trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13043478260869565,
  "eval_steps": 500,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13043478260869565,
      "eval_loss": 1.699319839477539,
      "eval_runtime": 3.6919,
      "eval_samples_per_second": 167.124,
      "eval_steps_per_second": 2.709,
      "step": 3
    },
    {
      "epoch": 0.13043478260869565,
      "step": 3,
      "total_flos": 3.355230384370483e+16,
      "train_loss": 1.4136133193969727,
      "train_runtime": 207.196,
      "train_samples_per_second": 7.413,
      "train_steps_per_second": 0.014
    }
  ],
  "logging_steps": 10,
  "max_steps": 3,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.355230384370483e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}