{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013021237017516665,
  "eval_steps": 3,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006200589055960316,
      "grad_norm": 0.16878783702850342,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.9729,
      "step": 1
    },
    {
      "epoch": 0.0012401178111920632,
      "grad_norm": 0.0865061804652214,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6661,
      "step": 2
    },
    {
      "epoch": 0.0018601767167880949,
      "grad_norm": 0.0920981764793396,
      "learning_rate": 1.2e-05,
      "loss": 0.5954,
      "step": 3
    },
    {
      "epoch": 0.0018601767167880949,
      "eval_loss": 0.762992262840271,
      "eval_runtime": 33.3972,
      "eval_samples_per_second": 2.994,
      "eval_steps_per_second": 2.994,
      "step": 3
    },
    {
      "epoch": 0.0024802356223841263,
      "grad_norm": 0.10451442003250122,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7227,
      "step": 4
    },
    {
      "epoch": 0.0031002945279801583,
      "grad_norm": 0.11351602524518967,
      "learning_rate": 2e-05,
      "loss": 0.5719,
      "step": 5
    },
    {
      "epoch": 0.0037203534335761897,
      "grad_norm": 0.12484906613826752,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.6972,
      "step": 6
    },
    {
      "epoch": 0.0037203534335761897,
      "eval_loss": 0.7615777850151062,
      "eval_runtime": 33.3804,
      "eval_samples_per_second": 2.996,
      "eval_steps_per_second": 2.996,
      "step": 6
    },
    {
      "epoch": 0.004340412339172222,
      "grad_norm": 0.11116621643304825,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 0.6789,
      "step": 7
    },
    {
      "epoch": 0.004960471244768253,
      "grad_norm": 0.16013608872890472,
      "learning_rate": 1.76e-05,
      "loss": 0.6612,
      "step": 8
    },
    {
      "epoch": 0.005580530150364285,
      "grad_norm": 0.1211152970790863,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 0.5557,
      "step": 9
    },
    {
      "epoch": 0.005580530150364285,
      "eval_loss": 0.7586225867271423,
      "eval_runtime": 33.7015,
      "eval_samples_per_second": 2.967,
      "eval_steps_per_second": 2.967,
      "step": 9
    },
    {
      "epoch": 0.0062005890559603165,
      "grad_norm": 0.1299518495798111,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.8339,
      "step": 10
    },
    {
      "epoch": 0.0068206479615563476,
      "grad_norm": 0.11476285755634308,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 0.5786,
      "step": 11
    },
    {
      "epoch": 0.0074407068671523795,
      "grad_norm": 0.18253028392791748,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.8889,
      "step": 12
    },
    {
      "epoch": 0.0074407068671523795,
      "eval_loss": 0.7548640966415405,
      "eval_runtime": 34.763,
      "eval_samples_per_second": 2.877,
      "eval_steps_per_second": 2.877,
      "step": 12
    },
    {
      "epoch": 0.008060765772748411,
      "grad_norm": 0.14364618062973022,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 0.7251,
      "step": 13
    },
    {
      "epoch": 0.008680824678344443,
      "grad_norm": 0.11001864820718765,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.6209,
      "step": 14
    },
    {
      "epoch": 0.009300883583940475,
      "grad_norm": 0.1239691898226738,
      "learning_rate": 1.2e-05,
      "loss": 0.6641,
      "step": 15
    },
    {
      "epoch": 0.009300883583940475,
      "eval_loss": 0.7505818009376526,
      "eval_runtime": 34.0273,
      "eval_samples_per_second": 2.939,
      "eval_steps_per_second": 2.939,
      "step": 15
    },
    {
      "epoch": 0.009920942489536505,
      "grad_norm": 0.11025531589984894,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.4851,
      "step": 16
    },
    {
      "epoch": 0.010541001395132537,
      "grad_norm": 0.10391498357057571,
      "learning_rate": 1.04e-05,
      "loss": 0.6274,
      "step": 17
    },
    {
      "epoch": 0.01116106030072857,
      "grad_norm": 0.13879302144050598,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.5931,
      "step": 18
    },
    {
      "epoch": 0.01116106030072857,
      "eval_loss": 0.7464621067047119,
      "eval_runtime": 34.3301,
      "eval_samples_per_second": 2.913,
      "eval_steps_per_second": 2.913,
      "step": 18
    },
    {
      "epoch": 0.011781119206324601,
      "grad_norm": 0.14016444981098175,
      "learning_rate": 8.8e-06,
      "loss": 0.6289,
      "step": 19
    },
    {
      "epoch": 0.012401178111920633,
      "grad_norm": 0.11601278930902481,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.4875,
      "step": 20
    },
    {
      "epoch": 0.013021237017516665,
      "grad_norm": 0.13207638263702393,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.6942,
      "step": 21
    },
    {
      "epoch": 0.013021237017516665,
      "eval_loss": 0.7427210807800293,
      "eval_runtime": 34.6202,
      "eval_samples_per_second": 2.888,
      "eval_steps_per_second": 2.888,
      "step": 21
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.866352126799053e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}