trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 560,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.39946380697050937,
      "eval_f1": 0.39951655391963925,
      "eval_loss": 1.6062450408935547,
      "eval_precision": 0.3999992623496508,
      "eval_recall": 0.39946380697050937,
      "eval_runtime": 1.0662,
      "eval_samples_per_second": 1049.495,
      "eval_steps_per_second": 13.13,
      "step": 112
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4486148346738159,
      "eval_f1": 0.44879096075280017,
      "eval_loss": 1.557194471359253,
      "eval_precision": 0.45032387618136827,
      "eval_recall": 0.4486148346738159,
      "eval_runtime": 0.9645,
      "eval_samples_per_second": 1160.176,
      "eval_steps_per_second": 14.515,
      "step": 224
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.48078641644325293,
      "eval_f1": 0.48044306647023427,
      "eval_loss": 1.4841872453689575,
      "eval_precision": 0.48189831555981366,
      "eval_recall": 0.48078641644325293,
      "eval_runtime": 0.9592,
      "eval_samples_per_second": 1166.651,
      "eval_steps_per_second": 14.596,
      "step": 336
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5102770330652369,
      "eval_f1": 0.5099868458795241,
      "eval_loss": 1.4472650289535522,
      "eval_precision": 0.5119449274550995,
      "eval_recall": 0.5102770330652369,
      "eval_runtime": 1.0814,
      "eval_samples_per_second": 1034.774,
      "eval_steps_per_second": 12.946,
      "step": 448
    },
    {
      "epoch": 4.46,
      "learning_rate": 1.0714285714285714e-06,
      "loss": 1.5567,
      "step": 500
    }
  ],
  "max_steps": 560,
  "num_train_epochs": 5,
  "total_flos": 127329432988800.0,
  "trial_name": null,
  "trial_params": null
}