trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "global_step": 1477,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8411080332409973,
      "eval_f1": 0.8052208835341366,
      "eval_loss": 0.06445828080177307,
      "eval_precision": 0.8038757099899766,
      "eval_recall": 0.8065705665437479,
      "eval_runtime": 4.9709,
      "eval_samples_per_second": 678.346,
      "eval_steps_per_second": 5.432,
      "step": 211
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.914016620498615,
      "eval_f1": 0.9096102150537634,
      "eval_loss": 0.03706464543938637,
      "eval_precision": 0.9117547995958235,
      "eval_recall": 0.9074756956084479,
      "eval_runtime": 4.9541,
      "eval_samples_per_second": 680.645,
      "eval_steps_per_second": 5.45,
      "step": 422
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9270914127423823,
      "eval_f1": 0.9288702928870293,
      "eval_loss": 0.03221126273274422,
      "eval_precision": 0.9274732620320856,
      "eval_recall": 0.93027153871941,
      "eval_runtime": 5.0612,
      "eval_samples_per_second": 666.244,
      "eval_steps_per_second": 5.335,
      "step": 633
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9380609418282548,
      "eval_f1": 0.9411566346315967,
      "eval_loss": 0.029083197936415672,
      "eval_precision": 0.9467435549525102,
      "eval_recall": 0.9356352665102247,
      "eval_runtime": 4.9781,
      "eval_samples_per_second": 677.372,
      "eval_steps_per_second": 5.424,
      "step": 844
    },
    {
      "epoch": 4.74,
      "loss": 0.1327,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.950803324099723,
      "eval_f1": 0.953245879582913,
      "eval_loss": 0.03200341761112213,
      "eval_precision": 0.9564630442119474,
      "eval_recall": 0.9500502849480389,
      "eval_runtime": 4.9815,
      "eval_samples_per_second": 676.904,
      "eval_steps_per_second": 5.42,
      "step": 1055
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9441551246537396,
      "eval_f1": 0.9509078681909886,
      "eval_loss": 0.03349672257900238,
      "eval_precision": 0.9537942664418212,
      "eval_recall": 0.9480388870264834,
      "eval_runtime": 4.9755,
      "eval_samples_per_second": 677.72,
      "eval_steps_per_second": 5.427,
      "step": 1266
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9472576177285319,
      "eval_f1": 0.9518680578929655,
      "eval_loss": 0.03363509103655815,
      "eval_precision": 0.9557282865833052,
      "eval_recall": 0.9480388870264834,
      "eval_runtime": 5.0017,
      "eval_samples_per_second": 674.172,
      "eval_steps_per_second": 5.398,
      "step": 1477
    }
  ],
  "max_steps": 1477,
  "num_train_epochs": 7,
  "total_flos": 5303134846185912.0,
  "trial_name": null,
  "trial_params": null
}