{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 199.7591328783621,
  "eval_steps": 6220,
  "global_step": 62200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 19.97591328783621,
      "grad_norm": 1.61403489112854,
      "learning_rate": 9.001607717041802e-06,
      "loss": 2.152,
      "step": 6220
    },
    {
      "epoch": 19.97591328783621,
      "eval_accuracy": 0.05365616255018859,
      "eval_loss": 3.0211591720581055,
      "eval_runtime": 37.9229,
      "eval_samples_per_second": 216.729,
      "eval_steps_per_second": 10.838,
      "step": 6220
    },
    {
      "epoch": 39.95182657567242,
      "grad_norm": 4.300863742828369,
      "learning_rate": 8.001607717041802e-06,
      "loss": 1.9424,
      "step": 12440
    },
    {
      "epoch": 39.95182657567242,
      "eval_accuracy": 0.056272052561138826,
      "eval_loss": 3.44952392578125,
      "eval_runtime": 37.2746,
      "eval_samples_per_second": 220.499,
      "eval_steps_per_second": 11.026,
      "step": 12440
    },
    {
      "epoch": 59.927739863508634,
      "grad_norm": 4.123779773712158,
      "learning_rate": 7.0017684887459816e-06,
      "loss": 1.7646,
      "step": 18660
    },
    {
      "epoch": 59.927739863508634,
      "eval_accuracy": 0.05613010504116478,
      "eval_loss": 3.9469401836395264,
      "eval_runtime": 37.2696,
      "eval_samples_per_second": 220.528,
      "eval_steps_per_second": 11.028,
      "step": 18660
    },
    {
      "epoch": 79.90365315134484,
      "grad_norm": 3.3579535484313965,
      "learning_rate": 6.002250803858522e-06,
      "loss": 1.6901,
      "step": 24880
    },
    {
      "epoch": 79.90365315134484,
      "eval_accuracy": 0.05502494220708115,
      "eval_loss": 4.235374450683594,
      "eval_runtime": 37.4434,
      "eval_samples_per_second": 219.505,
      "eval_steps_per_second": 10.977,
      "step": 24880
    },
    {
      "epoch": 99.87956643918105,
      "grad_norm": 3.154458999633789,
      "learning_rate": 5.002572347266882e-06,
      "loss": 1.6562,
      "step": 31100
    },
    {
      "epoch": 99.87956643918105,
      "eval_accuracy": 0.054848521717970555,
      "eval_loss": 4.673249244689941,
      "eval_runtime": 37.3153,
      "eval_samples_per_second": 220.258,
      "eval_steps_per_second": 11.014,
      "step": 31100
    },
    {
      "epoch": 119.85547972701727,
      "grad_norm": 3.416239023208618,
      "learning_rate": 4.0030546623794215e-06,
      "loss": 1.6398,
      "step": 37320
    },
    {
      "epoch": 119.85547972701727,
      "eval_accuracy": 0.05495396844709413,
      "eval_loss": 4.8611836433410645,
      "eval_runtime": 37.4062,
      "eval_samples_per_second": 219.723,
      "eval_steps_per_second": 10.987,
      "step": 37320
    },
    {
      "epoch": 139.83139301485346,
      "grad_norm": 1.5928527116775513,
      "learning_rate": 3.0035369774919613e-06,
      "loss": 1.6289,
      "step": 43540
    },
    {
      "epoch": 139.83139301485346,
      "eval_accuracy": 0.054959762223419605,
      "eval_loss": 4.878427982330322,
      "eval_runtime": 37.3881,
      "eval_samples_per_second": 219.829,
      "eval_steps_per_second": 10.993,
      "step": 43540
    },
    {
      "epoch": 159.80730630268968,
      "grad_norm": 0.8597731590270996,
      "learning_rate": 2.0038585209003218e-06,
      "loss": 1.6192,
      "step": 49760
    },
    {
      "epoch": 159.80730630268968,
      "eval_accuracy": 0.05538995011558584,
      "eval_loss": 5.251640796661377,
      "eval_runtime": 37.3375,
      "eval_samples_per_second": 220.127,
      "eval_steps_per_second": 11.008,
      "step": 49760
    },
    {
      "epoch": 179.7832195905259,
      "grad_norm": 1.7104542255401611,
      "learning_rate": 1.0041800643086816e-06,
      "loss": 1.6163,
      "step": 55980
    },
    {
      "epoch": 179.7832195905259,
      "eval_accuracy": 0.055778615944086195,
      "eval_loss": 5.283741474151611,
      "eval_runtime": 37.3303,
      "eval_samples_per_second": 220.169,
      "eval_steps_per_second": 11.01,
      "step": 55980
    },
    {
      "epoch": 199.7591328783621,
      "grad_norm": 1.8880465030670166,
      "learning_rate": 4.662379421221865e-09,
      "loss": 1.6165,
      "step": 62200
    },
    {
      "epoch": 199.7591328783621,
      "eval_accuracy": 0.055821876140649714,
      "eval_loss": 5.313088893890381,
      "eval_runtime": 37.4402,
      "eval_samples_per_second": 219.524,
      "eval_steps_per_second": 10.978,
      "step": 62200
    },
    {
      "epoch": 199.7591328783621,
      "step": 62200,
      "total_flos": 2.9422944418267996e+18,
      "train_loss": 1.7326023820588827,
      "train_runtime": 120684.8558,
      "train_samples_per_second": 103.17,
      "train_steps_per_second": 0.515
    }
  ],
  "logging_steps": 6220,
  "max_steps": 62200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 200,
  "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": 2.9422944418267996e+18,
  "train_batch_size": 25,
  "trial_name": null,
  "trial_params": null
}