checkpoint-2010/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 2010,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.487562189054726,
      "grad_norm": 814.1642456054688,
      "learning_rate": 7.517412935323384e-06,
      "loss": -64.4005,
      "step": 500
    },
    {
      "epoch": 4.975124378109452,
      "grad_norm": 71.82451629638672,
      "learning_rate": 5.029850746268657e-06,
      "loss": -161.253,
      "step": 1000
    },
    {
      "epoch": 7.462686567164179,
      "grad_norm": 99.78916931152344,
      "learning_rate": 2.5422885572139305e-06,
      "loss": -166.4897,
      "step": 1500
    },
    {
      "epoch": 9.950248756218905,
      "grad_norm": 46.463138580322266,
      "learning_rate": 5.4726368159203986e-08,
      "loss": -168.4679,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2010,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}