checkpoint-690/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 690,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.5981,
      "step": 230
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7892156862745098,
      "eval_combined_score": 0.8227014886222047,
      "eval_f1": 0.8561872909698997,
      "eval_loss": 0.45800894498825073,
      "eval_runtime": 4.1966,
      "eval_samples_per_second": 97.221,
      "eval_steps_per_second": 12.153,
      "step": 230
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.2e-05,
      "loss": 0.3739,
      "step": 460
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8480392156862745,
      "eval_combined_score": 0.8711185839523523,
      "eval_f1": 0.89419795221843,
      "eval_loss": 0.38060691952705383,
      "eval_runtime": 4.1663,
      "eval_samples_per_second": 97.928,
      "eval_steps_per_second": 12.241,
      "step": 460
    },
    {
      "epoch": 3.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1991,
      "step": 690
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8529411764705882,
      "eval_combined_score": 0.8743872549019608,
      "eval_f1": 0.8958333333333334,
      "eval_loss": 0.4879474937915802,
      "eval_runtime": 4.1609,
      "eval_samples_per_second": 98.056,
      "eval_steps_per_second": 12.257,
      "step": 690
    }
  ],
  "max_steps": 1150,
  "num_train_epochs": 5,
  "total_flos": 2895274053181440.0,
  "trial_name": null,
  "trial_params": null
}