{
  "best_metric": 1.9876124858856201,
  "best_model_checkpoint": "Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130",
  "epoch": 2.0,
  "global_step": 5130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 2.1955,
      "step": 500
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.4600431965442765e-05,
      "loss": 1.8704,
      "step": 1000
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.920086393088553e-05,
      "loss": 1.7624,
      "step": 1500
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.38012958963283e-05,
      "loss": 1.7039,
      "step": 2000
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.840172786177106e-05,
      "loss": 1.6626,
      "step": 2500
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.0070595741271973,
      "eval_runtime": 102.1824,
      "eval_samples_per_second": 386.446,
      "step": 2565
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.3002159827213822e-05,
      "loss": 1.6134,
      "step": 3000
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.7602591792656588e-05,
      "loss": 1.5933,
      "step": 3500
    },
    {
      "epoch": 1.56,
      "learning_rate": 1.2203023758099353e-05,
      "loss": 1.5742,
      "step": 4000
    },
    {
      "epoch": 1.75,
      "learning_rate": 6.803455723542117e-06,
      "loss": 1.5735,
      "step": 4500
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.4038876889848812e-06,
      "loss": 1.5623,
      "step": 5000
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.9876124858856201,
      "eval_runtime": 102.2828,
      "eval_samples_per_second": 386.067,
      "step": 5130
    }
  ],
  "max_steps": 5130,
  "num_train_epochs": 2,
  "total_flos": 31377467721646080,
  "trial_name": null,
  "trial_params": null
}