{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008454872120059184,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001690974424011837,
      "eval_loss": 4.1862688064575195,
      "eval_runtime": 144.1843,
      "eval_samples_per_second": 17.27,
      "eval_steps_per_second": 8.635,
      "step": 1
    },
    {
      "epoch": 0.0008454872120059184,
      "grad_norm": 2.369690418243408,
      "learning_rate": 5e-05,
      "loss": 4.3649,
      "step": 5
    },
    {
      "epoch": 0.0016909744240118367,
      "grad_norm": 2.449605941772461,
      "learning_rate": 0.0001,
      "loss": 4.3793,
      "step": 10
    },
    {
      "epoch": 0.0016909744240118367,
      "eval_loss": 3.8276214599609375,
      "eval_runtime": 145.1821,
      "eval_samples_per_second": 17.151,
      "eval_steps_per_second": 8.575,
      "step": 10
    },
    {
      "epoch": 0.0025364616360177552,
      "grad_norm": 2.2190847396850586,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.5244,
      "step": 15
    },
    {
      "epoch": 0.0033819488480236735,
      "grad_norm": 3.936417818069458,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.9154,
      "step": 20
    },
    {
      "epoch": 0.0033819488480236735,
      "eval_loss": 2.8749823570251465,
      "eval_runtime": 144.6618,
      "eval_samples_per_second": 17.213,
      "eval_steps_per_second": 8.606,
      "step": 20
    },
    {
      "epoch": 0.004227436060029592,
      "grad_norm": 2.9968788623809814,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.5404,
      "step": 25
    },
    {
      "epoch": 0.0050729232720355105,
      "grad_norm": 2.714506149291992,
      "learning_rate": 5e-05,
      "loss": 2.6043,
      "step": 30
    },
    {
      "epoch": 0.0050729232720355105,
      "eval_loss": 2.4659817218780518,
      "eval_runtime": 144.9504,
      "eval_samples_per_second": 17.178,
      "eval_steps_per_second": 8.589,
      "step": 30
    },
    {
      "epoch": 0.005918410484041429,
      "grad_norm": 3.2256219387054443,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.3781,
      "step": 35
    },
    {
      "epoch": 0.006763897696047347,
      "grad_norm": 4.219568252563477,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.25,
      "step": 40
    },
    {
      "epoch": 0.006763897696047347,
      "eval_loss": 2.3745951652526855,
      "eval_runtime": 145.1633,
      "eval_samples_per_second": 17.153,
      "eval_steps_per_second": 8.577,
      "step": 40
    },
    {
      "epoch": 0.007609384908053266,
      "grad_norm": 3.5372140407562256,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.2417,
      "step": 45
    },
    {
      "epoch": 0.008454872120059184,
      "grad_norm": 2.92573881149292,
      "learning_rate": 0.0,
      "loss": 2.3297,
      "step": 50
    },
    {
      "epoch": 0.008454872120059184,
      "eval_loss": 2.361982583999634,
      "eval_runtime": 144.4754,
      "eval_samples_per_second": 17.235,
      "eval_steps_per_second": 8.617,
      "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": 8143746210201600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}