{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032508167677128877,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.501633535425775e-05,
      "eval_loss": 2.9677481651306152,
      "eval_runtime": 448.1623,
      "eval_samples_per_second": 14.452,
      "eval_steps_per_second": 7.227,
      "step": 1
    },
    {
      "epoch": 0.00032508167677128876,
      "grad_norm": 2.2500431537628174,
      "learning_rate": 5e-05,
      "loss": 2.8747,
      "step": 5
    },
    {
      "epoch": 0.0006501633535425775,
      "grad_norm": 2.0692389011383057,
      "learning_rate": 0.0001,
      "loss": 2.8693,
      "step": 10
    },
    {
      "epoch": 0.0006501633535425775,
      "eval_loss": 2.6468188762664795,
      "eval_runtime": 450.692,
      "eval_samples_per_second": 14.371,
      "eval_steps_per_second": 7.187,
      "step": 10
    },
    {
      "epoch": 0.0009752450303138663,
      "grad_norm": 1.897547721862793,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.4755,
      "step": 15
    },
    {
      "epoch": 0.001300326707085155,
      "grad_norm": 2.1114673614501953,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.2338,
      "step": 20
    },
    {
      "epoch": 0.001300326707085155,
      "eval_loss": 2.098156690597534,
      "eval_runtime": 451.0667,
      "eval_samples_per_second": 14.359,
      "eval_steps_per_second": 7.181,
      "step": 20
    },
    {
      "epoch": 0.0016254083838564439,
      "grad_norm": 1.9440230131149292,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.1319,
      "step": 25
    },
    {
      "epoch": 0.0019504900606277327,
      "grad_norm": 2.016071081161499,
      "learning_rate": 5e-05,
      "loss": 1.9876,
      "step": 30
    },
    {
      "epoch": 0.0019504900606277327,
      "eval_loss": 2.0283923149108887,
      "eval_runtime": 451.3853,
      "eval_samples_per_second": 14.349,
      "eval_steps_per_second": 7.176,
      "step": 30
    },
    {
      "epoch": 0.0022755717373990213,
      "grad_norm": 1.917054533958435,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.0465,
      "step": 35
    },
    {
      "epoch": 0.00260065341417031,
      "grad_norm": 1.910294532775879,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.894,
      "step": 40
    },
    {
      "epoch": 0.00260065341417031,
      "eval_loss": 1.9974616765975952,
      "eval_runtime": 452.9359,
      "eval_samples_per_second": 14.3,
      "eval_steps_per_second": 7.151,
      "step": 40
    },
    {
      "epoch": 0.002925735090941599,
      "grad_norm": 1.7574785947799683,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.8849,
      "step": 45
    },
    {
      "epoch": 0.0032508167677128877,
      "grad_norm": 1.7009735107421875,
      "learning_rate": 0.0,
      "loss": 2.1017,
      "step": 50
    },
    {
      "epoch": 0.0032508167677128877,
      "eval_loss": 1.99276602268219,
      "eval_runtime": 450.8135,
      "eval_samples_per_second": 14.367,
      "eval_steps_per_second": 7.185,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9340299453136896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}