{
  "best_metric": 0.188609778881073,
  "best_model_checkpoint": "/kaggle/working/trainer/checkpoint-590",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 826,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.8571428571428576e-05,
      "loss": 2.4834,
      "step": 118
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.3096010982990265,
      "eval_runtime": 19.7327,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 118
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.601731601731602e-05,
      "loss": 0.2273,
      "step": 236
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.28577497601509094,
      "eval_runtime": 19.732,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 236
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.374458874458875e-05,
      "loss": 0.7001,
      "step": 354
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.27604082226753235,
      "eval_runtime": 19.749,
      "eval_samples_per_second": 1.317,
      "eval_steps_per_second": 0.658,
      "step": 354
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.119047619047619e-05,
      "loss": 0.1831,
      "step": 472
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.21857748925685883,
      "eval_runtime": 19.7556,
      "eval_samples_per_second": 1.316,
      "eval_steps_per_second": 0.658,
      "step": 472
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.8636363636363636e-05,
      "loss": 0.1718,
      "step": 590
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.188609778881073,
      "eval_runtime": 19.8276,
      "eval_samples_per_second": 1.311,
      "eval_steps_per_second": 0.656,
      "step": 590
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.6082251082251085e-05,
      "loss": 0.2381,
      "step": 708
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.2819238305091858,
      "eval_runtime": 19.7856,
      "eval_samples_per_second": 1.314,
      "eval_steps_per_second": 0.657,
      "step": 708
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.352813852813853e-05,
      "loss": 0.359,
      "step": 826
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.3825746774673462,
      "eval_runtime": 19.8497,
      "eval_samples_per_second": 1.31,
      "eval_steps_per_second": 0.655,
      "step": 826
    }
  ],
  "logging_steps": 500,
  "max_steps": 2360,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 1.5133641299460096e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}