last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006874328678839957,
  "eval_steps": 2,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 10.529623031616211,
      "learning_rate": 1e-05,
      "loss": 17.0476,
      "step": 1
    },
    {
      "epoch": 0.0034371643394199786,
      "eval_loss": 16.60216522216797,
      "eval_runtime": 44.6332,
      "eval_samples_per_second": 10.978,
      "eval_steps_per_second": 5.489,
      "step": 1
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 11.592485427856445,
      "learning_rate": 2e-05,
      "loss": 16.5754,
      "step": 2
    },
    {
      "epoch": 0.006874328678839957,
      "eval_loss": 16.4743709564209,
      "eval_runtime": 7.9083,
      "eval_samples_per_second": 61.96,
      "eval_steps_per_second": 30.98,
      "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": 46295078141952.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}