checkpoint-18/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 15.98961353302002,
      "eval_runtime": 3.0384,
      "eval_samples_per_second": 2.962,
      "eval_steps_per_second": 2.962,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_loss": 15.178080558776855,
      "eval_runtime": 3.0446,
      "eval_samples_per_second": 2.956,
      "eval_steps_per_second": 2.956,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_loss": 14.846773147583008,
      "eval_runtime": 3.0494,
      "eval_samples_per_second": 2.951,
      "eval_steps_per_second": 2.951,
      "step": 9
    },
    {
      "epoch": 4.0,
      "eval_loss": 14.293635368347168,
      "eval_runtime": 3.0571,
      "eval_samples_per_second": 2.944,
      "eval_steps_per_second": 2.944,
      "step": 12
    },
    {
      "epoch": 5.0,
      "eval_loss": 13.908576965332031,
      "eval_runtime": 3.0589,
      "eval_samples_per_second": 2.942,
      "eval_steps_per_second": 2.942,
      "step": 15
    },
    {
      "epoch": 6.0,
      "eval_loss": 13.70132064819336,
      "eval_runtime": 3.0763,
      "eval_samples_per_second": 2.926,
      "eval_steps_per_second": 2.926,
      "step": 18
    }
  ],
  "logging_steps": 500,
  "max_steps": 20,
  "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": 9627245488373760.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}