{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 67,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 790.1966869354249,
      "epoch": 0.14925373134328357,
      "grad_norm": 0.045969344675540924,
      "kl": 0.005614055693149567,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.0002,
      "reward": 0.43805805570445955,
      "reward_std": 0.1994351573754102,
      "rewards/accuracy_reward": 0.43805805570445955,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 741.1705680847168,
      "epoch": 0.29850746268656714,
      "grad_norm": 0.08663639426231384,
      "kl": 0.029787063598632812,
      "learning_rate": 1.777145961456971e-05,
      "loss": 0.0012,
      "reward": 0.5960937763564289,
      "reward_std": 0.1917683265171945,
      "rewards/accuracy_reward": 0.5960937763564289,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 716.4268184661865,
      "epoch": 0.44776119402985076,
      "grad_norm": 0.09228167682886124,
      "kl": 0.056108856201171876,
      "learning_rate": 1.3583679495453e-05,
      "loss": 0.0022,
      "reward": 0.5766741338185966,
      "reward_std": 0.19859230788424612,
      "rewards/accuracy_reward": 0.5766741338185966,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 738.0541633605957,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.09121408313512802,
      "kl": 0.117388916015625,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.0047,
      "reward": 0.5588169892318546,
      "reward_std": 0.21862531267106533,
      "rewards/accuracy_reward": 0.5588169892318546,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 724.3135387420655,
      "epoch": 0.746268656716418,
      "grad_norm": 0.07020629942417145,
      "kl": 0.108941650390625,
      "learning_rate": 3.7067960895016277e-06,
      "loss": 0.0044,
      "reward": 0.5783482406288385,
      "reward_std": 0.19667246341705322,
      "rewards/accuracy_reward": 0.5783482406288385,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 725.1489160537719,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.1016106829047203,
      "kl": 0.1120208740234375,
      "learning_rate": 6.641957350279838e-07,
      "loss": 0.0045,
      "reward": 0.5868303838185966,
      "reward_std": 0.1979663790669292,
      "rewards/accuracy_reward": 0.5868303838185966,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 716.7540152413504,
      "epoch": 1.0,
      "kl": 0.10584150041852679,
      "reward": 0.5781781708023378,
      "reward_std": 0.21474498443837678,
      "rewards/accuracy_reward": 0.5781781708023378,
      "rewards/format_reward": 0.0,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.0030148602681540288,
      "train_runtime": 6716.3318,
      "train_samples_per_second": 1.117,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 10,
  "max_steps": 67,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}