{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 9630,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19602945720465548,
      "eval_loss": 5.100234508514404,
      "eval_runtime": 4.3151,
      "eval_samples_per_second": 52.838,
      "eval_steps_per_second": 1.854,
      "step": 963
    },
    {
      "epoch": 1.0384215991692627,
      "grad_norm": 11248.8583984375,
      "learning_rate": 0.0005993999999999999,
      "loss": 1.3298,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.20184021698080817,
      "eval_loss": 4.873116493225098,
      "eval_runtime": 3.8079,
      "eval_samples_per_second": 59.876,
      "eval_steps_per_second": 2.101,
      "step": 1926
    },
    {
      "epoch": 2.0768431983385254,
      "grad_norm": 8729.2783203125,
      "learning_rate": 0.0005305446118192352,
      "loss": 1.1662,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2268942905208226,
      "eval_loss": 4.608329772949219,
      "eval_runtime": 3.813,
      "eval_samples_per_second": 59.796,
      "eval_steps_per_second": 2.098,
      "step": 2889
    },
    {
      "epoch": 3.115264797507788,
      "grad_norm": 10174.3515625,
      "learning_rate": 0.00046101969872537656,
      "loss": 1.1073,
      "step": 3000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.25517561025852303,
      "eval_loss": 4.374086380004883,
      "eval_runtime": 3.8036,
      "eval_samples_per_second": 59.942,
      "eval_steps_per_second": 2.103,
      "step": 3852
    },
    {
      "epoch": 4.153686396677051,
      "grad_norm": 10389.4033203125,
      "learning_rate": 0.00039149478563151795,
      "loss": 1.0428,
      "step": 4000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.27495107632093935,
      "eval_loss": 4.223287582397461,
      "eval_runtime": 3.8281,
      "eval_samples_per_second": 59.56,
      "eval_steps_per_second": 2.09,
      "step": 4815
    },
    {
      "epoch": 5.192107995846314,
      "grad_norm": 10395.3505859375,
      "learning_rate": 0.0003219698725376593,
      "loss": 0.9948,
      "step": 5000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.2876969821814811,
      "eval_loss": 4.120807647705078,
      "eval_runtime": 3.8204,
      "eval_samples_per_second": 59.68,
      "eval_steps_per_second": 2.094,
      "step": 5778
    },
    {
      "epoch": 6.230529595015576,
      "grad_norm": 11000.0849609375,
      "learning_rate": 0.00025244495944380066,
      "loss": 0.9598,
      "step": 6000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3017561025852302,
      "eval_loss": 4.021105766296387,
      "eval_runtime": 3.7916,
      "eval_samples_per_second": 60.134,
      "eval_steps_per_second": 2.11,
      "step": 6741
    },
    {
      "epoch": 7.268951194184839,
      "grad_norm": 11252.4794921875,
      "learning_rate": 0.00018292004634994205,
      "loss": 0.9315,
      "step": 7000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.3098585504858036,
      "eval_loss": 3.959293842315674,
      "eval_runtime": 3.8014,
      "eval_samples_per_second": 59.978,
      "eval_steps_per_second": 2.104,
      "step": 7704
    },
    {
      "epoch": 8.307372793354102,
      "grad_norm": 11713.1103515625,
      "learning_rate": 0.00011339513325608342,
      "loss": 0.9071,
      "step": 8000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.3187592268342088,
      "eval_loss": 3.912856340408325,
      "eval_runtime": 3.798,
      "eval_samples_per_second": 60.032,
      "eval_steps_per_second": 2.106,
      "step": 8667
    },
    {
      "epoch": 9.345794392523365,
      "grad_norm": 12162.0947265625,
      "learning_rate": 4.3870220162224794e-05,
      "loss": 0.8866,
      "step": 9000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.32276753527654756,
      "eval_loss": 3.8868300914764404,
      "eval_runtime": 3.8036,
      "eval_samples_per_second": 59.943,
      "eval_steps_per_second": 2.103,
      "step": 9630
    },
    {
      "epoch": 10.0,
      "step": 9630,
      "total_flos": 8.04910104576e+16,
      "train_loss": 1.0257348366615557,
      "train_runtime": 8691.946,
      "train_samples_per_second": 35.441,
      "train_steps_per_second": 1.108
    }
  ],
  "logging_steps": 1000,
  "max_steps": 9630,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.04910104576e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}