Add a6_coupled_proposer_coder round 2 Solver weights
Browse files- .gitattributes +1 -0
- a6_coupled_proposer_coder/round_2/args.json +556 -0
- a6_coupled_proposer_coder/round_2/chat_template.jinja +154 -0
- a6_coupled_proposer_coder/round_2/config.json +117 -0
- a6_coupled_proposer_coder/round_2/generation_config.json +9 -0
- a6_coupled_proposer_coder/round_2/model-00001-of-00004.safetensors +3 -0
- a6_coupled_proposer_coder/round_2/model-00002-of-00004.safetensors +3 -0
- a6_coupled_proposer_coder/round_2/model-00003-of-00004.safetensors +3 -0
- a6_coupled_proposer_coder/round_2/model-00004-of-00004.safetensors +3 -0
- a6_coupled_proposer_coder/round_2/model.safetensors.index.json +768 -0
- a6_coupled_proposer_coder/round_2/preprocessor_config.json +21 -0
- a6_coupled_proposer_coder/round_2/processor_config.json +61 -0
- a6_coupled_proposer_coder/round_2/tokenizer.json +3 -0
- a6_coupled_proposer_coder/round_2/tokenizer_config.json +33 -0
- a6_coupled_proposer_coder/round_2/trainer_state.json +2454 -0
.gitattributes
CHANGED
|
@@ -66,3 +66,4 @@ a1_api_proposer/round_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 66 |
m2_gpt_answer/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 67 |
m1_proposer_answer/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 68 |
c5_no_curriculum/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 66 |
m2_gpt_answer/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 67 |
m1_proposer_answer/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 68 |
c5_no_curriculum/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
a6_coupled_proposer_coder/round_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
a6_coupled_proposer_coder/round_2/args.json
ADDED
|
@@ -0,0 +1,556 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/data1/xiangding/cvis-ablate/runs/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_002/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/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_002/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/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_002/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/runs/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_001/solver/checkpoint-160",
|
| 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/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_002/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/runs/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_001/solver/checkpoint-160",
|
| 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": "/data1/xiangding/cvis-ablate/runs/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_001/solver/checkpoint-160",
|
| 543 |
+
"rank": 0,
|
| 544 |
+
"global_world_size": 4,
|
| 545 |
+
"local_world_size": 4,
|
| 546 |
+
"model_suffix": "checkpoint-160",
|
| 547 |
+
"model_info": "ModelInfo(model_type='qwen3_5', model_dir='/data1/xiangding/cvis-ablate/runs/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_001/solver/checkpoint-160', 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=None, 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=['vision', 'video'])",
|
| 549 |
+
"model_dir": "/data1/xiangding/cvis-ablate/runs/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_001/solver/checkpoint-160",
|
| 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/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_002/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/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_002/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/a6_coupled_proposer_coder/run_a6_coupled_proposer_coder_4g/iteration_002/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 |
+
}
|
a6_coupled_proposer_coder/round_2/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 %}
|
a6_coupled_proposer_coder/round_2/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 |
+
}
|
a6_coupled_proposer_coder/round_2/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 |
+
}
|
a6_coupled_proposer_coder/round_2/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27ac7682e989c6f1488bdef9197722f168818b7abfa2a50545df33ca51707c05
|
| 3 |
+
size 4942706120
|
a6_coupled_proposer_coder/round_2/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cd340c70f817eb6e26ddc31d51b95142b6a3e0f982c8b3c4224efd839bc8974
|
| 3 |
+
size 4987757928
|
a6_coupled_proposer_coder/round_2/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be9547d2fcb73ba2eaa5862966a197f8d7b6302d978308fe78236167afe80bd6
|
| 3 |
+
size 4954810240
|
a6_coupled_proposer_coder/round_2/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9b592801fd67d90f518459d8b065e171a6b1bf2256d9d2eb3824f7933bbce41
|
| 3 |
+
size 3934446832
|
a6_coupled_proposer_coder/round_2/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 |
+
}
|
a6_coupled_proposer_coder/round_2/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 |
+
}
|
a6_coupled_proposer_coder/round_2/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 |
+
}
|
a6_coupled_proposer_coder/round_2/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
a6_coupled_proposer_coder/round_2/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 |
+
}
|
a6_coupled_proposer_coder/round_2/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": 0.55859375,
|
| 19 |
+
"completions/max_length": 2048.0,
|
| 20 |
+
"completions/mean_length": 1500.96484375,
|
| 21 |
+
"completions/min_length": 100.0,
|
| 22 |
+
"epoch": 0.00625,
|
| 23 |
+
"frac_reward_zero_std": 0.34375,
|
| 24 |
+
"grad_norm": 5.606216833816739,
|
| 25 |
+
"kl": 0.0,
|
| 26 |
+
"learning_rate": 2e-07,
|
| 27 |
+
"loss": -1.30385160446167e-08,
|
| 28 |
+
"reward": 0.1953125,
|
| 29 |
+
"reward_std": 0.27579158544540405,
|
| 30 |
+
"rewards/MajorityAccuracy/mean": 0.1953125,
|
| 31 |
+
"rewards/MajorityAccuracy/std": 0.39721766114234924,
|
| 32 |
+
"step": 1,
|
| 33 |
+
"step_time": 188.3047705278732
|
| 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": 2.8858411638232995,
|
| 43 |
+
"kl": 0.0,
|
| 44 |
+
"learning_rate": 4e-07,
|
| 45 |
+
"loss": 1.4901161193847656e-08,
|
| 46 |
+
"step": 2,
|
| 47 |
+
"step_time": 21.914557746611536
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"clip_ratio/high_max": 0.0011214078112971038,
|
| 51 |
+
"clip_ratio/high_mean": 0.00028035195282427594,
|
| 52 |
+
"clip_ratio/low_mean": 0.00024866584863048047,
|
| 53 |
+
"clip_ratio/low_min": 0.0,
|
| 54 |
+
"clip_ratio/region_mean": 0.0005290178014547564,
|
| 55 |
+
"epoch": 0.01875,
|
| 56 |
+
"grad_norm": 2.0712591760467776,
|
| 57 |
+
"kl": 0.00019004343630513176,
|
| 58 |
+
"learning_rate": 6e-07,
|
| 59 |
+
"loss": 2.7212226996198297e-05,
|
| 60 |
+
"step": 3,
|
| 61 |
+
"step_time": 26.4460611497052
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"clip_ratio/high_max": 0.0008793409942882136,
|
| 65 |
+
"clip_ratio/high_mean": 0.0002198352485720534,
|
| 66 |
+
"clip_ratio/low_mean": 0.00013836271682521328,
|
| 67 |
+
"clip_ratio/low_min": 0.0,
|
| 68 |
+
"clip_ratio/region_mean": 0.00035819796175928786,
|
| 69 |
+
"epoch": 0.025,
|
| 70 |
+
"grad_norm": 1.823347226310293,
|
| 71 |
+
"kl": 0.00016133543613250367,
|
| 72 |
+
"learning_rate": 8e-07,
|
| 73 |
+
"loss": 3.433595702517778e-05,
|
| 74 |
+
"step": 4,
|
| 75 |
+
"step_time": 26.756933300755918
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"clip_ratio/high_max": 0.0006123507337179035,
|
| 79 |
+
"clip_ratio/high_mean": 0.00015308768342947587,
|
| 80 |
+
"clip_ratio/low_mean": 0.0003592419161577709,
|
| 81 |
+
"clip_ratio/low_min": 0.0,
|
| 82 |
+
"clip_ratio/region_mean": 0.0005123295995872468,
|
| 83 |
+
"epoch": 0.03125,
|
| 84 |
+
"grad_norm": 0.8983853750665316,
|
| 85 |
+
"kl": 0.00029941538014099933,
|
| 86 |
+
"learning_rate": 1e-06,
|
| 87 |
+
"loss": -6.004293481964851e-06,
|
| 88 |
+
"step": 5,
|
| 89 |
+
"step_time": 26.771767162252218
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"clip_ratio/high_max": 0.0010746239277068526,
|
| 93 |
+
"clip_ratio/high_mean": 0.00026865598192671314,
|
| 94 |
+
"clip_ratio/low_mean": 0.00034362523183517624,
|
| 95 |
+
"clip_ratio/low_min": 0.0,
|
| 96 |
+
"clip_ratio/region_mean": 0.0006122812064859318,
|
| 97 |
+
"epoch": 0.0375,
|
| 98 |
+
"grad_norm": 1.4609586330663038,
|
| 99 |
+
"kl": 0.0002043519307335373,
|
| 100 |
+
"learning_rate": 9.998973021172564e-07,
|
| 101 |
+
"loss": 0.00013339650467969477,
|
| 102 |
+
"step": 6,
|
| 103 |
+
"step_time": 26.78730608150363
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"clip_ratio/high_max": 0.00036231885314919055,
|
| 107 |
+
"clip_ratio/high_mean": 9.057971328729764e-05,
|
| 108 |
+
"clip_ratio/low_mean": 0.0004754894252982922,
|
| 109 |
+
"clip_ratio/low_min": 0.0,
|
| 110 |
+
"clip_ratio/region_mean": 0.0005660691313096322,
|
| 111 |
+
"epoch": 0.04375,
|
| 112 |
+
"grad_norm": 3.6345174835076377,
|
| 113 |
+
"kl": 0.0002829275981639512,
|
| 114 |
+
"learning_rate": 9.99589250656446e-07,
|
| 115 |
+
"loss": -1.9399418306420557e-05,
|
| 116 |
+
"step": 7,
|
| 117 |
+
"step_time": 26.780210436321795
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"clip_ratio/high_max": 0.0004025764937978238,
|
| 121 |
+
"clip_ratio/high_mean": 0.00013528935960493982,
|
| 122 |
+
"clip_ratio/low_mean": 0.0006467565617640503,
|
| 123 |
+
"clip_ratio/low_min": 0.0,
|
| 124 |
+
"clip_ratio/region_mean": 0.0007820459213689901,
|
| 125 |
+
"epoch": 0.05,
|
| 126 |
+
"grad_norm": 1.5758506923113982,
|
| 127 |
+
"kl": 0.0002531753107177792,
|
| 128 |
+
"learning_rate": 9.990759721625005e-07,
|
| 129 |
+
"loss": 1.957474887603894e-05,
|
| 130 |
+
"step": 8,
|
| 131 |
+
"step_time": 26.749734894372523
|
| 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": 0.51171875,
|
| 140 |
+
"completions/max_length": 2048.0,
|
| 141 |
+
"completions/mean_length": 1456.70703125,
|
| 142 |
+
"completions/min_length": 72.0,
|
| 143 |
+
"epoch": 0.05625,
|
| 144 |
+
"frac_reward_zero_std": 0.28125,
|
| 145 |
+
"grad_norm": 1.848997910048643,
|
| 146 |
+
"kl": 0.0002843823876901297,
|
| 147 |
+
"learning_rate": 9.983576774858775e-07,
|
| 148 |
+
"loss": 2.844084519892931e-06,
|
| 149 |
+
"reward": 0.27734375,
|
| 150 |
+
"reward_std": 0.33022910356521606,
|
| 151 |
+
"rewards/MajorityAccuracy/mean": 0.27734375,
|
| 152 |
+
"rewards/MajorityAccuracy/std": 0.4485645592212677,
|
| 153 |
+
"step": 9,
|
| 154 |
+
"step_time": 160.49761400232092
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"clip_ratio/high_max": 0.00414698343956843,
|
| 158 |
+
"clip_ratio/high_mean": 0.0010914744198089465,
|
| 159 |
+
"clip_ratio/low_mean": 0.0003975718227593461,
|
| 160 |
+
"clip_ratio/low_min": 0.0,
|
| 161 |
+
"clip_ratio/region_mean": 0.0014890462298353668,
|
| 162 |
+
"epoch": 0.0625,
|
| 163 |
+
"grad_norm": 3.097236156277033,
|
| 164 |
+
"kl": 0.000804823954240419,
|
| 165 |
+
"learning_rate": 9.974346616959475e-07,
|
| 166 |
+
"loss": -0.00014529936015605927,
|
| 167 |
+
"step": 10,
|
| 168 |
+
"step_time": 25.866033430676907
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"clip_ratio/high_max": 0.005964272044366226,
|
| 172 |
+
"clip_ratio/high_mean": 0.0017303042695857584,
|
| 173 |
+
"clip_ratio/low_mean": 0.0005826283013448119,
|
| 174 |
+
"clip_ratio/low_min": 0.0,
|
| 175 |
+
"clip_ratio/region_mean": 0.0023129325272748247,
|
| 176 |
+
"epoch": 0.06875,
|
| 177 |
+
"grad_norm": 2.8047182887656072,
|
| 178 |
+
"kl": 0.0008858921064529568,
|
| 179 |
+
"learning_rate": 9.963073039597796e-07,
|
| 180 |
+
"loss": -0.000382905884180218,
|
| 181 |
+
"step": 11,
|
| 182 |
+
"step_time": 25.9280865075998
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"clip_ratio/high_max": 0.002156771282898262,
|
| 186 |
+
"clip_ratio/high_mean": 0.0005649129816447385,
|
| 187 |
+
"clip_ratio/low_mean": 0.0005683501804014668,
|
| 188 |
+
"clip_ratio/low_min": 0.0,
|
| 189 |
+
"clip_ratio/region_mean": 0.0011332631620462053,
|
| 190 |
+
"epoch": 0.075,
|
| 191 |
+
"grad_norm": 1.7117844290295556,
|
| 192 |
+
"kl": 0.0006930714444024488,
|
| 193 |
+
"learning_rate": 9.949760673863846e-07,
|
| 194 |
+
"loss": 2.271088305860758e-06,
|
| 195 |
+
"step": 12,
|
| 196 |
+
"step_time": 26.355137751437724
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"clip_ratio/high_max": 0.0016437756858067587,
|
| 200 |
+
"clip_ratio/high_mean": 0.0004109439214516897,
|
| 201 |
+
"clip_ratio/low_mean": 0.0008071603733696975,
|
| 202 |
+
"clip_ratio/low_min": 0.0,
|
| 203 |
+
"clip_ratio/region_mean": 0.0012181042911834083,
|
| 204 |
+
"epoch": 0.08125,
|
| 205 |
+
"grad_norm": 1.677749987057057,
|
| 206 |
+
"kl": 0.0012578831010614522,
|
| 207 |
+
"learning_rate": 9.934414988364722e-07,
|
| 208 |
+
"loss": 0.0006382485735230148,
|
| 209 |
+
"step": 13,
|
| 210 |
+
"step_time": 26.6077218381688
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"clip_ratio/high_max": 0.0023538769164588302,
|
| 214 |
+
"clip_ratio/high_mean": 0.0006793783177272417,
|
| 215 |
+
"clip_ratio/low_mean": 0.0008690931063028984,
|
| 216 |
+
"clip_ratio/low_min": 0.0,
|
| 217 |
+
"clip_ratio/region_mean": 0.00154847142403014,
|
| 218 |
+
"epoch": 0.0875,
|
| 219 |
+
"grad_norm": 1.2112176722658297,
|
| 220 |
+
"kl": 0.0008604066169937141,
|
| 221 |
+
"learning_rate": 9.917042286978063e-07,
|
| 222 |
+
"loss": 8.709612302482128e-06,
|
| 223 |
+
"step": 14,
|
| 224 |
+
"step_time": 26.86326644057408
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"clip_ratio/high_max": 0.010847579396795481,
|
| 228 |
+
"clip_ratio/high_mean": 0.003078306937823072,
|
| 229 |
+
"clip_ratio/low_mean": 0.0015184328949544579,
|
| 230 |
+
"clip_ratio/low_min": 0.0,
|
| 231 |
+
"clip_ratio/region_mean": 0.0045967398036736995,
|
| 232 |
+
"epoch": 0.09375,
|
| 233 |
+
"grad_norm": 1.8372293190043518,
|
| 234 |
+
"kl": 0.0018305524572497234,
|
| 235 |
+
"learning_rate": 9.897649706262473e-07,
|
| 236 |
+
"loss": 0.0003731796459760517,
|
| 237 |
+
"step": 15,
|
| 238 |
+
"step_time": 26.79696254245937
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"clip_ratio/high_max": 0.0016473372816108167,
|
| 242 |
+
"clip_ratio/high_mean": 0.0004118343204027042,
|
| 243 |
+
"clip_ratio/low_mean": 0.002369589783484116,
|
| 244 |
+
"clip_ratio/low_min": 0.00079345703125,
|
| 245 |
+
"clip_ratio/region_mean": 0.0027814240602310747,
|
| 246 |
+
"epoch": 0.1,
|
| 247 |
+
"grad_norm": 1.7135356442492398,
|
| 248 |
+
"kl": 0.001052375380822923,
|
| 249 |
+
"learning_rate": 9.87624521252587e-07,
|
| 250 |
+
"loss": 0.00013452116400003433,
|
| 251 |
+
"step": 16,
|
| 252 |
+
"step_time": 26.44436268787831
|
| 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": 0.35546875,
|
| 261 |
+
"completions/max_length": 2048.0,
|
| 262 |
+
"completions/mean_length": 1222.75390625,
|
| 263 |
+
"completions/min_length": 97.0,
|
| 264 |
+
"epoch": 0.10625,
|
| 265 |
+
"frac_reward_zero_std": 0.1875,
|
| 266 |
+
"grad_norm": 3.6913227412595555,
|
| 267 |
+
"kl": 0.002803802053676918,
|
| 268 |
+
"learning_rate": 9.852837598553008e-07,
|
| 269 |
+
"loss": 2.805795520544052e-05,
|
| 270 |
+
"reward": 0.375,
|
| 271 |
+
"reward_std": 0.3628467619419098,
|
| 272 |
+
"rewards/MajorityAccuracy/mean": 0.375,
|
| 273 |
+
"rewards/MajorityAccuracy/std": 0.48507124185562134,
|
| 274 |
+
"step": 17,
|
| 275 |
+
"step_time": 151.84617505734786
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"clip_ratio/high_max": 0.0010267960897181183,
|
| 279 |
+
"clip_ratio/high_mean": 0.0002566990224295296,
|
| 280 |
+
"clip_ratio/low_mean": 0.0004286053153919056,
|
| 281 |
+
"clip_ratio/low_min": 0.0,
|
| 282 |
+
"clip_ratio/region_mean": 0.0006853043450973928,
|
| 283 |
+
"epoch": 0.1125,
|
| 284 |
+
"grad_norm": 1.4832971820836114,
|
| 285 |
+
"kl": 0.002057682242593728,
|
| 286 |
+
"learning_rate": 9.827436479993468e-07,
|
| 287 |
+
"loss": 0.0001626464945729822,
|
| 288 |
+
"step": 18,
|
| 289 |
+
"step_time": 26.30122840544209
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"clip_ratio/high_max": 0.004369564747321419,
|
| 293 |
+
"clip_ratio/high_mean": 0.0013230562944954727,
|
| 294 |
+
"clip_ratio/low_mean": 0.00019308950868435204,
|
| 295 |
+
"clip_ratio/low_min": 0.0,
|
| 296 |
+
"clip_ratio/region_mean": 0.0015161457849899307,
|
| 297 |
+
"epoch": 0.11875,
|
| 298 |
+
"grad_norm": 2.386755391380956,
|
| 299 |
+
"kl": 0.001902339659864083,
|
| 300 |
+
"learning_rate": 9.800052291411629e-07,
|
| 301 |
+
"loss": 0.00016830956155899912,
|
| 302 |
+
"step": 19,
|
| 303 |
+
"step_time": 24.516152495983988
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"clip_ratio/high_max": 0.002162047749152407,
|
| 307 |
+
"clip_ratio/high_mean": 0.0005405119372881018,
|
| 308 |
+
"clip_ratio/low_mean": 0.0005175533297006041,
|
| 309 |
+
"clip_ratio/low_min": 0.0,
|
| 310 |
+
"clip_ratio/region_mean": 0.0010580652597127482,
|
| 311 |
+
"epoch": 0.125,
|
| 312 |
+
"grad_norm": 1.1972550842877163,
|
| 313 |
+
"kl": 0.0016788062785053626,
|
| 314 |
+
"learning_rate": 9.770696282000244e-07,
|
| 315 |
+
"loss": -7.235071825562045e-05,
|
| 316 |
+
"step": 20,
|
| 317 |
+
"step_time": 26.694823323749006
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"clip_ratio/high_max": 0.007129688689019531,
|
| 321 |
+
"clip_ratio/high_mean": 0.0019381948368391022,
|
| 322 |
+
"clip_ratio/low_mean": 0.0017156466346932575,
|
| 323 |
+
"clip_ratio/low_min": 0.0,
|
| 324 |
+
"clip_ratio/region_mean": 0.00365384150063619,
|
| 325 |
+
"epoch": 0.13125,
|
| 326 |
+
"grad_norm": 2.962230691458331,
|
| 327 |
+
"kl": 0.0027328344294801354,
|
| 328 |
+
"learning_rate": 9.739380510959364e-07,
|
| 329 |
+
"loss": 0.00018247030675411224,
|
| 330 |
+
"step": 21,
|
| 331 |
+
"step_time": 26.129148083738983
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"clip_ratio/high_max": 0.0032285885245073587,
|
| 335 |
+
"clip_ratio/high_mean": 0.0008071471311268397,
|
| 336 |
+
"clip_ratio/low_mean": 0.0013540890213334933,
|
| 337 |
+
"clip_ratio/low_min": 0.0,
|
| 338 |
+
"clip_ratio/region_mean": 0.00216123613063246,
|
| 339 |
+
"epoch": 0.1375,
|
| 340 |
+
"grad_norm": 1.1382487634226954,
|
| 341 |
+
"kl": 0.002182609139708802,
|
| 342 |
+
"learning_rate": 9.706117842542516e-07,
|
| 343 |
+
"loss": 0.00015502178575843573,
|
| 344 |
+
"step": 22,
|
| 345 |
+
"step_time": 26.758186707273126
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"clip_ratio/high_max": 0.012339980050455779,
|
| 349 |
+
"clip_ratio/high_mean": 0.00546514370944351,
|
| 350 |
+
"clip_ratio/low_mean": 0.0029569870966952294,
|
| 351 |
+
"clip_ratio/low_min": 0.0,
|
| 352 |
+
"clip_ratio/region_mean": 0.00842213089345023,
|
| 353 |
+
"epoch": 0.14375,
|
| 354 |
+
"grad_norm": 3.0978291823786472,
|
| 355 |
+
"kl": 0.004071180184837431,
|
| 356 |
+
"learning_rate": 9.670921940772186e-07,
|
| 357 |
+
"loss": 1.9820407032966614e-05,
|
| 358 |
+
"step": 23,
|
| 359 |
+
"step_time": 22.204594512935728
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"clip_ratio/high_max": 0.007348174345679581,
|
| 363 |
+
"clip_ratio/high_mean": 0.002356355165829882,
|
| 364 |
+
"clip_ratio/low_mean": 0.0017242431640625,
|
| 365 |
+
"clip_ratio/low_min": 0.0,
|
| 366 |
+
"clip_ratio/region_mean": 0.0040805983589962125,
|
| 367 |
+
"epoch": 0.15,
|
| 368 |
+
"grad_norm": 2.1625817120905424,
|
| 369 |
+
"kl": 0.002910216018790379,
|
| 370 |
+
"learning_rate": 9.633807263826744e-07,
|
| 371 |
+
"loss": 0.0002314932644367218,
|
| 372 |
+
"step": 24,
|
| 373 |
+
"step_time": 26.789689438417554
|
| 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": 0.33203125,
|
| 382 |
+
"completions/max_length": 2048.0,
|
| 383 |
+
"completions/mean_length": 1109.5546875,
|
| 384 |
+
"completions/min_length": 61.0,
|
| 385 |
+
"epoch": 0.15625,
|
| 386 |
+
"frac_reward_zero_std": 0.28125,
|
| 387 |
+
"grad_norm": 3.77080168911558,
|
| 388 |
+
"kl": 0.003946406621253118,
|
| 389 |
+
"learning_rate": 9.594789058101153e-07,
|
| 390 |
+
"loss": 3.951125836465508e-05,
|
| 391 |
+
"reward": 0.4375,
|
| 392 |
+
"reward_std": 0.3262837529182434,
|
| 393 |
+
"rewards/MajorityAccuracy/mean": 0.4375,
|
| 394 |
+
"rewards/MajorityAccuracy/std": 0.49705013632774353,
|
| 395 |
+
"step": 25,
|
| 396 |
+
"step_time": 152.30702430848032
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"clip_ratio/high_max": 0.0014224967962945811,
|
| 400 |
+
"clip_ratio/high_mean": 0.0003556241990736453,
|
| 401 |
+
"clip_ratio/low_mean": 0.00023462018725695089,
|
| 402 |
+
"clip_ratio/low_min": 0.0,
|
| 403 |
+
"clip_ratio/region_mean": 0.000590244399063522,
|
| 404 |
+
"epoch": 0.1625,
|
| 405 |
+
"grad_norm": 1.639240016810571,
|
| 406 |
+
"kl": 0.003188775066519156,
|
| 407 |
+
"learning_rate": 9.55388335194388e-07,
|
| 408 |
+
"loss": 0.00015970671665854752,
|
| 409 |
+
"step": 26,
|
| 410 |
+
"step_time": 26.403241040650755
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"clip_ratio/high_max": 0.006476871581980959,
|
| 414 |
+
"clip_ratio/high_mean": 0.0016192178954952396,
|
| 415 |
+
"clip_ratio/low_mean": 0.0021940421138424426,
|
| 416 |
+
"clip_ratio/low_min": 0.0,
|
| 417 |
+
"clip_ratio/region_mean": 0.0038132600384415127,
|
| 418 |
+
"epoch": 0.16875,
|
| 419 |
+
"grad_norm": 9.865994962012495,
|
| 420 |
+
"kl": 0.005572378431679681,
|
| 421 |
+
"learning_rate": 9.511106949072587e-07,
|
| 422 |
+
"loss": -0.00011062673002015799,
|
| 423 |
+
"step": 27,
|
| 424 |
+
"step_time": 26.810135214123875
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"clip_ratio/high_max": 0.0014107222741586156,
|
| 428 |
+
"clip_ratio/high_mean": 0.00041214774137188215,
|
| 429 |
+
"clip_ratio/low_mean": 0.0006901289234519936,
|
| 430 |
+
"clip_ratio/low_min": 0.0,
|
| 431 |
+
"clip_ratio/region_mean": 0.0011022766575479181,
|
| 432 |
+
"epoch": 0.175,
|
| 433 |
+
"grad_norm": 2.9122241397074493,
|
| 434 |
+
"kl": 0.003556526731699705,
|
| 435 |
+
"learning_rate": 9.466477421671295e-07,
|
| 436 |
+
"loss": 0.00046713478513993323,
|
| 437 |
+
"step": 28,
|
| 438 |
+
"step_time": 26.751307879574597
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"clip_ratio/high_max": 0.0018441977153997868,
|
| 442 |
+
"clip_ratio/high_mean": 0.0005146514959051274,
|
| 443 |
+
"clip_ratio/low_mean": 0.0005621426098514348,
|
| 444 |
+
"clip_ratio/low_min": 0.0,
|
| 445 |
+
"clip_ratio/region_mean": 0.0010767941057565622,
|
| 446 |
+
"epoch": 0.18125,
|
| 447 |
+
"grad_norm": 1.90597811825541,
|
| 448 |
+
"kl": 0.004041846230393276,
|
| 449 |
+
"learning_rate": 9.420013103171891e-07,
|
| 450 |
+
"loss": 4.3206902773818e-05,
|
| 451 |
+
"step": 29,
|
| 452 |
+
"step_time": 24.068083395715803
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"clip_ratio/high_max": 0.005297821102431044,
|
| 456 |
+
"clip_ratio/high_mean": 0.0024777951039141044,
|
| 457 |
+
"clip_ratio/low_mean": 0.0015091607492649928,
|
| 458 |
+
"clip_ratio/low_min": 0.0,
|
| 459 |
+
"clip_ratio/region_mean": 0.003986955882282928,
|
| 460 |
+
"epoch": 0.1875,
|
| 461 |
+
"grad_norm": 1.948735237086094,
|
| 462 |
+
"kl": 0.005695960659068078,
|
| 463 |
+
"learning_rate": 9.37173308072291e-07,
|
| 464 |
+
"loss": 0.00012545660138130188,
|
| 465 |
+
"step": 30,
|
| 466 |
+
"step_time": 24.902542410884053
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"clip_ratio/high_max": 0.0020691311510745436,
|
| 470 |
+
"clip_ratio/high_mean": 0.000654463168757502,
|
| 471 |
+
"clip_ratio/low_mean": 0.001482179097365588,
|
| 472 |
+
"clip_ratio/low_min": 0.0,
|
| 473 |
+
"clip_ratio/region_mean": 0.002136642229743302,
|
| 474 |
+
"epoch": 0.19375,
|
| 475 |
+
"grad_norm": 1.7888438062682717,
|
| 476 |
+
"kl": 0.0033993063552770764,
|
| 477 |
+
"learning_rate": 9.321657187348688e-07,
|
| 478 |
+
"loss": 0.000337365287123248,
|
| 479 |
+
"step": 31,
|
| 480 |
+
"step_time": 26.817734819836915
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"clip_ratio/high_max": 0.012905410840176046,
|
| 484 |
+
"clip_ratio/high_mean": 0.0035803111386485398,
|
| 485 |
+
"clip_ratio/low_mean": 0.0031122632790356874,
|
| 486 |
+
"clip_ratio/low_min": 0.0,
|
| 487 |
+
"clip_ratio/region_mean": 0.006692574446788058,
|
| 488 |
+
"epoch": 0.2,
|
| 489 |
+
"grad_norm": 5.483962841577457,
|
| 490 |
+
"kl": 0.00826801307266578,
|
| 491 |
+
"learning_rate": 9.269805993802128e-07,
|
| 492 |
+
"loss": 0.0013441529590636492,
|
| 493 |
+
"step": 32,
|
| 494 |
+
"step_time": 26.802312726620585
|
| 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": 0.3984375,
|
| 503 |
+
"completions/max_length": 2048.0,
|
| 504 |
+
"completions/mean_length": 1246.44921875,
|
| 505 |
+
"completions/min_length": 87.0,
|
| 506 |
+
"epoch": 0.20625,
|
| 507 |
+
"frac_reward_zero_std": 0.3125,
|
| 508 |
+
"grad_norm": 3.169668118657378,
|
| 509 |
+
"kl": 0.010077673417981714,
|
| 510 |
+
"learning_rate": 9.216200800114411e-07,
|
| 511 |
+
"loss": 0.00010073660087073222,
|
| 512 |
+
"reward": 0.3828125,
|
| 513 |
+
"reward_std": 0.3152327537536621,
|
| 514 |
+
"rewards/MajorityAccuracy/mean": 0.3828125,
|
| 515 |
+
"rewards/MajorityAccuracy/std": 0.48702529072761536,
|
| 516 |
+
"step": 33,
|
| 517 |
+
"step_time": 152.06181476358324
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"clip_ratio/high_max": 6.459948053816333e-05,
|
| 521 |
+
"clip_ratio/high_mean": 1.6149870134540834e-05,
|
| 522 |
+
"clip_ratio/low_mean": 0.0001068115234375,
|
| 523 |
+
"clip_ratio/low_min": 0.0,
|
| 524 |
+
"clip_ratio/region_mean": 0.00012296139357204083,
|
| 525 |
+
"epoch": 0.2125,
|
| 526 |
+
"grad_norm": 0.6861516335737141,
|
| 527 |
+
"kl": 0.00507284258492291,
|
| 528 |
+
"learning_rate": 9.160863626845119e-07,
|
| 529 |
+
"loss": 0.00014806532999500632,
|
| 530 |
+
"step": 34,
|
| 531 |
+
"step_time": 26.781272462103516
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"clip_ratio/high_max": 0.002991562672832515,
|
| 535 |
+
"clip_ratio/high_mean": 0.0010348239375161938,
|
| 536 |
+
"clip_ratio/low_mean": 0.0006685301850666292,
|
| 537 |
+
"clip_ratio/low_min": 0.0,
|
| 538 |
+
"clip_ratio/region_mean": 0.0017033541444106959,
|
| 539 |
+
"epoch": 0.21875,
|
| 540 |
+
"grad_norm": 2.359441074499187,
|
| 541 |
+
"kl": 0.006358291779179126,
|
| 542 |
+
"learning_rate": 9.103817206036382e-07,
|
| 543 |
+
"loss": 0.00010046921670436859,
|
| 544 |
+
"step": 35,
|
| 545 |
+
"step_time": 25.782065051142126
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"clip_ratio/high_max": 0.0030526511691277847,
|
| 549 |
+
"clip_ratio/high_mean": 0.0009634044727135915,
|
| 550 |
+
"clip_ratio/low_mean": 0.0008805488760117441,
|
| 551 |
+
"clip_ratio/low_min": 0.0,
|
| 552 |
+
"clip_ratio/region_mean": 0.0018439533887431026,
|
| 553 |
+
"epoch": 0.225,
|
| 554 |
+
"grad_norm": 1.865147848388159,
|
| 555 |
+
"kl": 0.004987034248188138,
|
| 556 |
+
"learning_rate": 9.045084971874737e-07,
|
| 557 |
+
"loss": 0.0005342373042367399,
|
| 558 |
+
"step": 36,
|
| 559 |
+
"step_time": 26.772400795016438
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"clip_ratio/high_max": 0.009818466089200228,
|
| 563 |
+
"clip_ratio/high_mean": 0.0025935054145520553,
|
| 564 |
+
"clip_ratio/low_mean": 0.000924560910789296,
|
| 565 |
+
"clip_ratio/low_min": 0.0,
|
| 566 |
+
"clip_ratio/region_mean": 0.0035180663398932666,
|
| 567 |
+
"epoch": 0.23125,
|
| 568 |
+
"grad_norm": 3.052036002016119,
|
| 569 |
+
"kl": 0.00815884192707017,
|
| 570 |
+
"learning_rate": 8.984691051064574e-07,
|
| 571 |
+
"loss": 0.0006334966165013611,
|
| 572 |
+
"step": 37,
|
| 573 |
+
"step_time": 24.93086431734264
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"clip_ratio/high_max": 0.004491944229812361,
|
| 577 |
+
"clip_ratio/high_mean": 0.0013099921961838845,
|
| 578 |
+
"clip_ratio/low_mean": 0.0008559208035876509,
|
| 579 |
+
"clip_ratio/low_min": 0.0,
|
| 580 |
+
"clip_ratio/region_mean": 0.002165913007047493,
|
| 581 |
+
"epoch": 0.2375,
|
| 582 |
+
"grad_norm": 1.823211299879544,
|
| 583 |
+
"kl": 0.004164570942521095,
|
| 584 |
+
"learning_rate": 8.922660252917087e-07,
|
| 585 |
+
"loss": 0.00021481674048118293,
|
| 586 |
+
"step": 38,
|
| 587 |
+
"step_time": 26.52237160364166
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"clip_ratio/high_max": 0.005656240216922015,
|
| 591 |
+
"clip_ratio/high_mean": 0.001479164231568575,
|
| 592 |
+
"clip_ratio/low_mean": 0.0007960840812302195,
|
| 593 |
+
"clip_ratio/low_min": 0.0,
|
| 594 |
+
"clip_ratio/region_mean": 0.0022752483273507096,
|
| 595 |
+
"epoch": 0.24375,
|
| 596 |
+
"grad_norm": 2.9158427456776295,
|
| 597 |
+
"kl": 0.0051297046593390405,
|
| 598 |
+
"learning_rate": 8.859018059158809e-07,
|
| 599 |
+
"loss": 0.0006599152111448348,
|
| 600 |
+
"step": 39,
|
| 601 |
+
"step_time": 26.954755610320717
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"clip_ratio/high_max": 0.010580504545941949,
|
| 605 |
+
"clip_ratio/high_mean": 0.00323787669185549,
|
| 606 |
+
"clip_ratio/low_mean": 0.0009405654418515041,
|
| 607 |
+
"clip_ratio/low_min": 0.0,
|
| 608 |
+
"clip_ratio/region_mean": 0.00417844214825891,
|
| 609 |
+
"epoch": 0.25,
|
| 610 |
+
"grad_norm": 1.6960375317750764,
|
| 611 |
+
"kl": 0.008956166391726583,
|
| 612 |
+
"learning_rate": 8.793790613463954e-07,
|
| 613 |
+
"loss": 4.2109018977498636e-05,
|
| 614 |
+
"step": 40,
|
| 615 |
+
"step_time": 24.503174461890012
|
| 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": 0.484375,
|
| 624 |
+
"completions/max_length": 2048.0,
|
| 625 |
+
"completions/mean_length": 1414.3203125,
|
| 626 |
+
"completions/min_length": 76.0,
|
| 627 |
+
"epoch": 0.25625,
|
| 628 |
+
"frac_reward_zero_std": 0.375,
|
| 629 |
+
"grad_norm": 3.07688434855189,
|
| 630 |
+
"kl": 0.006781678122933954,
|
| 631 |
+
"learning_rate": 8.727004710714798e-07,
|
| 632 |
+
"loss": 6.781477713957429e-05,
|
| 633 |
+
"reward": 0.33984375,
|
| 634 |
+
"reward_std": 0.2760535776615143,
|
| 635 |
+
"rewards/MajorityAccuracy/mean": 0.33984375,
|
| 636 |
+
"rewards/MajorityAccuracy/std": 0.47458380460739136,
|
| 637 |
+
"step": 41,
|
| 638 |
+
"step_time": 164.43104731244966
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"clip_ratio/high_max": 0.0013421416806522757,
|
| 642 |
+
"clip_ratio/high_mean": 0.0003355354201630689,
|
| 643 |
+
"clip_ratio/low_mean": 0.00011169746539962944,
|
| 644 |
+
"clip_ratio/low_min": 0.0,
|
| 645 |
+
"clip_ratio/region_mean": 0.00044723288556269836,
|
| 646 |
+
"epoch": 0.2625,
|
| 647 |
+
"grad_norm": 0.9108995180233442,
|
| 648 |
+
"kl": 0.009245068300515413,
|
| 649 |
+
"learning_rate": 8.658687785994578e-07,
|
| 650 |
+
"loss": 0.0001063594245351851,
|
| 651 |
+
"step": 42,
|
| 652 |
+
"step_time": 26.777657305356115
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"clip_ratio/high_max": 0.0015448476042365655,
|
| 656 |
+
"clip_ratio/high_mean": 0.00044228929255041294,
|
| 657 |
+
"clip_ratio/low_mean": 0.00035024758290091995,
|
| 658 |
+
"clip_ratio/low_min": 0.0,
|
| 659 |
+
"clip_ratio/region_mean": 0.0007925368736323435,
|
| 660 |
+
"epoch": 0.26875,
|
| 661 |
+
"grad_norm": 1.9965443847354802,
|
| 662 |
+
"kl": 0.004579130647471175,
|
| 663 |
+
"learning_rate": 8.588867903317394e-07,
|
| 664 |
+
"loss": 0.0002555753162596375,
|
| 665 |
+
"step": 43,
|
| 666 |
+
"step_time": 26.671454454306513
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"clip_ratio/high_max": 0.0011959137336816639,
|
| 670 |
+
"clip_ratio/high_mean": 0.00029897843342041597,
|
| 671 |
+
"clip_ratio/low_mean": 0.0004930415016133338,
|
| 672 |
+
"clip_ratio/low_min": 0.0,
|
| 673 |
+
"clip_ratio/region_mean": 0.000792019949585665,
|
| 674 |
+
"epoch": 0.275,
|
| 675 |
+
"grad_norm": 1.463676960224298,
|
| 676 |
+
"kl": 0.005269953340757638,
|
| 677 |
+
"learning_rate": 8.51757374409974e-07,
|
| 678 |
+
"loss": 0.0002709788968786597,
|
| 679 |
+
"step": 44,
|
| 680 |
+
"step_time": 26.756558004766703
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"clip_ratio/high_max": 0.00883188605075702,
|
| 684 |
+
"clip_ratio/high_mean": 0.003266135841840878,
|
| 685 |
+
"clip_ratio/low_mean": 0.0005862714169779792,
|
| 686 |
+
"clip_ratio/low_min": 0.0,
|
| 687 |
+
"clip_ratio/region_mean": 0.003852407302474603,
|
| 688 |
+
"epoch": 0.28125,
|
| 689 |
+
"grad_norm": 2.052542738421567,
|
| 690 |
+
"kl": 0.006815884436946362,
|
| 691 |
+
"learning_rate": 8.444834595378433e-07,
|
| 692 |
+
"loss": 0.00018133223056793213,
|
| 693 |
+
"step": 45,
|
| 694 |
+
"step_time": 26.173103656154126
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"clip_ratio/high_max": 0.005354123146389611,
|
| 698 |
+
"clip_ratio/high_mean": 0.0017677561008895282,
|
| 699 |
+
"clip_ratio/low_mean": 0.002546884905314073,
|
| 700 |
+
"clip_ratio/low_min": 0.0,
|
| 701 |
+
"clip_ratio/region_mean": 0.004314641118980944,
|
| 702 |
+
"epoch": 0.2875,
|
| 703 |
+
"grad_norm": 3.3986667407402256,
|
| 704 |
+
"kl": 0.01189357868861407,
|
| 705 |
+
"learning_rate": 8.370680337779736e-07,
|
| 706 |
+
"loss": -0.0001356014981865883,
|
| 707 |
+
"step": 46,
|
| 708 |
+
"step_time": 26.260462895035744
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"clip_ratio/high_max": 0.0010145119740627706,
|
| 712 |
+
"clip_ratio/high_mean": 0.00025362799351569265,
|
| 713 |
+
"clip_ratio/low_mean": 0.00018161146181228105,
|
| 714 |
+
"clip_ratio/low_min": 0.0,
|
| 715 |
+
"clip_ratio/region_mean": 0.0004352394553279737,
|
| 716 |
+
"epoch": 0.29375,
|
| 717 |
+
"grad_norm": 0.6481654748875014,
|
| 718 |
+
"kl": 0.007272145478054881,
|
| 719 |
+
"learning_rate": 8.295141433244659e-07,
|
| 720 |
+
"loss": 0.00015869039634708315,
|
| 721 |
+
"step": 47,
|
| 722 |
+
"step_time": 26.849310339894146
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"clip_ratio/high_max": 0.004569976794300601,
|
| 726 |
+
"clip_ratio/high_mean": 0.0011424941985751502,
|
| 727 |
+
"clip_ratio/low_mean": 0.000152587890625,
|
| 728 |
+
"clip_ratio/low_min": 0.0,
|
| 729 |
+
"clip_ratio/region_mean": 0.0012950820892001502,
|
| 730 |
+
"epoch": 0.3,
|
| 731 |
+
"grad_norm": 0.8563004323875646,
|
| 732 |
+
"kl": 0.006553185754455626,
|
| 733 |
+
"learning_rate": 8.218248912515442e-07,
|
| 734 |
+
"loss": 0.00011660453310469165,
|
| 735 |
+
"step": 48,
|
| 736 |
+
"step_time": 27.31743890605867
|
| 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": 0.2109375,
|
| 745 |
+
"completions/max_length": 2048.0,
|
| 746 |
+
"completions/mean_length": 1064.27734375,
|
| 747 |
+
"completions/min_length": 83.0,
|
| 748 |
+
"epoch": 0.30625,
|
| 749 |
+
"frac_reward_zero_std": 0.1875,
|
| 750 |
+
"grad_norm": 1.9313143353327298,
|
| 751 |
+
"kl": 0.009502716595306993,
|
| 752 |
+
"learning_rate": 8.140034362388397e-07,
|
| 753 |
+
"loss": 9.501352906227112e-05,
|
| 754 |
+
"reward": 0.5,
|
| 755 |
+
"reward_std": 0.3658548891544342,
|
| 756 |
+
"rewards/MajorityAccuracy/mean": 0.5,
|
| 757 |
+
"rewards/MajorityAccuracy/std": 0.5009794235229492,
|
| 758 |
+
"step": 49,
|
| 759 |
+
"step_time": 146.90019334480166
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"clip_ratio/high_max": 0.003400452114874497,
|
| 763 |
+
"clip_ratio/high_mean": 0.0011136675566376653,
|
| 764 |
+
"clip_ratio/low_mean": 0.0005560034769587219,
|
| 765 |
+
"clip_ratio/low_min": 0.0,
|
| 766 |
+
"clip_ratio/region_mean": 0.0016696710517862812,
|
| 767 |
+
"epoch": 0.3125,
|
| 768 |
+
"grad_norm": 3.1022308593774204,
|
| 769 |
+
"kl": 0.012420274200849235,
|
| 770 |
+
"learning_rate": 8.060529912738314e-07,
|
| 771 |
+
"loss": 0.0006115883588790894,
|
| 772 |
+
"step": 50,
|
| 773 |
+
"step_time": 25.561117166653275
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"clip_ratio/high_max": 0.004666015753173269,
|
| 777 |
+
"clip_ratio/high_mean": 0.0020315693072916474,
|
| 778 |
+
"clip_ratio/low_mean": 0.00040092566814564634,
|
| 779 |
+
"clip_ratio/low_min": 0.0,
|
| 780 |
+
"clip_ratio/region_mean": 0.002432494977256283,
|
| 781 |
+
"epoch": 0.31875,
|
| 782 |
+
"grad_norm": 4.242587013400057,
|
| 783 |
+
"kl": 0.013193282298743725,
|
| 784 |
+
"learning_rate": 7.979768223319785e-07,
|
| 785 |
+
"loss": 9.048450738191605e-05,
|
| 786 |
+
"step": 51,
|
| 787 |
+
"step_time": 24.55659112520516
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"clip_ratio/high_max": 0.0018661128706298769,
|
| 791 |
+
"clip_ratio/high_mean": 0.0005658072477672249,
|
| 792 |
+
"clip_ratio/low_mean": 0.0002446834259899333,
|
| 793 |
+
"clip_ratio/low_min": 0.0,
|
| 794 |
+
"clip_ratio/region_mean": 0.0008104906737571582,
|
| 795 |
+
"epoch": 0.325,
|
| 796 |
+
"grad_norm": 1.6266561240408146,
|
| 797 |
+
"kl": 0.006816387234721333,
|
| 798 |
+
"learning_rate": 7.897782470350849e-07,
|
| 799 |
+
"loss": 0.00022866031213197857,
|
| 800 |
+
"step": 52,
|
| 801 |
+
"step_time": 26.097177994903177
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"clip_ratio/high_max": 0.003457591898040846,
|
| 805 |
+
"clip_ratio/high_mean": 0.0009365688820253126,
|
| 806 |
+
"clip_ratio/low_mean": 0.0029510309104807675,
|
| 807 |
+
"clip_ratio/low_min": 0.0,
|
| 808 |
+
"clip_ratio/region_mean": 0.0038875997852301225,
|
| 809 |
+
"epoch": 0.33125,
|
| 810 |
+
"grad_norm": 2.3345568992335926,
|
| 811 |
+
"kl": 0.01365865848492831,
|
| 812 |
+
"learning_rate": 7.814606332884488e-07,
|
| 813 |
+
"loss": 0.00016087423136923462,
|
| 814 |
+
"step": 53,
|
| 815 |
+
"step_time": 24.25691546453163
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"clip_ratio/high_max": 0.0030120480805635452,
|
| 819 |
+
"clip_ratio/high_mean": 0.0007530120201408863,
|
| 820 |
+
"clip_ratio/low_mean": 0.0023104490392142907,
|
| 821 |
+
"clip_ratio/low_min": 0.0,
|
| 822 |
+
"clip_ratio/region_mean": 0.003063461059355177,
|
| 823 |
+
"epoch": 0.3375,
|
| 824 |
+
"grad_norm": 1.7684910340943742,
|
| 825 |
+
"kl": 0.018248970969580114,
|
| 826 |
+
"learning_rate": 7.730273978973552e-07,
|
| 827 |
+
"loss": 0.0004619583487510681,
|
| 828 |
+
"step": 54,
|
| 829 |
+
"step_time": 19.890037880744785
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"clip_ratio/high_max": 0.008522132178768516,
|
| 833 |
+
"clip_ratio/high_mean": 0.0027934971294598654,
|
| 834 |
+
"clip_ratio/low_mean": 0.004569269513012841,
|
| 835 |
+
"clip_ratio/low_min": 0.0001220703125,
|
| 836 |
+
"clip_ratio/region_mean": 0.007362766802543774,
|
| 837 |
+
"epoch": 0.34375,
|
| 838 |
+
"grad_norm": 2.6760263785841834,
|
| 839 |
+
"kl": 0.01687159715220332,
|
| 840 |
+
"learning_rate": 7.644820051634812e-07,
|
| 841 |
+
"loss": 0.0004151761531829834,
|
| 842 |
+
"step": 55,
|
| 843 |
+
"step_time": 22.69812378566712
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"clip_ratio/high_max": 0.0054572397348238155,
|
| 847 |
+
"clip_ratio/high_mean": 0.002000092699745437,
|
| 848 |
+
"clip_ratio/low_mean": 0.002356464188778773,
|
| 849 |
+
"clip_ratio/low_min": 0.0003662109375,
|
| 850 |
+
"clip_ratio/region_mean": 0.004356556921266019,
|
| 851 |
+
"epoch": 0.35,
|
| 852 |
+
"grad_norm": 2.860013120470116,
|
| 853 |
+
"kl": 0.010616168263368309,
|
| 854 |
+
"learning_rate": 7.558279654617912e-07,
|
| 855 |
+
"loss": 0.0007155993953347206,
|
| 856 |
+
"step": 56,
|
| 857 |
+
"step_time": 25.854090100619942
|
| 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": 0.40234375,
|
| 866 |
+
"completions/max_length": 2048.0,
|
| 867 |
+
"completions/mean_length": 1294.33203125,
|
| 868 |
+
"completions/min_length": 75.0,
|
| 869 |
+
"epoch": 0.35625,
|
| 870 |
+
"frac_reward_zero_std": 0.21875,
|
| 871 |
+
"grad_norm": 1.7898305286642655,
|
| 872 |
+
"kl": 0.008049850817769766,
|
| 873 |
+
"learning_rate": 7.470688337985029e-07,
|
| 874 |
+
"loss": 8.050839824136347e-05,
|
| 875 |
+
"reward": 0.29296875,
|
| 876 |
+
"reward_std": 0.3439026176929474,
|
| 877 |
+
"rewards/MajorityAccuracy/mean": 0.29296875,
|
| 878 |
+
"rewards/MajorityAccuracy/std": 0.45601576566696167,
|
| 879 |
+
"step": 57,
|
| 880 |
+
"step_time": 153.20904665254056
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"clip_ratio/high_max": 0.0013844898639945313,
|
| 884 |
+
"clip_ratio/high_mean": 0.00037710908509325236,
|
| 885 |
+
"clip_ratio/low_mean": 0.0005270354704407509,
|
| 886 |
+
"clip_ratio/low_min": 6.103515625e-05,
|
| 887 |
+
"clip_ratio/region_mean": 0.0009041445518960245,
|
| 888 |
+
"epoch": 0.3625,
|
| 889 |
+
"grad_norm": 1.7871664529354057,
|
| 890 |
+
"kl": 0.00849593139719218,
|
| 891 |
+
"learning_rate": 7.382082083507225e-07,
|
| 892 |
+
"loss": 0.0003703143447637558,
|
| 893 |
+
"step": 58,
|
| 894 |
+
"step_time": 26.817008298356086
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"clip_ratio/high_max": 0.0009938945149770007,
|
| 898 |
+
"clip_ratio/high_mean": 0.00031186105843517,
|
| 899 |
+
"clip_ratio/low_mean": 0.0005351099425752182,
|
| 900 |
+
"clip_ratio/low_min": 0.0,
|
| 901 |
+
"clip_ratio/region_mean": 0.0008469710046483669,
|
| 902 |
+
"epoch": 0.36875,
|
| 903 |
+
"grad_norm": 1.807989580332024,
|
| 904 |
+
"kl": 0.012745879241265357,
|
| 905 |
+
"learning_rate": 7.292497289883432e-07,
|
| 906 |
+
"loss": -3.288514562882483e-06,
|
| 907 |
+
"step": 59,
|
| 908 |
+
"step_time": 26.457055531442165
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"clip_ratio/high_max": 0.0010734112292993814,
|
| 912 |
+
"clip_ratio/high_mean": 0.00026835280732484534,
|
| 913 |
+
"clip_ratio/low_mean": 0.0003625013450800907,
|
| 914 |
+
"clip_ratio/low_min": 0.0,
|
| 915 |
+
"clip_ratio/region_mean": 0.0006308541560429148,
|
| 916 |
+
"epoch": 0.375,
|
| 917 |
+
"grad_norm": 1.052694980674766,
|
| 918 |
+
"kl": 0.00932486547389999,
|
| 919 |
+
"learning_rate": 7.201970757788171e-07,
|
| 920 |
+
"loss": -2.7742964448407292e-05,
|
| 921 |
+
"step": 60,
|
| 922 |
+
"step_time": 26.730458761099726
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"clip_ratio/high_max": 0.002987310930620879,
|
| 926 |
+
"clip_ratio/high_mean": 0.000856733946420718,
|
| 927 |
+
"clip_ratio/low_mean": 0.0009995868676924147,
|
| 928 |
+
"clip_ratio/low_min": 0.0,
|
| 929 |
+
"clip_ratio/region_mean": 0.0018563208141131327,
|
| 930 |
+
"epoch": 0.38125,
|
| 931 |
+
"grad_norm": 2.5655909956155627,
|
| 932 |
+
"kl": 0.012800393276847899,
|
| 933 |
+
"learning_rate": 7.110539674754159e-07,
|
| 934 |
+
"loss": 0.00026796391466632485,
|
| 935 |
+
"step": 61,
|
| 936 |
+
"step_time": 26.51184447063133
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"clip_ratio/high_max": 0.006560867128428072,
|
| 940 |
+
"clip_ratio/high_mean": 0.002202709234552458,
|
| 941 |
+
"clip_ratio/low_mean": 0.004929073213133961,
|
| 942 |
+
"clip_ratio/low_min": 0.0,
|
| 943 |
+
"clip_ratio/region_mean": 0.0071317823603749275,
|
| 944 |
+
"epoch": 0.3875,
|
| 945 |
+
"grad_norm": 4.87487462300655,
|
| 946 |
+
"kl": 0.02928468445315957,
|
| 947 |
+
"learning_rate": 7.018241599895973e-07,
|
| 948 |
+
"loss": 0.00017079897224903107,
|
| 949 |
+
"step": 62,
|
| 950 |
+
"step_time": 21.999755011405796
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"clip_ratio/high_max": 0.005765936424722895,
|
| 954 |
+
"clip_ratio/high_mean": 0.0018633457002579235,
|
| 955 |
+
"clip_ratio/low_mean": 0.0019919475889764726,
|
| 956 |
+
"clip_ratio/low_min": 0.0001220703125,
|
| 957 |
+
"clip_ratio/region_mean": 0.0038552932674065232,
|
| 958 |
+
"epoch": 0.39375,
|
| 959 |
+
"grad_norm": 1.6977472398519102,
|
| 960 |
+
"kl": 0.009642413817346096,
|
| 961 |
+
"learning_rate": 6.925114448481088e-07,
|
| 962 |
+
"loss": 0.00024619512259960175,
|
| 963 |
+
"step": 63,
|
| 964 |
+
"step_time": 26.556101062335074
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"clip_ratio/high_max": 0.004446798411663622,
|
| 968 |
+
"clip_ratio/high_mean": 0.0016259615222224966,
|
| 969 |
+
"clip_ratio/low_mean": 0.0011026699794456363,
|
| 970 |
+
"clip_ratio/low_min": 0.0,
|
| 971 |
+
"clip_ratio/region_mean": 0.0027286314871162176,
|
| 972 |
+
"epoch": 0.4,
|
| 973 |
+
"grad_norm": 1.7590513384924056,
|
| 974 |
+
"kl": 0.00784820260014385,
|
| 975 |
+
"learning_rate": 6.831196476354614e-07,
|
| 976 |
+
"loss": 0.00024780078092589974,
|
| 977 |
+
"step": 64,
|
| 978 |
+
"step_time": 26.497205490246415
|
| 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": 0.359375,
|
| 987 |
+
"completions/max_length": 2048.0,
|
| 988 |
+
"completions/mean_length": 1253.55078125,
|
| 989 |
+
"completions/min_length": 63.0,
|
| 990 |
+
"epoch": 0.40625,
|
| 991 |
+
"frac_reward_zero_std": 0.34375,
|
| 992 |
+
"grad_norm": 2.3097380776164593,
|
| 993 |
+
"kl": 0.008485952916089445,
|
| 994 |
+
"learning_rate": 6.7365262642241e-07,
|
| 995 |
+
"loss": 8.489389438182116e-05,
|
| 996 |
+
"reward": 0.40234375,
|
| 997 |
+
"reward_std": 0.3156158924102783,
|
| 998 |
+
"rewards/MajorityAccuracy/mean": 0.40234375,
|
| 999 |
+
"rewards/MajorityAccuracy/std": 0.4913311004638672,
|
| 1000 |
+
"step": 65,
|
| 1001 |
+
"step_time": 160.84176068706438
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"clip_ratio/high_max": 0.0012978658996871673,
|
| 1005 |
+
"clip_ratio/high_mean": 0.0003244664749217918,
|
| 1006 |
+
"clip_ratio/low_mean": 0.0,
|
| 1007 |
+
"clip_ratio/low_min": 0.0,
|
| 1008 |
+
"clip_ratio/region_mean": 0.0003244664749217918,
|
| 1009 |
+
"epoch": 0.4125,
|
| 1010 |
+
"grad_norm": 0.7688825235541478,
|
| 1011 |
+
"kl": 0.010125637229066342,
|
| 1012 |
+
"learning_rate": 6.641142701810931e-07,
|
| 1013 |
+
"loss": 1.2389500625431538e-05,
|
| 1014 |
+
"step": 66,
|
| 1015 |
+
"step_time": 26.912673476617783
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"clip_ratio/high_max": 0.0012680605432251468,
|
| 1019 |
+
"clip_ratio/high_mean": 0.0003170151358062867,
|
| 1020 |
+
"clip_ratio/low_mean": 0.0004850265868299175,
|
| 1021 |
+
"clip_ratio/low_min": 0.0,
|
| 1022 |
+
"clip_ratio/region_mean": 0.0008020417226362042,
|
| 1023 |
+
"epoch": 0.41875,
|
| 1024 |
+
"grad_norm": 2.669466572800535,
|
| 1025 |
+
"kl": 0.008113744668662548,
|
| 1026 |
+
"learning_rate": 6.545084971874736e-07,
|
| 1027 |
+
"loss": 0.0003711618483066559,
|
| 1028 |
+
"step": 67,
|
| 1029 |
+
"step_time": 26.481263156980276
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"clip_ratio/high_max": 0.0013830054085701704,
|
| 1033 |
+
"clip_ratio/high_mean": 0.0003668377175927162,
|
| 1034 |
+
"clip_ratio/low_mean": 0.0007921823707874864,
|
| 1035 |
+
"clip_ratio/low_min": 0.0,
|
| 1036 |
+
"clip_ratio/region_mean": 0.0011590200883802027,
|
| 1037 |
+
"epoch": 0.425,
|
| 1038 |
+
"grad_norm": 2.178926765705087,
|
| 1039 |
+
"kl": 0.011899639619514346,
|
| 1040 |
+
"learning_rate": 6.448392534117461e-07,
|
| 1041 |
+
"loss": 0.00010982825187966228,
|
| 1042 |
+
"step": 68,
|
| 1043 |
+
"step_time": 25.897847419138998
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"clip_ratio/high_max": 0.0014127944596111774,
|
| 1047 |
+
"clip_ratio/high_mean": 0.0005217695725150406,
|
| 1048 |
+
"clip_ratio/low_mean": 0.0009453975726501085,
|
| 1049 |
+
"clip_ratio/low_min": 0.0,
|
| 1050 |
+
"clip_ratio/region_mean": 0.0014671671451651491,
|
| 1051 |
+
"epoch": 0.43125,
|
| 1052 |
+
"grad_norm": 1.8865733431017246,
|
| 1053 |
+
"kl": 0.01148706313688308,
|
| 1054 |
+
"learning_rate": 6.351105108973644e-07,
|
| 1055 |
+
"loss": 0.0001416386803612113,
|
| 1056 |
+
"step": 69,
|
| 1057 |
+
"step_time": 24.237813016865402
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"clip_ratio/high_max": 0.0033974867255892605,
|
| 1061 |
+
"clip_ratio/high_mean": 0.0009695506087155081,
|
| 1062 |
+
"clip_ratio/low_mean": 0.0009287104476243258,
|
| 1063 |
+
"clip_ratio/low_min": 0.00013469827536027879,
|
| 1064 |
+
"clip_ratio/region_mean": 0.0018982610636157915,
|
| 1065 |
+
"epoch": 0.4375,
|
| 1066 |
+
"grad_norm": 2.506857125153927,
|
| 1067 |
+
"kl": 0.0101005231263116,
|
| 1068 |
+
"learning_rate": 6.253262661293602e-07,
|
| 1069 |
+
"loss": 0.00010122917592525482,
|
| 1070 |
+
"step": 70,
|
| 1071 |
+
"step_time": 26.5892844744958
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"clip_ratio/high_max": 0.00019946807879023254,
|
| 1075 |
+
"clip_ratio/high_mean": 4.9867019697558135e-05,
|
| 1076 |
+
"clip_ratio/low_mean": 0.0001373291015625,
|
| 1077 |
+
"clip_ratio/low_min": 0.0,
|
| 1078 |
+
"clip_ratio/region_mean": 0.00018719612126005813,
|
| 1079 |
+
"epoch": 0.44375,
|
| 1080 |
+
"grad_norm": 0.6101290166953233,
|
| 1081 |
+
"kl": 0.023403054801747203,
|
| 1082 |
+
"learning_rate": 6.154905383926216e-07,
|
| 1083 |
+
"loss": 0.00022784454631619155,
|
| 1084 |
+
"step": 71,
|
| 1085 |
+
"step_time": 25.742948403116316
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"clip_ratio/high_max": 0.004786534060258418,
|
| 1089 |
+
"clip_ratio/high_mean": 0.0015110097592696548,
|
| 1090 |
+
"clip_ratio/low_mean": 0.0007626373480889015,
|
| 1091 |
+
"clip_ratio/low_min": 0.0,
|
| 1092 |
+
"clip_ratio/region_mean": 0.002273647114634514,
|
| 1093 |
+
"epoch": 0.45,
|
| 1094 |
+
"grad_norm": 1.0827166924417404,
|
| 1095 |
+
"kl": 0.012834195513278246,
|
| 1096 |
+
"learning_rate": 6.056073681208037e-07,
|
| 1097 |
+
"loss": 0.00018114666454494,
|
| 1098 |
+
"step": 72,
|
| 1099 |
+
"step_time": 26.984704324044287
|
| 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": 0.33203125,
|
| 1108 |
+
"completions/max_length": 2048.0,
|
| 1109 |
+
"completions/mean_length": 1159.07421875,
|
| 1110 |
+
"completions/min_length": 79.0,
|
| 1111 |
+
"epoch": 0.45625,
|
| 1112 |
+
"frac_reward_zero_std": 0.3125,
|
| 1113 |
+
"grad_norm": 2.814559552890671,
|
| 1114 |
+
"kl": 0.010964806308038533,
|
| 1115 |
+
"learning_rate": 5.956808152365532e-07,
|
| 1116 |
+
"loss": 0.00010966748232021928,
|
| 1117 |
+
"reward": 0.4765625,
|
| 1118 |
+
"reward_std": 0.323244571685791,
|
| 1119 |
+
"rewards/MajorityAccuracy/mean": 0.4765625,
|
| 1120 |
+
"rewards/MajorityAccuracy/std": 0.5004287362098694,
|
| 1121 |
+
"step": 73,
|
| 1122 |
+
"step_time": 151.48212130367756
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"clip_ratio/high_max": 0.002189066188293509,
|
| 1126 |
+
"clip_ratio/high_mean": 0.0005472665470733773,
|
| 1127 |
+
"clip_ratio/low_mean": 0.0003532672126311809,
|
| 1128 |
+
"clip_ratio/low_min": 0.0,
|
| 1129 |
+
"clip_ratio/region_mean": 0.000900533763342537,
|
| 1130 |
+
"epoch": 0.4625,
|
| 1131 |
+
"grad_norm": 2.0847799790591792,
|
| 1132 |
+
"kl": 0.02178597147576511,
|
| 1133 |
+
"learning_rate": 5.857149574837268e-07,
|
| 1134 |
+
"loss": 0.00013192334154155105,
|
| 1135 |
+
"step": 74,
|
| 1136 |
+
"step_time": 25.686971639283
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"clip_ratio/high_max": 0.0020634600296034478,
|
| 1140 |
+
"clip_ratio/high_mean": 0.000751882273107185,
|
| 1141 |
+
"clip_ratio/low_mean": 6.843771552667022e-05,
|
| 1142 |
+
"clip_ratio/low_min": 0.0,
|
| 1143 |
+
"clip_ratio/region_mean": 0.0008203199886338552,
|
| 1144 |
+
"epoch": 0.46875,
|
| 1145 |
+
"grad_norm": 1.8803994454649768,
|
| 1146 |
+
"kl": 0.016387052019126713,
|
| 1147 |
+
"learning_rate": 5.757138887522883e-07,
|
| 1148 |
+
"loss": 0.00023301903274841607,
|
| 1149 |
+
"step": 75,
|
| 1150 |
+
"step_time": 22.816880833823234
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"clip_ratio/high_max": 0.0024087407291517593,
|
| 1154 |
+
"clip_ratio/high_mean": 0.0007425305593642406,
|
| 1155 |
+
"clip_ratio/low_mean": 6.746269536961336e-05,
|
| 1156 |
+
"clip_ratio/low_min": 0.0,
|
| 1157 |
+
"clip_ratio/region_mean": 0.0008099932529148646,
|
| 1158 |
+
"epoch": 0.475,
|
| 1159 |
+
"grad_norm": 1.2769455628326094,
|
| 1160 |
+
"kl": 0.00945944746490568,
|
| 1161 |
+
"learning_rate": 5.656817173965732e-07,
|
| 1162 |
+
"loss": 0.00016746563778724521,
|
| 1163 |
+
"step": 76,
|
| 1164 |
+
"step_time": 26.938445050735027
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"clip_ratio/high_max": 0.0009808699833229184,
|
| 1168 |
+
"clip_ratio/high_mean": 0.0002452174958307296,
|
| 1169 |
+
"clip_ratio/low_mean": 0.00043754312173405197,
|
| 1170 |
+
"clip_ratio/low_min": 0.0,
|
| 1171 |
+
"clip_ratio/region_mean": 0.0006827606266597286,
|
| 1172 |
+
"epoch": 0.48125,
|
| 1173 |
+
"grad_norm": 1.4383447858326437,
|
| 1174 |
+
"kl": 0.01217155868653208,
|
| 1175 |
+
"learning_rate": 5.556225645476118e-07,
|
| 1176 |
+
"loss": 0.0001881580101326108,
|
| 1177 |
+
"step": 77,
|
| 1178 |
+
"step_time": 26.82154444977641
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"clip_ratio/high_max": 0.004762516189657617,
|
| 1182 |
+
"clip_ratio/high_mean": 0.0016999124145513633,
|
| 1183 |
+
"clip_ratio/low_mean": 0.00045931645945529453,
|
| 1184 |
+
"clip_ratio/low_min": 0.0,
|
| 1185 |
+
"clip_ratio/region_mean": 0.002159228901291499,
|
| 1186 |
+
"epoch": 0.4875,
|
| 1187 |
+
"grad_norm": 1.885770973388709,
|
| 1188 |
+
"kl": 0.013340331497602165,
|
| 1189 |
+
"learning_rate": 5.455405624202032e-07,
|
| 1190 |
+
"loss": 0.00010585412383079529,
|
| 1191 |
+
"step": 78,
|
| 1192 |
+
"step_time": 25.570450688246638
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"clip_ratio/high_max": 0.008039385022129864,
|
| 1196 |
+
"clip_ratio/high_mean": 0.002787033867207356,
|
| 1197 |
+
"clip_ratio/low_mean": 0.0007016238814685494,
|
| 1198 |
+
"clip_ratio/low_min": 0.0,
|
| 1199 |
+
"clip_ratio/region_mean": 0.0034886577195720747,
|
| 1200 |
+
"epoch": 0.49375,
|
| 1201 |
+
"grad_norm": 4.145044303148379,
|
| 1202 |
+
"kl": 0.020714069483801723,
|
| 1203 |
+
"learning_rate": 5.354398526154365e-07,
|
| 1204 |
+
"loss": 0.00014754633593838662,
|
| 1205 |
+
"step": 79,
|
| 1206 |
+
"step_time": 23.968969020992517
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"clip_ratio/high_max": 0.004414374619955197,
|
| 1210 |
+
"clip_ratio/high_mean": 0.0015082536629051901,
|
| 1211 |
+
"clip_ratio/low_mean": 0.0009248787973774597,
|
| 1212 |
+
"clip_ratio/low_min": 0.0,
|
| 1213 |
+
"clip_ratio/region_mean": 0.0024331324821105227,
|
| 1214 |
+
"epoch": 0.5,
|
| 1215 |
+
"grad_norm": 2.2032305174954407,
|
| 1216 |
+
"kl": 0.011072167428210378,
|
| 1217 |
+
"learning_rate": 5.253245844193564e-07,
|
| 1218 |
+
"loss": 0.00019322267326060683,
|
| 1219 |
+
"step": 80,
|
| 1220 |
+
"step_time": 27.00699529564008
|
| 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": 0.25390625,
|
| 1229 |
+
"completions/max_length": 2048.0,
|
| 1230 |
+
"completions/mean_length": 1124.91796875,
|
| 1231 |
+
"completions/min_length": 45.0,
|
| 1232 |
+
"epoch": 0.50625,
|
| 1233 |
+
"frac_reward_zero_std": 0.21875,
|
| 1234 |
+
"grad_norm": 1.5075334546362755,
|
| 1235 |
+
"kl": 0.016221102327108383,
|
| 1236 |
+
"learning_rate": 5.151989130984714e-07,
|
| 1237 |
+
"loss": 0.00016221888654399663,
|
| 1238 |
+
"reward": 0.48828125,
|
| 1239 |
+
"reward_std": 0.36098712682724,
|
| 1240 |
+
"rewards/MajorityAccuracy/mean": 0.48828125,
|
| 1241 |
+
"rewards/MajorityAccuracy/std": 0.5008417963981628,
|
| 1242 |
+
"step": 81,
|
| 1243 |
+
"step_time": 152.05836168816313
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"clip_ratio/high_max": 0.0027674001175910234,
|
| 1247 |
+
"clip_ratio/high_mean": 0.0007152057878556661,
|
| 1248 |
+
"clip_ratio/low_mean": 0.0002719455187616404,
|
| 1249 |
+
"clip_ratio/low_min": 0.0,
|
| 1250 |
+
"clip_ratio/region_mean": 0.0009871512957033701,
|
| 1251 |
+
"epoch": 0.5125,
|
| 1252 |
+
"grad_norm": 3.761082006477601,
|
| 1253 |
+
"kl": 0.021893260534852743,
|
| 1254 |
+
"learning_rate": 5.050669981928055e-07,
|
| 1255 |
+
"loss": 0.00014202776947058737,
|
| 1256 |
+
"step": 82,
|
| 1257 |
+
"step_time": 24.384640294592828
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"clip_ratio/high_max": 0.0012398773687891662,
|
| 1261 |
+
"clip_ratio/high_mean": 0.00030996934219729155,
|
| 1262 |
+
"clip_ratio/low_mean": 0.0004198546812403947,
|
| 1263 |
+
"clip_ratio/low_min": 0.0,
|
| 1264 |
+
"clip_ratio/region_mean": 0.0007298240197997075,
|
| 1265 |
+
"epoch": 0.51875,
|
| 1266 |
+
"grad_norm": 1.6029734956926691,
|
| 1267 |
+
"kl": 0.013670606771484017,
|
| 1268 |
+
"learning_rate": 4.949330018071946e-07,
|
| 1269 |
+
"loss": -0.00011822281521745026,
|
| 1270 |
+
"step": 83,
|
| 1271 |
+
"step_time": 23.540419476106763
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"clip_ratio/high_max": 0.004649537309887819,
|
| 1275 |
+
"clip_ratio/high_mean": 0.0016713853365217801,
|
| 1276 |
+
"clip_ratio/low_mean": 0.0002911664705607109,
|
| 1277 |
+
"clip_ratio/low_min": 0.0,
|
| 1278 |
+
"clip_ratio/region_mean": 0.001962551803444512,
|
| 1279 |
+
"epoch": 0.525,
|
| 1280 |
+
"grad_norm": 2.7788505367062695,
|
| 1281 |
+
"kl": 0.013794364058412611,
|
| 1282 |
+
"learning_rate": 4.848010869015287e-07,
|
| 1283 |
+
"loss": 0.00033229775726795197,
|
| 1284 |
+
"step": 84,
|
| 1285 |
+
"step_time": 26.26982248062268
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"clip_ratio/high_max": 0.001684176328126341,
|
| 1289 |
+
"clip_ratio/high_mean": 0.0004738312418339774,
|
| 1290 |
+
"clip_ratio/low_mean": 0.00021089012807351537,
|
| 1291 |
+
"clip_ratio/low_min": 0.0,
|
| 1292 |
+
"clip_ratio/region_mean": 0.0006847213735454716,
|
| 1293 |
+
"epoch": 0.53125,
|
| 1294 |
+
"grad_norm": 1.1310242368496026,
|
| 1295 |
+
"kl": 0.013298019184730947,
|
| 1296 |
+
"learning_rate": 4.746754155806437e-07,
|
| 1297 |
+
"loss": 2.434797352179885e-05,
|
| 1298 |
+
"step": 85,
|
| 1299 |
+
"step_time": 25.430210632737726
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"clip_ratio/high_max": 0.0030404664285015315,
|
| 1303 |
+
"clip_ratio/high_mean": 0.00114555585605558,
|
| 1304 |
+
"clip_ratio/low_mean": 0.00043798093975055963,
|
| 1305 |
+
"clip_ratio/low_min": 0.0,
|
| 1306 |
+
"clip_ratio/region_mean": 0.0015835368249099702,
|
| 1307 |
+
"epoch": 0.5375,
|
| 1308 |
+
"grad_norm": 1.9857721988952954,
|
| 1309 |
+
"kl": 0.010151166294235736,
|
| 1310 |
+
"learning_rate": 4.645601473845635e-07,
|
| 1311 |
+
"loss": 0.0003296658396720886,
|
| 1312 |
+
"step": 86,
|
| 1313 |
+
"step_time": 26.162267986685038
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"clip_ratio/high_max": 0.0012393580545904115,
|
| 1317 |
+
"clip_ratio/high_mean": 0.000511582191393245,
|
| 1318 |
+
"clip_ratio/low_mean": 0.0010581120222923346,
|
| 1319 |
+
"clip_ratio/low_min": 0.0001220703125,
|
| 1320 |
+
"clip_ratio/region_mean": 0.0015696942282374948,
|
| 1321 |
+
"epoch": 0.54375,
|
| 1322 |
+
"grad_norm": 1.5962373916371206,
|
| 1323 |
+
"kl": 0.01268746075220406,
|
| 1324 |
+
"learning_rate": 4.544594375797968e-07,
|
| 1325 |
+
"loss": 0.00048592500388622284,
|
| 1326 |
+
"step": 87,
|
| 1327 |
+
"step_time": 26.609270500484854
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"clip_ratio/high_max": 0.005307867788360454,
|
| 1331 |
+
"clip_ratio/high_mean": 0.0014495159739453811,
|
| 1332 |
+
"clip_ratio/low_mean": 0.0007076471447362565,
|
| 1333 |
+
"clip_ratio/low_min": 0.0,
|
| 1334 |
+
"clip_ratio/region_mean": 0.0021571631405095104,
|
| 1335 |
+
"epoch": 0.55,
|
| 1336 |
+
"grad_norm": 1.9356532775290536,
|
| 1337 |
+
"kl": 0.013042393722571433,
|
| 1338 |
+
"learning_rate": 4.443774354523882e-07,
|
| 1339 |
+
"loss": 6.589369149878621e-05,
|
| 1340 |
+
"step": 88,
|
| 1341 |
+
"step_time": 26.92362395953387
|
| 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": 0.27734375,
|
| 1350 |
+
"completions/max_length": 2048.0,
|
| 1351 |
+
"completions/mean_length": 1145.57421875,
|
| 1352 |
+
"completions/min_length": 55.0,
|
| 1353 |
+
"epoch": 0.55625,
|
| 1354 |
+
"frac_reward_zero_std": 0.21875,
|
| 1355 |
+
"grad_norm": 0.9813950563646651,
|
| 1356 |
+
"kl": 0.013398032519035041,
|
| 1357 |
+
"learning_rate": 4.3431828260342675e-07,
|
| 1358 |
+
"loss": 0.0001339763548457995,
|
| 1359 |
+
"reward": 0.35546875,
|
| 1360 |
+
"reward_std": 0.35692310333251953,
|
| 1361 |
+
"rewards/MajorityAccuracy/mean": 0.35546875,
|
| 1362 |
+
"rewards/MajorityAccuracy/std": 0.4795927405357361,
|
| 1363 |
+
"step": 89,
|
| 1364 |
+
"step_time": 150.88171829469502
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"clip_ratio/high_max": 0.0017963394639082253,
|
| 1368 |
+
"clip_ratio/high_mean": 0.0004703144877566956,
|
| 1369 |
+
"clip_ratio/low_mean": 0.000510408952322905,
|
| 1370 |
+
"clip_ratio/low_min": 0.0,
|
| 1371 |
+
"clip_ratio/region_mean": 0.0009807234400796006,
|
| 1372 |
+
"epoch": 0.5625,
|
| 1373 |
+
"grad_norm": 2.726758480379885,
|
| 1374 |
+
"kl": 0.019123253179714084,
|
| 1375 |
+
"learning_rate": 4.242861112477118e-07,
|
| 1376 |
+
"loss": 0.00045563987805508077,
|
| 1377 |
+
"step": 90,
|
| 1378 |
+
"step_time": 25.0485139307566
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"clip_ratio/high_max": 0.00639739038888365,
|
| 1382 |
+
"clip_ratio/high_mean": 0.0016344205505447462,
|
| 1383 |
+
"clip_ratio/low_mean": 0.0003209213537047617,
|
| 1384 |
+
"clip_ratio/low_min": 0.0,
|
| 1385 |
+
"clip_ratio/region_mean": 0.001955341904249508,
|
| 1386 |
+
"epoch": 0.56875,
|
| 1387 |
+
"grad_norm": 2.379646099449871,
|
| 1388 |
+
"kl": 0.014002847718074918,
|
| 1389 |
+
"learning_rate": 4.1428504251627325e-07,
|
| 1390 |
+
"loss": 0.0006718694930896163,
|
| 1391 |
+
"step": 91,
|
| 1392 |
+
"step_time": 26.86760963499546
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"clip_ratio/high_max": 0.00038698229764122516,
|
| 1396 |
+
"clip_ratio/high_mean": 9.674557441030629e-05,
|
| 1397 |
+
"clip_ratio/low_mean": 0.0007885509439802263,
|
| 1398 |
+
"clip_ratio/low_min": 0.0,
|
| 1399 |
+
"clip_ratio/region_mean": 0.0008852965147525538,
|
| 1400 |
+
"epoch": 0.575,
|
| 1401 |
+
"grad_norm": 2.969128625761763,
|
| 1402 |
+
"kl": 0.013753827777691185,
|
| 1403 |
+
"learning_rate": 4.0431918476344685e-07,
|
| 1404 |
+
"loss": 0.00025910421391017735,
|
| 1405 |
+
"step": 92,
|
| 1406 |
+
"step_time": 21.743984759319574
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"clip_ratio/high_max": 0.0031948270625434816,
|
| 1410 |
+
"clip_ratio/high_mean": 0.0009577342862030491,
|
| 1411 |
+
"clip_ratio/low_mean": 0.0011484454444143921,
|
| 1412 |
+
"clip_ratio/low_min": 0.0,
|
| 1413 |
+
"clip_ratio/region_mean": 0.0021061797451693565,
|
| 1414 |
+
"epoch": 0.58125,
|
| 1415 |
+
"grad_norm": 3.456621241953836,
|
| 1416 |
+
"kl": 0.017006980255246162,
|
| 1417 |
+
"learning_rate": 3.943926318791963e-07,
|
| 1418 |
+
"loss": 1.2588687241077423e-05,
|
| 1419 |
+
"step": 93,
|
| 1420 |
+
"step_time": 25.24093049298972
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"clip_ratio/high_max": 0.0010050795899587683,
|
| 1424 |
+
"clip_ratio/high_mean": 0.00027119974583911244,
|
| 1425 |
+
"clip_ratio/low_mean": 0.0009997659071814269,
|
| 1426 |
+
"clip_ratio/low_min": 0.0001830161054385826,
|
| 1427 |
+
"clip_ratio/region_mean": 0.0012709656584775075,
|
| 1428 |
+
"epoch": 0.5875,
|
| 1429 |
+
"grad_norm": 1.2976936574303308,
|
| 1430 |
+
"kl": 0.011330849956721067,
|
| 1431 |
+
"learning_rate": 3.845094616073783e-07,
|
| 1432 |
+
"loss": 9.047146886587143e-05,
|
| 1433 |
+
"step": 94,
|
| 1434 |
+
"step_time": 27.068362248595804
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"clip_ratio/high_max": 0.0025039714673766866,
|
| 1438 |
+
"clip_ratio/high_mean": 0.0006259928668441717,
|
| 1439 |
+
"clip_ratio/low_mean": 0.000564859263249673,
|
| 1440 |
+
"clip_ratio/low_min": 0.0,
|
| 1441 |
+
"clip_ratio/region_mean": 0.0011908521482837386,
|
| 1442 |
+
"epoch": 0.59375,
|
| 1443 |
+
"grad_norm": 2.148633367489874,
|
| 1444 |
+
"kl": 0.018928393255919218,
|
| 1445 |
+
"learning_rate": 3.7467373387063964e-07,
|
| 1446 |
+
"loss": 0.0004933763993903995,
|
| 1447 |
+
"step": 95,
|
| 1448 |
+
"step_time": 24.47440194664523
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"clip_ratio/high_max": 0.002359641279326752,
|
| 1452 |
+
"clip_ratio/high_mean": 0.000795143932919018,
|
| 1453 |
+
"clip_ratio/low_mean": 0.001050750863214489,
|
| 1454 |
+
"clip_ratio/low_min": 0.00018310546875,
|
| 1455 |
+
"clip_ratio/region_mean": 0.0018458948034094647,
|
| 1456 |
+
"epoch": 0.6,
|
| 1457 |
+
"grad_norm": 1.9862872677018202,
|
| 1458 |
+
"kl": 0.012734844931401312,
|
| 1459 |
+
"learning_rate": 3.648894891026358e-07,
|
| 1460 |
+
"loss": 0.0002440623939037323,
|
| 1461 |
+
"step": 96,
|
| 1462 |
+
"step_time": 26.855415117926896
|
| 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": 0.3046875,
|
| 1471 |
+
"completions/max_length": 2048.0,
|
| 1472 |
+
"completions/mean_length": 1187.1484375,
|
| 1473 |
+
"completions/min_length": 87.0,
|
| 1474 |
+
"epoch": 0.60625,
|
| 1475 |
+
"frac_reward_zero_std": 0.28125,
|
| 1476 |
+
"grad_norm": 1.9366440421586368,
|
| 1477 |
+
"kl": 0.015335718519054353,
|
| 1478 |
+
"learning_rate": 3.5516074658825397e-07,
|
| 1479 |
+
"loss": 0.00015335323405452073,
|
| 1480 |
+
"reward": 0.36328125,
|
| 1481 |
+
"reward_std": 0.3177414834499359,
|
| 1482 |
+
"rewards/MajorityAccuracy/mean": 0.36328125,
|
| 1483 |
+
"rewards/MajorityAccuracy/std": 0.48188698291778564,
|
| 1484 |
+
"step": 97,
|
| 1485 |
+
"step_time": 153.30846688896418
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"clip_ratio/high_max": 0.0016219945609918796,
|
| 1489 |
+
"clip_ratio/high_mean": 0.000501927732329932,
|
| 1490 |
+
"clip_ratio/low_mean": 0.00010682564970920794,
|
| 1491 |
+
"clip_ratio/low_min": 0.0,
|
| 1492 |
+
"clip_ratio/region_mean": 0.0006087533765821718,
|
| 1493 |
+
"epoch": 0.6125,
|
| 1494 |
+
"grad_norm": 2.4062821952776625,
|
| 1495 |
+
"kl": 0.014152053161524236,
|
| 1496 |
+
"learning_rate": 3.454915028125263e-07,
|
| 1497 |
+
"loss": 0.0003483220934867859,
|
| 1498 |
+
"step": 98,
|
| 1499 |
+
"step_time": 23.55763346143067
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"clip_ratio/high_max": 0.0004437869938556105,
|
| 1503 |
+
"clip_ratio/high_mean": 0.00011094674846390262,
|
| 1504 |
+
"clip_ratio/low_mean": 0.0,
|
| 1505 |
+
"clip_ratio/low_min": 0.0,
|
| 1506 |
+
"clip_ratio/region_mean": 0.00011094674846390262,
|
| 1507 |
+
"epoch": 0.61875,
|
| 1508 |
+
"grad_norm": 1.4121815667037685,
|
| 1509 |
+
"kl": 0.019883687957189977,
|
| 1510 |
+
"learning_rate": 3.3588572981890684e-07,
|
| 1511 |
+
"loss": 9.770601900527254e-05,
|
| 1512 |
+
"step": 99,
|
| 1513 |
+
"step_time": 26.2241800990887
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"clip_ratio/high_max": 0.0019981380391982384,
|
| 1517 |
+
"clip_ratio/high_mean": 0.0006287196174525889,
|
| 1518 |
+
"clip_ratio/low_mean": 6.340979234664701e-05,
|
| 1519 |
+
"clip_ratio/low_min": 0.0,
|
| 1520 |
+
"clip_ratio/region_mean": 0.0006921294043422677,
|
| 1521 |
+
"epoch": 0.625,
|
| 1522 |
+
"grad_norm": 1.6176491166724267,
|
| 1523 |
+
"kl": 0.014117960236035287,
|
| 1524 |
+
"learning_rate": 3.263473735775899e-07,
|
| 1525 |
+
"loss": -1.7299496903433464e-05,
|
| 1526 |
+
"step": 100,
|
| 1527 |
+
"step_time": 26.32435222575441
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"clip_ratio/high_max": 0.002249811921501532,
|
| 1531 |
+
"clip_ratio/high_mean": 0.0006981258993619122,
|
| 1532 |
+
"clip_ratio/low_mean": 0.0005020949465688318,
|
| 1533 |
+
"clip_ratio/low_min": 0.0,
|
| 1534 |
+
"clip_ratio/region_mean": 0.0012002208532067016,
|
| 1535 |
+
"epoch": 0.63125,
|
| 1536 |
+
"grad_norm": 1.4872203989093484,
|
| 1537 |
+
"kl": 0.021414539660327137,
|
| 1538 |
+
"learning_rate": 3.1688035236453865e-07,
|
| 1539 |
+
"loss": 0.0002170833759009838,
|
| 1540 |
+
"step": 101,
|
| 1541 |
+
"step_time": 26.85496973292902
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"clip_ratio/high_max": 0.0010540623261476867,
|
| 1545 |
+
"clip_ratio/high_mean": 0.0003275524559285259,
|
| 1546 |
+
"clip_ratio/low_mean": 0.000454813376563834,
|
| 1547 |
+
"clip_ratio/low_min": 0.0,
|
| 1548 |
+
"clip_ratio/region_mean": 0.0007823658306733705,
|
| 1549 |
+
"epoch": 0.6375,
|
| 1550 |
+
"grad_norm": 3.3641060610394167,
|
| 1551 |
+
"kl": 0.021506338845938444,
|
| 1552 |
+
"learning_rate": 3.0748855515189096e-07,
|
| 1553 |
+
"loss": 0.00018874387023970485,
|
| 1554 |
+
"step": 102,
|
| 1555 |
+
"step_time": 23.71711810771376
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"clip_ratio/high_max": 0.0024906673570512794,
|
| 1559 |
+
"clip_ratio/high_mean": 0.0006421858906833222,
|
| 1560 |
+
"clip_ratio/low_mean": 0.0011794294114224613,
|
| 1561 |
+
"clip_ratio/low_min": 0.0,
|
| 1562 |
+
"clip_ratio/region_mean": 0.0018216153112007305,
|
| 1563 |
+
"epoch": 0.64375,
|
| 1564 |
+
"grad_norm": 3.0784174021840154,
|
| 1565 |
+
"kl": 0.0164244354236871,
|
| 1566 |
+
"learning_rate": 2.981758400104028e-07,
|
| 1567 |
+
"loss": 0.0004769740626215935,
|
| 1568 |
+
"step": 103,
|
| 1569 |
+
"step_time": 26.336561407428235
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"clip_ratio/high_max": 0.003100353278568946,
|
| 1573 |
+
"clip_ratio/high_mean": 0.0012499930999183562,
|
| 1574 |
+
"clip_ratio/low_mean": 0.00029095710488036275,
|
| 1575 |
+
"clip_ratio/low_min": 0.0,
|
| 1576 |
+
"clip_ratio/region_mean": 0.0015409502084366977,
|
| 1577 |
+
"epoch": 0.65,
|
| 1578 |
+
"grad_norm": 2.019319007320239,
|
| 1579 |
+
"kl": 0.012274886714294553,
|
| 1580 |
+
"learning_rate": 2.8894603252458403e-07,
|
| 1581 |
+
"loss": 0.000340243277605623,
|
| 1582 |
+
"step": 104,
|
| 1583 |
+
"step_time": 26.79279213724658
|
| 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": 0.22265625,
|
| 1592 |
+
"completions/max_length": 2048.0,
|
| 1593 |
+
"completions/mean_length": 1065.9296875,
|
| 1594 |
+
"completions/min_length": 64.0,
|
| 1595 |
+
"epoch": 0.65625,
|
| 1596 |
+
"frac_reward_zero_std": 0.25,
|
| 1597 |
+
"grad_norm": 2.318784942320447,
|
| 1598 |
+
"kl": 0.016041144728660583,
|
| 1599 |
+
"learning_rate": 2.7980292422118277e-07,
|
| 1600 |
+
"loss": 0.00016043148934841156,
|
| 1601 |
+
"reward": 0.45703125,
|
| 1602 |
+
"reward_std": 0.3595416843891144,
|
| 1603 |
+
"rewards/MajorityAccuracy/mean": 0.45703125,
|
| 1604 |
+
"rewards/MajorityAccuracy/std": 0.4991260766983032,
|
| 1605 |
+
"step": 105,
|
| 1606 |
+
"step_time": 148.59657102404162
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"clip_ratio/high_max": 0.0012690311268670484,
|
| 1610 |
+
"clip_ratio/high_mean": 0.0003172577817167621,
|
| 1611 |
+
"clip_ratio/low_mean": 0.0006303573391051032,
|
| 1612 |
+
"clip_ratio/low_min": 0.0,
|
| 1613 |
+
"clip_ratio/region_mean": 0.0009476151208218653,
|
| 1614 |
+
"epoch": 0.6625,
|
| 1615 |
+
"grad_norm": 2.521996008180119,
|
| 1616 |
+
"kl": 0.019906243891455233,
|
| 1617 |
+
"learning_rate": 2.70750271011657e-07,
|
| 1618 |
+
"loss": 0.00020767131354659796,
|
| 1619 |
+
"step": 106,
|
| 1620 |
+
"step_time": 24.36162485089153
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"clip_ratio/high_max": 0.00122322316019563,
|
| 1624 |
+
"clip_ratio/high_mean": 0.00048566599070909433,
|
| 1625 |
+
"clip_ratio/low_mean": 0.000307607464492321,
|
| 1626 |
+
"clip_ratio/low_min": 0.0,
|
| 1627 |
+
"clip_ratio/region_mean": 0.0007932734552014153,
|
| 1628 |
+
"epoch": 0.66875,
|
| 1629 |
+
"grad_norm": 2.0435566149218234,
|
| 1630 |
+
"kl": 0.02649617218412459,
|
| 1631 |
+
"learning_rate": 2.6179179164927754e-07,
|
| 1632 |
+
"loss": 0.00032956473296508193,
|
| 1633 |
+
"step": 107,
|
| 1634 |
+
"step_time": 24.071168494876474
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"clip_ratio/high_max": 0.0005134374659974128,
|
| 1638 |
+
"clip_ratio/high_mean": 0.0001283593664993532,
|
| 1639 |
+
"clip_ratio/low_mean": 4.57763671875e-05,
|
| 1640 |
+
"clip_ratio/low_min": 0.0,
|
| 1641 |
+
"clip_ratio/region_mean": 0.0001741357336868532,
|
| 1642 |
+
"epoch": 0.675,
|
| 1643 |
+
"grad_norm": 0.6189195928860673,
|
| 1644 |
+
"kl": 0.016515519004315138,
|
| 1645 |
+
"learning_rate": 2.529311662014972e-07,
|
| 1646 |
+
"loss": 0.00017548140021972358,
|
| 1647 |
+
"step": 108,
|
| 1648 |
+
"step_time": 26.889955929014832
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"clip_ratio/high_max": 0.0015322828403441235,
|
| 1652 |
+
"clip_ratio/high_mean": 0.0005496275007317308,
|
| 1653 |
+
"clip_ratio/low_mean": 9.1552734375e-05,
|
| 1654 |
+
"clip_ratio/low_min": 0.0,
|
| 1655 |
+
"clip_ratio/region_mean": 0.0006411802351067308,
|
| 1656 |
+
"epoch": 0.68125,
|
| 1657 |
+
"grad_norm": 2.9551995077743616,
|
| 1658 |
+
"kl": 0.0322811680380255,
|
| 1659 |
+
"learning_rate": 2.441720345382089e-07,
|
| 1660 |
+
"loss": 0.0005817878991365433,
|
| 1661 |
+
"step": 109,
|
| 1662 |
+
"step_time": 23.195143049117178
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"clip_ratio/high_max": 0.002682091944734566,
|
| 1666 |
+
"clip_ratio/high_mean": 0.000866645928908838,
|
| 1667 |
+
"clip_ratio/low_mean": 0.0007261564023792744,
|
| 1668 |
+
"clip_ratio/low_min": 0.0,
|
| 1669 |
+
"clip_ratio/region_mean": 0.0015928023312881123,
|
| 1670 |
+
"epoch": 0.6875,
|
| 1671 |
+
"grad_norm": 3.132636702335117,
|
| 1672 |
+
"kl": 0.02283707750029862,
|
| 1673 |
+
"learning_rate": 2.355179948365189e-07,
|
| 1674 |
+
"loss": -0.00014597171684727073,
|
| 1675 |
+
"step": 110,
|
| 1676 |
+
"step_time": 20.656366089358926
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"clip_ratio/high_max": 0.005107845267048106,
|
| 1680 |
+
"clip_ratio/high_mean": 0.0014841695738141425,
|
| 1681 |
+
"clip_ratio/low_mean": 0.0004276201689208392,
|
| 1682 |
+
"clip_ratio/low_min": 0.0,
|
| 1683 |
+
"clip_ratio/region_mean": 0.0019117897536489181,
|
| 1684 |
+
"epoch": 0.69375,
|
| 1685 |
+
"grad_norm": 2.392570815096564,
|
| 1686 |
+
"kl": 0.019693527603521943,
|
| 1687 |
+
"learning_rate": 2.26972602102645e-07,
|
| 1688 |
+
"loss": 0.0002390172448940575,
|
| 1689 |
+
"step": 111,
|
| 1690 |
+
"step_time": 23.152191698551178
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"clip_ratio/high_max": 0.001587144666700624,
|
| 1694 |
+
"clip_ratio/high_mean": 0.00047844483560766093,
|
| 1695 |
+
"clip_ratio/low_mean": 0.0005006994379073149,
|
| 1696 |
+
"clip_ratio/low_min": 0.0,
|
| 1697 |
+
"clip_ratio/region_mean": 0.0009791442807909334,
|
| 1698 |
+
"epoch": 0.7,
|
| 1699 |
+
"grad_norm": 1.6053056260761815,
|
| 1700 |
+
"kl": 0.016719125560484827,
|
| 1701 |
+
"learning_rate": 2.1853936671155127e-07,
|
| 1702 |
+
"loss": 0.000181566399987787,
|
| 1703 |
+
"step": 112,
|
| 1704 |
+
"step_time": 25.206815155223012
|
| 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": 0.1796875,
|
| 1713 |
+
"completions/max_length": 2048.0,
|
| 1714 |
+
"completions/mean_length": 963.859375,
|
| 1715 |
+
"completions/min_length": 61.0,
|
| 1716 |
+
"epoch": 0.70625,
|
| 1717 |
+
"frac_reward_zero_std": 0.28125,
|
| 1718 |
+
"grad_norm": 4.700959710504933,
|
| 1719 |
+
"kl": 0.014897391898557544,
|
| 1720 |
+
"learning_rate": 2.1022175296491512e-07,
|
| 1721 |
+
"loss": 0.00014897342771291733,
|
| 1722 |
+
"reward": 0.51171875,
|
| 1723 |
+
"reward_std": 0.32970112562179565,
|
| 1724 |
+
"rewards/MajorityAccuracy/mean": 0.51171875,
|
| 1725 |
+
"rewards/MajorityAccuracy/std": 0.5008417963981628,
|
| 1726 |
+
"step": 113,
|
| 1727 |
+
"step_time": 147.80991449207067
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"clip_ratio/high_max": 0.005350639366952237,
|
| 1731 |
+
"clip_ratio/high_mean": 0.0016297472229780396,
|
| 1732 |
+
"clip_ratio/low_mean": 0.00018660418209037744,
|
| 1733 |
+
"clip_ratio/low_min": 0.0,
|
| 1734 |
+
"clip_ratio/region_mean": 0.0018163513850595336,
|
| 1735 |
+
"epoch": 0.7125,
|
| 1736 |
+
"grad_norm": 2.6967656822990085,
|
| 1737 |
+
"kl": 0.01593175297603011,
|
| 1738 |
+
"learning_rate": 2.0202317766802152e-07,
|
| 1739 |
+
"loss": 0.0005114333471283317,
|
| 1740 |
+
"step": 114,
|
| 1741 |
+
"step_time": 25.696516427677125
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"clip_ratio/high_max": 0.004435278955497779,
|
| 1745 |
+
"clip_ratio/high_mean": 0.0015059100733196829,
|
| 1746 |
+
"clip_ratio/low_mean": 0.0002976248779305024,
|
| 1747 |
+
"clip_ratio/low_min": 0.0,
|
| 1748 |
+
"clip_ratio/region_mean": 0.001803534963983111,
|
| 1749 |
+
"epoch": 0.71875,
|
| 1750 |
+
"grad_norm": 2.452078989170429,
|
| 1751 |
+
"kl": 0.021987432148307562,
|
| 1752 |
+
"learning_rate": 1.9394700872616853e-07,
|
| 1753 |
+
"loss": -0.0002527598408050835,
|
| 1754 |
+
"step": 115,
|
| 1755 |
+
"step_time": 20.869620594661683
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"clip_ratio/high_max": 0.0024426456657238305,
|
| 1759 |
+
"clip_ratio/high_mean": 0.0006106614164309576,
|
| 1760 |
+
"clip_ratio/low_mean": 0.00025417960569029674,
|
| 1761 |
+
"clip_ratio/low_min": 0.0,
|
| 1762 |
+
"clip_ratio/region_mean": 0.0008648410184832755,
|
| 1763 |
+
"epoch": 0.725,
|
| 1764 |
+
"grad_norm": 2.2922877564179487,
|
| 1765 |
+
"kl": 0.014657654566690326,
|
| 1766 |
+
"learning_rate": 1.8599656376116024e-07,
|
| 1767 |
+
"loss": 0.0001167621958302334,
|
| 1768 |
+
"step": 116,
|
| 1769 |
+
"step_time": 26.121913264505565
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"clip_ratio/high_max": 0.003312185035611037,
|
| 1773 |
+
"clip_ratio/high_mean": 0.0009557639950799057,
|
| 1774 |
+
"clip_ratio/low_mean": 9.1552734375e-05,
|
| 1775 |
+
"clip_ratio/low_min": 0.0,
|
| 1776 |
+
"clip_ratio/region_mean": 0.0010473167294549057,
|
| 1777 |
+
"epoch": 0.73125,
|
| 1778 |
+
"grad_norm": 1.7601861066767819,
|
| 1779 |
+
"kl": 0.013561386615037918,
|
| 1780 |
+
"learning_rate": 1.7817510874845582e-07,
|
| 1781 |
+
"loss": 0.00011909264139831066,
|
| 1782 |
+
"step": 117,
|
| 1783 |
+
"step_time": 25.90056585194543
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"clip_ratio/high_max": 0.0024355911882594228,
|
| 1787 |
+
"clip_ratio/high_mean": 0.0006768110688426532,
|
| 1788 |
+
"clip_ratio/low_mean": 0.0004510555154411122,
|
| 1789 |
+
"clip_ratio/low_min": 0.0,
|
| 1790 |
+
"clip_ratio/region_mean": 0.0011278665770078078,
|
| 1791 |
+
"epoch": 0.7375,
|
| 1792 |
+
"grad_norm": 2.53530808855517,
|
| 1793 |
+
"kl": 0.01908361993264407,
|
| 1794 |
+
"learning_rate": 1.7048585667553412e-07,
|
| 1795 |
+
"loss": 0.00016072207654360682,
|
| 1796 |
+
"step": 118,
|
| 1797 |
+
"step_time": 26.349508828949183
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"clip_ratio/high_max": 0.002359381403948646,
|
| 1801 |
+
"clip_ratio/high_mean": 0.0007609464937559096,
|
| 1802 |
+
"clip_ratio/low_mean": 0.0008956467172538396,
|
| 1803 |
+
"clip_ratio/low_min": 0.0,
|
| 1804 |
+
"clip_ratio/region_mean": 0.0016565932164667174,
|
| 1805 |
+
"epoch": 0.74375,
|
| 1806 |
+
"grad_norm": 2.8189323946370717,
|
| 1807 |
+
"kl": 0.01981773995794356,
|
| 1808 |
+
"learning_rate": 1.6293196622202632e-07,
|
| 1809 |
+
"loss": 0.00026135987718589604,
|
| 1810 |
+
"step": 119,
|
| 1811 |
+
"step_time": 25.248005941975862
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"clip_ratio/high_max": 0.002418089978164062,
|
| 1815 |
+
"clip_ratio/high_mean": 0.0006045224945410155,
|
| 1816 |
+
"clip_ratio/low_mean": 0.0005781989311799407,
|
| 1817 |
+
"clip_ratio/low_min": 0.0,
|
| 1818 |
+
"clip_ratio/region_mean": 0.0011827214257209562,
|
| 1819 |
+
"epoch": 0.75,
|
| 1820 |
+
"grad_norm": 2.5282220240022957,
|
| 1821 |
+
"kl": 0.021846559131518006,
|
| 1822 |
+
"learning_rate": 1.555165404621567e-07,
|
| 1823 |
+
"loss": 0.0005255404394119978,
|
| 1824 |
+
"step": 120,
|
| 1825 |
+
"step_time": 21.01740145124495
|
| 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": 0.203125,
|
| 1834 |
+
"completions/max_length": 2048.0,
|
| 1835 |
+
"completions/mean_length": 892.453125,
|
| 1836 |
+
"completions/min_length": 8.0,
|
| 1837 |
+
"epoch": 0.75625,
|
| 1838 |
+
"frac_reward_zero_std": 0.25,
|
| 1839 |
+
"grad_norm": 1.9773453277539026,
|
| 1840 |
+
"kl": 0.018411704571917653,
|
| 1841 |
+
"learning_rate": 1.4824262559002592e-07,
|
| 1842 |
+
"loss": 0.00018399418331682682,
|
| 1843 |
+
"reward": 0.51171875,
|
| 1844 |
+
"reward_std": 0.33850935101509094,
|
| 1845 |
+
"rewards/MajorityAccuracy/mean": 0.51171875,
|
| 1846 |
+
"rewards/MajorityAccuracy/std": 0.5008417963981628,
|
| 1847 |
+
"step": 121,
|
| 1848 |
+
"step_time": 145.47937744110823
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"clip_ratio/high_max": 0.0029582948627648875,
|
| 1852 |
+
"clip_ratio/high_mean": 0.0009141901064140256,
|
| 1853 |
+
"clip_ratio/low_mean": 6.899911750224419e-05,
|
| 1854 |
+
"clip_ratio/low_min": 0.0,
|
| 1855 |
+
"clip_ratio/region_mean": 0.000983189220278291,
|
| 1856 |
+
"epoch": 0.7625,
|
| 1857 |
+
"grad_norm": 2.982437146429989,
|
| 1858 |
+
"kl": 0.023795013432390988,
|
| 1859 |
+
"learning_rate": 1.4111320966826057e-07,
|
| 1860 |
+
"loss": -3.8972037145867944e-05,
|
| 1861 |
+
"step": 122,
|
| 1862 |
+
"step_time": 22.22421271726489
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"clip_ratio/high_max": 0.003593052999349311,
|
| 1866 |
+
"clip_ratio/high_mean": 0.0010209493411821313,
|
| 1867 |
+
"clip_ratio/low_mean": 0.0007826500732335262,
|
| 1868 |
+
"clip_ratio/low_min": 0.0,
|
| 1869 |
+
"clip_ratio/region_mean": 0.0018035993998637423,
|
| 1870 |
+
"epoch": 0.76875,
|
| 1871 |
+
"grad_norm": 2.8437587453103736,
|
| 1872 |
+
"kl": 0.02643446926958859,
|
| 1873 |
+
"learning_rate": 1.3413122140054217e-07,
|
| 1874 |
+
"loss": 0.00021958351135253906,
|
| 1875 |
+
"step": 123,
|
| 1876 |
+
"step_time": 21.667643836233765
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"clip_ratio/high_max": 0.0049036848795367405,
|
| 1880 |
+
"clip_ratio/high_mean": 0.0016762081322667655,
|
| 1881 |
+
"clip_ratio/low_mean": 0.00018232303773402236,
|
| 1882 |
+
"clip_ratio/low_min": 0.0,
|
| 1883 |
+
"clip_ratio/region_mean": 0.0018585311700007878,
|
| 1884 |
+
"epoch": 0.775,
|
| 1885 |
+
"grad_norm": 2.3327038285988695,
|
| 1886 |
+
"kl": 0.03281978843733668,
|
| 1887 |
+
"learning_rate": 1.272995289285202e-07,
|
| 1888 |
+
"loss": 0.0003964114293921739,
|
| 1889 |
+
"step": 124,
|
| 1890 |
+
"step_time": 20.526317009702325
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"clip_ratio/high_max": 0.0017071541224140674,
|
| 1894 |
+
"clip_ratio/high_mean": 0.0005365818869904615,
|
| 1895 |
+
"clip_ratio/low_mean": 0.0003077386791119352,
|
| 1896 |
+
"clip_ratio/low_min": 0.0,
|
| 1897 |
+
"clip_ratio/region_mean": 0.0008443205697403755,
|
| 1898 |
+
"epoch": 0.78125,
|
| 1899 |
+
"grad_norm": 3.332210609524098,
|
| 1900 |
+
"kl": 0.018155721598304808,
|
| 1901 |
+
"learning_rate": 1.2062093865360457e-07,
|
| 1902 |
+
"loss": 0.0003881789743900299,
|
| 1903 |
+
"step": 125,
|
| 1904 |
+
"step_time": 24.25803791405633
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"clip_ratio/high_max": 0.0016513787559233606,
|
| 1908 |
+
"clip_ratio/high_mean": 0.0004603370907716453,
|
| 1909 |
+
"clip_ratio/low_mean": 0.0004949598933308152,
|
| 1910 |
+
"clip_ratio/low_min": 0.0,
|
| 1911 |
+
"clip_ratio/region_mean": 0.0009552969841024606,
|
| 1912 |
+
"epoch": 0.7875,
|
| 1913 |
+
"grad_norm": 2.554985922081097,
|
| 1914 |
+
"kl": 0.0164392200531438,
|
| 1915 |
+
"learning_rate": 1.1409819408411897e-07,
|
| 1916 |
+
"loss": 0.0001943067618412897,
|
| 1917 |
+
"step": 126,
|
| 1918 |
+
"step_time": 26.3877339088358
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"clip_ratio/high_max": 0.00023191094805952162,
|
| 1922 |
+
"clip_ratio/high_mean": 5.7977737014880404e-05,
|
| 1923 |
+
"clip_ratio/low_mean": 0.0,
|
| 1924 |
+
"clip_ratio/low_min": 0.0,
|
| 1925 |
+
"clip_ratio/region_mean": 5.7977737014880404e-05,
|
| 1926 |
+
"epoch": 0.79375,
|
| 1927 |
+
"grad_norm": 1.5457688657922084,
|
| 1928 |
+
"kl": 0.028108223108574748,
|
| 1929 |
+
"learning_rate": 1.0773397470829143e-07,
|
| 1930 |
+
"loss": 0.0003492523683235049,
|
| 1931 |
+
"step": 127,
|
| 1932 |
+
"step_time": 26.839353243354708
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"clip_ratio/high_max": 0.005099613452330232,
|
| 1936 |
+
"clip_ratio/high_mean": 0.0018543468759162351,
|
| 1937 |
+
"clip_ratio/low_mean": 0.00030517578125,
|
| 1938 |
+
"clip_ratio/low_min": 0.0,
|
| 1939 |
+
"clip_ratio/region_mean": 0.002159522657166235,
|
| 1940 |
+
"epoch": 0.8,
|
| 1941 |
+
"grad_norm": 5.203744172754483,
|
| 1942 |
+
"kl": 0.03871213854290545,
|
| 1943 |
+
"learning_rate": 1.0153089489354256e-07,
|
| 1944 |
+
"loss": 0.0009392164647579193,
|
| 1945 |
+
"step": 128,
|
| 1946 |
+
"step_time": 26.460170093923807
|
| 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": 0.1875,
|
| 1955 |
+
"completions/max_length": 2048.0,
|
| 1956 |
+
"completions/mean_length": 957.71875,
|
| 1957 |
+
"completions/min_length": 61.0,
|
| 1958 |
+
"epoch": 0.80625,
|
| 1959 |
+
"frac_reward_zero_std": 0.25,
|
| 1960 |
+
"grad_norm": 2.6222123719647548,
|
| 1961 |
+
"kl": 0.018948738579638302,
|
| 1962 |
+
"learning_rate": 9.549150281252632e-08,
|
| 1963 |
+
"loss": 0.00018957722932100296,
|
| 1964 |
+
"reward": 0.4765625,
|
| 1965 |
+
"reward_std": 0.3504714369773865,
|
| 1966 |
+
"rewards/MajorityAccuracy/mean": 0.4765625,
|
| 1967 |
+
"rewards/MajorityAccuracy/std": 0.5004287362098694,
|
| 1968 |
+
"step": 129,
|
| 1969 |
+
"step_time": 144.40426534600556
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"clip_ratio/high_max": 0.007456095656380057,
|
| 1973 |
+
"clip_ratio/high_mean": 0.002116592862876132,
|
| 1974 |
+
"clip_ratio/low_mean": 0.00015413863002322614,
|
| 1975 |
+
"clip_ratio/low_min": 0.0,
|
| 1976 |
+
"clip_ratio/region_mean": 0.0022707314928993583,
|
| 1977 |
+
"epoch": 0.8125,
|
| 1978 |
+
"grad_norm": 2.5290767607280498,
|
| 1979 |
+
"kl": 0.014481889083981514,
|
| 1980 |
+
"learning_rate": 8.961827939636196e-08,
|
| 1981 |
+
"loss": 0.0003983275964856148,
|
| 1982 |
+
"step": 130,
|
| 1983 |
+
"step_time": 26.437537347432226
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"clip_ratio/high_max": 0.0018194128424511291,
|
| 1987 |
+
"clip_ratio/high_mean": 0.0004548532106127823,
|
| 1988 |
+
"clip_ratio/low_mean": 0.0008672485673741903,
|
| 1989 |
+
"clip_ratio/low_min": 0.0,
|
| 1990 |
+
"clip_ratio/region_mean": 0.001322101779805962,
|
| 1991 |
+
"epoch": 0.81875,
|
| 1992 |
+
"grad_norm": 2.506016914945286,
|
| 1993 |
+
"kl": 0.014930791803635657,
|
| 1994 |
+
"learning_rate": 8.391363731548811e-08,
|
| 1995 |
+
"loss": -0.0001332043466391042,
|
| 1996 |
+
"step": 131,
|
| 1997 |
+
"step_time": 26.393070542253554
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"clip_ratio/high_max": 0.0023377264151349664,
|
| 2001 |
+
"clip_ratio/high_mean": 0.0007157341315178201,
|
| 2002 |
+
"clip_ratio/low_mean": 0.0,
|
| 2003 |
+
"clip_ratio/low_min": 0.0,
|
| 2004 |
+
"clip_ratio/region_mean": 0.0007157341315178201,
|
| 2005 |
+
"epoch": 0.825,
|
| 2006 |
+
"grad_norm": 2.0788870010057363,
|
| 2007 |
+
"kl": 0.02226361888460815,
|
| 2008 |
+
"learning_rate": 7.837991998855897e-08,
|
| 2009 |
+
"loss": 0.00038806558586657047,
|
| 2010 |
+
"step": 132,
|
| 2011 |
+
"step_time": 18.64868103293702
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"clip_ratio/high_max": 0.0013784110342385247,
|
| 2015 |
+
"clip_ratio/high_mean": 0.0003826776519417763,
|
| 2016 |
+
"clip_ratio/low_mean": 0.00029164158695493825,
|
| 2017 |
+
"clip_ratio/low_min": 0.0,
|
| 2018 |
+
"clip_ratio/region_mean": 0.0006743192316207569,
|
| 2019 |
+
"epoch": 0.83125,
|
| 2020 |
+
"grad_norm": 1.864216434165241,
|
| 2021 |
+
"kl": 0.02279029111377895,
|
| 2022 |
+
"learning_rate": 7.301940061978722e-08,
|
| 2023 |
+
"loss": 0.0002834592596627772,
|
| 2024 |
+
"step": 133,
|
| 2025 |
+
"step_time": 23.989821745082736
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"clip_ratio/high_max": 0.0014006289347889833,
|
| 2029 |
+
"clip_ratio/high_mean": 0.00036584498775482643,
|
| 2030 |
+
"clip_ratio/low_mean": 0.00017641813974478282,
|
| 2031 |
+
"clip_ratio/low_min": 0.0,
|
| 2032 |
+
"clip_ratio/region_mean": 0.0005422631293185987,
|
| 2033 |
+
"epoch": 0.8375,
|
| 2034 |
+
"grad_norm": 1.9731489869023036,
|
| 2035 |
+
"kl": 0.015725456061773002,
|
| 2036 |
+
"learning_rate": 6.783428126513125e-08,
|
| 2037 |
+
"loss": 0.00021756267233286053,
|
| 2038 |
+
"step": 134,
|
| 2039 |
+
"step_time": 26.384173767641187
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"clip_ratio/high_max": 0.0036001861590193585,
|
| 2043 |
+
"clip_ratio/high_mean": 0.0011301446065772325,
|
| 2044 |
+
"clip_ratio/low_mean": 0.00022066082965466194,
|
| 2045 |
+
"clip_ratio/low_min": 0.0,
|
| 2046 |
+
"clip_ratio/region_mean": 0.0013508054398698732,
|
| 2047 |
+
"epoch": 0.84375,
|
| 2048 |
+
"grad_norm": 2.6833280318845723,
|
| 2049 |
+
"kl": 0.016115796053782105,
|
| 2050 |
+
"learning_rate": 6.282669192770895e-08,
|
| 2051 |
+
"loss": 0.0002916315570473671,
|
| 2052 |
+
"step": 135,
|
| 2053 |
+
"step_time": 26.149669816717505
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"clip_ratio/high_max": 0.001299136783927679,
|
| 2057 |
+
"clip_ratio/high_mean": 0.00032478419598191977,
|
| 2058 |
+
"clip_ratio/low_mean": 0.00021537522479775362,
|
| 2059 |
+
"clip_ratio/low_min": 0.0,
|
| 2060 |
+
"clip_ratio/region_mean": 0.0005401594135037158,
|
| 2061 |
+
"epoch": 0.85,
|
| 2062 |
+
"grad_norm": 2.9868806677288515,
|
| 2063 |
+
"kl": 0.013034120202064514,
|
| 2064 |
+
"learning_rate": 5.799868968281074e-08,
|
| 2065 |
+
"loss": 0.00031129387207329273,
|
| 2066 |
+
"step": 136,
|
| 2067 |
+
"step_time": 20.73135517630726
|
| 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": 0.1953125,
|
| 2076 |
+
"completions/max_length": 2048.0,
|
| 2077 |
+
"completions/mean_length": 980.27734375,
|
| 2078 |
+
"completions/min_length": 75.0,
|
| 2079 |
+
"epoch": 0.85625,
|
| 2080 |
+
"frac_reward_zero_std": 0.25,
|
| 2081 |
+
"grad_norm": 4.440131836192564,
|
| 2082 |
+
"kl": 0.015582472085952759,
|
| 2083 |
+
"learning_rate": 5.335225783287051e-08,
|
| 2084 |
+
"loss": 0.00015592118143104017,
|
| 2085 |
+
"reward": 0.3984375,
|
| 2086 |
+
"reward_std": 0.34416463971138,
|
| 2087 |
+
"rewards/MajorityAccuracy/mean": 0.3984375,
|
| 2088 |
+
"rewards/MajorityAccuracy/std": 0.4905354082584381,
|
| 2089 |
+
"step": 137,
|
| 2090 |
+
"step_time": 142.57792079774663
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"clip_ratio/high_max": 0.0021266622643452138,
|
| 2094 |
+
"clip_ratio/high_mean": 0.0006507903963210993,
|
| 2095 |
+
"clip_ratio/low_mean": 5.139802669873461e-05,
|
| 2096 |
+
"clip_ratio/low_min": 0.0,
|
| 2097 |
+
"clip_ratio/region_mean": 0.0007021884157438762,
|
| 2098 |
+
"epoch": 0.8625,
|
| 2099 |
+
"grad_norm": 2.9663982547300054,
|
| 2100 |
+
"kl": 0.01983001548796892,
|
| 2101 |
+
"learning_rate": 4.888930509274125e-08,
|
| 2102 |
+
"loss": 0.0005038690287619829,
|
| 2103 |
+
"step": 138,
|
| 2104 |
+
"step_time": 23.535357345361263
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"clip_ratio/high_max": 0.003666716511361301,
|
| 2108 |
+
"clip_ratio/high_mean": 0.0009166791278403252,
|
| 2109 |
+
"clip_ratio/low_mean": 0.00045362966920947656,
|
| 2110 |
+
"clip_ratio/low_min": 0.0,
|
| 2111 |
+
"clip_ratio/region_mean": 0.0013703087970498018,
|
| 2112 |
+
"epoch": 0.86875,
|
| 2113 |
+
"grad_norm": 4.395198025651034,
|
| 2114 |
+
"kl": 0.01521462865639478,
|
| 2115 |
+
"learning_rate": 4.4611664805611794e-08,
|
| 2116 |
+
"loss": 0.00011539517436176538,
|
| 2117 |
+
"step": 139,
|
| 2118 |
+
"step_time": 24.38248068233952
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"clip_ratio/high_max": 0.0034259310050401837,
|
| 2122 |
+
"clip_ratio/high_mean": 0.001215038020745851,
|
| 2123 |
+
"clip_ratio/low_mean": 0.00024632045824546367,
|
| 2124 |
+
"clip_ratio/low_min": 0.0,
|
| 2125 |
+
"clip_ratio/region_mean": 0.0014613584717153572,
|
| 2126 |
+
"epoch": 0.875,
|
| 2127 |
+
"grad_norm": 3.6403464235818257,
|
| 2128 |
+
"kl": 0.016983183682896197,
|
| 2129 |
+
"learning_rate": 4.0521094189884696e-08,
|
| 2130 |
+
"loss": 0.0003202706575393677,
|
| 2131 |
+
"step": 140,
|
| 2132 |
+
"step_time": 23.99797709006816
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"clip_ratio/high_max": 0.0012142655905336142,
|
| 2136 |
+
"clip_ratio/high_mean": 0.0004400292818900198,
|
| 2137 |
+
"clip_ratio/low_mean": 0.0004892739361821441,
|
| 2138 |
+
"clip_ratio/low_min": 0.0,
|
| 2139 |
+
"clip_ratio/region_mean": 0.0009293032071582275,
|
| 2140 |
+
"epoch": 0.88125,
|
| 2141 |
+
"grad_norm": 2.0926981803867863,
|
| 2142 |
+
"kl": 0.021027785260230303,
|
| 2143 |
+
"learning_rate": 3.6619273617325695e-08,
|
| 2144 |
+
"loss": 0.00012682715896517038,
|
| 2145 |
+
"step": 141,
|
| 2146 |
+
"step_time": 21.527921266388148
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"clip_ratio/high_max": 0.0036849585667368956,
|
| 2150 |
+
"clip_ratio/high_mean": 0.001146635711847921,
|
| 2151 |
+
"clip_ratio/low_mean": 0.0003837782460323069,
|
| 2152 |
+
"clip_ratio/low_min": 0.0,
|
| 2153 |
+
"clip_ratio/region_mean": 0.001530413954242249,
|
| 2154 |
+
"epoch": 0.8875,
|
| 2155 |
+
"grad_norm": 2.819442970345561,
|
| 2156 |
+
"kl": 0.017015724326483905,
|
| 2157 |
+
"learning_rate": 3.2907805922781476e-08,
|
| 2158 |
+
"loss": -1.2753240298479795e-05,
|
| 2159 |
+
"step": 142,
|
| 2160 |
+
"step_time": 24.03731997963041
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"clip_ratio/high_max": 0.0012342712725512683,
|
| 2164 |
+
"clip_ratio/high_mean": 0.0003666533302748576,
|
| 2165 |
+
"clip_ratio/low_mean": 0.0,
|
| 2166 |
+
"clip_ratio/low_min": 0.0,
|
| 2167 |
+
"clip_ratio/region_mean": 0.0003666533302748576,
|
| 2168 |
+
"epoch": 0.89375,
|
| 2169 |
+
"grad_norm": 1.8885223245714358,
|
| 2170 |
+
"kl": 0.012018601410090923,
|
| 2171 |
+
"learning_rate": 2.9388215745748345e-08,
|
| 2172 |
+
"loss": 0.00021350837778300047,
|
| 2173 |
+
"step": 143,
|
| 2174 |
+
"step_time": 26.27714396128431
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"clip_ratio/high_max": 0.0026151395577471703,
|
| 2178 |
+
"clip_ratio/high_mean": 0.000795660242147278,
|
| 2179 |
+
"clip_ratio/low_mean": 5.59734326088801e-05,
|
| 2180 |
+
"clip_ratio/low_min": 0.0,
|
| 2181 |
+
"clip_ratio/region_mean": 0.0008516336747561581,
|
| 2182 |
+
"epoch": 0.9,
|
| 2183 |
+
"grad_norm": 1.66508541320512,
|
| 2184 |
+
"kl": 0.016449726885184646,
|
| 2185 |
+
"learning_rate": 2.6061948904063658e-08,
|
| 2186 |
+
"loss": 0.00025443389313295484,
|
| 2187 |
+
"step": 144,
|
| 2188 |
+
"step_time": 23.805013419128954
|
| 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": 0.34375,
|
| 2197 |
+
"completions/max_length": 2048.0,
|
| 2198 |
+
"completions/mean_length": 1327.4140625,
|
| 2199 |
+
"completions/min_length": 73.0,
|
| 2200 |
+
"epoch": 0.90625,
|
| 2201 |
+
"frac_reward_zero_std": 0.25,
|
| 2202 |
+
"grad_norm": 1.5991297997601475,
|
| 2203 |
+
"kl": 0.012538798153400421,
|
| 2204 |
+
"learning_rate": 2.293037179997559e-08,
|
| 2205 |
+
"loss": 0.00012535843416117132,
|
| 2206 |
+
"reward": 0.40625,
|
| 2207 |
+
"reward_std": 0.32260435819625854,
|
| 2208 |
+
"rewards/MajorityAccuracy/mean": 0.40625,
|
| 2209 |
+
"rewards/MajorityAccuracy/std": 0.49209436774253845,
|
| 2210 |
+
"step": 145,
|
| 2211 |
+
"step_time": 154.91213830793276
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"clip_ratio/high_max": 0.0021942442399449646,
|
| 2215 |
+
"clip_ratio/high_mean": 0.0006614763187826611,
|
| 2216 |
+
"clip_ratio/low_mean": 0.0001276919720112346,
|
| 2217 |
+
"clip_ratio/low_min": 0.0,
|
| 2218 |
+
"clip_ratio/region_mean": 0.0007891682835179381,
|
| 2219 |
+
"epoch": 0.9125,
|
| 2220 |
+
"grad_norm": 1.555371250204115,
|
| 2221 |
+
"kl": 0.019821469439193606,
|
| 2222 |
+
"learning_rate": 1.9994770858837107e-08,
|
| 2223 |
+
"loss": 0.0003070698876399547,
|
| 2224 |
+
"step": 146,
|
| 2225 |
+
"step_time": 26.11635827831924
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"clip_ratio/high_max": 0.0018832191708497703,
|
| 2229 |
+
"clip_ratio/high_mean": 0.0004708047927124426,
|
| 2230 |
+
"clip_ratio/low_mean": 0.0002698006428545341,
|
| 2231 |
+
"clip_ratio/low_min": 0.0,
|
| 2232 |
+
"clip_ratio/region_mean": 0.0007406054355669767,
|
| 2233 |
+
"epoch": 0.91875,
|
| 2234 |
+
"grad_norm": 2.5515617805926705,
|
| 2235 |
+
"kl": 0.020527286920696497,
|
| 2236 |
+
"learning_rate": 1.725635200065323e-08,
|
| 2237 |
+
"loss": 0.0005617712158709764,
|
| 2238 |
+
"step": 147,
|
| 2239 |
+
"step_time": 26.58870870573446
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"clip_ratio/high_max": 0.0012422991276253015,
|
| 2243 |
+
"clip_ratio/high_mean": 0.00040005134360399097,
|
| 2244 |
+
"clip_ratio/low_mean": 0.0001983642578125,
|
| 2245 |
+
"clip_ratio/low_min": 0.0,
|
| 2246 |
+
"clip_ratio/region_mean": 0.000598415601416491,
|
| 2247 |
+
"epoch": 0.925,
|
| 2248 |
+
"grad_norm": 1.496804541212642,
|
| 2249 |
+
"kl": 0.013821870204992592,
|
| 2250 |
+
"learning_rate": 1.4716240144699187e-08,
|
| 2251 |
+
"loss": 0.00022093627194408327,
|
| 2252 |
+
"step": 148,
|
| 2253 |
+
"step_time": 26.871787667274475
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"clip_ratio/high_max": 0.00022813289251644164,
|
| 2257 |
+
"clip_ratio/high_mean": 5.703322312911041e-05,
|
| 2258 |
+
"clip_ratio/low_mean": 5.049839637649711e-05,
|
| 2259 |
+
"clip_ratio/low_min": 0.0,
|
| 2260 |
+
"clip_ratio/region_mean": 0.00010753161950560752,
|
| 2261 |
+
"epoch": 0.93125,
|
| 2262 |
+
"grad_norm": 1.627971014240769,
|
| 2263 |
+
"kl": 0.01196467806585133,
|
| 2264 |
+
"learning_rate": 1.2375478747413015e-08,
|
| 2265 |
+
"loss": 0.00041129649616777897,
|
| 2266 |
+
"step": 149,
|
| 2267 |
+
"step_time": 26.035625459626317
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"clip_ratio/high_max": 0.003374036430614069,
|
| 2271 |
+
"clip_ratio/high_mean": 0.0009122547635342926,
|
| 2272 |
+
"clip_ratio/low_mean": 0.0005696548978448845,
|
| 2273 |
+
"clip_ratio/low_min": 0.0,
|
| 2274 |
+
"clip_ratio/region_mean": 0.0014819096759310924,
|
| 2275 |
+
"epoch": 0.9375,
|
| 2276 |
+
"grad_norm": 1.3659531621905865,
|
| 2277 |
+
"kl": 0.01259796682279557,
|
| 2278 |
+
"learning_rate": 1.0235029373752757e-08,
|
| 2279 |
+
"loss": -1.2519310985226184e-05,
|
| 2280 |
+
"step": 150,
|
| 2281 |
+
"step_time": 26.784390155225992
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"clip_ratio/high_max": 0.0008043735433602706,
|
| 2285 |
+
"clip_ratio/high_mean": 0.00023374751253868453,
|
| 2286 |
+
"clip_ratio/low_mean": 0.0002720021875575185,
|
| 2287 |
+
"clip_ratio/low_min": 0.0,
|
| 2288 |
+
"clip_ratio/region_mean": 0.0005057497110101394,
|
| 2289 |
+
"epoch": 0.94375,
|
| 2290 |
+
"grad_norm": 1.5204546015157079,
|
| 2291 |
+
"kl": 0.022542449412867427,
|
| 2292 |
+
"learning_rate": 8.295771302193721e-09,
|
| 2293 |
+
"loss": 4.762128810398281e-06,
|
| 2294 |
+
"step": 151,
|
| 2295 |
+
"step_time": 26.828526579774916
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"clip_ratio/high_max": 0.0007785541092744097,
|
| 2299 |
+
"clip_ratio/high_mean": 0.00023893334946478717,
|
| 2300 |
+
"clip_ratio/low_mean": 0.00034330898779444396,
|
| 2301 |
+
"clip_ratio/low_min": 0.0,
|
| 2302 |
+
"clip_ratio/region_mean": 0.0005822423372592311,
|
| 2303 |
+
"epoch": 0.95,
|
| 2304 |
+
"grad_norm": 2.056995025581735,
|
| 2305 |
+
"kl": 0.013203594484366477,
|
| 2306 |
+
"learning_rate": 6.558501163527963e-09,
|
| 2307 |
+
"loss": 0.00017879066581372172,
|
| 2308 |
+
"step": 152,
|
| 2309 |
+
"step_time": 22.46877649659291
|
| 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": 0.2578125,
|
| 2318 |
+
"completions/max_length": 2048.0,
|
| 2319 |
+
"completions/mean_length": 1100.63671875,
|
| 2320 |
+
"completions/min_length": 39.0,
|
| 2321 |
+
"epoch": 0.95625,
|
| 2322 |
+
"frac_reward_zero_std": 0.3125,
|
| 2323 |
+
"grad_norm": 2.0861300163269747,
|
| 2324 |
+
"kl": 0.017137780087068677,
|
| 2325 |
+
"learning_rate": 5.023932613615445e-09,
|
| 2326 |
+
"loss": 0.00017138004477601498,
|
| 2327 |
+
"reward": 0.50390625,
|
| 2328 |
+
"reward_std": 0.32837191224098206,
|
| 2329 |
+
"rewards/MajorityAccuracy/mean": 0.50390625,
|
| 2330 |
+
"rewards/MajorityAccuracy/std": 0.5009641051292419,
|
| 2331 |
+
"step": 153,
|
| 2332 |
+
"step_time": 151.1778554720804
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"clip_ratio/high_max": 0.002739070769166574,
|
| 2336 |
+
"clip_ratio/high_mean": 0.0006847676922916435,
|
| 2337 |
+
"clip_ratio/low_mean": 0.00014070523320697248,
|
| 2338 |
+
"clip_ratio/low_min": 0.0,
|
| 2339 |
+
"clip_ratio/region_mean": 0.000825472925498616,
|
| 2340 |
+
"epoch": 0.9625,
|
| 2341 |
+
"grad_norm": 2.7658369518203596,
|
| 2342 |
+
"kl": 0.025747207226231694,
|
| 2343 |
+
"learning_rate": 3.6926960402202666e-09,
|
| 2344 |
+
"loss": 0.00047253823140636086,
|
| 2345 |
+
"step": 154,
|
| 2346 |
+
"step_time": 25.933444660622627
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"clip_ratio/high_max": 0.0018348658049944788,
|
| 2350 |
+
"clip_ratio/high_mean": 0.0004587164512486197,
|
| 2351 |
+
"clip_ratio/low_mean": 7.860199912101962e-05,
|
| 2352 |
+
"clip_ratio/low_min": 0.0,
|
| 2353 |
+
"clip_ratio/region_mean": 0.0005373184503696393,
|
| 2354 |
+
"epoch": 0.96875,
|
| 2355 |
+
"grad_norm": 1.5257599054930588,
|
| 2356 |
+
"kl": 0.016331729595549405,
|
| 2357 |
+
"learning_rate": 2.5653383040524224e-09,
|
| 2358 |
+
"loss": 0.0004008888790849596,
|
| 2359 |
+
"step": 155,
|
| 2360 |
+
"step_time": 26.112165028229356
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"clip_ratio/high_max": 0.0011859245350933634,
|
| 2364 |
+
"clip_ratio/high_mean": 0.00031201293859339785,
|
| 2365 |
+
"clip_ratio/low_mean": 0.00019531652287696488,
|
| 2366 |
+
"clip_ratio/low_min": 0.0,
|
| 2367 |
+
"clip_ratio/region_mean": 0.0005073294596513733,
|
| 2368 |
+
"epoch": 0.975,
|
| 2369 |
+
"grad_norm": 1.8531364029322832,
|
| 2370 |
+
"kl": 0.0224163883831352,
|
| 2371 |
+
"learning_rate": 1.642322514122385e-09,
|
| 2372 |
+
"loss": 0.00025151376030407846,
|
| 2373 |
+
"step": 156,
|
| 2374 |
+
"step_time": 24.848584819119424
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"clip_ratio/high_max": 0.0033258610928896815,
|
| 2378 |
+
"clip_ratio/high_mean": 0.0011526347661856562,
|
| 2379 |
+
"clip_ratio/low_mean": 0.00040354720840696245,
|
| 2380 |
+
"clip_ratio/low_min": 0.0,
|
| 2381 |
+
"clip_ratio/region_mean": 0.001556182003696449,
|
| 2382 |
+
"epoch": 0.98125,
|
| 2383 |
+
"grad_norm": 3.0348025655673396,
|
| 2384 |
+
"kl": 0.018698840984143317,
|
| 2385 |
+
"learning_rate": 9.240278374995636e-10,
|
| 2386 |
+
"loss": 0.00045529764611274004,
|
| 2387 |
+
"step": 157,
|
| 2388 |
+
"step_time": 21.268560386262834
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"clip_ratio/high_max": 0.0016404597408836707,
|
| 2392 |
+
"clip_ratio/high_mean": 0.0005139406748639885,
|
| 2393 |
+
"clip_ratio/low_mean": 0.00020405939721968025,
|
| 2394 |
+
"clip_ratio/low_min": 0.0,
|
| 2395 |
+
"clip_ratio/region_mean": 0.0007180000648077112,
|
| 2396 |
+
"epoch": 0.9875,
|
| 2397 |
+
"grad_norm": 2.246297913136839,
|
| 2398 |
+
"kl": 0.014192912611179054,
|
| 2399 |
+
"learning_rate": 4.1074934355384006e-10,
|
| 2400 |
+
"loss": 0.00037385508767329156,
|
| 2401 |
+
"step": 158,
|
| 2402 |
+
"step_time": 26.57611665641889
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"clip_ratio/high_max": 0.0005511196213774383,
|
| 2406 |
+
"clip_ratio/high_mean": 0.0001778795376594644,
|
| 2407 |
+
"clip_ratio/low_mean": 0.0002217830315203173,
|
| 2408 |
+
"clip_ratio/low_min": 0.0,
|
| 2409 |
+
"clip_ratio/region_mean": 0.0003996625709987711,
|
| 2410 |
+
"epoch": 0.99375,
|
| 2411 |
+
"grad_norm": 1.5731577186624661,
|
| 2412 |
+
"kl": 0.017033958225511014,
|
| 2413 |
+
"learning_rate": 1.0269788274358537e-10,
|
| 2414 |
+
"loss": 0.0001425997179467231,
|
| 2415 |
+
"step": 159,
|
| 2416 |
+
"step_time": 26.156078550498933
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"clip_ratio/high_max": 0.0012091316311853006,
|
| 2420 |
+
"clip_ratio/high_mean": 0.0003247487584303599,
|
| 2421 |
+
"clip_ratio/low_mean": 0.00023506835896114353,
|
| 2422 |
+
"clip_ratio/low_min": 0.0,
|
| 2423 |
+
"clip_ratio/region_mean": 0.0005598171192104928,
|
| 2424 |
+
"epoch": 1.0,
|
| 2425 |
+
"grad_norm": 1.0794931557478242,
|
| 2426 |
+
"kl": 0.013014320749789476,
|
| 2427 |
+
"learning_rate": 0.0,
|
| 2428 |
+
"loss": 3.9054568333085626e-05,
|
| 2429 |
+
"step": 160,
|
| 2430 |
+
"step_time": 26.677763238549232
|
| 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 |
+
}
|