{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03827751196172249,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 0.39523524045944214,
      "learning_rate": 2e-05,
      "loss": 1.6478,
      "step": 1
    },
    {
      "epoch": 0.003827751196172249,
      "eval_loss": 1.7360095977783203,
      "eval_runtime": 10.9253,
      "eval_samples_per_second": 10.068,
      "eval_steps_per_second": 5.034,
      "step": 1
    },
    {
      "epoch": 0.007655502392344498,
      "grad_norm": 0.37636616826057434,
      "learning_rate": 4e-05,
      "loss": 1.5945,
      "step": 2
    },
    {
      "epoch": 0.011483253588516746,
      "grad_norm": 0.37544843554496765,
      "learning_rate": 6e-05,
      "loss": 1.6232,
      "step": 3
    },
    {
      "epoch": 0.011483253588516746,
      "eval_loss": 1.7347116470336914,
      "eval_runtime": 10.3154,
      "eval_samples_per_second": 10.664,
      "eval_steps_per_second": 5.332,
      "step": 3
    },
    {
      "epoch": 0.015311004784688996,
      "grad_norm": 0.4099840223789215,
      "learning_rate": 8e-05,
      "loss": 1.7914,
      "step": 4
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 0.3720112144947052,
      "learning_rate": 0.0001,
      "loss": 1.4931,
      "step": 5
    },
    {
      "epoch": 0.022966507177033493,
      "grad_norm": 0.414368599653244,
      "learning_rate": 0.00012,
      "loss": 1.5382,
      "step": 6
    },
    {
      "epoch": 0.022966507177033493,
      "eval_loss": 1.720920443534851,
      "eval_runtime": 10.3421,
      "eval_samples_per_second": 10.636,
      "eval_steps_per_second": 5.318,
      "step": 6
    },
    {
      "epoch": 0.026794258373205742,
      "grad_norm": 0.5400865077972412,
      "learning_rate": 0.00014,
      "loss": 1.7169,
      "step": 7
    },
    {
      "epoch": 0.03062200956937799,
      "grad_norm": 0.5020793080329895,
      "learning_rate": 0.00016,
      "loss": 1.6388,
      "step": 8
    },
    {
      "epoch": 0.03444976076555024,
      "grad_norm": 0.5490452647209167,
      "learning_rate": 0.00018,
      "loss": 1.5667,
      "step": 9
    },
    {
      "epoch": 0.03444976076555024,
      "eval_loss": 1.6421552896499634,
      "eval_runtime": 10.324,
      "eval_samples_per_second": 10.655,
      "eval_steps_per_second": 5.327,
      "step": 9
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 0.523384153842926,
      "learning_rate": 0.0002,
      "loss": 1.3138,
      "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": 6332410861977600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}