{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8528916339135317,
  "eval_steps": 15000,
  "global_step": 165000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16844469399213924,
      "grad_norm": 21.554645538330078,
      "learning_rate": 2.524649073554183e-05,
      "loss": 2.3707,
      "step": 15000
    },
    {
      "epoch": 0.16844469399213924,
      "eval_loss": 1.823581576347351,
      "eval_runtime": 1119.2561,
      "eval_samples_per_second": 159.124,
      "eval_steps_per_second": 1.244,
      "step": 15000
    },
    {
      "epoch": 0.3368893879842785,
      "grad_norm": 14.726645469665527,
      "learning_rate": 2.772187909414187e-05,
      "loss": 1.9182,
      "step": 30000
    },
    {
      "epoch": 0.3368893879842785,
      "eval_loss": 1.6327084302902222,
      "eval_runtime": 1116.2417,
      "eval_samples_per_second": 159.553,
      "eval_steps_per_second": 1.247,
      "step": 30000
    },
    {
      "epoch": 0.5053340819764177,
      "grad_norm": 19.574451446533203,
      "learning_rate": 2.4915029009919522e-05,
      "loss": 1.7261,
      "step": 45000
    },
    {
      "epoch": 0.5053340819764177,
      "eval_loss": 1.5172808170318604,
      "eval_runtime": 1115.8439,
      "eval_samples_per_second": 159.61,
      "eval_steps_per_second": 1.247,
      "step": 45000
    },
    {
      "epoch": 0.673778775968557,
      "grad_norm": 20.48647689819336,
      "learning_rate": 2.2108740408010482e-05,
      "loss": 1.6107,
      "step": 60000
    },
    {
      "epoch": 0.673778775968557,
      "eval_loss": 1.4170897006988525,
      "eval_runtime": 1116.5576,
      "eval_samples_per_second": 159.508,
      "eval_steps_per_second": 1.247,
      "step": 60000
    },
    {
      "epoch": 0.8422234699606962,
      "grad_norm": 32.2099723815918,
      "learning_rate": 1.930226464533034e-05,
      "loss": 1.5123,
      "step": 75000
    },
    {
      "epoch": 0.8422234699606962,
      "eval_loss": 1.343780279159546,
      "eval_runtime": 1115.8728,
      "eval_samples_per_second": 159.606,
      "eval_steps_per_second": 1.247,
      "step": 75000
    },
    {
      "epoch": 1.0106681639528354,
      "grad_norm": 14.760332107543945,
      "learning_rate": 1.6495788882650198e-05,
      "loss": 1.4345,
      "step": 90000
    },
    {
      "epoch": 1.0106681639528354,
      "eval_loss": 1.2858102321624756,
      "eval_runtime": 1116.3944,
      "eval_samples_per_second": 159.531,
      "eval_steps_per_second": 1.247,
      "step": 90000
    },
    {
      "epoch": 1.1791128579449748,
      "grad_norm": 14.706148147583008,
      "learning_rate": 1.3689125959198953e-05,
      "loss": 1.3727,
      "step": 105000
    },
    {
      "epoch": 1.1791128579449748,
      "eval_loss": 1.2305110692977905,
      "eval_runtime": 1115.1142,
      "eval_samples_per_second": 159.715,
      "eval_steps_per_second": 1.248,
      "step": 105000
    },
    {
      "epoch": 1.347557551937114,
      "grad_norm": 16.19214630126953,
      "learning_rate": 1.0882837357289913e-05,
      "loss": 1.316,
      "step": 120000
    },
    {
      "epoch": 1.347557551937114,
      "eval_loss": 1.1903249025344849,
      "eval_runtime": 1117.3943,
      "eval_samples_per_second": 159.389,
      "eval_steps_per_second": 1.246,
      "step": 120000
    },
    {
      "epoch": 1.5160022459292533,
      "grad_norm": 19.906694412231445,
      "learning_rate": 8.07636159460977e-06,
      "loss": 1.2797,
      "step": 135000
    },
    {
      "epoch": 1.5160022459292533,
      "eval_loss": 1.160164475440979,
      "eval_runtime": 1114.4095,
      "eval_samples_per_second": 159.816,
      "eval_steps_per_second": 1.249,
      "step": 135000
    },
    {
      "epoch": 1.6844469399213926,
      "grad_norm": 15.975142478942871,
      "learning_rate": 5.269885831929627e-06,
      "loss": 1.233,
      "step": 150000
    },
    {
      "epoch": 1.6844469399213926,
      "eval_loss": 1.1218129396438599,
      "eval_runtime": 1115.4279,
      "eval_samples_per_second": 159.67,
      "eval_steps_per_second": 1.248,
      "step": 150000
    },
    {
      "epoch": 1.8528916339135317,
      "grad_norm": 11.748427391052246,
      "learning_rate": 2.4634100692494855e-06,
      "loss": 1.2073,
      "step": 165000
    },
    {
      "epoch": 1.8528916339135317,
      "eval_loss": 1.0992534160614014,
      "eval_runtime": 1115.015,
      "eval_samples_per_second": 159.729,
      "eval_steps_per_second": 1.248,
      "step": 165000
    }
  ],
  "logging_steps": 15000,
  "max_steps": 178100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 15000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2303528716185068e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}