{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24060150375939848,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012030075187969926,
      "grad_norm": 6.800055027008057,
      "learning_rate": 1e-05,
      "loss": 28.5635,
      "step": 1
    },
    {
      "epoch": 0.012030075187969926,
      "eval_loss": 1.9814797639846802,
      "eval_runtime": 20.5991,
      "eval_samples_per_second": 6.796,
      "eval_steps_per_second": 3.398,
      "step": 1
    },
    {
      "epoch": 0.02406015037593985,
      "grad_norm": 9.030173301696777,
      "learning_rate": 2e-05,
      "loss": 36.1407,
      "step": 2
    },
    {
      "epoch": 0.03609022556390978,
      "grad_norm": 14.515695571899414,
      "learning_rate": 3e-05,
      "loss": 40.8297,
      "step": 3
    },
    {
      "epoch": 0.0481203007518797,
      "grad_norm": 2.760538101196289,
      "learning_rate": 4e-05,
      "loss": 23.4217,
      "step": 4
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 3.105170965194702,
      "learning_rate": 5e-05,
      "loss": 23.9036,
      "step": 5
    },
    {
      "epoch": 0.06015037593984962,
      "eval_loss": 1.9180042743682861,
      "eval_runtime": 9.941,
      "eval_samples_per_second": 14.083,
      "eval_steps_per_second": 7.042,
      "step": 5
    },
    {
      "epoch": 0.07218045112781955,
      "grad_norm": 15.351724624633789,
      "learning_rate": 6e-05,
      "loss": 41.5397,
      "step": 6
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 11.699372291564941,
      "learning_rate": 7e-05,
      "loss": 34.4623,
      "step": 7
    },
    {
      "epoch": 0.0962406015037594,
      "grad_norm": 10.594860076904297,
      "learning_rate": 8e-05,
      "loss": 28.1834,
      "step": 8
    },
    {
      "epoch": 0.10827067669172932,
      "grad_norm": 4.002998352050781,
      "learning_rate": 9e-05,
      "loss": 22.5825,
      "step": 9
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 11.839838027954102,
      "learning_rate": 0.0001,
      "loss": 27.1386,
      "step": 10
    },
    {
      "epoch": 0.12030075187969924,
      "eval_loss": 1.6268460750579834,
      "eval_runtime": 9.9139,
      "eval_samples_per_second": 14.122,
      "eval_steps_per_second": 7.061,
      "step": 10
    },
    {
      "epoch": 0.13233082706766916,
      "grad_norm": 4.669586658477783,
      "learning_rate": 9.755282581475769e-05,
      "loss": 22.4411,
      "step": 11
    },
    {
      "epoch": 0.1443609022556391,
      "grad_norm": 18.783884048461914,
      "learning_rate": 9.045084971874738e-05,
      "loss": 24.9057,
      "step": 12
    },
    {
      "epoch": 0.15639097744360902,
      "grad_norm": 5.951033592224121,
      "learning_rate": 7.938926261462366e-05,
      "loss": 22.4748,
      "step": 13
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 3.586989641189575,
      "learning_rate": 6.545084971874738e-05,
      "loss": 21.7207,
      "step": 14
    },
    {
      "epoch": 0.18045112781954886,
      "grad_norm": 5.163401126861572,
      "learning_rate": 5e-05,
      "loss": 22.3279,
      "step": 15
    },
    {
      "epoch": 0.18045112781954886,
      "eval_loss": 1.3868980407714844,
      "eval_runtime": 9.9239,
      "eval_samples_per_second": 14.107,
      "eval_steps_per_second": 7.054,
      "step": 15
    },
    {
      "epoch": 0.1924812030075188,
      "grad_norm": 8.766792297363281,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 25.016,
      "step": 16
    },
    {
      "epoch": 0.20451127819548873,
      "grad_norm": 5.95711612701416,
      "learning_rate": 2.061073738537635e-05,
      "loss": 21.8665,
      "step": 17
    },
    {
      "epoch": 0.21654135338345865,
      "grad_norm": 6.319004535675049,
      "learning_rate": 9.549150281252633e-06,
      "loss": 22.8829,
      "step": 18
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 4.247712135314941,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 20.6744,
      "step": 19
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 3.0739986896514893,
      "learning_rate": 0.0,
      "loss": 20.0761,
      "step": 20
    },
    {
      "epoch": 0.24060150375939848,
      "eval_loss": 1.3583178520202637,
      "eval_runtime": 9.9315,
      "eval_samples_per_second": 14.097,
      "eval_steps_per_second": 7.048,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.4357877850112e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}