trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9962640099626401,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9962640099626401,
      "grad_norm": 34.157554626464844,
      "learning_rate": 0.0,
      "loss": 0.6567,
      "step": 200
    },
    {
      "epoch": 0.9962640099626401,
      "eval_accuracy": 0.6647058823529411,
      "eval_loss": 0.6134363412857056,
      "eval_runtime": 10.1692,
      "eval_samples_per_second": 33.434,
      "eval_steps_per_second": 4.228,
      "step": 200
    },
    {
      "epoch": 0.9962640099626401,
      "step": 200,
      "total_flos": 0.0,
      "train_loss": 0.6566852569580078,
      "train_runtime": 911.8731,
      "train_samples_per_second": 7.04,
      "train_steps_per_second": 0.219
    }
  ],
  "logging_steps": 200,
  "max_steps": 200,
  "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": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}