_ubuntu-only_lr2e-5_vit1e-5_aligner1e-5_bs384
|
|
| 76 |
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 77 |
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 78 |
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5-step254/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 76 |
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 77 |
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 78 |
qwen3-vl-4b-vl32b_traj_rollout_ws4_l1-l2_lr2e-5_vit1e-5_aligner1e-5-step254/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/args.json
ADDED
|
@@ -0,0 +1,388 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260201-003957",
|
| 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": 4,
|
| 10 |
+
"per_device_eval_batch_size": 1,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 2,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 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_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260201-003957/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_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260201-003957",
|
| 68 |
+
"disable_tqdm": null,
|
| 69 |
+
"remove_unused_columns": true,
|
| 70 |
+
"label_names": null,
|
| 71 |
+
"load_best_model_at_end": false,
|
| 72 |
+
"metric_for_best_model": "loss",
|
| 73 |
+
"greater_is_better": false,
|
| 74 |
+
"ignore_data_skip": false,
|
| 75 |
+
"fsdp": [],
|
| 76 |
+
"fsdp_min_num_params": 0,
|
| 77 |
+
"fsdp_config": null,
|
| 78 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 79 |
+
"accelerator_config": {
|
| 80 |
+
"dispatch_batches": false
|
| 81 |
+
},
|
| 82 |
+
"parallelism_config": null,
|
| 83 |
+
"deepspeed": {
|
| 84 |
+
"fp16": {
|
| 85 |
+
"enabled": "auto",
|
| 86 |
+
"loss_scale": 0,
|
| 87 |
+
"loss_scale_window": 1000,
|
| 88 |
+
"initial_scale_power": 16,
|
| 89 |
+
"hysteresis": 2,
|
| 90 |
+
"min_loss_scale": 1
|
| 91 |
+
},
|
| 92 |
+
"bf16": {
|
| 93 |
+
"enabled": "auto"
|
| 94 |
+
},
|
| 95 |
+
"zero_optimization": {
|
| 96 |
+
"stage": 1,
|
| 97 |
+
"offload_optimizer": {
|
| 98 |
+
"device": "none",
|
| 99 |
+
"pin_memory": true
|
| 100 |
+
},
|
| 101 |
+
"allgather_partitions": true,
|
| 102 |
+
"allgather_bucket_size": 200000000.0,
|
| 103 |
+
"overlap_comm": false,
|
| 104 |
+
"reduce_scatter": true,
|
| 105 |
+
"reduce_bucket_size": 200000000.0,
|
| 106 |
+
"contiguous_gradients": true
|
| 107 |
+
},
|
| 108 |
+
"gradient_accumulation_steps": "auto",
|
| 109 |
+
"gradient_clipping": "auto",
|
| 110 |
+
"steps_per_print": 2000,
|
| 111 |
+
"train_batch_size": "auto",
|
| 112 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 113 |
+
"wall_clock_breakdown": false
|
| 114 |
+
},
|
| 115 |
+
"label_smoothing_factor": 0.0,
|
| 116 |
+
"optim": "adamw_torch_fused",
|
| 117 |
+
"optim_args": null,
|
| 118 |
+
"adafactor": false,
|
| 119 |
+
"group_by_length": false,
|
| 120 |
+
"length_column_name": "length",
|
| 121 |
+
"report_to": [
|
| 122 |
+
"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_fsgm/share_304220499/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": "default",
|
| 227 |
+
"sequence_parallel_size": 1,
|
| 228 |
+
"template_backend": "swift",
|
| 229 |
+
"response_prefix": null,
|
| 230 |
+
"enable_thinking": null,
|
| 231 |
+
"add_non_thinking_prefix": true,
|
| 232 |
+
"dataset": [
|
| 233 |
+
"/apdcephfs_fsgm/share_304220499/weixian/workspace/data_preprocess/qwen3-vl_Agentnet_traj_preprocess/rollout_train_l1.ws3.jsonl#24250",
|
| 234 |
+
"/apdcephfs_fsgm/share_304220499/weixian/workspace/data_preprocess/qwen3-vl_Agentnet_traj_preprocess/rollout_train_l1.ws3.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": 48,
|
| 379 |
+
"local_world_size": 8,
|
| 380 |
+
"model_suffix": "Qwen3-VL-4B-Instruct",
|
| 381 |
+
"model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/apdcephfs_fsgm/share_304220499/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 0x7f70f3381120>, 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_fsgm/share_304220499/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_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260201-003957', 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=4, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=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_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260201-003957/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_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260201-003957', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 1, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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": "4.57.1",
|
| 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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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": "4.57.1"
|
| 13 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step254
|
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a658fcd073cb73e5f4c13c69c1a7791187df4c64259875025d58edadf434899b
|
| 3 |
+
size 4990497880
|
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e07a178d8f7dba5c8b9107b643aacccef7c2841e1e5a1cbf7dc742e0d6f0b46d
|
| 3 |
+
size 4663133960
|
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/trainer_state.json
ADDED
|
@@ -0,0 +1,1812 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 0.007905138339920948,
|
| 14 |
+
"grad_norm": 15.77699089050293,
|
| 15 |
+
"learning_rate": 7.692307692307694e-07,
|
| 16 |
+
"loss": 0.42103680968284607,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015810276679841896,
|
| 21 |
+
"grad_norm": 16.63542938232422,
|
| 22 |
+
"learning_rate": 1.5384615384615387e-06,
|
| 23 |
+
"loss": 0.43381649255752563,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.023715415019762844,
|
| 28 |
+
"grad_norm": 18.46222496032715,
|
| 29 |
+
"learning_rate": 2.307692307692308e-06,
|
| 30 |
+
"loss": 0.45291781425476074,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03162055335968379,
|
| 35 |
+
"grad_norm": 15.444769859313965,
|
| 36 |
+
"learning_rate": 3.0769230769230774e-06,
|
| 37 |
+
"loss": 0.32814690470695496,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.039525691699604744,
|
| 42 |
+
"grad_norm": 9.42475414276123,
|
| 43 |
+
"learning_rate": 3.846153846153847e-06,
|
| 44 |
+
"loss": 0.268908828496933,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04743083003952569,
|
| 49 |
+
"grad_norm": 6.8979668617248535,
|
| 50 |
+
"learning_rate": 4.615384615384616e-06,
|
| 51 |
+
"loss": 0.21556489169597626,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.05533596837944664,
|
| 56 |
+
"grad_norm": 3.7356679439544678,
|
| 57 |
+
"learning_rate": 5.384615384615385e-06,
|
| 58 |
+
"loss": 0.20179948210716248,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06324110671936758,
|
| 63 |
+
"grad_norm": 3.6363861560821533,
|
| 64 |
+
"learning_rate": 6.153846153846155e-06,
|
| 65 |
+
"loss": 0.18416088819503784,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.07114624505928854,
|
| 70 |
+
"grad_norm": 3.481579542160034,
|
| 71 |
+
"learning_rate": 6.923076923076923e-06,
|
| 72 |
+
"loss": 0.19544069468975067,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.07905138339920949,
|
| 77 |
+
"grad_norm": 2.922022819519043,
|
| 78 |
+
"learning_rate": 7.692307692307694e-06,
|
| 79 |
+
"loss": 0.1968146562576294,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08695652173913043,
|
| 84 |
+
"grad_norm": 2.5951032638549805,
|
| 85 |
+
"learning_rate": 8.461538461538462e-06,
|
| 86 |
+
"loss": 0.17362481355667114,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09486166007905138,
|
| 91 |
+
"grad_norm": 2.99121356010437,
|
| 92 |
+
"learning_rate": 9.230769230769232e-06,
|
| 93 |
+
"loss": 0.17670194804668427,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.10276679841897234,
|
| 98 |
+
"grad_norm": 3.3984293937683105,
|
| 99 |
+
"learning_rate": 1e-05,
|
| 100 |
+
"loss": 0.15578991174697876,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.11067193675889328,
|
| 105 |
+
"grad_norm": 3.347710609436035,
|
| 106 |
+
"learning_rate": 9.999575185316994e-06,
|
| 107 |
+
"loss": 0.14878934621810913,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.11857707509881422,
|
| 112 |
+
"grad_norm": 3.268404006958008,
|
| 113 |
+
"learning_rate": 9.998300813454981e-06,
|
| 114 |
+
"loss": 0.13730722665786743,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.12648221343873517,
|
| 119 |
+
"grad_norm": 3.168224573135376,
|
| 120 |
+
"learning_rate": 9.996177100962714e-06,
|
| 121 |
+
"loss": 0.14234212040901184,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.13438735177865613,
|
| 126 |
+
"grad_norm": 2.620702028274536,
|
| 127 |
+
"learning_rate": 9.99320440871389e-06,
|
| 128 |
+
"loss": 0.13136069476604462,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1422924901185771,
|
| 133 |
+
"grad_norm": 2.963843822479248,
|
| 134 |
+
"learning_rate": 9.98938324184584e-06,
|
| 135 |
+
"loss": 0.11818422377109528,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.15019762845849802,
|
| 140 |
+
"grad_norm": 3.2342100143432617,
|
| 141 |
+
"learning_rate": 9.984714249673676e-06,
|
| 142 |
+
"loss": 0.11709677428007126,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.15810276679841898,
|
| 147 |
+
"grad_norm": 3.465013265609741,
|
| 148 |
+
"learning_rate": 9.979198225579968e-06,
|
| 149 |
+
"loss": 0.12085666507482529,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.16600790513833993,
|
| 154 |
+
"grad_norm": 2.644714593887329,
|
| 155 |
+
"learning_rate": 9.972836106879936e-06,
|
| 156 |
+
"loss": 0.115155428647995,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.17391304347826086,
|
| 161 |
+
"grad_norm": 3.1987087726593018,
|
| 162 |
+
"learning_rate": 9.965628974662145e-06,
|
| 163 |
+
"loss": 0.10907091945409775,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.18181818181818182,
|
| 168 |
+
"grad_norm": 3.0469820499420166,
|
| 169 |
+
"learning_rate": 9.957578053604837e-06,
|
| 170 |
+
"loss": 0.10281195491552353,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.18972332015810275,
|
| 175 |
+
"grad_norm": 2.406339406967163,
|
| 176 |
+
"learning_rate": 9.9486847117678e-06,
|
| 177 |
+
"loss": 0.09363442659378052,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1976284584980237,
|
| 182 |
+
"grad_norm": 2.214507579803467,
|
| 183 |
+
"learning_rate": 9.938950460359912e-06,
|
| 184 |
+
"loss": 0.08398892730474472,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.20553359683794467,
|
| 189 |
+
"grad_norm": 1.9230656623840332,
|
| 190 |
+
"learning_rate": 9.928376953482343e-06,
|
| 191 |
+
"loss": 0.08280366659164429,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.2134387351778656,
|
| 196 |
+
"grad_norm": 2.025754690170288,
|
| 197 |
+
"learning_rate": 9.916965987847485e-06,
|
| 198 |
+
"loss": 0.08737964928150177,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.22134387351778656,
|
| 203 |
+
"grad_norm": 3.1691527366638184,
|
| 204 |
+
"learning_rate": 9.904719502473635e-06,
|
| 205 |
+
"loss": 0.07908620685338974,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.22924901185770752,
|
| 210 |
+
"grad_norm": 1.8445582389831543,
|
| 211 |
+
"learning_rate": 9.891639578355511e-06,
|
| 212 |
+
"loss": 0.07549957931041718,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.23715415019762845,
|
| 217 |
+
"grad_norm": 2.006866455078125,
|
| 218 |
+
"learning_rate": 9.877728438110645e-06,
|
| 219 |
+
"loss": 0.07024282962083817,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2450592885375494,
|
| 224 |
+
"grad_norm": 2.0398497581481934,
|
| 225 |
+
"learning_rate": 9.86298844560169e-06,
|
| 226 |
+
"loss": 0.07261291146278381,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.25296442687747034,
|
| 231 |
+
"grad_norm": 6.188963413238525,
|
| 232 |
+
"learning_rate": 9.847422105534739e-06,
|
| 233 |
+
"loss": 0.07808222621679306,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2608695652173913,
|
| 238 |
+
"grad_norm": 1.840552568435669,
|
| 239 |
+
"learning_rate": 9.831032063033726e-06,
|
| 240 |
+
"loss": 0.07136710733175278,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.26877470355731226,
|
| 245 |
+
"grad_norm": 1.8598898649215698,
|
| 246 |
+
"learning_rate": 9.813821103190932e-06,
|
| 247 |
+
"loss": 0.0677146166563034,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2766798418972332,
|
| 252 |
+
"grad_norm": 4.950652122497559,
|
| 253 |
+
"learning_rate": 9.795792150593739e-06,
|
| 254 |
+
"loss": 0.05624214559793472,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.2845849802371542,
|
| 259 |
+
"grad_norm": 1.3197205066680908,
|
| 260 |
+
"learning_rate": 9.776948268827658e-06,
|
| 261 |
+
"loss": 0.0570015087723732,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2924901185770751,
|
| 266 |
+
"grad_norm": 1.564042568206787,
|
| 267 |
+
"learning_rate": 9.757292659955755e-06,
|
| 268 |
+
"loss": 0.053566694259643555,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.30039525691699603,
|
| 273 |
+
"grad_norm": 4.4089202880859375,
|
| 274 |
+
"learning_rate": 9.736828663974527e-06,
|
| 275 |
+
"loss": 0.062199633568525314,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.308300395256917,
|
| 280 |
+
"grad_norm": 2.5468811988830566,
|
| 281 |
+
"learning_rate": 9.715559758246363e-06,
|
| 282 |
+
"loss": 0.060954779386520386,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.31620553359683795,
|
| 287 |
+
"grad_norm": 4.608983516693115,
|
| 288 |
+
"learning_rate": 9.693489556908641e-06,
|
| 289 |
+
"loss": 0.06053481623530388,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3241106719367589,
|
| 294 |
+
"grad_norm": 2.167358636856079,
|
| 295 |
+
"learning_rate": 9.670621810259596e-06,
|
| 296 |
+
"loss": 0.06121082231402397,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.33201581027667987,
|
| 301 |
+
"grad_norm": 2.1091678142547607,
|
| 302 |
+
"learning_rate": 9.646960404121042e-06,
|
| 303 |
+
"loss": 0.04749263450503349,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.33992094861660077,
|
| 308 |
+
"grad_norm": 5.505380630493164,
|
| 309 |
+
"learning_rate": 9.62250935917808e-06,
|
| 310 |
+
"loss": 0.04904608055949211,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.34782608695652173,
|
| 315 |
+
"grad_norm": 2.9503047466278076,
|
| 316 |
+
"learning_rate": 9.597272830295877e-06,
|
| 317 |
+
"loss": 0.0491236113011837,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3557312252964427,
|
| 322 |
+
"grad_norm": 2.594634771347046,
|
| 323 |
+
"learning_rate": 9.571255105813632e-06,
|
| 324 |
+
"loss": 0.05644471198320389,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.36363636363636365,
|
| 329 |
+
"grad_norm": 2.3219408988952637,
|
| 330 |
+
"learning_rate": 9.544460606815901e-06,
|
| 331 |
+
"loss": 0.045811206102371216,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.3715415019762846,
|
| 336 |
+
"grad_norm": 1.5839463472366333,
|
| 337 |
+
"learning_rate": 9.516893886381324e-06,
|
| 338 |
+
"loss": 0.04359353333711624,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3794466403162055,
|
| 343 |
+
"grad_norm": 3.002688407897949,
|
| 344 |
+
"learning_rate": 9.488559628808939e-06,
|
| 345 |
+
"loss": 0.03759331628680229,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.38735177865612647,
|
| 350 |
+
"grad_norm": 2.0967206954956055,
|
| 351 |
+
"learning_rate": 9.459462648822209e-06,
|
| 352 |
+
"loss": 0.042115505784749985,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.3952569169960474,
|
| 357 |
+
"grad_norm": 1.6116639375686646,
|
| 358 |
+
"learning_rate": 9.429607890750863e-06,
|
| 359 |
+
"loss": 0.03770685940980911,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.4031620553359684,
|
| 364 |
+
"grad_norm": 2.4549543857574463,
|
| 365 |
+
"learning_rate": 9.399000427690736e-06,
|
| 366 |
+
"loss": 0.039106663316488266,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.41106719367588934,
|
| 371 |
+
"grad_norm": 2.6150572299957275,
|
| 372 |
+
"learning_rate": 9.367645460641716e-06,
|
| 373 |
+
"loss": 0.03267104551196098,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.4189723320158103,
|
| 378 |
+
"grad_norm": 2.999572277069092,
|
| 379 |
+
"learning_rate": 9.335548317623957e-06,
|
| 380 |
+
"loss": 0.037257514894008636,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.4268774703557312,
|
| 385 |
+
"grad_norm": 2.002997636795044,
|
| 386 |
+
"learning_rate": 9.302714452772515e-06,
|
| 387 |
+
"loss": 0.03565370664000511,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.43478260869565216,
|
| 392 |
+
"grad_norm": 1.341861605644226,
|
| 393 |
+
"learning_rate": 9.269149445410545e-06,
|
| 394 |
+
"loss": 0.03531743586063385,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.4426877470355731,
|
| 399 |
+
"grad_norm": 2.4387803077697754,
|
| 400 |
+
"learning_rate": 9.234858999101232e-06,
|
| 401 |
+
"loss": 0.0331074595451355,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.4505928853754941,
|
| 406 |
+
"grad_norm": 2.4109466075897217,
|
| 407 |
+
"learning_rate": 9.199848940678607e-06,
|
| 408 |
+
"loss": 0.041402336210012436,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.45849802371541504,
|
| 413 |
+
"grad_norm": 1.5744589567184448,
|
| 414 |
+
"learning_rate": 9.164125219257419e-06,
|
| 415 |
+
"loss": 0.03215444087982178,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.466403162055336,
|
| 420 |
+
"grad_norm": 1.4844261407852173,
|
| 421 |
+
"learning_rate": 9.127693905222223e-06,
|
| 422 |
+
"loss": 0.033581748604774475,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.4743083003952569,
|
| 427 |
+
"grad_norm": 1.0413752794265747,
|
| 428 |
+
"learning_rate": 9.09056118919587e-06,
|
| 429 |
+
"loss": 0.028544113039970398,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.48221343873517786,
|
| 434 |
+
"grad_norm": 0.9989679455757141,
|
| 435 |
+
"learning_rate": 9.052733380987555e-06,
|
| 436 |
+
"loss": 0.028475910425186157,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.4901185770750988,
|
| 441 |
+
"grad_norm": 1.0700359344482422,
|
| 442 |
+
"learning_rate": 9.014216908520619e-06,
|
| 443 |
+
"loss": 0.02844514511525631,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.4980237154150198,
|
| 448 |
+
"grad_norm": 1.3273029327392578,
|
| 449 |
+
"learning_rate": 8.975018316740278e-06,
|
| 450 |
+
"loss": 0.032000623643398285,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5059288537549407,
|
| 455 |
+
"grad_norm": 1.6212908029556274,
|
| 456 |
+
"learning_rate": 8.93514426650147e-06,
|
| 457 |
+
"loss": 0.028899258002638817,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.5138339920948617,
|
| 462 |
+
"grad_norm": 1.4547276496887207,
|
| 463 |
+
"learning_rate": 8.894601533437e-06,
|
| 464 |
+
"loss": 0.037823665887117386,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.5217391304347826,
|
| 469 |
+
"grad_norm": 2.2724761962890625,
|
| 470 |
+
"learning_rate": 8.853397006806183e-06,
|
| 471 |
+
"loss": 0.028026675805449486,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5296442687747036,
|
| 476 |
+
"grad_norm": 1.2601908445358276,
|
| 477 |
+
"learning_rate": 8.811537688324187e-06,
|
| 478 |
+
"loss": 0.030289869755506516,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.5375494071146245,
|
| 483 |
+
"grad_norm": 1.8889567852020264,
|
| 484 |
+
"learning_rate": 8.769030690972262e-06,
|
| 485 |
+
"loss": 0.03144840523600578,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5454545454545454,
|
| 490 |
+
"grad_norm": 1.5089958906173706,
|
| 491 |
+
"learning_rate": 8.725883237789046e-06,
|
| 492 |
+
"loss": 0.0218746867030859,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5533596837944664,
|
| 497 |
+
"grad_norm": 2.9246809482574463,
|
| 498 |
+
"learning_rate": 8.682102660643196e-06,
|
| 499 |
+
"loss": 0.027847042307257652,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5612648221343873,
|
| 504 |
+
"grad_norm": 1.2851965427398682,
|
| 505 |
+
"learning_rate": 8.637696398987517e-06,
|
| 506 |
+
"loss": 0.032789893448352814,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5691699604743083,
|
| 511 |
+
"grad_norm": 2.656799554824829,
|
| 512 |
+
"learning_rate": 8.592671998594794e-06,
|
| 513 |
+
"loss": 0.02298162877559662,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5770750988142292,
|
| 518 |
+
"grad_norm": 3.905118942260742,
|
| 519 |
+
"learning_rate": 8.54703711027558e-06,
|
| 520 |
+
"loss": 0.030247194692492485,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5849802371541502,
|
| 525 |
+
"grad_norm": 1.6093782186508179,
|
| 526 |
+
"learning_rate": 8.50079948857812e-06,
|
| 527 |
+
"loss": 0.024632226675748825,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5928853754940712,
|
| 532 |
+
"grad_norm": 1.0438377857208252,
|
| 533 |
+
"learning_rate": 8.453966990470656e-06,
|
| 534 |
+
"loss": 0.022872319445014,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.6007905138339921,
|
| 539 |
+
"grad_norm": 1.2244499921798706,
|
| 540 |
+
"learning_rate": 8.406547574006326e-06,
|
| 541 |
+
"loss": 0.023443927988409996,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.6086956521739131,
|
| 546 |
+
"grad_norm": 3.3705008029937744,
|
| 547 |
+
"learning_rate": 8.358549296970877e-06,
|
| 548 |
+
"loss": 0.018181320279836655,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.616600790513834,
|
| 553 |
+
"grad_norm": 1.7295252084732056,
|
| 554 |
+
"learning_rate": 8.309980315513444e-06,
|
| 555 |
+
"loss": 0.022599346935749054,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6245059288537549,
|
| 560 |
+
"grad_norm": 1.0492676496505737,
|
| 561 |
+
"learning_rate": 8.260848882760616e-06,
|
| 562 |
+
"loss": 0.02399630844593048,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6324110671936759,
|
| 567 |
+
"grad_norm": 2.0064985752105713,
|
| 568 |
+
"learning_rate": 8.211163347414005e-06,
|
| 569 |
+
"loss": 0.01879449561238289,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6403162055335968,
|
| 574 |
+
"grad_norm": 1.1579527854919434,
|
| 575 |
+
"learning_rate": 8.160932152331587e-06,
|
| 576 |
+
"loss": 0.020744893699884415,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6482213438735178,
|
| 581 |
+
"grad_norm": 1.573108196258545,
|
| 582 |
+
"learning_rate": 8.11016383309305e-06,
|
| 583 |
+
"loss": 0.020675737410783768,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.6561264822134387,
|
| 588 |
+
"grad_norm": 0.8846186995506287,
|
| 589 |
+
"learning_rate": 8.058867016549372e-06,
|
| 590 |
+
"loss": 0.018739497289061546,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.6640316205533597,
|
| 595 |
+
"grad_norm": 1.0225743055343628,
|
| 596 |
+
"learning_rate": 8.007050419356898e-06,
|
| 597 |
+
"loss": 0.01843973435461521,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.6719367588932806,
|
| 602 |
+
"grad_norm": 3.950855016708374,
|
| 603 |
+
"learning_rate": 7.95472284649615e-06,
|
| 604 |
+
"loss": 0.017200864851474762,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.6798418972332015,
|
| 609 |
+
"grad_norm": 1.051491379737854,
|
| 610 |
+
"learning_rate": 7.90189318977564e-06,
|
| 611 |
+
"loss": 0.021487392485141754,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.6877470355731226,
|
| 616 |
+
"grad_norm": 1.5454410314559937,
|
| 617 |
+
"learning_rate": 7.848570426320918e-06,
|
| 618 |
+
"loss": 0.017703551799058914,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.6956521739130435,
|
| 623 |
+
"grad_norm": 0.9344668984413147,
|
| 624 |
+
"learning_rate": 7.794763617049124e-06,
|
| 625 |
+
"loss": 0.019065432250499725,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.7035573122529645,
|
| 630 |
+
"grad_norm": 2.3630218505859375,
|
| 631 |
+
"learning_rate": 7.740481905129307e-06,
|
| 632 |
+
"loss": 0.016719268634915352,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.7114624505928854,
|
| 637 |
+
"grad_norm": 1.2303354740142822,
|
| 638 |
+
"learning_rate": 7.685734514428767e-06,
|
| 639 |
+
"loss": 0.017706437036395073,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.7193675889328063,
|
| 644 |
+
"grad_norm": 0.782446026802063,
|
| 645 |
+
"learning_rate": 7.630530747945672e-06,
|
| 646 |
+
"loss": 0.016715146601200104,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.7272727272727273,
|
| 651 |
+
"grad_norm": 1.4542852640151978,
|
| 652 |
+
"learning_rate": 7.574879986228245e-06,
|
| 653 |
+
"loss": 0.017323564738035202,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7351778656126482,
|
| 658 |
+
"grad_norm": 0.8882444500923157,
|
| 659 |
+
"learning_rate": 7.518791685780769e-06,
|
| 660 |
+
"loss": 0.017167117446660995,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7430830039525692,
|
| 665 |
+
"grad_norm": 1.341637134552002,
|
| 666 |
+
"learning_rate": 7.462275377456671e-06,
|
| 667 |
+
"loss": 0.017168637365102768,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.7509881422924901,
|
| 672 |
+
"grad_norm": 0.8386677503585815,
|
| 673 |
+
"learning_rate": 7.405340664838994e-06,
|
| 674 |
+
"loss": 0.016178295016288757,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.758893280632411,
|
| 679 |
+
"grad_norm": 0.9866053462028503,
|
| 680 |
+
"learning_rate": 7.3479972226084925e-06,
|
| 681 |
+
"loss": 0.017345719039440155,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.766798418972332,
|
| 686 |
+
"grad_norm": 0.7647860646247864,
|
| 687 |
+
"learning_rate": 7.290254794899665e-06,
|
| 688 |
+
"loss": 0.015173953026533127,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.7747035573122529,
|
| 693 |
+
"grad_norm": 0.6555814146995544,
|
| 694 |
+
"learning_rate": 7.232123193644957e-06,
|
| 695 |
+
"loss": 0.012351523153483868,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.782608695652174,
|
| 700 |
+
"grad_norm": 0.7750186920166016,
|
| 701 |
+
"learning_rate": 7.173612296907473e-06,
|
| 702 |
+
"loss": 0.013352451846003532,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.7905138339920948,
|
| 707 |
+
"grad_norm": 1.8240841627120972,
|
| 708 |
+
"learning_rate": 7.114732047202433e-06,
|
| 709 |
+
"loss": 0.016192153096199036,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7984189723320159,
|
| 714 |
+
"grad_norm": 0.6934201717376709,
|
| 715 |
+
"learning_rate": 7.055492449807684e-06,
|
| 716 |
+
"loss": 0.015515042468905449,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8063241106719368,
|
| 721 |
+
"grad_norm": 0.809237003326416,
|
| 722 |
+
"learning_rate": 6.995903571063541e-06,
|
| 723 |
+
"loss": 0.018547531217336655,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.8142292490118577,
|
| 728 |
+
"grad_norm": 0.6926773190498352,
|
| 729 |
+
"learning_rate": 6.935975536662254e-06,
|
| 730 |
+
"loss": 0.013686897233128548,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.8221343873517787,
|
| 735 |
+
"grad_norm": 0.5690931081771851,
|
| 736 |
+
"learning_rate": 6.875718529927404e-06,
|
| 737 |
+
"loss": 0.013292870484292507,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.8300395256916996,
|
| 742 |
+
"grad_norm": 0.6487743258476257,
|
| 743 |
+
"learning_rate": 6.815142790083473e-06,
|
| 744 |
+
"loss": 0.013666905462741852,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.8379446640316206,
|
| 749 |
+
"grad_norm": 0.6930609941482544,
|
| 750 |
+
"learning_rate": 6.754258610515949e-06,
|
| 751 |
+
"loss": 0.012154589407145977,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.8458498023715415,
|
| 756 |
+
"grad_norm": 0.7813454270362854,
|
| 757 |
+
"learning_rate": 6.6930763370222104e-06,
|
| 758 |
+
"loss": 0.010252205654978752,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.8537549407114624,
|
| 763 |
+
"grad_norm": 0.8867809176445007,
|
| 764 |
+
"learning_rate": 6.631606366053507e-06,
|
| 765 |
+
"loss": 0.0136980339884758,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.8616600790513834,
|
| 770 |
+
"grad_norm": 1.073371171951294,
|
| 771 |
+
"learning_rate": 6.5698591429483286e-06,
|
| 772 |
+
"loss": 0.0125902583822608,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.8695652173913043,
|
| 777 |
+
"grad_norm": 0.9057207107543945,
|
| 778 |
+
"learning_rate": 6.507845160157476e-06,
|
| 779 |
+
"loss": 0.01218440942466259,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.8774703557312253,
|
| 784 |
+
"grad_norm": 0.7888494729995728,
|
| 785 |
+
"learning_rate": 6.445574955461134e-06,
|
| 786 |
+
"loss": 0.010093772783875465,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.8853754940711462,
|
| 791 |
+
"grad_norm": 1.1179150342941284,
|
| 792 |
+
"learning_rate": 6.383059110178205e-06,
|
| 793 |
+
"loss": 0.012896791100502014,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.8932806324110671,
|
| 798 |
+
"grad_norm": 0.7764596939086914,
|
| 799 |
+
"learning_rate": 6.320308247368285e-06,
|
| 800 |
+
"loss": 0.011423065327107906,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.9011857707509882,
|
| 805 |
+
"grad_norm": 0.6116583943367004,
|
| 806 |
+
"learning_rate": 6.2573330300265375e-06,
|
| 807 |
+
"loss": 0.010218895971775055,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.9090909090909091,
|
| 812 |
+
"grad_norm": 0.7787550687789917,
|
| 813 |
+
"learning_rate": 6.1941441592717564e-06,
|
| 814 |
+
"loss": 0.011938227340579033,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.9169960474308301,
|
| 819 |
+
"grad_norm": 1.4601852893829346,
|
| 820 |
+
"learning_rate": 6.130752372527981e-06,
|
| 821 |
+
"loss": 0.010627692565321922,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.924901185770751,
|
| 826 |
+
"grad_norm": 1.234760046005249,
|
| 827 |
+
"learning_rate": 6.067168441699927e-06,
|
| 828 |
+
"loss": 0.010819574818015099,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.932806324110672,
|
| 833 |
+
"grad_norm": 0.9453625679016113,
|
| 834 |
+
"learning_rate": 6.0034031713425636e-06,
|
| 835 |
+
"loss": 0.01119691040366888,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.9407114624505929,
|
| 840 |
+
"grad_norm": 0.571775496006012,
|
| 841 |
+
"learning_rate": 5.939467396825137e-06,
|
| 842 |
+
"loss": 0.009475297294557095,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.9486166007905138,
|
| 847 |
+
"grad_norm": 0.6600437164306641,
|
| 848 |
+
"learning_rate": 5.875371982489959e-06,
|
| 849 |
+
"loss": 0.009599719196557999,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.9565217391304348,
|
| 854 |
+
"grad_norm": 1.791795253753662,
|
| 855 |
+
"learning_rate": 5.811127819806277e-06,
|
| 856 |
+
"loss": 0.009260142222046852,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.9644268774703557,
|
| 861 |
+
"grad_norm": 0.4926028251647949,
|
| 862 |
+
"learning_rate": 5.746745825519539e-06,
|
| 863 |
+
"loss": 0.007991988211870193,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.9723320158102767,
|
| 868 |
+
"grad_norm": 0.8104107975959778,
|
| 869 |
+
"learning_rate": 5.682236939796337e-06,
|
| 870 |
+
"loss": 0.007563046179711819,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.9802371541501976,
|
| 875 |
+
"grad_norm": 0.9674690365791321,
|
| 876 |
+
"learning_rate": 5.617612124365411e-06,
|
| 877 |
+
"loss": 0.00828514900058508,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.9881422924901185,
|
| 882 |
+
"grad_norm": 0.9782751202583313,
|
| 883 |
+
"learning_rate": 5.55288236065495e-06,
|
| 884 |
+
"loss": 0.010305792093276978,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.9960474308300395,
|
| 889 |
+
"grad_norm": 0.7988375425338745,
|
| 890 |
+
"learning_rate": 5.4880586479265774e-06,
|
| 891 |
+
"loss": 0.008228166960179806,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.0,
|
| 896 |
+
"grad_norm": 1.5495506525039673,
|
| 897 |
+
"learning_rate": 5.423152001406282e-06,
|
| 898 |
+
"loss": 0.006378662772476673,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.007905138339921,
|
| 903 |
+
"grad_norm": 0.6450592875480652,
|
| 904 |
+
"learning_rate": 5.358173450412649e-06,
|
| 905 |
+
"loss": 0.006625718902796507,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.0158102766798418,
|
| 910 |
+
"grad_norm": 0.6858895421028137,
|
| 911 |
+
"learning_rate": 5.293134036482697e-06,
|
| 912 |
+
"loss": 0.009561844170093536,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.023715415019763,
|
| 917 |
+
"grad_norm": 0.9555614590644836,
|
| 918 |
+
"learning_rate": 5.228044811495632e-06,
|
| 919 |
+
"loss": 0.00772759597748518,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.0316205533596838,
|
| 924 |
+
"grad_norm": 0.46189069747924805,
|
| 925 |
+
"learning_rate": 5.162916835794843e-06,
|
| 926 |
+
"loss": 0.006483909673988819,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.0395256916996047,
|
| 931 |
+
"grad_norm": 0.9199791550636292,
|
| 932 |
+
"learning_rate": 5.097761176308471e-06,
|
| 933 |
+
"loss": 0.007392100058495998,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.0474308300395256,
|
| 938 |
+
"grad_norm": 0.8859105706214905,
|
| 939 |
+
"learning_rate": 5.032588904668851e-06,
|
| 940 |
+
"loss": 0.007549676578491926,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.0553359683794465,
|
| 945 |
+
"grad_norm": 1.559400200843811,
|
| 946 |
+
"learning_rate": 4.967411095331149e-06,
|
| 947 |
+
"loss": 0.008893043734133244,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.0632411067193677,
|
| 952 |
+
"grad_norm": 0.8761066794395447,
|
| 953 |
+
"learning_rate": 4.9022388236915306e-06,
|
| 954 |
+
"loss": 0.008203836157917976,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.0711462450592886,
|
| 959 |
+
"grad_norm": 0.9917057752609253,
|
| 960 |
+
"learning_rate": 4.837083164205159e-06,
|
| 961 |
+
"loss": 0.007457341533154249,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.0790513833992095,
|
| 966 |
+
"grad_norm": 0.8223298192024231,
|
| 967 |
+
"learning_rate": 4.771955188504371e-06,
|
| 968 |
+
"loss": 0.006578846834599972,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.0869565217391304,
|
| 973 |
+
"grad_norm": 0.9074115753173828,
|
| 974 |
+
"learning_rate": 4.7068659635173034e-06,
|
| 975 |
+
"loss": 0.007472721394151449,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.0948616600790513,
|
| 980 |
+
"grad_norm": 0.43064776062965393,
|
| 981 |
+
"learning_rate": 4.641826549587352e-06,
|
| 982 |
+
"loss": 0.005520315375179052,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.1027667984189724,
|
| 987 |
+
"grad_norm": 0.5693991184234619,
|
| 988 |
+
"learning_rate": 4.57684799859372e-06,
|
| 989 |
+
"loss": 0.005801580846309662,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.1106719367588933,
|
| 994 |
+
"grad_norm": 0.6696038246154785,
|
| 995 |
+
"learning_rate": 4.511941352073424e-06,
|
| 996 |
+
"loss": 0.0058603910729289055,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.1185770750988142,
|
| 1001 |
+
"grad_norm": 0.3668532371520996,
|
| 1002 |
+
"learning_rate": 4.447117639345052e-06,
|
| 1003 |
+
"loss": 0.004593988414853811,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.1264822134387351,
|
| 1008 |
+
"grad_norm": 0.47169455885887146,
|
| 1009 |
+
"learning_rate": 4.382387875634592e-06,
|
| 1010 |
+
"loss": 0.008238094858825207,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.1343873517786562,
|
| 1015 |
+
"grad_norm": 0.5430543422698975,
|
| 1016 |
+
"learning_rate": 4.317763060203665e-06,
|
| 1017 |
+
"loss": 0.005791869014501572,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.1422924901185771,
|
| 1022 |
+
"grad_norm": 0.3594886064529419,
|
| 1023 |
+
"learning_rate": 4.253254174480462e-06,
|
| 1024 |
+
"loss": 0.0048874374479055405,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.150197628458498,
|
| 1029 |
+
"grad_norm": 0.4173608720302582,
|
| 1030 |
+
"learning_rate": 4.188872180193723e-06,
|
| 1031 |
+
"loss": 0.004091914743185043,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.158102766798419,
|
| 1036 |
+
"grad_norm": 0.3325529396533966,
|
| 1037 |
+
"learning_rate": 4.124628017510043e-06,
|
| 1038 |
+
"loss": 0.004636446014046669,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.1660079051383399,
|
| 1043 |
+
"grad_norm": 0.25673943758010864,
|
| 1044 |
+
"learning_rate": 4.060532603174865e-06,
|
| 1045 |
+
"loss": 0.003512149676680565,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.1739130434782608,
|
| 1050 |
+
"grad_norm": 0.8225778341293335,
|
| 1051 |
+
"learning_rate": 3.996596828657437e-06,
|
| 1052 |
+
"loss": 0.004270743578672409,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.1818181818181819,
|
| 1057 |
+
"grad_norm": 0.5607500672340393,
|
| 1058 |
+
"learning_rate": 3.932831558300074e-06,
|
| 1059 |
+
"loss": 0.004617046099156141,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.1897233201581028,
|
| 1064 |
+
"grad_norm": 0.31929197907447815,
|
| 1065 |
+
"learning_rate": 3.869247627472021e-06,
|
| 1066 |
+
"loss": 0.005788344424217939,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.1976284584980237,
|
| 1071 |
+
"grad_norm": 0.42114102840423584,
|
| 1072 |
+
"learning_rate": 3.8058558407282465e-06,
|
| 1073 |
+
"loss": 0.003865439211949706,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.2055335968379446,
|
| 1078 |
+
"grad_norm": 0.3219948410987854,
|
| 1079 |
+
"learning_rate": 3.742666969973463e-06,
|
| 1080 |
+
"loss": 0.003933921456336975,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.2134387351778657,
|
| 1085 |
+
"grad_norm": 0.40599867701530457,
|
| 1086 |
+
"learning_rate": 3.6796917526317153e-06,
|
| 1087 |
+
"loss": 0.0035232803784310818,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.2213438735177866,
|
| 1092 |
+
"grad_norm": 0.5560054183006287,
|
| 1093 |
+
"learning_rate": 3.6169408898217973e-06,
|
| 1094 |
+
"loss": 0.005120030604302883,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.2292490118577075,
|
| 1099 |
+
"grad_norm": 0.220501109957695,
|
| 1100 |
+
"learning_rate": 3.554425044538868e-06,
|
| 1101 |
+
"loss": 0.0034878007136285305,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.2371541501976284,
|
| 1106 |
+
"grad_norm": 0.33977070450782776,
|
| 1107 |
+
"learning_rate": 3.4921548398425246e-06,
|
| 1108 |
+
"loss": 0.0032174824737012386,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.2450592885375493,
|
| 1113 |
+
"grad_norm": 0.4450984597206116,
|
| 1114 |
+
"learning_rate": 3.430140857051675e-06,
|
| 1115 |
+
"loss": 0.003823072649538517,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.2529644268774702,
|
| 1120 |
+
"grad_norm": 0.3816457986831665,
|
| 1121 |
+
"learning_rate": 3.3683936339464957e-06,
|
| 1122 |
+
"loss": 0.005069481208920479,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.2608695652173914,
|
| 1127 |
+
"grad_norm": 0.3566303551197052,
|
| 1128 |
+
"learning_rate": 3.306923662977789e-06,
|
| 1129 |
+
"loss": 0.003994639962911606,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.2687747035573123,
|
| 1134 |
+
"grad_norm": 0.27767708897590637,
|
| 1135 |
+
"learning_rate": 3.2457413894840516e-06,
|
| 1136 |
+
"loss": 0.004050858318805695,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.2766798418972332,
|
| 1141 |
+
"grad_norm": 0.6555705666542053,
|
| 1142 |
+
"learning_rate": 3.184857209916528e-06,
|
| 1143 |
+
"loss": 0.005383260548114777,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.2845849802371543,
|
| 1148 |
+
"grad_norm": 0.38021984696388245,
|
| 1149 |
+
"learning_rate": 3.1242814700725977e-06,
|
| 1150 |
+
"loss": 0.004063721280544996,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.2924901185770752,
|
| 1155 |
+
"grad_norm": 0.5424526929855347,
|
| 1156 |
+
"learning_rate": 3.064024463337747e-06,
|
| 1157 |
+
"loss": 0.0038591232150793076,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.300395256916996,
|
| 1162 |
+
"grad_norm": 0.47592127323150635,
|
| 1163 |
+
"learning_rate": 3.0040964289364618e-06,
|
| 1164 |
+
"loss": 0.003366923425346613,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.308300395256917,
|
| 1169 |
+
"grad_norm": 0.5974819660186768,
|
| 1170 |
+
"learning_rate": 2.944507550192318e-06,
|
| 1171 |
+
"loss": 0.002857337472960353,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.316205533596838,
|
| 1176 |
+
"grad_norm": 0.3529670238494873,
|
| 1177 |
+
"learning_rate": 2.885267952797569e-06,
|
| 1178 |
+
"loss": 0.0030626333318650723,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.3241106719367588,
|
| 1183 |
+
"grad_norm": 0.2585272789001465,
|
| 1184 |
+
"learning_rate": 2.826387703092528e-06,
|
| 1185 |
+
"loss": 0.0034771538339555264,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.33201581027668,
|
| 1190 |
+
"grad_norm": 0.26374223828315735,
|
| 1191 |
+
"learning_rate": 2.7678768063550454e-06,
|
| 1192 |
+
"loss": 0.0024083282332867384,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.3399209486166008,
|
| 1197 |
+
"grad_norm": 0.3238804340362549,
|
| 1198 |
+
"learning_rate": 2.7097452051003375e-06,
|
| 1199 |
+
"loss": 0.002948346547782421,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.3478260869565217,
|
| 1204 |
+
"grad_norm": 0.7156248688697815,
|
| 1205 |
+
"learning_rate": 2.6520027773915075e-06,
|
| 1206 |
+
"loss": 0.003965778276324272,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.3557312252964426,
|
| 1211 |
+
"grad_norm": 0.7334011197090149,
|
| 1212 |
+
"learning_rate": 2.594659335161008e-06,
|
| 1213 |
+
"loss": 0.0036394651979207993,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.3636363636363638,
|
| 1218 |
+
"grad_norm": 0.3002645671367645,
|
| 1219 |
+
"learning_rate": 2.5377246225433306e-06,
|
| 1220 |
+
"loss": 0.00266829039901495,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.3715415019762847,
|
| 1225 |
+
"grad_norm": 1.095378041267395,
|
| 1226 |
+
"learning_rate": 2.481208314219233e-06,
|
| 1227 |
+
"loss": 0.0027972832322120667,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.3794466403162056,
|
| 1232 |
+
"grad_norm": 0.3117959201335907,
|
| 1233 |
+
"learning_rate": 2.4251200137717545e-06,
|
| 1234 |
+
"loss": 0.0031013768166303635,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.3873517786561265,
|
| 1239 |
+
"grad_norm": 0.26806971430778503,
|
| 1240 |
+
"learning_rate": 2.3694692520543293e-06,
|
| 1241 |
+
"loss": 0.0024062381125986576,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.3952569169960474,
|
| 1246 |
+
"grad_norm": 0.5937316417694092,
|
| 1247 |
+
"learning_rate": 2.3142654855712353e-06,
|
| 1248 |
+
"loss": 0.002327256603166461,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.4031620553359683,
|
| 1253 |
+
"grad_norm": 0.3918744921684265,
|
| 1254 |
+
"learning_rate": 2.259518094870693e-06,
|
| 1255 |
+
"loss": 0.0020535802468657494,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.4110671936758894,
|
| 1260 |
+
"grad_norm": 0.2091464251279831,
|
| 1261 |
+
"learning_rate": 2.2052363829508776e-06,
|
| 1262 |
+
"loss": 0.0014890478923916817,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.4189723320158103,
|
| 1267 |
+
"grad_norm": 0.4339018166065216,
|
| 1268 |
+
"learning_rate": 2.151429573679084e-06,
|
| 1269 |
+
"loss": 0.0025304430164396763,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.4268774703557312,
|
| 1274 |
+
"grad_norm": 0.35317882895469666,
|
| 1275 |
+
"learning_rate": 2.098106810224362e-06,
|
| 1276 |
+
"loss": 0.0023727738298475742,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.434782608695652,
|
| 1281 |
+
"grad_norm": 0.19894669950008392,
|
| 1282 |
+
"learning_rate": 2.0452771535038518e-06,
|
| 1283 |
+
"loss": 0.0024110060185194016,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.4426877470355732,
|
| 1288 |
+
"grad_norm": 0.1785030961036682,
|
| 1289 |
+
"learning_rate": 1.9929495806431024e-06,
|
| 1290 |
+
"loss": 0.0024499250575900078,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.4505928853754941,
|
| 1295 |
+
"grad_norm": 0.17710956931114197,
|
| 1296 |
+
"learning_rate": 1.9411329834506286e-06,
|
| 1297 |
+
"loss": 0.002269516699016094,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.458498023715415,
|
| 1302 |
+
"grad_norm": 0.24377702176570892,
|
| 1303 |
+
"learning_rate": 1.8898361669069497e-06,
|
| 1304 |
+
"loss": 0.002242635004222393,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.466403162055336,
|
| 1309 |
+
"grad_norm": 0.17319411039352417,
|
| 1310 |
+
"learning_rate": 1.8390678476684143e-06,
|
| 1311 |
+
"loss": 0.0015832515200600028,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.4743083003952568,
|
| 1316 |
+
"grad_norm": 0.3506351411342621,
|
| 1317 |
+
"learning_rate": 1.7888366525859968e-06,
|
| 1318 |
+
"loss": 0.0012599490582942963,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.4822134387351777,
|
| 1323 |
+
"grad_norm": 0.49592605233192444,
|
| 1324 |
+
"learning_rate": 1.7391511172393849e-06,
|
| 1325 |
+
"loss": 0.0021263286471366882,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.4901185770750989,
|
| 1330 |
+
"grad_norm": 0.3620193600654602,
|
| 1331 |
+
"learning_rate": 1.6900196844865575e-06,
|
| 1332 |
+
"loss": 0.003170725889503956,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.4980237154150198,
|
| 1337 |
+
"grad_norm": 0.155870258808136,
|
| 1338 |
+
"learning_rate": 1.6414507030291249e-06,
|
| 1339 |
+
"loss": 0.0018343538977205753,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.5059288537549407,
|
| 1344 |
+
"grad_norm": 0.3445264995098114,
|
| 1345 |
+
"learning_rate": 1.5934524259936757e-06,
|
| 1346 |
+
"loss": 0.0016385617200285196,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.5138339920948618,
|
| 1351 |
+
"grad_norm": 0.16461081802845,
|
| 1352 |
+
"learning_rate": 1.5460330095293447e-06,
|
| 1353 |
+
"loss": 0.0017919661477208138,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.5217391304347827,
|
| 1358 |
+
"grad_norm": 0.2403573989868164,
|
| 1359 |
+
"learning_rate": 1.4992005114218805e-06,
|
| 1360 |
+
"loss": 0.0014230485539883375,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.5296442687747036,
|
| 1365 |
+
"grad_norm": 0.20152945816516876,
|
| 1366 |
+
"learning_rate": 1.4529628897244214e-06,
|
| 1367 |
+
"loss": 0.001776442863047123,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.5375494071146245,
|
| 1372 |
+
"grad_norm": 0.2909387946128845,
|
| 1373 |
+
"learning_rate": 1.4073280014052077e-06,
|
| 1374 |
+
"loss": 0.0016154279001057148,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.5454545454545454,
|
| 1379 |
+
"grad_norm": 0.16838698089122772,
|
| 1380 |
+
"learning_rate": 1.3623036010124845e-06,
|
| 1381 |
+
"loss": 0.001428220421075821,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.5533596837944663,
|
| 1386 |
+
"grad_norm": 0.30013203620910645,
|
| 1387 |
+
"learning_rate": 1.3178973393568055e-06,
|
| 1388 |
+
"loss": 0.0018139774911105633,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.5612648221343872,
|
| 1393 |
+
"grad_norm": 0.18099738657474518,
|
| 1394 |
+
"learning_rate": 1.2741167622109557e-06,
|
| 1395 |
+
"loss": 0.001746204448863864,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.5691699604743083,
|
| 1400 |
+
"grad_norm": 0.17493419349193573,
|
| 1401 |
+
"learning_rate": 1.2309693090277392e-06,
|
| 1402 |
+
"loss": 0.0011324796359986067,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.5770750988142292,
|
| 1407 |
+
"grad_norm": 0.10918938368558884,
|
| 1408 |
+
"learning_rate": 1.1884623116758121e-06,
|
| 1409 |
+
"loss": 0.0017581683350726962,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.5849802371541502,
|
| 1414 |
+
"grad_norm": 0.16340740025043488,
|
| 1415 |
+
"learning_rate": 1.1466029931938182e-06,
|
| 1416 |
+
"loss": 0.0019770762883126736,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.5928853754940713,
|
| 1421 |
+
"grad_norm": 0.10986919701099396,
|
| 1422 |
+
"learning_rate": 1.1053984665630025e-06,
|
| 1423 |
+
"loss": 0.0012620555935427547,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.6007905138339922,
|
| 1428 |
+
"grad_norm": 0.12008050829172134,
|
| 1429 |
+
"learning_rate": 1.064855733498531e-06,
|
| 1430 |
+
"loss": 0.001485881395637989,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.608695652173913,
|
| 1435 |
+
"grad_norm": 0.15469031035900116,
|
| 1436 |
+
"learning_rate": 1.024981683259723e-06,
|
| 1437 |
+
"loss": 0.0012907737400382757,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.616600790513834,
|
| 1442 |
+
"grad_norm": 0.4024447500705719,
|
| 1443 |
+
"learning_rate": 9.857830914793827e-07,
|
| 1444 |
+
"loss": 0.0016375603154301643,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.6245059288537549,
|
| 1449 |
+
"grad_norm": 0.18589317798614502,
|
| 1450 |
+
"learning_rate": 9.472666190124457e-07,
|
| 1451 |
+
"loss": 0.0016270795604214072,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.6324110671936758,
|
| 1456 |
+
"grad_norm": 0.20000141859054565,
|
| 1457 |
+
"learning_rate": 9.094388108041302e-07,
|
| 1458 |
+
"loss": 0.0013950997963547707,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.6403162055335967,
|
| 1463 |
+
"grad_norm": 0.11565146595239639,
|
| 1464 |
+
"learning_rate": 8.723060947777778e-07,
|
| 1465 |
+
"loss": 0.0012794029898941517,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.6482213438735178,
|
| 1470 |
+
"grad_norm": 0.12397163361310959,
|
| 1471 |
+
"learning_rate": 8.358747807425827e-07,
|
| 1472 |
+
"loss": 0.0010168085573241115,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.6561264822134387,
|
| 1477 |
+
"grad_norm": 0.0919703021645546,
|
| 1478 |
+
"learning_rate": 8.001510593213946e-07,
|
| 1479 |
+
"loss": 0.0010871316771954298,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.6640316205533598,
|
| 1484 |
+
"grad_norm": 0.1583489179611206,
|
| 1485 |
+
"learning_rate": 7.651410008987698e-07,
|
| 1486 |
+
"loss": 0.0010751537047326565,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.6719367588932808,
|
| 1491 |
+
"grad_norm": 0.7466919422149658,
|
| 1492 |
+
"learning_rate": 7.308505545894567e-07,
|
| 1493 |
+
"loss": 0.001687210751697421,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.6798418972332017,
|
| 1498 |
+
"grad_norm": 0.07502717524766922,
|
| 1499 |
+
"learning_rate": 6.972855472274853e-07,
|
| 1500 |
+
"loss": 0.0007722179288975894,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.6877470355731226,
|
| 1505 |
+
"grad_norm": 0.1141902506351471,
|
| 1506 |
+
"learning_rate": 6.644516823760439e-07,
|
| 1507 |
+
"loss": 0.0009294347837567329,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.6956521739130435,
|
| 1512 |
+
"grad_norm": 0.15124619007110596,
|
| 1513 |
+
"learning_rate": 6.323545393582847e-07,
|
| 1514 |
+
"loss": 0.001659550704061985,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.7035573122529644,
|
| 1519 |
+
"grad_norm": 0.3951869308948517,
|
| 1520 |
+
"learning_rate": 6.009995723092655e-07,
|
| 1521 |
+
"loss": 0.0014122012071311474,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.7114624505928853,
|
| 1526 |
+
"grad_norm": 0.0976693257689476,
|
| 1527 |
+
"learning_rate": 5.703921092491393e-07,
|
| 1528 |
+
"loss": 0.0012070460943505168,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.7193675889328062,
|
| 1533 |
+
"grad_norm": 0.11402706801891327,
|
| 1534 |
+
"learning_rate": 5.405373511777939e-07,
|
| 1535 |
+
"loss": 0.0017175176180899143,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.7272727272727273,
|
| 1540 |
+
"grad_norm": 0.09963912516832352,
|
| 1541 |
+
"learning_rate": 5.114403711910631e-07,
|
| 1542 |
+
"loss": 0.0010232492350041866,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.7351778656126482,
|
| 1547 |
+
"grad_norm": 0.14201438426971436,
|
| 1548 |
+
"learning_rate": 4.831061136186787e-07,
|
| 1549 |
+
"loss": 0.001740424893796444,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.7430830039525693,
|
| 1554 |
+
"grad_norm": 0.38846060633659363,
|
| 1555 |
+
"learning_rate": 4.555393931841001e-07,
|
| 1556 |
+
"loss": 0.0011055013164877892,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.7509881422924902,
|
| 1561 |
+
"grad_norm": 0.10771837830543518,
|
| 1562 |
+
"learning_rate": 4.287448941863692e-07,
|
| 1563 |
+
"loss": 0.001104390830732882,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.7588932806324111,
|
| 1568 |
+
"grad_norm": 0.14714020490646362,
|
| 1569 |
+
"learning_rate": 4.0272716970412516e-07,
|
| 1570 |
+
"loss": 0.0008194673573598266,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.766798418972332,
|
| 1575 |
+
"grad_norm": 0.07330888509750366,
|
| 1576 |
+
"learning_rate": 3.7749064082191976e-07,
|
| 1577 |
+
"loss": 0.0009911219822242856,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.774703557312253,
|
| 1582 |
+
"grad_norm": 0.10180023312568665,
|
| 1583 |
+
"learning_rate": 3.53039595878959e-07,
|
| 1584 |
+
"loss": 0.001625074539333582,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.7826086956521738,
|
| 1589 |
+
"grad_norm": 0.06447973102331161,
|
| 1590 |
+
"learning_rate": 3.2937818974040637e-07,
|
| 1591 |
+
"loss": 0.0008694930002093315,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.7905138339920947,
|
| 1596 |
+
"grad_norm": 0.08145026117563248,
|
| 1597 |
+
"learning_rate": 3.0651044309136016e-07,
|
| 1598 |
+
"loss": 0.0008252444094978273,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.7984189723320159,
|
| 1603 |
+
"grad_norm": 0.08554449677467346,
|
| 1604 |
+
"learning_rate": 2.844402417536374e-07,
|
| 1605 |
+
"loss": 0.0012224346864968538,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.8063241106719368,
|
| 1610 |
+
"grad_norm": 0.07281271368265152,
|
| 1611 |
+
"learning_rate": 2.631713360254734e-07,
|
| 1612 |
+
"loss": 0.001510316040366888,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.8142292490118577,
|
| 1617 |
+
"grad_norm": 0.08442871272563934,
|
| 1618 |
+
"learning_rate": 2.4270734004424643e-07,
|
| 1619 |
+
"loss": 0.0011369193671271205,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.8221343873517788,
|
| 1624 |
+
"grad_norm": 0.42188599705696106,
|
| 1625 |
+
"learning_rate": 2.2305173117234236e-07,
|
| 1626 |
+
"loss": 0.0010267121251672506,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.8300395256916997,
|
| 1631 |
+
"grad_norm": 0.3233380913734436,
|
| 1632 |
+
"learning_rate": 2.042078494062616e-07,
|
| 1633 |
+
"loss": 0.0010518430499359965,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.8379446640316206,
|
| 1638 |
+
"grad_norm": 0.07007841765880585,
|
| 1639 |
+
"learning_rate": 1.861788968090683e-07,
|
| 1640 |
+
"loss": 0.0010208109160885215,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.8458498023715415,
|
| 1645 |
+
"grad_norm": 0.13290899991989136,
|
| 1646 |
+
"learning_rate": 1.68967936966275e-07,
|
| 1647 |
+
"loss": 0.001091842306777835,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.8537549407114624,
|
| 1652 |
+
"grad_norm": 0.11768372356891632,
|
| 1653 |
+
"learning_rate": 1.5257789446526172e-07,
|
| 1654 |
+
"loss": 0.0011766953393816948,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.8616600790513833,
|
| 1659 |
+
"grad_norm": 0.06013408675789833,
|
| 1660 |
+
"learning_rate": 1.3701155439831249e-07,
|
| 1661 |
+
"loss": 0.0009503662586212158,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.8695652173913042,
|
| 1666 |
+
"grad_norm": 0.09728754311800003,
|
| 1667 |
+
"learning_rate": 1.2227156188935552e-07,
|
| 1668 |
+
"loss": 0.001422834349796176,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.8774703557312253,
|
| 1673 |
+
"grad_norm": 0.10177087783813477,
|
| 1674 |
+
"learning_rate": 1.0836042164448945e-07,
|
| 1675 |
+
"loss": 0.000977285671979189,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.8853754940711462,
|
| 1680 |
+
"grad_norm": 0.05201971158385277,
|
| 1681 |
+
"learning_rate": 9.528049752636714e-08,
|
| 1682 |
+
"loss": 0.0007519847131334245,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.8932806324110671,
|
| 1687 |
+
"grad_norm": 0.08124888688325882,
|
| 1688 |
+
"learning_rate": 8.303401215251583e-08,
|
| 1689 |
+
"loss": 0.0009279723162762821,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.9011857707509883,
|
| 1694 |
+
"grad_norm": 0.13961008191108704,
|
| 1695 |
+
"learning_rate": 7.16230465176565e-08,
|
| 1696 |
+
"loss": 0.0008354739984497428,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.9090909090909092,
|
| 1701 |
+
"grad_norm": 0.05196058750152588,
|
| 1702 |
+
"learning_rate": 6.104953964008897e-08,
|
| 1703 |
+
"loss": 0.0009414660162292421,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.91699604743083,
|
| 1708 |
+
"grad_norm": 0.07124029099941254,
|
| 1709 |
+
"learning_rate": 5.1315288232201e-08,
|
| 1710 |
+
"loss": 0.0008576106047257781,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.924901185770751,
|
| 1715 |
+
"grad_norm": 0.05527196452021599,
|
| 1716 |
+
"learning_rate": 4.2421946395164174e-08,
|
| 1717 |
+
"loss": 0.000688934582285583,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.9328063241106719,
|
| 1722 |
+
"grad_norm": 0.09299924224615097,
|
| 1723 |
+
"learning_rate": 3.437102533785541e-08,
|
| 1724 |
+
"loss": 0.0009912521345540881,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.9407114624505928,
|
| 1729 |
+
"grad_norm": 0.057924672961235046,
|
| 1730 |
+
"learning_rate": 2.7163893120066288e-08,
|
| 1731 |
+
"loss": 0.0007424440118484199,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.9486166007905137,
|
| 1736 |
+
"grad_norm": 0.04557636380195618,
|
| 1737 |
+
"learning_rate": 2.0801774420031172e-08,
|
| 1738 |
+
"loss": 0.0006406870088540018,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.9565217391304348,
|
| 1743 |
+
"grad_norm": 0.17290093004703522,
|
| 1744 |
+
"learning_rate": 1.5285750326325953e-08,
|
| 1745 |
+
"loss": 0.000998645555227995,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.9644268774703557,
|
| 1750 |
+
"grad_norm": 0.09099423885345459,
|
| 1751 |
+
"learning_rate": 1.0616758154161633e-08,
|
| 1752 |
+
"loss": 0.0008060235413722694,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.9723320158102768,
|
| 1757 |
+
"grad_norm": 0.09854293614625931,
|
| 1758 |
+
"learning_rate": 6.7955912861095155e-09,
|
| 1759 |
+
"loss": 0.0011094892397522926,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.9802371541501977,
|
| 1764 |
+
"grad_norm": 0.10680408030748367,
|
| 1765 |
+
"learning_rate": 3.822899037286276e-09,
|
| 1766 |
+
"loss": 0.0010115326149389148,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.9881422924901186,
|
| 1771 |
+
"grad_norm": 0.06111829727888107,
|
| 1772 |
+
"learning_rate": 1.6991865450188827e-09,
|
| 1773 |
+
"loss": 0.0006179866613820195,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.9960474308300395,
|
| 1778 |
+
"grad_norm": 0.07574126869440079,
|
| 1779 |
+
"learning_rate": 4.2481468300603625e-10,
|
| 1780 |
+
"loss": 0.0009162229252979159,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.0,
|
| 1785 |
+
"grad_norm": 0.6144468784332275,
|
| 1786 |
+
"learning_rate": 0.0,
|
| 1787 |
+
"loss": 0.0009967066580429673,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
}
|
| 1790 |
+
],
|
| 1791 |
+
"logging_steps": 1,
|
| 1792 |
+
"max_steps": 254,
|
| 1793 |
+
"num_input_tokens_seen": 0,
|
| 1794 |
+
"num_train_epochs": 2,
|
| 1795 |
+
"save_steps": 100,
|
| 1796 |
+
"stateful_callbacks": {
|
| 1797 |
+
"TrainerControl": {
|
| 1798 |
+
"args": {
|
| 1799 |
+
"should_epoch_stop": false,
|
| 1800 |
+
"should_evaluate": false,
|
| 1801 |
+
"should_log": false,
|
| 1802 |
+
"should_save": true,
|
| 1803 |
+
"should_training_stop": true
|
| 1804 |
+
},
|
| 1805 |
+
"attributes": {}
|
| 1806 |
+
}
|
| 1807 |
+
},
|
| 1808 |
+
"total_flos": 1.983196683879999e+19,
|
| 1809 |
+
"train_batch_size": 4,
|
| 1810 |
+
"trial_name": null,
|
| 1811 |
+
"trial_params": null
|
| 1812 |
+
}
|
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2394f2b24fbf7e0ddd5793740885569f4b133c14aa0ad02fda94d39ea061b29d
|
| 3 |
+
size 9297
|
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3-vl-4b-vl32b_traj_rollout_ws3_l1_lr2e-5_vit1e-5_aligner1e-5_bs384-step254/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)
|