{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 0,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 1.663339614868164,
      "learning_rate": 1e-05,
      "loss": 5.9531,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 1.4756760597229004,
      "learning_rate": 9.944154131125643e-06,
      "loss": 5.3477,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.191918969154358,
      "learning_rate": 9.777864028930705e-06,
      "loss": 4.5273,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 1.6238677501678467,
      "learning_rate": 9.504844339512096e-06,
      "loss": 5.5703,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.4413729906082153,
      "learning_rate": 9.131193871579975e-06,
      "loss": 5.1211,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.4946938753128052,
      "learning_rate": 8.665259359149132e-06,
      "loss": 5.0664,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.5755618810653687,
      "learning_rate": 8.117449009293668e-06,
      "loss": 5.4727,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 1.6488808393478394,
      "learning_rate": 7.500000000000001e-06,
      "loss": 5.457,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.5335092544555664,
      "learning_rate": 6.8267051218319766e-06,
      "loss": 5.1816,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 1.3840856552124023,
      "learning_rate": 6.112604669781572e-06,
      "loss": 5.207,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 1.471366286277771,
      "learning_rate": 5.373650467932122e-06,
      "loss": 4.9531,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.246780514717102,
      "learning_rate": 4.626349532067879e-06,
      "loss": 4.6504,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 1.3924837112426758,
      "learning_rate": 3.887395330218429e-06,
      "loss": 4.9648,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.4361528158187866,
      "learning_rate": 3.173294878168025e-06,
      "loss": 5.0898,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.4786005020141602,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 5.1758,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.8507946729660034,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 5.9141,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 1.1421499252319336,
      "learning_rate": 1.3347406408508695e-06,
      "loss": 4.584,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.3540844917297363,
      "learning_rate": 8.688061284200266e-07,
      "loss": 4.7227,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 1.6656677722930908,
      "learning_rate": 4.951556604879049e-07,
      "loss": 5.3984,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.9267923831939697,
      "learning_rate": 2.2213597106929608e-07,
      "loss": 6.0957,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.2231636047363281,
      "learning_rate": 5.584586887435739e-08,
      "loss": 4.6309,
      "step": 21
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 21,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.974293630825267e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}