{
  "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": 3.0524420738220215,
      "eval_runtime": 984.158,
      "eval_samples_per_second": 6.581,
      "eval_steps_per_second": 3.291,
      "step": 1
    },
    {
      "epoch": 0.00032508167677128876,
      "grad_norm": 1.2409887313842773,
      "learning_rate": 5e-05,
      "loss": 3.0219,
      "step": 5
    },
    {
      "epoch": 0.0006501633535425775,
      "grad_norm": 1.2553097009658813,
      "learning_rate": 0.0001,
      "loss": 3.0028,
      "step": 10
    },
    {
      "epoch": 0.0006501633535425775,
      "eval_loss": 2.840944290161133,
      "eval_runtime": 1001.2393,
      "eval_samples_per_second": 6.469,
      "eval_steps_per_second": 3.235,
      "step": 10
    },
    {
      "epoch": 0.0009752450303138663,
      "grad_norm": 1.2685163021087646,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.7042,
      "step": 15
    },
    {
      "epoch": 0.001300326707085155,
      "grad_norm": 2.3047077655792236,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.4863,
      "step": 20
    },
    {
      "epoch": 0.001300326707085155,
      "eval_loss": 2.3000075817108154,
      "eval_runtime": 1000.5051,
      "eval_samples_per_second": 6.474,
      "eval_steps_per_second": 3.237,
      "step": 20
    },
    {
      "epoch": 0.0016254083838564439,
      "grad_norm": 1.6231160163879395,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.354,
      "step": 25
    },
    {
      "epoch": 0.0019504900606277327,
      "grad_norm": 1.5642887353897095,
      "learning_rate": 5e-05,
      "loss": 2.1653,
      "step": 30
    },
    {
      "epoch": 0.0019504900606277327,
      "eval_loss": 2.2030398845672607,
      "eval_runtime": 1000.1014,
      "eval_samples_per_second": 6.476,
      "eval_steps_per_second": 3.239,
      "step": 30
    },
    {
      "epoch": 0.0022755717373990213,
      "grad_norm": 1.5200837850570679,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.1988,
      "step": 35
    },
    {
      "epoch": 0.00260065341417031,
      "grad_norm": 1.474457025527954,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.0655,
      "step": 40
    },
    {
      "epoch": 0.00260065341417031,
      "eval_loss": 2.1556448936462402,
      "eval_runtime": 999.6273,
      "eval_samples_per_second": 6.479,
      "eval_steps_per_second": 3.24,
      "step": 40
    },
    {
      "epoch": 0.002925735090941599,
      "grad_norm": 1.442267894744873,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.0189,
      "step": 45
    },
    {
      "epoch": 0.0032508167677128877,
      "grad_norm": 1.5506565570831299,
      "learning_rate": 0.0,
      "loss": 2.2706,
      "step": 50
    },
    {
      "epoch": 0.0032508167677128877,
      "eval_loss": 2.1504440307617188,
      "eval_runtime": 1001.5404,
      "eval_samples_per_second": 6.467,
      "eval_steps_per_second": 3.234,
      "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": 1.6144088520720384e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}