{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0390625,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00390625,
      "grad_norm": 0.5725095272064209,
      "learning_rate": 2e-05,
      "loss": 2.2884,
      "step": 1
    },
    {
      "epoch": 0.0078125,
      "grad_norm": 0.5407800674438477,
      "learning_rate": 4e-05,
      "loss": 2.0524,
      "step": 2
    },
    {
      "epoch": 0.01171875,
      "grad_norm": 0.5954123139381409,
      "learning_rate": 6e-05,
      "loss": 2.2442,
      "step": 3
    },
    {
      "epoch": 0.01171875,
      "eval_loss": 2.415464401245117,
      "eval_runtime": 4.7023,
      "eval_samples_per_second": 22.967,
      "eval_steps_per_second": 11.484,
      "step": 3
    },
    {
      "epoch": 0.015625,
      "grad_norm": 0.5602393746376038,
      "learning_rate": 8e-05,
      "loss": 2.3431,
      "step": 4
    },
    {
      "epoch": 0.01953125,
      "grad_norm": 0.5732829570770264,
      "learning_rate": 0.0001,
      "loss": 2.4076,
      "step": 5
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 0.5825575590133667,
      "learning_rate": 0.00012,
      "loss": 1.9119,
      "step": 6
    },
    {
      "epoch": 0.0234375,
      "eval_loss": 2.3804562091827393,
      "eval_runtime": 4.6982,
      "eval_samples_per_second": 22.988,
      "eval_steps_per_second": 11.494,
      "step": 6
    },
    {
      "epoch": 0.02734375,
      "grad_norm": 0.8043889999389648,
      "learning_rate": 0.00014,
      "loss": 2.0573,
      "step": 7
    },
    {
      "epoch": 0.03125,
      "grad_norm": 0.6341584324836731,
      "learning_rate": 0.00016,
      "loss": 1.9364,
      "step": 8
    },
    {
      "epoch": 0.03515625,
      "grad_norm": 0.8237600922584534,
      "learning_rate": 0.00018,
      "loss": 2.6282,
      "step": 9
    },
    {
      "epoch": 0.03515625,
      "eval_loss": 2.232496976852417,
      "eval_runtime": 5.3978,
      "eval_samples_per_second": 20.008,
      "eval_steps_per_second": 10.004,
      "step": 9
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 0.6488352417945862,
      "learning_rate": 0.0002,
      "loss": 1.8504,
      "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": 1628749242040320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}