{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.992,
  "eval_steps": 10,
  "global_step": 31,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 72.5,
      "learning_rate": 1e-05,
      "loss": 0.791,
      "mean_token_accuracy": 0.7902325183153153,
      "step": 5
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.78125,
      "learning_rate": 1e-05,
      "loss": 0.458,
      "mean_token_accuracy": 0.8656408250331878,
      "step": 10
    },
    {
      "epoch": 0.32,
      "eval_loss": 0.5019531846046448,
      "eval_mean_token_accuracy": 0.8634858332057991,
      "eval_runtime": 8.0528,
      "eval_samples_per_second": 12.542,
      "eval_steps_per_second": 12.542,
      "step": 10
    },
    {
      "epoch": 0.48,
      "grad_norm": 2.390625,
      "learning_rate": 1e-05,
      "loss": 0.4723,
      "mean_token_accuracy": 0.8590857356786727,
      "step": 15
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.1640625,
      "learning_rate": 1e-05,
      "loss": 0.3782,
      "mean_token_accuracy": 0.8752073399722576,
      "step": 20
    },
    {
      "epoch": 0.64,
      "eval_loss": 0.44335949420928955,
      "eval_mean_token_accuracy": 0.8705554610431785,
      "eval_runtime": 8.1133,
      "eval_samples_per_second": 12.449,
      "eval_steps_per_second": 12.449,
      "step": 20
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.5234375,
      "learning_rate": 1e-05,
      "loss": 0.4699,
      "mean_token_accuracy": 0.8568822145462036,
      "step": 25
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.5390625,
      "learning_rate": 1e-05,
      "loss": 0.4329,
      "mean_token_accuracy": 0.8653567247092724,
      "step": 30
    },
    {
      "epoch": 0.96,
      "eval_loss": 0.42237037420272827,
      "eval_mean_token_accuracy": 0.8750163653109333,
      "eval_runtime": 8.1202,
      "eval_samples_per_second": 12.438,
      "eval_steps_per_second": 12.438,
      "step": 30
    },
    {
      "epoch": 0.992,
      "mean_token_accuracy": 0.8463566526770592,
      "step": 31,
      "total_flos": 3.478922794514227e+16,
      "train_loss": 0.5009717364465037,
      "train_runtime": 188.6962,
      "train_samples_per_second": 2.65,
      "train_steps_per_second": 0.164
    }
  ],
  "logging_steps": 5,
  "max_steps": 31,
  "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": 3.478922794514227e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}