default/checkpoint-10/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.044444444444444446,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 3.639567466962035e-06,
      "learning_rate": 4.988888888888889e-06,
      "loss": 0.6992,
      "step": 10
    },
    {
      "epoch": 0.044444444444444446,
      "eval_accuracy": 0.5314685314685315,
      "eval_loss": 0.6923828125,
      "eval_runtime": 17.5567,
      "eval_samples_per_second": 11.392,
      "eval_steps_per_second": 1.424,
      "step": 10
    }
  ],
  "logging_steps": 10,
  "max_steps": 4500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}