checkpoint-180/trainer_state.json

{
  "best_global_step": 180,
  "best_metric": 0.07337220758199692,
  "best_model_checkpoint": "../trained_models/hazard_model\\checkpoint-180",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 2.024980068206787,
      "eval_runtime": 29.0401,
      "eval_samples_per_second": 8.264,
      "eval_steps_per_second": 0.517,
      "step": 60
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.739890992641449,
      "eval_runtime": 28.9542,
      "eval_samples_per_second": 8.289,
      "eval_steps_per_second": 0.518,
      "step": 120
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.07337220758199692,
      "eval_runtime": 45.0725,
      "eval_samples_per_second": 5.325,
      "eval_steps_per_second": 0.333,
      "step": 180
    }
  ],
  "logging_steps": 500,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 189453567098880.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}