trainer_state.json

{
  "best_metric": 0.11622841656208038,
  "best_model_checkpoint": "gbert-base-argument_mining/checkpoint-292",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 292,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9315068493150684,
      "eval_loss": 0.38721901178359985,
      "eval_runtime": 0.5424,
      "eval_samples_per_second": 269.173,
      "eval_steps_per_second": 35.029,
      "step": 73
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9178082191780822,
      "eval_loss": 0.29867371916770935,
      "eval_runtime": 0.4382,
      "eval_samples_per_second": 333.146,
      "eval_steps_per_second": 43.355,
      "step": 146
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.958904109589041,
      "eval_loss": 0.15189063549041748,
      "eval_runtime": 0.4321,
      "eval_samples_per_second": 337.889,
      "eval_steps_per_second": 43.972,
      "step": 219
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9657534246575342,
      "eval_loss": 0.11622841656208038,
      "eval_runtime": 0.4288,
      "eval_samples_per_second": 340.51,
      "eval_steps_per_second": 44.313,
      "step": 292
    }
  ],
  "logging_steps": 500,
  "max_steps": 730,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 58622426224992.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}