Add m1_proposer_answer round 1 Solver weights

Browse files

Files changed (15) hide show

.gitattributes +1 -0
m1_proposer_answer/round_1/args.json +556 -0
m1_proposer_answer/round_1/chat_template.jinja +154 -0
m1_proposer_answer/round_1/config.json +117 -0
m1_proposer_answer/round_1/generation_config.json +9 -0
m1_proposer_answer/round_1/model-00001-of-00004.safetensors +3 -0
m1_proposer_answer/round_1/model-00002-of-00004.safetensors +3 -0
m1_proposer_answer/round_1/model-00003-of-00004.safetensors +3 -0
m1_proposer_answer/round_1/model-00004-of-00004.safetensors +3 -0
m1_proposer_answer/round_1/model.safetensors.index.json +768 -0
m1_proposer_answer/round_1/preprocessor_config.json +21 -0
m1_proposer_answer/round_1/processor_config.json +61 -0
m1_proposer_answer/round_1/tokenizer.json +3 -0
m1_proposer_answer/round_1/tokenizer_config.json +33 -0
m1_proposer_answer/round_1/trainer_state.json +2454 -0

.gitattributes CHANGED Viewed

@@ -49,3 +49,4 @@ c4_no_difficulty_filter/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -te
 c4_no_difficulty_filter/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 a4_fixed_images/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 m2_gpt_answer/round_1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

 c4_no_difficulty_filter/round_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 a4_fixed_images/round_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 m2_gpt_answer/round_1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+m1_proposer_answer/round_1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

m1_proposer_answer/round_1/args.json ADDED Viewed

	@@ -0,0 +1,556 @@

+{
+  "output_dir": "/data1/xiangding/cvis-ablate/runs/m1_proposer_answer/run_m1_proposer_answer_4g/iteration_001/solver",
+  "per_device_train_batch_size": 1,
+  "num_train_epochs": 3.0,
+  "max_steps": 160,
+  "learning_rate": 1e-06,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_steps": 0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "optim_target_modules": null,
+  "gradient_accumulation_steps": 8,
+  "average_tokens_across_devices": true,
+  "max_grad_norm": 1.0,
+  "label_smoothing_factor": 0.0,
+  "bf16": true,
+  "fp16": false,
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "use_liger_kernel": false,
+  "liger_kernel_config": null,
+  "use_cache": false,
+  "neftune_noise_alpha": null,
+  "torch_empty_cache_steps": null,
+  "auto_find_batch_size": false,
+  "logging_strategy": "steps",
+  "logging_steps": 1,
+  "logging_first_step": true,
+  "log_on_each_node": true,
+  "logging_nan_inf_filter": true,
+  "include_num_input_tokens_seen": false,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "disable_tqdm": null,
+  "report_to": [
+    "tensorboard"
+  ],
+  "run_name": "/data1/xiangding/cvis-ablate/runs/m1_proposer_answer/run_m1_proposer_answer_4g/iteration_001/solver",
+  "project": "huggingface",
+  "trackio_space_id": null,
+  "trackio_bucket_id": null,
+  "trackio_static_space_id": null,
+  "eval_strategy": "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": null,
+  "include_for_metrics": [],
+  "batch_eval_metrics": false,
+  "save_only_model": false,
+  "save_strategy": "steps",
+  "save_steps": 16.0,
+  "save_on_each_node": false,
+  "save_total_limit": 1,
+  "enable_jit_checkpoint": false,
+  "push_to_hub": false,
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_always_push": false,
+  "hub_revision": null,
+  "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": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "dataloader_drop_last": false,
+  "dataloader_num_workers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": true,
+  "dataloader_prefetch_factor": null,
+  "dataloader_multiprocessing_context": null,
+  "dataloader_in_order": true,
+  "remove_unused_columns": false,
+  "label_names": null,
+  "train_sampling_strategy": "random",
+  "length_column_name": "length",
+  "ddp_find_unused_parameters": false,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_static_graph": null,
+  "ddp_backend": null,
+  "ddp_timeout": 18000000,
+  "fsdp": [],
+  "fsdp_config": null,
+  "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": "auto",
+      "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": null,
+  "skip_memory_metrics": true,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "resume_from_checkpoint": null,
+  "local_rank": 0,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "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": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": "grpo",
+  "mrl_dims": null,
+  "eval_metric": null,
+  "callbacks": [
+    "cvis_step_timing"
+  ],
+  "early_stop_interval": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "tuner_type": "full",
+  "use_galore": false,
+  "galore_target_modules": null,
+  "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/m1_proposer_answer/run_m1_proposer_answer_4g/iteration_001/solver/runs",
+  "warmup_ratio": 0.03,
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "/data1/xiangding/cvis-ablate/models/Qwen3.5-9B",
+  "model_type": "qwen3_5",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "experts_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen3_5",
+  "system": "Base your inference and reasoning strictly on the provided image. Provide the final answer in <answer> and </answer>.",
+  "max_length": 2048,
+  "truncation_strategy": "left",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": false,
+  "loss_scale": "last_round+ignore_empty_think",
+  "sequence_parallel_size": 1,
+  "is_binary_loss_scale": null,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": false,
+  "preserve_thinking": null,
+  "add_non_thinking_prefix": true,
+  "disable_ignore_empty_think": false,
+  "dataset": [
+    "/data1/xiangding/cvis-ablate/runs/m1_proposer_answer/run_m1_proposer_answer_4g/iteration_001/solver/train.jsonl"
+  ],
+  "val_dataset": [],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "dataset_num_proc": 1,
+  "load_from_cache_file": false,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "disable_auto_column_mapping": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "decision_drop_instructions": 0.0,
+  "decision_subsample_options": 0,
+  "decision_state_as_text": 0.0,
+  "decision_shuffle_fields": false,
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 2048,
+  "temperature": 1.0,
+  "top_k": -1,
+  "top_p": 1.0,
+  "repetition_penalty": 1.0,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "structured_outputs_regex": null,
+  "adapters": [],
+  "external_plugins": [
+    "/data1/xiangding/cvis-ablate/repo/cvis/plugins/swift_reward.py"
+  ],
+  "custom_register_path": [],
+  "model_kwargs": {},
+  "enable_npu_model_patch": true,
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "packing_strategy": "binpack",
+  "lazy_tokenize": true,
+  "use_hf": false,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [
+    "model.visual.merger"
+  ],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": false,
+  "freeze_aligner": false,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "target_parameters": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": "ms-swift",
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_notification_method": null,
+  "swanlab_webhook_url": null,
+  "swanlab_secret": null,
+  "swanlab_sender_email": null,
+  "swanlab_receiver_email": null,
+  "swanlab_smtp_server": null,
+  "swanlab_smtp_port": null,
+  "swanlab_email_language": "zh",
+  "swanlab_mode": "cloud",
+  "add_version": false,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "reward_model": null,
+  "reward_adapters": [],
+  "reward_model_type": null,
+  "reward_model_revision": null,
+  "reward_template": null,
+  "num_ppo_epochs": 4,
+  "whiten_rewards": false,
+  "kl_coef": 0.05,
+  "cliprange": 0.2,
+  "vf_coef": 0.1,
+  "cliprange_value": 0.2,
+  "gamma": 1.0,
+  "lam": 0.95,
+  "num_mini_batches": 1,
+  "local_rollout_forward_batch_size": 64,
+  "num_sample_generations": 10,
+  "response_length": 2048,
+  "missing_eos_penalty": null,
+  "vllm_gpu_memory_utilization": 0.2,
+  "vllm_tensor_parallel_size": 1,
+  "vllm_pipeline_parallel_size": 1,
+  "vllm_enable_expert_parallel": false,
+  "vllm_max_num_seqs": null,
+  "vllm_max_model_len": 4096,
+  "vllm_disable_custom_all_reduce": true,
+  "vllm_enforce_eager": false,
+  "vllm_limit_mm_per_prompt": null,
+  "vllm_max_lora_rank": 16,
+  "vllm_enable_prefix_caching": true,
+  "vllm_use_async_engine": null,
+  "vllm_quantization": null,
+  "vllm_reasoning_parser": null,
+  "vllm_disable_cascade_attn": false,
+  "vllm_mm_processor_cache_gb": null,
+  "vllm_speculative_config": null,
+  "vllm_engine_kwargs": {},
+  "vllm_data_parallel_size": 1,
+  "min_p": 0.0,
+  "use_vllm": true,
+  "vllm_mode": "colocate",
+  "vllm_enable_lora": false,
+  "vllm_server_base_url": null,
+  "vllm_server_host": null,
+  "vllm_server_port": [
+    8000
+  ],
+  "vllm_server_timeout": 240.0,
+  "vllm_server_group_port": null,
+  "enable_flattened_weight_sync": true,
+  "async_generate": false,
+  "sleep_level": 0,
+  "move_model_batches": null,
+  "offload_optimizer": false,
+  "offload_model": false,
+  "wandb_log_unique_prompts": null,
+  "generation_batch_size": 256,
+  "steps_per_generation": null,
+  "teacher_tag_key": "dataset",
+  "epsilon": 0.2,
+  "epsilon_high": null,
+  "delta": null,
+  "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": null,
+  "repetition_n_grams": 3,
+  "repetition_max_penalty": -1.0,
+  "reward_model_plugin": null,
+  "chord_sft_dataset": [],
+  "chord_sft_per_device_train_batch_size": null,
+  "chord_enable_phi_function": false,
+  "chord_mu_warmup_steps": null,
+  "chord_mu_decay_steps": null,
+  "chord_mu_peak": null,
+  "chord_mu_valley": null,
+  "sync_ref_model": false,
+  "ref_model_sync_steps": 512,
+  "ref_model_mixup_alpha": 0.6,
+  "multi_turn_scheduler": null,
+  "max_turns": null,
+  "completion_length_limit_scope": "per_round",
+  "vllm_server_pass_dataset": false,
+  "use_gym_env": null,
+  "gym_env": null,
+  "dynamic_sample": false,
+  "max_resample_times": 3,
+  "overlong_filter": false,
+  "soft_max_length": null,
+  "soft_cache_length": null,
+  "scale_rewards": "group",
+  "log_entropy": false,
+  "top_entropy_quantile": 1.0,
+  "importance_sampling_level": "token",
+  "tau_pos": 1.0,
+  "tau_neg": 1.05,
+  "advantage_estimator": "grpo",
+  "kl_in_reward": false,
+  "teacher_kl_coef": 1.0,
+  "advantage_reweight": null,
+  "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,
+  "num_generations_eval": null,
+  "rollout_importance_sampling_mode": null,
+  "rollout_importance_sampling_threshold": 2.0,
+  "log_rollout_offpolicy_metrics": false,
+  "off_policy_sequence_mask_delta": null,
+  "num_generations": 8,
+  "reward_funcs": [
+    "cvis_majority_accuracy"
+  ],
+  "reward_weights": null,
+  "log_completions": false,
+  "num_iterations": 1,
+  "teacher_model": null,
+  "teacher_adapters": [],
+  "teacher_model_type": null,
+  "teacher_model_revision": null,
+  "teacher_deepspeed": null,
+  "teacher_model_server": null,
+  "offload_teacher_model": false,
+  "rlhf_type": "grpo",
+  "ref_model": "/data1/xiangding/cvis-ablate/models/Qwen3.5-9B",
+  "ref_adapters": [],
+  "ref_model_type": "qwen3_5",
+  "ref_model_revision": null,
+  "beta": 0.01,
+  "label_smoothing": 0,
+  "max_completion_length": 2048,
+  "rpo_alpha": null,
+  "ld_alpha": null,
+  "discopop_tau": 0.05,
+  "loss_weights": null,
+  "cpo_alpha": 1.0,
+  "simpo_gamma": 1,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "center_rewards_coefficient": null,
+  "sft_alpha": 0,
+  "lmbda": 0.5,
+  "seq_kd": false,
+  "gkd_logits_topk": null,
+  "swift_version": "4.6.0",
+  "ckpt_dir": null,
+  "rank": 0,
+  "global_world_size": 4,
+  "local_world_size": 4,
+  "model_suffix": "Qwen3.5-9B",
+  "model_info": "ModelInfo(model_type='qwen3_5', model_dir='/data1/xiangding/cvis-ablate/models/Qwen3.5-9B', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen3_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.5-0.8B', hf_model_id='Qwen/Qwen3.5-0.8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B', hf_model_id='Qwen/Qwen3.5-2B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B', hf_model_id='Qwen/Qwen3.5-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B', hf_model_id='Qwen/Qwen3.5-9B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B', hf_model_id='Qwen/Qwen3.5-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B-FP8', hf_model_id='Qwen/Qwen3.5-27B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-0.8B-Base', hf_model_id='Qwen/Qwen3.5-0.8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B-Base', hf_model_id='Qwen/Qwen3.5-2B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B-Base', hf_model_id='Qwen/Qwen3.5-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B-Base', hf_model_id='Qwen/Qwen3.5-9B-Base', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.6-27B', hf_model_id='Qwen/Qwen3.6-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.6-27B-FP8', hf_model_id='Qwen/Qwen3.6-27B-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.8-27B', hf_model_id='Qwen/Qwen3.8-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.8-27B-FP8', hf_model_id='Qwen/Qwen3.8-27B-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_8', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3_5Loader'>, template='qwen3_5', model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp='model.language_model.layers.{}.mlp', down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), mcore_model_type=None, architectures=['Qwen3_5ForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=5.2.0', 'qwen_vl_utils>=0.0.14', 'decord'], tags=[])",
+  "model_dir": "/data1/xiangding/cvis-ablate/models/Qwen3.5-9B",
+  "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='')",
+  "_val_dataset_exists": false,
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "GRPOConfig(output_dir='/data1/xiangding/cvis-ablate/runs/m1_proposer_answer/run_m1_proposer_answer_4g/iteration_001/solver', per_device_train_batch_size=1, num_train_epochs=3.0, max_steps=160, learning_rate=1e-06, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0.03, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=8, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=1, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['tensorboard'], run_name='/data1/xiangding/cvis-ablate/runs/m1_proposer_answer/run_m1_proposer_answer_4g/iteration_001/solver', project='huggingface', trackio_space_id=None, trackio_bucket_id=None, trackio_static_space_id=None, eval_strategy=<IntervalStrategy.NO: 'no'>, eval_steps=16.0, eval_delay=0, per_device_eval_batch_size=1, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=False, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=16, save_on_each_node=False, save_total_limit=1, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='reward', greater_is_better=True, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, dataloader_drop_last=True, dataloader_num_workers=1, dataloader_pin_memory=True, dataloader_persistent_workers=True, dataloader_prefetch_factor=2, dataloader_multiprocessing_context=None, dataloader_in_order=True, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_static_graph=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 0, 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=False, do_predict=False, resume_from_checkpoint=None, local_rank=0, model_init_kwargs=None, disable_dropout=False, cast_lm_head_to_fp32=False, num_generations=8, num_generations_eval=None, max_completion_length=2048, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=256, steps_per_generation=64, temperature=1.0, top_p=1.0, top_k=-1, min_p=0.0, generation_kwargs=None, chat_template_kwargs=None, repetition_penalty=1.0, use_transformers_paged=False, cache_implementation=None, use_vllm=True, vllm_mode='colocate', vllm_model_impl='vllm', vllm_enable_sleep_mode=False, vllm_structured_outputs_regex=None, vllm_server_base_url=None, vllm_server_host=None, vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_group_port=51216, vllm_gpu_memory_utilization=0.2, vllm_max_model_length=None, vllm_tensor_parallel_size=1, beta=0.01, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, sapo_temperature_neg=1.05, sapo_temperature_pos=1.0, importance_sampling_level='token', reward_weights=None, multi_objective_aggregation='sum_then_normalize', scale_rewards='group', loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, top_entropy_quantile=1.0, max_tool_calling_iterations=None, vllm_importance_sampling_correction=True, vllm_importance_sampling_mode='sequence_mask', vllm_importance_sampling_cap=3.0, off_policy_mask_threshold=None, use_bias_correction_kl=False, log_completions=False, num_completions_to_print=None, log_unique_prompts=False, log_completions_hub_repo=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, resume_only_model=False, optimizer=None, mrl_dims=None, eval_metric=None, callbacks=['cvis_step_timing'], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False, logging_dir='/data1/xiangding/cvis-ablate/runs/m1_proposer_answer/run_m1_proposer_answer_4g/iteration_001/solver/runs', warmup_ratio=0.0, vllm_pipeline_parallel_size=1, vllm_enable_expert_parallel=False, vllm_max_num_seqs=None, vllm_max_model_len=4096, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt=None, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=None, vllm_quantization=None, vllm_reasoning_parser=None, vllm_disable_cascade_attn=False, vllm_mm_processor_cache_gb=None, vllm_speculative_config=None, vllm_engine_kwargs={}, vllm_data_parallel_size=1, stop_words=[], vllm_enable_lora=False, lora_rank=8, vllm_server_group_port=None, enable_flattened_weight_sync=True, async_generate=False, structured_outputs_regex=None, sleep_level=0, move_model_batches=None, offload_optimizer=False, offload_model=False, wandb_log_unique_prompts=None, teacher_tag_key='dataset', cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=2048, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=None, reward_model_plugin=None, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', vllm_server_pass_dataset=False, use_gym_env=None, gym_env=None, dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, tau_pos=1.0, tau_neg=1.05, advantage_estimator='grpo', kl_in_reward=False, teacher_kl_coef=1.0, advantage_reweight=None, rlsd_lambda=0.5, rlsd_reweight_clip_range=0.2, rlsd_lambda_warmup_steps=0, rlsd_lambda_decay_steps=0, rlsd_negative_only=False, sdar_loss_coef=0.0, sdar_gate_beta=5.0, real_tau=0.5, fipo_decay_rate=32.0, fipo_clip_range=0.2, fipo_clip_high_only=True, fipo_safety_threshold=4.0, dataset_shuffle=True, rollout_importance_sampling_mode=None, rollout_importance_sampling_threshold=2.0, log_rollout_offpolicy_metrics=False, off_policy_sequence_mask_delta=None, offload_teacher_model=False)",
+  "_teacher_use_disable_adapter": false
+}

m1_proposer_answer/round_1/chat_template.jinja ADDED Viewed

	@@ -0,0 +1,154 @@

+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\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>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- 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 %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

m1_proposer_answer/round_1/config.json ADDED Viewed

	@@ -0,0 +1,117 @@

+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "hidden_size": 4096,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": 248044,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": false,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.17.0",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "axial"
+    },
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

m1_proposer_answer/round_1/generation_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    248044,
+    248046
+  ],
+  "transformers_version": "5.17.0",
+  "use_cache": true
+}

m1_proposer_answer/round_1/model-00001-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8a26205482ec74565df7027133a86e48a77954d55b8fbb0046878cab6bf2d7e8
+size 4942706120

m1_proposer_answer/round_1/model-00002-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca7309d680c175bc2cf620ad4b7c385471d6aea9d9c89387f7348f23ee28dab1
+size 4987757928

m1_proposer_answer/round_1/model-00003-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7eeeeb7dec40630e884bd7772deca79dfd4a8d4585379e464240772e84ec5c1a
+size 4954810240

m1_proposer_answer/round_1/model-00004-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7474c0894c08403d53110ffd52c43a50c33b2fcdbddd88a937cdc510eca7db28
+size 3934446832

m1_proposer_answer/round_1/model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,768 @@

+{
+  "metadata": {
+    "total_parameters": 1469680,
+    "total_size": 18819627488
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
+    "model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
+    "model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
+    "model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
+  }
+}

m1_proposer_answer/round_1/preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

m1_proposer_answer/round_1/processor_config.json ADDED Viewed

	@@ -0,0 +1,61 @@

+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "max_video_tokens": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

m1_proposer_answer/round_1/tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

m1_proposer_answer/round_1/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "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+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

m1_proposer_answer/round_1/trainer_state.json ADDED Viewed

	@@ -0,0 +1,2454 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 16.0,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.62109375,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1507.81640625,
+      "completions/min_length": 52.0,
+      "epoch": 0.00625,
+      "frac_reward_zero_std": 0.8125,
+      "grad_norm": 1.8235772903554404,
+      "kl": 0.0,
+      "learning_rate": 2e-07,
+      "loss": 3.725290298461914e-09,
+      "reward": 0.08984375,
+      "reward_std": 0.0861440896987915,
+      "rewards/MajorityAccuracy/mean": 0.08984375,
+      "rewards/MajorityAccuracy/std": 0.2865179181098938,
+      "step": 1,
+      "step_time": 177.2819549627602
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.0125,
+      "grad_norm": 0.5968322100752262,
+      "kl": 0.0,
+      "learning_rate": 4e-07,
+      "loss": -3.725290298461914e-09,
+      "step": 2,
+      "step_time": 27.54501908365637
+    },
+    {
+      "clip_ratio/high_max": 0.00023422860249411315,
+      "clip_ratio/high_mean": 5.855715062352829e-05,
+      "clip_ratio/low_mean": 3.0517578125e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 8.907472874852829e-05,
+      "epoch": 0.01875,
+      "grad_norm": 1.120939955918273,
+      "kl": 0.00020326585581642576,
+      "learning_rate": 6e-07,
+      "loss": 2.3149996195570566e-05,
+      "step": 3,
+      "step_time": 26.40415352350101
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.025,
+      "grad_norm": 0.008125982807563855,
+      "kl": 0.0002121110019288608,
+      "learning_rate": 8e-07,
+      "loss": 2.1230268885119585e-06,
+      "step": 4,
+      "step_time": 26.605264748446643
+    },
+    {
+      "clip_ratio/high_max": 0.0005154639366082847,
+      "clip_ratio/high_mean": 0.00012886598415207118,
+      "clip_ratio/low_mean": 0.0006103515625,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0007392175466520712,
+      "epoch": 0.03125,
+      "grad_norm": 1.5195979613004638,
+      "kl": 0.0002506144955987111,
+      "learning_rate": 1e-06,
+      "loss": 0.00017511064652353525,
+      "step": 5,
+      "step_time": 26.812567389570177
+    },
+    {
+      "clip_ratio/high_max": 0.0003267973952461034,
+      "clip_ratio/high_mean": 8.169934881152585e-05,
+      "clip_ratio/low_mean": 9.498480358161032e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00017668415239313617,
+      "epoch": 0.0375,
+      "grad_norm": 1.2886395405170576,
+      "kl": 0.00023961582064657705,
+      "learning_rate": 9.998973021172564e-07,
+      "loss": 0.00013967281847726554,
+      "step": 6,
+      "step_time": 26.536803510971367
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.04375,
+      "grad_norm": 0.0029639956149802565,
+      "kl": 0.00017263766858377494,
+      "learning_rate": 9.99589250656446e-07,
+      "loss": 1.7280335669056512e-06,
+      "step": 7,
+      "step_time": 27.59376015374437
+    },
+    {
+      "clip_ratio/high_max": 0.0016136237536557019,
+      "clip_ratio/high_mean": 0.00040340593841392547,
+      "clip_ratio/low_mean": 0.0004640333845600253,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0008674393229739508,
+      "epoch": 0.05,
+      "grad_norm": 1.9092659639360128,
+      "kl": 0.00036703036312246695,
+      "learning_rate": 9.990759721625005e-07,
+      "loss": 0.000330757990013808,
+      "step": 8,
+      "step_time": 27.29972771042958
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.546875,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1419.203125,
+      "completions/min_length": 79.0,
+      "epoch": 0.05625,
+      "frac_reward_zero_std": 0.6875,
+      "grad_norm": 2.098496913711791,
+      "kl": 0.0002831585134117631,
+      "learning_rate": 9.983576774858775e-07,
+      "loss": 2.843035872501787e-06,
+      "reward": 0.1484375,
+      "reward_std": 0.12927988171577454,
+      "rewards/MajorityAccuracy/mean": 0.1484375,
+      "rewards/MajorityAccuracy/std": 0.3562295734882355,
+      "step": 9,
+      "step_time": 178.28205867949873
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.0625,
+      "grad_norm": 0.00601901484439787,
+      "kl": 0.0006133791903266683,
+      "learning_rate": 9.974346616959475e-07,
+      "loss": 6.136287083791103e-06,
+      "step": 10,
+      "step_time": 27.104037229903042
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.06875,
+      "grad_norm": 0.008290153256219561,
+      "kl": 0.0007819118909537792,
+      "learning_rate": 9.963073039597796e-07,
+      "loss": 7.823275154805742e-06,
+      "step": 11,
+      "step_time": 27.09182495623827
+    },
+    {
+      "clip_ratio/high_max": 0.005412128317402676,
+      "clip_ratio/high_mean": 0.001353032079350669,
+      "clip_ratio/low_mean": 1.52587890625e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.001368290868413169,
+      "epoch": 0.075,
+      "grad_norm": 0.6965834616247321,
+      "kl": 0.0004171378350292798,
+      "learning_rate": 9.949760673863846e-07,
+      "loss": -2.3723858248558827e-05,
+      "step": 12,
+      "step_time": 26.956677444744855
+    },
+    {
+      "clip_ratio/high_max": 0.0007575757335871458,
+      "clip_ratio/high_mean": 0.00018939393339678645,
+      "clip_ratio/low_mean": 0.0008858311921358109,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0010752251255325973,
+      "epoch": 0.08125,
+      "grad_norm": 2.636465341054292,
+      "kl": 0.0008410161972278729,
+      "learning_rate": 9.934414988364722e-07,
+      "loss": 2.665841566340532e-05,
+      "step": 13,
+      "step_time": 25.998644553590566
+    },
+    {
+      "clip_ratio/high_max": 0.005640423347358592,
+      "clip_ratio/high_mean": 0.0021383722669270355,
+      "clip_ratio/low_mean": 0.0028953809378435835,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.005033753288444132,
+      "epoch": 0.0875,
+      "grad_norm": 1.7883319726467786,
+      "kl": 0.0011762244685087353,
+      "learning_rate": 9.917042286978063e-07,
+      "loss": 0.00010657217353582382,
+      "step": 14,
+      "step_time": 24.461548109538853
+    },
+    {
+      "clip_ratio/high_max": 0.002728054649196565,
+      "clip_ratio/high_mean": 0.0006820136622991413,
+      "clip_ratio/low_mean": 0.0001220703125,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0008040839747991413,
+      "epoch": 0.09375,
+      "grad_norm": 0.7689914891220312,
+      "kl": 0.000849124240630772,
+      "learning_rate": 9.897649706262473e-07,
+      "loss": 5.176894410396926e-05,
+      "step": 15,
+      "step_time": 26.638053173199296
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.1,
+      "grad_norm": 0.009978139461005866,
+      "kl": 0.0007774191763019189,
+      "learning_rate": 9.87624521252587e-07,
+      "loss": 7.782724424032494e-06,
+      "step": 16,
+      "step_time": 27.052169392816722
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.62109375,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1561.82421875,
+      "completions/min_length": 10.0,
+      "epoch": 0.10625,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.005245659238244828,
+      "kl": 0.0009311293833889067,
+      "learning_rate": 9.852837598553008e-07,
+      "loss": 9.321906873083208e-06,
+      "reward": 0.0625,
+      "reward_std": 0.10771076381206512,
+      "rewards/MajorityAccuracy/mean": 0.0625,
+      "rewards/MajorityAccuracy/std": 0.24253562092781067,
+      "step": 17,
+      "step_time": 171.29826306318864
+    },
+    {
+      "clip_ratio/high_max": 0.0014880952658131719,
+      "clip_ratio/high_mean": 0.00037202381645329297,
+      "clip_ratio/low_mean": 0.0005324418598320335,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0009044656762853265,
+      "epoch": 0.1125,
+      "grad_norm": 2.5954010054499275,
+      "kl": 0.00202986913791392,
+      "learning_rate": 9.827436479993468e-07,
+      "loss": -1.0340620974602643e-05,
+      "step": 18,
+      "step_time": 26.82198541564867
+    },
+    {
+      "clip_ratio/high_max": 0.0005113306688144803,
+      "clip_ratio/high_mean": 0.00012783266720362008,
+      "clip_ratio/low_mean": 0.0006897801431478001,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0008176128103514202,
+      "epoch": 0.11875,
+      "grad_norm": 1.5253947360698732,
+      "kl": 0.002278831321746111,
+      "learning_rate": 9.800052291411629e-07,
+      "loss": 0.00033733044983819127,
+      "step": 19,
+      "step_time": 26.992370984051377
+    },
+    {
+      "clip_ratio/high_max": 0.0001610485924175009,
+      "clip_ratio/high_mean": 4.026214810437523e-05,
+      "clip_ratio/low_mean": 9.1552734375e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00013181488247937523,
+      "epoch": 0.125,
+      "grad_norm": 0.8092593799290034,
+      "kl": 0.0012567421654239297,
+      "learning_rate": 9.770696282000244e-07,
+      "loss": 6.669329013675451e-05,
+      "step": 20,
+      "step_time": 26.859167395625263
+    },
+    {
+      "clip_ratio/high_max": 0.0011068055318901315,
+      "clip_ratio/high_mean": 0.00035437330734566785,
+      "clip_ratio/low_mean": 0.00041237971527152695,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0007667530226171948,
+      "epoch": 0.13125,
+      "grad_norm": 1.3161831202609933,
+      "kl": 0.0023406175459967926,
+      "learning_rate": 9.739380510959364e-07,
+      "loss": 0.00019088073167949915,
+      "step": 21,
+      "step_time": 26.90115578705445
+    },
+    {
+      "clip_ratio/high_max": 0.0014409221475943923,
+      "clip_ratio/high_mean": 0.0003602305368985981,
+      "clip_ratio/low_mean": 0.0021121045283507556,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0024723350652493536,
+      "epoch": 0.1375,
+      "grad_norm": 1.6605297829039345,
+      "kl": 0.0023793510044924915,
+      "learning_rate": 9.706117842542516e-07,
+      "loss": -0.00010600823588902131,
+      "step": 22,
+      "step_time": 26.529486192390323
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.14375,
+      "grad_norm": 0.010393035701162423,
+      "kl": 0.002015301870414987,
+      "learning_rate": 9.670921940772186e-07,
+      "loss": 2.0159997802693397e-05,
+      "step": 23,
+      "step_time": 26.92375068552792
+    },
+    {
+      "clip_ratio/high_max": 0.0007309941574931145,
+      "clip_ratio/high_mean": 0.00018274853937327862,
+      "clip_ratio/low_mean": 0.0008673729753354564,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.001050121514708735,
+      "epoch": 0.15,
+      "grad_norm": 0.7557304578989614,
+      "kl": 0.0020514242496574298,
+      "learning_rate": 9.633807263826744e-07,
+      "loss": 1.990123200812377e-05,
+      "step": 24,
+      "step_time": 26.912497670389712
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.53515625,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1524.3671875,
+      "completions/min_length": 62.0,
+      "epoch": 0.15625,
+      "frac_reward_zero_std": 0.84375,
+      "grad_norm": 1.1651169593645025,
+      "kl": 0.0018118007719749585,
+      "learning_rate": 9.594789058101153e-07,
+      "loss": 1.8126695067621768e-05,
+      "reward": 0.13671875,
+      "reward_std": 0.07061731815338135,
+      "rewards/MajorityAccuracy/mean": 0.13671875,
+      "rewards/MajorityAccuracy/std": 0.34422317147254944,
+      "step": 25,
+      "step_time": 163.54246024927124
+    },
+    {
+      "clip_ratio/high_max": 0.0011613607202889398,
+      "clip_ratio/high_mean": 0.00029034018007223494,
+      "clip_ratio/low_mean": 0.0009596541640348732,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0012499943513830658,
+      "epoch": 0.1625,
+      "grad_norm": 4.109543551008228,
+      "kl": 0.0036223788338247687,
+      "learning_rate": 9.55388335194388e-07,
+      "loss": 0.00012265269469935447,
+      "step": 26,
+      "step_time": 26.67042667232454
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.16875,
+      "grad_norm": 0.011039025010580104,
+      "kl": 0.002650492446264252,
+      "learning_rate": 9.511106949072587e-07,
+      "loss": 2.6508587325224653e-05,
+      "step": 27,
+      "step_time": 27.011303344275802
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.175,
+      "grad_norm": 0.01259314366029664,
+      "kl": 0.0027553302934393287,
+      "learning_rate": 9.466477421671295e-07,
+      "loss": 2.7563328330870718e-05,
+      "step": 28,
+      "step_time": 27.43171972827986
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.18125,
+      "grad_norm": 0.018334977141973376,
+      "kl": 0.003600360214477405,
+      "learning_rate": 9.420013103171891e-07,
+      "loss": 3.602530341595411e-05,
+      "step": 29,
+      "step_time": 26.982325692661107
+    },
+    {
+      "clip_ratio/high_max": 0.003243707978981547,
+      "clip_ratio/high_mean": 0.0008109269947453868,
+      "clip_ratio/low_mean": 6.103515625e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0008719621509953868,
+      "epoch": 0.1875,
+      "grad_norm": 0.6002188405759098,
+      "kl": 0.0044708729546982795,
+      "learning_rate": 9.37173308072291e-07,
+      "loss": 0.0001719572173897177,
+      "step": 30,
+      "step_time": 26.732330822385848
+    },
+    {
+      "clip_ratio/high_max": 0.00040983606595546007,
+      "clip_ratio/high_mean": 0.00010245901648886502,
+      "clip_ratio/low_mean": 0.000946044921875,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.001048503938363865,
+      "epoch": 0.19375,
+      "grad_norm": 0.7126591461884292,
+      "kl": 0.004865155729930848,
+      "learning_rate": 9.321657187348688e-07,
+      "loss": 0.00017080048564821482,
+      "step": 31,
+      "step_time": 26.950641526840627
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.2,
+      "grad_norm": 0.037977826232870715,
+      "kl": 0.004005931958090514,
+      "learning_rate": 9.269805993802128e-07,
+      "loss": 4.006523886346258e-05,
+      "step": 32,
+      "step_time": 27.362936487887055
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.61328125,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1646.4296875,
+      "completions/min_length": 30.0,
+      "epoch": 0.20625,
+      "frac_reward_zero_std": 0.78125,
+      "grad_norm": 13.523030432423296,
+      "kl": 0.0031676926591899246,
+      "learning_rate": 9.216200800114411e-07,
+      "loss": 3.1698058592155576e-05,
+      "reward": 0.078125,
+      "reward_std": 0.09495474398136139,
+      "rewards/MajorityAccuracy/mean": 0.078125,
+      "rewards/MajorityAccuracy/std": 0.26889389753341675,
+      "step": 33,
+      "step_time": 179.411544454284
+    },
+    {
+      "clip_ratio/high_max": 0.00023025162954581901,
+      "clip_ratio/high_mean": 5.7562907386454754e-05,
+      "clip_ratio/low_mean": 4.57763671875e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00010333927457395475,
+      "epoch": 0.2125,
+      "grad_norm": 0.9464828712063403,
+      "kl": 0.0032382322242483497,
+      "learning_rate": 9.160863626845119e-07,
+      "loss": -8.923107088776305e-05,
+      "step": 34,
+      "step_time": 26.802862763870507
+    },
+    {
+      "clip_ratio/high_max": 0.000900421138794627,
+      "clip_ratio/high_mean": 0.0003091430899075931,
+      "clip_ratio/low_mean": 0.00016255105401796754,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00047169414392556064,
+      "epoch": 0.21875,
+      "grad_norm": 0.9849937074588093,
+      "kl": 0.0032972949848044664,
+      "learning_rate": 9.103817206036382e-07,
+      "loss": 0.00012960511958226562,
+      "step": 35,
+      "step_time": 27.06772213988006
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.225,
+      "grad_norm": 0.019609927400104272,
+      "kl": 0.0032961306860670447,
+      "learning_rate": 9.045084971874737e-07,
+      "loss": 3.296560316812247e-05,
+      "step": 36,
+      "step_time": 26.659050672780722
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.23125,
+      "grad_norm": 0.010402726769541678,
+      "kl": 0.0037650765443686396,
+      "learning_rate": 8.984691051064574e-07,
+      "loss": 3.769922477658838e-05,
+      "step": 37,
+      "step_time": 27.05770122213289
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0022783598105888814,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0022783598105888814,
+      "epoch": 0.2375,
+      "grad_norm": 1.8032674857112958,
+      "kl": 0.0066002721432596445,
+      "learning_rate": 8.922660252917087e-07,
+      "loss": 0.0002797610068228096,
+      "step": 38,
+      "step_time": 24.97022458491847
+    },
+    {
+      "clip_ratio/high_max": 0.0004302925954107195,
+      "clip_ratio/high_mean": 0.00010757314885267988,
+      "clip_ratio/low_mean": 0.001065103555447422,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0011726767043001018,
+      "epoch": 0.24375,
+      "grad_norm": 1.0551039138870986,
+      "kl": 0.0036179817107040435,
+      "learning_rate": 8.859018059158809e-07,
+      "loss": 0.00047041074139997363,
+      "step": 39,
+      "step_time": 26.573595809284598
+    },
+    {
+      "clip_ratio/high_max": 0.0007225433364510536,
+      "clip_ratio/high_mean": 0.0001806358341127634,
+      "clip_ratio/low_mean": 0.001524041043012403,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0017046768771251664,
+      "epoch": 0.25,
+      "grad_norm": 1.7659536136942666,
+      "kl": 0.004762540280353278,
+      "learning_rate": 8.793790613463954e-07,
+      "loss": 0.0001945684343809262,
+      "step": 40,
+      "step_time": 27.034735680557787
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.59765625,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1561.1171875,
+      "completions/min_length": 86.0,
+      "epoch": 0.25625,
+      "frac_reward_zero_std": 0.84375,
+      "grad_norm": 0.0095720298234479,
+      "kl": 0.002686580555746332,
+      "learning_rate": 8.727004710714798e-07,
+      "loss": 2.6876186893787235e-05,
+      "reward": 0.09765625,
+      "reward_std": 0.07745210826396942,
+      "rewards/MajorityAccuracy/mean": 0.09765625,
+      "rewards/MajorityAccuracy/std": 0.29743078351020813,
+      "step": 41,
+      "step_time": 164.75104446616024
+    },
+    {
+      "clip_ratio/high_max": 0.00030397331283893436,
+      "clip_ratio/high_mean": 7.599332820973359e-05,
+      "clip_ratio/low_mean": 0.0001068115234375,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0001828048516472336,
+      "epoch": 0.2625,
+      "grad_norm": 0.5560505710622571,
+      "kl": 0.004013727622805163,
+      "learning_rate": 8.658687785994578e-07,
+      "loss": 0.00011029034794773906,
+      "step": 42,
+      "step_time": 26.99202277418226
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.26875,
+      "grad_norm": 0.016696945544601226,
+      "kl": 0.00558138795895502,
+      "learning_rate": 8.588867903317394e-07,
+      "loss": 5.583100937656127e-05,
+      "step": 43,
+      "step_time": 26.97776234615594
+    },
+    {
+      "clip_ratio/high_max": 0.0003795586817432195,
+      "clip_ratio/high_mean": 9.488967043580487e-05,
+      "clip_ratio/low_mean": 0.00018189165712101385,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0002767813275568187,
+      "epoch": 0.275,
+      "grad_norm": 0.79682018394004,
+      "kl": 0.003996353741968051,
+      "learning_rate": 8.51757374409974e-07,
+      "loss": -9.537604637444019e-05,
+      "step": 44,
+      "step_time": 26.637193395756185
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.28125,
+      "grad_norm": 0.016185023640383052,
+      "kl": 0.005350254359655082,
+      "learning_rate": 8.444834595378433e-07,
+      "loss": 5.348042759578675e-05,
+      "step": 45,
+      "step_time": 27.204410531558096
+    },
+    {
+      "clip_ratio/high_max": 0.001856719158240594,
+      "clip_ratio/high_mean": 0.0004641797895601485,
+      "clip_ratio/low_mean": 0.0003509521484375,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0008151319379976485,
+      "epoch": 0.2875,
+      "grad_norm": 1.0769752797524776,
+      "kl": 0.005875883740372956,
+      "learning_rate": 8.370680337779736e-07,
+      "loss": 0.00013251713244244456,
+      "step": 46,
+      "step_time": 26.830352597869933
+    },
+    {
+      "clip_ratio/high_max": 0.005456331593450159,
+      "clip_ratio/high_mean": 0.0014689486706629395,
+      "clip_ratio/low_mean": 0.000701904296875,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0021708529675379395,
+      "epoch": 0.29375,
+      "grad_norm": 1.324172107289365,
+      "kl": 0.00696696963859722,
+      "learning_rate": 8.295141433244659e-07,
+      "loss": 9.872863302007318e-06,
+      "step": 47,
+      "step_time": 26.95655009429902
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.3,
+      "grad_norm": 0.03714203696292484,
+      "kl": 0.009226670779753476,
+      "learning_rate": 8.218248912515442e-07,
+      "loss": 9.224010864272714e-05,
+      "step": 48,
+      "step_time": 26.999500666745007
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.55078125,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1515.66796875,
+      "completions/min_length": 61.0,
+      "epoch": 0.30625,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 1.154353171041609,
+      "kl": 0.00446900655515492,
+      "learning_rate": 8.140034362388397e-07,
+      "loss": 4.470593557925895e-05,
+      "reward": 0.1015625,
+      "reward_std": 0.10771076381206512,
+      "rewards/MajorityAccuracy/mean": 0.1015625,
+      "rewards/MajorityAccuracy/std": 0.3026638329029083,
+      "step": 49,
+      "step_time": 159.88641359191388
+    },
+    {
+      "clip_ratio/high_max": 0.0013748531200690195,
+      "clip_ratio/high_mean": 0.0003437132800172549,
+      "clip_ratio/low_mean": 3.0517578125e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0003742308581422549,
+      "epoch": 0.3125,
+      "grad_norm": 0.9177011675635179,
+      "kl": 0.012847435078583658,
+      "learning_rate": 8.060529912738314e-07,
+      "loss": 0.00012757224612869322,
+      "step": 50,
+      "step_time": 25.720251586288214
+    },
+    {
+      "clip_ratio/high_max": 0.0010912689758697525,
+      "clip_ratio/high_mean": 0.00031393567405757494,
+      "clip_ratio/low_mean": 0.0006421898724511266,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0009561255501466803,
+      "epoch": 0.31875,
+      "grad_norm": 1.4397627439261769,
+      "kl": 0.012131983879953623,
+      "learning_rate": 7.979768223319785e-07,
+      "loss": 0.00015034424723125994,
+      "step": 51,
+      "step_time": 26.437583366408944
+    },
+    {
+      "clip_ratio/high_max": 0.00015782828268129379,
+      "clip_ratio/high_mean": 3.9457070670323446e-05,
+      "clip_ratio/low_mean": 0.0001983642578125,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00023782132848282345,
+      "epoch": 0.325,
+      "grad_norm": 0.6317794552184987,
+      "kl": 0.006284663104452193,
+      "learning_rate": 7.897782470350849e-07,
+      "loss": 7.370468665612862e-05,
+      "step": 52,
+      "step_time": 27.034135276917368
+    },
+    {
+      "clip_ratio/high_max": 0.00186744294478558,
+      "clip_ratio/high_mean": 0.000466860736196395,
+      "clip_ratio/low_mean": 0.0007807363290339708,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0012475970579544082,
+      "epoch": 0.33125,
+      "grad_norm": 1.9905261266376115,
+      "kl": 0.010930973920039833,
+      "learning_rate": 7.814606332884488e-07,
+      "loss": -6.791499617975205e-05,
+      "step": 53,
+      "step_time": 26.368849969934672
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.3375,
+      "grad_norm": 0.018207813486788488,
+      "kl": 0.007224219618365169,
+      "learning_rate": 7.730273978973552e-07,
+      "loss": 7.224986620713025e-05,
+      "step": 54,
+      "step_time": 26.64780141087249
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.34375,
+      "grad_norm": 0.034604963391197854,
+      "kl": 0.008045608818065375,
+      "learning_rate": 7.644820051634812e-07,
+      "loss": 8.042568515520543e-05,
+      "step": 55,
+      "step_time": 26.87330221896991
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.35,
+      "grad_norm": 0.03296137153200811,
+      "kl": 0.009706451615784317,
+      "learning_rate": 7.558279654617912e-07,
+      "loss": 9.704505646368489e-05,
+      "step": 56,
+      "step_time": 27.11862536892295
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.43359375,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1343.2734375,
+      "completions/min_length": 80.0,
+      "epoch": 0.35625,
+      "frac_reward_zero_std": 0.78125,
+      "grad_norm": 2.6287291726820055,
+      "kl": 0.009951809654012322,
+      "learning_rate": 7.470688337985029e-07,
+      "loss": 9.952746768249199e-05,
+      "reward": 0.06640625,
+      "reward_std": 0.09954919666051865,
+      "rewards/MajorityAccuracy/mean": 0.06640625,
+      "rewards/MajorityAccuracy/std": 0.24947862327098846,
+      "step": 57,
+      "step_time": 156.6750803105533
+    },
+    {
+      "clip_ratio/high_max": 0.0002304147492395714,
+      "clip_ratio/high_mean": 5.760368730989285e-05,
+      "clip_ratio/low_mean": 0.00019243467249907553,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0002500383598089684,
+      "epoch": 0.3625,
+      "grad_norm": 0.9189189192166226,
+      "kl": 0.011124333599582314,
+      "learning_rate": 7.382082083507225e-07,
+      "loss": 0.00019801066082436591,
+      "step": 58,
+      "step_time": 26.832797868642956
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.36875,
+      "grad_norm": 0.01802307485006237,
+      "kl": 0.00753511325456202,
+      "learning_rate": 7.292497289883432e-07,
+      "loss": 7.534979522461072e-05,
+      "step": 59,
+      "step_time": 27.09886820986867
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.375,
+      "grad_norm": 0.019215794601671582,
+      "kl": 0.007480954809579998,
+      "learning_rate": 7.201970757788171e-07,
+      "loss": 7.48137608752586e-05,
+      "step": 60,
+      "step_time": 26.962629404850304
+    },
+    {
+      "clip_ratio/high_max": 0.002650445167091675,
+      "clip_ratio/high_mean": 0.0006626112917729188,
+      "clip_ratio/low_mean": 0.0006019914289936423,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00126460272440454,
+      "epoch": 0.38125,
+      "grad_norm": 2.0878387985867146,
+      "kl": 0.013353421236388385,
+      "learning_rate": 7.110539674754159e-07,
+      "loss": 0.0006817997200414538,
+      "step": 61,
+      "step_time": 27.024767535272986
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.3875,
+      "grad_norm": 0.022597934936552284,
+      "kl": 0.008731478126719594,
+      "learning_rate": 7.018241599895973e-07,
+      "loss": 8.730891568120569e-05,
+      "step": 62,
+      "step_time": 26.88828439451754
+    },
+    {
+      "clip_ratio/high_max": 0.0010070493444800377,
+      "clip_ratio/high_mean": 0.0002517623361200094,
+      "clip_ratio/low_mean": 0.0006343272616504692,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0008860895977704786,
+      "epoch": 0.39375,
+      "grad_norm": 2.983959978239013,
+      "kl": 0.010646957787685096,
+      "learning_rate": 6.925114448481088e-07,
+      "loss": 0.00012753244664054364,
+      "step": 63,
+      "step_time": 26.877964835148305
+    },
+    {
+      "clip_ratio/high_max": 0.005357957212254405,
+      "clip_ratio/high_mean": 0.0013394893030636013,
+      "clip_ratio/low_mean": 0.001194599928567186,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0025340892316307873,
+      "epoch": 0.4,
+      "grad_norm": 2.5591930509515897,
+      "kl": 0.016508333093952388,
+      "learning_rate": 6.831196476354614e-07,
+      "loss": -0.00017710903193801641,
+      "step": 64,
+      "step_time": 25.411937365308404
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.40234375,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1353.046875,
+      "completions/min_length": 95.0,
+      "epoch": 0.40625,
+      "frac_reward_zero_std": 0.78125,
+      "grad_norm": 1.2030938823708033,
+      "kl": 0.008779516036156565,
+      "learning_rate": 6.7365262642241e-07,
+      "loss": 8.780478674452752e-05,
+      "reward": 0.15625,
+      "reward_std": 0.09271685779094696,
+      "rewards/MajorityAccuracy/mean": 0.15625,
+      "rewards/MajorityAccuracy/std": 0.3638034462928772,
+      "step": 65,
+      "step_time": 156.432923567947
+    },
+    {
+      "clip_ratio/high_max": 0.0006752088738721795,
+      "clip_ratio/high_mean": 0.00016880221846804488,
+      "clip_ratio/low_mean": 8.232262189267203e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0002511248403607169,
+      "epoch": 0.4125,
+      "grad_norm": 0.8438696659616179,
+      "kl": 0.01237497921101749,
+      "learning_rate": 6.641142701810931e-07,
+      "loss": 0.00026803489890880883,
+      "step": 66,
+      "step_time": 26.59718051319942
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.41875,
+      "grad_norm": 0.04980937451383027,
+      "kl": 0.01220573706086725,
+      "learning_rate": 6.545084971874736e-07,
+      "loss": 0.0001220768317580223,
+      "step": 67,
+      "step_time": 25.974684783723205
+    },
+    {
+      "clip_ratio/high_max": 0.0019074143056059256,
+      "clip_ratio/high_mean": 0.0004768535764014814,
+      "clip_ratio/low_mean": 0.0006395168820745312,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0011163704621139914,
+      "epoch": 0.425,
+      "grad_norm": 1.3931029996713908,
+      "kl": 0.01779834704939276,
+      "learning_rate": 6.448392534117461e-07,
+      "loss": 0.0004487178521230817,
+      "step": 68,
+      "step_time": 24.184219307266176
+    },
+    {
+      "clip_ratio/high_max": 0.0034293873322894797,
+      "clip_ratio/high_mean": 0.0008573468330723699,
+      "clip_ratio/low_mean": 0.0003709999145939946,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0012283467476663645,
+      "epoch": 0.43125,
+      "grad_norm": 1.2943729157055044,
+      "kl": 0.010206820792518556,
+      "learning_rate": 6.351105108973644e-07,
+      "loss": 8.257511944975704e-05,
+      "step": 69,
+      "step_time": 26.946012017317116
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.4375,
+      "grad_norm": 0.0370824411247142,
+      "kl": 0.013905228115618229,
+      "learning_rate": 6.253262661293602e-07,
+      "loss": 0.00013903352373745292,
+      "step": 70,
+      "step_time": 26.957798649091274
+    },
+    {
+      "clip_ratio/high_max": 0.003002236320753582,
+      "clip_ratio/high_mean": 0.0007505590801883955,
+      "clip_ratio/low_mean": 7.62939453125e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0008268530255008955,
+      "epoch": 0.44375,
+      "grad_norm": 0.5649645837007092,
+      "kl": 0.010286175878718495,
+      "learning_rate": 6.154905383926216e-07,
+      "loss": 0.00011830424045911059,
+      "step": 71,
+      "step_time": 26.460277082398534
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.45,
+      "grad_norm": 0.018828265488435955,
+      "kl": 0.01051688869483769,
+      "learning_rate": 6.056073681208037e-07,
+      "loss": 0.00010517022019485012,
+      "step": 72,
+      "step_time": 27.15914153214544
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.54296875,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1480.265625,
+      "completions/min_length": 105.0,
+      "epoch": 0.45625,
+      "frac_reward_zero_std": 0.78125,
+      "grad_norm": 0.01828691626237035,
+      "kl": 0.006869596312753856,
+      "learning_rate": 5.956808152365532e-07,
+      "loss": 6.865868635941297e-05,
+      "reward": 0.09375,
+      "reward_std": 0.10231750458478928,
+      "rewards/MajorityAccuracy/mean": 0.09375,
+      "rewards/MajorityAccuracy/std": 0.2920515835285187,
+      "step": 73,
+      "step_time": 169.1829187180847
+    },
+    {
+      "clip_ratio/high_max": 0.00022374701802618802,
+      "clip_ratio/high_mean": 5.5936754506547004e-05,
+      "clip_ratio/low_mean": 0.000213623046875,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.000269559801381547,
+      "epoch": 0.4625,
+      "grad_norm": 0.6381979996886552,
+      "kl": 0.012247174163348973,
+      "learning_rate": 5.857149574837268e-07,
+      "loss": 5.683078052243218e-05,
+      "step": 74,
+      "step_time": 27.01538314903155
+    },
+    {
+      "clip_ratio/high_max": 0.0019469246617518365,
+      "clip_ratio/high_mean": 0.00048673116543795913,
+      "clip_ratio/low_mean": 0.0003333898166602012,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0008201209820981603,
+      "epoch": 0.46875,
+      "grad_norm": 2.1809159826488624,
+      "kl": 0.013598177465610206,
+      "learning_rate": 5.757138887522883e-07,
+      "loss": 0.00024087363271974027,
+      "step": 75,
+      "step_time": 27.097287375945598
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.475,
+      "grad_norm": 0.024357954630142304,
+      "kl": 0.00871447630925104,
+      "learning_rate": 5.656817173965732e-07,
+      "loss": 8.710857218829915e-05,
+      "step": 76,
+      "step_time": 27.11480687605217
+    },
+    {
+      "clip_ratio/high_max": 0.0015798720705788583,
+      "clip_ratio/high_mean": 0.00041446270915912464,
+      "clip_ratio/low_mean": 0.000244140625,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0006586033341591246,
+      "epoch": 0.48125,
+      "grad_norm": 1.1042011723014662,
+      "kl": 0.006976698816288263,
+      "learning_rate": 5.556225645476118e-07,
+      "loss": 0.0001779216981958598,
+      "step": 77,
+      "step_time": 27.27309865737334
+    },
+    {
+      "clip_ratio/high_max": 0.0029926826246082783,
+      "clip_ratio/high_mean": 0.0007481706561520696,
+      "clip_ratio/low_mean": 0.0010631325421854854,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.001811303198337555,
+      "epoch": 0.4875,
+      "grad_norm": 2.2386035679333944,
+      "kl": 0.021839435794390738,
+      "learning_rate": 5.455405624202032e-07,
+      "loss": 0.0003933809930458665,
+      "step": 78,
+      "step_time": 26.641473723575473
+    },
+    {
+      "clip_ratio/high_max": 0.0029102854168741032,
+      "clip_ratio/high_mean": 0.0007540319820691366,
+      "clip_ratio/low_mean": 0.00021077847850392573,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0009648104605730623,
+      "epoch": 0.49375,
+      "grad_norm": 1.1684376210164706,
+      "kl": 0.014173172297887504,
+      "learning_rate": 5.354398526154365e-07,
+      "loss": 0.0001540904340799898,
+      "step": 79,
+      "step_time": 26.2325482647866
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.5,
+      "grad_norm": 0.023680673911039566,
+      "kl": 0.01050564693287015,
+      "learning_rate": 5.253245844193564e-07,
+      "loss": 0.00010505324462428689,
+      "step": 80,
+      "step_time": 26.795159440953285
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.42578125,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1401.23828125,
+      "completions/min_length": 66.0,
+      "epoch": 0.50625,
+      "frac_reward_zero_std": 0.6875,
+      "grad_norm": 0.04030691077262455,
+      "kl": 0.018764963373541832,
+      "learning_rate": 5.151989130984714e-07,
+      "loss": 0.0001876021851785481,
+      "reward": 0.078125,
+      "reward_std": 0.1263929009437561,
+      "rewards/MajorityAccuracy/mean": 0.078125,
+      "rewards/MajorityAccuracy/std": 0.26889389753341675,
+      "step": 81,
+      "step_time": 157.43829696904868
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.00035919540096074343,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00035919540096074343,
+      "epoch": 0.5125,
+      "grad_norm": 1.468183002189007,
+      "kl": 0.01168537640478462,
+      "learning_rate": 5.050669981928055e-07,
+      "loss": 0.0001765538181643933,
+      "step": 82,
+      "step_time": 26.57122299168259
+    },
+    {
+      "clip_ratio/high_max": 0.0015211465361062437,
+      "clip_ratio/high_mean": 0.00044851807615486905,
+      "clip_ratio/low_mean": 0.0002328948539798148,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0006814129374106415,
+      "epoch": 0.51875,
+      "grad_norm": 1.4472751694927448,
+      "kl": 0.012297893001232296,
+      "learning_rate": 4.949330018071946e-07,
+      "loss": 0.00012261344818398356,
+      "step": 83,
+      "step_time": 26.319694240111858
+    },
+    {
+      "clip_ratio/high_max": 0.0005856432544533163,
+      "clip_ratio/high_mean": 0.00014641081361332908,
+      "clip_ratio/low_mean": 0.0004263619630364701,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0005727727766497992,
+      "epoch": 0.525,
+      "grad_norm": 1.5593219933718963,
+      "kl": 0.014456238714046776,
+      "learning_rate": 4.848010869015287e-07,
+      "loss": 0.0003469269722700119,
+      "step": 84,
+      "step_time": 26.783488856628537
+    },
+    {
+      "clip_ratio/high_max": 0.00015441630966961384,
+      "clip_ratio/high_mean": 3.860407741740346e-05,
+      "clip_ratio/low_mean": 0.00047378950694110245,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0005123935843585059,
+      "epoch": 0.53125,
+      "grad_norm": 1.0033734540405483,
+      "kl": 0.009365220030304044,
+      "learning_rate": 4.746754155806437e-07,
+      "loss": 0.00018618092872202396,
+      "step": 85,
+      "step_time": 26.83496230468154
+    },
+    {
+      "clip_ratio/high_max": 0.0019749078928725794,
+      "clip_ratio/high_mean": 0.0004937269732181448,
+      "clip_ratio/low_mean": 0.000798522713012062,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0012922496862302069,
+      "epoch": 0.5375,
+      "grad_norm": 1.7019260625212422,
+      "kl": 0.01620011660270393,
+      "learning_rate": 4.645601473845635e-07,
+      "loss": -0.00011216345592401922,
+      "step": 86,
+      "step_time": 26.952285648323596
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.54375,
+      "grad_norm": 0.015099932449218431,
+      "kl": 0.006309934193268418,
+      "learning_rate": 4.544594375797968e-07,
+      "loss": 6.310711614787579e-05,
+      "step": 87,
+      "step_time": 27.227852480486035
+    },
+    {
+      "clip_ratio/high_max": 0.0014356424144352786,
+      "clip_ratio/high_mean": 0.00035891060360881966,
+      "clip_ratio/low_mean": 6.103515625e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00041994575985881966,
+      "epoch": 0.55,
+      "grad_norm": 0.6802696656717124,
+      "kl": 0.017813479993492365,
+      "learning_rate": 4.443774354523882e-07,
+      "loss": 0.0001278062554774806,
+      "step": 88,
+      "step_time": 26.36451459908858
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.42578125,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1372.5546875,
+      "completions/min_length": 104.0,
+      "epoch": 0.55625,
+      "frac_reward_zero_std": 0.78125,
+      "grad_norm": 0.023151204442446994,
+      "kl": 0.010745718842372298,
+      "learning_rate": 4.3431828260342675e-07,
+      "loss": 0.00010748470958787948,
+      "reward": 0.109375,
+      "reward_std": 0.10178953409194946,
+      "rewards/MajorityAccuracy/mean": 0.109375,
+      "rewards/MajorityAccuracy/std": 0.31272050738334656,
+      "step": 89,
+      "step_time": 161.6896539060399
+    },
+    {
+      "clip_ratio/high_max": 0.001036830319208093,
+      "clip_ratio/high_mean": 0.00025920757980202325,
+      "clip_ratio/low_mean": 0.00021704024038626812,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00047624782018829137,
+      "epoch": 0.5625,
+      "grad_norm": 1.4479969171464213,
+      "kl": 0.015131806954741478,
+      "learning_rate": 4.242861112477118e-07,
+      "loss": 0.00018898912821896374,
+      "step": 90,
+      "step_time": 27.330287978518754
+    },
+    {
+      "clip_ratio/high_max": 0.000748650636523962,
+      "clip_ratio/high_mean": 0.0001871626591309905,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0001871626591309905,
+      "epoch": 0.56875,
+      "grad_norm": 1.6233761839534222,
+      "kl": 0.010346731753088534,
+      "learning_rate": 4.1428504251627325e-07,
+      "loss": 0.00015490964869968593,
+      "step": 91,
+      "step_time": 26.672464127652347
+    },
+    {
+      "clip_ratio/high_max": 0.001690799806965515,
+      "clip_ratio/high_mean": 0.00042269995174137875,
+      "clip_ratio/low_mean": 9.1552734375e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0005142526861163788,
+      "epoch": 0.575,
+      "grad_norm": 0.7839776299760853,
+      "kl": 0.01430910942144692,
+      "learning_rate": 4.0431918476344685e-07,
+      "loss": 0.0002364989195484668,
+      "step": 92,
+      "step_time": 26.243466397747397
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.58125,
+      "grad_norm": 0.06011538617189931,
+      "kl": 0.021385682513937354,
+      "learning_rate": 3.943926318791963e-07,
+      "loss": 0.00021372745686676353,
+      "step": 93,
+      "step_time": 24.460721372626722
+    },
+    {
+      "clip_ratio/high_max": 0.00047964986879378557,
+      "clip_ratio/high_mean": 0.00011991246719844639,
+      "clip_ratio/low_mean": 0.00048779033386381343,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0006077028010622598,
+      "epoch": 0.5875,
+      "grad_norm": 1.1336953776766314,
+      "kl": 0.014302460243925452,
+      "learning_rate": 3.845094616073783e-07,
+      "loss": 0.0003261067031417042,
+      "step": 94,
+      "step_time": 25.942532342858613
+    },
+    {
+      "clip_ratio/high_max": 0.001074297157174442,
+      "clip_ratio/high_mean": 0.0002685742892936105,
+      "clip_ratio/low_mean": 0.0004134220980631653,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.000681996392813744,
+      "epoch": 0.59375,
+      "grad_norm": 1.3162579179804246,
+      "kl": 0.01187098235823214,
+      "learning_rate": 3.7467373387063964e-07,
+      "loss": 0.00021524648764170706,
+      "step": 95,
+      "step_time": 26.98814983991906
+    },
+    {
+      "clip_ratio/high_max": 0.0024325912236236036,
+      "clip_ratio/high_mean": 0.0006081478059059009,
+      "clip_ratio/low_mean": 0.00016937669715844095,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0007775245030643418,
+      "epoch": 0.6,
+      "grad_norm": 2.0080688096935106,
+      "kl": 0.02259773830883205,
+      "learning_rate": 3.648894891026358e-07,
+      "loss": 0.00034420654992572963,
+      "step": 96,
+      "step_time": 26.476862422190607
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.3984375,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1320.09375,
+      "completions/min_length": 132.0,
+      "epoch": 0.60625,
+      "frac_reward_zero_std": 0.84375,
+      "grad_norm": 1.7286845708014833,
+      "kl": 0.0178290787152946,
+      "learning_rate": 3.5516074658825397e-07,
+      "loss": 0.00017827155534178019,
+      "reward": 0.03125,
+      "reward_std": 0.06378498673439026,
+      "rewards/MajorityAccuracy/mean": 0.03125,
+      "rewards/MajorityAccuracy/std": 0.17433346807956696,
+      "step": 97,
+      "step_time": 154.44210411421955
+    },
+    {
+      "clip_ratio/high_max": 0.0009191176504828036,
+      "clip_ratio/high_mean": 0.0002297794126207009,
+      "clip_ratio/low_mean": 1.885938399937004e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00024863879662007093,
+      "epoch": 0.6125,
+      "grad_norm": 2.502292557077299,
+      "kl": 0.01579635846428573,
+      "learning_rate": 3.454915028125263e-07,
+      "loss": 4.413771603140049e-05,
+      "step": 98,
+      "step_time": 22.85462570656091
+    },
+    {
+      "clip_ratio/high_max": 0.0002939447294920683,
+      "clip_ratio/high_mean": 7.348618237301707e-05,
+      "clip_ratio/low_mean": 0.000152587890625,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00022607407299801707,
+      "epoch": 0.61875,
+      "grad_norm": 1.0219419102292078,
+      "kl": 0.01679926400538534,
+      "learning_rate": 3.3588572981890684e-07,
+      "loss": 0.00021697618649341166,
+      "step": 99,
+      "step_time": 26.765038440469652
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.625,
+      "grad_norm": 0.03026794717890847,
+      "kl": 0.01039301318814978,
+      "learning_rate": 3.263473735775899e-07,
+      "loss": 0.00010400135215604678,
+      "step": 100,
+      "step_time": 26.877484743483365
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.63125,
+      "grad_norm": 0.0477417206253373,
+      "kl": 0.015311384107917547,
+      "learning_rate": 3.1688035236453865e-07,
+      "loss": 0.00015321244427468628,
+      "step": 101,
+      "step_time": 26.605776181910187
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.6375,
+      "grad_norm": 0.021713577192659133,
+      "kl": 0.008446975669357926,
+      "learning_rate": 3.0748855515189096e-07,
+      "loss": 8.44213500386104e-05,
+      "step": 102,
+      "step_time": 27.039478654041886
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.64375,
+      "grad_norm": 0.0500846318519706,
+      "kl": 0.012924895156174898,
+      "learning_rate": 2.981758400104028e-07,
+      "loss": 0.0001292554079554975,
+      "step": 103,
+      "step_time": 26.765728789381683
+    },
+    {
+      "clip_ratio/high_max": 0.0006183147634146735,
+      "clip_ratio/high_mean": 0.00015457869085366838,
+      "clip_ratio/low_mean": 0.0015487591372220777,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0017033378171618097,
+      "epoch": 0.65,
+      "grad_norm": 1.542101630080852,
+      "kl": 0.01352716307155788,
+      "learning_rate": 2.8894603252458403e-07,
+      "loss": 0.0002724425867199898,
+      "step": 104,
+      "step_time": 25.733699928037822
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.42578125,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1331.046875,
+      "completions/min_length": 88.0,
+      "epoch": 0.65625,
+      "frac_reward_zero_std": 0.8125,
+      "grad_norm": 0.029195187228000158,
+      "kl": 0.015703897108323872,
+      "learning_rate": 2.7980292422118277e-07,
+      "loss": 0.00015708077989984304,
+      "reward": 0.0625,
+      "reward_std": 0.07141612470149994,
+      "rewards/MajorityAccuracy/mean": 0.0625,
+      "rewards/MajorityAccuracy/std": 0.24253562092781067,
+      "step": 105,
+      "step_time": 154.14334033429623
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.6625,
+      "grad_norm": 1.4994768722423415,
+      "kl": 0.009777658036909997,
+      "learning_rate": 2.70750271011657e-07,
+      "loss": -2.522302747820504e-05,
+      "step": 106,
+      "step_time": 27.10605376539752
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.66875,
+      "grad_norm": 0.015432477751076666,
+      "kl": 0.007634364010300487,
+      "learning_rate": 2.6179179164927754e-07,
+      "loss": 7.631300104549155e-05,
+      "step": 107,
+      "step_time": 27.18943145032972
+    },
+    {
+      "clip_ratio/high_max": 0.0008983310108305886,
+      "clip_ratio/high_mean": 0.00022458275270764716,
+      "clip_ratio/low_mean": 0.0009245195324183442,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0011491022887639701,
+      "epoch": 0.675,
+      "grad_norm": 1.8440944307055476,
+      "kl": 0.01736880501266569,
+      "learning_rate": 2.529311662014972e-07,
+      "loss": -2.0738301827805117e-05,
+      "step": 108,
+      "step_time": 26.61964293476194
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.68125,
+      "grad_norm": 0.029564612840075576,
+      "kl": 0.010009491816163063,
+      "learning_rate": 2.441720345382089e-07,
+      "loss": 0.00010014248255174607,
+      "step": 109,
+      "step_time": 26.47751919273287
+    },
+    {
+      "clip_ratio/high_max": 0.00236713164485991,
+      "clip_ratio/high_mean": 0.0005917829112149775,
+      "clip_ratio/low_mean": 0.000926397096918663,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.001518179997219704,
+      "epoch": 0.6875,
+      "grad_norm": 3.9500588322701,
+      "kl": 0.01923341676592827,
+      "learning_rate": 2.355179948365189e-07,
+      "loss": 0.0004456048191059381,
+      "step": 110,
+      "step_time": 27.13659136276692
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.69375,
+      "grad_norm": 0.01808303292179546,
+      "kl": 0.011186737101525068,
+      "learning_rate": 2.26972602102645e-07,
+      "loss": 0.00011187456402694806,
+      "step": 111,
+      "step_time": 26.935521917883307
+    },
+    {
+      "clip_ratio/high_max": 0.0016937769541982561,
+      "clip_ratio/high_mean": 0.00042344423854956403,
+      "clip_ratio/low_mean": 3.0517578125e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00045396181667456403,
+      "epoch": 0.7,
+      "grad_norm": 0.6333793110835408,
+      "kl": 0.018489439389668405,
+      "learning_rate": 2.1853936671155127e-07,
+      "loss": 0.0002662469050846994,
+      "step": 112,
+      "step_time": 22.65738155785948
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.3046875,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1177.5,
+      "completions/min_length": 10.0,
+      "epoch": 0.70625,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 4.399573740437156,
+      "kl": 0.02099012373946607,
+      "learning_rate": 2.1022175296491512e-07,
+      "loss": 0.00020997099636588246,
+      "reward": 0.171875,
+      "reward_std": 0.10482378304004669,
+      "rewards/MajorityAccuracy/mean": 0.171875,
+      "rewards/MajorityAccuracy/std": 0.3780107796192169,
+      "step": 113,
+      "step_time": 152.79690040508285
+    },
+    {
+      "clip_ratio/high_max": 0.0022732564248144627,
+      "clip_ratio/high_mean": 0.0006157704483484849,
+      "clip_ratio/low_mean": 0.0001068115234375,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0007225819645100273,
+      "epoch": 0.7125,
+      "grad_norm": 1.6999569631526663,
+      "kl": 0.012765144114382565,
+      "learning_rate": 2.0202317766802152e-07,
+      "loss": 0.00022171199088916183,
+      "step": 114,
+      "step_time": 25.505992654711008
+    },
+    {
+      "clip_ratio/high_max": 0.002832389815011993,
+      "clip_ratio/high_mean": 0.0007080974537529983,
+      "clip_ratio/low_mean": 0.00045675926412513945,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0011648567269730847,
+      "epoch": 0.71875,
+      "grad_norm": 1.4941499806420737,
+      "kl": 0.01109716051723808,
+      "learning_rate": 1.9394700872616853e-07,
+      "loss": 0.0002744462981354445,
+      "step": 115,
+      "step_time": 27.08673968585208
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.725,
+      "grad_norm": 0.029163133933410825,
+      "kl": 0.0157310098875314,
+      "learning_rate": 1.8599656376116024e-07,
+      "loss": 0.00015721381350886077,
+      "step": 116,
+      "step_time": 26.825206097681075
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.73125,
+      "grad_norm": 0.035106713120906026,
+      "kl": 0.01622657710686326,
+      "learning_rate": 1.7817510874845582e-07,
+      "loss": 0.00016229500761255622,
+      "step": 117,
+      "step_time": 25.031286623328924
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.7375,
+      "grad_norm": 0.03269685192507236,
+      "kl": 0.010970906121656299,
+      "learning_rate": 1.7048585667553412e-07,
+      "loss": 0.00010973076859954745,
+      "step": 118,
+      "step_time": 26.69840591121465
+    },
+    {
+      "clip_ratio/high_max": 0.0002168883802369237,
+      "clip_ratio/high_mean": 5.4222095059230924e-05,
+      "clip_ratio/low_mean": 0.0001572325054439716,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00021145460050320253,
+      "epoch": 0.74375,
+      "grad_norm": 0.7828780268548782,
+      "kl": 0.011238506296649575,
+      "learning_rate": 1.6293196622202632e-07,
+      "loss": 5.9209236496826634e-05,
+      "step": 119,
+      "step_time": 26.86710120458156
+    },
+    {
+      "clip_ratio/high_max": 0.0019035532604902983,
+      "clip_ratio/high_mean": 0.00047588831512257457,
+      "clip_ratio/low_mean": 0.0003684155599330552,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0008443038750556298,
+      "epoch": 0.75,
+      "grad_norm": 2.8952095910655045,
+      "kl": 0.0151667749742046,
+      "learning_rate": 1.555165404621567e-07,
+      "loss": 0.00016583604156039655,
+      "step": 120,
+      "step_time": 25.068036573473364
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.41796875,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1190.1875,
+      "completions/min_length": 60.0,
+      "epoch": 0.75625,
+      "frac_reward_zero_std": 0.71875,
+      "grad_norm": 1.852357755417005,
+      "kl": 0.020978386281058192,
+      "learning_rate": 1.4824262559002592e-07,
+      "loss": 0.00020975868392270058,
+      "reward": 0.125,
+      "reward_std": 0.12217669934034348,
+      "rewards/MajorityAccuracy/mean": 0.125,
+      "rewards/MajorityAccuracy/std": 0.33136674761772156,
+      "step": 121,
+      "step_time": 150.99877596180886
+    },
+    {
+      "clip_ratio/high_max": 0.0010778531868709251,
+      "clip_ratio/high_mean": 0.0002694632967177313,
+      "clip_ratio/low_mean": 9.1552734375e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0003610160310927313,
+      "epoch": 0.7625,
+      "grad_norm": 0.8200329565435454,
+      "kl": 0.00914413557620719,
+      "learning_rate": 1.4111320966826057e-07,
+      "loss": 0.00010975699115078896,
+      "step": 122,
+      "step_time": 26.776213052216917
+    },
+    {
+      "clip_ratio/high_max": 0.0015804232680238783,
+      "clip_ratio/high_mean": 0.00042359260260127485,
+      "clip_ratio/low_mean": 0.0001220703125,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0005456629151012748,
+      "epoch": 0.76875,
+      "grad_norm": 1.0871516110859851,
+      "kl": 0.014426440349780023,
+      "learning_rate": 1.3413122140054217e-07,
+      "loss": 0.00023178658739198,
+      "step": 123,
+      "step_time": 26.691455316264182
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.775,
+      "grad_norm": 0.015225187732103898,
+      "kl": 0.008163404301740229,
+      "learning_rate": 1.272995289285202e-07,
+      "loss": 8.163601160049438e-05,
+      "step": 124,
+      "step_time": 27.203925523441285
+    },
+    {
+      "clip_ratio/high_max": 0.0003822630096692592,
+      "clip_ratio/high_mean": 9.55657524173148e-05,
+      "clip_ratio/low_mean": 9.108684389502741e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0001866525963123422,
+      "epoch": 0.78125,
+      "grad_norm": 1.0456848685068305,
+      "kl": 0.017831664299592376,
+      "learning_rate": 1.2062093865360457e-07,
+      "loss": 0.00017555346130393445,
+      "step": 125,
+      "step_time": 25.13827875163406
+    },
+    {
+      "clip_ratio/high_max": 0.0033226608065888286,
+      "clip_ratio/high_mean": 0.0008306652016472071,
+      "clip_ratio/low_mean": 0.0008886561554390937,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0017193213279824704,
+      "epoch": 0.7875,
+      "grad_norm": 3.2094835586405748,
+      "kl": 0.01365972391795367,
+      "learning_rate": 1.1409819408411897e-07,
+      "loss": 6.014561949996278e-05,
+      "step": 126,
+      "step_time": 27.087209628429264
+    },
+    {
+      "clip_ratio/high_max": 0.0012360726250335574,
+      "clip_ratio/high_mean": 0.00030901815625838935,
+      "clip_ratio/low_mean": 4.57763671875e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00035479452344588935,
+      "epoch": 0.79375,
+      "grad_norm": 1.096953891730799,
+      "kl": 0.01426635798998177,
+      "learning_rate": 1.0773397470829143e-07,
+      "loss": 0.0003346058074384928,
+      "step": 127,
+      "step_time": 26.836154578719288
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.8,
+      "grad_norm": 0.06987881304847188,
+      "kl": 0.018999760504812002,
+      "learning_rate": 1.0153089489354256e-07,
+      "loss": 0.00019001578039024025,
+      "step": 128,
+      "step_time": 19.537395481020212
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.37890625,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1249.0390625,
+      "completions/min_length": 64.0,
+      "epoch": 0.80625,
+      "frac_reward_zero_std": 0.84375,
+      "grad_norm": 0.04673626588155259,
+      "kl": 0.012517470517195761,
+      "learning_rate": 9.549150281252632e-08,
+      "loss": 0.0001251695939572528,
+      "reward": 0.078125,
+      "reward_std": 0.07061977684497833,
+      "rewards/MajorityAccuracy/mean": 0.078125,
+      "rewards/MajorityAccuracy/std": 0.26889389753341675,
+      "step": 129,
+      "step_time": 156.86324841761962
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.8125,
+      "grad_norm": 0.02274537921370547,
+      "kl": 0.011074492591433227,
+      "learning_rate": 8.961827939636196e-08,
+      "loss": 0.00011072507913922891,
+      "step": 130,
+      "step_time": 27.18872858118266
+    },
+    {
+      "clip_ratio/high_max": 7.97193861217238e-05,
+      "clip_ratio/high_mean": 1.992984653043095e-05,
+      "clip_ratio/low_mean": 3.0517578125e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 5.044742465543095e-05,
+      "epoch": 0.81875,
+      "grad_norm": 0.6873060924827216,
+      "kl": 0.021253438317216933,
+      "learning_rate": 8.391363731548811e-08,
+      "loss": 0.00024855026276782155,
+      "step": 131,
+      "step_time": 25.752799670677632
+    },
+    {
+      "clip_ratio/high_max": 0.0005626126439892687,
+      "clip_ratio/high_mean": 0.00014065316099731717,
+      "clip_ratio/low_mean": 0.00013899661280447617,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00027964977743977215,
+      "epoch": 0.825,
+      "grad_norm": 1.357999707169394,
+      "kl": 0.01425129035487771,
+      "learning_rate": 7.837991998855897e-08,
+      "loss": 4.429294858709909e-05,
+      "step": 132,
+      "step_time": 26.547014091629535
+    },
+    {
+      "clip_ratio/high_max": 0.0017875017947517335,
+      "clip_ratio/high_mean": 0.0004468754486879334,
+      "clip_ratio/low_mean": 1.52587890625e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0004621342377504334,
+      "epoch": 0.83125,
+      "grad_norm": 2.0626184393880713,
+      "kl": 0.011470346536953002,
+      "learning_rate": 7.301940061978722e-08,
+      "loss": 0.00032814836595207453,
+      "step": 133,
+      "step_time": 27.090106007643044
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.8375,
+      "grad_norm": 0.03291072259783065,
+      "kl": 0.012683136039413512,
+      "learning_rate": 6.783428126513125e-08,
+      "loss": 0.00012685688852798194,
+      "step": 134,
+      "step_time": 26.810902387369424
+    },
+    {
+      "clip_ratio/high_max": 0.00010080645006382838,
+      "clip_ratio/high_mean": 2.5201612515957095e-05,
+      "clip_ratio/low_mean": 0.0001722746092127636,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0001974762217287207,
+      "epoch": 0.84375,
+      "grad_norm": 0.9329415584197308,
+      "kl": 0.015216854168102145,
+      "learning_rate": 6.282669192770895e-08,
+      "loss": 0.00016667565796524286,
+      "step": 135,
+      "step_time": 26.53485087584704
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.85,
+      "grad_norm": 0.02527168799710476,
+      "kl": 0.01225942256860435,
+      "learning_rate": 5.799868968281074e-08,
+      "loss": 0.00012267293641343713,
+      "step": 136,
+      "step_time": 27.064406784251332
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.44921875,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1391.20703125,
+      "completions/min_length": 60.0,
+      "epoch": 0.85625,
+      "frac_reward_zero_std": 0.84375,
+      "grad_norm": 3.2673729262802826,
+      "kl": 0.014151524868793786,
+      "learning_rate": 5.335225783287051e-08,
+      "loss": 0.00014146300964057446,
+      "reward": 0.09375,
+      "reward_std": 0.07061977684497833,
+      "rewards/MajorityAccuracy/mean": 0.09375,
+      "rewards/MajorityAccuracy/std": 0.2920515835285187,
+      "step": 137,
+      "step_time": 157.97751324716955
+    },
+    {
+      "clip_ratio/high_max": 0.0005625000267173164,
+      "clip_ratio/high_mean": 0.0001406250066793291,
+      "clip_ratio/low_mean": 7.62939453125e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0002169189519918291,
+      "epoch": 0.8625,
+      "grad_norm": 0.6359359587835077,
+      "kl": 0.007396275468636304,
+      "learning_rate": 4.888930509274125e-08,
+      "loss": 0.0001643006398808211,
+      "step": 138,
+      "step_time": 27.179388634860516
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.86875,
+      "grad_norm": 0.034903839450665955,
+      "kl": 0.01108026027213782,
+      "learning_rate": 4.4611664805611794e-08,
+      "loss": 0.00011078552051912993,
+      "step": 139,
+      "step_time": 26.624722996726632
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.875,
+      "grad_norm": 0.03895507539992596,
+      "kl": 0.01511156721971929,
+      "learning_rate": 4.0521094189884696e-08,
+      "loss": 0.00015112917753867805,
+      "step": 140,
+      "step_time": 24.263086621649563
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.88125,
+      "grad_norm": 0.01975312792886866,
+      "kl": 0.009903040598146617,
+      "learning_rate": 3.6619273617325695e-08,
+      "loss": 9.902417514240369e-05,
+      "step": 141,
+      "step_time": 27.16489995410666
+    },
+    {
+      "clip_ratio/high_max": 0.0003225806576665491,
+      "clip_ratio/high_mean": 8.064516441663727e-05,
+      "clip_ratio/low_mean": 0.00015921594604151323,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0002398611104581505,
+      "epoch": 0.8875,
+      "grad_norm": 1.1230453494816666,
+      "kl": 0.009959969262126833,
+      "learning_rate": 3.2907805922781476e-08,
+      "loss": 0.0001246541942236945,
+      "step": 142,
+      "step_time": 25.601745033171028
+    },
+    {
+      "clip_ratio/high_max": 0.00030517578125,
+      "clip_ratio/high_mean": 7.62939453125e-05,
+      "clip_ratio/low_mean": 5.8125729992752895e-05,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0001344196753052529,
+      "epoch": 0.89375,
+      "grad_norm": 0.8367566020787549,
+      "kl": 0.010120446560904384,
+      "learning_rate": 2.9388215745748345e-08,
+      "loss": 8.353935845661908e-05,
+      "step": 143,
+      "step_time": 27.26591040752828
+    },
+    {
+      "clip_ratio/high_max": 0.006762079079635441,
+      "clip_ratio/high_mean": 0.0016905197699088603,
+      "clip_ratio/low_mean": 0.0001140510939876549,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0018045708638965152,
+      "epoch": 0.9,
+      "grad_norm": 4.1242327413908635,
+      "kl": 0.01979304593987763,
+      "learning_rate": 2.6061948904063658e-08,
+      "loss": 0.00046489015221595764,
+      "step": 144,
+      "step_time": 26.319018109235913
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.3671875,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1178.77734375,
+      "completions/min_length": 68.0,
+      "epoch": 0.90625,
+      "frac_reward_zero_std": 0.875,
+      "grad_norm": 0.043390373763185275,
+      "kl": 0.02089148503728211,
+      "learning_rate": 2.293037179997559e-08,
+      "loss": 0.00020895429770462215,
+      "reward": 0.0703125,
+      "reward_std": 0.058391720056533813,
+      "rewards/MajorityAccuracy/mean": 0.0703125,
+      "rewards/MajorityAccuracy/std": 0.2561737596988678,
+      "step": 145,
+      "step_time": 152.9770716270432
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.00021258502965793014,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00021258502965793014,
+      "epoch": 0.9125,
+      "grad_norm": 3.7417050130527216,
+      "kl": 0.012743567349389195,
+      "learning_rate": 1.9994770858837107e-08,
+      "loss": 0.00016488137771375477,
+      "step": 146,
+      "step_time": 26.360899354796857
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.91875,
+      "grad_norm": 0.017627693309420905,
+      "kl": 0.008871013240423054,
+      "learning_rate": 1.725635200065323e-08,
+      "loss": 8.874472405295819e-05,
+      "step": 147,
+      "step_time": 26.728741920553148
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.925,
+      "grad_norm": 0.027850791805096278,
+      "kl": 0.012429802678525448,
+      "learning_rate": 1.4716240144699187e-08,
+      "loss": 0.00012430702918209136,
+      "step": 148,
+      "step_time": 25.1067868899554
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.93125,
+      "grad_norm": 0.022899454634798085,
+      "kl": 0.011438554211053997,
+      "learning_rate": 1.2375478747413015e-08,
+      "loss": 0.00011431316670496017,
+      "step": 149,
+      "step_time": 27.200391781982034
+    },
+    {
+      "clip_ratio/high_max": 0.0005530973430722952,
+      "clip_ratio/high_mean": 0.0001382743357680738,
+      "clip_ratio/low_mean": 0.0002983602425956633,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0004366345783637371,
+      "epoch": 0.9375,
+      "grad_norm": 2.1559927542706125,
+      "kl": 0.021093261195346713,
+      "learning_rate": 1.0235029373752757e-08,
+      "loss": 3.055015986319631e-05,
+      "step": 150,
+      "step_time": 27.177560928743333
+    },
+    {
+      "clip_ratio/high_max": 0.0003370907070348039,
+      "clip_ratio/high_mean": 8.427267675870098e-05,
+      "clip_ratio/low_mean": 0.0002516035019652918,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0003358761787239928,
+      "epoch": 0.94375,
+      "grad_norm": 0.8691245019975007,
+      "kl": 0.014613950857892632,
+      "learning_rate": 8.295771302193721e-09,
+      "loss": 0.0002329107519472018,
+      "step": 151,
+      "step_time": 26.683163667097688
+    },
+    {
+      "clip_ratio/high_max": 0.00045256695739226416,
+      "clip_ratio/high_mean": 0.00011314173934806604,
+      "clip_ratio/low_mean": 0.0001068115234375,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.00021995326278556604,
+      "epoch": 0.95,
+      "grad_norm": 0.9560972480384264,
+      "kl": 0.01186251942999661,
+      "learning_rate": 6.558501163527963e-09,
+      "loss": 0.00018430141790304333,
+      "step": 152,
+      "step_time": 27.185652676969767
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.37890625,
+      "completions/max_length": 2048.0,
+      "completions/mean_length": 1257.12890625,
+      "completions/min_length": 9.0,
+      "epoch": 0.95625,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 1.494069921352415,
+      "kl": 0.011846404056996107,
+      "learning_rate": 5.023932613615445e-09,
+      "loss": 0.0001184874345199205,
+      "reward": 0.07421875,
+      "reward_std": 0.1060032919049263,
+      "rewards/MajorityAccuracy/mean": 0.07421875,
+      "rewards/MajorityAccuracy/std": 0.2626400291919708,
+      "step": 153,
+      "step_time": 156.35617168108
+    },
+    {
+      "clip_ratio/high_max": 6.979340832913294e-05,
+      "clip_ratio/high_mean": 1.7448352082283236e-05,
+      "clip_ratio/low_mean": 0.0004445223603397608,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.000461970712422044,
+      "epoch": 0.9625,
+      "grad_norm": 0.8112326159698409,
+      "kl": 0.014378462685272098,
+      "learning_rate": 3.6926960402202666e-09,
+      "loss": 0.00010994858894264325,
+      "step": 154,
+      "step_time": 26.154397854115814
+    },
+    {
+      "clip_ratio/high_max": 0.0007042253273539245,
+      "clip_ratio/high_mean": 0.00021308239956852049,
+      "clip_ratio/low_mean": 0.00040516959415981546,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.000618251993728336,
+      "epoch": 0.96875,
+      "grad_norm": 2.143100458610283,
+      "kl": 0.01617168402299285,
+      "learning_rate": 2.5653383040524224e-09,
+      "loss": 1.2679087376454845e-05,
+      "step": 155,
+      "step_time": 27.15231363195926
+    },
+    {
+      "clip_ratio/high_max": 0.0018848067265935242,
+      "clip_ratio/high_mean": 0.00047120168164838105,
+      "clip_ratio/low_mean": 0.0001678466796875,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0006390483613358811,
+      "epoch": 0.975,
+      "grad_norm": 2.0663625813673905,
+      "kl": 0.01631955022457987,
+      "learning_rate": 1.642322514122385e-09,
+      "loss": 0.00023865113325882703,
+      "step": 156,
+      "step_time": 26.607338081579655
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.98125,
+      "grad_norm": 0.14358644842033974,
+      "kl": 0.011463151429779828,
+      "learning_rate": 9.240278374995636e-10,
+      "loss": 0.00011462045949883759,
+      "step": 157,
+      "step_time": 27.141568647231907
+    },
+    {
+      "clip_ratio/high_max": 0.0006358536920743063,
+      "clip_ratio/high_mean": 0.00015896342301857658,
+      "clip_ratio/low_mean": 0.00033033998079190496,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0004893034038104815,
+      "epoch": 0.9875,
+      "grad_norm": 1.7532337311980066,
+      "kl": 0.011919080396182835,
+      "learning_rate": 4.1074934355384006e-10,
+      "loss": 0.0002080941922031343,
+      "step": 158,
+      "step_time": 27.232368832919747
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 0.99375,
+      "grad_norm": 0.022185758933601262,
+      "kl": 0.013458746136166155,
+      "learning_rate": 1.0269788274358537e-10,
+      "loss": 0.0001346150820609182,
+      "step": 159,
+      "step_time": 26.474060396198183
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "epoch": 1.0,
+      "grad_norm": 0.02565273377492213,
+      "kl": 0.014351242687553167,
+      "learning_rate": 0.0,
+      "loss": 0.000143471741466783,
+      "step": 160,
+      "step_time": 26.587386595550925
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 16,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}