Upload completed SigLIP2-Large Qwen3-4B S2 checkpoint
Browse files- .gitattributes +1 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/args.json +393 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/chat_template.jinja +61 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/chat_template.json +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/config.json +256 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/generation_config.json +12 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/model-00001-of-00002.safetensors +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/model-00002-of-00002.safetensors +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/model.safetensors.index.json +801 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/processor_config.json +203 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_0.pth +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_1.pth +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_2.pth +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_3.pth +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_4.pth +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_5.pth +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_6.pth +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_7.pth +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/scheduler.pt +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/tokenizer.json +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/tokenizer_config.json +19 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/trainer_state.json +2490 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/training_args.bin +3 -0
- ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/zero_to_fp32.py +760 -0
.gitattributes
CHANGED
|
@@ -93,3 +93,4 @@ ckpts/S2/4b/qwen3_5_2b/v13_5/v0-20260821-172306/checkpoint-1530/tokenizer.json f
|
|
| 93 |
ckpts/S2/4b/qwen3_5_2b/v13_6/v0-20260820-192228/checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 94 |
ckpts/S2/4b/qwen3_5_2b/v14_1_mkl_layer3/v0-20261012-043050/checkpoint-1530/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 95 |
ckpts/S2/4b/qwen3_5_2b/baseline_tmerge_64f_20pct/v0-20261012-171609/checkpoint-1530/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 93 |
ckpts/S2/4b/qwen3_5_2b/v13_6/v0-20260820-192228/checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 94 |
ckpts/S2/4b/qwen3_5_2b/v14_1_mkl_layer3/v0-20261012-043050/checkpoint-1530/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 95 |
ckpts/S2/4b/qwen3_5_2b/baseline_tmerge_64f_20pct/v0-20261012-171609/checkpoint-1530/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/args.json
ADDED
|
@@ -0,0 +1,393 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/home/wangjunjie09/exps/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108",
|
| 3 |
+
"per_device_train_batch_size": 1,
|
| 4 |
+
"num_train_epochs": 1.0,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"learning_rate": 1e-05,
|
| 7 |
+
"lr_scheduler_type": "cosine",
|
| 8 |
+
"lr_scheduler_kwargs": null,
|
| 9 |
+
"warmup_steps": 0,
|
| 10 |
+
"optim": "adamw_torch_fused",
|
| 11 |
+
"optim_args": null,
|
| 12 |
+
"weight_decay": 0.1,
|
| 13 |
+
"adam_beta1": 0.9,
|
| 14 |
+
"adam_beta2": 0.95,
|
| 15 |
+
"adam_epsilon": 1e-08,
|
| 16 |
+
"optim_target_modules": null,
|
| 17 |
+
"gradient_accumulation_steps": 8,
|
| 18 |
+
"average_tokens_across_devices": true,
|
| 19 |
+
"max_grad_norm": 1.0,
|
| 20 |
+
"label_smoothing_factor": 0.0,
|
| 21 |
+
"bf16": true,
|
| 22 |
+
"fp16": false,
|
| 23 |
+
"bf16_full_eval": false,
|
| 24 |
+
"fp16_full_eval": false,
|
| 25 |
+
"tf32": null,
|
| 26 |
+
"gradient_checkpointing": true,
|
| 27 |
+
"gradient_checkpointing_kwargs": "{\"use_reentrant\": false}",
|
| 28 |
+
"torch_compile": false,
|
| 29 |
+
"torch_compile_backend": null,
|
| 30 |
+
"torch_compile_mode": null,
|
| 31 |
+
"use_liger_kernel": false,
|
| 32 |
+
"liger_kernel_config": null,
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"neftune_noise_alpha": null,
|
| 35 |
+
"torch_empty_cache_steps": null,
|
| 36 |
+
"auto_find_batch_size": false,
|
| 37 |
+
"logging_strategy": "steps",
|
| 38 |
+
"logging_steps": 5,
|
| 39 |
+
"logging_first_step": true,
|
| 40 |
+
"log_on_each_node": true,
|
| 41 |
+
"logging_nan_inf_filter": true,
|
| 42 |
+
"include_num_input_tokens_seen": false,
|
| 43 |
+
"log_level": "passive",
|
| 44 |
+
"log_level_replica": "warning",
|
| 45 |
+
"disable_tqdm": null,
|
| 46 |
+
"report_to": [
|
| 47 |
+
"none"
|
| 48 |
+
],
|
| 49 |
+
"run_name": "/home/wangjunjie09/exps/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108",
|
| 50 |
+
"project": "huggingface",
|
| 51 |
+
"trackio_space_id": "trackio",
|
| 52 |
+
"eval_strategy": "no",
|
| 53 |
+
"eval_steps": 100.0,
|
| 54 |
+
"eval_delay": 0,
|
| 55 |
+
"per_device_eval_batch_size": 1,
|
| 56 |
+
"prediction_loss_only": false,
|
| 57 |
+
"eval_on_start": false,
|
| 58 |
+
"eval_do_concat_batches": true,
|
| 59 |
+
"eval_use_gather_object": false,
|
| 60 |
+
"eval_accumulation_steps": null,
|
| 61 |
+
"include_for_metrics": [],
|
| 62 |
+
"batch_eval_metrics": false,
|
| 63 |
+
"save_only_model": false,
|
| 64 |
+
"save_strategy": "steps",
|
| 65 |
+
"save_steps": 100.0,
|
| 66 |
+
"save_on_each_node": false,
|
| 67 |
+
"save_total_limit": 1,
|
| 68 |
+
"enable_jit_checkpoint": false,
|
| 69 |
+
"push_to_hub": false,
|
| 70 |
+
"hub_token": null,
|
| 71 |
+
"hub_private_repo": null,
|
| 72 |
+
"hub_model_id": null,
|
| 73 |
+
"hub_strategy": "every_save",
|
| 74 |
+
"hub_always_push": false,
|
| 75 |
+
"hub_revision": null,
|
| 76 |
+
"load_best_model_at_end": false,
|
| 77 |
+
"metric_for_best_model": "loss",
|
| 78 |
+
"greater_is_better": false,
|
| 79 |
+
"ignore_data_skip": false,
|
| 80 |
+
"restore_callback_states_from_checkpoint": false,
|
| 81 |
+
"full_determinism": false,
|
| 82 |
+
"seed": 42,
|
| 83 |
+
"data_seed": 42,
|
| 84 |
+
"use_cpu": false,
|
| 85 |
+
"accelerator_config": "{\"dispatch_batches\": false}",
|
| 86 |
+
"parallelism_config": null,
|
| 87 |
+
"dataloader_drop_last": false,
|
| 88 |
+
"dataloader_num_workers": 8,
|
| 89 |
+
"dataloader_pin_memory": true,
|
| 90 |
+
"dataloader_persistent_workers": true,
|
| 91 |
+
"dataloader_prefetch_factor": 4,
|
| 92 |
+
"remove_unused_columns": true,
|
| 93 |
+
"label_names": null,
|
| 94 |
+
"train_sampling_strategy": "random",
|
| 95 |
+
"length_column_name": "length",
|
| 96 |
+
"ddp_find_unused_parameters": null,
|
| 97 |
+
"ddp_bucket_cap_mb": null,
|
| 98 |
+
"ddp_broadcast_buffers": null,
|
| 99 |
+
"ddp_backend": null,
|
| 100 |
+
"ddp_timeout": 7200,
|
| 101 |
+
"fsdp": [],
|
| 102 |
+
"fsdp_config": null,
|
| 103 |
+
"deepspeed": {
|
| 104 |
+
"fp16": {
|
| 105 |
+
"enabled": "auto",
|
| 106 |
+
"loss_scale": 0,
|
| 107 |
+
"loss_scale_window": 1000,
|
| 108 |
+
"initial_scale_power": 16,
|
| 109 |
+
"hysteresis": 2,
|
| 110 |
+
"min_loss_scale": 1
|
| 111 |
+
},
|
| 112 |
+
"bf16": {
|
| 113 |
+
"enabled": "auto"
|
| 114 |
+
},
|
| 115 |
+
"zero_optimization": {
|
| 116 |
+
"stage": 2,
|
| 117 |
+
"offload_optimizer": {
|
| 118 |
+
"device": "none",
|
| 119 |
+
"pin_memory": true
|
| 120 |
+
},
|
| 121 |
+
"allgather_partitions": true,
|
| 122 |
+
"allgather_bucket_size": 200000000.0,
|
| 123 |
+
"overlap_comm": false,
|
| 124 |
+
"reduce_scatter": true,
|
| 125 |
+
"reduce_bucket_size": 200000000.0,
|
| 126 |
+
"contiguous_gradients": true
|
| 127 |
+
},
|
| 128 |
+
"gradient_accumulation_steps": "auto",
|
| 129 |
+
"gradient_clipping": "auto",
|
| 130 |
+
"steps_per_print": 2000,
|
| 131 |
+
"train_batch_size": "auto",
|
| 132 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 133 |
+
"wall_clock_breakdown": false
|
| 134 |
+
},
|
| 135 |
+
"debug": null,
|
| 136 |
+
"skip_memory_metrics": true,
|
| 137 |
+
"do_train": false,
|
| 138 |
+
"do_eval": false,
|
| 139 |
+
"do_predict": false,
|
| 140 |
+
"resume_from_checkpoint": null,
|
| 141 |
+
"warmup_ratio": 0.05,
|
| 142 |
+
"logging_dir": "/home/wangjunjie09/exps/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/runs",
|
| 143 |
+
"local_rank": 0,
|
| 144 |
+
"sortish_sampler": false,
|
| 145 |
+
"predict_with_generate": false,
|
| 146 |
+
"generation_max_length": null,
|
| 147 |
+
"generation_num_beams": null,
|
| 148 |
+
"generation_config": null,
|
| 149 |
+
"tuner_backend": "peft",
|
| 150 |
+
"llm_checkpointing": 16,
|
| 151 |
+
"vit_gradient_checkpointing": true,
|
| 152 |
+
"router_aux_loss_coef": 0.0,
|
| 153 |
+
"enable_dft_loss": false,
|
| 154 |
+
"enable_channel_loss": false,
|
| 155 |
+
"safe_serialization": true,
|
| 156 |
+
"max_shard_size": "5GB",
|
| 157 |
+
"check_model": true,
|
| 158 |
+
"acc_strategy": "token",
|
| 159 |
+
"train_dataloader_shuffle": true,
|
| 160 |
+
"group_by_length": false,
|
| 161 |
+
"group_by_packed_video_cost": true,
|
| 162 |
+
"group_by_packed_compute_cost": false,
|
| 163 |
+
"group_by_packed_modality": false,
|
| 164 |
+
"max_epochs": null,
|
| 165 |
+
"aligner_lr": null,
|
| 166 |
+
"vit_lr": 1e-06,
|
| 167 |
+
"use_logits_to_keep": true,
|
| 168 |
+
"ds3_gather_for_generation": true,
|
| 169 |
+
"resume_only_model": false,
|
| 170 |
+
"optimizer": null,
|
| 171 |
+
"loss_type": null,
|
| 172 |
+
"eval_metric": null,
|
| 173 |
+
"callbacks": [],
|
| 174 |
+
"early_stop_interval": null,
|
| 175 |
+
"eval_use_evalscope": false,
|
| 176 |
+
"eval_dataset": [],
|
| 177 |
+
"eval_dataset_args": null,
|
| 178 |
+
"eval_limit": null,
|
| 179 |
+
"eval_generation_config": null,
|
| 180 |
+
"extra_eval_args": null,
|
| 181 |
+
"tuner_type": "full",
|
| 182 |
+
"use_galore": false,
|
| 183 |
+
"galore_target_modules": null,
|
| 184 |
+
"galore_rank": 128,
|
| 185 |
+
"galore_update_proj_gap": 50,
|
| 186 |
+
"galore_scale": 1.0,
|
| 187 |
+
"galore_proj_type": "std",
|
| 188 |
+
"galore_optim_per_parameter": false,
|
| 189 |
+
"galore_with_embedding": false,
|
| 190 |
+
"galore_quantization": false,
|
| 191 |
+
"galore_proj_quant": false,
|
| 192 |
+
"galore_proj_bits": 4,
|
| 193 |
+
"galore_proj_group_size": 256,
|
| 194 |
+
"galore_cos_threshold": 0.4,
|
| 195 |
+
"galore_gamma_proj": 2,
|
| 196 |
+
"galore_queue_size": 5,
|
| 197 |
+
"lisa_activated_layers": 0,
|
| 198 |
+
"lisa_step_interval": 20,
|
| 199 |
+
"use_flash_ckpt": false,
|
| 200 |
+
"use_ray": false,
|
| 201 |
+
"ray_exp_name": null,
|
| 202 |
+
"device_groups": null,
|
| 203 |
+
"model": "/home/wangjunjie09/VisionEncoder/exps/S1/4b/siglip2_large/siglip2_large/v0-20261024-050359/checkpoint-2181",
|
| 204 |
+
"model_type": "llava_siglip2_qwen3",
|
| 205 |
+
"model_revision": null,
|
| 206 |
+
"task_type": "causal_lm",
|
| 207 |
+
"torch_dtype": "bfloat16",
|
| 208 |
+
"attn_impl": "flash_attn",
|
| 209 |
+
"experts_impl": null,
|
| 210 |
+
"new_special_tokens": [],
|
| 211 |
+
"num_labels": null,
|
| 212 |
+
"problem_type": null,
|
| 213 |
+
"rope_scaling": null,
|
| 214 |
+
"device_map": null,
|
| 215 |
+
"max_memory": {},
|
| 216 |
+
"max_model_len": null,
|
| 217 |
+
"local_repo_path": null,
|
| 218 |
+
"init_strategy": null,
|
| 219 |
+
"template": "llava_siglip2_qwen3",
|
| 220 |
+
"system": null,
|
| 221 |
+
"max_length": 16384,
|
| 222 |
+
"truncation_strategy": "delete",
|
| 223 |
+
"max_pixels": null,
|
| 224 |
+
"agent_template": null,
|
| 225 |
+
"norm_bbox": null,
|
| 226 |
+
"use_chat_template": true,
|
| 227 |
+
"padding_side": "right",
|
| 228 |
+
"padding_free": true,
|
| 229 |
+
"loss_scale": "default",
|
| 230 |
+
"sequence_parallel_size": 1,
|
| 231 |
+
"template_backend": "swift",
|
| 232 |
+
"response_prefix": null,
|
| 233 |
+
"enable_thinking": null,
|
| 234 |
+
"add_non_thinking_prefix": true,
|
| 235 |
+
"dataset": [],
|
| 236 |
+
"val_dataset": [],
|
| 237 |
+
"cached_dataset": [
|
| 238 |
+
"/share/m2v_intern/wangjunjie09/datasets/prepared/s2/img576_vid144/image_20pct/train",
|
| 239 |
+
"/share/m2v_intern/wangjunjie09/datasets/prepared/s2/img576_vid144/video_20pct/v2/train"
|
| 240 |
+
],
|
| 241 |
+
"cached_val_dataset": [],
|
| 242 |
+
"split_dataset_ratio": 0.0,
|
| 243 |
+
"dataset_num_proc": 16,
|
| 244 |
+
"load_from_cache_file": false,
|
| 245 |
+
"dataset_shuffle": true,
|
| 246 |
+
"val_dataset_shuffle": false,
|
| 247 |
+
"streaming": false,
|
| 248 |
+
"interleave_prob": null,
|
| 249 |
+
"stopping_strategy": "first_exhausted",
|
| 250 |
+
"shuffle_buffer_size": 1000,
|
| 251 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 252 |
+
"columns": {},
|
| 253 |
+
"strict": false,
|
| 254 |
+
"model_name": null,
|
| 255 |
+
"model_author": null,
|
| 256 |
+
"custom_dataset_info": [],
|
| 257 |
+
"quant_method": null,
|
| 258 |
+
"quant_bits": null,
|
| 259 |
+
"hqq_axis": null,
|
| 260 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 261 |
+
"bnb_4bit_quant_type": "nf4",
|
| 262 |
+
"bnb_4bit_use_double_quant": true,
|
| 263 |
+
"bnb_4bit_quant_storage": null,
|
| 264 |
+
"max_new_tokens": 64,
|
| 265 |
+
"temperature": 0.0,
|
| 266 |
+
"top_k": null,
|
| 267 |
+
"top_p": null,
|
| 268 |
+
"repetition_penalty": null,
|
| 269 |
+
"num_beams": 1,
|
| 270 |
+
"stream": false,
|
| 271 |
+
"stop_words": [],
|
| 272 |
+
"logprobs": false,
|
| 273 |
+
"top_logprobs": null,
|
| 274 |
+
"structured_outputs_regex": null,
|
| 275 |
+
"train_type": null,
|
| 276 |
+
"adapters": [],
|
| 277 |
+
"external_plugins": [
|
| 278 |
+
"video_mllm/training/model_plugin.py",
|
| 279 |
+
"video_mllm/data/dataset_plugin.py",
|
| 280 |
+
"/home/wangjunjie09/VisionEncoder/video_mllm/training/log_spacing_plugin.py"
|
| 281 |
+
],
|
| 282 |
+
"custom_register_path": [
|
| 283 |
+
"/home/wangjunjie09/VisionEncoder/video_mllm/training/log_spacing_plugin.py"
|
| 284 |
+
],
|
| 285 |
+
"model_kwargs": {
|
| 286 |
+
"vision_source_id": "siglip2_large_patch16_384",
|
| 287 |
+
"num_frames": 32,
|
| 288 |
+
"eval_frames": 32,
|
| 289 |
+
"s2_use_video_frame_cache": true,
|
| 290 |
+
"s2_video_frame_cache": "/share/m2v_intern_v3/wangjunjie09/datasets/video_cache/s2/frames/jpeg/384/32"
|
| 291 |
+
},
|
| 292 |
+
"video_cache": {},
|
| 293 |
+
"image_teacher_models": {},
|
| 294 |
+
"load_args": false,
|
| 295 |
+
"load_data_args": false,
|
| 296 |
+
"packing": true,
|
| 297 |
+
"packing_length": 16384,
|
| 298 |
+
"packing_num_proc": 1,
|
| 299 |
+
"lazy_tokenize": false,
|
| 300 |
+
"use_hf": true,
|
| 301 |
+
"ignore_args_error": false,
|
| 302 |
+
"use_swift_lora": false,
|
| 303 |
+
"freeze_parameters": [],
|
| 304 |
+
"freeze_parameters_regex": null,
|
| 305 |
+
"freeze_parameters_ratio": 0.0,
|
| 306 |
+
"trainable_parameters": [
|
| 307 |
+
"model.multi_modal_projector"
|
| 308 |
+
],
|
| 309 |
+
"trainable_parameters_regex": null,
|
| 310 |
+
"freeze_llm": false,
|
| 311 |
+
"freeze_vit": false,
|
| 312 |
+
"freeze_aligner": false,
|
| 313 |
+
"target_modules": [
|
| 314 |
+
"all-linear"
|
| 315 |
+
],
|
| 316 |
+
"target_regex": null,
|
| 317 |
+
"target_parameters": null,
|
| 318 |
+
"modules_to_save": [],
|
| 319 |
+
"lora_rank": 8,
|
| 320 |
+
"lora_alpha": 32,
|
| 321 |
+
"lora_dropout": 0.05,
|
| 322 |
+
"lora_bias": "none",
|
| 323 |
+
"lora_dtype": null,
|
| 324 |
+
"lorap_lr_ratio": null,
|
| 325 |
+
"use_rslora": false,
|
| 326 |
+
"use_dora": false,
|
| 327 |
+
"lora_ga_batch_size": 2,
|
| 328 |
+
"lora_ga_iters": 2,
|
| 329 |
+
"lora_ga_max_length": 1024,
|
| 330 |
+
"lora_ga_direction": "ArB2r",
|
| 331 |
+
"lora_ga_scale": "stable",
|
| 332 |
+
"lora_ga_stable_gamma": 16,
|
| 333 |
+
"init_weights": true,
|
| 334 |
+
"fourier_n_frequency": 2000,
|
| 335 |
+
"fourier_scaling": 300.0,
|
| 336 |
+
"boft_block_size": 4,
|
| 337 |
+
"boft_block_num": 0,
|
| 338 |
+
"boft_n_butterfly_factor": 1,
|
| 339 |
+
"boft_dropout": 0.0,
|
| 340 |
+
"vera_rank": 256,
|
| 341 |
+
"vera_projection_prng_key": 0,
|
| 342 |
+
"vera_dropout": 0.0,
|
| 343 |
+
"vera_d_initial": 0.1,
|
| 344 |
+
"adapter_act": "gelu",
|
| 345 |
+
"adapter_length": 128,
|
| 346 |
+
"adalora_target_r": 8,
|
| 347 |
+
"adalora_init_r": 12,
|
| 348 |
+
"adalora_tinit": 0,
|
| 349 |
+
"adalora_tfinal": 0,
|
| 350 |
+
"adalora_deltaT": 1,
|
| 351 |
+
"adalora_beta1": 0.85,
|
| 352 |
+
"adalora_beta2": 0.85,
|
| 353 |
+
"adalora_orth_reg_weight": 0.5,
|
| 354 |
+
"llamapro_num_new_blocks": 4,
|
| 355 |
+
"llamapro_num_groups": null,
|
| 356 |
+
"reft_layer_key": null,
|
| 357 |
+
"reft_layers": null,
|
| 358 |
+
"reft_rank": 4,
|
| 359 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 360 |
+
"reft_args": null,
|
| 361 |
+
"swanlab_token": null,
|
| 362 |
+
"swanlab_project": "ms-swift",
|
| 363 |
+
"swanlab_workspace": null,
|
| 364 |
+
"swanlab_exp_name": null,
|
| 365 |
+
"swanlab_notification_method": null,
|
| 366 |
+
"swanlab_webhook_url": null,
|
| 367 |
+
"swanlab_secret": null,
|
| 368 |
+
"swanlab_sender_email": null,
|
| 369 |
+
"swanlab_receiver_email": null,
|
| 370 |
+
"swanlab_smtp_server": null,
|
| 371 |
+
"swanlab_smtp_port": null,
|
| 372 |
+
"swanlab_email_language": "zh",
|
| 373 |
+
"swanlab_mode": "cloud",
|
| 374 |
+
"add_version": true,
|
| 375 |
+
"create_checkpoint_symlink": false,
|
| 376 |
+
"v12_resolution": 384,
|
| 377 |
+
"zero_hpz_partition_size": null,
|
| 378 |
+
"deepspeed_autotp_size": null,
|
| 379 |
+
"swift_version": "4.1.0.dev0",
|
| 380 |
+
"ckpt_dir": "/home/wangjunjie09/VisionEncoder/exps/S1/4b/siglip2_large/siglip2_large/v0-20261024-050359/checkpoint-2181",
|
| 381 |
+
"rank": 0,
|
| 382 |
+
"global_world_size": 8,
|
| 383 |
+
"local_world_size": 8,
|
| 384 |
+
"model_suffix": "checkpoint-2181",
|
| 385 |
+
"model_info": "ModelInfo(model_type='llava_siglip2_qwen3', model_dir='/home/wangjunjie09/VisionEncoder/exps/S1/4b/siglip2_large/siglip2_large/v0-20261024-050359/checkpoint-2181', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
|
| 386 |
+
"model_meta": "ModelMeta(model_type='llava_siglip2_qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None)], template=None, ignore_patterns=None, requires=None, tags=[])], loader=<class 'model_plugin.SigLIP2Qwen3Loader'>, template='llava_siglip2_qwen3', model_arch=MultiModelKeys(arch_name='llava_hf', 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.multi_modal_projector'], vision_tower=['model.vision_tower'], generator=[]), architectures=['LlavaOnevisionForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=[], tags=['vision', 'video'])",
|
| 387 |
+
"model_dir": "/home/wangjunjie09/VisionEncoder/exps/S1/4b/siglip2_large/siglip2_large/v0-20261024-050359/checkpoint-2181",
|
| 388 |
+
"template_meta": "QwenTemplateMeta(template_type='llava_siglip2_qwen3', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'model_plugin.SigLIP2LlavaTemplate'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='hermes', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')",
|
| 389 |
+
"_val_dataset_exists": false,
|
| 390 |
+
"hub": "<class 'swift.hub.hub.HFHub'>",
|
| 391 |
+
"evaluation_strategy": "steps",
|
| 392 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/home/wangjunjie09/exps/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108', per_device_train_batch_size=1, num_train_epochs=1.0, max_steps=-1, learning_rate=1e-05, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0.05, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=8, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': False}, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=5, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=[], run_name='/home/wangjunjie09/exps/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108', project='huggingface', trackio_space_id='trackio', eval_strategy=<IntervalStrategy.NO: 'no'>, eval_steps=100.0, eval_delay=0, per_device_eval_batch_size=1, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=False, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=100, save_on_each_node=False, save_total_limit=1, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, dataloader_drop_last=False, dataloader_num_workers=8, dataloader_pin_memory=True, dataloader_persistent_workers=True, dataloader_prefetch_factor=4, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_backend=None, ddp_timeout=7200, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=False, do_predict=False, resume_from_checkpoint=None, warmup_ratio=0.05, logging_dir='/home/wangjunjie09/exps/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/runs', local_rank=0, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', llm_checkpointing=16, vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, group_by_packed_video_cost=True, group_by_packed_compute_cost=False, group_by_packed_modality=False, max_epochs=None, aligner_lr=None, vit_lr=1e-06, use_logits_to_keep=True, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
|
| 393 |
+
}
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/chat_template.jinja
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- for message in messages %}
|
| 18 |
+
{%- if message.content is string %}
|
| 19 |
+
{%- set content = message.content %}
|
| 20 |
+
{%- else %}
|
| 21 |
+
{%- set content = '' %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
+
{%- elif message.role == "assistant" %}
|
| 26 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
+
{%- if message.tool_calls %}
|
| 28 |
+
{%- for tool_call in message.tool_calls %}
|
| 29 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
+
{{- '\n' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- if tool_call.function %}
|
| 33 |
+
{%- set tool_call = tool_call.function %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
+
{{- tool_call.name }}
|
| 37 |
+
{{- '", "arguments": ' }}
|
| 38 |
+
{%- if tool_call.arguments is string %}
|
| 39 |
+
{{- tool_call.arguments }}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{{- tool_call.arguments | tojson }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- '}\n</tool_call>' }}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{{- '<|im_end|>\n' }}
|
| 47 |
+
{%- elif message.role == "tool" %}
|
| 48 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
+
{{- '<|im_start|>user' }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{{- '\n<tool_response>\n' }}
|
| 52 |
+
{{- content }}
|
| 53 |
+
{{- '\n</tool_response>' }}
|
| 54 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
+
{{- '<|im_end|>\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endfor %}
|
| 59 |
+
{%- if add_generation_prompt %}
|
| 60 |
+
{{- '<|im_start|>assistant\n' }}
|
| 61 |
+
{%- endif %}
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + ' '}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ '\n' + content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ '\n' + content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
| 3 |
+
}
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/config.json
ADDED
|
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlavaOnevisionForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"eval_num_frames": 32,
|
| 9 |
+
"hidden_size": 2560,
|
| 10 |
+
"image_grid_pinpoints": [
|
| 11 |
+
[
|
| 12 |
+
384,
|
| 13 |
+
384
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
384,
|
| 17 |
+
768
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
384,
|
| 21 |
+
1152
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
384,
|
| 25 |
+
1536
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
384,
|
| 29 |
+
1920
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
384,
|
| 33 |
+
2304
|
| 34 |
+
],
|
| 35 |
+
[
|
| 36 |
+
768,
|
| 37 |
+
384
|
| 38 |
+
],
|
| 39 |
+
[
|
| 40 |
+
768,
|
| 41 |
+
768
|
| 42 |
+
],
|
| 43 |
+
[
|
| 44 |
+
768,
|
| 45 |
+
1152
|
| 46 |
+
],
|
| 47 |
+
[
|
| 48 |
+
768,
|
| 49 |
+
1536
|
| 50 |
+
],
|
| 51 |
+
[
|
| 52 |
+
768,
|
| 53 |
+
1920
|
| 54 |
+
],
|
| 55 |
+
[
|
| 56 |
+
768,
|
| 57 |
+
2304
|
| 58 |
+
],
|
| 59 |
+
[
|
| 60 |
+
1152,
|
| 61 |
+
384
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
1152,
|
| 65 |
+
768
|
| 66 |
+
],
|
| 67 |
+
[
|
| 68 |
+
1152,
|
| 69 |
+
1152
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
1152,
|
| 73 |
+
1536
|
| 74 |
+
],
|
| 75 |
+
[
|
| 76 |
+
1152,
|
| 77 |
+
1920
|
| 78 |
+
],
|
| 79 |
+
[
|
| 80 |
+
1152,
|
| 81 |
+
2304
|
| 82 |
+
],
|
| 83 |
+
[
|
| 84 |
+
1536,
|
| 85 |
+
384
|
| 86 |
+
],
|
| 87 |
+
[
|
| 88 |
+
1536,
|
| 89 |
+
768
|
| 90 |
+
],
|
| 91 |
+
[
|
| 92 |
+
1536,
|
| 93 |
+
1152
|
| 94 |
+
],
|
| 95 |
+
[
|
| 96 |
+
1536,
|
| 97 |
+
1536
|
| 98 |
+
],
|
| 99 |
+
[
|
| 100 |
+
1536,
|
| 101 |
+
1920
|
| 102 |
+
],
|
| 103 |
+
[
|
| 104 |
+
1536,
|
| 105 |
+
2304
|
| 106 |
+
],
|
| 107 |
+
[
|
| 108 |
+
1920,
|
| 109 |
+
384
|
| 110 |
+
],
|
| 111 |
+
[
|
| 112 |
+
1920,
|
| 113 |
+
768
|
| 114 |
+
],
|
| 115 |
+
[
|
| 116 |
+
1920,
|
| 117 |
+
1152
|
| 118 |
+
],
|
| 119 |
+
[
|
| 120 |
+
1920,
|
| 121 |
+
1536
|
| 122 |
+
],
|
| 123 |
+
[
|
| 124 |
+
1920,
|
| 125 |
+
1920
|
| 126 |
+
],
|
| 127 |
+
[
|
| 128 |
+
1920,
|
| 129 |
+
2304
|
| 130 |
+
],
|
| 131 |
+
[
|
| 132 |
+
2304,
|
| 133 |
+
384
|
| 134 |
+
],
|
| 135 |
+
[
|
| 136 |
+
2304,
|
| 137 |
+
768
|
| 138 |
+
],
|
| 139 |
+
[
|
| 140 |
+
2304,
|
| 141 |
+
1152
|
| 142 |
+
],
|
| 143 |
+
[
|
| 144 |
+
2304,
|
| 145 |
+
1536
|
| 146 |
+
],
|
| 147 |
+
[
|
| 148 |
+
2304,
|
| 149 |
+
1920
|
| 150 |
+
],
|
| 151 |
+
[
|
| 152 |
+
2304,
|
| 153 |
+
2304
|
| 154 |
+
]
|
| 155 |
+
],
|
| 156 |
+
"image_token_index": 151669,
|
| 157 |
+
"model_type": "llava_onevision",
|
| 158 |
+
"multimodal_projector_bias": true,
|
| 159 |
+
"pad_token_id": 151643,
|
| 160 |
+
"projector_hidden_act": "gelu",
|
| 161 |
+
"text_config": {
|
| 162 |
+
"_name_or_path": "/share/m2v_intern_v3/wangjunjie09/model_cache/huggingface/Qwen/Qwen3-4B-Instruct-2507",
|
| 163 |
+
"architectures": [
|
| 164 |
+
"Qwen3ForCausalLM"
|
| 165 |
+
],
|
| 166 |
+
"attention_bias": false,
|
| 167 |
+
"attention_dropout": 0.0,
|
| 168 |
+
"bos_token_id": 151643,
|
| 169 |
+
"dtype": "bfloat16",
|
| 170 |
+
"eos_token_id": 151645,
|
| 171 |
+
"head_dim": 128,
|
| 172 |
+
"hidden_act": "silu",
|
| 173 |
+
"hidden_size": 2560,
|
| 174 |
+
"initializer_range": 0.02,
|
| 175 |
+
"intermediate_size": 9728,
|
| 176 |
+
"layer_types": [
|
| 177 |
+
"full_attention",
|
| 178 |
+
"full_attention",
|
| 179 |
+
"full_attention",
|
| 180 |
+
"full_attention",
|
| 181 |
+
"full_attention",
|
| 182 |
+
"full_attention",
|
| 183 |
+
"full_attention",
|
| 184 |
+
"full_attention",
|
| 185 |
+
"full_attention",
|
| 186 |
+
"full_attention",
|
| 187 |
+
"full_attention",
|
| 188 |
+
"full_attention",
|
| 189 |
+
"full_attention",
|
| 190 |
+
"full_attention",
|
| 191 |
+
"full_attention",
|
| 192 |
+
"full_attention",
|
| 193 |
+
"full_attention",
|
| 194 |
+
"full_attention",
|
| 195 |
+
"full_attention",
|
| 196 |
+
"full_attention",
|
| 197 |
+
"full_attention",
|
| 198 |
+
"full_attention",
|
| 199 |
+
"full_attention",
|
| 200 |
+
"full_attention",
|
| 201 |
+
"full_attention",
|
| 202 |
+
"full_attention",
|
| 203 |
+
"full_attention",
|
| 204 |
+
"full_attention",
|
| 205 |
+
"full_attention",
|
| 206 |
+
"full_attention",
|
| 207 |
+
"full_attention",
|
| 208 |
+
"full_attention",
|
| 209 |
+
"full_attention",
|
| 210 |
+
"full_attention",
|
| 211 |
+
"full_attention",
|
| 212 |
+
"full_attention"
|
| 213 |
+
],
|
| 214 |
+
"max_position_embeddings": 262144,
|
| 215 |
+
"max_window_layers": 36,
|
| 216 |
+
"model_type": "qwen3",
|
| 217 |
+
"num_attention_heads": 32,
|
| 218 |
+
"num_hidden_layers": 36,
|
| 219 |
+
"num_key_value_heads": 8,
|
| 220 |
+
"pad_token_id": 151643,
|
| 221 |
+
"rms_norm_eps": 1e-06,
|
| 222 |
+
"rope_parameters": {
|
| 223 |
+
"rope_theta": 5000000,
|
| 224 |
+
"rope_type": "default"
|
| 225 |
+
},
|
| 226 |
+
"sliding_window": null,
|
| 227 |
+
"tie_word_embeddings": true,
|
| 228 |
+
"use_cache": false,
|
| 229 |
+
"use_sliding_window": false,
|
| 230 |
+
"vocab_size": 151936
|
| 231 |
+
},
|
| 232 |
+
"tie_word_embeddings": true,
|
| 233 |
+
"train_num_frames": 32,
|
| 234 |
+
"transformers_version": "5.5.4",
|
| 235 |
+
"use_cache": false,
|
| 236 |
+
"video_token_index": 151670,
|
| 237 |
+
"vision_aspect_ratio": "anyres_max_9",
|
| 238 |
+
"vision_config": {
|
| 239 |
+
"attention_dropout": 0.0,
|
| 240 |
+
"dtype": "bfloat16",
|
| 241 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 242 |
+
"hidden_size": 1024,
|
| 243 |
+
"image_size": 384,
|
| 244 |
+
"intermediate_size": 4096,
|
| 245 |
+
"layer_norm_eps": 1e-06,
|
| 246 |
+
"model_type": "siglip_vision_model",
|
| 247 |
+
"num_attention_heads": 16,
|
| 248 |
+
"num_channels": 3,
|
| 249 |
+
"num_hidden_layers": 24,
|
| 250 |
+
"patch_size": 16,
|
| 251 |
+
"vision_use_head": false
|
| 252 |
+
},
|
| 253 |
+
"vision_family": "siglip2_large",
|
| 254 |
+
"vision_feature_layer": -2,
|
| 255 |
+
"vision_feature_select_strategy": "full"
|
| 256 |
+
}
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"output_attentions": false,
|
| 9 |
+
"output_hidden_states": false,
|
| 10 |
+
"transformers_version": "5.5.4",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a07950ddb98a960a5d39c861ccbac3b9fb2ccb06eaa35ab519af9e4c427ea5d6
|
| 3 |
+
size 4987508560
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aba1ef249583adeaf1c1aa435b124304ba484152819ccd64bc669e8a0c61ffde
|
| 3 |
+
size 4461193728
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,801 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4335339520,
|
| 4 |
+
"total_size": 9448591360
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.lm_head.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.image_newline": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"model.language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"model.language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"model.language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"model.language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"model.language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"model.language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"model.language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.language_model.model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.language_model.model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.language_model.model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.language_model.model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.language_model.model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.language_model.model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.language_model.model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.language_model.model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.language_model.model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.multi_modal_projector.linear_1.bias": "model-00002-of-00002.safetensors",
|
| 408 |
+
"model.multi_modal_projector.linear_1.weight": "model-00002-of-00002.safetensors",
|
| 409 |
+
"model.multi_modal_projector.linear_2.bias": "model-00002-of-00002.safetensors",
|
| 410 |
+
"model.multi_modal_projector.linear_2.weight": "model-00002-of-00002.safetensors",
|
| 411 |
+
"model.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
|
| 413 |
+
"model.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 414 |
+
"model.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 415 |
+
"model.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 416 |
+
"model.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 417 |
+
"model.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 419 |
+
"model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 420 |
+
"model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 421 |
+
"model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 422 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 423 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 425 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 430 |
+
"model.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 433 |
+
"model.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 435 |
+
"model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 436 |
+
"model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 441 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 442 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 443 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 444 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 445 |
+
"model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 446 |
+
"model.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 447 |
+
"model.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 448 |
+
"model.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 449 |
+
"model.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 450 |
+
"model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 451 |
+
"model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 452 |
+
"model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 453 |
+
"model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 454 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 455 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 456 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 457 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 458 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 459 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 460 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 461 |
+
"model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 462 |
+
"model.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 463 |
+
"model.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 464 |
+
"model.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 465 |
+
"model.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 466 |
+
"model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 467 |
+
"model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 468 |
+
"model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 469 |
+
"model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 470 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 471 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 472 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 473 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 474 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 475 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 476 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 477 |
+
"model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 478 |
+
"model.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 479 |
+
"model.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 480 |
+
"model.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 481 |
+
"model.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 482 |
+
"model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 483 |
+
"model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 484 |
+
"model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 485 |
+
"model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 486 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 487 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 488 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 489 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 490 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 491 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 492 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 493 |
+
"model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 494 |
+
"model.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 495 |
+
"model.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 496 |
+
"model.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 497 |
+
"model.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 498 |
+
"model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 499 |
+
"model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 500 |
+
"model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 501 |
+
"model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 502 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 503 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 504 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 505 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 506 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 507 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 508 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 509 |
+
"model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 510 |
+
"model.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 511 |
+
"model.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 512 |
+
"model.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 513 |
+
"model.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 514 |
+
"model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 515 |
+
"model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 516 |
+
"model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 517 |
+
"model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 518 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 519 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 520 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 521 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 522 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 523 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 524 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 525 |
+
"model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 526 |
+
"model.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 527 |
+
"model.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 528 |
+
"model.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 529 |
+
"model.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 530 |
+
"model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 531 |
+
"model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 532 |
+
"model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 533 |
+
"model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 534 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 535 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 536 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 537 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 538 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 539 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 540 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 541 |
+
"model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 542 |
+
"model.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 543 |
+
"model.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 544 |
+
"model.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 545 |
+
"model.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 546 |
+
"model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 547 |
+
"model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 548 |
+
"model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 549 |
+
"model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 550 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 551 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 552 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 553 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 554 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 555 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 556 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 557 |
+
"model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 558 |
+
"model.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 559 |
+
"model.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 560 |
+
"model.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 561 |
+
"model.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 562 |
+
"model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 563 |
+
"model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 564 |
+
"model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 565 |
+
"model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 566 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 567 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 568 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 569 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 570 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 571 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 572 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 573 |
+
"model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 574 |
+
"model.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 575 |
+
"model.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 576 |
+
"model.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 577 |
+
"model.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 578 |
+
"model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 579 |
+
"model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 580 |
+
"model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 581 |
+
"model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 582 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 583 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 584 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 585 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 586 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 587 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 588 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 589 |
+
"model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 590 |
+
"model.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 591 |
+
"model.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 592 |
+
"model.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 593 |
+
"model.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 594 |
+
"model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 595 |
+
"model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 596 |
+
"model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 597 |
+
"model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 598 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 599 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 600 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 601 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 602 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 603 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 604 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 605 |
+
"model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 606 |
+
"model.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 607 |
+
"model.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 608 |
+
"model.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 609 |
+
"model.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 610 |
+
"model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 611 |
+
"model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 612 |
+
"model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 613 |
+
"model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 614 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 615 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 616 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 617 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 618 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 619 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 620 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 621 |
+
"model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 622 |
+
"model.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 623 |
+
"model.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 624 |
+
"model.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 625 |
+
"model.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 626 |
+
"model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 627 |
+
"model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 628 |
+
"model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 629 |
+
"model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 630 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 631 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 632 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 633 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 634 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 635 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 730 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 731 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 732 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 733 |
+
"model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 734 |
+
"model.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 735 |
+
"model.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 736 |
+
"model.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 737 |
+
"model.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 738 |
+
"model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 739 |
+
"model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 740 |
+
"model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 741 |
+
"model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 742 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 743 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 744 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 745 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 746 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 747 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 748 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 749 |
+
"model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 750 |
+
"model.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 751 |
+
"model.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 752 |
+
"model.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 753 |
+
"model.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 754 |
+
"model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 755 |
+
"model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 756 |
+
"model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 757 |
+
"model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 758 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 759 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 760 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 761 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 762 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 763 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 764 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 765 |
+
"model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 766 |
+
"model.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 767 |
+
"model.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 768 |
+
"model.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 769 |
+
"model.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 770 |
+
"model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 771 |
+
"model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 772 |
+
"model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 773 |
+
"model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 774 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 775 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 776 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 777 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 778 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 779 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 780 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 781 |
+
"model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 782 |
+
"model.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
|
| 783 |
+
"model.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
|
| 784 |
+
"model.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
|
| 785 |
+
"model.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
|
| 786 |
+
"model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 787 |
+
"model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 788 |
+
"model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 789 |
+
"model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 790 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 791 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 792 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 793 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 794 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 795 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 796 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 797 |
+
"model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 798 |
+
"model.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 799 |
+
"model.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors"
|
| 800 |
+
}
|
| 801 |
+
}
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/processor_config.json
ADDED
|
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": null,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_pad": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_grid_pinpoints": [
|
| 9 |
+
[
|
| 10 |
+
384,
|
| 11 |
+
384
|
| 12 |
+
],
|
| 13 |
+
[
|
| 14 |
+
384,
|
| 15 |
+
768
|
| 16 |
+
],
|
| 17 |
+
[
|
| 18 |
+
384,
|
| 19 |
+
1152
|
| 20 |
+
],
|
| 21 |
+
[
|
| 22 |
+
384,
|
| 23 |
+
1536
|
| 24 |
+
],
|
| 25 |
+
[
|
| 26 |
+
384,
|
| 27 |
+
1920
|
| 28 |
+
],
|
| 29 |
+
[
|
| 30 |
+
384,
|
| 31 |
+
2304
|
| 32 |
+
],
|
| 33 |
+
[
|
| 34 |
+
768,
|
| 35 |
+
384
|
| 36 |
+
],
|
| 37 |
+
[
|
| 38 |
+
768,
|
| 39 |
+
768
|
| 40 |
+
],
|
| 41 |
+
[
|
| 42 |
+
768,
|
| 43 |
+
1152
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
768,
|
| 47 |
+
1536
|
| 48 |
+
],
|
| 49 |
+
[
|
| 50 |
+
768,
|
| 51 |
+
1920
|
| 52 |
+
],
|
| 53 |
+
[
|
| 54 |
+
768,
|
| 55 |
+
2304
|
| 56 |
+
],
|
| 57 |
+
[
|
| 58 |
+
1152,
|
| 59 |
+
384
|
| 60 |
+
],
|
| 61 |
+
[
|
| 62 |
+
1152,
|
| 63 |
+
768
|
| 64 |
+
],
|
| 65 |
+
[
|
| 66 |
+
1152,
|
| 67 |
+
1152
|
| 68 |
+
],
|
| 69 |
+
[
|
| 70 |
+
1152,
|
| 71 |
+
1536
|
| 72 |
+
],
|
| 73 |
+
[
|
| 74 |
+
1152,
|
| 75 |
+
1920
|
| 76 |
+
],
|
| 77 |
+
[
|
| 78 |
+
1152,
|
| 79 |
+
2304
|
| 80 |
+
],
|
| 81 |
+
[
|
| 82 |
+
1536,
|
| 83 |
+
384
|
| 84 |
+
],
|
| 85 |
+
[
|
| 86 |
+
1536,
|
| 87 |
+
768
|
| 88 |
+
],
|
| 89 |
+
[
|
| 90 |
+
1536,
|
| 91 |
+
1152
|
| 92 |
+
],
|
| 93 |
+
[
|
| 94 |
+
1536,
|
| 95 |
+
1536
|
| 96 |
+
],
|
| 97 |
+
[
|
| 98 |
+
1536,
|
| 99 |
+
1920
|
| 100 |
+
],
|
| 101 |
+
[
|
| 102 |
+
1536,
|
| 103 |
+
2304
|
| 104 |
+
],
|
| 105 |
+
[
|
| 106 |
+
1920,
|
| 107 |
+
384
|
| 108 |
+
],
|
| 109 |
+
[
|
| 110 |
+
1920,
|
| 111 |
+
768
|
| 112 |
+
],
|
| 113 |
+
[
|
| 114 |
+
1920,
|
| 115 |
+
1152
|
| 116 |
+
],
|
| 117 |
+
[
|
| 118 |
+
1920,
|
| 119 |
+
1536
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
1920,
|
| 123 |
+
1920
|
| 124 |
+
],
|
| 125 |
+
[
|
| 126 |
+
1920,
|
| 127 |
+
2304
|
| 128 |
+
],
|
| 129 |
+
[
|
| 130 |
+
2304,
|
| 131 |
+
384
|
| 132 |
+
],
|
| 133 |
+
[
|
| 134 |
+
2304,
|
| 135 |
+
768
|
| 136 |
+
],
|
| 137 |
+
[
|
| 138 |
+
2304,
|
| 139 |
+
1152
|
| 140 |
+
],
|
| 141 |
+
[
|
| 142 |
+
2304,
|
| 143 |
+
1536
|
| 144 |
+
],
|
| 145 |
+
[
|
| 146 |
+
2304,
|
| 147 |
+
1920
|
| 148 |
+
],
|
| 149 |
+
[
|
| 150 |
+
2304,
|
| 151 |
+
2304
|
| 152 |
+
]
|
| 153 |
+
],
|
| 154 |
+
"image_mean": [
|
| 155 |
+
0.5,
|
| 156 |
+
0.5,
|
| 157 |
+
0.5
|
| 158 |
+
],
|
| 159 |
+
"image_processor_type": "LlavaOnevisionImageProcessor",
|
| 160 |
+
"image_std": [
|
| 161 |
+
0.5,
|
| 162 |
+
0.5,
|
| 163 |
+
0.5
|
| 164 |
+
],
|
| 165 |
+
"resample": 2,
|
| 166 |
+
"rescale_factor": 0.00392156862745098,
|
| 167 |
+
"size": {
|
| 168 |
+
"height": 384,
|
| 169 |
+
"width": 384
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"image_token": "<image>",
|
| 173 |
+
"num_image_tokens": 576,
|
| 174 |
+
"processor_class": "LlavaOnevisionProcessor",
|
| 175 |
+
"video_processor": {
|
| 176 |
+
"do_convert_rgb": null,
|
| 177 |
+
"do_normalize": true,
|
| 178 |
+
"do_rescale": true,
|
| 179 |
+
"do_resize": true,
|
| 180 |
+
"do_sample_frames": false,
|
| 181 |
+
"image_mean": [
|
| 182 |
+
0.5,
|
| 183 |
+
0.5,
|
| 184 |
+
0.5
|
| 185 |
+
],
|
| 186 |
+
"image_std": [
|
| 187 |
+
0.5,
|
| 188 |
+
0.5,
|
| 189 |
+
0.5
|
| 190 |
+
],
|
| 191 |
+
"resample": 2,
|
| 192 |
+
"rescale_factor": 0.00392156862745098,
|
| 193 |
+
"return_metadata": false,
|
| 194 |
+
"size": {
|
| 195 |
+
"height": 384,
|
| 196 |
+
"width": 384
|
| 197 |
+
},
|
| 198 |
+
"video_processor_type": "LlavaOnevisionVideoProcessor"
|
| 199 |
+
},
|
| 200 |
+
"video_token": "<video>",
|
| 201 |
+
"vision_aspect_ratio": "anyres_max_9",
|
| 202 |
+
"vision_feature_select_strategy": null
|
| 203 |
+
}
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8f92cf63e0989759370d24108b469c492c12202403f036015307ce49f12cedc
|
| 3 |
+
size 16389
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ed40a0a4e9f365d2c6cc004d97e6705894eba46c8be4c160c1455bc3062dee1
|
| 3 |
+
size 16389
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d688b304d19c260b5cfa471535ed51d7e1d60b3a0d0159dfd1a04b87904a9f42
|
| 3 |
+
size 16389
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9967425ebcaee80d9b518fa0244d52f739b1b983d87cda71d5fede0c073e9d3b
|
| 3 |
+
size 16389
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:469900fd39c667ffbd49c3c407c0ba317a1e9f5f9339a99b5d38423b7d0ce6d4
|
| 3 |
+
size 16389
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:124688471ff2a6e80f2fcefedbf741fb18d08dd539d5bd07a52e81be545142a5
|
| 3 |
+
size 16389
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e69f1ced9f992a72c948698e5eb06088610788988cdb2fdbdd624e064319d60
|
| 3 |
+
size 16389
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a376268a55d6ee10c371c06aa952334c4c6a1af9ea2d71b1951a57367a0c6722
|
| 3 |
+
size 16389
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da1584d8b64fecf58e060dc759aaaff776ddb91eb330f9ad1f9448cb2a2f39f8
|
| 3 |
+
size 1593
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9024318c850eaadf26be79389d21b07a7afd8f1af749b89f9109b06c0d12173c
|
| 3 |
+
size 11423018
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<image>",
|
| 10 |
+
"<video>"
|
| 11 |
+
],
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"model_max_length": 1010000,
|
| 14 |
+
"pad_token": "<|endoftext|>",
|
| 15 |
+
"processor_class": "LlavaOnevisionProcessor",
|
| 16 |
+
"split_special_tokens": false,
|
| 17 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 18 |
+
"unk_token": null
|
| 19 |
+
}
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/trainer_state.json
ADDED
|
@@ -0,0 +1,2490 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 100.0,
|
| 7 |
+
"global_step": 1530,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00065359477124183,
|
| 14 |
+
"grad_norm": 37.487098693847656,
|
| 15 |
+
"learning_rate": 1.2987012987012988e-08,
|
| 16 |
+
"loss": 2.6174159049987793,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.498206599713056
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.0032679738562091504,
|
| 22 |
+
"grad_norm": 35.58439636230469,
|
| 23 |
+
"learning_rate": 6.493506493506492e-08,
|
| 24 |
+
"loss": 2.5398545265197754,
|
| 25 |
+
"step": 5,
|
| 26 |
+
"token_acc": 0.5117717990788148
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.006535947712418301,
|
| 30 |
+
"grad_norm": 27.617551803588867,
|
| 31 |
+
"learning_rate": 1.2987012987012984e-07,
|
| 32 |
+
"loss": 2.48166561126709,
|
| 33 |
+
"step": 10,
|
| 34 |
+
"token_acc": 0.517078772614048
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.00980392156862745,
|
| 38 |
+
"grad_norm": 12.80578899383545,
|
| 39 |
+
"learning_rate": 1.948051948051948e-07,
|
| 40 |
+
"loss": 2.109092140197754,
|
| 41 |
+
"step": 15,
|
| 42 |
+
"token_acc": 0.5542840977796021
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.013071895424836602,
|
| 46 |
+
"grad_norm": 7.174593448638916,
|
| 47 |
+
"learning_rate": 2.597402597402597e-07,
|
| 48 |
+
"loss": 1.6617883682250976,
|
| 49 |
+
"step": 20,
|
| 50 |
+
"token_acc": 0.6178204353083434
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.016339869281045753,
|
| 54 |
+
"grad_norm": 3.7175638675689697,
|
| 55 |
+
"learning_rate": 3.2467532467532465e-07,
|
| 56 |
+
"loss": 1.4801443099975586,
|
| 57 |
+
"step": 25,
|
| 58 |
+
"token_acc": 0.6439660077973259
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0196078431372549,
|
| 62 |
+
"grad_norm": 4.880731105804443,
|
| 63 |
+
"learning_rate": 3.896103896103896e-07,
|
| 64 |
+
"loss": 1.3889575958251954,
|
| 65 |
+
"step": 30,
|
| 66 |
+
"token_acc": 0.6632652525877853
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.02287581699346405,
|
| 70 |
+
"grad_norm": 2.293424606323242,
|
| 71 |
+
"learning_rate": 4.545454545454545e-07,
|
| 72 |
+
"loss": 1.3116580963134765,
|
| 73 |
+
"step": 35,
|
| 74 |
+
"token_acc": 0.6738253608831022
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.026143790849673203,
|
| 78 |
+
"grad_norm": 3.7746570110321045,
|
| 79 |
+
"learning_rate": 5.194805194805194e-07,
|
| 80 |
+
"loss": 1.2499441146850585,
|
| 81 |
+
"step": 40,
|
| 82 |
+
"token_acc": 0.6811100850759235
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.029411764705882353,
|
| 86 |
+
"grad_norm": 6.167793273925781,
|
| 87 |
+
"learning_rate": 5.844155844155844e-07,
|
| 88 |
+
"loss": 1.192238998413086,
|
| 89 |
+
"step": 45,
|
| 90 |
+
"token_acc": 0.6917249603390083
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.032679738562091505,
|
| 94 |
+
"grad_norm": 3.714318037033081,
|
| 95 |
+
"learning_rate": 6.493506493506493e-07,
|
| 96 |
+
"loss": 1.1589247703552246,
|
| 97 |
+
"step": 50,
|
| 98 |
+
"token_acc": 0.7012059451762193
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.03594771241830065,
|
| 102 |
+
"grad_norm": 7.468631267547607,
|
| 103 |
+
"learning_rate": 7.142857142857143e-07,
|
| 104 |
+
"loss": 1.1704049110412598,
|
| 105 |
+
"step": 55,
|
| 106 |
+
"token_acc": 0.6980293614609508
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.0392156862745098,
|
| 110 |
+
"grad_norm": 6.417658805847168,
|
| 111 |
+
"learning_rate": 7.792207792207792e-07,
|
| 112 |
+
"loss": 1.1185226440429688,
|
| 113 |
+
"step": 60,
|
| 114 |
+
"token_acc": 0.7117014370185812
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.042483660130718956,
|
| 118 |
+
"grad_norm": 3.59606671333313,
|
| 119 |
+
"learning_rate": 8.44155844155844e-07,
|
| 120 |
+
"loss": 1.103659439086914,
|
| 121 |
+
"step": 65,
|
| 122 |
+
"token_acc": 0.710606975733389
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0457516339869281,
|
| 126 |
+
"grad_norm": 3.3894736766815186,
|
| 127 |
+
"learning_rate": 9.09090909090909e-07,
|
| 128 |
+
"loss": 1.1238019943237305,
|
| 129 |
+
"step": 70,
|
| 130 |
+
"token_acc": 0.7076875590433342
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.049019607843137254,
|
| 134 |
+
"grad_norm": 4.485665321350098,
|
| 135 |
+
"learning_rate": 9.74025974025974e-07,
|
| 136 |
+
"loss": 1.1299985885620116,
|
| 137 |
+
"step": 75,
|
| 138 |
+
"token_acc": 0.7009239561172986
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.05228758169934641,
|
| 142 |
+
"grad_norm": 3.7222633361816406,
|
| 143 |
+
"learning_rate": 9.999894816041221e-07,
|
| 144 |
+
"loss": 1.0768622398376464,
|
| 145 |
+
"step": 80,
|
| 146 |
+
"token_acc": 0.7137428715634119
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.05555555555555555,
|
| 150 |
+
"grad_norm": 4.0969929695129395,
|
| 151 |
+
"learning_rate": 9.999252041208325e-07,
|
| 152 |
+
"loss": 1.1004796981811524,
|
| 153 |
+
"step": 85,
|
| 154 |
+
"token_acc": 0.7073845986157283
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.058823529411764705,
|
| 158 |
+
"grad_norm": 4.78889274597168,
|
| 159 |
+
"learning_rate": 9.99802500210544e-07,
|
| 160 |
+
"loss": 1.0721593856811524,
|
| 161 |
+
"step": 90,
|
| 162 |
+
"token_acc": 0.7182469574888349
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.06209150326797386,
|
| 166 |
+
"grad_norm": 4.737462997436523,
|
| 167 |
+
"learning_rate": 9.99621384213704e-07,
|
| 168 |
+
"loss": 1.0795677185058594,
|
| 169 |
+
"step": 95,
|
| 170 |
+
"token_acc": 0.7141577336159146
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.06535947712418301,
|
| 174 |
+
"grad_norm": 7.180952072143555,
|
| 175 |
+
"learning_rate": 9.993818772974002e-07,
|
| 176 |
+
"loss": 1.0497736930847168,
|
| 177 |
+
"step": 100,
|
| 178 |
+
"token_acc": 0.7222854012729751
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.06862745098039216,
|
| 182 |
+
"grad_norm": 2.6949493885040283,
|
| 183 |
+
"learning_rate": 9.99084007452886e-07,
|
| 184 |
+
"loss": 1.0393510818481446,
|
| 185 |
+
"step": 105,
|
| 186 |
+
"token_acc": 0.722550271305458
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.0718954248366013,
|
| 190 |
+
"grad_norm": 4.692465305328369,
|
| 191 |
+
"learning_rate": 9.98727809492311e-07,
|
| 192 |
+
"loss": 1.0661162376403808,
|
| 193 |
+
"step": 110,
|
| 194 |
+
"token_acc": 0.7169941039292471
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.07516339869281045,
|
| 198 |
+
"grad_norm": 4.411740303039551,
|
| 199 |
+
"learning_rate": 9.983133250446507e-07,
|
| 200 |
+
"loss": 1.0683698654174805,
|
| 201 |
+
"step": 115,
|
| 202 |
+
"token_acc": 0.7133460640780819
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.0784313725490196,
|
| 206 |
+
"grad_norm": 4.77487325668335,
|
| 207 |
+
"learning_rate": 9.978406025508422e-07,
|
| 208 |
+
"loss": 1.0595972061157226,
|
| 209 |
+
"step": 120,
|
| 210 |
+
"token_acc": 0.7164824334464491
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.08169934640522876,
|
| 214 |
+
"grad_norm": 4.149869441986084,
|
| 215 |
+
"learning_rate": 9.973096972581224e-07,
|
| 216 |
+
"loss": 1.0410707473754883,
|
| 217 |
+
"step": 125,
|
| 218 |
+
"token_acc": 0.7201861025148132
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.08496732026143791,
|
| 222 |
+
"grad_norm": 4.482669830322266,
|
| 223 |
+
"learning_rate": 9.967206712135716e-07,
|
| 224 |
+
"loss": 1.042248249053955,
|
| 225 |
+
"step": 130,
|
| 226 |
+
"token_acc": 0.7223222181761432
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.08823529411764706,
|
| 230 |
+
"grad_norm": 8.391205787658691,
|
| 231 |
+
"learning_rate": 9.960735932568622e-07,
|
| 232 |
+
"loss": 1.0062286376953125,
|
| 233 |
+
"step": 135,
|
| 234 |
+
"token_acc": 0.7288336223580869
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.0915032679738562,
|
| 238 |
+
"grad_norm": 5.650303363800049,
|
| 239 |
+
"learning_rate": 9.95368539012213e-07,
|
| 240 |
+
"loss": 1.03353271484375,
|
| 241 |
+
"step": 140,
|
| 242 |
+
"token_acc": 0.7225992894639164
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.09477124183006536,
|
| 246 |
+
"grad_norm": 5.011268615722656,
|
| 247 |
+
"learning_rate": 9.94605590879551e-07,
|
| 248 |
+
"loss": 1.0167567253112793,
|
| 249 |
+
"step": 145,
|
| 250 |
+
"token_acc": 0.7287733222351831
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.09803921568627451,
|
| 254 |
+
"grad_norm": 4.620847702026367,
|
| 255 |
+
"learning_rate": 9.937848380248816e-07,
|
| 256 |
+
"loss": 1.0046657562255858,
|
| 257 |
+
"step": 150,
|
| 258 |
+
"token_acc": 0.7273684573104422
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.10130718954248366,
|
| 262 |
+
"grad_norm": 7.521317958831787,
|
| 263 |
+
"learning_rate": 9.929063763698672e-07,
|
| 264 |
+
"loss": 1.0060005187988281,
|
| 265 |
+
"step": 155,
|
| 266 |
+
"token_acc": 0.7281812125249834
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.10457516339869281,
|
| 270 |
+
"grad_norm": 6.834804534912109,
|
| 271 |
+
"learning_rate": 9.919703085806174e-07,
|
| 272 |
+
"loss": 0.9995226860046387,
|
| 273 |
+
"step": 160,
|
| 274 |
+
"token_acc": 0.7350646081557308
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.10784313725490197,
|
| 278 |
+
"grad_norm": 4.372734546661377,
|
| 279 |
+
"learning_rate": 9.9097674405569e-07,
|
| 280 |
+
"loss": 1.029765510559082,
|
| 281 |
+
"step": 165,
|
| 282 |
+
"token_acc": 0.7215937663498707
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.1111111111111111,
|
| 286 |
+
"grad_norm": 6.708244800567627,
|
| 287 |
+
"learning_rate": 9.899257989133057e-07,
|
| 288 |
+
"loss": 0.9966096878051758,
|
| 289 |
+
"step": 170,
|
| 290 |
+
"token_acc": 0.7327855691922202
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.11437908496732026,
|
| 294 |
+
"grad_norm": 5.262089252471924,
|
| 295 |
+
"learning_rate": 9.88817595977777e-07,
|
| 296 |
+
"loss": 1.0036701202392577,
|
| 297 |
+
"step": 175,
|
| 298 |
+
"token_acc": 0.7241035415096848
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.11764705882352941,
|
| 302 |
+
"grad_norm": 5.186875343322754,
|
| 303 |
+
"learning_rate": 9.87652264765155e-07,
|
| 304 |
+
"loss": 0.9910825729370117,
|
| 305 |
+
"step": 180,
|
| 306 |
+
"token_acc": 0.7287636555249534
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.12091503267973856,
|
| 310 |
+
"grad_norm": 6.756556987762451,
|
| 311 |
+
"learning_rate": 9.864299414680904e-07,
|
| 312 |
+
"loss": 1.0290884017944335,
|
| 313 |
+
"step": 185,
|
| 314 |
+
"token_acc": 0.7258321650715888
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.12418300653594772,
|
| 318 |
+
"grad_norm": 8.717490196228027,
|
| 319 |
+
"learning_rate": 9.851507689399188e-07,
|
| 320 |
+
"loss": 0.9761259078979492,
|
| 321 |
+
"step": 190,
|
| 322 |
+
"token_acc": 0.7322245028725334
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.12745098039215685,
|
| 326 |
+
"grad_norm": 5.428329944610596,
|
| 327 |
+
"learning_rate": 9.838148966779644e-07,
|
| 328 |
+
"loss": 0.9808815956115723,
|
| 329 |
+
"step": 195,
|
| 330 |
+
"token_acc": 0.7326248105827907
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.13071895424836602,
|
| 334 |
+
"grad_norm": 11.826949119567871,
|
| 335 |
+
"learning_rate": 9.824224808060689e-07,
|
| 336 |
+
"loss": 0.9701013565063477,
|
| 337 |
+
"step": 200,
|
| 338 |
+
"token_acc": 0.7368753917155718
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.13398692810457516,
|
| 342 |
+
"grad_norm": 4.152238845825195,
|
| 343 |
+
"learning_rate": 9.809736840563434e-07,
|
| 344 |
+
"loss": 0.9894078254699707,
|
| 345 |
+
"step": 205,
|
| 346 |
+
"token_acc": 0.7319060086115499
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.13725490196078433,
|
| 350 |
+
"grad_norm": 7.72074031829834,
|
| 351 |
+
"learning_rate": 9.794686757501526e-07,
|
| 352 |
+
"loss": 0.9568647384643555,
|
| 353 |
+
"step": 210,
|
| 354 |
+
"token_acc": 0.7405125765594339
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.14052287581699346,
|
| 358 |
+
"grad_norm": 6.2891764640808105,
|
| 359 |
+
"learning_rate": 9.779076317783244e-07,
|
| 360 |
+
"loss": 0.9645475387573242,
|
| 361 |
+
"step": 215,
|
| 362 |
+
"token_acc": 0.7383844708829055
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.1437908496732026,
|
| 366 |
+
"grad_norm": 8.742475509643555,
|
| 367 |
+
"learning_rate": 9.762907345805932e-07,
|
| 368 |
+
"loss": 1.005259132385254,
|
| 369 |
+
"step": 220,
|
| 370 |
+
"token_acc": 0.7278260917947776
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.14705882352941177,
|
| 374 |
+
"grad_norm": 9.067325592041016,
|
| 375 |
+
"learning_rate": 9.746181731242791e-07,
|
| 376 |
+
"loss": 0.9713424682617188,
|
| 377 |
+
"step": 225,
|
| 378 |
+
"token_acc": 0.7355438090661541
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.1503267973856209,
|
| 382 |
+
"grad_norm": 5.31483268737793,
|
| 383 |
+
"learning_rate": 9.72890142882203e-07,
|
| 384 |
+
"loss": 0.9598846435546875,
|
| 385 |
+
"step": 230,
|
| 386 |
+
"token_acc": 0.7411211858213046
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.15359477124183007,
|
| 390 |
+
"grad_norm": 14.251708030700684,
|
| 391 |
+
"learning_rate": 9.711068458098417e-07,
|
| 392 |
+
"loss": 0.9714849472045899,
|
| 393 |
+
"step": 235,
|
| 394 |
+
"token_acc": 0.7338732122976792
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1568627450980392,
|
| 398 |
+
"grad_norm": 7.291672706604004,
|
| 399 |
+
"learning_rate": 9.69268490321724e-07,
|
| 400 |
+
"loss": 0.9817766189575196,
|
| 401 |
+
"step": 240,
|
| 402 |
+
"token_acc": 0.7326437493989293
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.16013071895424835,
|
| 406 |
+
"grad_norm": 12.170002937316895,
|
| 407 |
+
"learning_rate": 9.67375291267076e-07,
|
| 408 |
+
"loss": 0.9801557540893555,
|
| 409 |
+
"step": 245,
|
| 410 |
+
"token_acc": 0.7311134841277546
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.16339869281045752,
|
| 414 |
+
"grad_norm": 7.71054744720459,
|
| 415 |
+
"learning_rate": 9.654274699047078e-07,
|
| 416 |
+
"loss": 0.9933223724365234,
|
| 417 |
+
"step": 250,
|
| 418 |
+
"token_acc": 0.7321582563894122
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.16666666666666666,
|
| 422 |
+
"grad_norm": 6.522094249725342,
|
| 423 |
+
"learning_rate": 9.634252538771587e-07,
|
| 424 |
+
"loss": 0.9696138381958008,
|
| 425 |
+
"step": 255,
|
| 426 |
+
"token_acc": 0.7330871401916763
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.16993464052287582,
|
| 430 |
+
"grad_norm": 6.7956013679504395,
|
| 431 |
+
"learning_rate": 9.613688771840906e-07,
|
| 432 |
+
"loss": 0.9824813842773438,
|
| 433 |
+
"step": 260,
|
| 434 |
+
"token_acc": 0.7275903399382858
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.17320261437908496,
|
| 438 |
+
"grad_norm": 7.285985946655273,
|
| 439 |
+
"learning_rate": 9.592585801549396e-07,
|
| 440 |
+
"loss": 0.9660924911499024,
|
| 441 |
+
"step": 265,
|
| 442 |
+
"token_acc": 0.7365396905098827
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.17647058823529413,
|
| 446 |
+
"grad_norm": 4.643677234649658,
|
| 447 |
+
"learning_rate": 9.570946094208307e-07,
|
| 448 |
+
"loss": 0.956600570678711,
|
| 449 |
+
"step": 270,
|
| 450 |
+
"token_acc": 0.7400797629391974
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.17973856209150327,
|
| 454 |
+
"grad_norm": 6.63626766204834,
|
| 455 |
+
"learning_rate": 9.548772178857525e-07,
|
| 456 |
+
"loss": 0.9600159645080566,
|
| 457 |
+
"step": 275,
|
| 458 |
+
"token_acc": 0.7352620031634267
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.1830065359477124,
|
| 462 |
+
"grad_norm": 7.296706676483154,
|
| 463 |
+
"learning_rate": 9.526066646970005e-07,
|
| 464 |
+
"loss": 0.9449337005615235,
|
| 465 |
+
"step": 280,
|
| 466 |
+
"token_acc": 0.7419554797252926
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.18627450980392157,
|
| 470 |
+
"grad_norm": 7.971829414367676,
|
| 471 |
+
"learning_rate": 9.502832152148906e-07,
|
| 472 |
+
"loss": 0.9815473556518555,
|
| 473 |
+
"step": 285,
|
| 474 |
+
"token_acc": 0.7321873051164556
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.1895424836601307,
|
| 478 |
+
"grad_norm": 5.92852783203125,
|
| 479 |
+
"learning_rate": 9.479071409817466e-07,
|
| 480 |
+
"loss": 0.951810359954834,
|
| 481 |
+
"step": 290,
|
| 482 |
+
"token_acc": 0.7357849973144375
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.19281045751633988,
|
| 486 |
+
"grad_norm": 4.31951904296875,
|
| 487 |
+
"learning_rate": 9.454787196901644e-07,
|
| 488 |
+
"loss": 0.9596097946166993,
|
| 489 |
+
"step": 295,
|
| 490 |
+
"token_acc": 0.736672814059449
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.19607843137254902,
|
| 494 |
+
"grad_norm": 6.891040325164795,
|
| 495 |
+
"learning_rate": 9.429982351505583e-07,
|
| 496 |
+
"loss": 0.9675204277038574,
|
| 497 |
+
"step": 300,
|
| 498 |
+
"token_acc": 0.7357593339390365
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.19934640522875818,
|
| 502 |
+
"grad_norm": 5.005938529968262,
|
| 503 |
+
"learning_rate": 9.40465977257992e-07,
|
| 504 |
+
"loss": 0.9583789825439453,
|
| 505 |
+
"step": 305,
|
| 506 |
+
"token_acc": 0.7359373849374585
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.20261437908496732,
|
| 510 |
+
"grad_norm": 9.155474662780762,
|
| 511 |
+
"learning_rate": 9.378822419582984e-07,
|
| 512 |
+
"loss": 0.9387321472167969,
|
| 513 |
+
"step": 310,
|
| 514 |
+
"token_acc": 0.7409644343950913
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.20588235294117646,
|
| 518 |
+
"grad_norm": 5.862011909484863,
|
| 519 |
+
"learning_rate": 9.352473312134921e-07,
|
| 520 |
+
"loss": 0.9353184700012207,
|
| 521 |
+
"step": 315,
|
| 522 |
+
"token_acc": 0.7447350347350955
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.20915032679738563,
|
| 526 |
+
"grad_norm": 4.55186128616333,
|
| 527 |
+
"learning_rate": 9.325615529664795e-07,
|
| 528 |
+
"loss": 0.961051082611084,
|
| 529 |
+
"step": 320,
|
| 530 |
+
"token_acc": 0.7375694127390293
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.21241830065359477,
|
| 534 |
+
"grad_norm": 7.405783176422119,
|
| 535 |
+
"learning_rate": 9.29825221105069e-07,
|
| 536 |
+
"loss": 0.9282285690307617,
|
| 537 |
+
"step": 325,
|
| 538 |
+
"token_acc": 0.7463020145607374
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.21568627450980393,
|
| 542 |
+
"grad_norm": 4.437286376953125,
|
| 543 |
+
"learning_rate": 9.270386554252869e-07,
|
| 544 |
+
"loss": 0.987796401977539,
|
| 545 |
+
"step": 330,
|
| 546 |
+
"token_acc": 0.7294508641567916
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.21895424836601307,
|
| 550 |
+
"grad_norm": 5.703218936920166,
|
| 551 |
+
"learning_rate": 9.24202181594003e-07,
|
| 552 |
+
"loss": 0.93038330078125,
|
| 553 |
+
"step": 335,
|
| 554 |
+
"token_acc": 0.743964535062663
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.2222222222222222,
|
| 558 |
+
"grad_norm": 5.6957879066467285,
|
| 559 |
+
"learning_rate": 9.21316131110869e-07,
|
| 560 |
+
"loss": 0.9411786079406739,
|
| 561 |
+
"step": 340,
|
| 562 |
+
"token_acc": 0.7370189919572179
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.22549019607843138,
|
| 566 |
+
"grad_norm": 5.429040431976318,
|
| 567 |
+
"learning_rate": 9.183808412695775e-07,
|
| 568 |
+
"loss": 0.914295768737793,
|
| 569 |
+
"step": 345,
|
| 570 |
+
"token_acc": 0.7475255203157224
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.22875816993464052,
|
| 574 |
+
"grad_norm": 8.422659873962402,
|
| 575 |
+
"learning_rate": 9.153966551184404e-07,
|
| 576 |
+
"loss": 0.9484868049621582,
|
| 577 |
+
"step": 350,
|
| 578 |
+
"token_acc": 0.7393365465759709
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.23202614379084968,
|
| 582 |
+
"grad_norm": 8.870351791381836,
|
| 583 |
+
"learning_rate": 9.12363921420299e-07,
|
| 584 |
+
"loss": 0.9556077003479004,
|
| 585 |
+
"step": 355,
|
| 586 |
+
"token_acc": 0.738435938266231
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.23529411764705882,
|
| 590 |
+
"grad_norm": 6.629728317260742,
|
| 591 |
+
"learning_rate": 9.092829946117615e-07,
|
| 592 |
+
"loss": 0.9680583953857422,
|
| 593 |
+
"step": 360,
|
| 594 |
+
"token_acc": 0.7362247135054376
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.238562091503268,
|
| 598 |
+
"grad_norm": 7.083685398101807,
|
| 599 |
+
"learning_rate": 9.061542347617824e-07,
|
| 600 |
+
"loss": 0.9491727828979493,
|
| 601 |
+
"step": 365,
|
| 602 |
+
"token_acc": 0.7373380961470292
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.24183006535947713,
|
| 606 |
+
"grad_norm": 4.022984504699707,
|
| 607 |
+
"learning_rate": 9.029780075295787e-07,
|
| 608 |
+
"loss": 0.9155566215515136,
|
| 609 |
+
"step": 370,
|
| 610 |
+
"token_acc": 0.7481828482989249
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.24509803921568626,
|
| 614 |
+
"grad_norm": 7.642209529876709,
|
| 615 |
+
"learning_rate": 8.99754684121897e-07,
|
| 616 |
+
"loss": 0.9566659927368164,
|
| 617 |
+
"step": 375,
|
| 618 |
+
"token_acc": 0.7335383598847576
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.24836601307189543,
|
| 622 |
+
"grad_norm": 12.620061874389648,
|
| 623 |
+
"learning_rate": 8.964846412496301e-07,
|
| 624 |
+
"loss": 0.9460546493530273,
|
| 625 |
+
"step": 380,
|
| 626 |
+
"token_acc": 0.7363932933768302
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.25163398692810457,
|
| 630 |
+
"grad_norm": 7.53920316696167,
|
| 631 |
+
"learning_rate": 8.931682610837896e-07,
|
| 632 |
+
"loss": 0.922614860534668,
|
| 633 |
+
"step": 385,
|
| 634 |
+
"token_acc": 0.7445524881837613
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.2549019607843137,
|
| 638 |
+
"grad_norm": 5.7319135665893555,
|
| 639 |
+
"learning_rate": 8.898059312108425e-07,
|
| 640 |
+
"loss": 0.9245988845825195,
|
| 641 |
+
"step": 390,
|
| 642 |
+
"token_acc": 0.746327721923947
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.2581699346405229,
|
| 646 |
+
"grad_norm": 6.358862400054932,
|
| 647 |
+
"learning_rate": 8.86398044587414e-07,
|
| 648 |
+
"loss": 0.9413824081420898,
|
| 649 |
+
"step": 395,
|
| 650 |
+
"token_acc": 0.7400325424021034
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.26143790849673204,
|
| 654 |
+
"grad_norm": 5.716063022613525,
|
| 655 |
+
"learning_rate": 8.829449994943612e-07,
|
| 656 |
+
"loss": 0.9343231201171875,
|
| 657 |
+
"step": 400,
|
| 658 |
+
"token_acc": 0.7380929935952533
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.2647058823529412,
|
| 662 |
+
"grad_norm": 4.901727199554443,
|
| 663 |
+
"learning_rate": 8.794471994902276e-07,
|
| 664 |
+
"loss": 0.9230119705200195,
|
| 665 |
+
"step": 405,
|
| 666 |
+
"token_acc": 0.7428686376513581
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.2679738562091503,
|
| 670 |
+
"grad_norm": 5.407273769378662,
|
| 671 |
+
"learning_rate": 8.759050533640777e-07,
|
| 672 |
+
"loss": 0.9501132011413574,
|
| 673 |
+
"step": 410,
|
| 674 |
+
"token_acc": 0.7382072722262847
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.27124183006535946,
|
| 678 |
+
"grad_norm": 10.502655982971191,
|
| 679 |
+
"learning_rate": 8.723189750877224e-07,
|
| 680 |
+
"loss": 0.9346388816833496,
|
| 681 |
+
"step": 415,
|
| 682 |
+
"token_acc": 0.7427824937935453
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.27450980392156865,
|
| 686 |
+
"grad_norm": 5.800553321838379,
|
| 687 |
+
"learning_rate": 8.686893837673379e-07,
|
| 688 |
+
"loss": 0.9222194671630859,
|
| 689 |
+
"step": 420,
|
| 690 |
+
"token_acc": 0.7449170672371573
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.2777777777777778,
|
| 694 |
+
"grad_norm": 5.452874660491943,
|
| 695 |
+
"learning_rate": 8.650167035944841e-07,
|
| 696 |
+
"loss": 0.918070125579834,
|
| 697 |
+
"step": 425,
|
| 698 |
+
"token_acc": 0.7458841498962293
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.28104575163398693,
|
| 702 |
+
"grad_norm": 7.133504867553711,
|
| 703 |
+
"learning_rate": 8.613013637965303e-07,
|
| 704 |
+
"loss": 0.9358392715454101,
|
| 705 |
+
"step": 430,
|
| 706 |
+
"token_acc": 0.74008143544143
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.28431372549019607,
|
| 710 |
+
"grad_norm": 5.590691566467285,
|
| 711 |
+
"learning_rate": 8.5754379858649e-07,
|
| 712 |
+
"loss": 0.9125219345092773,
|
| 713 |
+
"step": 435,
|
| 714 |
+
"token_acc": 0.7487142440233278
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.2875816993464052,
|
| 718 |
+
"grad_norm": 4.133114814758301,
|
| 719 |
+
"learning_rate": 8.537444471122747e-07,
|
| 720 |
+
"loss": 0.9120442390441894,
|
| 721 |
+
"step": 440,
|
| 722 |
+
"token_acc": 0.7470229110060045
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.2908496732026144,
|
| 726 |
+
"grad_norm": 7.450751781463623,
|
| 727 |
+
"learning_rate": 8.499037534053712e-07,
|
| 728 |
+
"loss": 0.9132026672363281,
|
| 729 |
+
"step": 445,
|
| 730 |
+
"token_acc": 0.7494350299419145
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.29411764705882354,
|
| 734 |
+
"grad_norm": 5.723353385925293,
|
| 735 |
+
"learning_rate": 8.460221663289468e-07,
|
| 736 |
+
"loss": 0.8951844215393067,
|
| 737 |
+
"step": 450,
|
| 738 |
+
"token_acc": 0.7518667994680269
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.2973856209150327,
|
| 742 |
+
"grad_norm": 6.323465824127197,
|
| 743 |
+
"learning_rate": 8.421001395253906e-07,
|
| 744 |
+
"loss": 0.9172885894775391,
|
| 745 |
+
"step": 455,
|
| 746 |
+
"token_acc": 0.7466637709818086
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.3006535947712418,
|
| 750 |
+
"grad_norm": 6.585511207580566,
|
| 751 |
+
"learning_rate": 8.38138131363296e-07,
|
| 752 |
+
"loss": 0.9039304733276368,
|
| 753 |
+
"step": 460,
|
| 754 |
+
"token_acc": 0.7509074950968175
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.30392156862745096,
|
| 758 |
+
"grad_norm": 6.171856880187988,
|
| 759 |
+
"learning_rate": 8.341366048838915e-07,
|
| 760 |
+
"loss": 0.9312383651733398,
|
| 761 |
+
"step": 465,
|
| 762 |
+
"token_acc": 0.7420631940346548
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.30718954248366015,
|
| 766 |
+
"grad_norm": 11.727663040161133,
|
| 767 |
+
"learning_rate": 8.300960277469247e-07,
|
| 768 |
+
"loss": 0.9180435180664063,
|
| 769 |
+
"step": 470,
|
| 770 |
+
"token_acc": 0.7459852690976388
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.3104575163398693,
|
| 774 |
+
"grad_norm": 5.027020454406738,
|
| 775 |
+
"learning_rate": 8.260168721760066e-07,
|
| 776 |
+
"loss": 0.9219095230102539,
|
| 777 |
+
"step": 475,
|
| 778 |
+
"token_acc": 0.7395984482809678
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.3137254901960784,
|
| 782 |
+
"grad_norm": 3.750598907470703,
|
| 783 |
+
"learning_rate": 8.218996149034228e-07,
|
| 784 |
+
"loss": 0.9236850738525391,
|
| 785 |
+
"step": 480,
|
| 786 |
+
"token_acc": 0.7432284828491675
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.31699346405228757,
|
| 790 |
+
"grad_norm": 5.205167770385742,
|
| 791 |
+
"learning_rate": 8.177447371144174e-07,
|
| 792 |
+
"loss": 0.9272337913513183,
|
| 793 |
+
"step": 485,
|
| 794 |
+
"token_acc": 0.7390940813164026
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.3202614379084967,
|
| 798 |
+
"grad_norm": 6.060414791107178,
|
| 799 |
+
"learning_rate": 8.135527243909572e-07,
|
| 800 |
+
"loss": 0.9162891387939454,
|
| 801 |
+
"step": 490,
|
| 802 |
+
"token_acc": 0.7456594778796571
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.3235294117647059,
|
| 806 |
+
"grad_norm": 5.669540882110596,
|
| 807 |
+
"learning_rate": 8.093240666549815e-07,
|
| 808 |
+
"loss": 0.9326946258544921,
|
| 809 |
+
"step": 495,
|
| 810 |
+
"token_acc": 0.7425646779983168
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.32679738562091504,
|
| 814 |
+
"grad_norm": 6.681833744049072,
|
| 815 |
+
"learning_rate": 8.050592581111439e-07,
|
| 816 |
+
"loss": 0.9172059059143066,
|
| 817 |
+
"step": 500,
|
| 818 |
+
"token_acc": 0.7475074568335492
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.3300653594771242,
|
| 822 |
+
"grad_norm": 6.1682515144348145,
|
| 823 |
+
"learning_rate": 8.007587971890558e-07,
|
| 824 |
+
"loss": 0.9116528511047364,
|
| 825 |
+
"step": 505,
|
| 826 |
+
"token_acc": 0.7481865684804656
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.3333333333333333,
|
| 830 |
+
"grad_norm": 6.87222146987915,
|
| 831 |
+
"learning_rate": 7.964231864850335e-07,
|
| 832 |
+
"loss": 0.9385147094726562,
|
| 833 |
+
"step": 510,
|
| 834 |
+
"token_acc": 0.7400723652185259
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.3366013071895425,
|
| 838 |
+
"grad_norm": 5.943138122558594,
|
| 839 |
+
"learning_rate": 7.920529327033603e-07,
|
| 840 |
+
"loss": 0.9146569252014161,
|
| 841 |
+
"step": 515,
|
| 842 |
+
"token_acc": 0.7456709900178122
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.33986928104575165,
|
| 846 |
+
"grad_norm": 7.1031317710876465,
|
| 847 |
+
"learning_rate": 7.876485465970679e-07,
|
| 848 |
+
"loss": 0.9254459381103516,
|
| 849 |
+
"step": 520,
|
| 850 |
+
"token_acc": 0.7409749297039295
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.3431372549019608,
|
| 854 |
+
"grad_norm": 12.593496322631836,
|
| 855 |
+
"learning_rate": 7.832105429082441e-07,
|
| 856 |
+
"loss": 0.9072103500366211,
|
| 857 |
+
"step": 525,
|
| 858 |
+
"token_acc": 0.7478444641793226
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.3464052287581699,
|
| 862 |
+
"grad_norm": 7.187231540679932,
|
| 863 |
+
"learning_rate": 7.787394403078746e-07,
|
| 864 |
+
"loss": 0.914094352722168,
|
| 865 |
+
"step": 530,
|
| 866 |
+
"token_acc": 0.7446886788542055
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.34967320261437906,
|
| 870 |
+
"grad_norm": 7.671436309814453,
|
| 871 |
+
"learning_rate": 7.742357613352268e-07,
|
| 872 |
+
"loss": 0.9172598838806152,
|
| 873 |
+
"step": 535,
|
| 874 |
+
"token_acc": 0.7422301379590761
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.35294117647058826,
|
| 878 |
+
"grad_norm": 6.882475852966309,
|
| 879 |
+
"learning_rate": 7.69700032336779e-07,
|
| 880 |
+
"loss": 0.9130062103271485,
|
| 881 |
+
"step": 540,
|
| 882 |
+
"token_acc": 0.7447843650085612
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.3562091503267974,
|
| 886 |
+
"grad_norm": 8.801658630371094,
|
| 887 |
+
"learning_rate": 7.65132783404707e-07,
|
| 888 |
+
"loss": 0.9127139091491699,
|
| 889 |
+
"step": 545,
|
| 890 |
+
"token_acc": 0.7488867837836305
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.35947712418300654,
|
| 894 |
+
"grad_norm": 6.594692230224609,
|
| 895 |
+
"learning_rate": 7.605345483149322e-07,
|
| 896 |
+
"loss": 0.9141340255737305,
|
| 897 |
+
"step": 550,
|
| 898 |
+
"token_acc": 0.7455132961278321
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.3627450980392157,
|
| 902 |
+
"grad_norm": 12.87818431854248,
|
| 903 |
+
"learning_rate": 7.559058644647378e-07,
|
| 904 |
+
"loss": 0.9186776161193848,
|
| 905 |
+
"step": 555,
|
| 906 |
+
"token_acc": 0.7428907711385275
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.3660130718954248,
|
| 910 |
+
"grad_norm": 290.5351257324219,
|
| 911 |
+
"learning_rate": 7.51247272809965e-07,
|
| 912 |
+
"loss": 0.8787559509277344,
|
| 913 |
+
"step": 560,
|
| 914 |
+
"token_acc": 0.7526543173344381
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.369281045751634,
|
| 918 |
+
"grad_norm": 3.8215227127075195,
|
| 919 |
+
"learning_rate": 7.465593178017896e-07,
|
| 920 |
+
"loss": 0.922991943359375,
|
| 921 |
+
"step": 565,
|
| 922 |
+
"token_acc": 0.7447598575566914
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.37254901960784315,
|
| 926 |
+
"grad_norm": 9.614330291748047,
|
| 927 |
+
"learning_rate": 7.418425473230923e-07,
|
| 928 |
+
"loss": 0.9263418197631836,
|
| 929 |
+
"step": 570,
|
| 930 |
+
"token_acc": 0.743005062605471
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.3758169934640523,
|
| 934 |
+
"grad_norm": 9.313026428222656,
|
| 935 |
+
"learning_rate": 7.370975126244279e-07,
|
| 936 |
+
"loss": 0.9136220932006835,
|
| 937 |
+
"step": 575,
|
| 938 |
+
"token_acc": 0.7439836008815076
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.3790849673202614,
|
| 942 |
+
"grad_norm": 5.885051250457764,
|
| 943 |
+
"learning_rate": 7.323247682596e-07,
|
| 944 |
+
"loss": 0.892108154296875,
|
| 945 |
+
"step": 580,
|
| 946 |
+
"token_acc": 0.7555090377816404
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.38235294117647056,
|
| 950 |
+
"grad_norm": 7.033209800720215,
|
| 951 |
+
"learning_rate": 7.275248720208499e-07,
|
| 952 |
+
"loss": 0.9108446121215821,
|
| 953 |
+
"step": 585,
|
| 954 |
+
"token_acc": 0.746905962413173
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.38562091503267976,
|
| 958 |
+
"grad_norm": 5.163381576538086,
|
| 959 |
+
"learning_rate": 7.226983848736678e-07,
|
| 960 |
+
"loss": 0.8831884384155273,
|
| 961 |
+
"step": 590,
|
| 962 |
+
"token_acc": 0.7554064799363878
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.3888888888888889,
|
| 966 |
+
"grad_norm": 5.518078327178955,
|
| 967 |
+
"learning_rate": 7.178458708912327e-07,
|
| 968 |
+
"loss": 0.9059237480163574,
|
| 969 |
+
"step": 595,
|
| 970 |
+
"token_acc": 0.7452373031714349
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.39215686274509803,
|
| 974 |
+
"grad_norm": 3.9449164867401123,
|
| 975 |
+
"learning_rate": 7.12967897188488e-07,
|
| 976 |
+
"loss": 0.9253978729248047,
|
| 977 |
+
"step": 600,
|
| 978 |
+
"token_acc": 0.7438855203846312
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.3954248366013072,
|
| 982 |
+
"grad_norm": 5.861351490020752,
|
| 983 |
+
"learning_rate": 7.080650338558633e-07,
|
| 984 |
+
"loss": 0.9073525428771972,
|
| 985 |
+
"step": 605,
|
| 986 |
+
"token_acc": 0.7446656733418859
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.39869281045751637,
|
| 990 |
+
"grad_norm": 14.756239891052246,
|
| 991 |
+
"learning_rate": 7.03137853892648e-07,
|
| 992 |
+
"loss": 0.8790291786193848,
|
| 993 |
+
"step": 610,
|
| 994 |
+
"token_acc": 0.7570771711903374
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.4019607843137255,
|
| 998 |
+
"grad_norm": 5.367140293121338,
|
| 999 |
+
"learning_rate": 6.981869331400237e-07,
|
| 1000 |
+
"loss": 0.9010520935058594,
|
| 1001 |
+
"step": 615,
|
| 1002 |
+
"token_acc": 0.7464469607890513
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.40522875816993464,
|
| 1006 |
+
"grad_norm": 14.675331115722656,
|
| 1007 |
+
"learning_rate": 6.93212850213767e-07,
|
| 1008 |
+
"loss": 0.898799991607666,
|
| 1009 |
+
"step": 620,
|
| 1010 |
+
"token_acc": 0.746772997032641
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.4084967320261438,
|
| 1014 |
+
"grad_norm": 10.118048667907715,
|
| 1015 |
+
"learning_rate": 6.882161864366243e-07,
|
| 1016 |
+
"loss": 0.9324123382568359,
|
| 1017 |
+
"step": 625,
|
| 1018 |
+
"token_acc": 0.7403827921969283
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.4117647058823529,
|
| 1022 |
+
"grad_norm": 16.30902671813965,
|
| 1023 |
+
"learning_rate": 6.831975257703747e-07,
|
| 1024 |
+
"loss": 0.8974993705749512,
|
| 1025 |
+
"step": 630,
|
| 1026 |
+
"token_acc": 0.7507663826195856
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.4150326797385621,
|
| 1030 |
+
"grad_norm": 8.51706600189209,
|
| 1031 |
+
"learning_rate": 6.781574547475805e-07,
|
| 1032 |
+
"loss": 0.8791131973266602,
|
| 1033 |
+
"step": 635,
|
| 1034 |
+
"token_acc": 0.7548131131647997
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.41830065359477125,
|
| 1038 |
+
"grad_norm": 6.906656742095947,
|
| 1039 |
+
"learning_rate": 6.730965624030401e-07,
|
| 1040 |
+
"loss": 0.8914268493652344,
|
| 1041 |
+
"step": 640,
|
| 1042 |
+
"token_acc": 0.7546357825454085
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.4215686274509804,
|
| 1046 |
+
"grad_norm": 5.998027324676514,
|
| 1047 |
+
"learning_rate": 6.680154402049463e-07,
|
| 1048 |
+
"loss": 0.8878538131713867,
|
| 1049 |
+
"step": 645,
|
| 1050 |
+
"token_acc": 0.7512867444373388
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.42483660130718953,
|
| 1054 |
+
"grad_norm": 6.729011535644531,
|
| 1055 |
+
"learning_rate": 6.629146819857618e-07,
|
| 1056 |
+
"loss": 0.8908896446228027,
|
| 1057 |
+
"step": 650,
|
| 1058 |
+
"token_acc": 0.7489311869288223
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.42810457516339867,
|
| 1062 |
+
"grad_norm": 6.539777755737305,
|
| 1063 |
+
"learning_rate": 6.577948838728183e-07,
|
| 1064 |
+
"loss": 0.9151935577392578,
|
| 1065 |
+
"step": 655,
|
| 1066 |
+
"token_acc": 0.746645189766754
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.43137254901960786,
|
| 1070 |
+
"grad_norm": 6.659360885620117,
|
| 1071 |
+
"learning_rate": 6.52656644218645e-07,
|
| 1072 |
+
"loss": 0.9175146102905274,
|
| 1073 |
+
"step": 660,
|
| 1074 |
+
"token_acc": 0.747121529979997
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.434640522875817,
|
| 1078 |
+
"grad_norm": 7.235111713409424,
|
| 1079 |
+
"learning_rate": 6.475005635310417e-07,
|
| 1080 |
+
"loss": 0.8863768577575684,
|
| 1081 |
+
"step": 665,
|
| 1082 |
+
"token_acc": 0.7506970962720747
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.43790849673202614,
|
| 1086 |
+
"grad_norm": 12.579602241516113,
|
| 1087 |
+
"learning_rate": 6.423272444028947e-07,
|
| 1088 |
+
"loss": 0.8902733802795411,
|
| 1089 |
+
"step": 670,
|
| 1090 |
+
"token_acc": 0.7533475139590534
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.4411764705882353,
|
| 1094 |
+
"grad_norm": 8.955584526062012,
|
| 1095 |
+
"learning_rate": 6.371372914417535e-07,
|
| 1096 |
+
"loss": 0.8827089309692383,
|
| 1097 |
+
"step": 675,
|
| 1098 |
+
"token_acc": 0.7537726486156352
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.4444444444444444,
|
| 1102 |
+
"grad_norm": 8.001651763916016,
|
| 1103 |
+
"learning_rate": 6.319313111991684e-07,
|
| 1104 |
+
"loss": 0.9012702941894531,
|
| 1105 |
+
"step": 680,
|
| 1106 |
+
"token_acc": 0.7493865437104168
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.4477124183006536,
|
| 1110 |
+
"grad_norm": 7.84200382232666,
|
| 1111 |
+
"learning_rate": 6.267099120998041e-07,
|
| 1112 |
+
"loss": 0.8855411529541015,
|
| 1113 |
+
"step": 685,
|
| 1114 |
+
"token_acc": 0.7531292210715894
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.45098039215686275,
|
| 1118 |
+
"grad_norm": 4.571206569671631,
|
| 1119 |
+
"learning_rate": 6.214737043703322e-07,
|
| 1120 |
+
"loss": 0.8840375900268554,
|
| 1121 |
+
"step": 690,
|
| 1122 |
+
"token_acc": 0.7510286333906034
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.4542483660130719,
|
| 1126 |
+
"grad_norm": 8.034171104431152,
|
| 1127 |
+
"learning_rate": 6.162232999681138e-07,
|
| 1128 |
+
"loss": 0.8775747299194336,
|
| 1129 |
+
"step": 695,
|
| 1130 |
+
"token_acc": 0.7522305667886258
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.45751633986928103,
|
| 1134 |
+
"grad_norm": 4.609678745269775,
|
| 1135 |
+
"learning_rate": 6.109593125096798e-07,
|
| 1136 |
+
"loss": 0.8953985214233399,
|
| 1137 |
+
"step": 700,
|
| 1138 |
+
"token_acc": 0.747183557695607
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.46078431372549017,
|
| 1142 |
+
"grad_norm": 14.576176643371582,
|
| 1143 |
+
"learning_rate": 6.056823571990176e-07,
|
| 1144 |
+
"loss": 0.8983377456665039,
|
| 1145 |
+
"step": 705,
|
| 1146 |
+
"token_acc": 0.7492189082843707
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.46405228758169936,
|
| 1150 |
+
"grad_norm": 6.3813157081604,
|
| 1151 |
+
"learning_rate": 6.003930507556718e-07,
|
| 1152 |
+
"loss": 0.8842323303222657,
|
| 1153 |
+
"step": 710,
|
| 1154 |
+
"token_acc": 0.754341550077726
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.4673202614379085,
|
| 1158 |
+
"grad_norm": 9.677647590637207,
|
| 1159 |
+
"learning_rate": 5.95092011342668e-07,
|
| 1160 |
+
"loss": 0.8869538307189941,
|
| 1161 |
+
"step": 715,
|
| 1162 |
+
"token_acc": 0.7510954105563142
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.47058823529411764,
|
| 1166 |
+
"grad_norm": 8.170088768005371,
|
| 1167 |
+
"learning_rate": 5.89779858494268e-07,
|
| 1168 |
+
"loss": 0.8976833343505859,
|
| 1169 |
+
"step": 720,
|
| 1170 |
+
"token_acc": 0.7521914683252046
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.4738562091503268,
|
| 1174 |
+
"grad_norm": 5.440218925476074,
|
| 1175 |
+
"learning_rate": 5.844572130435648e-07,
|
| 1176 |
+
"loss": 0.8882529258728027,
|
| 1177 |
+
"step": 725,
|
| 1178 |
+
"token_acc": 0.751892419009854
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.477124183006536,
|
| 1182 |
+
"grad_norm": 6.152303695678711,
|
| 1183 |
+
"learning_rate": 5.79124697049925e-07,
|
| 1184 |
+
"loss": 0.8901869773864746,
|
| 1185 |
+
"step": 730,
|
| 1186 |
+
"token_acc": 0.7537441389451488
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.4803921568627451,
|
| 1190 |
+
"grad_norm": 4.193750858306885,
|
| 1191 |
+
"learning_rate": 5.737829337262887e-07,
|
| 1192 |
+
"loss": 0.8810691833496094,
|
| 1193 |
+
"step": 735,
|
| 1194 |
+
"token_acc": 0.7554882508679214
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.48366013071895425,
|
| 1198 |
+
"grad_norm": 8.233670234680176,
|
| 1199 |
+
"learning_rate": 5.684325473663348e-07,
|
| 1200 |
+
"loss": 0.8956683158874512,
|
| 1201 |
+
"step": 740,
|
| 1202 |
+
"token_acc": 0.7509427060639803
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.4869281045751634,
|
| 1206 |
+
"grad_norm": 5.511728763580322,
|
| 1207 |
+
"learning_rate": 5.630741632715197e-07,
|
| 1208 |
+
"loss": 0.8929777145385742,
|
| 1209 |
+
"step": 745,
|
| 1210 |
+
"token_acc": 0.7507163960281671
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.49019607843137253,
|
| 1214 |
+
"grad_norm": 5.376450061798096,
|
| 1215 |
+
"learning_rate": 5.577084076779975e-07,
|
| 1216 |
+
"loss": 0.8719209671020508,
|
| 1217 |
+
"step": 750,
|
| 1218 |
+
"token_acc": 0.7572041161743156
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.4934640522875817,
|
| 1222 |
+
"grad_norm": 9.586094856262207,
|
| 1223 |
+
"learning_rate": 5.523359076834315e-07,
|
| 1224 |
+
"loss": 0.8506996154785156,
|
| 1225 |
+
"step": 755,
|
| 1226 |
+
"token_acc": 0.7625819237522382
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.49673202614379086,
|
| 1230 |
+
"grad_norm": 7.716261386871338,
|
| 1231 |
+
"learning_rate": 5.469572911737059e-07,
|
| 1232 |
+
"loss": 0.8809006690979004,
|
| 1233 |
+
"step": 760,
|
| 1234 |
+
"token_acc": 0.7548848670827958
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.5,
|
| 1238 |
+
"grad_norm": 7.649358749389648,
|
| 1239 |
+
"learning_rate": 5.415731867495439e-07,
|
| 1240 |
+
"loss": 0.865907096862793,
|
| 1241 |
+
"step": 765,
|
| 1242 |
+
"token_acc": 0.7575605653847398
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.5032679738562091,
|
| 1246 |
+
"grad_norm": 3.605656385421753,
|
| 1247 |
+
"learning_rate": 5.361842236530431e-07,
|
| 1248 |
+
"loss": 0.8870879173278808,
|
| 1249 |
+
"step": 770,
|
| 1250 |
+
"token_acc": 0.7502894056847546
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.5065359477124183,
|
| 1254 |
+
"grad_norm": 4.340315341949463,
|
| 1255 |
+
"learning_rate": 5.307910316941358e-07,
|
| 1256 |
+
"loss": 0.8538712501525879,
|
| 1257 |
+
"step": 775,
|
| 1258 |
+
"token_acc": 0.7556668066276929
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.5098039215686274,
|
| 1262 |
+
"grad_norm": 6.465386390686035,
|
| 1263 |
+
"learning_rate": 5.253942411769828e-07,
|
| 1264 |
+
"loss": 0.891909408569336,
|
| 1265 |
+
"step": 780,
|
| 1266 |
+
"token_acc": 0.7521188181733514
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.5130718954248366,
|
| 1270 |
+
"grad_norm": 8.652735710144043,
|
| 1271 |
+
"learning_rate": 5.199944828263099e-07,
|
| 1272 |
+
"loss": 0.888407039642334,
|
| 1273 |
+
"step": 785,
|
| 1274 |
+
"token_acc": 0.7489556670693224
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.5163398692810458,
|
| 1278 |
+
"grad_norm": 12.463289260864258,
|
| 1279 |
+
"learning_rate": 5.145923877136939e-07,
|
| 1280 |
+
"loss": 0.9002778053283691,
|
| 1281 |
+
"step": 790,
|
| 1282 |
+
"token_acc": 0.7487689080269405
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 0.5196078431372549,
|
| 1286 |
+
"grad_norm": 5.695556163787842,
|
| 1287 |
+
"learning_rate": 5.091885871838107e-07,
|
| 1288 |
+
"loss": 0.8682380676269531,
|
| 1289 |
+
"step": 795,
|
| 1290 |
+
"token_acc": 0.7549715422066791
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.5228758169934641,
|
| 1294 |
+
"grad_norm": 6.701079845428467,
|
| 1295 |
+
"learning_rate": 5.037837127806485e-07,
|
| 1296 |
+
"loss": 0.8678909301757812,
|
| 1297 |
+
"step": 800,
|
| 1298 |
+
"token_acc": 0.758570783435713
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.5261437908496732,
|
| 1302 |
+
"grad_norm": 5.196365833282471,
|
| 1303 |
+
"learning_rate": 4.983783961736989e-07,
|
| 1304 |
+
"loss": 0.8812294006347656,
|
| 1305 |
+
"step": 805,
|
| 1306 |
+
"token_acc": 0.7531668338202591
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.5294117647058824,
|
| 1310 |
+
"grad_norm": 8.013653755187988,
|
| 1311 |
+
"learning_rate": 4.929732690841345e-07,
|
| 1312 |
+
"loss": 0.8850101470947266,
|
| 1313 |
+
"step": 810,
|
| 1314 |
+
"token_acc": 0.755188627665391
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.5326797385620915,
|
| 1318 |
+
"grad_norm": 4.5341901779174805,
|
| 1319 |
+
"learning_rate": 4.875689632109795e-07,
|
| 1320 |
+
"loss": 0.8962369918823242,
|
| 1321 |
+
"step": 815,
|
| 1322 |
+
"token_acc": 0.7502165510175569
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.5359477124183006,
|
| 1326 |
+
"grad_norm": 4.184832572937012,
|
| 1327 |
+
"learning_rate": 4.821661101572809e-07,
|
| 1328 |
+
"loss": 0.8962749481201172,
|
| 1329 |
+
"step": 820,
|
| 1330 |
+
"token_acc": 0.7499191897424846
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.5392156862745098,
|
| 1334 |
+
"grad_norm": 4.258326530456543,
|
| 1335 |
+
"learning_rate": 4.767653413562956e-07,
|
| 1336 |
+
"loss": 0.8798933029174805,
|
| 1337 |
+
"step": 825,
|
| 1338 |
+
"token_acc": 0.755239544859445
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 0.5424836601307189,
|
| 1342 |
+
"grad_norm": 7.058263778686523,
|
| 1343 |
+
"learning_rate": 4.713672879976923e-07,
|
| 1344 |
+
"loss": 0.9016656875610352,
|
| 1345 |
+
"step": 830,
|
| 1346 |
+
"token_acc": 0.7479241002599004
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.545751633986928,
|
| 1350 |
+
"grad_norm": 6.879621505737305,
|
| 1351 |
+
"learning_rate": 4.65972580953785e-07,
|
| 1352 |
+
"loss": 0.8691974639892578,
|
| 1353 |
+
"step": 835,
|
| 1354 |
+
"token_acc": 0.7561613558870243
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.5490196078431373,
|
| 1358 |
+
"grad_norm": 4.422628402709961,
|
| 1359 |
+
"learning_rate": 4.605818507058036e-07,
|
| 1360 |
+
"loss": 0.887212085723877,
|
| 1361 |
+
"step": 840,
|
| 1362 |
+
"token_acc": 0.753934473880907
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.5522875816993464,
|
| 1366 |
+
"grad_norm": 12.295745849609375,
|
| 1367 |
+
"learning_rate": 4.551957272702075e-07,
|
| 1368 |
+
"loss": 0.8901713371276856,
|
| 1369 |
+
"step": 845,
|
| 1370 |
+
"token_acc": 0.7503860523038606
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.5555555555555556,
|
| 1374 |
+
"grad_norm": 5.576113224029541,
|
| 1375 |
+
"learning_rate": 4.4981484012505717e-07,
|
| 1376 |
+
"loss": 0.8752371788024902,
|
| 1377 |
+
"step": 850,
|
| 1378 |
+
"token_acc": 0.7520030722502488
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.5588235294117647,
|
| 1382 |
+
"grad_norm": 6.602466106414795,
|
| 1383 |
+
"learning_rate": 4.444398181364455e-07,
|
| 1384 |
+
"loss": 0.8587551116943359,
|
| 1385 |
+
"step": 855,
|
| 1386 |
+
"token_acc": 0.7549308274914996
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 0.5620915032679739,
|
| 1390 |
+
"grad_norm": 5.416597366333008,
|
| 1391 |
+
"learning_rate": 4.390712894850032e-07,
|
| 1392 |
+
"loss": 0.9101902961730957,
|
| 1393 |
+
"step": 860,
|
| 1394 |
+
"token_acc": 0.7453985884994787
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.565359477124183,
|
| 1398 |
+
"grad_norm": 5.920382499694824,
|
| 1399 |
+
"learning_rate": 4.337098815924818e-07,
|
| 1400 |
+
"loss": 0.872370719909668,
|
| 1401 |
+
"step": 865,
|
| 1402 |
+
"token_acc": 0.7531041002008744
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.5686274509803921,
|
| 1406 |
+
"grad_norm": 5.837653160095215,
|
| 1407 |
+
"learning_rate": 4.2835622104842737e-07,
|
| 1408 |
+
"loss": 0.8716938018798828,
|
| 1409 |
+
"step": 870,
|
| 1410 |
+
"token_acc": 0.7536278692890452
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.5718954248366013,
|
| 1414 |
+
"grad_norm": 5.391213893890381,
|
| 1415 |
+
"learning_rate": 4.2301093353695157e-07,
|
| 1416 |
+
"loss": 0.8524575233459473,
|
| 1417 |
+
"step": 875,
|
| 1418 |
+
"token_acc": 0.7579852852919603
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.5751633986928104,
|
| 1422 |
+
"grad_norm": 7.946040153503418,
|
| 1423 |
+
"learning_rate": 4.1767464376360583e-07,
|
| 1424 |
+
"loss": 0.8718924522399902,
|
| 1425 |
+
"step": 880,
|
| 1426 |
+
"token_acc": 0.7552487792580739
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.5784313725490197,
|
| 1430 |
+
"grad_norm": 6.376768589019775,
|
| 1431 |
+
"learning_rate": 4.123479753823739e-07,
|
| 1432 |
+
"loss": 0.8928994178771973,
|
| 1433 |
+
"step": 885,
|
| 1434 |
+
"token_acc": 0.7500042190057772
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.5816993464052288,
|
| 1438 |
+
"grad_norm": 11.016767501831055,
|
| 1439 |
+
"learning_rate": 4.070315509227832e-07,
|
| 1440 |
+
"loss": 0.8705690383911133,
|
| 1441 |
+
"step": 890,
|
| 1442 |
+
"token_acc": 0.7580315369953214
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.5849673202614379,
|
| 1446 |
+
"grad_norm": 6.641153335571289,
|
| 1447 |
+
"learning_rate": 4.017259917171516e-07,
|
| 1448 |
+
"loss": 0.8787604331970215,
|
| 1449 |
+
"step": 895,
|
| 1450 |
+
"token_acc": 0.7524980564320666
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 0.5882352941176471,
|
| 1454 |
+
"grad_norm": 9.561841011047363,
|
| 1455 |
+
"learning_rate": 3.964319178279703e-07,
|
| 1456 |
+
"loss": 0.8630864143371582,
|
| 1457 |
+
"step": 900,
|
| 1458 |
+
"token_acc": 0.7562903765058616
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.5915032679738562,
|
| 1462 |
+
"grad_norm": 7.717654228210449,
|
| 1463 |
+
"learning_rate": 3.911499479754379e-07,
|
| 1464 |
+
"loss": 0.864194679260254,
|
| 1465 |
+
"step": 905,
|
| 1466 |
+
"token_acc": 0.7585523285306962
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.5947712418300654,
|
| 1470 |
+
"grad_norm": 6.744503498077393,
|
| 1471 |
+
"learning_rate": 3.8588069946515053e-07,
|
| 1472 |
+
"loss": 0.8427804946899414,
|
| 1473 |
+
"step": 910,
|
| 1474 |
+
"token_acc": 0.760405322915395
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.5980392156862745,
|
| 1478 |
+
"grad_norm": 7.937130451202393,
|
| 1479 |
+
"learning_rate": 3.80624788115956e-07,
|
| 1480 |
+
"loss": 0.8696054458618164,
|
| 1481 |
+
"step": 915,
|
| 1482 |
+
"token_acc": 0.7552524618137435
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 0.6013071895424836,
|
| 1486 |
+
"grad_norm": 6.8685383796691895,
|
| 1487 |
+
"learning_rate": 3.753828281879845e-07,
|
| 1488 |
+
"loss": 0.881092643737793,
|
| 1489 |
+
"step": 920,
|
| 1490 |
+
"token_acc": 0.7541656208862413
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.6045751633986928,
|
| 1494 |
+
"grad_norm": 9.054306030273438,
|
| 1495 |
+
"learning_rate": 3.701554323108582e-07,
|
| 1496 |
+
"loss": 0.8444313049316406,
|
| 1497 |
+
"step": 925,
|
| 1498 |
+
"token_acc": 0.7635365756857587
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.6078431372549019,
|
| 1502 |
+
"grad_norm": 6.022561550140381,
|
| 1503 |
+
"learning_rate": 3.649432114120943e-07,
|
| 1504 |
+
"loss": 0.8867866516113281,
|
| 1505 |
+
"step": 930,
|
| 1506 |
+
"token_acc": 0.7535050039101903
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.6111111111111112,
|
| 1510 |
+
"grad_norm": 6.068019390106201,
|
| 1511 |
+
"learning_rate": 3.597467746457049e-07,
|
| 1512 |
+
"loss": 0.8907625198364257,
|
| 1513 |
+
"step": 935,
|
| 1514 |
+
"token_acc": 0.7495557200036731
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.6143790849673203,
|
| 1518 |
+
"grad_norm": 12.781665802001953,
|
| 1519 |
+
"learning_rate": 3.5456672932100486e-07,
|
| 1520 |
+
"loss": 0.8726570129394531,
|
| 1521 |
+
"step": 940,
|
| 1522 |
+
"token_acc": 0.755860241139858
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.6176470588235294,
|
| 1526 |
+
"grad_norm": 6.0184526443481445,
|
| 1527 |
+
"learning_rate": 3.494036808316366e-07,
|
| 1528 |
+
"loss": 0.8669966697692871,
|
| 1529 |
+
"step": 945,
|
| 1530 |
+
"token_acc": 0.7587844653665098
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 0.6209150326797386,
|
| 1534 |
+
"grad_norm": 7.143519878387451,
|
| 1535 |
+
"learning_rate": 3.4425823258481577e-07,
|
| 1536 |
+
"loss": 0.8384815216064453,
|
| 1537 |
+
"step": 950,
|
| 1538 |
+
"token_acc": 0.7623802515758198
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.6241830065359477,
|
| 1542 |
+
"grad_norm": 4.520479202270508,
|
| 1543 |
+
"learning_rate": 3.3913098593081257e-07,
|
| 1544 |
+
"loss": 0.8636306762695313,
|
| 1545 |
+
"step": 955,
|
| 1546 |
+
"token_acc": 0.7577649122145322
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 0.6274509803921569,
|
| 1550 |
+
"grad_norm": 10.978309631347656,
|
| 1551 |
+
"learning_rate": 3.3402254009266993e-07,
|
| 1552 |
+
"loss": 0.8907316207885743,
|
| 1553 |
+
"step": 960,
|
| 1554 |
+
"token_acc": 0.7508105378060901
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.630718954248366,
|
| 1558 |
+
"grad_norm": 17.958463668823242,
|
| 1559 |
+
"learning_rate": 3.289334920961743e-07,
|
| 1560 |
+
"loss": 0.8657588005065918,
|
| 1561 |
+
"step": 965,
|
| 1562 |
+
"token_acc": 0.7571940218123064
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.6339869281045751,
|
| 1566 |
+
"grad_norm": 10.117110252380371,
|
| 1567 |
+
"learning_rate": 3.238644367000787e-07,
|
| 1568 |
+
"loss": 0.8703916549682618,
|
| 1569 |
+
"step": 970,
|
| 1570 |
+
"token_acc": 0.7563307493540051
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.6372549019607843,
|
| 1574 |
+
"grad_norm": 12.344156265258789,
|
| 1575 |
+
"learning_rate": 3.1881596632659507e-07,
|
| 1576 |
+
"loss": 0.862150764465332,
|
| 1577 |
+
"step": 975,
|
| 1578 |
+
"token_acc": 0.7568722780388945
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.6405228758169934,
|
| 1582 |
+
"grad_norm": 10.103394508361816,
|
| 1583 |
+
"learning_rate": 3.1378867099215637e-07,
|
| 1584 |
+
"loss": 0.8719820022583008,
|
| 1585 |
+
"step": 980,
|
| 1586 |
+
"token_acc": 0.7566879120758466
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.6437908496732027,
|
| 1590 |
+
"grad_norm": 12.435319900512695,
|
| 1591 |
+
"learning_rate": 3.0878313823846147e-07,
|
| 1592 |
+
"loss": 0.8849006652832031,
|
| 1593 |
+
"step": 985,
|
| 1594 |
+
"token_acc": 0.751441171922078
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 0.6470588235294118,
|
| 1598 |
+
"grad_norm": 4.279510498046875,
|
| 1599 |
+
"learning_rate": 3.037999530638098e-07,
|
| 1600 |
+
"loss": 0.847292137145996,
|
| 1601 |
+
"step": 990,
|
| 1602 |
+
"token_acc": 0.7629621045312319
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 0.6503267973856209,
|
| 1606 |
+
"grad_norm": 5.993341445922852,
|
| 1607 |
+
"learning_rate": 2.988396978547308e-07,
|
| 1608 |
+
"loss": 0.8687959671020508,
|
| 1609 |
+
"step": 995,
|
| 1610 |
+
"token_acc": 0.7572986282096377
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.6535947712418301,
|
| 1614 |
+
"grad_norm": 6.901057243347168,
|
| 1615 |
+
"learning_rate": 2.9390295231792177e-07,
|
| 1616 |
+
"loss": 0.8603469848632812,
|
| 1617 |
+
"step": 1000,
|
| 1618 |
+
"token_acc": 0.7583413107940881
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 0.6568627450980392,
|
| 1622 |
+
"grad_norm": 7.8023223876953125,
|
| 1623 |
+
"learning_rate": 2.8899029341249647e-07,
|
| 1624 |
+
"loss": 0.8732683181762695,
|
| 1625 |
+
"step": 1005,
|
| 1626 |
+
"token_acc": 0.7525172527948254
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.6601307189542484,
|
| 1630 |
+
"grad_norm": 18.202165603637695,
|
| 1631 |
+
"learning_rate": 2.8410229528255603e-07,
|
| 1632 |
+
"loss": 0.8719052314758301,
|
| 1633 |
+
"step": 1010,
|
| 1634 |
+
"token_acc": 0.7542081112196293
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.6633986928104575,
|
| 1638 |
+
"grad_norm": 9.392253875732422,
|
| 1639 |
+
"learning_rate": 2.792395291900882e-07,
|
| 1640 |
+
"loss": 0.868570613861084,
|
| 1641 |
+
"step": 1015,
|
| 1642 |
+
"token_acc": 0.7561802397684994
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 0.6666666666666666,
|
| 1646 |
+
"grad_norm": 9.627971649169922,
|
| 1647 |
+
"learning_rate": 2.74402563448204e-07,
|
| 1648 |
+
"loss": 0.8408105850219727,
|
| 1649 |
+
"step": 1020,
|
| 1650 |
+
"token_acc": 0.7616618924520832
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 0.6699346405228758,
|
| 1654 |
+
"grad_norm": 8.638592720031738,
|
| 1655 |
+
"learning_rate": 2.6959196335471934e-07,
|
| 1656 |
+
"loss": 0.8683024406433105,
|
| 1657 |
+
"step": 1025,
|
| 1658 |
+
"token_acc": 0.7549661059947256
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.673202614379085,
|
| 1662 |
+
"grad_norm": 6.08807897567749,
|
| 1663 |
+
"learning_rate": 2.6480829112608725e-07,
|
| 1664 |
+
"loss": 0.880455493927002,
|
| 1665 |
+
"step": 1030,
|
| 1666 |
+
"token_acc": 0.7536131867040687
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.6764705882352942,
|
| 1670 |
+
"grad_norm": 13.55544376373291,
|
| 1671 |
+
"learning_rate": 2.6005210583169267e-07,
|
| 1672 |
+
"loss": 0.8712383270263672,
|
| 1673 |
+
"step": 1035,
|
| 1674 |
+
"token_acc": 0.7557811646725909
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 0.6797385620915033,
|
| 1678 |
+
"grad_norm": 5.275318622589111,
|
| 1679 |
+
"learning_rate": 2.5532396332851264e-07,
|
| 1680 |
+
"loss": 0.8636394500732422,
|
| 1681 |
+
"step": 1040,
|
| 1682 |
+
"token_acc": 0.7589678902922972
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.6830065359477124,
|
| 1686 |
+
"grad_norm": 93.20777893066406,
|
| 1687 |
+
"learning_rate": 2.5062441619615455e-07,
|
| 1688 |
+
"loss": 0.86343994140625,
|
| 1689 |
+
"step": 1045,
|
| 1690 |
+
"token_acc": 0.7548636811190711
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.6862745098039216,
|
| 1694 |
+
"grad_norm": 14.879707336425781,
|
| 1695 |
+
"learning_rate": 2.4595401367227454e-07,
|
| 1696 |
+
"loss": 0.8756172180175781,
|
| 1697 |
+
"step": 1050,
|
| 1698 |
+
"token_acc": 0.7560932198676233
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 0.6895424836601307,
|
| 1702 |
+
"grad_norm": 10.011735916137695,
|
| 1703 |
+
"learning_rate": 2.413133015883885e-07,
|
| 1704 |
+
"loss": 0.8724102020263672,
|
| 1705 |
+
"step": 1055,
|
| 1706 |
+
"token_acc": 0.7582246981942093
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 0.6928104575163399,
|
| 1710 |
+
"grad_norm": 6.412021160125732,
|
| 1711 |
+
"learning_rate": 2.367028223060813e-07,
|
| 1712 |
+
"loss": 0.8606518745422364,
|
| 1713 |
+
"step": 1060,
|
| 1714 |
+
"token_acc": 0.7540960193775421
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.696078431372549,
|
| 1718 |
+
"grad_norm": 6.765170097351074,
|
| 1719 |
+
"learning_rate": 2.3212311465361918e-07,
|
| 1720 |
+
"loss": 0.8533823966979981,
|
| 1721 |
+
"step": 1065,
|
| 1722 |
+
"token_acc": 0.7613560558979651
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.6993464052287581,
|
| 1726 |
+
"grad_norm": 5.552716255187988,
|
| 1727 |
+
"learning_rate": 2.2757471386297854e-07,
|
| 1728 |
+
"loss": 0.8646259307861328,
|
| 1729 |
+
"step": 1070,
|
| 1730 |
+
"token_acc": 0.7571566753414246
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 0.7026143790849673,
|
| 1734 |
+
"grad_norm": 7.162012577056885,
|
| 1735 |
+
"learning_rate": 2.2305815150729164e-07,
|
| 1736 |
+
"loss": 0.8759864807128906,
|
| 1737 |
+
"step": 1075,
|
| 1738 |
+
"token_acc": 0.7565973814958302
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.7058823529411765,
|
| 1742 |
+
"grad_norm": 11.198907852172852,
|
| 1743 |
+
"learning_rate": 2.185739554387223e-07,
|
| 1744 |
+
"loss": 0.8665878295898437,
|
| 1745 |
+
"step": 1080,
|
| 1746 |
+
"token_acc": 0.7559690525809144
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.7091503267973857,
|
| 1750 |
+
"grad_norm": 6.9092230796813965,
|
| 1751 |
+
"learning_rate": 2.1412264972677535e-07,
|
| 1752 |
+
"loss": 0.8813034057617187,
|
| 1753 |
+
"step": 1085,
|
| 1754 |
+
"token_acc": 0.7537947818212689
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.7124183006535948,
|
| 1758 |
+
"grad_norm": 5.031152248382568,
|
| 1759 |
+
"learning_rate": 2.0970475459704906e-07,
|
| 1760 |
+
"loss": 0.8597887039184571,
|
| 1761 |
+
"step": 1090,
|
| 1762 |
+
"token_acc": 0.7539719023646414
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 0.7156862745098039,
|
| 1766 |
+
"grad_norm": 16.611862182617188,
|
| 1767 |
+
"learning_rate": 2.053207863704352e-07,
|
| 1768 |
+
"loss": 0.8692708015441895,
|
| 1769 |
+
"step": 1095,
|
| 1770 |
+
"token_acc": 0.7516191124941299
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 0.7189542483660131,
|
| 1774 |
+
"grad_norm": 5.341334342956543,
|
| 1775 |
+
"learning_rate": 2.0097125740277694e-07,
|
| 1776 |
+
"loss": 0.8398311614990235,
|
| 1777 |
+
"step": 1100,
|
| 1778 |
+
"token_acc": 0.7621621000763811
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 0.7222222222222222,
|
| 1782 |
+
"grad_norm": 10.300467491149902,
|
| 1783 |
+
"learning_rate": 1.966566760249901e-07,
|
| 1784 |
+
"loss": 0.8506832122802734,
|
| 1785 |
+
"step": 1105,
|
| 1786 |
+
"token_acc": 0.7592774494297844
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.7254901960784313,
|
| 1790 |
+
"grad_norm": 10.09868049621582,
|
| 1791 |
+
"learning_rate": 1.9237754648365324e-07,
|
| 1792 |
+
"loss": 0.900604248046875,
|
| 1793 |
+
"step": 1110,
|
| 1794 |
+
"token_acc": 0.7462892051123411
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.7287581699346405,
|
| 1798 |
+
"grad_norm": 8.113758087158203,
|
| 1799 |
+
"learning_rate": 1.8813436888207769e-07,
|
| 1800 |
+
"loss": 0.8620754241943359,
|
| 1801 |
+
"step": 1115,
|
| 1802 |
+
"token_acc": 0.7577026200667952
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.7320261437908496,
|
| 1806 |
+
"grad_norm": 5.918531894683838,
|
| 1807 |
+
"learning_rate": 1.839276391218585e-07,
|
| 1808 |
+
"loss": 0.8488912582397461,
|
| 1809 |
+
"step": 1120,
|
| 1810 |
+
"token_acc": 0.7599006406066152
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 0.7352941176470589,
|
| 1814 |
+
"grad_norm": 4.2873406410217285,
|
| 1815 |
+
"learning_rate": 1.7975784884492023e-07,
|
| 1816 |
+
"loss": 0.8580251693725586,
|
| 1817 |
+
"step": 1125,
|
| 1818 |
+
"token_acc": 0.7576126793989127
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 0.738562091503268,
|
| 1822 |
+
"grad_norm": 10.180582046508789,
|
| 1823 |
+
"learning_rate": 1.7562548537605682e-07,
|
| 1824 |
+
"loss": 0.8625364303588867,
|
| 1825 |
+
"step": 1130,
|
| 1826 |
+
"token_acc": 0.7562667399217087
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 0.7418300653594772,
|
| 1830 |
+
"grad_norm": 7.027617454528809,
|
| 1831 |
+
"learning_rate": 1.7153103166597866e-07,
|
| 1832 |
+
"loss": 0.873720359802246,
|
| 1833 |
+
"step": 1135,
|
| 1834 |
+
"token_acc": 0.7520613146525421
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 0.7450980392156863,
|
| 1838 |
+
"grad_norm": 6.446381092071533,
|
| 1839 |
+
"learning_rate": 1.674749662348704e-07,
|
| 1840 |
+
"loss": 0.8539299011230469,
|
| 1841 |
+
"step": 1140,
|
| 1842 |
+
"token_acc": 0.757313314008084
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 0.7483660130718954,
|
| 1846 |
+
"grad_norm": 12.690937995910645,
|
| 1847 |
+
"learning_rate": 1.6345776311646475e-07,
|
| 1848 |
+
"loss": 0.8512314796447754,
|
| 1849 |
+
"step": 1145,
|
| 1850 |
+
"token_acc": 0.7543136392060588
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.7516339869281046,
|
| 1854 |
+
"grad_norm": 13.710820198059082,
|
| 1855 |
+
"learning_rate": 1.5947989180264376e-07,
|
| 1856 |
+
"loss": 0.850362491607666,
|
| 1857 |
+
"step": 1150,
|
| 1858 |
+
"token_acc": 0.7602147483240541
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.7549019607843137,
|
| 1862 |
+
"grad_norm": 18.35642433166504,
|
| 1863 |
+
"learning_rate": 1.5554181718856735e-07,
|
| 1864 |
+
"loss": 0.8482881546020508,
|
| 1865 |
+
"step": 1155,
|
| 1866 |
+
"token_acc": 0.7590690438888766
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 0.7581699346405228,
|
| 1870 |
+
"grad_norm": 5.593527317047119,
|
| 1871 |
+
"learning_rate": 1.5164399951834255e-07,
|
| 1872 |
+
"loss": 0.850483512878418,
|
| 1873 |
+
"step": 1160,
|
| 1874 |
+
"token_acc": 0.7623601692459282
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 0.761437908496732,
|
| 1878 |
+
"grad_norm": 6.853276252746582,
|
| 1879 |
+
"learning_rate": 1.477868943312332e-07,
|
| 1880 |
+
"loss": 0.8317161560058594,
|
| 1881 |
+
"step": 1165,
|
| 1882 |
+
"token_acc": 0.7641581520526362
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 0.7647058823529411,
|
| 1886 |
+
"grad_norm": 5.213442325592041,
|
| 1887 |
+
"learning_rate": 1.439709524084216e-07,
|
| 1888 |
+
"loss": 0.8588911056518554,
|
| 1889 |
+
"step": 1170,
|
| 1890 |
+
"token_acc": 0.7563062849434318
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 0.7679738562091504,
|
| 1894 |
+
"grad_norm": 6.626988410949707,
|
| 1895 |
+
"learning_rate": 1.401966197203259e-07,
|
| 1896 |
+
"loss": 0.887431526184082,
|
| 1897 |
+
"step": 1175,
|
| 1898 |
+
"token_acc": 0.7477346068156614
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.7712418300653595,
|
| 1902 |
+
"grad_norm": 34.325374603271484,
|
| 1903 |
+
"learning_rate": 1.364643373744786e-07,
|
| 1904 |
+
"loss": 0.8355258941650391,
|
| 1905 |
+
"step": 1180,
|
| 1906 |
+
"token_acc": 0.7623506782749544
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.7745098039215687,
|
| 1910 |
+
"grad_norm": 11.060457229614258,
|
| 1911 |
+
"learning_rate": 1.3277454156397455e-07,
|
| 1912 |
+
"loss": 0.8725744247436523,
|
| 1913 |
+
"step": 1185,
|
| 1914 |
+
"token_acc": 0.753054212946662
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.7777777777777778,
|
| 1918 |
+
"grad_norm": 9.093491554260254,
|
| 1919 |
+
"learning_rate": 1.291276635164929e-07,
|
| 1920 |
+
"loss": 0.8521162033081054,
|
| 1921 |
+
"step": 1190,
|
| 1922 |
+
"token_acc": 0.7594714449721991
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.7810457516339869,
|
| 1926 |
+
"grad_norm": 5.935420036315918,
|
| 1927 |
+
"learning_rate": 1.2552412944389974e-07,
|
| 1928 |
+
"loss": 0.8706039428710938,
|
| 1929 |
+
"step": 1195,
|
| 1930 |
+
"token_acc": 0.7542373352147417
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 0.7843137254901961,
|
| 1934 |
+
"grad_norm": 13.490633964538574,
|
| 1935 |
+
"learning_rate": 1.2196436049243581e-07,
|
| 1936 |
+
"loss": 0.8588811874389648,
|
| 1937 |
+
"step": 1200,
|
| 1938 |
+
"token_acc": 0.7572196773551085
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 0.7875816993464052,
|
| 1942 |
+
"grad_norm": 10.966169357299805,
|
| 1943 |
+
"learning_rate": 1.1844877269349729e-07,
|
| 1944 |
+
"loss": 0.8785253524780273,
|
| 1945 |
+
"step": 1205,
|
| 1946 |
+
"token_acc": 0.752854595621101
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 0.7908496732026143,
|
| 1950 |
+
"grad_norm": 11.2511625289917,
|
| 1951 |
+
"learning_rate": 1.1497777691501481e-07,
|
| 1952 |
+
"loss": 0.8818739891052246,
|
| 1953 |
+
"step": 1210,
|
| 1954 |
+
"token_acc": 0.7522409021438308
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.7941176470588235,
|
| 1958 |
+
"grad_norm": 4.565039157867432,
|
| 1959 |
+
"learning_rate": 1.115517788134338e-07,
|
| 1960 |
+
"loss": 0.8602027893066406,
|
| 1961 |
+
"step": 1215,
|
| 1962 |
+
"token_acc": 0.7582818530922519
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.7973856209150327,
|
| 1966 |
+
"grad_norm": 7.833784103393555,
|
| 1967 |
+
"learning_rate": 1.0817117878630677e-07,
|
| 1968 |
+
"loss": 0.8467609405517578,
|
| 1969 |
+
"step": 1220,
|
| 1970 |
+
"token_acc": 0.7593314191960624
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.8006535947712419,
|
| 1974 |
+
"grad_norm": 5.748198509216309,
|
| 1975 |
+
"learning_rate": 1.0483637192549727e-07,
|
| 1976 |
+
"loss": 0.8560993194580078,
|
| 1977 |
+
"step": 1225,
|
| 1978 |
+
"token_acc": 0.7622658846413165
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 0.803921568627451,
|
| 1982 |
+
"grad_norm": 8.58458137512207,
|
| 1983 |
+
"learning_rate": 1.0154774797100669e-07,
|
| 1984 |
+
"loss": 0.8701459884643554,
|
| 1985 |
+
"step": 1230,
|
| 1986 |
+
"token_acc": 0.7587804563764405
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 0.8071895424836601,
|
| 1990 |
+
"grad_norm": 6.152071952819824,
|
| 1991 |
+
"learning_rate": 9.830569126542415e-08,
|
| 1992 |
+
"loss": 0.8580265045166016,
|
| 1993 |
+
"step": 1235,
|
| 1994 |
+
"token_acc": 0.7594657877799232
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 0.8104575163398693,
|
| 1998 |
+
"grad_norm": 9.056794166564941,
|
| 1999 |
+
"learning_rate": 9.511058070900884e-08,
|
| 2000 |
+
"loss": 0.8577810287475586,
|
| 2001 |
+
"step": 1240,
|
| 2002 |
+
"token_acc": 0.7581700085360408
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 0.8137254901960784,
|
| 2006 |
+
"grad_norm": 5.065214157104492,
|
| 2007 |
+
"learning_rate": 9.196278971540788e-08,
|
| 2008 |
+
"loss": 0.8471344947814942,
|
| 2009 |
+
"step": 1245,
|
| 2010 |
+
"token_acc": 0.7609422192699306
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.8169934640522876,
|
| 2014 |
+
"grad_norm": 5.456727027893066,
|
| 2015 |
+
"learning_rate": 8.886268616801473e-08,
|
| 2016 |
+
"loss": 0.8427347183227539,
|
| 2017 |
+
"step": 1250,
|
| 2018 |
+
"token_acc": 0.7594633740459583
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.8202614379084967,
|
| 2022 |
+
"grad_norm": 6.386508941650391,
|
| 2023 |
+
"learning_rate": 8.58106323769755e-08,
|
| 2024 |
+
"loss": 0.8886966705322266,
|
| 2025 |
+
"step": 1255,
|
| 2026 |
+
"token_acc": 0.7516346449646223
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.8235294117647058,
|
| 2030 |
+
"grad_norm": 6.188743591308594,
|
| 2031 |
+
"learning_rate": 8.280698503684458e-08,
|
| 2032 |
+
"loss": 0.8710406303405762,
|
| 2033 |
+
"step": 1260,
|
| 2034 |
+
"token_acc": 0.7558621322896462
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 0.826797385620915,
|
| 2038 |
+
"grad_norm": 7.567935943603516,
|
| 2039 |
+
"learning_rate": 7.985209518489855e-08,
|
| 2040 |
+
"loss": 0.8466134071350098,
|
| 2041 |
+
"step": 1265,
|
| 2042 |
+
"token_acc": 0.7615091931748358
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 0.8300653594771242,
|
| 2046 |
+
"grad_norm": 5.818873882293701,
|
| 2047 |
+
"learning_rate": 7.694630816010955e-08,
|
| 2048 |
+
"loss": 0.8441858291625977,
|
| 2049 |
+
"step": 1270,
|
| 2050 |
+
"token_acc": 0.7613573204621911
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 0.8333333333333334,
|
| 2054 |
+
"grad_norm": 13.99504280090332,
|
| 2055 |
+
"learning_rate": 7.40899635627859e-08,
|
| 2056 |
+
"loss": 0.8651030540466309,
|
| 2057 |
+
"step": 1275,
|
| 2058 |
+
"token_acc": 0.7530825502191227
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 0.8366013071895425,
|
| 2062 |
+
"grad_norm": 5.689146518707275,
|
| 2063 |
+
"learning_rate": 7.128339521488303e-08,
|
| 2064 |
+
"loss": 0.8586328506469727,
|
| 2065 |
+
"step": 1280,
|
| 2066 |
+
"token_acc": 0.7586334462732756
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.8398692810457516,
|
| 2070 |
+
"grad_norm": 15.805248260498047,
|
| 2071 |
+
"learning_rate": 6.852693112098901e-08,
|
| 2072 |
+
"loss": 0.8295412063598633,
|
| 2073 |
+
"step": 1285,
|
| 2074 |
+
"token_acc": 0.7655464520494973
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.8431372549019608,
|
| 2078 |
+
"grad_norm": 8.934541702270508,
|
| 2079 |
+
"learning_rate": 6.582089342999092e-08,
|
| 2080 |
+
"loss": 0.8811175346374511,
|
| 2081 |
+
"step": 1290,
|
| 2082 |
+
"token_acc": 0.7527143183278207
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.8464052287581699,
|
| 2086 |
+
"grad_norm": 14.72507095336914,
|
| 2087 |
+
"learning_rate": 6.316559839742514e-08,
|
| 2088 |
+
"loss": 0.838381290435791,
|
| 2089 |
+
"step": 1295,
|
| 2090 |
+
"token_acc": 0.7645128251557523
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 0.8496732026143791,
|
| 2094 |
+
"grad_norm": 5.926730155944824,
|
| 2095 |
+
"learning_rate": 6.056135634851673e-08,
|
| 2096 |
+
"loss": 0.871578598022461,
|
| 2097 |
+
"step": 1300,
|
| 2098 |
+
"token_acc": 0.7555121840836126
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 0.8529411764705882,
|
| 2102 |
+
"grad_norm": 5.995481491088867,
|
| 2103 |
+
"learning_rate": 5.8008471641910916e-08,
|
| 2104 |
+
"loss": 0.8710478782653809,
|
| 2105 |
+
"step": 1305,
|
| 2106 |
+
"token_acc": 0.7532794740475871
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 0.8562091503267973,
|
| 2110 |
+
"grad_norm": 5.127398490905762,
|
| 2111 |
+
"learning_rate": 5.55072426341035e-08,
|
| 2112 |
+
"loss": 0.8740388870239257,
|
| 2113 |
+
"step": 1310,
|
| 2114 |
+
"token_acc": 0.7543315848036878
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 0.8594771241830066,
|
| 2118 |
+
"grad_norm": 5.126923084259033,
|
| 2119 |
+
"learning_rate": 5.3057961644571044e-08,
|
| 2120 |
+
"loss": 0.8427873611450195,
|
| 2121 |
+
"step": 1315,
|
| 2122 |
+
"token_acc": 0.7625971421408875
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 0.8627450980392157,
|
| 2126 |
+
"grad_norm": 6.314314365386963,
|
| 2127 |
+
"learning_rate": 5.066091492160768e-08,
|
| 2128 |
+
"loss": 0.8267030715942383,
|
| 2129 |
+
"step": 1320,
|
| 2130 |
+
"token_acc": 0.7635984588589223
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.8660130718954249,
|
| 2134 |
+
"grad_norm": 12.666987419128418,
|
| 2135 |
+
"learning_rate": 4.831638260887155e-08,
|
| 2136 |
+
"loss": 0.8426649093627929,
|
| 2137 |
+
"step": 1325,
|
| 2138 |
+
"token_acc": 0.7595191803565187
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.869281045751634,
|
| 2142 |
+
"grad_norm": 5.081419467926025,
|
| 2143 |
+
"learning_rate": 4.602463871264356e-08,
|
| 2144 |
+
"loss": 0.8698280334472657,
|
| 2145 |
+
"step": 1330,
|
| 2146 |
+
"token_acc": 0.7555854847994439
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 0.8725490196078431,
|
| 2150 |
+
"grad_norm": 8.229781150817871,
|
| 2151 |
+
"learning_rate": 4.3785951069804984e-08,
|
| 2152 |
+
"loss": 0.8581441879272461,
|
| 2153 |
+
"step": 1335,
|
| 2154 |
+
"token_acc": 0.7557744274133193
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 0.8758169934640523,
|
| 2158 |
+
"grad_norm": 7.342142105102539,
|
| 2159 |
+
"learning_rate": 4.160058131653449e-08,
|
| 2160 |
+
"loss": 0.8913490295410156,
|
| 2161 |
+
"step": 1340,
|
| 2162 |
+
"token_acc": 0.7517754021163445
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 0.8790849673202614,
|
| 2166 |
+
"grad_norm": 8.286077499389648,
|
| 2167 |
+
"learning_rate": 3.946878485773153e-08,
|
| 2168 |
+
"loss": 0.8548911094665528,
|
| 2169 |
+
"step": 1345,
|
| 2170 |
+
"token_acc": 0.7620560958504372
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 0.8823529411764706,
|
| 2174 |
+
"grad_norm": 6.084384918212891,
|
| 2175 |
+
"learning_rate": 3.739081083716622e-08,
|
| 2176 |
+
"loss": 0.8061566352844238,
|
| 2177 |
+
"step": 1350,
|
| 2178 |
+
"token_acc": 0.7711253337147216
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 0.8856209150326797,
|
| 2182 |
+
"grad_norm": 5.660301685333252,
|
| 2183 |
+
"learning_rate": 3.536690210836207e-08,
|
| 2184 |
+
"loss": 0.8830486297607422,
|
| 2185 |
+
"step": 1355,
|
| 2186 |
+
"token_acc": 0.7520467252396166
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.8888888888888888,
|
| 2190 |
+
"grad_norm": 7.621434211730957,
|
| 2191 |
+
"learning_rate": 3.339729520621426e-08,
|
| 2192 |
+
"loss": 0.862850284576416,
|
| 2193 |
+
"step": 1360,
|
| 2194 |
+
"token_acc": 0.7573062261753494
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.8921568627450981,
|
| 2198 |
+
"grad_norm": 6.972575664520264,
|
| 2199 |
+
"learning_rate": 3.148222031934461e-08,
|
| 2200 |
+
"loss": 0.8393045425415039,
|
| 2201 |
+
"step": 1365,
|
| 2202 |
+
"token_acc": 0.7625342935528121
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 0.8954248366013072,
|
| 2206 |
+
"grad_norm": 64.0177001953125,
|
| 2207 |
+
"learning_rate": 2.9621901263200467e-08,
|
| 2208 |
+
"loss": 0.8557392120361328,
|
| 2209 |
+
"step": 1370,
|
| 2210 |
+
"token_acc": 0.7588428397765794
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 0.8986928104575164,
|
| 2214 |
+
"grad_norm": 6.67932653427124,
|
| 2215 |
+
"learning_rate": 2.7816555453896383e-08,
|
| 2216 |
+
"loss": 0.8675075531005859,
|
| 2217 |
+
"step": 1375,
|
| 2218 |
+
"token_acc": 0.7558890629724306
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 0.9019607843137255,
|
| 2222 |
+
"grad_norm": 7.125704765319824,
|
| 2223 |
+
"learning_rate": 2.606639388280524e-08,
|
| 2224 |
+
"loss": 0.8539167404174804,
|
| 2225 |
+
"step": 1380,
|
| 2226 |
+
"token_acc": 0.7594271449218237
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 0.9052287581699346,
|
| 2230 |
+
"grad_norm": 6.156618595123291,
|
| 2231 |
+
"learning_rate": 2.437162109189933e-08,
|
| 2232 |
+
"loss": 0.8776717185974121,
|
| 2233 |
+
"step": 1385,
|
| 2234 |
+
"token_acc": 0.7533992583436341
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 0.9084967320261438,
|
| 2238 |
+
"grad_norm": 7.479340076446533,
|
| 2239 |
+
"learning_rate": 2.2732435149845685e-08,
|
| 2240 |
+
"loss": 0.8254794120788574,
|
| 2241 |
+
"step": 1390,
|
| 2242 |
+
"token_acc": 0.7661349219282839
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.9117647058823529,
|
| 2246 |
+
"grad_norm": 6.171672344207764,
|
| 2247 |
+
"learning_rate": 2.1149027628857395e-08,
|
| 2248 |
+
"loss": 0.8587844848632813,
|
| 2249 |
+
"step": 1395,
|
| 2250 |
+
"token_acc": 0.7600484247475947
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.9150326797385621,
|
| 2254 |
+
"grad_norm": 9.97986125946045,
|
| 2255 |
+
"learning_rate": 1.962158358230476e-08,
|
| 2256 |
+
"loss": 0.8485973358154297,
|
| 2257 |
+
"step": 1400,
|
| 2258 |
+
"token_acc": 0.7616578794918458
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 0.9183006535947712,
|
| 2262 |
+
"grad_norm": 6.307647228240967,
|
| 2263 |
+
"learning_rate": 1.8150281523088172e-08,
|
| 2264 |
+
"loss": 0.8581897735595703,
|
| 2265 |
+
"step": 1405,
|
| 2266 |
+
"token_acc": 0.7576772507398603
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 0.9215686274509803,
|
| 2270 |
+
"grad_norm": 12.043375968933105,
|
| 2271 |
+
"learning_rate": 1.6735293402774686e-08,
|
| 2272 |
+
"loss": 0.8523383140563965,
|
| 2273 |
+
"step": 1410,
|
| 2274 |
+
"token_acc": 0.7614154144449831
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 0.9248366013071896,
|
| 2278 |
+
"grad_norm": 7.317742347717285,
|
| 2279 |
+
"learning_rate": 1.5376784591502655e-08,
|
| 2280 |
+
"loss": 0.8557430267333984,
|
| 2281 |
+
"step": 1415,
|
| 2282 |
+
"token_acc": 0.7574991715949745
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 0.9281045751633987,
|
| 2286 |
+
"grad_norm": 6.130329608917236,
|
| 2287 |
+
"learning_rate": 1.4074913858654447e-08,
|
| 2288 |
+
"loss": 0.8476279258728028,
|
| 2289 |
+
"step": 1420,
|
| 2290 |
+
"token_acc": 0.7589302559587447
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 0.9313725490196079,
|
| 2294 |
+
"grad_norm": 9.104378700256348,
|
| 2295 |
+
"learning_rate": 1.2829833354301045e-08,
|
| 2296 |
+
"loss": 0.8584016799926758,
|
| 2297 |
+
"step": 1425,
|
| 2298 |
+
"token_acc": 0.7588700997392905
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.934640522875817,
|
| 2302 |
+
"grad_norm": 8.593672752380371,
|
| 2303 |
+
"learning_rate": 1.1641688591420507e-08,
|
| 2304 |
+
"loss": 0.8483757019042969,
|
| 2305 |
+
"step": 1430,
|
| 2306 |
+
"token_acc": 0.7574017140218701
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.9379084967320261,
|
| 2310 |
+
"grad_norm": 8.238764762878418,
|
| 2311 |
+
"learning_rate": 1.0510618428891394e-08,
|
| 2312 |
+
"loss": 0.8432640075683594,
|
| 2313 |
+
"step": 1435,
|
| 2314 |
+
"token_acc": 0.7622347501799228
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.9411764705882353,
|
| 2318 |
+
"grad_norm": 8.958550453186035,
|
| 2319 |
+
"learning_rate": 9.436755055264645e-09,
|
| 2320 |
+
"loss": 0.8572895050048828,
|
| 2321 |
+
"step": 1440,
|
| 2322 |
+
"token_acc": 0.7582088671113997
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 0.9444444444444444,
|
| 2326 |
+
"grad_norm": 17.699148178100586,
|
| 2327 |
+
"learning_rate": 8.420223973314322e-09,
|
| 2328 |
+
"loss": 0.8499961853027344,
|
| 2329 |
+
"step": 1445,
|
| 2330 |
+
"token_acc": 0.7612553118180774
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 0.9477124183006536,
|
| 2334 |
+
"grad_norm": 5.91080379486084,
|
| 2335 |
+
"learning_rate": 7.461143985370566e-09,
|
| 2336 |
+
"loss": 0.8674579620361328,
|
| 2337 |
+
"step": 1450,
|
| 2338 |
+
"token_acc": 0.7535058352710942
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 0.9509803921568627,
|
| 2342 |
+
"grad_norm": 8.176779747009277,
|
| 2343 |
+
"learning_rate": 6.559627179434479e-09,
|
| 2344 |
+
"loss": 0.859739112854004,
|
| 2345 |
+
"step": 1455,
|
| 2346 |
+
"token_acc": 0.7578491077839534
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 0.954248366013072,
|
| 2350 |
+
"grad_norm": 9.1267728805542,
|
| 2351 |
+
"learning_rate": 5.7157789160788835e-09,
|
| 2352 |
+
"loss": 0.8468132972717285,
|
| 2353 |
+
"step": 1460,
|
| 2354 |
+
"token_acc": 0.7593696990387591
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.9575163398692811,
|
| 2358 |
+
"grad_norm": 16.017799377441406,
|
| 2359 |
+
"learning_rate": 4.929697816134615e-09,
|
| 2360 |
+
"loss": 0.8684418678283692,
|
| 2361 |
+
"step": 1465,
|
| 2362 |
+
"token_acc": 0.7562206735994149
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.9607843137254902,
|
| 2366 |
+
"grad_norm": 28.990785598754883,
|
| 2367 |
+
"learning_rate": 4.2014757491644625e-09,
|
| 2368 |
+
"loss": 0.8431227684020997,
|
| 2369 |
+
"step": 1470,
|
| 2370 |
+
"token_acc": 0.7642535489787241
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 0.9640522875816994,
|
| 2374 |
+
"grad_norm": 6.331573009490967,
|
| 2375 |
+
"learning_rate": 3.5311978227268168e-09,
|
| 2376 |
+
"loss": 0.8435378074645996,
|
| 2377 |
+
"step": 1475,
|
| 2378 |
+
"token_acc": 0.7640296169563433
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 0.9673202614379085,
|
| 2382 |
+
"grad_norm": 4.91044282913208,
|
| 2383 |
+
"learning_rate": 2.9189423724286787e-09,
|
| 2384 |
+
"loss": 0.8525236129760743,
|
| 2385 |
+
"step": 1480,
|
| 2386 |
+
"token_acc": 0.7625303152789006
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 0.9705882352941176,
|
| 2390 |
+
"grad_norm": 10.381224632263184,
|
| 2391 |
+
"learning_rate": 2.364780952770762e-09,
|
| 2392 |
+
"loss": 0.8472789764404297,
|
| 2393 |
+
"step": 1485,
|
| 2394 |
+
"token_acc": 0.7592068306301962
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 0.9738562091503268,
|
| 2398 |
+
"grad_norm": 6.547264099121094,
|
| 2399 |
+
"learning_rate": 1.8687783287847923e-09,
|
| 2400 |
+
"loss": 0.8428874969482422,
|
| 2401 |
+
"step": 1490,
|
| 2402 |
+
"token_acc": 0.7630187741454488
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 0.9771241830065359,
|
| 2406 |
+
"grad_norm": 8.050070762634277,
|
| 2407 |
+
"learning_rate": 1.4309924684645093e-09,
|
| 2408 |
+
"loss": 0.842342758178711,
|
| 2409 |
+
"step": 1495,
|
| 2410 |
+
"token_acc": 0.7627188586924483
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.9803921568627451,
|
| 2414 |
+
"grad_norm": 8.127850532531738,
|
| 2415 |
+
"learning_rate": 1.0514745359909706e-09,
|
| 2416 |
+
"loss": 0.8480354309082031,
|
| 2417 |
+
"step": 1500,
|
| 2418 |
+
"token_acc": 0.7590301954173192
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.9836601307189542,
|
| 2422 |
+
"grad_norm": 8.412128448486328,
|
| 2423 |
+
"learning_rate": 7.302688857526718e-10,
|
| 2424 |
+
"loss": 0.8590973854064942,
|
| 2425 |
+
"step": 1505,
|
| 2426 |
+
"token_acc": 0.7566188445133772
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 0.9869281045751634,
|
| 2430 |
+
"grad_norm": 5.362924098968506,
|
| 2431 |
+
"learning_rate": 4.674130571621915e-10,
|
| 2432 |
+
"loss": 0.8728810310363769,
|
| 2433 |
+
"step": 1510,
|
| 2434 |
+
"token_acc": 0.7542876549499066
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 0.9901960784313726,
|
| 2438 |
+
"grad_norm": 8.187644958496094,
|
| 2439 |
+
"learning_rate": 2.629377702687563e-10,
|
| 2440 |
+
"loss": 0.8894187927246093,
|
| 2441 |
+
"step": 1515,
|
| 2442 |
+
"token_acc": 0.7508393262945263
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 0.9934640522875817,
|
| 2446 |
+
"grad_norm": 11.362393379211426,
|
| 2447 |
+
"learning_rate": 1.1686692216805738e-10,
|
| 2448 |
+
"loss": 0.835467529296875,
|
| 2449 |
+
"step": 1520,
|
| 2450 |
+
"token_acc": 0.7657808701483779
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 0.9967320261437909,
|
| 2454 |
+
"grad_norm": 7.286565780639648,
|
| 2455 |
+
"learning_rate": 2.921758420926235e-11,
|
| 2456 |
+
"loss": 0.8575159072875976,
|
| 2457 |
+
"step": 1525,
|
| 2458 |
+
"token_acc": 0.7611364236475896
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 1.0,
|
| 2462 |
+
"grad_norm": 6.377807140350342,
|
| 2463 |
+
"learning_rate": 0.0,
|
| 2464 |
+
"loss": 0.8194162368774414,
|
| 2465 |
+
"step": 1530,
|
| 2466 |
+
"token_acc": 0.767421420499728
|
| 2467 |
+
}
|
| 2468 |
+
],
|
| 2469 |
+
"logging_steps": 5,
|
| 2470 |
+
"max_steps": 1530,
|
| 2471 |
+
"num_input_tokens_seen": 0,
|
| 2472 |
+
"num_train_epochs": 1,
|
| 2473 |
+
"save_steps": 100,
|
| 2474 |
+
"stateful_callbacks": {
|
| 2475 |
+
"TrainerControl": {
|
| 2476 |
+
"args": {
|
| 2477 |
+
"should_epoch_stop": false,
|
| 2478 |
+
"should_evaluate": false,
|
| 2479 |
+
"should_log": false,
|
| 2480 |
+
"should_save": true,
|
| 2481 |
+
"should_training_stop": true
|
| 2482 |
+
},
|
| 2483 |
+
"attributes": {}
|
| 2484 |
+
}
|
| 2485 |
+
},
|
| 2486 |
+
"total_flos": 3.4420572398597177e+19,
|
| 2487 |
+
"train_batch_size": 1,
|
| 2488 |
+
"trial_name": null,
|
| 2489 |
+
"trial_params": null
|
| 2490 |
+
}
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1461acf90052a1a25454bda634e4331a1323cd1d1fec93cbaa0b4cd70bc1b11
|
| 3 |
+
size 8977
|
ckpts/S2/4b/siglip2_large/siglip2_large/v0-20261024-091108/checkpoint-1530/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)
|