{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00074020340789649,
  "eval_steps": 4,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.96081363158596e-05,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 2.96081363158596e-05,
      "eval_loss": NaN,
      "eval_runtime": 187.4172,
      "eval_samples_per_second": 151.758,
      "eval_steps_per_second": 18.974,
      "step": 1
    },
    {
      "epoch": 5.92162726317192e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 8.882440894757879e-05,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0001184325452634384,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0001184325452634384,
      "eval_loss": NaN,
      "eval_runtime": 187.023,
      "eval_samples_per_second": 152.078,
      "eval_steps_per_second": 19.014,
      "step": 4
    },
    {
      "epoch": 0.000148040681579298,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00017764881789515758,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00020725695421101718,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0002368650905268768,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0002368650905268768,
      "eval_loss": NaN,
      "eval_runtime": 187.8465,
      "eval_samples_per_second": 151.411,
      "eval_steps_per_second": 18.93,
      "step": 8
    },
    {
      "epoch": 0.00026647322684273636,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.000296081363158596,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0003256894994744556,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.00035529763579031517,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00035529763579031517,
      "eval_loss": NaN,
      "eval_runtime": 187.7617,
      "eval_samples_per_second": 151.479,
      "eval_steps_per_second": 18.939,
      "step": 12
    },
    {
      "epoch": 0.0003849057721061748,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.00041451390842203435,
      "grad_norm": NaN,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.000444122044737894,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0004737301810537536,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0004737301810537536,
      "eval_loss": NaN,
      "eval_runtime": 187.8396,
      "eval_samples_per_second": 151.416,
      "eval_steps_per_second": 18.931,
      "step": 16
    },
    {
      "epoch": 0.0005033383173696132,
      "grad_norm": NaN,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0005329464536854727,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0005625545900013323,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.000592162726317192,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.000592162726317192,
      "eval_loss": NaN,
      "eval_runtime": 187.8379,
      "eval_samples_per_second": 151.418,
      "eval_steps_per_second": 18.931,
      "step": 20
    },
    {
      "epoch": 0.0006217708626330516,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0006513789989489112,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0006809871352647707,
      "grad_norm": NaN,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.0007105952715806303,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0007105952715806303,
      "eval_loss": NaN,
      "eval_runtime": 187.8379,
      "eval_samples_per_second": 151.418,
      "eval_steps_per_second": 18.931,
      "step": 24
    },
    {
      "epoch": 0.00074020340789649,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 108182215065600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}