{
  "best_metric": 1.1167163848876953,
  "best_model_checkpoint": "/kaggle/output/checkpoint-8000",
  "epoch": 128.0,
  "eval_steps": 1000,
  "global_step": 8000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.7777777777777777e-11,
      "loss": 1.2395,
      "step": 1
    },
    {
      "epoch": 16.0,
      "learning_rate": 2.7638888888888893e-08,
      "loss": 1.1422,
      "step": 1000
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.33073852295409184,
      "eval_loss": 1.1557353734970093,
      "eval_runtime": 54.1805,
      "eval_samples_per_second": 92.469,
      "eval_steps_per_second": 11.572,
      "step": 1000
    },
    {
      "epoch": 32.0,
      "learning_rate": 5.541666666666667e-08,
      "loss": 1.1401,
      "step": 2000
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.3311377245508982,
      "eval_loss": 1.1507551670074463,
      "eval_runtime": 53.98,
      "eval_samples_per_second": 92.812,
      "eval_steps_per_second": 11.615,
      "step": 2000
    },
    {
      "epoch": 48.0,
      "learning_rate": 8.316666666666666e-08,
      "loss": 1.1287,
      "step": 3000
    },
    {
      "epoch": 48.0,
      "eval_accuracy": 0.3321357285429142,
      "eval_loss": 1.1441665887832642,
      "eval_runtime": 53.9873,
      "eval_samples_per_second": 92.8,
      "eval_steps_per_second": 11.614,
      "step": 3000
    },
    {
      "epoch": 64.0,
      "learning_rate": 1.1094444444444445e-07,
      "loss": 1.117,
      "step": 4000
    },
    {
      "epoch": 64.0,
      "eval_accuracy": 0.3287425149700599,
      "eval_loss": 1.134506344795227,
      "eval_runtime": 54.0067,
      "eval_samples_per_second": 92.766,
      "eval_steps_per_second": 11.61,
      "step": 4000
    },
    {
      "epoch": 80.0,
      "learning_rate": 1.3872222222222222e-07,
      "loss": 1.1111,
      "step": 5000
    },
    {
      "epoch": 80.0,
      "eval_accuracy": 0.32954091816367265,
      "eval_loss": 1.1283142566680908,
      "eval_runtime": 54.0921,
      "eval_samples_per_second": 92.62,
      "eval_steps_per_second": 11.591,
      "step": 5000
    },
    {
      "epoch": 96.0,
      "learning_rate": 1.6650000000000002e-07,
      "loss": 1.1053,
      "step": 6000
    },
    {
      "epoch": 96.0,
      "eval_accuracy": 0.32894211576846305,
      "eval_loss": 1.1218452453613281,
      "eval_runtime": 54.0607,
      "eval_samples_per_second": 92.674,
      "eval_steps_per_second": 11.598,
      "step": 6000
    },
    {
      "epoch": 112.0,
      "learning_rate": 1.9422222222222223e-07,
      "loss": 1.0952,
      "step": 7000
    },
    {
      "epoch": 112.0,
      "eval_accuracy": 0.33073852295409184,
      "eval_loss": 1.118302583694458,
      "eval_runtime": 53.9252,
      "eval_samples_per_second": 92.906,
      "eval_steps_per_second": 11.627,
      "step": 7000
    },
    {
      "epoch": 128.0,
      "learning_rate": 2.2197222222222225e-07,
      "loss": 1.0909,
      "step": 8000
    },
    {
      "epoch": 128.0,
      "eval_accuracy": 0.3281437125748503,
      "eval_loss": 1.1167163848876953,
      "eval_runtime": 54.095,
      "eval_samples_per_second": 92.615,
      "eval_steps_per_second": 11.591,
      "step": 8000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10000000,
  "num_train_epochs": 161291,
  "save_steps": 1000,
  "total_flos": 1.6722841042944e+16,
  "trial_name": null,
  "trial_params": null
}