{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004613344097802895,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.613344097802895e-05,
      "grad_norm": 0.20551034808158875,
      "learning_rate": 2e-05,
      "loss": 1.4261,
      "step": 1
    },
    {
      "epoch": 9.22668819560579e-05,
      "grad_norm": 0.19003470242023468,
      "learning_rate": 4e-05,
      "loss": 1.3726,
      "step": 2
    },
    {
      "epoch": 0.00013840032293408684,
      "grad_norm": 0.17476262152194977,
      "learning_rate": 6e-05,
      "loss": 1.4715,
      "step": 3
    },
    {
      "epoch": 0.00013840032293408684,
      "eval_loss": 1.390396237373352,
      "eval_runtime": 377.0815,
      "eval_samples_per_second": 24.204,
      "eval_steps_per_second": 12.103,
      "step": 3
    },
    {
      "epoch": 0.0001845337639121158,
      "grad_norm": 0.180754616856575,
      "learning_rate": 8e-05,
      "loss": 1.3052,
      "step": 4
    },
    {
      "epoch": 0.00023066720489014475,
      "grad_norm": 0.19912365078926086,
      "learning_rate": 0.0001,
      "loss": 1.184,
      "step": 5
    },
    {
      "epoch": 0.0002768006458681737,
      "grad_norm": 0.1971464902162552,
      "learning_rate": 0.00012,
      "loss": 1.4939,
      "step": 6
    },
    {
      "epoch": 0.0002768006458681737,
      "eval_loss": 1.3867459297180176,
      "eval_runtime": 387.0451,
      "eval_samples_per_second": 23.581,
      "eval_steps_per_second": 11.792,
      "step": 6
    },
    {
      "epoch": 0.00032293408684620263,
      "grad_norm": 0.15864993631839752,
      "learning_rate": 0.00014,
      "loss": 1.294,
      "step": 7
    },
    {
      "epoch": 0.0003690675278242316,
      "grad_norm": 0.2074289172887802,
      "learning_rate": 0.00016,
      "loss": 1.4761,
      "step": 8
    },
    {
      "epoch": 0.00041520096880226054,
      "grad_norm": 0.20530371367931366,
      "learning_rate": 0.00018,
      "loss": 1.4234,
      "step": 9
    },
    {
      "epoch": 0.00041520096880226054,
      "eval_loss": 1.3728744983673096,
      "eval_runtime": 385.1713,
      "eval_samples_per_second": 23.696,
      "eval_steps_per_second": 11.849,
      "step": 9
    },
    {
      "epoch": 0.0004613344097802895,
      "grad_norm": 0.19796575605869293,
      "learning_rate": 0.0002,
      "loss": 1.434,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 31373400342528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}