{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 58,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 6.099521160125732,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4051,
      "step": 5
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 7.150094032287598,
      "learning_rate": 9.992134075089085e-06,
      "loss": 0.4124,
      "step": 10
    },
    {
      "epoch": 0.26200873362445415,
      "grad_norm": 7.586390495300293,
      "learning_rate": 9.944154131125643e-06,
      "loss": 0.4349,
      "step": 15
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 5.689783096313477,
      "learning_rate": 9.852982837266955e-06,
      "loss": 0.4195,
      "step": 20
    },
    {
      "epoch": 0.4366812227074236,
      "grad_norm": 5.594226360321045,
      "learning_rate": 9.719416651541839e-06,
      "loss": 0.4551,
      "step": 25
    },
    {
      "epoch": 0.5240174672489083,
      "grad_norm": 5.31730842590332,
      "learning_rate": 9.544622387061055e-06,
      "loss": 0.4028,
      "step": 30
    },
    {
      "epoch": 0.611353711790393,
      "grad_norm": 6.336578845977783,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.482,
      "step": 35
    },
    {
      "epoch": 0.6986899563318777,
      "grad_norm": 5.558196067810059,
      "learning_rate": 9.077804344796302e-06,
      "loss": 0.477,
      "step": 40
    },
    {
      "epoch": 0.7860262008733624,
      "grad_norm": 6.426137924194336,
      "learning_rate": 8.789858615727266e-06,
      "loss": 0.4114,
      "step": 45
    },
    {
      "epoch": 0.8733624454148472,
      "grad_norm": 5.5606889724731445,
      "learning_rate": 8.46880528014271e-06,
      "loss": 0.4838,
      "step": 50
    },
    {
      "epoch": 0.9606986899563319,
      "grad_norm": 4.891933917999268,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.4448,
      "step": 55
    }
  ],
  "logging_steps": 5,
  "max_steps": 174,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.746584933774131e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}