checkpoint-300/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 39.51091766357422,
      "learning_rate": 3.563829787234043e-05,
      "loss": 2.526,
      "step": 100
    },
    {
      "epoch": 2.0,
      "grad_norm": 40.35090255737305,
      "learning_rate": 1.7907801418439718e-05,
      "loss": 2.1323,
      "step": 200
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.34549331665039,
      "learning_rate": 1.773049645390071e-07,
      "loss": 1.8826,
      "step": 300
    }
  ],
  "logging_steps": 100,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 409273344000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}