trainer_state.json

{
  "best_metric": 0.004898133222013712,
  "best_model_checkpoint": "data/train-test///model/checkpoint-3351",
  "epoch": 1.0,
  "global_step": 3351,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 1.850790808713817e-05,
      "loss": 0.1149,
      "step": 500
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7015816174276335e-05,
      "loss": 0.0198,
      "step": 1000
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.5523724261414504e-05,
      "loss": 0.0101,
      "step": 1500
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.4031632348552673e-05,
      "loss": 0.0063,
      "step": 2000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.253954043569084e-05,
      "loss": 0.0067,
      "step": 2500
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.1047448522829008e-05,
      "loss": 0.0068,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": null,
      "eval_f1": 0.9943977591036415,
      "eval_loss": 0.004898133222013712,
      "eval_precision": 0.9943977591036415,
      "eval_recall": 0.9943977591036415,
      "eval_runtime": 1.5284,
      "eval_samples_per_second": 634.661,
      "eval_steps_per_second": 79.823,
      "step": 3351
    }
  ],
  "max_steps": 6702,
  "num_train_epochs": 2,
  "total_flos": 2597776456686000.0,
  "trial_name": null,
  "trial_params": null
}