last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005039370078740158,
  "eval_steps": 2,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002519685039370079,
      "grad_norm": 7.116703033447266,
      "learning_rate": 1e-05,
      "loss": 2.7367,
      "step": 1
    },
    {
      "epoch": 0.0002519685039370079,
      "eval_loss": 2.8593077659606934,
      "eval_runtime": 128.7427,
      "eval_samples_per_second": 51.925,
      "eval_steps_per_second": 25.967,
      "step": 1
    },
    {
      "epoch": 0.0005039370078740158,
      "grad_norm": 7.5051984786987305,
      "learning_rate": 2e-05,
      "loss": 3.1469,
      "step": 2
    },
    {
      "epoch": 0.0005039370078740158,
      "eval_loss": 2.7861061096191406,
      "eval_runtime": 68.7197,
      "eval_samples_per_second": 97.279,
      "eval_steps_per_second": 48.647,
      "step": 2
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 391582234705920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}