trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 23,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 7.830950736999512,
      "learning_rate": 1.4539904997395468e-05,
      "loss": 1.3644,
      "step": 10
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 2.2085812091827393,
      "learning_rate": 1.0899347581163222e-06,
      "loss": 1.1085,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0610344409942627,
      "eval_runtime": 3.6404,
      "eval_samples_per_second": 169.488,
      "eval_steps_per_second": 2.747,
      "step": 23
    },
    {
      "epoch": 1.0,
      "step": 23,
      "total_flos": 2.572343380583383e+17,
      "train_loss": 1.21880755217179,
      "train_runtime": 428.8113,
      "train_samples_per_second": 27.329,
      "train_steps_per_second": 0.054
    }
  ],
  "logging_steps": 10,
  "max_steps": 23,
  "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": 2.572343380583383e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}