{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 10,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": Infinity,
      "learning_rate": 0.00017600000000000002,
      "loss": 5.3252,
      "step": 5
    },
    {
      "epoch": 0.16,
      "grad_norm": 47.4116325378418,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.8728,
      "step": 10
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.47811615467071533,
      "eval_runtime": 348.301,
      "eval_samples_per_second": 0.574,
      "eval_steps_per_second": 0.287,
      "step": 10
    },
    {
      "epoch": 0.24,
      "grad_norm": 4.025637149810791,
      "learning_rate": 9.6e-05,
      "loss": 0.3961,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 4.001928806304932,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.3335,
      "step": 20
    },
    {
      "epoch": 0.32,
      "eval_loss": 0.3375803232192993,
      "eval_runtime": 347.7016,
      "eval_samples_per_second": 0.575,
      "eval_steps_per_second": 0.288,
      "step": 20
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.0807480812072754,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2833,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1864510458066432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}