trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 4.0,
      "epoch": 0.8,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 4.45111483335495,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.9199999570846558,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.031114899553358555,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 2
    },
    {
      "completion_length": 4.0,
      "epoch": 1.4,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 4.011214812596639,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 1.9199999570846558,
      "rewards/consensus_reward_func": 2.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.09121479839086533,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 4
    },
    {
      "completion_length": 4.0,
      "epoch": 2.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 4.602512041727702,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 3.2533332904179892,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.015845506141583126,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 6
    },
    {
      "completion_length": 4.0,
      "epoch": 2.8,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 4.456474184989929,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.9199999570846558,
      "rewards/consensus_reward_func": 1.5,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.036474294029176235,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 8
    },
    {
      "completion_length": 4.0,
      "epoch": 3.4,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 3.9540088176727295,
      "reward_std": 0.0,
      "rewards/concensus_correctness_reward_func": 2.585333267847697,
      "rewards/consensus_reward_func": 1.3333333333333333,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.035342139502366386,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 10
    },
    {
      "epoch": 3.4,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 322.7294,
      "train_samples_per_second": 0.124,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}