{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9454545454545453,
  "eval_steps": 500,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 4.227509557931787,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.864,
      "step": 1
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 5.316110098123688,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.0091,
      "step": 2
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 4.369115154565446,
      "learning_rate": 1e-05,
      "loss": 0.9419,
      "step": 3
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 2.212193153986046,
      "learning_rate": 9.957224306869053e-06,
      "loss": 0.8397,
      "step": 4
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 2.0353503035139973,
      "learning_rate": 9.829629131445342e-06,
      "loss": 0.7215,
      "step": 5
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 1.8292874608991594,
      "learning_rate": 9.619397662556434e-06,
      "loss": 0.7944,
      "step": 6
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 1.7294151311711272,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.8327,
      "step": 7
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 1.0270472993455948,
      "learning_rate": 8.966766701456177e-06,
      "loss": 0.7433,
      "step": 8
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 1.0628843838802013,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.7553,
      "step": 9
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.9306841163645898,
      "learning_rate": 8.043807145043604e-06,
      "loss": 0.7046,
      "step": 10
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.8836238327982504,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.6762,
      "step": 11
    },
    {
      "epoch": 1.309090909090909,
      "grad_norm": 0.7923189991616242,
      "learning_rate": 6.913417161825449e-06,
      "loss": 0.6831,
      "step": 12
    },
    {
      "epoch": 1.4181818181818182,
      "grad_norm": 0.7775840291037229,
      "learning_rate": 6.294095225512604e-06,
      "loss": 0.6189,
      "step": 13
    },
    {
      "epoch": 1.5272727272727273,
      "grad_norm": 0.7910058984018784,
      "learning_rate": 5.65263096110026e-06,
      "loss": 0.6928,
      "step": 14
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.9216699601603215,
      "learning_rate": 5e-06,
      "loss": 0.7075,
      "step": 15
    },
    {
      "epoch": 1.7454545454545456,
      "grad_norm": 0.7353245591402325,
      "learning_rate": 4.347369038899744e-06,
      "loss": 0.59,
      "step": 16
    },
    {
      "epoch": 1.8545454545454545,
      "grad_norm": 0.7518643144678038,
      "learning_rate": 3.705904774487396e-06,
      "loss": 0.6566,
      "step": 17
    },
    {
      "epoch": 1.9636363636363636,
      "grad_norm": 0.7463216548494543,
      "learning_rate": 3.0865828381745515e-06,
      "loss": 0.6502,
      "step": 18
    },
    {
      "epoch": 2.0727272727272728,
      "grad_norm": 0.7235181727359761,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.5826,
      "step": 19
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.769932219907721,
      "learning_rate": 1.956192854956397e-06,
      "loss": 0.6651,
      "step": 20
    },
    {
      "epoch": 2.290909090909091,
      "grad_norm": 0.7616252077226875,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.5523,
      "step": 21
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.7373210083457005,
      "learning_rate": 1.0332332985438248e-06,
      "loss": 0.592,
      "step": 22
    },
    {
      "epoch": 2.509090909090909,
      "grad_norm": 0.6531623422131294,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.6052,
      "step": 23
    },
    {
      "epoch": 2.618181818181818,
      "grad_norm": 0.716885462935242,
      "learning_rate": 3.8060233744356634e-07,
      "loss": 0.6015,
      "step": 24
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.7300944307135169,
      "learning_rate": 1.7037086855465902e-07,
      "loss": 0.5736,
      "step": 25
    },
    {
      "epoch": 2.8363636363636364,
      "grad_norm": 0.6691712683426007,
      "learning_rate": 4.2775693130948094e-08,
      "loss": 0.5576,
      "step": 26
    },
    {
      "epoch": 2.9454545454545453,
      "grad_norm": 0.6510070355731671,
      "learning_rate": 0.0,
      "loss": 0.5451,
      "step": 27
    },
    {
      "epoch": 2.9454545454545453,
      "step": 27,
      "total_flos": 1.4475914574299136e+16,
      "train_loss": 0.6946969076439187,
      "train_runtime": 576.23,
      "train_samples_per_second": 4.503,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 1,
  "max_steps": 27,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4475914574299136e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}