Add m2_gpt_answer round 1 Solver weights
Browse files- .gitattributes +1 -0
- m2_gpt_answer/round_1/args.json +556 -0
- m2_gpt_answer/round_1/chat_template.jinja +154 -0
- m2_gpt_answer/round_1/config.json +117 -0
- m2_gpt_answer/round_1/generation_config.json +9 -0
- m2_gpt_answer/round_1/model-00001-of-00004.safetensors +3 -0
- m2_gpt_answer/round_1/model-00002-of-00004.safetensors +3 -0
- m2_gpt_answer/round_1/model-00003-of-00004.safetensors +3 -0
- m2_gpt_answer/round_1/model-00004-of-00004.safetensors +3 -0
- m2_gpt_answer/round_1/model.safetensors.index.json +768 -0
- m2_gpt_answer/round_1/preprocessor_config.json +21 -0
- m2_gpt_answer/round_1/processor_config.json +61 -0
- m2_gpt_answer/round_1/tokenizer.json +3 -0
- m2_gpt_answer/round_1/tokenizer_config.json +33 -0
- m2_gpt_answer/round_1/trainer_state.json +2454 -0
.gitattributes
CHANGED
|
@@ -48,3 +48,4 @@ c4_no_difficulty_filter/round_2/tokenizer.json filter=lfs diff=lfs merge=lfs -te
|
|
| 48 |
c4_no_difficulty_filter/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 49 |
c4_no_difficulty_filter/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 50 |
a4_fixed_images/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 48 |
c4_no_difficulty_filter/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 49 |
c4_no_difficulty_filter/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 50 |
a4_fixed_images/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
m2_gpt_answer/round_1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
m2_gpt_answer/round_1/args.json
ADDED
|
@@ -0,0 +1,556 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/data1/xiangding/cvis-ablate/runs/m2_gpt_answer/run_m2_gpt_answer_4g/iteration_001/solver",
|
| 3 |
+
"per_device_train_batch_size": 1,
|
| 4 |
+
"num_train_epochs": 3.0,
|
| 5 |
+
"max_steps": 160,
|
| 6 |
+
"learning_rate": 1e-06,
|
| 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": null,
|
| 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": 1,
|
| 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 |
+
"tensorboard"
|
| 48 |
+
],
|
| 49 |
+
"run_name": "/data1/xiangding/cvis-ablate/runs/m2_gpt_answer/run_m2_gpt_answer_4g/iteration_001/solver",
|
| 50 |
+
"project": "huggingface",
|
| 51 |
+
"trackio_space_id": null,
|
| 52 |
+
"trackio_bucket_id": null,
|
| 53 |
+
"trackio_static_space_id": null,
|
| 54 |
+
"eval_strategy": "no",
|
| 55 |
+
"eval_steps": 16.0,
|
| 56 |
+
"eval_delay": 0,
|
| 57 |
+
"per_device_eval_batch_size": 1,
|
| 58 |
+
"prediction_loss_only": false,
|
| 59 |
+
"eval_on_start": false,
|
| 60 |
+
"eval_do_concat_batches": true,
|
| 61 |
+
"eval_use_gather_object": false,
|
| 62 |
+
"eval_accumulation_steps": null,
|
| 63 |
+
"include_for_metrics": [],
|
| 64 |
+
"batch_eval_metrics": false,
|
| 65 |
+
"save_only_model": false,
|
| 66 |
+
"save_strategy": "steps",
|
| 67 |
+
"save_steps": 16.0,
|
| 68 |
+
"save_on_each_node": false,
|
| 69 |
+
"save_total_limit": 1,
|
| 70 |
+
"enable_jit_checkpoint": false,
|
| 71 |
+
"push_to_hub": false,
|
| 72 |
+
"hub_token": null,
|
| 73 |
+
"hub_private_repo": null,
|
| 74 |
+
"hub_model_id": null,
|
| 75 |
+
"hub_strategy": "every_save",
|
| 76 |
+
"hub_always_push": false,
|
| 77 |
+
"hub_revision": null,
|
| 78 |
+
"load_best_model_at_end": false,
|
| 79 |
+
"metric_for_best_model": "reward",
|
| 80 |
+
"greater_is_better": true,
|
| 81 |
+
"ignore_data_skip": false,
|
| 82 |
+
"restore_callback_states_from_checkpoint": false,
|
| 83 |
+
"full_determinism": false,
|
| 84 |
+
"seed": 42,
|
| 85 |
+
"data_seed": 42,
|
| 86 |
+
"use_cpu": false,
|
| 87 |
+
"accelerator_config": {
|
| 88 |
+
"dispatch_batches": false
|
| 89 |
+
},
|
| 90 |
+
"parallelism_config": null,
|
| 91 |
+
"dataloader_drop_last": false,
|
| 92 |
+
"dataloader_num_workers": null,
|
| 93 |
+
"dataloader_pin_memory": true,
|
| 94 |
+
"dataloader_persistent_workers": true,
|
| 95 |
+
"dataloader_prefetch_factor": null,
|
| 96 |
+
"dataloader_multiprocessing_context": null,
|
| 97 |
+
"dataloader_in_order": true,
|
| 98 |
+
"remove_unused_columns": false,
|
| 99 |
+
"label_names": null,
|
| 100 |
+
"train_sampling_strategy": "random",
|
| 101 |
+
"length_column_name": "length",
|
| 102 |
+
"ddp_find_unused_parameters": false,
|
| 103 |
+
"ddp_bucket_cap_mb": null,
|
| 104 |
+
"ddp_broadcast_buffers": null,
|
| 105 |
+
"ddp_static_graph": null,
|
| 106 |
+
"ddp_backend": null,
|
| 107 |
+
"ddp_timeout": 18000000,
|
| 108 |
+
"fsdp": [],
|
| 109 |
+
"fsdp_config": null,
|
| 110 |
+
"deepspeed": {
|
| 111 |
+
"fp16": {
|
| 112 |
+
"enabled": "auto",
|
| 113 |
+
"loss_scale": 0,
|
| 114 |
+
"loss_scale_window": 1000,
|
| 115 |
+
"initial_scale_power": 16,
|
| 116 |
+
"hysteresis": 2,
|
| 117 |
+
"min_loss_scale": 1
|
| 118 |
+
},
|
| 119 |
+
"bf16": {
|
| 120 |
+
"enabled": "auto"
|
| 121 |
+
},
|
| 122 |
+
"zero_optimization": {
|
| 123 |
+
"stage": 3,
|
| 124 |
+
"offload_optimizer": {
|
| 125 |
+
"device": "none",
|
| 126 |
+
"pin_memory": true
|
| 127 |
+
},
|
| 128 |
+
"offload_param": {
|
| 129 |
+
"device": "none",
|
| 130 |
+
"pin_memory": true
|
| 131 |
+
},
|
| 132 |
+
"overlap_comm": false,
|
| 133 |
+
"contiguous_gradients": true,
|
| 134 |
+
"sub_group_size": 1000000000.0,
|
| 135 |
+
"reduce_bucket_size": "auto",
|
| 136 |
+
"zero_quantized_weights": false,
|
| 137 |
+
"zero_quantized_gradients": false,
|
| 138 |
+
"stage3_prefetch_bucket_size": "auto",
|
| 139 |
+
"stage3_param_persistence_threshold": "auto",
|
| 140 |
+
"stage3_max_live_parameters": 1000000000.0,
|
| 141 |
+
"stage3_max_reuse_distance": 1000000000.0,
|
| 142 |
+
"stage3_gather_16bit_weights_on_model_save": true
|
| 143 |
+
},
|
| 144 |
+
"gradient_accumulation_steps": "auto",
|
| 145 |
+
"gradient_clipping": "auto",
|
| 146 |
+
"steps_per_print": 2000,
|
| 147 |
+
"train_batch_size": "auto",
|
| 148 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 149 |
+
"wall_clock_breakdown": false
|
| 150 |
+
},
|
| 151 |
+
"debug": null,
|
| 152 |
+
"skip_memory_metrics": true,
|
| 153 |
+
"do_train": false,
|
| 154 |
+
"do_eval": false,
|
| 155 |
+
"do_predict": false,
|
| 156 |
+
"resume_from_checkpoint": null,
|
| 157 |
+
"local_rank": 0,
|
| 158 |
+
"sortish_sampler": false,
|
| 159 |
+
"predict_with_generate": false,
|
| 160 |
+
"generation_max_length": null,
|
| 161 |
+
"generation_num_beams": null,
|
| 162 |
+
"generation_config": null,
|
| 163 |
+
"tuner_backend": "peft",
|
| 164 |
+
"vit_gradient_checkpointing": true,
|
| 165 |
+
"router_aux_loss_coef": 0.0,
|
| 166 |
+
"enable_dft_loss": false,
|
| 167 |
+
"enable_channel_loss": false,
|
| 168 |
+
"safe_serialization": true,
|
| 169 |
+
"max_shard_size": "5GB",
|
| 170 |
+
"check_model": true,
|
| 171 |
+
"acc_strategy": "token",
|
| 172 |
+
"train_dataloader_shuffle": true,
|
| 173 |
+
"group_by_length": false,
|
| 174 |
+
"max_epochs": null,
|
| 175 |
+
"aligner_lr": null,
|
| 176 |
+
"vit_lr": null,
|
| 177 |
+
"use_logits_to_keep": null,
|
| 178 |
+
"ds3_gather_for_generation": true,
|
| 179 |
+
"resume_only_model": false,
|
| 180 |
+
"optimizer": null,
|
| 181 |
+
"loss_type": "grpo",
|
| 182 |
+
"mrl_dims": null,
|
| 183 |
+
"eval_metric": null,
|
| 184 |
+
"callbacks": [
|
| 185 |
+
"cvis_step_timing"
|
| 186 |
+
],
|
| 187 |
+
"early_stop_interval": null,
|
| 188 |
+
"eval_use_evalscope": false,
|
| 189 |
+
"eval_dataset": [],
|
| 190 |
+
"eval_dataset_args": null,
|
| 191 |
+
"eval_limit": null,
|
| 192 |
+
"eval_generation_config": null,
|
| 193 |
+
"extra_eval_args": null,
|
| 194 |
+
"tuner_type": "full",
|
| 195 |
+
"use_galore": false,
|
| 196 |
+
"galore_target_modules": null,
|
| 197 |
+
"galore_rank": 128,
|
| 198 |
+
"galore_update_proj_gap": 50,
|
| 199 |
+
"galore_scale": 1.0,
|
| 200 |
+
"galore_proj_type": "std",
|
| 201 |
+
"galore_optim_per_parameter": false,
|
| 202 |
+
"galore_with_embedding": false,
|
| 203 |
+
"galore_quantization": false,
|
| 204 |
+
"galore_proj_quant": false,
|
| 205 |
+
"galore_proj_bits": 4,
|
| 206 |
+
"galore_proj_group_size": 256,
|
| 207 |
+
"galore_cos_threshold": 0.4,
|
| 208 |
+
"galore_gamma_proj": 2,
|
| 209 |
+
"galore_queue_size": 5,
|
| 210 |
+
"lisa_activated_layers": 0,
|
| 211 |
+
"lisa_step_interval": 20,
|
| 212 |
+
"use_flash_ckpt": false,
|
| 213 |
+
"logging_dir": "/data1/xiangding/cvis-ablate/runs/m2_gpt_answer/run_m2_gpt_answer_4g/iteration_001/solver/runs",
|
| 214 |
+
"warmup_ratio": 0.03,
|
| 215 |
+
"use_ray": false,
|
| 216 |
+
"ray_exp_name": null,
|
| 217 |
+
"device_groups": null,
|
| 218 |
+
"model": "/data1/xiangding/cvis-ablate/models/Qwen3.5-9B",
|
| 219 |
+
"model_type": "qwen3_5",
|
| 220 |
+
"model_revision": null,
|
| 221 |
+
"task_type": "causal_lm",
|
| 222 |
+
"torch_dtype": "bfloat16",
|
| 223 |
+
"attn_impl": null,
|
| 224 |
+
"experts_impl": null,
|
| 225 |
+
"new_special_tokens": [],
|
| 226 |
+
"num_labels": null,
|
| 227 |
+
"problem_type": null,
|
| 228 |
+
"rope_scaling": null,
|
| 229 |
+
"device_map": null,
|
| 230 |
+
"max_memory": {},
|
| 231 |
+
"max_model_len": null,
|
| 232 |
+
"local_repo_path": null,
|
| 233 |
+
"init_strategy": null,
|
| 234 |
+
"template": "qwen3_5",
|
| 235 |
+
"system": "Base your inference and reasoning strictly on the provided image. Provide the final answer in <answer> and </answer>.",
|
| 236 |
+
"max_length": 2048,
|
| 237 |
+
"truncation_strategy": "left",
|
| 238 |
+
"max_pixels": null,
|
| 239 |
+
"agent_template": null,
|
| 240 |
+
"norm_bbox": null,
|
| 241 |
+
"use_chat_template": true,
|
| 242 |
+
"padding_side": "right",
|
| 243 |
+
"padding_free": false,
|
| 244 |
+
"loss_scale": "last_round+ignore_empty_think",
|
| 245 |
+
"sequence_parallel_size": 1,
|
| 246 |
+
"is_binary_loss_scale": null,
|
| 247 |
+
"template_backend": "swift",
|
| 248 |
+
"response_prefix": null,
|
| 249 |
+
"enable_thinking": false,
|
| 250 |
+
"preserve_thinking": null,
|
| 251 |
+
"add_non_thinking_prefix": true,
|
| 252 |
+
"disable_ignore_empty_think": false,
|
| 253 |
+
"dataset": [
|
| 254 |
+
"/data1/xiangding/cvis-ablate/runs/m2_gpt_answer/run_m2_gpt_answer_4g/iteration_001/solver/train.jsonl"
|
| 255 |
+
],
|
| 256 |
+
"val_dataset": [],
|
| 257 |
+
"cached_dataset": [],
|
| 258 |
+
"cached_val_dataset": [],
|
| 259 |
+
"split_dataset_ratio": 0.0,
|
| 260 |
+
"dataset_num_proc": 1,
|
| 261 |
+
"load_from_cache_file": false,
|
| 262 |
+
"dataset_shuffle": true,
|
| 263 |
+
"val_dataset_shuffle": false,
|
| 264 |
+
"streaming": false,
|
| 265 |
+
"interleave_prob": null,
|
| 266 |
+
"stopping_strategy": "first_exhausted",
|
| 267 |
+
"shuffle_buffer_size": 1000,
|
| 268 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 269 |
+
"columns": {},
|
| 270 |
+
"strict": false,
|
| 271 |
+
"disable_auto_column_mapping": false,
|
| 272 |
+
"model_name": null,
|
| 273 |
+
"model_author": null,
|
| 274 |
+
"custom_dataset_info": [],
|
| 275 |
+
"decision_drop_instructions": 0.0,
|
| 276 |
+
"decision_subsample_options": 0,
|
| 277 |
+
"decision_state_as_text": 0.0,
|
| 278 |
+
"decision_shuffle_fields": false,
|
| 279 |
+
"quant_method": null,
|
| 280 |
+
"quant_bits": null,
|
| 281 |
+
"hqq_axis": null,
|
| 282 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 283 |
+
"bnb_4bit_quant_type": "nf4",
|
| 284 |
+
"bnb_4bit_use_double_quant": true,
|
| 285 |
+
"bnb_4bit_quant_storage": null,
|
| 286 |
+
"max_new_tokens": 2048,
|
| 287 |
+
"temperature": 1.0,
|
| 288 |
+
"top_k": -1,
|
| 289 |
+
"top_p": 1.0,
|
| 290 |
+
"repetition_penalty": 1.0,
|
| 291 |
+
"num_beams": 1,
|
| 292 |
+
"stream": false,
|
| 293 |
+
"stop_words": [],
|
| 294 |
+
"logprobs": false,
|
| 295 |
+
"top_logprobs": null,
|
| 296 |
+
"structured_outputs_regex": null,
|
| 297 |
+
"adapters": [],
|
| 298 |
+
"external_plugins": [
|
| 299 |
+
"/data1/xiangding/cvis-ablate/repo/cvis/plugins/swift_reward.py"
|
| 300 |
+
],
|
| 301 |
+
"custom_register_path": [],
|
| 302 |
+
"model_kwargs": {},
|
| 303 |
+
"enable_npu_model_patch": true,
|
| 304 |
+
"load_args": false,
|
| 305 |
+
"load_data_args": false,
|
| 306 |
+
"packing": false,
|
| 307 |
+
"packing_length": null,
|
| 308 |
+
"packing_num_proc": 1,
|
| 309 |
+
"packing_strategy": "binpack",
|
| 310 |
+
"lazy_tokenize": true,
|
| 311 |
+
"use_hf": false,
|
| 312 |
+
"ignore_args_error": false,
|
| 313 |
+
"use_swift_lora": false,
|
| 314 |
+
"freeze_parameters": [],
|
| 315 |
+
"freeze_parameters_regex": null,
|
| 316 |
+
"freeze_parameters_ratio": 0.0,
|
| 317 |
+
"trainable_parameters": [
|
| 318 |
+
"model.visual.merger"
|
| 319 |
+
],
|
| 320 |
+
"trainable_parameters_regex": null,
|
| 321 |
+
"freeze_llm": false,
|
| 322 |
+
"freeze_vit": false,
|
| 323 |
+
"freeze_aligner": false,
|
| 324 |
+
"target_modules": [
|
| 325 |
+
"all-linear"
|
| 326 |
+
],
|
| 327 |
+
"target_regex": null,
|
| 328 |
+
"target_parameters": null,
|
| 329 |
+
"modules_to_save": [],
|
| 330 |
+
"lora_rank": 8,
|
| 331 |
+
"lora_alpha": 32.0,
|
| 332 |
+
"lora_dropout": 0.05,
|
| 333 |
+
"lora_bias": "none",
|
| 334 |
+
"lora_dtype": null,
|
| 335 |
+
"lorap_lr_ratio": null,
|
| 336 |
+
"use_rslora": false,
|
| 337 |
+
"use_dora": false,
|
| 338 |
+
"lora_ga_batch_size": 2,
|
| 339 |
+
"lora_ga_iters": 2,
|
| 340 |
+
"lora_ga_max_length": 1024,
|
| 341 |
+
"lora_ga_direction": "ArB2r",
|
| 342 |
+
"lora_ga_scale": "stable",
|
| 343 |
+
"lora_ga_stable_gamma": 16,
|
| 344 |
+
"init_weights": true,
|
| 345 |
+
"fourier_n_frequency": 2000,
|
| 346 |
+
"fourier_scaling": 300.0,
|
| 347 |
+
"boft_block_size": 4,
|
| 348 |
+
"boft_block_num": 0,
|
| 349 |
+
"boft_n_butterfly_factor": 1,
|
| 350 |
+
"boft_dropout": 0.0,
|
| 351 |
+
"vera_rank": 256,
|
| 352 |
+
"vera_projection_prng_key": 0,
|
| 353 |
+
"vera_dropout": 0.0,
|
| 354 |
+
"vera_d_initial": 0.1,
|
| 355 |
+
"adapter_act": "gelu",
|
| 356 |
+
"adapter_length": 128,
|
| 357 |
+
"adalora_target_r": 8,
|
| 358 |
+
"adalora_init_r": 12,
|
| 359 |
+
"adalora_tinit": 0,
|
| 360 |
+
"adalora_tfinal": 0,
|
| 361 |
+
"adalora_deltaT": 1,
|
| 362 |
+
"adalora_beta1": 0.85,
|
| 363 |
+
"adalora_beta2": 0.85,
|
| 364 |
+
"adalora_orth_reg_weight": 0.5,
|
| 365 |
+
"llamapro_num_new_blocks": 4,
|
| 366 |
+
"llamapro_num_groups": null,
|
| 367 |
+
"reft_layer_key": null,
|
| 368 |
+
"reft_layers": null,
|
| 369 |
+
"reft_rank": 4,
|
| 370 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 371 |
+
"reft_args": null,
|
| 372 |
+
"swanlab_token": null,
|
| 373 |
+
"swanlab_project": "ms-swift",
|
| 374 |
+
"swanlab_workspace": null,
|
| 375 |
+
"swanlab_exp_name": null,
|
| 376 |
+
"swanlab_notification_method": null,
|
| 377 |
+
"swanlab_webhook_url": null,
|
| 378 |
+
"swanlab_secret": null,
|
| 379 |
+
"swanlab_sender_email": null,
|
| 380 |
+
"swanlab_receiver_email": null,
|
| 381 |
+
"swanlab_smtp_server": null,
|
| 382 |
+
"swanlab_smtp_port": null,
|
| 383 |
+
"swanlab_email_language": "zh",
|
| 384 |
+
"swanlab_mode": "cloud",
|
| 385 |
+
"add_version": false,
|
| 386 |
+
"create_checkpoint_symlink": false,
|
| 387 |
+
"zero_hpz_partition_size": null,
|
| 388 |
+
"deepspeed_autotp_size": null,
|
| 389 |
+
"reward_model": null,
|
| 390 |
+
"reward_adapters": [],
|
| 391 |
+
"reward_model_type": null,
|
| 392 |
+
"reward_model_revision": null,
|
| 393 |
+
"reward_template": null,
|
| 394 |
+
"num_ppo_epochs": 4,
|
| 395 |
+
"whiten_rewards": false,
|
| 396 |
+
"kl_coef": 0.05,
|
| 397 |
+
"cliprange": 0.2,
|
| 398 |
+
"vf_coef": 0.1,
|
| 399 |
+
"cliprange_value": 0.2,
|
| 400 |
+
"gamma": 1.0,
|
| 401 |
+
"lam": 0.95,
|
| 402 |
+
"num_mini_batches": 1,
|
| 403 |
+
"local_rollout_forward_batch_size": 64,
|
| 404 |
+
"num_sample_generations": 10,
|
| 405 |
+
"response_length": 2048,
|
| 406 |
+
"missing_eos_penalty": null,
|
| 407 |
+
"vllm_gpu_memory_utilization": 0.2,
|
| 408 |
+
"vllm_tensor_parallel_size": 1,
|
| 409 |
+
"vllm_pipeline_parallel_size": 1,
|
| 410 |
+
"vllm_enable_expert_parallel": false,
|
| 411 |
+
"vllm_max_num_seqs": null,
|
| 412 |
+
"vllm_max_model_len": 4096,
|
| 413 |
+
"vllm_disable_custom_all_reduce": true,
|
| 414 |
+
"vllm_enforce_eager": false,
|
| 415 |
+
"vllm_limit_mm_per_prompt": null,
|
| 416 |
+
"vllm_max_lora_rank": 16,
|
| 417 |
+
"vllm_enable_prefix_caching": true,
|
| 418 |
+
"vllm_use_async_engine": null,
|
| 419 |
+
"vllm_quantization": null,
|
| 420 |
+
"vllm_reasoning_parser": null,
|
| 421 |
+
"vllm_disable_cascade_attn": false,
|
| 422 |
+
"vllm_mm_processor_cache_gb": null,
|
| 423 |
+
"vllm_speculative_config": null,
|
| 424 |
+
"vllm_engine_kwargs": {},
|
| 425 |
+
"vllm_data_parallel_size": 1,
|
| 426 |
+
"min_p": 0.0,
|
| 427 |
+
"use_vllm": true,
|
| 428 |
+
"vllm_mode": "colocate",
|
| 429 |
+
"vllm_enable_lora": false,
|
| 430 |
+
"vllm_server_base_url": null,
|
| 431 |
+
"vllm_server_host": null,
|
| 432 |
+
"vllm_server_port": [
|
| 433 |
+
8000
|
| 434 |
+
],
|
| 435 |
+
"vllm_server_timeout": 240.0,
|
| 436 |
+
"vllm_server_group_port": null,
|
| 437 |
+
"enable_flattened_weight_sync": true,
|
| 438 |
+
"async_generate": false,
|
| 439 |
+
"sleep_level": 0,
|
| 440 |
+
"move_model_batches": null,
|
| 441 |
+
"offload_optimizer": false,
|
| 442 |
+
"offload_model": false,
|
| 443 |
+
"wandb_log_unique_prompts": null,
|
| 444 |
+
"generation_batch_size": 256,
|
| 445 |
+
"steps_per_generation": null,
|
| 446 |
+
"teacher_tag_key": "dataset",
|
| 447 |
+
"epsilon": 0.2,
|
| 448 |
+
"epsilon_high": null,
|
| 449 |
+
"delta": null,
|
| 450 |
+
"cosine_min_len_value_wrong": -0.5,
|
| 451 |
+
"cosine_max_len_value_wrong": 0.0,
|
| 452 |
+
"cosine_min_len_value_correct": 1.0,
|
| 453 |
+
"cosine_max_len_value_correct": 0.5,
|
| 454 |
+
"cosine_max_len": null,
|
| 455 |
+
"repetition_n_grams": 3,
|
| 456 |
+
"repetition_max_penalty": -1.0,
|
| 457 |
+
"reward_model_plugin": null,
|
| 458 |
+
"chord_sft_dataset": [],
|
| 459 |
+
"chord_sft_per_device_train_batch_size": null,
|
| 460 |
+
"chord_enable_phi_function": false,
|
| 461 |
+
"chord_mu_warmup_steps": null,
|
| 462 |
+
"chord_mu_decay_steps": null,
|
| 463 |
+
"chord_mu_peak": null,
|
| 464 |
+
"chord_mu_valley": null,
|
| 465 |
+
"sync_ref_model": false,
|
| 466 |
+
"ref_model_sync_steps": 512,
|
| 467 |
+
"ref_model_mixup_alpha": 0.6,
|
| 468 |
+
"multi_turn_scheduler": null,
|
| 469 |
+
"max_turns": null,
|
| 470 |
+
"completion_length_limit_scope": "per_round",
|
| 471 |
+
"vllm_server_pass_dataset": false,
|
| 472 |
+
"use_gym_env": null,
|
| 473 |
+
"gym_env": null,
|
| 474 |
+
"dynamic_sample": false,
|
| 475 |
+
"max_resample_times": 3,
|
| 476 |
+
"overlong_filter": false,
|
| 477 |
+
"soft_max_length": null,
|
| 478 |
+
"soft_cache_length": null,
|
| 479 |
+
"scale_rewards": "group",
|
| 480 |
+
"log_entropy": false,
|
| 481 |
+
"top_entropy_quantile": 1.0,
|
| 482 |
+
"importance_sampling_level": "token",
|
| 483 |
+
"tau_pos": 1.0,
|
| 484 |
+
"tau_neg": 1.05,
|
| 485 |
+
"advantage_estimator": "grpo",
|
| 486 |
+
"kl_in_reward": false,
|
| 487 |
+
"teacher_kl_coef": 1.0,
|
| 488 |
+
"advantage_reweight": null,
|
| 489 |
+
"rlsd_lambda": 0.5,
|
| 490 |
+
"rlsd_reweight_clip_range": 0.2,
|
| 491 |
+
"rlsd_lambda_warmup_steps": 0,
|
| 492 |
+
"rlsd_lambda_decay_steps": 0,
|
| 493 |
+
"rlsd_negative_only": false,
|
| 494 |
+
"sdar_loss_coef": 0.0,
|
| 495 |
+
"sdar_gate_beta": 5.0,
|
| 496 |
+
"real_tau": 0.5,
|
| 497 |
+
"fipo_decay_rate": 32.0,
|
| 498 |
+
"fipo_clip_range": 0.2,
|
| 499 |
+
"fipo_clip_high_only": true,
|
| 500 |
+
"fipo_safety_threshold": 4.0,
|
| 501 |
+
"num_generations_eval": null,
|
| 502 |
+
"rollout_importance_sampling_mode": null,
|
| 503 |
+
"rollout_importance_sampling_threshold": 2.0,
|
| 504 |
+
"log_rollout_offpolicy_metrics": false,
|
| 505 |
+
"off_policy_sequence_mask_delta": null,
|
| 506 |
+
"num_generations": 8,
|
| 507 |
+
"reward_funcs": [
|
| 508 |
+
"cvis_majority_accuracy"
|
| 509 |
+
],
|
| 510 |
+
"reward_weights": null,
|
| 511 |
+
"log_completions": false,
|
| 512 |
+
"num_iterations": 1,
|
| 513 |
+
"teacher_model": null,
|
| 514 |
+
"teacher_adapters": [],
|
| 515 |
+
"teacher_model_type": null,
|
| 516 |
+
"teacher_model_revision": null,
|
| 517 |
+
"teacher_deepspeed": null,
|
| 518 |
+
"teacher_model_server": null,
|
| 519 |
+
"offload_teacher_model": false,
|
| 520 |
+
"rlhf_type": "grpo",
|
| 521 |
+
"ref_model": "/data1/xiangding/cvis-ablate/models/Qwen3.5-9B",
|
| 522 |
+
"ref_adapters": [],
|
| 523 |
+
"ref_model_type": "qwen3_5",
|
| 524 |
+
"ref_model_revision": null,
|
| 525 |
+
"beta": 0.01,
|
| 526 |
+
"label_smoothing": 0,
|
| 527 |
+
"max_completion_length": 2048,
|
| 528 |
+
"rpo_alpha": null,
|
| 529 |
+
"ld_alpha": null,
|
| 530 |
+
"discopop_tau": 0.05,
|
| 531 |
+
"loss_weights": null,
|
| 532 |
+
"cpo_alpha": 1.0,
|
| 533 |
+
"simpo_gamma": 1,
|
| 534 |
+
"desirable_weight": 1.0,
|
| 535 |
+
"undesirable_weight": 1.0,
|
| 536 |
+
"center_rewards_coefficient": null,
|
| 537 |
+
"sft_alpha": 0,
|
| 538 |
+
"lmbda": 0.5,
|
| 539 |
+
"seq_kd": false,
|
| 540 |
+
"gkd_logits_topk": null,
|
| 541 |
+
"swift_version": "4.6.0",
|
| 542 |
+
"ckpt_dir": null,
|
| 543 |
+
"rank": 0,
|
| 544 |
+
"global_world_size": 4,
|
| 545 |
+
"local_world_size": 4,
|
| 546 |
+
"model_suffix": "Qwen3.5-9B",
|
| 547 |
+
"model_info": "ModelInfo(model_type='qwen3_5', model_dir='/data1/xiangding/cvis-ablate/models/Qwen3.5-9B', 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)",
|
| 548 |
+
"model_meta": "ModelMeta(model_type='qwen3_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.5-0.8B', hf_model_id='Qwen/Qwen3.5-0.8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B', hf_model_id='Qwen/Qwen3.5-2B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B', hf_model_id='Qwen/Qwen3.5-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B', hf_model_id='Qwen/Qwen3.5-9B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B', hf_model_id='Qwen/Qwen3.5-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B-FP8', hf_model_id='Qwen/Qwen3.5-27B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-0.8B-Base', hf_model_id='Qwen/Qwen3.5-0.8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B-Base', hf_model_id='Qwen/Qwen3.5-2B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B-Base', hf_model_id='Qwen/Qwen3.5-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B-Base', hf_model_id='Qwen/Qwen3.5-9B-Base', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.6-27B', hf_model_id='Qwen/Qwen3.6-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.6-27B-FP8', hf_model_id='Qwen/Qwen3.6-27B-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.8-27B', hf_model_id='Qwen/Qwen3.8-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.8-27B-FP8', hf_model_id='Qwen/Qwen3.8-27B-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_8', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3_5Loader'>, template='qwen3_5', model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp='model.language_model.layers.{}.mlp', down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), mcore_model_type=None, architectures=['Qwen3_5ForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=5.2.0', 'qwen_vl_utils>=0.0.14', 'decord'], tags=[])",
|
| 549 |
+
"model_dir": "/data1/xiangding/cvis-ablate/models/Qwen3.5-9B",
|
| 550 |
+
"template_meta": "QwenTemplateMeta(template_type='qwen3_5', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3_5Template'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='qwen3_5', is_thinking=True, thinking_prefix='<think>\\n', non_thinking_prefix='<think>\\n\\n</think>\\n\\n', preserve_thinking=None, history_thinking_prefix='')",
|
| 551 |
+
"_val_dataset_exists": false,
|
| 552 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 553 |
+
"evaluation_strategy": "steps",
|
| 554 |
+
"training_args": "GRPOConfig(output_dir='/data1/xiangding/cvis-ablate/runs/m2_gpt_answer/run_m2_gpt_answer_4g/iteration_001/solver', per_device_train_batch_size=1, num_train_epochs=3.0, max_steps=160, learning_rate=1e-06, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0.03, 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=None, 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=1, 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=['tensorboard'], run_name='/data1/xiangding/cvis-ablate/runs/m2_gpt_answer/run_m2_gpt_answer_4g/iteration_001/solver', project='huggingface', trackio_space_id=None, trackio_bucket_id=None, trackio_static_space_id=None, eval_strategy=<IntervalStrategy.NO: 'no'>, eval_steps=16.0, 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=16, 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='reward', greater_is_better=True, 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=True, dataloader_num_workers=1, dataloader_pin_memory=True, dataloader_persistent_workers=True, dataloader_prefetch_factor=2, dataloader_multiprocessing_context=None, dataloader_in_order=True, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_static_graph=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=False, do_predict=False, resume_from_checkpoint=None, local_rank=0, model_init_kwargs=None, disable_dropout=False, cast_lm_head_to_fp32=False, num_generations=8, num_generations_eval=None, max_completion_length=2048, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=256, steps_per_generation=64, temperature=1.0, top_p=1.0, top_k=-1, min_p=0.0, generation_kwargs=None, chat_template_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_mode='colocate', vllm_model_impl='vllm', vllm_enable_sleep_mode=False, vllm_structured_outputs_regex=None, vllm_server_base_url=None, vllm_server_host=None, vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_group_port=51216, vllm_gpu_memory_utilization=0.2, vllm_max_model_length=None, vllm_tensor_parallel_size=1, beta=0.01, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, sapo_temperature_neg=1.05, sapo_temperature_pos=1.0, importance_sampling_level='token', reward_weights=None, multi_objective_aggregation='sum_then_normalize', scale_rewards='group', loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, max_tool_calling_iterations=None, vllm_importance_sampling_correction=True, vllm_importance_sampling_mode='sequence_mask', vllm_importance_sampling_cap=3.0, off_policy_mask_threshold=None, use_bias_correction_kl=False, log_completions=False, num_completions_to_print=None, log_unique_prompts=False, log_completions_hub_repo=None, tuner_backend='peft', 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, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, mrl_dims=None, eval_metric=None, callbacks=['cvis_step_timing'], 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, logging_dir='/data1/xiangding/cvis-ablate/runs/m2_gpt_answer/run_m2_gpt_answer_4g/iteration_001/solver/runs', warmup_ratio=0.0, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=None, vllm_max_model_len=4096, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt=None, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=None, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_mm_processor_cache_gb=None, vllm_speculative_config=None, vllm_engine_kwargs={}, vllm_data_parallel_size=1, stop_words=[], vllm_enable_lora=False, lora_rank=8, vllm_server_group_port=None, enable_flattened_weight_sync=True, async_generate=False, structured_outputs_regex=None, sleep_level=0, move_model_batches=None, offload_optimizer=False, offload_model=False, wandb_log_unique_prompts=None, teacher_tag_key='dataset', cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=2048, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, use_gym_env=None, gym_env=None, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, tau_pos=1.0, tau_neg=1.05, advantage_estimator='grpo', kl_in_reward=False, teacher_kl_coef=1.0, advantage_reweight=None, rlsd_lambda=0.5, rlsd_reweight_clip_range=0.2, rlsd_lambda_warmup_steps=0, rlsd_lambda_decay_steps=0, rlsd_negative_only=False, sdar_loss_coef=0.0, sdar_gate_beta=5.0, real_tau=0.5, fipo_decay_rate=32.0, fipo_clip_range=0.2, fipo_clip_high_only=True, fipo_safety_threshold=4.0, dataset_shuffle=True, rollout_importance_sampling_mode=None, rollout_importance_sampling_threshold=2.0, log_rollout_offpolicy_metrics=False, off_policy_sequence_mask_delta=None, offload_teacher_model=False)",
|
| 555 |
+
"_teacher_use_disable_adapter": false
|
| 556 |
+
}
|
m2_gpt_answer/round_1/chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
m2_gpt_answer/round_1/config.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"hidden_size": 4096,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_type": "qwen3_5",
|
| 10 |
+
"pad_token_id": 248044,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_output_gate": true,
|
| 15 |
+
"bos_token_id": null,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 248044,
|
| 18 |
+
"full_attention_interval": 4,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 4096,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 12288,
|
| 24 |
+
"layer_types": [
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention"
|
| 57 |
+
],
|
| 58 |
+
"linear_conv_kernel_dim": 4,
|
| 59 |
+
"linear_key_head_dim": 128,
|
| 60 |
+
"linear_num_key_heads": 16,
|
| 61 |
+
"linear_num_value_heads": 32,
|
| 62 |
+
"linear_value_head_dim": 128,
|
| 63 |
+
"mamba_ssm_dtype": "float32",
|
| 64 |
+
"max_position_embeddings": 262144,
|
| 65 |
+
"mlp_only_layers": [],
|
| 66 |
+
"model_type": "qwen3_5_text",
|
| 67 |
+
"mtp_num_hidden_layers": 1,
|
| 68 |
+
"mtp_use_dedicated_embeddings": false,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_hidden_layers": 32,
|
| 71 |
+
"num_key_value_heads": 4,
|
| 72 |
+
"pad_token_id": 248044,
|
| 73 |
+
"partial_rotary_factor": 0.25,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_parameters": {
|
| 76 |
+
"mrope_interleaved": true,
|
| 77 |
+
"mrope_section": [
|
| 78 |
+
11,
|
| 79 |
+
11,
|
| 80 |
+
10
|
| 81 |
+
],
|
| 82 |
+
"partial_rotary_factor": 0.25,
|
| 83 |
+
"rope_theta": 10000000,
|
| 84 |
+
"rope_type": "default"
|
| 85 |
+
},
|
| 86 |
+
"tie_word_embeddings": false,
|
| 87 |
+
"use_cache": false,
|
| 88 |
+
"vocab_size": 248320
|
| 89 |
+
},
|
| 90 |
+
"tie_word_embeddings": false,
|
| 91 |
+
"transformers_version": "5.17.0",
|
| 92 |
+
"use_cache": false,
|
| 93 |
+
"video_token_id": 248057,
|
| 94 |
+
"vision_config": {
|
| 95 |
+
"deepstack_visual_indexes": [],
|
| 96 |
+
"depth": 27,
|
| 97 |
+
"dtype": "bfloat16",
|
| 98 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
+
"hidden_size": 1152,
|
| 100 |
+
"in_channels": 3,
|
| 101 |
+
"initializer_range": 0.02,
|
| 102 |
+
"intermediate_size": 4304,
|
| 103 |
+
"model_type": "qwen3_5_vision",
|
| 104 |
+
"num_heads": 16,
|
| 105 |
+
"num_position_embeddings": 2304,
|
| 106 |
+
"out_hidden_size": 4096,
|
| 107 |
+
"patch_size": 16,
|
| 108 |
+
"rope_parameters": {
|
| 109 |
+
"rope_theta": 10000.0,
|
| 110 |
+
"rope_type": "axial"
|
| 111 |
+
},
|
| 112 |
+
"spatial_merge_size": 2,
|
| 113 |
+
"temporal_patch_size": 2
|
| 114 |
+
},
|
| 115 |
+
"vision_end_token_id": 248054,
|
| 116 |
+
"vision_start_token_id": 248053
|
| 117 |
+
}
|
m2_gpt_answer/round_1/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248044,
|
| 5 |
+
248046
|
| 6 |
+
],
|
| 7 |
+
"transformers_version": "5.17.0",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
m2_gpt_answer/round_1/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cfefe2a3519bc3f88b32b36e2b0abda744aa1fd5bbced816cfc10d4ed6c93c8
|
| 3 |
+
size 4942706120
|
m2_gpt_answer/round_1/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b11e187a0f11526fddea5a0754ff4fdb94abdd6ad6c59736d05756c65781c0ee
|
| 3 |
+
size 4987757928
|
m2_gpt_answer/round_1/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c26dc98ed89291edcbecd001789d2672cfd056b4b465d9e3f514bf7d7161681
|
| 3 |
+
size 4954810240
|
m2_gpt_answer/round_1/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4db1ec84c944d92febfceb5ff3206e716ad586dd986ae292f78db73b94e695fa
|
| 3 |
+
size 3934446832
|
m2_gpt_answer/round_1/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,768 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 1469680,
|
| 4 |
+
"total_size": 18819627488
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 411 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 412 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 413 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 414 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 415 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 416 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 417 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 418 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 419 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 425 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 426 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 427 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 428 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 430 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 431 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 432 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 433 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 730 |
+
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
| 731 |
+
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
| 732 |
+
"model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
|
| 733 |
+
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 734 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 735 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 736 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 737 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 738 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 739 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 740 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 741 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 742 |
+
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
| 743 |
+
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
| 744 |
+
"model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
|
| 745 |
+
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
| 746 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 747 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 748 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 749 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 750 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 751 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 752 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 753 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 754 |
+
"model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
|
| 755 |
+
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
| 756 |
+
"model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
|
| 757 |
+
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
| 758 |
+
"model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 759 |
+
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 760 |
+
"model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 761 |
+
"model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 762 |
+
"model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
|
| 763 |
+
"model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
|
| 764 |
+
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
| 765 |
+
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
| 766 |
+
"model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
|
| 767 |
+
}
|
| 768 |
+
}
|
m2_gpt_answer/round_1/preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
m2_gpt_answer/round_1/processor_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"max_video_tokens": 768,
|
| 48 |
+
"merge_size": 2,
|
| 49 |
+
"min_frames": 4,
|
| 50 |
+
"patch_size": 16,
|
| 51 |
+
"resample": 3,
|
| 52 |
+
"rescale_factor": 0.00392156862745098,
|
| 53 |
+
"return_metadata": false,
|
| 54 |
+
"size": {
|
| 55 |
+
"longest_edge": 25165824,
|
| 56 |
+
"shortest_edge": 4096
|
| 57 |
+
},
|
| 58 |
+
"temporal_patch_size": 2,
|
| 59 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 60 |
+
}
|
| 61 |
+
}
|
m2_gpt_answer/round_1/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
m2_gpt_answer/round_1/tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": true,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|
m2_gpt_answer/round_1/trainer_state.json
ADDED
|
@@ -0,0 +1,2454 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 16.0,
|
| 7 |
+
"global_step": 160,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"clip_ratio/high_max": 0.0,
|
| 14 |
+
"clip_ratio/high_mean": 0.0,
|
| 15 |
+
"clip_ratio/low_mean": 0.0,
|
| 16 |
+
"clip_ratio/low_min": 0.0,
|
| 17 |
+
"clip_ratio/region_mean": 0.0,
|
| 18 |
+
"completions/clipped_ratio": 0.62109375,
|
| 19 |
+
"completions/max_length": 2048.0,
|
| 20 |
+
"completions/mean_length": 1507.81640625,
|
| 21 |
+
"completions/min_length": 52.0,
|
| 22 |
+
"epoch": 0.00625,
|
| 23 |
+
"frac_reward_zero_std": 0.5625,
|
| 24 |
+
"grad_norm": 0.0,
|
| 25 |
+
"kl": 0.0,
|
| 26 |
+
"learning_rate": 2e-07,
|
| 27 |
+
"loss": 0.0,
|
| 28 |
+
"reward": 0.1875,
|
| 29 |
+
"reward_std": 0.17571194469928741,
|
| 30 |
+
"rewards/MajorityAccuracy/mean": 0.1875,
|
| 31 |
+
"rewards/MajorityAccuracy/std": 0.3910769522190094,
|
| 32 |
+
"step": 1,
|
| 33 |
+
"step_time": 178.7896606498398
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"clip_ratio/high_max": 0.0,
|
| 37 |
+
"clip_ratio/high_mean": 0.0,
|
| 38 |
+
"clip_ratio/low_mean": 0.0,
|
| 39 |
+
"clip_ratio/low_min": 0.0,
|
| 40 |
+
"clip_ratio/region_mean": 0.0,
|
| 41 |
+
"epoch": 0.0125,
|
| 42 |
+
"grad_norm": 2.185980886036328,
|
| 43 |
+
"kl": 0.0,
|
| 44 |
+
"learning_rate": 4e-07,
|
| 45 |
+
"loss": -7.450580596923828e-09,
|
| 46 |
+
"step": 2,
|
| 47 |
+
"step_time": 27.124415250029415
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"clip_ratio/high_max": 0.0013773217797279358,
|
| 51 |
+
"clip_ratio/high_mean": 0.0004434581132954918,
|
| 52 |
+
"clip_ratio/low_mean": 0.00010203529382124543,
|
| 53 |
+
"clip_ratio/low_min": 0.0,
|
| 54 |
+
"clip_ratio/region_mean": 0.0005454934071167372,
|
| 55 |
+
"epoch": 0.01875,
|
| 56 |
+
"grad_norm": 1.7953059774994742,
|
| 57 |
+
"kl": 0.00017462602136220085,
|
| 58 |
+
"learning_rate": 6e-07,
|
| 59 |
+
"loss": -5.694771243724972e-05,
|
| 60 |
+
"step": 3,
|
| 61 |
+
"step_time": 26.27218489954248
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"clip_ratio/high_max": 0.0,
|
| 65 |
+
"clip_ratio/high_mean": 0.0,
|
| 66 |
+
"clip_ratio/low_mean": 0.0,
|
| 67 |
+
"clip_ratio/low_min": 0.0,
|
| 68 |
+
"clip_ratio/region_mean": 0.0,
|
| 69 |
+
"epoch": 0.025,
|
| 70 |
+
"grad_norm": 2.4093481687935117,
|
| 71 |
+
"kl": 0.00011761307268898236,
|
| 72 |
+
"learning_rate": 8e-07,
|
| 73 |
+
"loss": -7.122889655875042e-05,
|
| 74 |
+
"step": 4,
|
| 75 |
+
"step_time": 26.96228581573814
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"clip_ratio/high_max": 0.0002840909000951797,
|
| 79 |
+
"clip_ratio/high_mean": 7.102272502379492e-05,
|
| 80 |
+
"clip_ratio/low_mean": 4.57763671875e-05,
|
| 81 |
+
"clip_ratio/low_min": 0.0,
|
| 82 |
+
"clip_ratio/region_mean": 0.00011679909221129492,
|
| 83 |
+
"epoch": 0.03125,
|
| 84 |
+
"grad_norm": 1.072997581635797,
|
| 85 |
+
"kl": 0.00018810161782312207,
|
| 86 |
+
"learning_rate": 1e-06,
|
| 87 |
+
"loss": 0.00010540421499172226,
|
| 88 |
+
"step": 5,
|
| 89 |
+
"step_time": 27.36039845412597
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"clip_ratio/high_max": 0.0037742469139629975,
|
| 93 |
+
"clip_ratio/high_mean": 0.0011034082745027263,
|
| 94 |
+
"clip_ratio/low_mean": 0.00034109875559806824,
|
| 95 |
+
"clip_ratio/low_min": 0.0,
|
| 96 |
+
"clip_ratio/region_mean": 0.001444507022824837,
|
| 97 |
+
"epoch": 0.0375,
|
| 98 |
+
"grad_norm": 3.2164878796619454,
|
| 99 |
+
"kl": 0.00025482484852545895,
|
| 100 |
+
"learning_rate": 9.998973021172564e-07,
|
| 101 |
+
"loss": 0.0001144066482083872,
|
| 102 |
+
"step": 6,
|
| 103 |
+
"step_time": 26.77787152864039
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"clip_ratio/high_max": 0.000564317568205297,
|
| 107 |
+
"clip_ratio/high_mean": 0.00014107939205132425,
|
| 108 |
+
"clip_ratio/low_mean": 0.0004140653254580684,
|
| 109 |
+
"clip_ratio/low_min": 0.0,
|
| 110 |
+
"clip_ratio/region_mean": 0.0005551447175093926,
|
| 111 |
+
"epoch": 0.04375,
|
| 112 |
+
"grad_norm": 1.8710246113105973,
|
| 113 |
+
"kl": 0.00020456586207728833,
|
| 114 |
+
"learning_rate": 9.99589250656446e-07,
|
| 115 |
+
"loss": -0.0002703708305489272,
|
| 116 |
+
"step": 7,
|
| 117 |
+
"step_time": 27.34861043980345
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"clip_ratio/high_max": 0.001103524824429769,
|
| 121 |
+
"clip_ratio/high_mean": 0.00027588120610744227,
|
| 122 |
+
"clip_ratio/low_mean": 0.000766170494898688,
|
| 123 |
+
"clip_ratio/low_min": 0.0,
|
| 124 |
+
"clip_ratio/region_mean": 0.001042051699187141,
|
| 125 |
+
"epoch": 0.05,
|
| 126 |
+
"grad_norm": 1.965507832966646,
|
| 127 |
+
"kl": 0.0003829687302641105,
|
| 128 |
+
"learning_rate": 9.990759721625005e-07,
|
| 129 |
+
"loss": 0.00010553540050750598,
|
| 130 |
+
"step": 8,
|
| 131 |
+
"step_time": 27.245121552608907
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"clip_ratio/high_max": 0.0,
|
| 135 |
+
"clip_ratio/high_mean": 0.0,
|
| 136 |
+
"clip_ratio/low_mean": 0.0,
|
| 137 |
+
"clip_ratio/low_min": 0.0,
|
| 138 |
+
"clip_ratio/region_mean": 0.0,
|
| 139 |
+
"completions/clipped_ratio": 0.546875,
|
| 140 |
+
"completions/max_length": 2048.0,
|
| 141 |
+
"completions/mean_length": 1441.81640625,
|
| 142 |
+
"completions/min_length": 71.0,
|
| 143 |
+
"epoch": 0.05625,
|
| 144 |
+
"frac_reward_zero_std": 0.4375,
|
| 145 |
+
"grad_norm": 0.9326660449364611,
|
| 146 |
+
"kl": 0.00046222814853535965,
|
| 147 |
+
"learning_rate": 9.983576774858775e-07,
|
| 148 |
+
"loss": 4.616433670889819e-06,
|
| 149 |
+
"reward": 0.25390625,
|
| 150 |
+
"reward_std": 0.26196834444999695,
|
| 151 |
+
"rewards/MajorityAccuracy/mean": 0.25390625,
|
| 152 |
+
"rewards/MajorityAccuracy/std": 0.4360972046852112,
|
| 153 |
+
"step": 9,
|
| 154 |
+
"step_time": 179.84880754724145
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"clip_ratio/high_max": 0.0017640654987189919,
|
| 158 |
+
"clip_ratio/high_mean": 0.00044101637467974797,
|
| 159 |
+
"clip_ratio/low_mean": 0.0007171630859375,
|
| 160 |
+
"clip_ratio/low_min": 0.0,
|
| 161 |
+
"clip_ratio/region_mean": 0.0011581794533412904,
|
| 162 |
+
"epoch": 0.0625,
|
| 163 |
+
"grad_norm": 4.634081992462312,
|
| 164 |
+
"kl": 0.0006026089540682733,
|
| 165 |
+
"learning_rate": 9.974346616959475e-07,
|
| 166 |
+
"loss": 0.00040873244870454073,
|
| 167 |
+
"step": 10,
|
| 168 |
+
"step_time": 27.282617416698486
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"clip_ratio/high_max": 0.0016100632201414555,
|
| 172 |
+
"clip_ratio/high_mean": 0.0004025158050353639,
|
| 173 |
+
"clip_ratio/low_mean": 0.0003662109375,
|
| 174 |
+
"clip_ratio/low_min": 0.0,
|
| 175 |
+
"clip_ratio/region_mean": 0.0007687267425353639,
|
| 176 |
+
"epoch": 0.06875,
|
| 177 |
+
"grad_norm": 2.193437884242025,
|
| 178 |
+
"kl": 0.0007231979470816441,
|
| 179 |
+
"learning_rate": 9.963073039597796e-07,
|
| 180 |
+
"loss": 0.00025112324510701,
|
| 181 |
+
"step": 11,
|
| 182 |
+
"step_time": 27.080120282713324
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"clip_ratio/high_max": 0.0,
|
| 186 |
+
"clip_ratio/high_mean": 0.0,
|
| 187 |
+
"clip_ratio/low_mean": 0.0,
|
| 188 |
+
"clip_ratio/low_min": 0.0,
|
| 189 |
+
"clip_ratio/region_mean": 0.0,
|
| 190 |
+
"epoch": 0.075,
|
| 191 |
+
"grad_norm": 0.00907201968956752,
|
| 192 |
+
"kl": 0.0006838288463768549,
|
| 193 |
+
"learning_rate": 9.949760673863846e-07,
|
| 194 |
+
"loss": 6.833456609456334e-06,
|
| 195 |
+
"step": 12,
|
| 196 |
+
"step_time": 27.208505463320762
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"clip_ratio/high_max": 0.013113857014104724,
|
| 200 |
+
"clip_ratio/high_mean": 0.004399530967930332,
|
| 201 |
+
"clip_ratio/low_mean": 0.002226034688646905,
|
| 202 |
+
"clip_ratio/low_min": 0.0,
|
| 203 |
+
"clip_ratio/region_mean": 0.006625565671129152,
|
| 204 |
+
"epoch": 0.08125,
|
| 205 |
+
"grad_norm": 3.8307610417674587,
|
| 206 |
+
"kl": 0.0027278243651380762,
|
| 207 |
+
"learning_rate": 9.934414988364722e-07,
|
| 208 |
+
"loss": 0.0009147766977548599,
|
| 209 |
+
"step": 13,
|
| 210 |
+
"step_time": 25.384500038810074
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"clip_ratio/high_max": 0.006285081326495856,
|
| 214 |
+
"clip_ratio/high_mean": 0.0023724668426439166,
|
| 215 |
+
"clip_ratio/low_mean": 0.0022768571507185698,
|
| 216 |
+
"clip_ratio/low_min": 0.0,
|
| 217 |
+
"clip_ratio/region_mean": 0.004649323993362486,
|
| 218 |
+
"epoch": 0.0875,
|
| 219 |
+
"grad_norm": 2.230043001950076,
|
| 220 |
+
"kl": 0.003729292715433985,
|
| 221 |
+
"learning_rate": 9.917042286978063e-07,
|
| 222 |
+
"loss": 0.0007281379075720906,
|
| 223 |
+
"step": 14,
|
| 224 |
+
"step_time": 24.801373071968555
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"clip_ratio/high_max": 0.005266240768833086,
|
| 228 |
+
"clip_ratio/high_mean": 0.0014566947284038179,
|
| 229 |
+
"clip_ratio/low_mean": 0.003259337187046185,
|
| 230 |
+
"clip_ratio/low_min": 0.0,
|
| 231 |
+
"clip_ratio/region_mean": 0.00471603189362213,
|
| 232 |
+
"epoch": 0.09375,
|
| 233 |
+
"grad_norm": 2.2191397683831724,
|
| 234 |
+
"kl": 0.013081108016194776,
|
| 235 |
+
"learning_rate": 9.897649706262473e-07,
|
| 236 |
+
"loss": 0.00014253941481001675,
|
| 237 |
+
"step": 15,
|
| 238 |
+
"step_time": 26.945116117596626
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"clip_ratio/high_max": 0.0024619381583761424,
|
| 242 |
+
"clip_ratio/high_mean": 0.0006154845395940356,
|
| 243 |
+
"clip_ratio/low_mean": 0.0013427734375,
|
| 244 |
+
"clip_ratio/low_min": 0.0,
|
| 245 |
+
"clip_ratio/region_mean": 0.0019582579407142475,
|
| 246 |
+
"epoch": 0.1,
|
| 247 |
+
"grad_norm": 1.3146293053810698,
|
| 248 |
+
"kl": 0.0009420434289495461,
|
| 249 |
+
"learning_rate": 9.87624521252587e-07,
|
| 250 |
+
"loss": -8.751641871640459e-06,
|
| 251 |
+
"step": 16,
|
| 252 |
+
"step_time": 27.2990025957115
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"clip_ratio/high_max": 0.0,
|
| 256 |
+
"clip_ratio/high_mean": 0.0,
|
| 257 |
+
"clip_ratio/low_mean": 0.0,
|
| 258 |
+
"clip_ratio/low_min": 0.0,
|
| 259 |
+
"clip_ratio/region_mean": 0.0,
|
| 260 |
+
"completions/clipped_ratio": 0.6171875,
|
| 261 |
+
"completions/max_length": 2048.0,
|
| 262 |
+
"completions/mean_length": 1604.55078125,
|
| 263 |
+
"completions/min_length": 10.0,
|
| 264 |
+
"epoch": 0.10625,
|
| 265 |
+
"frac_reward_zero_std": 0.59375,
|
| 266 |
+
"grad_norm": 0.008193893687286576,
|
| 267 |
+
"kl": 0.0013322316663106903,
|
| 268 |
+
"learning_rate": 9.852837598553008e-07,
|
| 269 |
+
"loss": 1.3324530300451443e-05,
|
| 270 |
+
"reward": 0.1640625,
|
| 271 |
+
"reward_std": 0.18345539271831512,
|
| 272 |
+
"rewards/MajorityAccuracy/mean": 0.1640625,
|
| 273 |
+
"rewards/MajorityAccuracy/std": 0.3710577189922333,
|
| 274 |
+
"step": 17,
|
| 275 |
+
"step_time": 174.18403197219595
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"clip_ratio/high_max": 0.002236227272078395,
|
| 279 |
+
"clip_ratio/high_mean": 0.000818858272396028,
|
| 280 |
+
"clip_ratio/low_mean": 0.0010629050302668475,
|
| 281 |
+
"clip_ratio/low_min": 0.0,
|
| 282 |
+
"clip_ratio/region_mean": 0.0018817633026628755,
|
| 283 |
+
"epoch": 0.1125,
|
| 284 |
+
"grad_norm": 3.319209612759599,
|
| 285 |
+
"kl": 0.0018375443905824795,
|
| 286 |
+
"learning_rate": 9.827436479993468e-07,
|
| 287 |
+
"loss": -8.853046165313572e-05,
|
| 288 |
+
"step": 18,
|
| 289 |
+
"step_time": 27.064020570367575
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"clip_ratio/high_max": 0.0,
|
| 293 |
+
"clip_ratio/high_mean": 0.0,
|
| 294 |
+
"clip_ratio/low_mean": 0.0,
|
| 295 |
+
"clip_ratio/low_min": 0.0,
|
| 296 |
+
"clip_ratio/region_mean": 0.0,
|
| 297 |
+
"epoch": 0.11875,
|
| 298 |
+
"grad_norm": 0.009566650453194795,
|
| 299 |
+
"kl": 0.0014385551767190918,
|
| 300 |
+
"learning_rate": 9.800052291411629e-07,
|
| 301 |
+
"loss": 1.438864001102047e-05,
|
| 302 |
+
"step": 19,
|
| 303 |
+
"step_time": 27.291975549422204
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"clip_ratio/high_max": 0.00021005415328545496,
|
| 307 |
+
"clip_ratio/high_mean": 5.251353832136374e-05,
|
| 308 |
+
"clip_ratio/low_mean": 7.62939453125e-05,
|
| 309 |
+
"clip_ratio/low_min": 0.0,
|
| 310 |
+
"clip_ratio/region_mean": 0.00012880748363386374,
|
| 311 |
+
"epoch": 0.125,
|
| 312 |
+
"grad_norm": 0.6131866421180472,
|
| 313 |
+
"kl": 0.0019188604346709326,
|
| 314 |
+
"learning_rate": 9.770696282000244e-07,
|
| 315 |
+
"loss": 0.00010337845742469653,
|
| 316 |
+
"step": 20,
|
| 317 |
+
"step_time": 27.20410337438807
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"clip_ratio/high_max": 0.0056635628279764205,
|
| 321 |
+
"clip_ratio/high_mean": 0.0019469585167826153,
|
| 322 |
+
"clip_ratio/low_mean": 0.005828180874232203,
|
| 323 |
+
"clip_ratio/low_min": 0.0,
|
| 324 |
+
"clip_ratio/region_mean": 0.0077751393255312,
|
| 325 |
+
"epoch": 0.13125,
|
| 326 |
+
"grad_norm": 2.797574821847709,
|
| 327 |
+
"kl": 0.03604976640781388,
|
| 328 |
+
"learning_rate": 9.739380510959364e-07,
|
| 329 |
+
"loss": 1.3680182746611536e-06,
|
| 330 |
+
"step": 21,
|
| 331 |
+
"step_time": 27.162267697509378
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"clip_ratio/high_max": 0.003690138109959662,
|
| 335 |
+
"clip_ratio/high_mean": 0.0009463531168876216,
|
| 336 |
+
"clip_ratio/low_mean": 0.0033756858319975436,
|
| 337 |
+
"clip_ratio/low_min": 0.0,
|
| 338 |
+
"clip_ratio/region_mean": 0.0043220389052294195,
|
| 339 |
+
"epoch": 0.1375,
|
| 340 |
+
"grad_norm": 1.6852128125334782,
|
| 341 |
+
"kl": 0.002837828593328595,
|
| 342 |
+
"learning_rate": 9.706117842542516e-07,
|
| 343 |
+
"loss": 0.0003748750314116478,
|
| 344 |
+
"step": 22,
|
| 345 |
+
"step_time": 27.413413154892623
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"clip_ratio/high_max": 0.003199125058017671,
|
| 349 |
+
"clip_ratio/high_mean": 0.0009406175231561065,
|
| 350 |
+
"clip_ratio/low_mean": 0.0011785277747549117,
|
| 351 |
+
"clip_ratio/low_min": 0.0,
|
| 352 |
+
"clip_ratio/region_mean": 0.002119145297911018,
|
| 353 |
+
"epoch": 0.14375,
|
| 354 |
+
"grad_norm": 1.2312470679981846,
|
| 355 |
+
"kl": 0.002455158333759755,
|
| 356 |
+
"learning_rate": 9.670921940772186e-07,
|
| 357 |
+
"loss": 0.0002553936210460961,
|
| 358 |
+
"step": 23,
|
| 359 |
+
"step_time": 27.29539625532925
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"clip_ratio/high_max": 0.0,
|
| 363 |
+
"clip_ratio/high_mean": 0.0,
|
| 364 |
+
"clip_ratio/low_mean": 0.0,
|
| 365 |
+
"clip_ratio/low_min": 0.0,
|
| 366 |
+
"clip_ratio/region_mean": 0.0,
|
| 367 |
+
"epoch": 0.15,
|
| 368 |
+
"grad_norm": 0.014567408944604654,
|
| 369 |
+
"kl": 0.0025341224973089993,
|
| 370 |
+
"learning_rate": 9.633807263826744e-07,
|
| 371 |
+
"loss": 2.5360219296999276e-05,
|
| 372 |
+
"step": 24,
|
| 373 |
+
"step_time": 27.30520359799266
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"clip_ratio/high_max": 0.0,
|
| 377 |
+
"clip_ratio/high_mean": 0.0,
|
| 378 |
+
"clip_ratio/low_mean": 0.0,
|
| 379 |
+
"clip_ratio/low_min": 0.0,
|
| 380 |
+
"clip_ratio/region_mean": 0.0,
|
| 381 |
+
"completions/clipped_ratio": 0.55078125,
|
| 382 |
+
"completions/max_length": 2048.0,
|
| 383 |
+
"completions/mean_length": 1518.0625,
|
| 384 |
+
"completions/min_length": 58.0,
|
| 385 |
+
"epoch": 0.15625,
|
| 386 |
+
"frac_reward_zero_std": 0.4375,
|
| 387 |
+
"grad_norm": 2.3706447488652262,
|
| 388 |
+
"kl": 0.0028431631508283317,
|
| 389 |
+
"learning_rate": 9.594789058101153e-07,
|
| 390 |
+
"loss": 2.8428803489077836e-05,
|
| 391 |
+
"reward": 0.3046875,
|
| 392 |
+
"reward_std": 0.2556639611721039,
|
| 393 |
+
"rewards/MajorityAccuracy/mean": 0.3046875,
|
| 394 |
+
"rewards/MajorityAccuracy/std": 0.4611765742301941,
|
| 395 |
+
"step": 25,
|
| 396 |
+
"step_time": 164.97645979514346
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"clip_ratio/high_max": 0.003770759292820003,
|
| 400 |
+
"clip_ratio/high_mean": 0.001059043168424978,
|
| 401 |
+
"clip_ratio/low_mean": 0.000591995136346668,
|
| 402 |
+
"clip_ratio/low_min": 0.0,
|
| 403 |
+
"clip_ratio/region_mean": 0.0016510382847627625,
|
| 404 |
+
"epoch": 0.1625,
|
| 405 |
+
"grad_norm": 4.250587627241846,
|
| 406 |
+
"kl": 0.00340888267965056,
|
| 407 |
+
"learning_rate": 9.55388335194388e-07,
|
| 408 |
+
"loss": 0.00035597512032836676,
|
| 409 |
+
"step": 26,
|
| 410 |
+
"step_time": 26.76314634643495
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"clip_ratio/high_max": 0.0011432734754635021,
|
| 414 |
+
"clip_ratio/high_mean": 0.00028581836886587553,
|
| 415 |
+
"clip_ratio/low_mean": 0.000244140625,
|
| 416 |
+
"clip_ratio/low_min": 0.0,
|
| 417 |
+
"clip_ratio/region_mean": 0.0005299589938658755,
|
| 418 |
+
"epoch": 0.16875,
|
| 419 |
+
"grad_norm": 1.2299124430987665,
|
| 420 |
+
"kl": 0.0034635508491192013,
|
| 421 |
+
"learning_rate": 9.511106949072587e-07,
|
| 422 |
+
"loss": 9.074649278772995e-05,
|
| 423 |
+
"step": 27,
|
| 424 |
+
"step_time": 27.12398390378803
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"clip_ratio/high_max": 0.0008579761488363147,
|
| 428 |
+
"clip_ratio/high_mean": 0.00021449403720907867,
|
| 429 |
+
"clip_ratio/low_mean": 0.0005028351588407531,
|
| 430 |
+
"clip_ratio/low_min": 0.0,
|
| 431 |
+
"clip_ratio/region_mean": 0.0007173291960498318,
|
| 432 |
+
"epoch": 0.175,
|
| 433 |
+
"grad_norm": 1.2326659585408837,
|
| 434 |
+
"kl": 0.0029444643296301365,
|
| 435 |
+
"learning_rate": 9.466477421671295e-07,
|
| 436 |
+
"loss": 0.00012250505096744746,
|
| 437 |
+
"step": 28,
|
| 438 |
+
"step_time": 27.36941067688167
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"clip_ratio/high_max": 0.0006853188533568755,
|
| 442 |
+
"clip_ratio/high_mean": 0.00017132971333921887,
|
| 443 |
+
"clip_ratio/low_mean": 9.1552734375e-05,
|
| 444 |
+
"clip_ratio/low_min": 0.0,
|
| 445 |
+
"clip_ratio/region_mean": 0.00026288244771421887,
|
| 446 |
+
"epoch": 0.18125,
|
| 447 |
+
"grad_norm": 0.6052072957331098,
|
| 448 |
+
"kl": 0.002879777835914865,
|
| 449 |
+
"learning_rate": 9.420013103171891e-07,
|
| 450 |
+
"loss": 2.9595228625112213e-05,
|
| 451 |
+
"step": 29,
|
| 452 |
+
"step_time": 27.093292559031397
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"clip_ratio/high_max": 0.001008792722132057,
|
| 456 |
+
"clip_ratio/high_mean": 0.0003247039785492234,
|
| 457 |
+
"clip_ratio/low_mean": 0.000583641929551959,
|
| 458 |
+
"clip_ratio/low_min": 0.0,
|
| 459 |
+
"clip_ratio/region_mean": 0.0009083459081011824,
|
| 460 |
+
"epoch": 0.1875,
|
| 461 |
+
"grad_norm": 1.2303193349650685,
|
| 462 |
+
"kl": 0.002949665125925094,
|
| 463 |
+
"learning_rate": 9.37173308072291e-07,
|
| 464 |
+
"loss": 7.716580876149237e-05,
|
| 465 |
+
"step": 30,
|
| 466 |
+
"step_time": 26.962128093466163
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"clip_ratio/high_max": 0.003148014424368739,
|
| 470 |
+
"clip_ratio/high_mean": 0.0007870036060921848,
|
| 471 |
+
"clip_ratio/low_mean": 0.0007975361149874516,
|
| 472 |
+
"clip_ratio/low_min": 0.0,
|
| 473 |
+
"clip_ratio/region_mean": 0.0015845397065277211,
|
| 474 |
+
"epoch": 0.19375,
|
| 475 |
+
"grad_norm": 1.3396662938730775,
|
| 476 |
+
"kl": 0.005278581811580807,
|
| 477 |
+
"learning_rate": 9.321657187348688e-07,
|
| 478 |
+
"loss": 0.00013794249389320612,
|
| 479 |
+
"step": 31,
|
| 480 |
+
"step_time": 27.287543520331383
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"clip_ratio/high_max": 0.002574356331024319,
|
| 484 |
+
"clip_ratio/high_mean": 0.0008708630048204213,
|
| 485 |
+
"clip_ratio/low_mean": 0.001007080078125,
|
| 486 |
+
"clip_ratio/low_min": 0.0,
|
| 487 |
+
"clip_ratio/region_mean": 0.0018779430829454213,
|
| 488 |
+
"epoch": 0.2,
|
| 489 |
+
"grad_norm": 1.2681409904300367,
|
| 490 |
+
"kl": 0.01249885669676587,
|
| 491 |
+
"learning_rate": 9.269805993802128e-07,
|
| 492 |
+
"loss": 0.0001968826400116086,
|
| 493 |
+
"step": 32,
|
| 494 |
+
"step_time": 27.196493628900498
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"clip_ratio/high_max": 0.0,
|
| 498 |
+
"clip_ratio/high_mean": 0.0,
|
| 499 |
+
"clip_ratio/low_mean": 0.0,
|
| 500 |
+
"clip_ratio/low_min": 0.0,
|
| 501 |
+
"clip_ratio/region_mean": 0.0,
|
| 502 |
+
"completions/clipped_ratio": 0.5859375,
|
| 503 |
+
"completions/max_length": 2048.0,
|
| 504 |
+
"completions/mean_length": 1601.70703125,
|
| 505 |
+
"completions/min_length": 175.0,
|
| 506 |
+
"epoch": 0.20625,
|
| 507 |
+
"frac_reward_zero_std": 0.40625,
|
| 508 |
+
"grad_norm": 1.1148538706002433,
|
| 509 |
+
"kl": 0.0030230206029955298,
|
| 510 |
+
"learning_rate": 9.216200800114411e-07,
|
| 511 |
+
"loss": 3.024189209099859e-05,
|
| 512 |
+
"reward": 0.2890625,
|
| 513 |
+
"reward_std": 0.2678920328617096,
|
| 514 |
+
"rewards/MajorityAccuracy/mean": 0.2890625,
|
| 515 |
+
"rewards/MajorityAccuracy/std": 0.45421499013900757,
|
| 516 |
+
"step": 33,
|
| 517 |
+
"step_time": 178.60102953156456
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"clip_ratio/high_max": 0.00020096790103707463,
|
| 521 |
+
"clip_ratio/high_mean": 5.0241975259268656e-05,
|
| 522 |
+
"clip_ratio/low_mean": 0.0001220703125,
|
| 523 |
+
"clip_ratio/low_min": 0.0,
|
| 524 |
+
"clip_ratio/region_mean": 0.00017231228775926866,
|
| 525 |
+
"epoch": 0.2125,
|
| 526 |
+
"grad_norm": 0.5528045410242501,
|
| 527 |
+
"kl": 0.0026585767627693713,
|
| 528 |
+
"learning_rate": 9.160863626845119e-07,
|
| 529 |
+
"loss": -2.4503367967554368e-05,
|
| 530 |
+
"step": 34,
|
| 531 |
+
"step_time": 27.03593083564192
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"clip_ratio/high_max": 0.0011352022920618765,
|
| 535 |
+
"clip_ratio/high_mean": 0.0003053969794564182,
|
| 536 |
+
"clip_ratio/low_mean": 0.000396728515625,
|
| 537 |
+
"clip_ratio/low_min": 0.0,
|
| 538 |
+
"clip_ratio/region_mean": 0.0007021254859864712,
|
| 539 |
+
"epoch": 0.21875,
|
| 540 |
+
"grad_norm": 1.2078527597409483,
|
| 541 |
+
"kl": 0.003207199042662978,
|
| 542 |
+
"learning_rate": 9.103817206036382e-07,
|
| 543 |
+
"loss": 3.1955496524460614e-05,
|
| 544 |
+
"step": 35,
|
| 545 |
+
"step_time": 27.188250748440623
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"clip_ratio/high_max": 0.0013293229858390987,
|
| 549 |
+
"clip_ratio/high_mean": 0.0003323307464597747,
|
| 550 |
+
"clip_ratio/low_mean": 6.103515625e-05,
|
| 551 |
+
"clip_ratio/low_min": 0.0,
|
| 552 |
+
"clip_ratio/region_mean": 0.0003933659027097747,
|
| 553 |
+
"epoch": 0.225,
|
| 554 |
+
"grad_norm": 0.7367129990933238,
|
| 555 |
+
"kl": 0.004017930885311216,
|
| 556 |
+
"learning_rate": 9.045084971874737e-07,
|
| 557 |
+
"loss": 7.962075324030593e-05,
|
| 558 |
+
"step": 36,
|
| 559 |
+
"step_time": 26.870144669432193
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"clip_ratio/high_max": 0.0035909312427975237,
|
| 563 |
+
"clip_ratio/high_mean": 0.001069298836227972,
|
| 564 |
+
"clip_ratio/low_mean": 0.0010761254379758611,
|
| 565 |
+
"clip_ratio/low_min": 0.0,
|
| 566 |
+
"clip_ratio/region_mean": 0.002145424281479791,
|
| 567 |
+
"epoch": 0.23125,
|
| 568 |
+
"grad_norm": 1.2707822478984958,
|
| 569 |
+
"kl": 0.0040383366285823286,
|
| 570 |
+
"learning_rate": 8.984691051064574e-07,
|
| 571 |
+
"loss": -0.00016151652380358428,
|
| 572 |
+
"step": 37,
|
| 573 |
+
"step_time": 27.212935904506594
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"clip_ratio/high_max": 0.0032586434099357575,
|
| 577 |
+
"clip_ratio/high_mean": 0.0010430965267005377,
|
| 578 |
+
"clip_ratio/low_mean": 0.0016632505066809244,
|
| 579 |
+
"clip_ratio/low_min": 0.0,
|
| 580 |
+
"clip_ratio/region_mean": 0.0027063469897257164,
|
| 581 |
+
"epoch": 0.2375,
|
| 582 |
+
"grad_norm": 2.226404436011445,
|
| 583 |
+
"kl": 0.007110731094144285,
|
| 584 |
+
"learning_rate": 8.922660252917087e-07,
|
| 585 |
+
"loss": 0.00021227523393463343,
|
| 586 |
+
"step": 38,
|
| 587 |
+
"step_time": 26.375135579146445
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"clip_ratio/high_max": 0.001886820507934317,
|
| 591 |
+
"clip_ratio/high_mean": 0.00047170512698357925,
|
| 592 |
+
"clip_ratio/low_mean": 0.00048828125,
|
| 593 |
+
"clip_ratio/low_min": 0.0,
|
| 594 |
+
"clip_ratio/region_mean": 0.0009599863769835792,
|
| 595 |
+
"epoch": 0.24375,
|
| 596 |
+
"grad_norm": 0.8971392939226038,
|
| 597 |
+
"kl": 0.003974045539507642,
|
| 598 |
+
"learning_rate": 8.859018059158809e-07,
|
| 599 |
+
"loss": 0.00022811771486885846,
|
| 600 |
+
"step": 39,
|
| 601 |
+
"step_time": 26.710039532743394
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"clip_ratio/high_max": 0.00529877285589464,
|
| 605 |
+
"clip_ratio/high_mean": 0.0019266789386165328,
|
| 606 |
+
"clip_ratio/low_mean": 0.0008866159478202462,
|
| 607 |
+
"clip_ratio/low_min": 0.0,
|
| 608 |
+
"clip_ratio/region_mean": 0.0028132948791608214,
|
| 609 |
+
"epoch": 0.25,
|
| 610 |
+
"grad_norm": 2.4790650024126633,
|
| 611 |
+
"kl": 0.0058745190617628396,
|
| 612 |
+
"learning_rate": 8.793790613463954e-07,
|
| 613 |
+
"loss": 0.00025444914354011416,
|
| 614 |
+
"step": 40,
|
| 615 |
+
"step_time": 27.184158651158214
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"clip_ratio/high_max": 0.0,
|
| 619 |
+
"clip_ratio/high_mean": 0.0,
|
| 620 |
+
"clip_ratio/low_mean": 0.0,
|
| 621 |
+
"clip_ratio/low_min": 0.0,
|
| 622 |
+
"clip_ratio/region_mean": 0.0,
|
| 623 |
+
"completions/clipped_ratio": 0.4921875,
|
| 624 |
+
"completions/max_length": 2048.0,
|
| 625 |
+
"completions/mean_length": 1419.10546875,
|
| 626 |
+
"completions/min_length": 95.0,
|
| 627 |
+
"epoch": 0.25625,
|
| 628 |
+
"frac_reward_zero_std": 0.34375,
|
| 629 |
+
"grad_norm": 0.7800816598241538,
|
| 630 |
+
"kl": 0.004536907275905833,
|
| 631 |
+
"learning_rate": 8.727004710714798e-07,
|
| 632 |
+
"loss": 4.5384265831671655e-05,
|
| 633 |
+
"reward": 0.37890625,
|
| 634 |
+
"reward_std": 0.28156307339668274,
|
| 635 |
+
"rewards/MajorityAccuracy/mean": 0.37890625,
|
| 636 |
+
"rewards/MajorityAccuracy/std": 0.48606500029563904,
|
| 637 |
+
"step": 41,
|
| 638 |
+
"step_time": 159.60785855259746
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"clip_ratio/high_max": 0.000851455595693551,
|
| 642 |
+
"clip_ratio/high_mean": 0.00021286389892338775,
|
| 643 |
+
"clip_ratio/low_mean": 4.57763671875e-05,
|
| 644 |
+
"clip_ratio/low_min": 0.0,
|
| 645 |
+
"clip_ratio/region_mean": 0.00025864026974886656,
|
| 646 |
+
"epoch": 0.2625,
|
| 647 |
+
"grad_norm": 0.9503160164851729,
|
| 648 |
+
"kl": 0.004958472098223865,
|
| 649 |
+
"learning_rate": 8.658687785994578e-07,
|
| 650 |
+
"loss": 0.00010069702693726867,
|
| 651 |
+
"step": 42,
|
| 652 |
+
"step_time": 26.87623574770987
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"clip_ratio/high_max": 0.002317378864972852,
|
| 656 |
+
"clip_ratio/high_mean": 0.0007141309288272168,
|
| 657 |
+
"clip_ratio/low_mean": 0.0002593994140625,
|
| 658 |
+
"clip_ratio/low_min": 0.0,
|
| 659 |
+
"clip_ratio/region_mean": 0.0009735303319757804,
|
| 660 |
+
"epoch": 0.26875,
|
| 661 |
+
"grad_norm": 1.4514930961866483,
|
| 662 |
+
"kl": 0.005580351396929473,
|
| 663 |
+
"learning_rate": 8.588867903317394e-07,
|
| 664 |
+
"loss": 7.251377974171191e-05,
|
| 665 |
+
"step": 43,
|
| 666 |
+
"step_time": 26.939780762884766
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"clip_ratio/high_max": 0.0020224897016305476,
|
| 670 |
+
"clip_ratio/high_mean": 0.0005623580109386239,
|
| 671 |
+
"clip_ratio/low_mean": 0.0005309279295033775,
|
| 672 |
+
"clip_ratio/low_min": 0.0,
|
| 673 |
+
"clip_ratio/region_mean": 0.0010932859586318955,
|
| 674 |
+
"epoch": 0.275,
|
| 675 |
+
"grad_norm": 1.7483129696744557,
|
| 676 |
+
"kl": 0.005516084784176201,
|
| 677 |
+
"learning_rate": 8.51757374409974e-07,
|
| 678 |
+
"loss": 0.00015027611516416073,
|
| 679 |
+
"step": 44,
|
| 680 |
+
"step_time": 26.624086203984916
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"clip_ratio/high_max": 0.004067128291353583,
|
| 684 |
+
"clip_ratio/high_mean": 0.0012817707465728745,
|
| 685 |
+
"clip_ratio/low_mean": 0.0008503270073560998,
|
| 686 |
+
"clip_ratio/low_min": 0.0,
|
| 687 |
+
"clip_ratio/region_mean": 0.00213209779758472,
|
| 688 |
+
"epoch": 0.28125,
|
| 689 |
+
"grad_norm": 1.7107130167732032,
|
| 690 |
+
"kl": 0.006045827700290829,
|
| 691 |
+
"learning_rate": 8.444834595378433e-07,
|
| 692 |
+
"loss": 6.178910552989691e-05,
|
| 693 |
+
"step": 45,
|
| 694 |
+
"step_time": 27.232452333904803
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"clip_ratio/high_max": 0.004322588836657815,
|
| 698 |
+
"clip_ratio/high_mean": 0.001597473685251316,
|
| 699 |
+
"clip_ratio/low_mean": 0.00316668301820755,
|
| 700 |
+
"clip_ratio/low_min": 0.00042724609375,
|
| 701 |
+
"clip_ratio/region_mean": 0.004764156707096845,
|
| 702 |
+
"epoch": 0.2875,
|
| 703 |
+
"grad_norm": 2.1774114381388814,
|
| 704 |
+
"kl": 0.0058113892446272075,
|
| 705 |
+
"learning_rate": 8.370680337779736e-07,
|
| 706 |
+
"loss": 7.571838796138763e-05,
|
| 707 |
+
"step": 46,
|
| 708 |
+
"step_time": 27.206646519713104
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"clip_ratio/high_max": 0.0010762019664980471,
|
| 712 |
+
"clip_ratio/high_mean": 0.0002690504916245118,
|
| 713 |
+
"clip_ratio/low_mean": 0.0012969970703125,
|
| 714 |
+
"clip_ratio/low_min": 0.0,
|
| 715 |
+
"clip_ratio/region_mean": 0.0015660475473850965,
|
| 716 |
+
"epoch": 0.29375,
|
| 717 |
+
"grad_norm": 1.0433579358115308,
|
| 718 |
+
"kl": 0.007375664543360472,
|
| 719 |
+
"learning_rate": 8.295141433244659e-07,
|
| 720 |
+
"loss": 0.0003386746975593269,
|
| 721 |
+
"step": 47,
|
| 722 |
+
"step_time": 27.220828437246382
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"clip_ratio/high_max": 0.007152990292524919,
|
| 726 |
+
"clip_ratio/high_mean": 0.002139552634616848,
|
| 727 |
+
"clip_ratio/low_mean": 0.0019448939710855484,
|
| 728 |
+
"clip_ratio/low_min": 0.0,
|
| 729 |
+
"clip_ratio/region_mean": 0.004084446612978354,
|
| 730 |
+
"epoch": 0.3,
|
| 731 |
+
"grad_norm": 1.6786031848736098,
|
| 732 |
+
"kl": 0.01234168279916048,
|
| 733 |
+
"learning_rate": 8.218248912515442e-07,
|
| 734 |
+
"loss": 6.168705294840038e-05,
|
| 735 |
+
"step": 48,
|
| 736 |
+
"step_time": 26.9682992445305
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"clip_ratio/high_max": 0.0,
|
| 740 |
+
"clip_ratio/high_mean": 0.0,
|
| 741 |
+
"clip_ratio/low_mean": 0.0,
|
| 742 |
+
"clip_ratio/low_min": 0.0,
|
| 743 |
+
"clip_ratio/region_mean": 0.0,
|
| 744 |
+
"completions/clipped_ratio": 0.4921875,
|
| 745 |
+
"completions/max_length": 2048.0,
|
| 746 |
+
"completions/mean_length": 1530.9453125,
|
| 747 |
+
"completions/min_length": 125.0,
|
| 748 |
+
"epoch": 0.30625,
|
| 749 |
+
"frac_reward_zero_std": 0.3125,
|
| 750 |
+
"grad_norm": 1.3329669184299138,
|
| 751 |
+
"kl": 0.004251354752341285,
|
| 752 |
+
"learning_rate": 8.140034362388397e-07,
|
| 753 |
+
"loss": 4.2496249079704285e-05,
|
| 754 |
+
"reward": 0.3046875,
|
| 755 |
+
"reward_std": 0.2982693612575531,
|
| 756 |
+
"rewards/MajorityAccuracy/mean": 0.3046875,
|
| 757 |
+
"rewards/MajorityAccuracy/std": 0.4611765742301941,
|
| 758 |
+
"step": 49,
|
| 759 |
+
"step_time": 166.1194721814245
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"clip_ratio/high_max": 0.0032744391646701843,
|
| 763 |
+
"clip_ratio/high_mean": 0.0009966629950213246,
|
| 764 |
+
"clip_ratio/low_mean": 0.0007647376660315786,
|
| 765 |
+
"clip_ratio/low_min": 0.0,
|
| 766 |
+
"clip_ratio/region_mean": 0.0017614006428630091,
|
| 767 |
+
"epoch": 0.3125,
|
| 768 |
+
"grad_norm": 2.6830542262195856,
|
| 769 |
+
"kl": 0.009125121869146824,
|
| 770 |
+
"learning_rate": 8.060529912738314e-07,
|
| 771 |
+
"loss": -0.00017929868772625923,
|
| 772 |
+
"step": 50,
|
| 773 |
+
"step_time": 25.702873463276774
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"clip_ratio/high_max": 0.0019972609006799757,
|
| 777 |
+
"clip_ratio/high_mean": 0.0006830764323240146,
|
| 778 |
+
"clip_ratio/low_mean": 0.0003662109375,
|
| 779 |
+
"clip_ratio/low_min": 0.0,
|
| 780 |
+
"clip_ratio/region_mean": 0.0010492873698240146,
|
| 781 |
+
"epoch": 0.31875,
|
| 782 |
+
"grad_norm": 1.9502031690359583,
|
| 783 |
+
"kl": 0.008702823310159147,
|
| 784 |
+
"learning_rate": 7.979768223319785e-07,
|
| 785 |
+
"loss": 1.4901452232152224e-06,
|
| 786 |
+
"step": 51,
|
| 787 |
+
"step_time": 26.660391591489315
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"clip_ratio/high_max": 0.0016684215952409431,
|
| 791 |
+
"clip_ratio/high_mean": 0.0004171053988102358,
|
| 792 |
+
"clip_ratio/low_mean": 0.0005756048340117559,
|
| 793 |
+
"clip_ratio/low_min": 0.0,
|
| 794 |
+
"clip_ratio/region_mean": 0.0009927102237270446,
|
| 795 |
+
"epoch": 0.325,
|
| 796 |
+
"grad_norm": 0.9765320185467453,
|
| 797 |
+
"kl": 0.005593930603936315,
|
| 798 |
+
"learning_rate": 7.897782470350849e-07,
|
| 799 |
+
"loss": 9.117442823480815e-05,
|
| 800 |
+
"step": 52,
|
| 801 |
+
"step_time": 27.265800840221345
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"clip_ratio/high_max": 0.0075628290651366115,
|
| 805 |
+
"clip_ratio/high_mean": 0.0029765604704152793,
|
| 806 |
+
"clip_ratio/low_mean": 0.0011408126156311482,
|
| 807 |
+
"clip_ratio/low_min": 0.0,
|
| 808 |
+
"clip_ratio/region_mean": 0.004117373144254088,
|
| 809 |
+
"epoch": 0.33125,
|
| 810 |
+
"grad_norm": 2.357796371652783,
|
| 811 |
+
"kl": 0.00846524682128802,
|
| 812 |
+
"learning_rate": 7.814606332884488e-07,
|
| 813 |
+
"loss": 0.00019525177776813507,
|
| 814 |
+
"step": 53,
|
| 815 |
+
"step_time": 26.54177844664082
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"clip_ratio/high_max": 0.001644681120524183,
|
| 819 |
+
"clip_ratio/high_mean": 0.00041117028013104573,
|
| 820 |
+
"clip_ratio/low_mean": 0.0010146817367058247,
|
| 821 |
+
"clip_ratio/low_min": 0.0,
|
| 822 |
+
"clip_ratio/region_mean": 0.0014258520095609128,
|
| 823 |
+
"epoch": 0.3375,
|
| 824 |
+
"grad_norm": 1.1279178540731098,
|
| 825 |
+
"kl": 0.006727178988512605,
|
| 826 |
+
"learning_rate": 7.730273978973552e-07,
|
| 827 |
+
"loss": 0.00022372754756361246,
|
| 828 |
+
"step": 54,
|
| 829 |
+
"step_time": 26.73672230914235
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"clip_ratio/high_max": 0.0014486262807622552,
|
| 833 |
+
"clip_ratio/high_mean": 0.0004019654879812151,
|
| 834 |
+
"clip_ratio/low_mean": 0.0005035400390625,
|
| 835 |
+
"clip_ratio/low_min": 0.0,
|
| 836 |
+
"clip_ratio/region_mean": 0.0009055055234057363,
|
| 837 |
+
"epoch": 0.34375,
|
| 838 |
+
"grad_norm": 0.7419309181466202,
|
| 839 |
+
"kl": 0.008356018690392375,
|
| 840 |
+
"learning_rate": 7.644820051634812e-07,
|
| 841 |
+
"loss": 6.616937025683001e-05,
|
| 842 |
+
"step": 55,
|
| 843 |
+
"step_time": 26.945021900348365
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"clip_ratio/high_max": 0.002262234964291565,
|
| 847 |
+
"clip_ratio/high_mean": 0.0005655587410728913,
|
| 848 |
+
"clip_ratio/low_mean": 0.0014579449052689597,
|
| 849 |
+
"clip_ratio/low_min": 0.0,
|
| 850 |
+
"clip_ratio/region_mean": 0.00202350364997983,
|
| 851 |
+
"epoch": 0.35,
|
| 852 |
+
"grad_norm": 2.3958487675632423,
|
| 853 |
+
"kl": 0.010660360218025744,
|
| 854 |
+
"learning_rate": 7.558279654617912e-07,
|
| 855 |
+
"loss": -7.055008609313518e-06,
|
| 856 |
+
"step": 56,
|
| 857 |
+
"step_time": 27.252678310032934
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"clip_ratio/high_max": 0.0,
|
| 861 |
+
"clip_ratio/high_mean": 0.0,
|
| 862 |
+
"clip_ratio/low_mean": 0.0,
|
| 863 |
+
"clip_ratio/low_min": 0.0,
|
| 864 |
+
"clip_ratio/region_mean": 0.0,
|
| 865 |
+
"completions/clipped_ratio": 0.390625,
|
| 866 |
+
"completions/max_length": 2048.0,
|
| 867 |
+
"completions/mean_length": 1309.125,
|
| 868 |
+
"completions/min_length": 82.0,
|
| 869 |
+
"epoch": 0.35625,
|
| 870 |
+
"frac_reward_zero_std": 0.21875,
|
| 871 |
+
"grad_norm": 2.049325243326204,
|
| 872 |
+
"kl": 0.009697679022792727,
|
| 873 |
+
"learning_rate": 7.470688337985029e-07,
|
| 874 |
+
"loss": 9.70281325862743e-05,
|
| 875 |
+
"reward": 0.34765625,
|
| 876 |
+
"reward_std": 0.3541523218154907,
|
| 877 |
+
"rewards/MajorityAccuracy/mean": 0.34765625,
|
| 878 |
+
"rewards/MajorityAccuracy/std": 0.4771590530872345,
|
| 879 |
+
"step": 57,
|
| 880 |
+
"step_time": 156.73555186064914
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"clip_ratio/high_max": 0.006104011830757372,
|
| 884 |
+
"clip_ratio/high_mean": 0.0016200567588384729,
|
| 885 |
+
"clip_ratio/low_mean": 0.0019680435179907363,
|
| 886 |
+
"clip_ratio/low_min": 0.0,
|
| 887 |
+
"clip_ratio/region_mean": 0.003588100284105167,
|
| 888 |
+
"epoch": 0.3625,
|
| 889 |
+
"grad_norm": 4.164029490763559,
|
| 890 |
+
"kl": 0.014764062943868339,
|
| 891 |
+
"learning_rate": 7.382082083507225e-07,
|
| 892 |
+
"loss": -0.0001940007059602067,
|
| 893 |
+
"step": 58,
|
| 894 |
+
"step_time": 25.85300212353468
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"clip_ratio/high_max": 0.0008743869257159531,
|
| 898 |
+
"clip_ratio/high_mean": 0.00023592895740875974,
|
| 899 |
+
"clip_ratio/low_mean": 0.0005006799656257499,
|
| 900 |
+
"clip_ratio/low_min": 0.0,
|
| 901 |
+
"clip_ratio/region_mean": 0.0007366089266724885,
|
| 902 |
+
"epoch": 0.36875,
|
| 903 |
+
"grad_norm": 1.5177558025000017,
|
| 904 |
+
"kl": 0.009233972581569105,
|
| 905 |
+
"learning_rate": 7.292497289883432e-07,
|
| 906 |
+
"loss": 0.00025203265249729156,
|
| 907 |
+
"step": 59,
|
| 908 |
+
"step_time": 27.252421147190034
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"clip_ratio/high_max": 0.002258668711874634,
|
| 912 |
+
"clip_ratio/high_mean": 0.0006808435173297767,
|
| 913 |
+
"clip_ratio/low_mean": 0.00041962601608247496,
|
| 914 |
+
"clip_ratio/low_min": 0.0,
|
| 915 |
+
"clip_ratio/region_mean": 0.001100469526136294,
|
| 916 |
+
"epoch": 0.375,
|
| 917 |
+
"grad_norm": 1.6514938095282765,
|
| 918 |
+
"kl": 0.008027084404602647,
|
| 919 |
+
"learning_rate": 7.201970757788171e-07,
|
| 920 |
+
"loss": 0.00022597808856517076,
|
| 921 |
+
"step": 60,
|
| 922 |
+
"step_time": 27.22258753562346
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"clip_ratio/high_max": 0.005605180864222348,
|
| 926 |
+
"clip_ratio/high_mean": 0.0018301502350368537,
|
| 927 |
+
"clip_ratio/low_mean": 0.0005035400390625,
|
| 928 |
+
"clip_ratio/low_min": 0.0,
|
| 929 |
+
"clip_ratio/region_mean": 0.0023336902959272265,
|
| 930 |
+
"epoch": 0.38125,
|
| 931 |
+
"grad_norm": 1.9917461713861795,
|
| 932 |
+
"kl": 0.012484997976571321,
|
| 933 |
+
"learning_rate": 7.110539674754159e-07,
|
| 934 |
+
"loss": 0.00013591902097687125,
|
| 935 |
+
"step": 61,
|
| 936 |
+
"step_time": 27.251567658036947
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"clip_ratio/high_max": 0.002423430953058414,
|
| 940 |
+
"clip_ratio/high_mean": 0.0006964097010495607,
|
| 941 |
+
"clip_ratio/low_mean": 0.00128173828125,
|
| 942 |
+
"clip_ratio/low_min": 0.0,
|
| 943 |
+
"clip_ratio/region_mean": 0.001978147993213497,
|
| 944 |
+
"epoch": 0.3875,
|
| 945 |
+
"grad_norm": 2.1878308924072964,
|
| 946 |
+
"kl": 0.011614893097430468,
|
| 947 |
+
"learning_rate": 7.018241599895973e-07,
|
| 948 |
+
"loss": 0.0005136229447089136,
|
| 949 |
+
"step": 62,
|
| 950 |
+
"step_time": 27.2353545865044
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"clip_ratio/high_max": 0.014930696925148368,
|
| 954 |
+
"clip_ratio/high_mean": 0.004674579220591113,
|
| 955 |
+
"clip_ratio/low_mean": 0.0014629686993430369,
|
| 956 |
+
"clip_ratio/low_min": 0.0,
|
| 957 |
+
"clip_ratio/region_mean": 0.006137547839898616,
|
| 958 |
+
"epoch": 0.39375,
|
| 959 |
+
"grad_norm": 2.7377225744422433,
|
| 960 |
+
"kl": 0.014967182418331504,
|
| 961 |
+
"learning_rate": 6.925114448481088e-07,
|
| 962 |
+
"loss": 0.0008161189616657794,
|
| 963 |
+
"step": 63,
|
| 964 |
+
"step_time": 26.92964067030698
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"clip_ratio/high_max": 0.005721951340092346,
|
| 968 |
+
"clip_ratio/high_mean": 0.0016521645229659043,
|
| 969 |
+
"clip_ratio/low_mean": 0.002309099741978571,
|
| 970 |
+
"clip_ratio/low_min": 0.0,
|
| 971 |
+
"clip_ratio/region_mean": 0.003961264264944475,
|
| 972 |
+
"epoch": 0.4,
|
| 973 |
+
"grad_norm": 3.572315222352847,
|
| 974 |
+
"kl": 0.04394343448802829,
|
| 975 |
+
"learning_rate": 6.831196476354614e-07,
|
| 976 |
+
"loss": 0.002968005370348692,
|
| 977 |
+
"step": 64,
|
| 978 |
+
"step_time": 25.841632113792002
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"clip_ratio/high_max": 0.0,
|
| 982 |
+
"clip_ratio/high_mean": 0.0,
|
| 983 |
+
"clip_ratio/low_mean": 0.0,
|
| 984 |
+
"clip_ratio/low_min": 0.0,
|
| 985 |
+
"clip_ratio/region_mean": 0.0,
|
| 986 |
+
"completions/clipped_ratio": 0.40234375,
|
| 987 |
+
"completions/max_length": 2048.0,
|
| 988 |
+
"completions/mean_length": 1295.42578125,
|
| 989 |
+
"completions/min_length": 145.0,
|
| 990 |
+
"epoch": 0.40625,
|
| 991 |
+
"frac_reward_zero_std": 0.53125,
|
| 992 |
+
"grad_norm": 1.8775101345042424,
|
| 993 |
+
"kl": 0.011832903372123837,
|
| 994 |
+
"learning_rate": 6.7365262642241e-07,
|
| 995 |
+
"loss": 0.00011835037730634212,
|
| 996 |
+
"reward": 0.3828125,
|
| 997 |
+
"reward_std": 0.20042762160301208,
|
| 998 |
+
"rewards/MajorityAccuracy/mean": 0.3828125,
|
| 999 |
+
"rewards/MajorityAccuracy/std": 0.48702529072761536,
|
| 1000 |
+
"step": 65,
|
| 1001 |
+
"step_time": 156.763874867931
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"clip_ratio/high_max": 0.004682003840571269,
|
| 1005 |
+
"clip_ratio/high_mean": 0.0013028413159190677,
|
| 1006 |
+
"clip_ratio/low_mean": 0.00020079053501831368,
|
| 1007 |
+
"clip_ratio/low_min": 0.0,
|
| 1008 |
+
"clip_ratio/region_mean": 0.0015036318509373814,
|
| 1009 |
+
"epoch": 0.4125,
|
| 1010 |
+
"grad_norm": 1.5940507320949877,
|
| 1011 |
+
"kl": 0.011823832406662405,
|
| 1012 |
+
"learning_rate": 6.641142701810931e-07,
|
| 1013 |
+
"loss": 0.0004147123545408249,
|
| 1014 |
+
"step": 66,
|
| 1015 |
+
"step_time": 26.960144304204732
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"clip_ratio/high_max": 0.0,
|
| 1019 |
+
"clip_ratio/high_mean": 0.0,
|
| 1020 |
+
"clip_ratio/low_mean": 0.0,
|
| 1021 |
+
"clip_ratio/low_min": 0.0,
|
| 1022 |
+
"clip_ratio/region_mean": 0.0,
|
| 1023 |
+
"epoch": 0.41875,
|
| 1024 |
+
"grad_norm": 0.060239089274313665,
|
| 1025 |
+
"kl": 0.014853667467832565,
|
| 1026 |
+
"learning_rate": 6.545084971874736e-07,
|
| 1027 |
+
"loss": 0.00014863701653666794,
|
| 1028 |
+
"step": 67,
|
| 1029 |
+
"step_time": 27.294059942942113
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"clip_ratio/high_max": 0.0021070526563562453,
|
| 1033 |
+
"clip_ratio/high_mean": 0.0005887437946512364,
|
| 1034 |
+
"clip_ratio/low_mean": 0.000795140047557652,
|
| 1035 |
+
"clip_ratio/low_min": 0.0,
|
| 1036 |
+
"clip_ratio/region_mean": 0.0013838838422088884,
|
| 1037 |
+
"epoch": 0.425,
|
| 1038 |
+
"grad_norm": 1.515128508194636,
|
| 1039 |
+
"kl": 0.018135719117708504,
|
| 1040 |
+
"learning_rate": 6.448392534117461e-07,
|
| 1041 |
+
"loss": 0.00031879800371825695,
|
| 1042 |
+
"step": 68,
|
| 1043 |
+
"step_time": 22.902290848083794
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"clip_ratio/high_max": 0.0037217775534372777,
|
| 1047 |
+
"clip_ratio/high_mean": 0.0009304443883593194,
|
| 1048 |
+
"clip_ratio/low_mean": 0.00010539629147388041,
|
| 1049 |
+
"clip_ratio/low_min": 0.0,
|
| 1050 |
+
"clip_ratio/region_mean": 0.0010358406798331998,
|
| 1051 |
+
"epoch": 0.43125,
|
| 1052 |
+
"grad_norm": 1.0858592338494226,
|
| 1053 |
+
"kl": 0.012419712962582707,
|
| 1054 |
+
"learning_rate": 6.351105108973644e-07,
|
| 1055 |
+
"loss": 0.0002268437237944454,
|
| 1056 |
+
"step": 69,
|
| 1057 |
+
"step_time": 27.28266723267734
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"clip_ratio/high_max": 0.0007943998934933916,
|
| 1061 |
+
"clip_ratio/high_mean": 0.0001985999733733479,
|
| 1062 |
+
"clip_ratio/low_mean": 0.0005340576171875,
|
| 1063 |
+
"clip_ratio/low_min": 0.0,
|
| 1064 |
+
"clip_ratio/region_mean": 0.0007326575905608479,
|
| 1065 |
+
"epoch": 0.4375,
|
| 1066 |
+
"grad_norm": 1.1676904529418188,
|
| 1067 |
+
"kl": 0.017147170496173203,
|
| 1068 |
+
"learning_rate": 6.253262661293602e-07,
|
| 1069 |
+
"loss": 0.0004290329525247216,
|
| 1070 |
+
"step": 70,
|
| 1071 |
+
"step_time": 26.640363234095275
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"clip_ratio/high_max": 0.0056535360927227885,
|
| 1075 |
+
"clip_ratio/high_mean": 0.0021171192202018574,
|
| 1076 |
+
"clip_ratio/low_mean": 0.0004584624184644781,
|
| 1077 |
+
"clip_ratio/low_min": 0.0,
|
| 1078 |
+
"clip_ratio/region_mean": 0.002575581631390378,
|
| 1079 |
+
"epoch": 0.44375,
|
| 1080 |
+
"grad_norm": 1.4536244347648257,
|
| 1081 |
+
"kl": 0.011886020423844457,
|
| 1082 |
+
"learning_rate": 6.154905383926216e-07,
|
| 1083 |
+
"loss": 0.000322720967233181,
|
| 1084 |
+
"step": 71,
|
| 1085 |
+
"step_time": 25.76099731773138
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"clip_ratio/high_max": 0.003381900256499648,
|
| 1089 |
+
"clip_ratio/high_mean": 0.0009206373360939324,
|
| 1090 |
+
"clip_ratio/low_mean": 0.0002593994140625,
|
| 1091 |
+
"clip_ratio/low_min": 0.0,
|
| 1092 |
+
"clip_ratio/region_mean": 0.0011800367501564324,
|
| 1093 |
+
"epoch": 0.45,
|
| 1094 |
+
"grad_norm": 1.0563796230406777,
|
| 1095 |
+
"kl": 0.011061037890613079,
|
| 1096 |
+
"learning_rate": 6.056073681208037e-07,
|
| 1097 |
+
"loss": 0.00018180932966060936,
|
| 1098 |
+
"step": 72,
|
| 1099 |
+
"step_time": 27.453147082123905
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"clip_ratio/high_max": 0.0,
|
| 1103 |
+
"clip_ratio/high_mean": 0.0,
|
| 1104 |
+
"clip_ratio/low_mean": 0.0,
|
| 1105 |
+
"clip_ratio/low_min": 0.0,
|
| 1106 |
+
"clip_ratio/region_mean": 0.0,
|
| 1107 |
+
"completions/clipped_ratio": 0.484375,
|
| 1108 |
+
"completions/max_length": 2048.0,
|
| 1109 |
+
"completions/mean_length": 1463.43359375,
|
| 1110 |
+
"completions/min_length": 111.0,
|
| 1111 |
+
"epoch": 0.45625,
|
| 1112 |
+
"frac_reward_zero_std": 0.46875,
|
| 1113 |
+
"grad_norm": 1.6808151199689243,
|
| 1114 |
+
"kl": 0.007875836221501231,
|
| 1115 |
+
"learning_rate": 5.956808152365532e-07,
|
| 1116 |
+
"loss": 7.879305485403165e-05,
|
| 1117 |
+
"reward": 0.23828125,
|
| 1118 |
+
"reward_std": 0.26052290201187134,
|
| 1119 |
+
"rewards/MajorityAccuracy/mean": 0.23828125,
|
| 1120 |
+
"rewards/MajorityAccuracy/std": 0.4268665909767151,
|
| 1121 |
+
"step": 73,
|
| 1122 |
+
"step_time": 162.47661208128557
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"clip_ratio/high_max": 0.0012077553401468322,
|
| 1126 |
+
"clip_ratio/high_mean": 0.00033981762317125686,
|
| 1127 |
+
"clip_ratio/low_mean": 0.000312393360218266,
|
| 1128 |
+
"clip_ratio/low_min": 0.0,
|
| 1129 |
+
"clip_ratio/region_mean": 0.0006522109870275017,
|
| 1130 |
+
"epoch": 0.4625,
|
| 1131 |
+
"grad_norm": 1.6881795697930746,
|
| 1132 |
+
"kl": 0.011874880758114159,
|
| 1133 |
+
"learning_rate": 5.857149574837268e-07,
|
| 1134 |
+
"loss": 1.3156450222595595e-05,
|
| 1135 |
+
"step": 74,
|
| 1136 |
+
"step_time": 27.192961319815367
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"clip_ratio/high_max": 0.00012980270548723638,
|
| 1140 |
+
"clip_ratio/high_mean": 3.2450676371809095e-05,
|
| 1141 |
+
"clip_ratio/low_mean": 1.52587890625e-05,
|
| 1142 |
+
"clip_ratio/low_min": 0.0,
|
| 1143 |
+
"clip_ratio/region_mean": 4.7709465434309095e-05,
|
| 1144 |
+
"epoch": 0.46875,
|
| 1145 |
+
"grad_norm": 0.34904590426306786,
|
| 1146 |
+
"kl": 0.012078255647793412,
|
| 1147 |
+
"learning_rate": 5.757138887522883e-07,
|
| 1148 |
+
"loss": 0.00011722731142072007,
|
| 1149 |
+
"step": 75,
|
| 1150 |
+
"step_time": 27.104355107061565
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"clip_ratio/high_max": 0.001195300108520314,
|
| 1154 |
+
"clip_ratio/high_mean": 0.0002988250271300785,
|
| 1155 |
+
"clip_ratio/low_mean": 3.0517578125e-05,
|
| 1156 |
+
"clip_ratio/low_min": 0.0,
|
| 1157 |
+
"clip_ratio/region_mean": 0.0003293426052550785,
|
| 1158 |
+
"epoch": 0.475,
|
| 1159 |
+
"grad_norm": 1.128983717615791,
|
| 1160 |
+
"kl": 0.011563299456611276,
|
| 1161 |
+
"learning_rate": 5.656817173965732e-07,
|
| 1162 |
+
"loss": 0.0001455167803214863,
|
| 1163 |
+
"step": 76,
|
| 1164 |
+
"step_time": 27.086320106871426
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"clip_ratio/high_max": 0.0008824775723041967,
|
| 1168 |
+
"clip_ratio/high_mean": 0.00024010193737922236,
|
| 1169 |
+
"clip_ratio/low_mean": 0.00024556969583500177,
|
| 1170 |
+
"clip_ratio/low_min": 0.0,
|
| 1171 |
+
"clip_ratio/region_mean": 0.0004856716295762453,
|
| 1172 |
+
"epoch": 0.48125,
|
| 1173 |
+
"grad_norm": 0.6529876388678957,
|
| 1174 |
+
"kl": 0.00690898229368031,
|
| 1175 |
+
"learning_rate": 5.556225645476118e-07,
|
| 1176 |
+
"loss": 9.223123925039545e-05,
|
| 1177 |
+
"step": 77,
|
| 1178 |
+
"step_time": 27.355760572012514
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"clip_ratio/high_max": 0.009795165999094024,
|
| 1182 |
+
"clip_ratio/high_mean": 0.003546995147189591,
|
| 1183 |
+
"clip_ratio/low_mean": 0.002593907483969815,
|
| 1184 |
+
"clip_ratio/low_min": 0.0,
|
| 1185 |
+
"clip_ratio/region_mean": 0.006140902609331533,
|
| 1186 |
+
"epoch": 0.4875,
|
| 1187 |
+
"grad_norm": 4.341174276081142,
|
| 1188 |
+
"kl": 0.01744568848516792,
|
| 1189 |
+
"learning_rate": 5.455405624202032e-07,
|
| 1190 |
+
"loss": 0.00030361447716131806,
|
| 1191 |
+
"step": 78,
|
| 1192 |
+
"step_time": 26.883789440151304
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"clip_ratio/high_max": 0.005477546801557764,
|
| 1196 |
+
"clip_ratio/high_mean": 0.0019760947398026474,
|
| 1197 |
+
"clip_ratio/low_mean": 0.0010247627669741632,
|
| 1198 |
+
"clip_ratio/low_min": 0.0,
|
| 1199 |
+
"clip_ratio/region_mean": 0.0030008574831299484,
|
| 1200 |
+
"epoch": 0.49375,
|
| 1201 |
+
"grad_norm": 2.325479579021149,
|
| 1202 |
+
"kl": 0.012093300581909716,
|
| 1203 |
+
"learning_rate": 5.354398526154365e-07,
|
| 1204 |
+
"loss": 0.000514226034283638,
|
| 1205 |
+
"step": 79,
|
| 1206 |
+
"step_time": 26.820620184764266
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"clip_ratio/high_max": 0.001345065946225077,
|
| 1210 |
+
"clip_ratio/high_mean": 0.00033626648655626923,
|
| 1211 |
+
"clip_ratio/low_mean": 9.1552734375e-05,
|
| 1212 |
+
"clip_ratio/low_min": 0.0,
|
| 1213 |
+
"clip_ratio/region_mean": 0.00042781922093126923,
|
| 1214 |
+
"epoch": 0.5,
|
| 1215 |
+
"grad_norm": 0.642416331225494,
|
| 1216 |
+
"kl": 0.009604967781342566,
|
| 1217 |
+
"learning_rate": 5.253245844193564e-07,
|
| 1218 |
+
"loss": 0.0001321070740232244,
|
| 1219 |
+
"step": 80,
|
| 1220 |
+
"step_time": 26.81855206936598
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"clip_ratio/high_max": 0.0,
|
| 1224 |
+
"clip_ratio/high_mean": 0.0,
|
| 1225 |
+
"clip_ratio/low_mean": 0.0,
|
| 1226 |
+
"clip_ratio/low_min": 0.0,
|
| 1227 |
+
"clip_ratio/region_mean": 0.0,
|
| 1228 |
+
"completions/clipped_ratio": 0.45703125,
|
| 1229 |
+
"completions/max_length": 2048.0,
|
| 1230 |
+
"completions/mean_length": 1409.5234375,
|
| 1231 |
+
"completions/min_length": 101.0,
|
| 1232 |
+
"epoch": 0.50625,
|
| 1233 |
+
"frac_reward_zero_std": 0.34375,
|
| 1234 |
+
"grad_norm": 1.1792312684618247,
|
| 1235 |
+
"kl": 0.011064736172556877,
|
| 1236 |
+
"learning_rate": 5.151989130984714e-07,
|
| 1237 |
+
"loss": 0.00011057086521759629,
|
| 1238 |
+
"reward": 0.3359375,
|
| 1239 |
+
"reward_std": 0.2973518669605255,
|
| 1240 |
+
"rewards/MajorityAccuracy/mean": 0.3359375,
|
| 1241 |
+
"rewards/MajorityAccuracy/std": 0.4732423424720764,
|
| 1242 |
+
"step": 81,
|
| 1243 |
+
"step_time": 167.03189278766513
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"clip_ratio/high_max": 0.002750054933130741,
|
| 1247 |
+
"clip_ratio/high_mean": 0.0007150225428631529,
|
| 1248 |
+
"clip_ratio/low_mean": 3.0517578125e-05,
|
| 1249 |
+
"clip_ratio/low_min": 0.0,
|
| 1250 |
+
"clip_ratio/region_mean": 0.0007455401355400681,
|
| 1251 |
+
"epoch": 0.5125,
|
| 1252 |
+
"grad_norm": 2.5357267116056046,
|
| 1253 |
+
"kl": 0.012928071315400302,
|
| 1254 |
+
"learning_rate": 5.050669981928055e-07,
|
| 1255 |
+
"loss": 0.0004080343060195446,
|
| 1256 |
+
"step": 82,
|
| 1257 |
+
"step_time": 26.759944117628038
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"clip_ratio/high_max": 0.0024361335526918992,
|
| 1261 |
+
"clip_ratio/high_mean": 0.0006247290184546728,
|
| 1262 |
+
"clip_ratio/low_mean": 0.0006913511897437274,
|
| 1263 |
+
"clip_ratio/low_min": 0.0,
|
| 1264 |
+
"clip_ratio/region_mean": 0.0013160802191123366,
|
| 1265 |
+
"epoch": 0.51875,
|
| 1266 |
+
"grad_norm": 2.3783107598348874,
|
| 1267 |
+
"kl": 0.01028850709553808,
|
| 1268 |
+
"learning_rate": 4.949330018071946e-07,
|
| 1269 |
+
"loss": 0.0002521015703678131,
|
| 1270 |
+
"step": 83,
|
| 1271 |
+
"step_time": 26.87578664533794
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"clip_ratio/high_max": 0.0018149354218621738,
|
| 1275 |
+
"clip_ratio/high_mean": 0.0005789732331322739,
|
| 1276 |
+
"clip_ratio/low_mean": 0.00024316677809110843,
|
| 1277 |
+
"clip_ratio/low_min": 0.0,
|
| 1278 |
+
"clip_ratio/region_mean": 0.0008221399984904565,
|
| 1279 |
+
"epoch": 0.525,
|
| 1280 |
+
"grad_norm": 1.6813296309047943,
|
| 1281 |
+
"kl": 0.01169077877420932,
|
| 1282 |
+
"learning_rate": 4.848010869015287e-07,
|
| 1283 |
+
"loss": 0.00014298950554803014,
|
| 1284 |
+
"step": 84,
|
| 1285 |
+
"step_time": 27.003930322360247
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"clip_ratio/high_max": 0.0016770472429925576,
|
| 1289 |
+
"clip_ratio/high_mean": 0.0005282837992126588,
|
| 1290 |
+
"clip_ratio/low_mean": 0.0002593994140625,
|
| 1291 |
+
"clip_ratio/low_min": 0.0,
|
| 1292 |
+
"clip_ratio/region_mean": 0.0007876832169131376,
|
| 1293 |
+
"epoch": 0.53125,
|
| 1294 |
+
"grad_norm": 1.5941277424702178,
|
| 1295 |
+
"kl": 0.010193743975833058,
|
| 1296 |
+
"learning_rate": 4.746754155806437e-07,
|
| 1297 |
+
"loss": 0.00035219985875301063,
|
| 1298 |
+
"step": 85,
|
| 1299 |
+
"step_time": 26.783120159525424
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"clip_ratio/high_max": 0.011278942954959348,
|
| 1303 |
+
"clip_ratio/high_mean": 0.002937364341050852,
|
| 1304 |
+
"clip_ratio/low_mean": 0.0008612158126197755,
|
| 1305 |
+
"clip_ratio/low_min": 0.0,
|
| 1306 |
+
"clip_ratio/region_mean": 0.00379858014639467,
|
| 1307 |
+
"epoch": 0.5375,
|
| 1308 |
+
"grad_norm": 2.846220750635182,
|
| 1309 |
+
"kl": 0.020119948661886156,
|
| 1310 |
+
"learning_rate": 4.645601473845635e-07,
|
| 1311 |
+
"loss": 8.439162775175646e-05,
|
| 1312 |
+
"step": 86,
|
| 1313 |
+
"step_time": 26.541902352590114
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"clip_ratio/high_max": 0.0002558631604188122,
|
| 1317 |
+
"clip_ratio/high_mean": 6.396579010470305e-05,
|
| 1318 |
+
"clip_ratio/low_mean": 0.00026722038819571026,
|
| 1319 |
+
"clip_ratio/low_min": 0.0,
|
| 1320 |
+
"clip_ratio/region_mean": 0.0003311861764814239,
|
| 1321 |
+
"epoch": 0.54375,
|
| 1322 |
+
"grad_norm": 0.9123996761897317,
|
| 1323 |
+
"kl": 0.00816284364555031,
|
| 1324 |
+
"learning_rate": 4.544594375797968e-07,
|
| 1325 |
+
"loss": 8.146118489094079e-05,
|
| 1326 |
+
"step": 87,
|
| 1327 |
+
"step_time": 27.210516281425953
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"clip_ratio/high_max": 0.004432391477166675,
|
| 1331 |
+
"clip_ratio/high_mean": 0.0012328372104093432,
|
| 1332 |
+
"clip_ratio/low_mean": 0.00048525542661082,
|
| 1333 |
+
"clip_ratio/low_min": 0.0,
|
| 1334 |
+
"clip_ratio/region_mean": 0.0017180926442961209,
|
| 1335 |
+
"epoch": 0.55,
|
| 1336 |
+
"grad_norm": 1.8431309678001164,
|
| 1337 |
+
"kl": 0.013344233389943838,
|
| 1338 |
+
"learning_rate": 4.443774354523882e-07,
|
| 1339 |
+
"loss": 0.0001710494834696874,
|
| 1340 |
+
"step": 88,
|
| 1341 |
+
"step_time": 27.234486498869956
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"clip_ratio/high_max": 0.0,
|
| 1345 |
+
"clip_ratio/high_mean": 0.0,
|
| 1346 |
+
"clip_ratio/low_mean": 0.0,
|
| 1347 |
+
"clip_ratio/low_min": 0.0,
|
| 1348 |
+
"clip_ratio/region_mean": 0.0,
|
| 1349 |
+
"completions/clipped_ratio": 0.34375,
|
| 1350 |
+
"completions/max_length": 2048.0,
|
| 1351 |
+
"completions/mean_length": 1249.5625,
|
| 1352 |
+
"completions/min_length": 101.0,
|
| 1353 |
+
"epoch": 0.55625,
|
| 1354 |
+
"frac_reward_zero_std": 0.375,
|
| 1355 |
+
"grad_norm": 1.1268241398943988,
|
| 1356 |
+
"kl": 0.011294388794340193,
|
| 1357 |
+
"learning_rate": 4.3431828260342675e-07,
|
| 1358 |
+
"loss": 0.00011294377327430993,
|
| 1359 |
+
"reward": 0.42578125,
|
| 1360 |
+
"reward_std": 0.2726386487483978,
|
| 1361 |
+
"rewards/MajorityAccuracy/mean": 0.42578125,
|
| 1362 |
+
"rewards/MajorityAccuracy/std": 0.49542948603630066,
|
| 1363 |
+
"step": 89,
|
| 1364 |
+
"step_time": 154.92280183220282
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"clip_ratio/high_max": 0.0005373116437112913,
|
| 1368 |
+
"clip_ratio/high_mean": 0.0001638090434425976,
|
| 1369 |
+
"clip_ratio/low_mean": 0.0003742343978956342,
|
| 1370 |
+
"clip_ratio/low_min": 0.0,
|
| 1371 |
+
"clip_ratio/region_mean": 0.0005380434413382318,
|
| 1372 |
+
"epoch": 0.5625,
|
| 1373 |
+
"grad_norm": 2.241294299391583,
|
| 1374 |
+
"kl": 0.015336559270508587,
|
| 1375 |
+
"learning_rate": 4.242861112477118e-07,
|
| 1376 |
+
"loss": 0.00023289202363230288,
|
| 1377 |
+
"step": 90,
|
| 1378 |
+
"step_time": 27.228838209528476
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"clip_ratio/high_max": 0.0012453629315132275,
|
| 1382 |
+
"clip_ratio/high_mean": 0.0004308631359890569,
|
| 1383 |
+
"clip_ratio/low_mean": 0.000701904296875,
|
| 1384 |
+
"clip_ratio/low_min": 0.0,
|
| 1385 |
+
"clip_ratio/region_mean": 0.001132767429226078,
|
| 1386 |
+
"epoch": 0.56875,
|
| 1387 |
+
"grad_norm": 2.616323670278535,
|
| 1388 |
+
"kl": 0.011864107218571007,
|
| 1389 |
+
"learning_rate": 4.1428504251627325e-07,
|
| 1390 |
+
"loss": -0.0001357533037662506,
|
| 1391 |
+
"step": 91,
|
| 1392 |
+
"step_time": 26.82597736408934
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"clip_ratio/high_max": 0.0030657084425911307,
|
| 1396 |
+
"clip_ratio/high_mean": 0.0009679702852736227,
|
| 1397 |
+
"clip_ratio/low_mean": 0.000244140625,
|
| 1398 |
+
"clip_ratio/low_min": 0.0,
|
| 1399 |
+
"clip_ratio/region_mean": 0.0012121109175495803,
|
| 1400 |
+
"epoch": 0.575,
|
| 1401 |
+
"grad_norm": 1.1681510240543613,
|
| 1402 |
+
"kl": 0.012650871183723211,
|
| 1403 |
+
"learning_rate": 4.0431918476344685e-07,
|
| 1404 |
+
"loss": 0.0002260434557683766,
|
| 1405 |
+
"step": 92,
|
| 1406 |
+
"step_time": 25.838407851289958
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"clip_ratio/high_max": 0.0034614389878697693,
|
| 1410 |
+
"clip_ratio/high_mean": 0.0009423934388905764,
|
| 1411 |
+
"clip_ratio/low_mean": 0.0027554708285606466,
|
| 1412 |
+
"clip_ratio/low_min": 0.0,
|
| 1413 |
+
"clip_ratio/region_mean": 0.003697864289279096,
|
| 1414 |
+
"epoch": 0.58125,
|
| 1415 |
+
"grad_norm": 3.0642794067775023,
|
| 1416 |
+
"kl": 0.016640262445434928,
|
| 1417 |
+
"learning_rate": 3.943926318791963e-07,
|
| 1418 |
+
"loss": 0.00016787639469839633,
|
| 1419 |
+
"step": 93,
|
| 1420 |
+
"step_time": 25.24869475979358
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"clip_ratio/high_max": 0.005030727275880054,
|
| 1424 |
+
"clip_ratio/high_mean": 0.001664450544922147,
|
| 1425 |
+
"clip_ratio/low_mean": 0.00037462016189238057,
|
| 1426 |
+
"clip_ratio/low_min": 0.0,
|
| 1427 |
+
"clip_ratio/region_mean": 0.002039070714090485,
|
| 1428 |
+
"epoch": 0.5875,
|
| 1429 |
+
"grad_norm": 2.159690689639241,
|
| 1430 |
+
"kl": 0.014591581770218909,
|
| 1431 |
+
"learning_rate": 3.845094616073783e-07,
|
| 1432 |
+
"loss": 0.0004564328701235354,
|
| 1433 |
+
"step": 94,
|
| 1434 |
+
"step_time": 24.99718160694465
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"clip_ratio/high_max": 0.0019642367551568896,
|
| 1438 |
+
"clip_ratio/high_mean": 0.0007247603498399258,
|
| 1439 |
+
"clip_ratio/low_mean": 0.0009098173686652444,
|
| 1440 |
+
"clip_ratio/low_min": 0.0,
|
| 1441 |
+
"clip_ratio/region_mean": 0.0016345777257811278,
|
| 1442 |
+
"epoch": 0.59375,
|
| 1443 |
+
"grad_norm": 1.621480160689911,
|
| 1444 |
+
"kl": 0.011820225277915597,
|
| 1445 |
+
"learning_rate": 3.7467373387063964e-07,
|
| 1446 |
+
"loss": 0.00029627562616951764,
|
| 1447 |
+
"step": 95,
|
| 1448 |
+
"step_time": 27.18271924275905
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"clip_ratio/high_max": 0.003298453870229423,
|
| 1452 |
+
"clip_ratio/high_mean": 0.0008246134675573558,
|
| 1453 |
+
"clip_ratio/low_mean": 9.498480358161032e-05,
|
| 1454 |
+
"clip_ratio/low_min": 0.0,
|
| 1455 |
+
"clip_ratio/region_mean": 0.0009195982711389661,
|
| 1456 |
+
"epoch": 0.6,
|
| 1457 |
+
"grad_norm": 1.717684565081737,
|
| 1458 |
+
"kl": 0.017729216371662915,
|
| 1459 |
+
"learning_rate": 3.648894891026358e-07,
|
| 1460 |
+
"loss": 0.0005867662839591503,
|
| 1461 |
+
"step": 96,
|
| 1462 |
+
"step_time": 26.737219403497875
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"clip_ratio/high_max": 0.0,
|
| 1466 |
+
"clip_ratio/high_mean": 0.0,
|
| 1467 |
+
"clip_ratio/low_mean": 0.0,
|
| 1468 |
+
"clip_ratio/low_min": 0.0,
|
| 1469 |
+
"clip_ratio/region_mean": 0.0,
|
| 1470 |
+
"completions/clipped_ratio": 0.421875,
|
| 1471 |
+
"completions/max_length": 2048.0,
|
| 1472 |
+
"completions/mean_length": 1410.22265625,
|
| 1473 |
+
"completions/min_length": 105.0,
|
| 1474 |
+
"epoch": 0.60625,
|
| 1475 |
+
"frac_reward_zero_std": 0.1875,
|
| 1476 |
+
"grad_norm": 1.500907551798478,
|
| 1477 |
+
"kl": 0.012207877123728395,
|
| 1478 |
+
"learning_rate": 3.5516074658825397e-07,
|
| 1479 |
+
"loss": 0.00012210757995489985,
|
| 1480 |
+
"reward": 0.33984375,
|
| 1481 |
+
"reward_std": 0.364021360874176,
|
| 1482 |
+
"rewards/MajorityAccuracy/mean": 0.33984375,
|
| 1483 |
+
"rewards/MajorityAccuracy/std": 0.47458380460739136,
|
| 1484 |
+
"step": 97,
|
| 1485 |
+
"step_time": 157.54930535005406
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"clip_ratio/high_max": 0.002009971285588108,
|
| 1489 |
+
"clip_ratio/high_mean": 0.0006292676662269514,
|
| 1490 |
+
"clip_ratio/low_mean": 0.00043805937821161933,
|
| 1491 |
+
"clip_ratio/low_min": 0.0,
|
| 1492 |
+
"clip_ratio/region_mean": 0.0010673270444385707,
|
| 1493 |
+
"epoch": 0.6125,
|
| 1494 |
+
"grad_norm": 2.793317679865097,
|
| 1495 |
+
"kl": 0.013201590394601226,
|
| 1496 |
+
"learning_rate": 3.454915028125263e-07,
|
| 1497 |
+
"loss": 0.00024410337209701538,
|
| 1498 |
+
"step": 98,
|
| 1499 |
+
"step_time": 26.522718750406057
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"clip_ratio/high_max": 0.0025563907402101904,
|
| 1503 |
+
"clip_ratio/high_mean": 0.0008830963706714101,
|
| 1504 |
+
"clip_ratio/low_mean": 0.000914754349651048,
|
| 1505 |
+
"clip_ratio/low_min": 6.103515625e-05,
|
| 1506 |
+
"clip_ratio/region_mean": 0.0017978507385123521,
|
| 1507 |
+
"epoch": 0.61875,
|
| 1508 |
+
"grad_norm": 2.3649188802219085,
|
| 1509 |
+
"kl": 0.014511542278341949,
|
| 1510 |
+
"learning_rate": 3.3588572981890684e-07,
|
| 1511 |
+
"loss": 0.00024278927594423294,
|
| 1512 |
+
"step": 99,
|
| 1513 |
+
"step_time": 26.524361558724195
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"clip_ratio/high_max": 0.0011438667279435322,
|
| 1517 |
+
"clip_ratio/high_mean": 0.00028596668198588304,
|
| 1518 |
+
"clip_ratio/low_mean": 0.0003509521484375,
|
| 1519 |
+
"clip_ratio/low_min": 0.0,
|
| 1520 |
+
"clip_ratio/region_mean": 0.0006369188231474254,
|
| 1521 |
+
"epoch": 0.625,
|
| 1522 |
+
"grad_norm": 1.3178876751117026,
|
| 1523 |
+
"kl": 0.01065819093491882,
|
| 1524 |
+
"learning_rate": 3.263473735775899e-07,
|
| 1525 |
+
"loss": 9.752159530762583e-05,
|
| 1526 |
+
"step": 100,
|
| 1527 |
+
"step_time": 27.145337983965874
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"clip_ratio/high_max": 0.0023751286935294047,
|
| 1531 |
+
"clip_ratio/high_mean": 0.0006939420782146044,
|
| 1532 |
+
"clip_ratio/low_mean": 0.00043854436626133975,
|
| 1533 |
+
"clip_ratio/low_min": 0.0,
|
| 1534 |
+
"clip_ratio/region_mean": 0.001132486448113923,
|
| 1535 |
+
"epoch": 0.63125,
|
| 1536 |
+
"grad_norm": 2.3320596978553607,
|
| 1537 |
+
"kl": 0.01558808726258576,
|
| 1538 |
+
"learning_rate": 3.1688035236453865e-07,
|
| 1539 |
+
"loss": 0.00027671089628711343,
|
| 1540 |
+
"step": 101,
|
| 1541 |
+
"step_time": 26.068868320435286
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"clip_ratio/high_max": 0.0038306038768496364,
|
| 1545 |
+
"clip_ratio/high_mean": 0.0010495627284399234,
|
| 1546 |
+
"clip_ratio/low_mean": 0.0003920411691069603,
|
| 1547 |
+
"clip_ratio/low_min": 0.0,
|
| 1548 |
+
"clip_ratio/region_mean": 0.0014416039048228413,
|
| 1549 |
+
"epoch": 0.6375,
|
| 1550 |
+
"grad_norm": 1.7216529797623734,
|
| 1551 |
+
"kl": 0.008885040530003607,
|
| 1552 |
+
"learning_rate": 3.0748855515189096e-07,
|
| 1553 |
+
"loss": 0.00015222324873320758,
|
| 1554 |
+
"step": 102,
|
| 1555 |
+
"step_time": 27.147549544926733
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"clip_ratio/high_max": 0.0025533086736686528,
|
| 1559 |
+
"clip_ratio/high_mean": 0.00067494111135602,
|
| 1560 |
+
"clip_ratio/low_mean": 0.000487335397338029,
|
| 1561 |
+
"clip_ratio/low_min": 0.0,
|
| 1562 |
+
"clip_ratio/region_mean": 0.001162276508694049,
|
| 1563 |
+
"epoch": 0.64375,
|
| 1564 |
+
"grad_norm": 1.8941504836829348,
|
| 1565 |
+
"kl": 0.018843257217667997,
|
| 1566 |
+
"learning_rate": 2.981758400104028e-07,
|
| 1567 |
+
"loss": 0.0003612434375099838,
|
| 1568 |
+
"step": 103,
|
| 1569 |
+
"step_time": 27.027293679770082
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"clip_ratio/high_max": 0.0042776035916176625,
|
| 1573 |
+
"clip_ratio/high_mean": 0.0015498416596528841,
|
| 1574 |
+
"clip_ratio/low_mean": 0.00037299165705917403,
|
| 1575 |
+
"clip_ratio/low_min": 0.0,
|
| 1576 |
+
"clip_ratio/region_mean": 0.0019228332967031747,
|
| 1577 |
+
"epoch": 0.65,
|
| 1578 |
+
"grad_norm": 1.7926315017616006,
|
| 1579 |
+
"kl": 0.01464485249016434,
|
| 1580 |
+
"learning_rate": 2.8894603252458403e-07,
|
| 1581 |
+
"loss": 0.00034605711698532104,
|
| 1582 |
+
"step": 104,
|
| 1583 |
+
"step_time": 26.566488713026047
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"clip_ratio/high_max": 0.0,
|
| 1587 |
+
"clip_ratio/high_mean": 0.0,
|
| 1588 |
+
"clip_ratio/low_mean": 0.0,
|
| 1589 |
+
"clip_ratio/low_min": 0.0,
|
| 1590 |
+
"clip_ratio/region_mean": 0.0,
|
| 1591 |
+
"completions/clipped_ratio": 0.3828125,
|
| 1592 |
+
"completions/max_length": 2048.0,
|
| 1593 |
+
"completions/mean_length": 1340.26953125,
|
| 1594 |
+
"completions/min_length": 123.0,
|
| 1595 |
+
"epoch": 0.65625,
|
| 1596 |
+
"frac_reward_zero_std": 0.3125,
|
| 1597 |
+
"grad_norm": 2.0317826101182765,
|
| 1598 |
+
"kl": 0.012531956541351974,
|
| 1599 |
+
"learning_rate": 2.7980292422118277e-07,
|
| 1600 |
+
"loss": 0.00012528366642072797,
|
| 1601 |
+
"reward": 0.359375,
|
| 1602 |
+
"reward_std": 0.32772529125213623,
|
| 1603 |
+
"rewards/MajorityAccuracy/mean": 0.359375,
|
| 1604 |
+
"rewards/MajorityAccuracy/std": 0.4807571768760681,
|
| 1605 |
+
"step": 105,
|
| 1606 |
+
"step_time": 156.75952491676435
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"clip_ratio/high_max": 0.000417546383687295,
|
| 1610 |
+
"clip_ratio/high_mean": 0.00010438659592182375,
|
| 1611 |
+
"clip_ratio/low_mean": 0.000274658203125,
|
| 1612 |
+
"clip_ratio/low_min": 0.0,
|
| 1613 |
+
"clip_ratio/region_mean": 0.00037904480268480256,
|
| 1614 |
+
"epoch": 0.6625,
|
| 1615 |
+
"grad_norm": 1.832561146473964,
|
| 1616 |
+
"kl": 0.01721205865032971,
|
| 1617 |
+
"learning_rate": 2.70750271011657e-07,
|
| 1618 |
+
"loss": 0.0003257420612499118,
|
| 1619 |
+
"step": 106,
|
| 1620 |
+
"step_time": 27.148350415751338
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"clip_ratio/high_max": 0.0012097757135052234,
|
| 1624 |
+
"clip_ratio/high_mean": 0.00030244392837630585,
|
| 1625 |
+
"clip_ratio/low_mean": 0.0002288818359375,
|
| 1626 |
+
"clip_ratio/low_min": 0.0,
|
| 1627 |
+
"clip_ratio/region_mean": 0.0005313257643138058,
|
| 1628 |
+
"epoch": 0.66875,
|
| 1629 |
+
"grad_norm": 0.997301065385491,
|
| 1630 |
+
"kl": 0.008027508738450706,
|
| 1631 |
+
"learning_rate": 2.6179179164927754e-07,
|
| 1632 |
+
"loss": 0.00024193961871787906,
|
| 1633 |
+
"step": 107,
|
| 1634 |
+
"step_time": 27.359571520239115
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"clip_ratio/high_max": 0.001132406119722873,
|
| 1638 |
+
"clip_ratio/high_mean": 0.00035459943319438025,
|
| 1639 |
+
"clip_ratio/low_mean": 0.0006863282324047759,
|
| 1640 |
+
"clip_ratio/low_min": 0.0,
|
| 1641 |
+
"clip_ratio/region_mean": 0.0010409276655991562,
|
| 1642 |
+
"epoch": 0.675,
|
| 1643 |
+
"grad_norm": 3.1106847223100518,
|
| 1644 |
+
"kl": 0.016563388635404408,
|
| 1645 |
+
"learning_rate": 2.529311662014972e-07,
|
| 1646 |
+
"loss": 0.00033478904515504837,
|
| 1647 |
+
"step": 108,
|
| 1648 |
+
"step_time": 25.088318042457104
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"clip_ratio/high_max": 0.00062167633586796,
|
| 1652 |
+
"clip_ratio/high_mean": 0.00015541908396699,
|
| 1653 |
+
"clip_ratio/low_mean": 0.0002735246962402016,
|
| 1654 |
+
"clip_ratio/low_min": 0.0,
|
| 1655 |
+
"clip_ratio/region_mean": 0.0004289437783882022,
|
| 1656 |
+
"epoch": 0.68125,
|
| 1657 |
+
"grad_norm": 1.0857581417318738,
|
| 1658 |
+
"kl": 0.012133828015066683,
|
| 1659 |
+
"learning_rate": 2.441720345382089e-07,
|
| 1660 |
+
"loss": 0.0004086225526407361,
|
| 1661 |
+
"step": 109,
|
| 1662 |
+
"step_time": 27.001190629322082
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"clip_ratio/high_max": 0.0021673139999620616,
|
| 1666 |
+
"clip_ratio/high_mean": 0.0005418284999905154,
|
| 1667 |
+
"clip_ratio/low_mean": 0.0004739256728498731,
|
| 1668 |
+
"clip_ratio/low_min": 0.0,
|
| 1669 |
+
"clip_ratio/region_mean": 0.0010157541692024097,
|
| 1670 |
+
"epoch": 0.6875,
|
| 1671 |
+
"grad_norm": 3.9606064291090544,
|
| 1672 |
+
"kl": 0.01842797629069537,
|
| 1673 |
+
"learning_rate": 2.355179948365189e-07,
|
| 1674 |
+
"loss": 0.0005763514200225472,
|
| 1675 |
+
"step": 110,
|
| 1676 |
+
"step_time": 27.313880170229822
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"clip_ratio/high_max": 0.0017284111090702936,
|
| 1680 |
+
"clip_ratio/high_mean": 0.0007242807623697445,
|
| 1681 |
+
"clip_ratio/low_mean": 0.00031577885965816677,
|
| 1682 |
+
"clip_ratio/low_min": 0.0,
|
| 1683 |
+
"clip_ratio/region_mean": 0.0010400596365798265,
|
| 1684 |
+
"epoch": 0.69375,
|
| 1685 |
+
"grad_norm": 1.5135995496151007,
|
| 1686 |
+
"kl": 0.012553507345728576,
|
| 1687 |
+
"learning_rate": 2.26972602102645e-07,
|
| 1688 |
+
"loss": 0.00012128427624702454,
|
| 1689 |
+
"step": 111,
|
| 1690 |
+
"step_time": 26.66713598649949
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"clip_ratio/high_max": 0.005452543904539198,
|
| 1694 |
+
"clip_ratio/high_mean": 0.0019388627406442538,
|
| 1695 |
+
"clip_ratio/low_mean": 0.0002903959721152205,
|
| 1696 |
+
"clip_ratio/low_min": 0.0,
|
| 1697 |
+
"clip_ratio/region_mean": 0.002229258738225326,
|
| 1698 |
+
"epoch": 0.7,
|
| 1699 |
+
"grad_norm": 2.143870643657561,
|
| 1700 |
+
"kl": 0.02200764766894281,
|
| 1701 |
+
"learning_rate": 2.1853936671155127e-07,
|
| 1702 |
+
"loss": 0.0004231315979268402,
|
| 1703 |
+
"step": 112,
|
| 1704 |
+
"step_time": 24.66957320086658
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"clip_ratio/high_max": 0.0,
|
| 1708 |
+
"clip_ratio/high_mean": 0.0,
|
| 1709 |
+
"clip_ratio/low_mean": 0.0,
|
| 1710 |
+
"clip_ratio/low_min": 0.0,
|
| 1711 |
+
"clip_ratio/region_mean": 0.0,
|
| 1712 |
+
"completions/clipped_ratio": 0.2109375,
|
| 1713 |
+
"completions/max_length": 2048.0,
|
| 1714 |
+
"completions/mean_length": 1105.95703125,
|
| 1715 |
+
"completions/min_length": 48.0,
|
| 1716 |
+
"epoch": 0.70625,
|
| 1717 |
+
"frac_reward_zero_std": 0.40625,
|
| 1718 |
+
"grad_norm": 2.7285425444936124,
|
| 1719 |
+
"kl": 0.028295591473579407,
|
| 1720 |
+
"learning_rate": 2.1022175296491512e-07,
|
| 1721 |
+
"loss": 0.0002830786688718945,
|
| 1722 |
+
"reward": 0.4921875,
|
| 1723 |
+
"reward_std": 0.2872144281864166,
|
| 1724 |
+
"rewards/MajorityAccuracy/mean": 0.4921875,
|
| 1725 |
+
"rewards/MajorityAccuracy/std": 0.5009182691574097,
|
| 1726 |
+
"step": 113,
|
| 1727 |
+
"step_time": 151.86861566081643
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"clip_ratio/high_max": 0.002627604510053061,
|
| 1731 |
+
"clip_ratio/high_mean": 0.0007435935076500755,
|
| 1732 |
+
"clip_ratio/low_mean": 3.0517578125e-05,
|
| 1733 |
+
"clip_ratio/low_min": 0.0,
|
| 1734 |
+
"clip_ratio/region_mean": 0.0007741110857750755,
|
| 1735 |
+
"epoch": 0.7125,
|
| 1736 |
+
"grad_norm": 1.480893968057655,
|
| 1737 |
+
"kl": 0.0164707750082016,
|
| 1738 |
+
"learning_rate": 2.0202317766802152e-07,
|
| 1739 |
+
"loss": 0.0001287244667764753,
|
| 1740 |
+
"step": 114,
|
| 1741 |
+
"step_time": 24.106747506186366
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"clip_ratio/high_max": 0.0,
|
| 1745 |
+
"clip_ratio/high_mean": 0.0,
|
| 1746 |
+
"clip_ratio/low_mean": 0.0,
|
| 1747 |
+
"clip_ratio/low_min": 0.0,
|
| 1748 |
+
"clip_ratio/region_mean": 0.0,
|
| 1749 |
+
"epoch": 0.71875,
|
| 1750 |
+
"grad_norm": 0.7314452458777096,
|
| 1751 |
+
"kl": 0.013424914446659386,
|
| 1752 |
+
"learning_rate": 1.9394700872616853e-07,
|
| 1753 |
+
"loss": 0.0002008121373364702,
|
| 1754 |
+
"step": 115,
|
| 1755 |
+
"step_time": 26.95093895168975
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"clip_ratio/high_max": 0.0014262408221838996,
|
| 1759 |
+
"clip_ratio/high_mean": 0.0004273186314094346,
|
| 1760 |
+
"clip_ratio/low_mean": 0.00045532791409641504,
|
| 1761 |
+
"clip_ratio/low_min": 0.0,
|
| 1762 |
+
"clip_ratio/region_mean": 0.0008826465418678708,
|
| 1763 |
+
"epoch": 0.725,
|
| 1764 |
+
"grad_norm": 2.6519881886395895,
|
| 1765 |
+
"kl": 0.013705393066629767,
|
| 1766 |
+
"learning_rate": 1.8599656376116024e-07,
|
| 1767 |
+
"loss": 0.00027579593006521463,
|
| 1768 |
+
"step": 116,
|
| 1769 |
+
"step_time": 26.961054045706987
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"clip_ratio/high_max": 0.0014450431553996168,
|
| 1773 |
+
"clip_ratio/high_mean": 0.0005509369202627568,
|
| 1774 |
+
"clip_ratio/low_mean": 0.0002649667294463143,
|
| 1775 |
+
"clip_ratio/low_min": 0.0,
|
| 1776 |
+
"clip_ratio/region_mean": 0.000815903649709071,
|
| 1777 |
+
"epoch": 0.73125,
|
| 1778 |
+
"grad_norm": 3.688351107873593,
|
| 1779 |
+
"kl": 0.018965681083500385,
|
| 1780 |
+
"learning_rate": 1.7817510874845582e-07,
|
| 1781 |
+
"loss": 3.324123099446297e-05,
|
| 1782 |
+
"step": 117,
|
| 1783 |
+
"step_time": 24.545702875591815
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"clip_ratio/high_max": 0.0011959299590671435,
|
| 1787 |
+
"clip_ratio/high_mean": 0.00033160253587993793,
|
| 1788 |
+
"clip_ratio/low_mean": 0.0001445149136998225,
|
| 1789 |
+
"clip_ratio/low_min": 0.0,
|
| 1790 |
+
"clip_ratio/region_mean": 0.00047611745321773924,
|
| 1791 |
+
"epoch": 0.7375,
|
| 1792 |
+
"grad_norm": 1.1337738357504468,
|
| 1793 |
+
"kl": 0.02132789883762598,
|
| 1794 |
+
"learning_rate": 1.7048585667553412e-07,
|
| 1795 |
+
"loss": 0.00018476313562132418,
|
| 1796 |
+
"step": 118,
|
| 1797 |
+
"step_time": 26.661875354591757
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"clip_ratio/high_max": 0.0015893470699666068,
|
| 1801 |
+
"clip_ratio/high_mean": 0.0007123826289898716,
|
| 1802 |
+
"clip_ratio/low_mean": 0.0006725128841935657,
|
| 1803 |
+
"clip_ratio/low_min": 6.103515625e-05,
|
| 1804 |
+
"clip_ratio/region_mean": 0.001384895516821416,
|
| 1805 |
+
"epoch": 0.74375,
|
| 1806 |
+
"grad_norm": 1.6748394014851675,
|
| 1807 |
+
"kl": 0.012326097581535578,
|
| 1808 |
+
"learning_rate": 1.6293196622202632e-07,
|
| 1809 |
+
"loss": 0.0003840271383523941,
|
| 1810 |
+
"step": 119,
|
| 1811 |
+
"step_time": 26.73579535726458
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"clip_ratio/high_max": 0.002675875562999863,
|
| 1815 |
+
"clip_ratio/high_mean": 0.0007926013840915402,
|
| 1816 |
+
"clip_ratio/low_mean": 0.0006797059177188203,
|
| 1817 |
+
"clip_ratio/low_min": 0.0,
|
| 1818 |
+
"clip_ratio/region_mean": 0.0014723073109053075,
|
| 1819 |
+
"epoch": 0.75,
|
| 1820 |
+
"grad_norm": 2.911741639998382,
|
| 1821 |
+
"kl": 0.018149175448343158,
|
| 1822 |
+
"learning_rate": 1.555165404621567e-07,
|
| 1823 |
+
"loss": 0.00018735327466856688,
|
| 1824 |
+
"step": 120,
|
| 1825 |
+
"step_time": 26.517592524643987
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"clip_ratio/high_max": 0.0,
|
| 1829 |
+
"clip_ratio/high_mean": 0.0,
|
| 1830 |
+
"clip_ratio/low_mean": 0.0,
|
| 1831 |
+
"clip_ratio/low_min": 0.0,
|
| 1832 |
+
"clip_ratio/region_mean": 0.0,
|
| 1833 |
+
"completions/clipped_ratio": 0.296875,
|
| 1834 |
+
"completions/max_length": 2048.0,
|
| 1835 |
+
"completions/mean_length": 1143.41015625,
|
| 1836 |
+
"completions/min_length": 67.0,
|
| 1837 |
+
"epoch": 0.75625,
|
| 1838 |
+
"frac_reward_zero_std": 0.28125,
|
| 1839 |
+
"grad_norm": 2.0389056356985247,
|
| 1840 |
+
"kl": 0.016144975554198027,
|
| 1841 |
+
"learning_rate": 1.4824262559002592e-07,
|
| 1842 |
+
"loss": 0.00016140488150995225,
|
| 1843 |
+
"reward": 0.44140625,
|
| 1844 |
+
"reward_std": 0.3110278248786926,
|
| 1845 |
+
"rewards/MajorityAccuracy/mean": 0.44140625,
|
| 1846 |
+
"rewards/MajorityAccuracy/std": 0.4975275695323944,
|
| 1847 |
+
"step": 121,
|
| 1848 |
+
"step_time": 150.5176954693161
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"clip_ratio/high_max": 0.0018153203855035827,
|
| 1852 |
+
"clip_ratio/high_mean": 0.0007078805247147102,
|
| 1853 |
+
"clip_ratio/low_mean": 0.00032315405223926064,
|
| 1854 |
+
"clip_ratio/low_min": 0.0,
|
| 1855 |
+
"clip_ratio/region_mean": 0.0010310345969628543,
|
| 1856 |
+
"epoch": 0.7625,
|
| 1857 |
+
"grad_norm": 1.6061740509834261,
|
| 1858 |
+
"kl": 0.011550423922017217,
|
| 1859 |
+
"learning_rate": 1.4111320966826057e-07,
|
| 1860 |
+
"loss": 0.00015704799443483353,
|
| 1861 |
+
"step": 122,
|
| 1862 |
+
"step_time": 26.77427643770352
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"clip_ratio/high_max": 0.0006391375791281462,
|
| 1866 |
+
"clip_ratio/high_mean": 0.00015978439478203654,
|
| 1867 |
+
"clip_ratio/low_mean": 0.00036326546978671104,
|
| 1868 |
+
"clip_ratio/low_min": 0.0,
|
| 1869 |
+
"clip_ratio/region_mean": 0.0005230498718447052,
|
| 1870 |
+
"epoch": 0.76875,
|
| 1871 |
+
"grad_norm": 1.86895961349613,
|
| 1872 |
+
"kl": 0.013036656891927123,
|
| 1873 |
+
"learning_rate": 1.3413122140054217e-07,
|
| 1874 |
+
"loss": 0.00015709138824604452,
|
| 1875 |
+
"step": 123,
|
| 1876 |
+
"step_time": 26.83413082268089
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"clip_ratio/high_max": 0.002246078453026712,
|
| 1880 |
+
"clip_ratio/high_mean": 0.0006474105612142012,
|
| 1881 |
+
"clip_ratio/low_mean": 0.00046409732021857053,
|
| 1882 |
+
"clip_ratio/low_min": 0.0,
|
| 1883 |
+
"clip_ratio/region_mean": 0.0011115078814327717,
|
| 1884 |
+
"epoch": 0.775,
|
| 1885 |
+
"grad_norm": 2.352420633528596,
|
| 1886 |
+
"kl": 0.01247078471351415,
|
| 1887 |
+
"learning_rate": 1.272995289285202e-07,
|
| 1888 |
+
"loss": 3.7558816984528676e-05,
|
| 1889 |
+
"step": 124,
|
| 1890 |
+
"step_time": 26.803358951583505
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"clip_ratio/high_max": 0.0036501993890851736,
|
| 1894 |
+
"clip_ratio/high_mean": 0.0009561038459651172,
|
| 1895 |
+
"clip_ratio/low_mean": 0.0007382543990388513,
|
| 1896 |
+
"clip_ratio/low_min": 0.0,
|
| 1897 |
+
"clip_ratio/region_mean": 0.0016943582413659897,
|
| 1898 |
+
"epoch": 0.78125,
|
| 1899 |
+
"grad_norm": 2.8910372147491126,
|
| 1900 |
+
"kl": 0.02074527135118842,
|
| 1901 |
+
"learning_rate": 1.2062093865360457e-07,
|
| 1902 |
+
"loss": 0.0001837483432609588,
|
| 1903 |
+
"step": 125,
|
| 1904 |
+
"step_time": 24.288759532850236
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"clip_ratio/high_max": 0.0026483920228201896,
|
| 1908 |
+
"clip_ratio/high_mean": 0.0008193975081667304,
|
| 1909 |
+
"clip_ratio/low_mean": 0.0001220703125,
|
| 1910 |
+
"clip_ratio/low_min": 0.0,
|
| 1911 |
+
"clip_ratio/region_mean": 0.0009414678206667304,
|
| 1912 |
+
"epoch": 0.7875,
|
| 1913 |
+
"grad_norm": 4.023992774875382,
|
| 1914 |
+
"kl": 0.013820423046126962,
|
| 1915 |
+
"learning_rate": 1.1409819408411897e-07,
|
| 1916 |
+
"loss": 0.00025101564824581146,
|
| 1917 |
+
"step": 126,
|
| 1918 |
+
"step_time": 25.903222512919456
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"clip_ratio/high_max": 0.003107370008365251,
|
| 1922 |
+
"clip_ratio/high_mean": 0.0009863038612820674,
|
| 1923 |
+
"clip_ratio/low_mean": 0.00010162601392949,
|
| 1924 |
+
"clip_ratio/low_min": 0.0,
|
| 1925 |
+
"clip_ratio/region_mean": 0.0010879298752115574,
|
| 1926 |
+
"epoch": 0.79375,
|
| 1927 |
+
"grad_norm": 2.2054708333693167,
|
| 1928 |
+
"kl": 0.010519876144826412,
|
| 1929 |
+
"learning_rate": 1.0773397470829143e-07,
|
| 1930 |
+
"loss": -6.286700954660773e-05,
|
| 1931 |
+
"step": 127,
|
| 1932 |
+
"step_time": 27.158158623147756
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"clip_ratio/high_max": 0.0028547824476845562,
|
| 1936 |
+
"clip_ratio/high_mean": 0.0009664886747486889,
|
| 1937 |
+
"clip_ratio/low_mean": 0.0005482601336552761,
|
| 1938 |
+
"clip_ratio/low_min": 0.0,
|
| 1939 |
+
"clip_ratio/region_mean": 0.0015147487938520499,
|
| 1940 |
+
"epoch": 0.8,
|
| 1941 |
+
"grad_norm": 2.8731813965289015,
|
| 1942 |
+
"kl": 0.021771034924313426,
|
| 1943 |
+
"learning_rate": 1.0153089489354256e-07,
|
| 1944 |
+
"loss": 0.00021373992785811424,
|
| 1945 |
+
"step": 128,
|
| 1946 |
+
"step_time": 20.217902249656618
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"clip_ratio/high_max": 0.0,
|
| 1950 |
+
"clip_ratio/high_mean": 0.0,
|
| 1951 |
+
"clip_ratio/low_mean": 0.0,
|
| 1952 |
+
"clip_ratio/low_min": 0.0,
|
| 1953 |
+
"clip_ratio/region_mean": 0.0,
|
| 1954 |
+
"completions/clipped_ratio": 0.3671875,
|
| 1955 |
+
"completions/max_length": 2048.0,
|
| 1956 |
+
"completions/mean_length": 1286.40234375,
|
| 1957 |
+
"completions/min_length": 64.0,
|
| 1958 |
+
"epoch": 0.80625,
|
| 1959 |
+
"frac_reward_zero_std": 0.34375,
|
| 1960 |
+
"grad_norm": 2.005787772278593,
|
| 1961 |
+
"kl": 0.013114183326251805,
|
| 1962 |
+
"learning_rate": 9.549150281252632e-08,
|
| 1963 |
+
"loss": 0.00013115070760250092,
|
| 1964 |
+
"reward": 0.42578125,
|
| 1965 |
+
"reward_std": 0.29853135347366333,
|
| 1966 |
+
"rewards/MajorityAccuracy/mean": 0.42578125,
|
| 1967 |
+
"rewards/MajorityAccuracy/std": 0.49542948603630066,
|
| 1968 |
+
"step": 129,
|
| 1969 |
+
"step_time": 157.4148386567831
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"clip_ratio/high_max": 0.002138290976290591,
|
| 1973 |
+
"clip_ratio/high_mean": 0.0005618177274300251,
|
| 1974 |
+
"clip_ratio/low_mean": 0.0002288818359375,
|
| 1975 |
+
"clip_ratio/low_min": 0.0,
|
| 1976 |
+
"clip_ratio/region_mean": 0.0007906995633675251,
|
| 1977 |
+
"epoch": 0.8125,
|
| 1978 |
+
"grad_norm": 2.08904212543673,
|
| 1979 |
+
"kl": 0.011717377114109695,
|
| 1980 |
+
"learning_rate": 8.961827939636196e-08,
|
| 1981 |
+
"loss": 8.414518379140645e-05,
|
| 1982 |
+
"step": 130,
|
| 1983 |
+
"step_time": 27.211289812345058
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"clip_ratio/high_max": 0.0018704086833167821,
|
| 1987 |
+
"clip_ratio/high_mean": 0.00046760217082919553,
|
| 1988 |
+
"clip_ratio/low_mean": 0.00010897496395045891,
|
| 1989 |
+
"clip_ratio/low_min": 0.0,
|
| 1990 |
+
"clip_ratio/region_mean": 0.0005765771347796544,
|
| 1991 |
+
"epoch": 0.81875,
|
| 1992 |
+
"grad_norm": 1.2940009841281295,
|
| 1993 |
+
"kl": 0.018802671693265438,
|
| 1994 |
+
"learning_rate": 8.391363731548811e-08,
|
| 1995 |
+
"loss": 0.00041521855746395886,
|
| 1996 |
+
"step": 131,
|
| 1997 |
+
"step_time": 25.663362492341548
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"clip_ratio/high_max": 0.0007809894159436226,
|
| 2001 |
+
"clip_ratio/high_mean": 0.00019524735398590565,
|
| 2002 |
+
"clip_ratio/low_mean": 0.00018310546875,
|
| 2003 |
+
"clip_ratio/low_min": 0.0,
|
| 2004 |
+
"clip_ratio/region_mean": 0.00037835282273590565,
|
| 2005 |
+
"epoch": 0.825,
|
| 2006 |
+
"grad_norm": 2.2659032610450804,
|
| 2007 |
+
"kl": 0.024288598215207458,
|
| 2008 |
+
"learning_rate": 7.837991998855897e-08,
|
| 2009 |
+
"loss": 4.155319766141474e-05,
|
| 2010 |
+
"step": 132,
|
| 2011 |
+
"step_time": 27.127761925105006
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"clip_ratio/high_max": 0.0011635841146926396,
|
| 2015 |
+
"clip_ratio/high_mean": 0.0002908960286731599,
|
| 2016 |
+
"clip_ratio/low_mean": 4.57763671875e-05,
|
| 2017 |
+
"clip_ratio/low_min": 0.0,
|
| 2018 |
+
"clip_ratio/region_mean": 0.0003366723940416705,
|
| 2019 |
+
"epoch": 0.83125,
|
| 2020 |
+
"grad_norm": 1.2027726049012224,
|
| 2021 |
+
"kl": 0.013474109000526369,
|
| 2022 |
+
"learning_rate": 7.301940061978722e-08,
|
| 2023 |
+
"loss": 0.00014812254812568426,
|
| 2024 |
+
"step": 133,
|
| 2025 |
+
"step_time": 27.17989344894886
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"clip_ratio/high_max": 0.0007101523151504807,
|
| 2029 |
+
"clip_ratio/high_mean": 0.00020159504674666096,
|
| 2030 |
+
"clip_ratio/low_mean": 1.52587890625e-05,
|
| 2031 |
+
"clip_ratio/low_min": 0.0,
|
| 2032 |
+
"clip_ratio/region_mean": 0.00021685383580916096,
|
| 2033 |
+
"epoch": 0.8375,
|
| 2034 |
+
"grad_norm": 1.5116612416673314,
|
| 2035 |
+
"kl": 0.014873861568048596,
|
| 2036 |
+
"learning_rate": 6.783428126513125e-08,
|
| 2037 |
+
"loss": 0.0001528908615000546,
|
| 2038 |
+
"step": 134,
|
| 2039 |
+
"step_time": 27.101213085930794
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"clip_ratio/high_max": 0.0006580309564014897,
|
| 2043 |
+
"clip_ratio/high_mean": 0.00016450773910037242,
|
| 2044 |
+
"clip_ratio/low_mean": 0.0004848864300583955,
|
| 2045 |
+
"clip_ratio/low_min": 0.0,
|
| 2046 |
+
"clip_ratio/region_mean": 0.0006493941727967467,
|
| 2047 |
+
"epoch": 0.84375,
|
| 2048 |
+
"grad_norm": 1.2477027167430241,
|
| 2049 |
+
"kl": 0.011218057246878743,
|
| 2050 |
+
"learning_rate": 6.282669192770895e-08,
|
| 2051 |
+
"loss": 0.00038393778959289193,
|
| 2052 |
+
"step": 135,
|
| 2053 |
+
"step_time": 26.775175200775266
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"clip_ratio/high_max": 0.004140779929002747,
|
| 2057 |
+
"clip_ratio/high_mean": 0.001255273753486108,
|
| 2058 |
+
"clip_ratio/low_mean": 0.00021811773513036314,
|
| 2059 |
+
"clip_ratio/low_min": 0.0,
|
| 2060 |
+
"clip_ratio/region_mean": 0.0014733914795215242,
|
| 2061 |
+
"epoch": 0.85,
|
| 2062 |
+
"grad_norm": 2.1301702643809977,
|
| 2063 |
+
"kl": 0.019102163263596594,
|
| 2064 |
+
"learning_rate": 5.799868968281074e-08,
|
| 2065 |
+
"loss": 0.00043929379899054766,
|
| 2066 |
+
"step": 136,
|
| 2067 |
+
"step_time": 25.975405287463218
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"clip_ratio/high_max": 0.0,
|
| 2071 |
+
"clip_ratio/high_mean": 0.0,
|
| 2072 |
+
"clip_ratio/low_mean": 0.0,
|
| 2073 |
+
"clip_ratio/low_min": 0.0,
|
| 2074 |
+
"clip_ratio/region_mean": 0.0,
|
| 2075 |
+
"completions/clipped_ratio": 0.33203125,
|
| 2076 |
+
"completions/max_length": 2048.0,
|
| 2077 |
+
"completions/mean_length": 1311.03125,
|
| 2078 |
+
"completions/min_length": 67.0,
|
| 2079 |
+
"epoch": 0.85625,
|
| 2080 |
+
"frac_reward_zero_std": 0.25,
|
| 2081 |
+
"grad_norm": 2.255772665666545,
|
| 2082 |
+
"kl": 0.012873913627117872,
|
| 2083 |
+
"learning_rate": 5.335225783287051e-08,
|
| 2084 |
+
"loss": 0.00012876844266429543,
|
| 2085 |
+
"reward": 0.42578125,
|
| 2086 |
+
"reward_std": 0.34758201241493225,
|
| 2087 |
+
"rewards/MajorityAccuracy/mean": 0.42578125,
|
| 2088 |
+
"rewards/MajorityAccuracy/std": 0.49542948603630066,
|
| 2089 |
+
"step": 137,
|
| 2090 |
+
"step_time": 156.85262884711847
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"clip_ratio/high_max": 0.0004257223554304801,
|
| 2094 |
+
"clip_ratio/high_mean": 0.00012711225826933514,
|
| 2095 |
+
"clip_ratio/low_mean": 8.404215986956842e-05,
|
| 2096 |
+
"clip_ratio/low_min": 0.0,
|
| 2097 |
+
"clip_ratio/region_mean": 0.00021115441995789297,
|
| 2098 |
+
"epoch": 0.8625,
|
| 2099 |
+
"grad_norm": 1.04314486197749,
|
| 2100 |
+
"kl": 0.010508630773983896,
|
| 2101 |
+
"learning_rate": 4.888930509274125e-08,
|
| 2102 |
+
"loss": 9.008088090922683e-05,
|
| 2103 |
+
"step": 138,
|
| 2104 |
+
"step_time": 27.08571282029152
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"clip_ratio/high_max": 0.001344632742984686,
|
| 2108 |
+
"clip_ratio/high_mean": 0.0004236206514178775,
|
| 2109 |
+
"clip_ratio/low_mean": 0.00025698032914078794,
|
| 2110 |
+
"clip_ratio/low_min": 0.0,
|
| 2111 |
+
"clip_ratio/region_mean": 0.0006806009805586655,
|
| 2112 |
+
"epoch": 0.86875,
|
| 2113 |
+
"grad_norm": 2.40257013655585,
|
| 2114 |
+
"kl": 0.014357224106788635,
|
| 2115 |
+
"learning_rate": 4.4611664805611794e-08,
|
| 2116 |
+
"loss": 0.00025775673566386104,
|
| 2117 |
+
"step": 139,
|
| 2118 |
+
"step_time": 26.750408893916756
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"clip_ratio/high_max": 0.0016461986670037732,
|
| 2122 |
+
"clip_ratio/high_mean": 0.00043469781303429045,
|
| 2123 |
+
"clip_ratio/low_mean": 0.00010915836901403964,
|
| 2124 |
+
"clip_ratio/low_min": 0.0,
|
| 2125 |
+
"clip_ratio/region_mean": 0.0005438561747723725,
|
| 2126 |
+
"epoch": 0.875,
|
| 2127 |
+
"grad_norm": 3.110474449392379,
|
| 2128 |
+
"kl": 0.02077977906446904,
|
| 2129 |
+
"learning_rate": 4.0521094189884696e-08,
|
| 2130 |
+
"loss": 0.00034930527908727527,
|
| 2131 |
+
"step": 140,
|
| 2132 |
+
"step_time": 25.09260071394965
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"clip_ratio/high_max": 0.003080704133026302,
|
| 2136 |
+
"clip_ratio/high_mean": 0.0009358059578516986,
|
| 2137 |
+
"clip_ratio/low_mean": 7.62939453125e-05,
|
| 2138 |
+
"clip_ratio/low_min": 0.0,
|
| 2139 |
+
"clip_ratio/region_mean": 0.0010120999068021774,
|
| 2140 |
+
"epoch": 0.88125,
|
| 2141 |
+
"grad_norm": 1.7054901864903442,
|
| 2142 |
+
"kl": 0.013106250204145908,
|
| 2143 |
+
"learning_rate": 3.6619273617325695e-08,
|
| 2144 |
+
"loss": 0.0001784638297976926,
|
| 2145 |
+
"step": 141,
|
| 2146 |
+
"step_time": 26.974509556312114
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"clip_ratio/high_max": 0.0014546868624165654,
|
| 2150 |
+
"clip_ratio/high_mean": 0.00047080682270461693,
|
| 2151 |
+
"clip_ratio/low_mean": 0.00027407957168179564,
|
| 2152 |
+
"clip_ratio/low_min": 0.0,
|
| 2153 |
+
"clip_ratio/region_mean": 0.0007448863834724762,
|
| 2154 |
+
"epoch": 0.8875,
|
| 2155 |
+
"grad_norm": 1.2133872160915742,
|
| 2156 |
+
"kl": 0.01174894452560693,
|
| 2157 |
+
"learning_rate": 3.2907805922781476e-08,
|
| 2158 |
+
"loss": 4.974424882675521e-05,
|
| 2159 |
+
"step": 142,
|
| 2160 |
+
"step_time": 24.96699824742973
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"clip_ratio/high_max": 0.0009560612525092438,
|
| 2164 |
+
"clip_ratio/high_mean": 0.0003190750830981415,
|
| 2165 |
+
"clip_ratio/low_mean": 0.0004249073681421578,
|
| 2166 |
+
"clip_ratio/low_min": 0.0,
|
| 2167 |
+
"clip_ratio/region_mean": 0.0007439824403263628,
|
| 2168 |
+
"epoch": 0.89375,
|
| 2169 |
+
"grad_norm": 1.6818638897117202,
|
| 2170 |
+
"kl": 0.011891627684235573,
|
| 2171 |
+
"learning_rate": 2.9388215745748345e-08,
|
| 2172 |
+
"loss": -4.013351281173527e-05,
|
| 2173 |
+
"step": 143,
|
| 2174 |
+
"step_time": 27.378150519449264
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"clip_ratio/high_max": 0.006041410699253902,
|
| 2178 |
+
"clip_ratio/high_mean": 0.001546066974697169,
|
| 2179 |
+
"clip_ratio/low_mean": 0.0002160869917133823,
|
| 2180 |
+
"clip_ratio/low_min": 0.0,
|
| 2181 |
+
"clip_ratio/region_mean": 0.0017621539809624664,
|
| 2182 |
+
"epoch": 0.9,
|
| 2183 |
+
"grad_norm": 5.272968502224774,
|
| 2184 |
+
"kl": 0.023750445106998086,
|
| 2185 |
+
"learning_rate": 2.6061948904063658e-08,
|
| 2186 |
+
"loss": 0.0011926210718229413,
|
| 2187 |
+
"step": 144,
|
| 2188 |
+
"step_time": 27.020721114706248
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"clip_ratio/high_max": 0.0,
|
| 2192 |
+
"clip_ratio/high_mean": 0.0,
|
| 2193 |
+
"clip_ratio/low_mean": 0.0,
|
| 2194 |
+
"clip_ratio/low_min": 0.0,
|
| 2195 |
+
"clip_ratio/region_mean": 0.0,
|
| 2196 |
+
"completions/clipped_ratio": 0.328125,
|
| 2197 |
+
"completions/max_length": 2048.0,
|
| 2198 |
+
"completions/mean_length": 1149.6484375,
|
| 2199 |
+
"completions/min_length": 64.0,
|
| 2200 |
+
"epoch": 0.90625,
|
| 2201 |
+
"frac_reward_zero_std": 0.3125,
|
| 2202 |
+
"grad_norm": 1.8738226371034372,
|
| 2203 |
+
"kl": 0.019277071696706116,
|
| 2204 |
+
"learning_rate": 2.293037179997559e-08,
|
| 2205 |
+
"loss": 0.0001928066776599735,
|
| 2206 |
+
"reward": 0.40234375,
|
| 2207 |
+
"reward_std": 0.3061625361442566,
|
| 2208 |
+
"rewards/MajorityAccuracy/mean": 0.40234375,
|
| 2209 |
+
"rewards/MajorityAccuracy/std": 0.4913311004638672,
|
| 2210 |
+
"step": 145,
|
| 2211 |
+
"step_time": 153.19985870318487
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"clip_ratio/high_max": 0.00107973424019292,
|
| 2215 |
+
"clip_ratio/high_mean": 0.00026993356004823,
|
| 2216 |
+
"clip_ratio/low_mean": 8.267681550933048e-05,
|
| 2217 |
+
"clip_ratio/low_min": 0.0,
|
| 2218 |
+
"clip_ratio/region_mean": 0.0003526103755575605,
|
| 2219 |
+
"epoch": 0.9125,
|
| 2220 |
+
"grad_norm": 1.8441153677613775,
|
| 2221 |
+
"kl": 0.01808511232957244,
|
| 2222 |
+
"learning_rate": 1.9994770858837107e-08,
|
| 2223 |
+
"loss": 0.00026482847169972956,
|
| 2224 |
+
"step": 146,
|
| 2225 |
+
"step_time": 26.585303988773376
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"clip_ratio/high_max": 0.0006212723674252629,
|
| 2229 |
+
"clip_ratio/high_mean": 0.00018615183944348246,
|
| 2230 |
+
"clip_ratio/low_mean": 0.00018310546875,
|
| 2231 |
+
"clip_ratio/low_min": 0.0,
|
| 2232 |
+
"clip_ratio/region_mean": 0.00036925730819348246,
|
| 2233 |
+
"epoch": 0.91875,
|
| 2234 |
+
"grad_norm": 1.3246564938802323,
|
| 2235 |
+
"kl": 0.010885267052799463,
|
| 2236 |
+
"learning_rate": 1.725635200065323e-08,
|
| 2237 |
+
"loss": 5.2755574870388955e-05,
|
| 2238 |
+
"step": 147,
|
| 2239 |
+
"step_time": 26.774310589767992
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"clip_ratio/high_max": 0.0011089640320278704,
|
| 2243 |
+
"clip_ratio/high_mean": 0.0003260183220845647,
|
| 2244 |
+
"clip_ratio/low_mean": 0.000152587890625,
|
| 2245 |
+
"clip_ratio/low_min": 0.0,
|
| 2246 |
+
"clip_ratio/region_mean": 0.0004786062127095647,
|
| 2247 |
+
"epoch": 0.925,
|
| 2248 |
+
"grad_norm": 1.2375186794314033,
|
| 2249 |
+
"kl": 0.013374958303757012,
|
| 2250 |
+
"learning_rate": 1.4716240144699187e-08,
|
| 2251 |
+
"loss": 0.0001623814314370975,
|
| 2252 |
+
"step": 148,
|
| 2253 |
+
"step_time": 25.967770383227617
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"clip_ratio/high_max": 0.0010876868764171377,
|
| 2257 |
+
"clip_ratio/high_mean": 0.00036955663017579354,
|
| 2258 |
+
"clip_ratio/low_mean": 0.000274658203125,
|
| 2259 |
+
"clip_ratio/low_min": 0.0,
|
| 2260 |
+
"clip_ratio/region_mean": 0.0006442148369387724,
|
| 2261 |
+
"epoch": 0.93125,
|
| 2262 |
+
"grad_norm": 2.029947709757379,
|
| 2263 |
+
"kl": 0.010261706658639014,
|
| 2264 |
+
"learning_rate": 1.2375478747413015e-08,
|
| 2265 |
+
"loss": 0.0003235442563891411,
|
| 2266 |
+
"step": 149,
|
| 2267 |
+
"step_time": 27.10868100868538
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"clip_ratio/high_max": 0.0033460412596468814,
|
| 2271 |
+
"clip_ratio/high_mean": 0.0011268717807979556,
|
| 2272 |
+
"clip_ratio/low_mean": 0.00011950279076700099,
|
| 2273 |
+
"clip_ratio/low_min": 0.0,
|
| 2274 |
+
"clip_ratio/region_mean": 0.001246374573383946,
|
| 2275 |
+
"epoch": 0.9375,
|
| 2276 |
+
"grad_norm": 3.6271664479085963,
|
| 2277 |
+
"kl": 0.017023048014380038,
|
| 2278 |
+
"learning_rate": 1.0235029373752757e-08,
|
| 2279 |
+
"loss": 5.363486707210541e-05,
|
| 2280 |
+
"step": 150,
|
| 2281 |
+
"step_time": 24.47630182467401
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"clip_ratio/high_max": 0.002445639402139932,
|
| 2285 |
+
"clip_ratio/high_mean": 0.0009227143455063924,
|
| 2286 |
+
"clip_ratio/low_mean": 4.57763671875e-05,
|
| 2287 |
+
"clip_ratio/low_min": 0.0,
|
| 2288 |
+
"clip_ratio/region_mean": 0.0009684907126938924,
|
| 2289 |
+
"epoch": 0.94375,
|
| 2290 |
+
"grad_norm": 1.5020869889680406,
|
| 2291 |
+
"kl": 0.01249236660078168,
|
| 2292 |
+
"learning_rate": 8.295771302193721e-09,
|
| 2293 |
+
"loss": 0.00018033827655017376,
|
| 2294 |
+
"step": 151,
|
| 2295 |
+
"step_time": 26.95716746430844
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"clip_ratio/high_max": 0.001650063284614589,
|
| 2299 |
+
"clip_ratio/high_mean": 0.0004934388325636974,
|
| 2300 |
+
"clip_ratio/low_mean": 0.00019625235290732235,
|
| 2301 |
+
"clip_ratio/low_min": 0.0,
|
| 2302 |
+
"clip_ratio/region_mean": 0.0006896911854710197,
|
| 2303 |
+
"epoch": 0.95,
|
| 2304 |
+
"grad_norm": 1.5739510582678575,
|
| 2305 |
+
"kl": 0.011081037227995694,
|
| 2306 |
+
"learning_rate": 6.558501163527963e-09,
|
| 2307 |
+
"loss": 0.00012614107981789857,
|
| 2308 |
+
"step": 152,
|
| 2309 |
+
"step_time": 27.18557010963559
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"clip_ratio/high_max": 0.0,
|
| 2313 |
+
"clip_ratio/high_mean": 0.0,
|
| 2314 |
+
"clip_ratio/low_mean": 0.0,
|
| 2315 |
+
"clip_ratio/low_min": 0.0,
|
| 2316 |
+
"clip_ratio/region_mean": 0.0,
|
| 2317 |
+
"completions/clipped_ratio": 0.26953125,
|
| 2318 |
+
"completions/max_length": 2048.0,
|
| 2319 |
+
"completions/mean_length": 1150.03125,
|
| 2320 |
+
"completions/min_length": 107.0,
|
| 2321 |
+
"epoch": 0.95625,
|
| 2322 |
+
"frac_reward_zero_std": 0.3125,
|
| 2323 |
+
"grad_norm": 2.5591682855807916,
|
| 2324 |
+
"kl": 0.011543067288585007,
|
| 2325 |
+
"learning_rate": 5.023932613615445e-09,
|
| 2326 |
+
"loss": 0.00011544139124453068,
|
| 2327 |
+
"reward": 0.40234375,
|
| 2328 |
+
"reward_std": 0.3168239891529083,
|
| 2329 |
+
"rewards/MajorityAccuracy/mean": 0.40234375,
|
| 2330 |
+
"rewards/MajorityAccuracy/std": 0.4913311004638672,
|
| 2331 |
+
"step": 153,
|
| 2332 |
+
"step_time": 155.97207239968702
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"clip_ratio/high_max": 0.0005720309636672027,
|
| 2336 |
+
"clip_ratio/high_mean": 0.00014300774091680069,
|
| 2337 |
+
"clip_ratio/low_mean": 0.00026403970332466997,
|
| 2338 |
+
"clip_ratio/low_min": 0.0,
|
| 2339 |
+
"clip_ratio/region_mean": 0.00040704744787944946,
|
| 2340 |
+
"epoch": 0.9625,
|
| 2341 |
+
"grad_norm": 1.2324527599769524,
|
| 2342 |
+
"kl": 0.014179605524986982,
|
| 2343 |
+
"learning_rate": 3.6926960402202666e-09,
|
| 2344 |
+
"loss": 0.00011564690066734329,
|
| 2345 |
+
"step": 154,
|
| 2346 |
+
"step_time": 24.99460589233786
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"clip_ratio/high_max": 0.0016655974905006588,
|
| 2350 |
+
"clip_ratio/high_mean": 0.000445992176537402,
|
| 2351 |
+
"clip_ratio/low_mean": 0.0001138901188824093,
|
| 2352 |
+
"clip_ratio/low_min": 0.0,
|
| 2353 |
+
"clip_ratio/region_mean": 0.0005598822972388007,
|
| 2354 |
+
"epoch": 0.96875,
|
| 2355 |
+
"grad_norm": 1.121351227938532,
|
| 2356 |
+
"kl": 0.016848871717229486,
|
| 2357 |
+
"learning_rate": 2.5653383040524224e-09,
|
| 2358 |
+
"loss": 0.00025989642017520964,
|
| 2359 |
+
"step": 155,
|
| 2360 |
+
"step_time": 26.90376070700586
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"clip_ratio/high_max": 0.002579508742201142,
|
| 2364 |
+
"clip_ratio/high_mean": 0.0007437872736772988,
|
| 2365 |
+
"clip_ratio/low_mean": 0.0006488782237283885,
|
| 2366 |
+
"clip_ratio/low_min": 0.0,
|
| 2367 |
+
"clip_ratio/region_mean": 0.001392665486491751,
|
| 2368 |
+
"epoch": 0.975,
|
| 2369 |
+
"grad_norm": 4.121432624205103,
|
| 2370 |
+
"kl": 0.016875527566298842,
|
| 2371 |
+
"learning_rate": 1.642322514122385e-09,
|
| 2372 |
+
"loss": 0.0011288411915302277,
|
| 2373 |
+
"step": 156,
|
| 2374 |
+
"step_time": 26.19243620382622
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"clip_ratio/high_max": 0.0009874667666736059,
|
| 2378 |
+
"clip_ratio/high_mean": 0.0002783687068586005,
|
| 2379 |
+
"clip_ratio/low_mean": 0.000152587890625,
|
| 2380 |
+
"clip_ratio/low_min": 0.0,
|
| 2381 |
+
"clip_ratio/region_mean": 0.0004309565993025899,
|
| 2382 |
+
"epoch": 0.98125,
|
| 2383 |
+
"grad_norm": 1.2135017968458275,
|
| 2384 |
+
"kl": 0.011579423560760915,
|
| 2385 |
+
"learning_rate": 9.240278374995636e-10,
|
| 2386 |
+
"loss": 2.01210641534999e-05,
|
| 2387 |
+
"step": 157,
|
| 2388 |
+
"step_time": 26.641949845012277
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"clip_ratio/high_max": 0.0024109986115945503,
|
| 2392 |
+
"clip_ratio/high_mean": 0.0006977490229473915,
|
| 2393 |
+
"clip_ratio/low_mean": 0.00024955448134278413,
|
| 2394 |
+
"clip_ratio/low_min": 0.0,
|
| 2395 |
+
"clip_ratio/region_mean": 0.0009473035133851226,
|
| 2396 |
+
"epoch": 0.9875,
|
| 2397 |
+
"grad_norm": 2.246499148973172,
|
| 2398 |
+
"kl": 0.017616624711081386,
|
| 2399 |
+
"learning_rate": 4.1074934355384006e-10,
|
| 2400 |
+
"loss": 0.00015400093980133533,
|
| 2401 |
+
"step": 158,
|
| 2402 |
+
"step_time": 26.87474637059495
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"clip_ratio/high_max": 0.0018625442316988483,
|
| 2406 |
+
"clip_ratio/high_mean": 0.0004656360579247121,
|
| 2407 |
+
"clip_ratio/low_mean": 9.126353870669845e-05,
|
| 2408 |
+
"clip_ratio/low_min": 0.0,
|
| 2409 |
+
"clip_ratio/region_mean": 0.0005568995966314105,
|
| 2410 |
+
"epoch": 0.99375,
|
| 2411 |
+
"grad_norm": 1.5477246558278992,
|
| 2412 |
+
"kl": 0.01950817694887519,
|
| 2413 |
+
"learning_rate": 1.0269788274358537e-10,
|
| 2414 |
+
"loss": 0.00022149967844597995,
|
| 2415 |
+
"step": 159,
|
| 2416 |
+
"step_time": 25.499553514178842
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"clip_ratio/high_max": 0.0012550948158605024,
|
| 2420 |
+
"clip_ratio/high_mean": 0.0003908200415025931,
|
| 2421 |
+
"clip_ratio/low_mean": 0.00026536249060882255,
|
| 2422 |
+
"clip_ratio/low_min": 0.0,
|
| 2423 |
+
"clip_ratio/region_mean": 0.0006561825430253521,
|
| 2424 |
+
"epoch": 1.0,
|
| 2425 |
+
"grad_norm": 2.3621031577198286,
|
| 2426 |
+
"kl": 0.014688356197439134,
|
| 2427 |
+
"learning_rate": 0.0,
|
| 2428 |
+
"loss": -2.161935844924301e-05,
|
| 2429 |
+
"step": 160,
|
| 2430 |
+
"step_time": 26.80869789654389
|
| 2431 |
+
}
|
| 2432 |
+
],
|
| 2433 |
+
"logging_steps": 1,
|
| 2434 |
+
"max_steps": 160,
|
| 2435 |
+
"num_input_tokens_seen": 0,
|
| 2436 |
+
"num_train_epochs": 1,
|
| 2437 |
+
"save_steps": 16,
|
| 2438 |
+
"stateful_callbacks": {
|
| 2439 |
+
"TrainerControl": {
|
| 2440 |
+
"args": {
|
| 2441 |
+
"should_epoch_stop": false,
|
| 2442 |
+
"should_evaluate": false,
|
| 2443 |
+
"should_log": false,
|
| 2444 |
+
"should_save": true,
|
| 2445 |
+
"should_training_stop": true
|
| 2446 |
+
},
|
| 2447 |
+
"attributes": {}
|
| 2448 |
+
}
|
| 2449 |
+
},
|
| 2450 |
+
"total_flos": 0.0,
|
| 2451 |
+
"train_batch_size": 1,
|
| 2452 |
+
"trial_name": null,
|
| 2453 |
+
"trial_params": null
|
| 2454 |
+
}
|