{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006837606837606838,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006837606837606838,
      "grad_norm": 1.0428560972213745,
      "learning_rate": 2e-05,
      "loss": 2.584,
      "step": 1
    },
    {
      "epoch": 0.0006837606837606838,
      "eval_loss": 2.547212600708008,
      "eval_runtime": 35.8849,
      "eval_samples_per_second": 17.166,
      "eval_steps_per_second": 8.583,
      "step": 1
    },
    {
      "epoch": 0.0013675213675213675,
      "grad_norm": 1.0410929918289185,
      "learning_rate": 4e-05,
      "loss": 2.5779,
      "step": 2
    },
    {
      "epoch": 0.0020512820512820513,
      "grad_norm": 1.01620614528656,
      "learning_rate": 6e-05,
      "loss": 2.5313,
      "step": 3
    },
    {
      "epoch": 0.0020512820512820513,
      "eval_loss": 2.5372848510742188,
      "eval_runtime": 35.024,
      "eval_samples_per_second": 17.588,
      "eval_steps_per_second": 8.794,
      "step": 3
    },
    {
      "epoch": 0.002735042735042735,
      "grad_norm": 0.9978483319282532,
      "learning_rate": 8e-05,
      "loss": 2.4736,
      "step": 4
    },
    {
      "epoch": 0.003418803418803419,
      "grad_norm": 1.1760221719741821,
      "learning_rate": 0.0001,
      "loss": 2.4999,
      "step": 5
    },
    {
      "epoch": 0.0041025641025641026,
      "grad_norm": 1.2855255603790283,
      "learning_rate": 0.00012,
      "loss": 2.4886,
      "step": 6
    },
    {
      "epoch": 0.0041025641025641026,
      "eval_loss": 2.394721508026123,
      "eval_runtime": 35.0451,
      "eval_samples_per_second": 17.577,
      "eval_steps_per_second": 8.789,
      "step": 6
    },
    {
      "epoch": 0.004786324786324786,
      "grad_norm": 0.9151820540428162,
      "learning_rate": 0.00014,
      "loss": 2.3836,
      "step": 7
    },
    {
      "epoch": 0.00547008547008547,
      "grad_norm": 0.6948174238204956,
      "learning_rate": 0.00016,
      "loss": 2.2564,
      "step": 8
    },
    {
      "epoch": 0.006153846153846154,
      "grad_norm": 0.8624392747879028,
      "learning_rate": 0.00018,
      "loss": 2.3481,
      "step": 9
    },
    {
      "epoch": 0.006153846153846154,
      "eval_loss": 2.281820058822632,
      "eval_runtime": 35.0533,
      "eval_samples_per_second": 17.573,
      "eval_steps_per_second": 8.787,
      "step": 9
    },
    {
      "epoch": 0.006837606837606838,
      "grad_norm": 1.2487035989761353,
      "learning_rate": 0.0002,
      "loss": 2.3472,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}