{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5194805194805194,
  "eval_steps": 15,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017316017316017316,
      "eval_loss": 0.8123326897621155,
      "eval_runtime": 21.4215,
      "eval_samples_per_second": 4.528,
      "eval_steps_per_second": 0.607,
      "step": 1
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 1.44769287109375,
      "learning_rate": 3e-05,
      "loss": 3.0463,
      "step": 3
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 0.9673851728439331,
      "learning_rate": 6e-05,
      "loss": 2.883,
      "step": 6
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 1.2237026691436768,
      "learning_rate": 9e-05,
      "loss": 3.0048,
      "step": 9
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 1.0807669162750244,
      "learning_rate": 9.9962857531815e-05,
      "loss": 2.8812,
      "step": 12
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 0.8111446499824524,
      "learning_rate": 9.976801044672608e-05,
      "loss": 2.8254,
      "step": 15
    },
    {
      "epoch": 0.2597402597402597,
      "eval_loss": 0.7221285700798035,
      "eval_runtime": 21.8495,
      "eval_samples_per_second": 4.439,
      "eval_steps_per_second": 0.595,
      "step": 15
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 0.7993184924125671,
      "learning_rate": 9.940682350363912e-05,
      "loss": 2.5783,
      "step": 18
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.88717120885849,
      "learning_rate": 9.888050389939172e-05,
      "loss": 3.0288,
      "step": 21
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.9446913003921509,
      "learning_rate": 9.819081075450014e-05,
      "loss": 2.6752,
      "step": 24
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 0.7598215937614441,
      "learning_rate": 9.734004923364257e-05,
      "loss": 2.6636,
      "step": 27
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.9138664603233337,
      "learning_rate": 9.63310628410961e-05,
      "loss": 2.6451,
      "step": 30
    },
    {
      "epoch": 0.5194805194805194,
      "eval_loss": 0.6947051286697388,
      "eval_runtime": 21.8569,
      "eval_samples_per_second": 4.438,
      "eval_steps_per_second": 0.595,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 173,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.545618673631232e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}