{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9975308641975309,
  "eval_steps": 6,
  "global_step": 101,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.9886,
      "step": 6
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.24954715371131897,
      "learning_rate": 0.001,
      "loss": 0.984,
      "step": 12
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.33483922481536865,
      "learning_rate": 0.0016329931618554523,
      "loss": 0.9071,
      "step": 18
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 1.0519644021987915,
      "learning_rate": 0.0012649110640673518,
      "loss": 3.3881,
      "step": 24
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 2.5967140197753906,
      "learning_rate": 0.0008944271909999159,
      "loss": 2.3416,
      "step": 30
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.6895209550857544,
      "learning_rate": 0.0007071067811865475,
      "loss": 0.7674,
      "step": 36
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 0.22938764095306396,
      "learning_rate": 0.0006030226891555273,
      "loss": 0.7034,
      "step": 42
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.21268492937088013,
      "learning_rate": 0.0005345224838248488,
      "loss": 0.6851,
      "step": 48
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.20341278612613678,
      "learning_rate": 0.0004850712500726659,
      "loss": 0.6684,
      "step": 54
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.2080058604478836,
      "learning_rate": 0.00044721359549995795,
      "loss": 0.6385,
      "step": 60
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 0.21044473350048065,
      "learning_rate": 0.0004170288281141495,
      "loss": 0.6324,
      "step": 66
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.20623333752155304,
      "learning_rate": 0.0003922322702763681,
      "loss": 0.6319,
      "step": 72
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 0.26323583722114563,
      "learning_rate": 0.0003713906763541037,
      "loss": 0.6401,
      "step": 78
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.17696638405323029,
      "learning_rate": 0.00035355339059327376,
      "loss": 0.6248,
      "step": 84
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.1904665231704712,
      "learning_rate": 0.0003380617018914066,
      "loss": 0.6202,
      "step": 90
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.21308590471744537,
      "learning_rate": 0.0003244428422615251,
      "loss": 0.6346,
      "step": 96
    },
    {
      "epoch": 0.9975308641975309,
      "step": 101,
      "total_flos": 1.0258028421510595e+18,
      "train_loss": 0.9721237692502466,
      "train_runtime": 907.9026,
      "train_samples_per_second": 14.272,
      "train_steps_per_second": 0.111
    }
  ],
  "logging_steps": 6,
  "max_steps": 101,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0258028421510595e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}