{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6879999999999997,
  "eval_steps": 30,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.128,
      "grad_norm": 1.7691179513931274,
      "learning_rate": 2.857142857142857e-05,
      "loss": 10.1767,
      "step": 1
    },
    {
      "epoch": 0.256,
      "grad_norm": 1.533618450164795,
      "learning_rate": 2.7142857142857144e-05,
      "loss": 10.1053,
      "step": 2
    },
    {
      "epoch": 0.384,
      "grad_norm": 1.8578174114227295,
      "learning_rate": 2.5714285714285714e-05,
      "loss": 10.1344,
      "step": 3
    },
    {
      "epoch": 0.512,
      "grad_norm": 1.893380880355835,
      "learning_rate": 2.4285714285714288e-05,
      "loss": 10.0509,
      "step": 4
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.9985988140106201,
      "learning_rate": 2.2857142857142858e-05,
      "loss": 9.9777,
      "step": 5
    },
    {
      "epoch": 0.768,
      "grad_norm": 2.318725109100342,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 10.0346,
      "step": 6
    },
    {
      "epoch": 0.896,
      "grad_norm": 2.3330538272857666,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 10.0432,
      "step": 7
    },
    {
      "epoch": 1.024,
      "grad_norm": 2.386380672454834,
      "learning_rate": 1.8571428571428572e-05,
      "loss": 9.9037,
      "step": 8
    },
    {
      "epoch": 1.152,
      "grad_norm": 2.525782346725464,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 9.8192,
      "step": 9
    },
    {
      "epoch": 1.28,
      "grad_norm": 2.6987812519073486,
      "learning_rate": 1.5714285714285715e-05,
      "loss": 9.7915,
      "step": 10
    },
    {
      "epoch": 1.408,
      "grad_norm": 2.681642532348633,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 9.6911,
      "step": 11
    },
    {
      "epoch": 1.536,
      "grad_norm": 2.9579291343688965,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 9.6579,
      "step": 12
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 3.073641300201416,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 9.6782,
      "step": 13
    },
    {
      "epoch": 1.792,
      "grad_norm": 3.179450035095215,
      "learning_rate": 9.999999999999999e-06,
      "loss": 9.5699,
      "step": 14
    },
    {
      "epoch": 1.92,
      "grad_norm": 3.1641924381256104,
      "learning_rate": 8.571428571428571e-06,
      "loss": 9.5342,
      "step": 15
    },
    {
      "epoch": 2.048,
      "grad_norm": 3.2276086807250977,
      "learning_rate": 7.142857142857143e-06,
      "loss": 9.5571,
      "step": 16
    },
    {
      "epoch": 2.176,
      "grad_norm": 3.0624403953552246,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 9.4244,
      "step": 17
    },
    {
      "epoch": 2.304,
      "grad_norm": 3.3281595706939697,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 9.4145,
      "step": 18
    },
    {
      "epoch": 2.432,
      "grad_norm": 3.577859878540039,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 9.499,
      "step": 19
    },
    {
      "epoch": 2.56,
      "grad_norm": 3.7756576538085938,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 9.4644,
      "step": 20
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 3.3084795475006104,
      "learning_rate": 0.0,
      "loss": 9.348,
      "step": 21
    },
    {
      "epoch": 2.6879999999999997,
      "step": 21,
      "total_flos": 247581948423984.0,
      "train_loss": 9.755998475211006,
      "train_runtime": 4057.189,
      "train_samples_per_second": 0.092,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 21,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 247581948423984.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}