{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001295840352468576,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.591680704937152e-05,
      "eval_loss": 11.910928726196289,
      "eval_runtime": 201.7525,
      "eval_samples_per_second": 80.529,
      "eval_steps_per_second": 40.267,
      "step": 1
    },
    {
      "epoch": 0.0001295840352468576,
      "grad_norm": 5.612617492675781,
      "learning_rate": 5e-05,
      "loss": 11.9112,
      "step": 5
    },
    {
      "epoch": 0.0002591680704937152,
      "grad_norm": 5.775433540344238,
      "learning_rate": 0.0001,
      "loss": 11.8222,
      "step": 10
    },
    {
      "epoch": 0.0002591680704937152,
      "eval_loss": 11.683552742004395,
      "eval_runtime": 201.5314,
      "eval_samples_per_second": 80.618,
      "eval_steps_per_second": 40.311,
      "step": 10
    },
    {
      "epoch": 0.0003887521057405728,
      "grad_norm": 5.224070072174072,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.571,
      "step": 15
    },
    {
      "epoch": 0.0005183361409874304,
      "grad_norm": 5.187327861785889,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.3059,
      "step": 20
    },
    {
      "epoch": 0.0005183361409874304,
      "eval_loss": 11.109954833984375,
      "eval_runtime": 202.249,
      "eval_samples_per_second": 80.332,
      "eval_steps_per_second": 40.168,
      "step": 20
    },
    {
      "epoch": 0.000647920176234288,
      "grad_norm": 5.364950656890869,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.008,
      "step": 25
    },
    {
      "epoch": 0.0007775042114811456,
      "grad_norm": 4.986256122589111,
      "learning_rate": 5e-05,
      "loss": 10.8036,
      "step": 30
    },
    {
      "epoch": 0.0007775042114811456,
      "eval_loss": 10.687889099121094,
      "eval_runtime": 202.1656,
      "eval_samples_per_second": 80.365,
      "eval_steps_per_second": 40.185,
      "step": 30
    },
    {
      "epoch": 0.0009070882467280031,
      "grad_norm": 4.7963056564331055,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.6133,
      "step": 35
    },
    {
      "epoch": 0.0010366722819748608,
      "grad_norm": 4.745049953460693,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.543,
      "step": 40
    },
    {
      "epoch": 0.0010366722819748608,
      "eval_loss": 10.496466636657715,
      "eval_runtime": 199.5182,
      "eval_samples_per_second": 81.431,
      "eval_steps_per_second": 40.718,
      "step": 40
    },
    {
      "epoch": 0.0011662563172217184,
      "grad_norm": 4.337930202484131,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.4968,
      "step": 45
    },
    {
      "epoch": 0.001295840352468576,
      "grad_norm": 4.661583423614502,
      "learning_rate": 0.0,
      "loss": 10.4447,
      "step": 50
    },
    {
      "epoch": 0.001295840352468576,
      "eval_loss": 10.457128524780273,
      "eval_runtime": 207.9854,
      "eval_samples_per_second": 78.116,
      "eval_steps_per_second": 39.06,
      "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": 3359875399680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}