checkpoint-250/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06212144742972511,
  "eval_steps": 1000,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024848578971890044,
      "grad_norm": 1.1403515692366237,
      "learning_rate": 0.0002475,
      "loss": 0.7727,
      "step": 100
    },
    {
      "epoch": 0.04969715794378009,
      "grad_norm": 2.0321728234236067,
      "learning_rate": 0.0004975,
      "loss": 0.6434,
      "step": 200
    }
  ],
  "logging_steps": 100,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 32166462357504.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}