{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.991460112476567,
  "eval_steps": 500,
  "global_step": 13200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 71.72611999511719,
      "learning_rate": 4.545454545454546e-05,
      "loss": 146.616,
      "step": 1201
    },
    {
      "epoch": 1.0,
      "eval_loss": 21.393348693847656,
      "eval_runtime": 150.0562,
      "eval_samples_per_second": 42.657,
      "eval_steps_per_second": 5.338,
      "step": 1201
    },
    {
      "epoch": 2.0,
      "grad_norm": 64.23561096191406,
      "learning_rate": 4.0905303030303035e-05,
      "loss": 61.2117,
      "step": 2402
    },
    {
      "epoch": 2.0,
      "eval_loss": 15.90537166595459,
      "eval_runtime": 150.5381,
      "eval_samples_per_second": 42.521,
      "eval_steps_per_second": 5.321,
      "step": 2402
    },
    {
      "epoch": 3.0,
      "grad_norm": 71.59235382080078,
      "learning_rate": 3.635606060606061e-05,
      "loss": 34.1493,
      "step": 3603
    },
    {
      "epoch": 3.0,
      "eval_loss": 14.073749542236328,
      "eval_runtime": 150.2674,
      "eval_samples_per_second": 42.597,
      "eval_steps_per_second": 5.33,
      "step": 3603
    },
    {
      "epoch": 4.0,
      "grad_norm": 63.900787353515625,
      "learning_rate": 3.180681818181818e-05,
      "loss": 17.8552,
      "step": 4804
    },
    {
      "epoch": 4.0,
      "eval_loss": 13.909745216369629,
      "eval_runtime": 150.2467,
      "eval_samples_per_second": 42.603,
      "eval_steps_per_second": 5.331,
      "step": 4804
    },
    {
      "epoch": 5.0,
      "grad_norm": 49.56394958496094,
      "learning_rate": 2.725757575757576e-05,
      "loss": 10.0752,
      "step": 6005
    },
    {
      "epoch": 5.0,
      "eval_loss": 14.089239120483398,
      "eval_runtime": 149.8889,
      "eval_samples_per_second": 42.705,
      "eval_steps_per_second": 5.344,
      "step": 6005
    },
    {
      "epoch": 6.0,
      "grad_norm": 35.2913703918457,
      "learning_rate": 2.2708333333333334e-05,
      "loss": 7.2341,
      "step": 7206
    },
    {
      "epoch": 6.0,
      "eval_loss": 14.01687240600586,
      "eval_runtime": 149.9631,
      "eval_samples_per_second": 42.684,
      "eval_steps_per_second": 5.341,
      "step": 7206
    },
    {
      "epoch": 7.0,
      "grad_norm": 48.220890045166016,
      "learning_rate": 1.8159090909090907e-05,
      "loss": 5.7299,
      "step": 8407
    },
    {
      "epoch": 7.0,
      "eval_loss": 13.829411506652832,
      "eval_runtime": 149.9321,
      "eval_samples_per_second": 42.693,
      "eval_steps_per_second": 5.342,
      "step": 8407
    },
    {
      "epoch": 8.0,
      "grad_norm": 22.624107360839844,
      "learning_rate": 1.3609848484848487e-05,
      "loss": 4.6004,
      "step": 9608
    },
    {
      "epoch": 8.0,
      "eval_loss": 13.629751205444336,
      "eval_runtime": 150.1179,
      "eval_samples_per_second": 42.64,
      "eval_steps_per_second": 5.336,
      "step": 9608
    },
    {
      "epoch": 9.0,
      "grad_norm": 18.675453186035156,
      "learning_rate": 9.060606060606062e-06,
      "loss": 3.6897,
      "step": 10809
    },
    {
      "epoch": 9.0,
      "eval_loss": 13.462262153625488,
      "eval_runtime": 150.0276,
      "eval_samples_per_second": 42.665,
      "eval_steps_per_second": 5.339,
      "step": 10809
    },
    {
      "epoch": 10.0,
      "grad_norm": 15.451993942260742,
      "learning_rate": 4.511363636363637e-06,
      "loss": 2.8693,
      "step": 12010
    },
    {
      "epoch": 10.0,
      "eval_loss": 13.392560958862305,
      "eval_runtime": 150.4044,
      "eval_samples_per_second": 42.559,
      "eval_steps_per_second": 5.326,
      "step": 12010
    }
  ],
  "logging_steps": 500,
  "max_steps": 13200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 11,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.01088135299072e+17,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}