trainer_state.json

{
  "best_metric": 0.633144736289978,
  "best_model_checkpoint": "./results2_silvia\\checkpoint-5895",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 7860,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.001,
      "loss": 0.6389,
      "step": 1965
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6714603881641743,
      "eval_f1": 0.0,
      "eval_false_negatives": 5163,
      "eval_false_positives": 0,
      "eval_loss": 0.6334741115570068,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 733.5758,
      "eval_samples_per_second": 21.422,
      "eval_steps_per_second": 0.671,
      "eval_true_negatives": 10552,
      "eval_true_positives": 0,
      "step": 1965
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.001,
      "loss": 0.6344,
      "step": 3930
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6714603881641743,
      "eval_f1": 0.0,
      "eval_false_negatives": 5163,
      "eval_false_positives": 0,
      "eval_loss": 0.6339382529258728,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 732.9949,
      "eval_samples_per_second": 21.439,
      "eval_steps_per_second": 0.671,
      "eval_true_negatives": 10552,
      "eval_true_positives": 0,
      "step": 3930
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.001,
      "loss": 0.6334,
      "step": 5895
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6714603881641743,
      "eval_f1": 0.0,
      "eval_false_negatives": 5163,
      "eval_false_positives": 0,
      "eval_loss": 0.633144736289978,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 733.4836,
      "eval_samples_per_second": 21.425,
      "eval_steps_per_second": 0.671,
      "eval_true_negatives": 10552,
      "eval_true_positives": 0,
      "step": 5895
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.001,
      "loss": 0.6334,
      "step": 7860
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6714603881641743,
      "eval_f1": 0.0,
      "eval_false_negatives": 5163,
      "eval_false_positives": 0,
      "eval_loss": 0.633177638053894,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 733.9925,
      "eval_samples_per_second": 21.41,
      "eval_steps_per_second": 0.67,
      "eval_true_negatives": 10552,
      "eval_true_positives": 0,
      "step": 7860
    }
  ],
  "logging_steps": 500,
  "max_steps": 7860,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 3.330654297887539e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}