last-checkpoint/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009171507184347295,
  "eval_steps": 1000,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003057169061449098,
      "grad_norm": NaN,
      "learning_rate": 4.999999989150923e-05,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.006114338122898196,
      "grad_norm": NaN,
      "learning_rate": 4.99999995525116e-05,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.009171507184347295,
      "grad_norm": NaN,
      "learning_rate": 4.999999898290334e-05,
      "loss": 0.0,
      "step": 600
    }
  ],
  "logging_steps": 200,
  "max_steps": 6542000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 179452957671360.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}