{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08161044613710555,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000544069640914037,
      "eval_loss": 0.23080985248088837,
      "eval_runtime": 24.1847,
      "eval_samples_per_second": 16.002,
      "eval_steps_per_second": 8.022,
      "step": 1
    },
    {
      "epoch": 0.00544069640914037,
      "grad_norm": 0.28848734498023987,
      "learning_rate": 0.0002,
      "loss": 0.3543,
      "step": 10
    },
    {
      "epoch": 0.01088139281828074,
      "grad_norm": 0.28202658891677856,
      "learning_rate": 0.0002,
      "loss": 0.2399,
      "step": 20
    },
    {
      "epoch": 0.01632208922742111,
      "grad_norm": 0.39430463314056396,
      "learning_rate": 0.0002,
      "loss": 0.2353,
      "step": 30
    },
    {
      "epoch": 0.02176278563656148,
      "grad_norm": 0.24603690207004547,
      "learning_rate": 0.0002,
      "loss": 0.1954,
      "step": 40
    },
    {
      "epoch": 0.02720348204570185,
      "grad_norm": 0.2858443260192871,
      "learning_rate": 0.0002,
      "loss": 0.194,
      "step": 50
    },
    {
      "epoch": 0.02720348204570185,
      "eval_loss": 0.1075894683599472,
      "eval_runtime": 24.2053,
      "eval_samples_per_second": 15.988,
      "eval_steps_per_second": 8.015,
      "step": 50
    },
    {
      "epoch": 0.03264417845484222,
      "grad_norm": 1.0796252489089966,
      "learning_rate": 0.0002,
      "loss": 0.2065,
      "step": 60
    },
    {
      "epoch": 0.03808487486398259,
      "grad_norm": 0.3447917103767395,
      "learning_rate": 0.0002,
      "loss": 0.1985,
      "step": 70
    },
    {
      "epoch": 0.04352557127312296,
      "grad_norm": 0.30337709188461304,
      "learning_rate": 0.0002,
      "loss": 0.2268,
      "step": 80
    },
    {
      "epoch": 0.04896626768226333,
      "grad_norm": 0.12297934293746948,
      "learning_rate": 0.0002,
      "loss": 0.2141,
      "step": 90
    },
    {
      "epoch": 0.0544069640914037,
      "grad_norm": 0.2504233121871948,
      "learning_rate": 0.0002,
      "loss": 0.185,
      "step": 100
    },
    {
      "epoch": 0.0544069640914037,
      "eval_loss": 0.10059353709220886,
      "eval_runtime": 24.2252,
      "eval_samples_per_second": 15.975,
      "eval_steps_per_second": 8.008,
      "step": 100
    },
    {
      "epoch": 0.05984766050054407,
      "grad_norm": 0.21035900712013245,
      "learning_rate": 0.0002,
      "loss": 0.2442,
      "step": 110
    },
    {
      "epoch": 0.06528835690968444,
      "grad_norm": 0.41095128655433655,
      "learning_rate": 0.0002,
      "loss": 0.1617,
      "step": 120
    },
    {
      "epoch": 0.07072905331882481,
      "grad_norm": 0.19263286888599396,
      "learning_rate": 0.0002,
      "loss": 0.1611,
      "step": 130
    },
    {
      "epoch": 0.07616974972796518,
      "grad_norm": 0.24695733189582825,
      "learning_rate": 0.0002,
      "loss": 0.1977,
      "step": 140
    },
    {
      "epoch": 0.08161044613710555,
      "grad_norm": 0.3113032579421997,
      "learning_rate": 0.0002,
      "loss": 0.219,
      "step": 150
    },
    {
      "epoch": 0.08161044613710555,
      "eval_loss": 0.09649600088596344,
      "eval_runtime": 24.2365,
      "eval_samples_per_second": 15.968,
      "eval_steps_per_second": 8.004,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.262621331075891e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}