{
  "best_global_step": null,
  "best_metric": 1.8485572338104248,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 24760,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 8.519086837768555,
      "learning_rate": 3.60080775444265e-05,
      "loss": 2.7844,
      "step": 2476
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.363213539123535,
      "eval_runtime": 30.9857,
      "eval_samples_per_second": 142.582,
      "eval_steps_per_second": 17.847,
      "step": 2476
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.55427360534668,
      "learning_rate": 3.2008077544426496e-05,
      "loss": 2.3842,
      "step": 4952
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.1710569858551025,
      "eval_runtime": 31.1916,
      "eval_samples_per_second": 141.641,
      "eval_steps_per_second": 17.729,
      "step": 4952
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.62738037109375,
      "learning_rate": 2.8012924071082395e-05,
      "loss": 2.2331,
      "step": 7428
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.086531162261963,
      "eval_runtime": 31.228,
      "eval_samples_per_second": 141.475,
      "eval_steps_per_second": 17.708,
      "step": 7428
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.015053749084473,
      "learning_rate": 2.4012924071082392e-05,
      "loss": 2.1379,
      "step": 9904
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.0061919689178467,
      "eval_runtime": 31.2124,
      "eval_samples_per_second": 141.546,
      "eval_steps_per_second": 17.717,
      "step": 9904
    },
    {
      "epoch": 5.0,
      "grad_norm": 7.610133647918701,
      "learning_rate": 2.001292407108239e-05,
      "loss": 2.0648,
      "step": 12380
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.9433549642562866,
      "eval_runtime": 29.5538,
      "eval_samples_per_second": 149.49,
      "eval_steps_per_second": 18.712,
      "step": 12380
    },
    {
      "epoch": 6.0,
      "grad_norm": 9.3466796875,
      "learning_rate": 1.6016155088852988e-05,
      "loss": 2.0067,
      "step": 14856
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.9069130420684814,
      "eval_runtime": 31.3798,
      "eval_samples_per_second": 140.791,
      "eval_steps_per_second": 17.623,
      "step": 14856
    },
    {
      "epoch": 7.0,
      "grad_norm": 8.526801109313965,
      "learning_rate": 1.201615508885299e-05,
      "loss": 1.9619,
      "step": 17332
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.8961998224258423,
      "eval_runtime": 31.5705,
      "eval_samples_per_second": 139.941,
      "eval_steps_per_second": 17.516,
      "step": 17332
    },
    {
      "epoch": 8.0,
      "grad_norm": 7.524344444274902,
      "learning_rate": 8.017770597738289e-06,
      "loss": 1.9311,
      "step": 19808
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.8643718957901,
      "eval_runtime": 31.7102,
      "eval_samples_per_second": 139.324,
      "eval_steps_per_second": 17.439,
      "step": 19808
    },
    {
      "epoch": 9.0,
      "grad_norm": 8.725274085998535,
      "learning_rate": 4.019386106623587e-06,
      "loss": 1.9096,
      "step": 22284
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.8564258813858032,
      "eval_runtime": 21.3743,
      "eval_samples_per_second": 206.697,
      "eval_steps_per_second": 25.872,
      "step": 22284
    },
    {
      "epoch": 10.0,
      "grad_norm": 7.118903636932373,
      "learning_rate": 2.2617124394184172e-08,
      "loss": 1.8867,
      "step": 24760
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.8485572338104248,
      "eval_runtime": 21.6819,
      "eval_samples_per_second": 203.765,
      "eval_steps_per_second": 25.505,
      "step": 24760
    },
    {
      "epoch": 10.0,
      "step": 24760,
      "total_flos": 2.606916709515264e+16,
      "train_loss": 2.1300495104566335,
      "train_runtime": 6282.2508,
      "train_samples_per_second": 63.081,
      "train_steps_per_second": 3.941
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.8408753871917725,
      "eval_runtime": 21.4119,
      "eval_samples_per_second": 206.334,
      "eval_steps_per_second": 25.827,
      "step": 24760
    }
  ],
  "logging_steps": 500,
  "max_steps": 24760,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.606916709515264e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}