{
  "best_global_step": 500,
  "best_metric": 4.811308860778809,
  "best_model_checkpoint": "/tmp/colab_artifacts_v2/pretrain_checkpoints/checkpoint-500",
  "epoch": 0.10501995379122034,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010501995379122032,
      "grad_norm": 16.108776092529297,
      "learning_rate": 4.716981132075472e-06,
      "loss": 7.048248901367187,
      "step": 50
    },
    {
      "epoch": 0.021003990758244065,
      "grad_norm": 7.494509220123291,
      "learning_rate": 9.958071278825997e-06,
      "loss": 5.635718994140625,
      "step": 100
    },
    {
      "epoch": 0.0315059861373661,
      "grad_norm": 3.1452040672302246,
      "learning_rate": 1.5199161425576522e-05,
      "loss": 4.769013366699219,
      "step": 150
    },
    {
      "epoch": 0.04200798151648813,
      "grad_norm": 6.104097843170166,
      "learning_rate": 2.0440251572327044e-05,
      "loss": 4.167159423828125,
      "step": 200
    },
    {
      "epoch": 0.05250997689561017,
      "grad_norm": 2.9789626598358154,
      "learning_rate": 2.5681341719077568e-05,
      "loss": 4.021661987304688,
      "step": 250
    },
    {
      "epoch": 0.0630119722747322,
      "grad_norm": 3.7343900203704834,
      "learning_rate": 3.092243186582809e-05,
      "loss": 3.8835012817382815,
      "step": 300
    },
    {
      "epoch": 0.07351396765385423,
      "grad_norm": 3.598313808441162,
      "learning_rate": 3.6163522012578616e-05,
      "loss": 3.719826354980469,
      "step": 350
    },
    {
      "epoch": 0.08401596303297626,
      "grad_norm": 2.9602694511413574,
      "learning_rate": 4.140461215932914e-05,
      "loss": 3.6351690673828125,
      "step": 400
    },
    {
      "epoch": 0.0945179584120983,
      "grad_norm": 2.4005064964294434,
      "learning_rate": 4.664570230607967e-05,
      "loss": 3.552754211425781,
      "step": 450
    },
    {
      "epoch": 0.10501995379122034,
      "grad_norm": 3.6799378395080566,
      "learning_rate": 4.978991596638656e-05,
      "loss": 3.5413519287109376,
      "step": 500
    },
    {
      "epoch": 0.10501995379122034,
      "eval_loss": 4.811308860778809,
      "eval_runtime": 24.7312,
      "eval_samples_per_second": 10.958,
      "eval_steps_per_second": 2.75,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 4761,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7126390485221376.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}