{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6879999999999997,
  "eval_steps": 30,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.128,
      "grad_norm": 1.7210274934768677,
      "learning_rate": 2.857142857142857e-05,
      "loss": 10.176,
      "step": 1
    },
    {
      "epoch": 0.256,
      "grad_norm": 1.5320605039596558,
      "learning_rate": 2.7142857142857144e-05,
      "loss": 10.1016,
      "step": 2
    },
    {
      "epoch": 0.384,
      "grad_norm": 1.87909734249115,
      "learning_rate": 2.5714285714285714e-05,
      "loss": 10.1459,
      "step": 3
    },
    {
      "epoch": 0.512,
      "grad_norm": 1.8966753482818604,
      "learning_rate": 2.4285714285714288e-05,
      "loss": 10.0505,
      "step": 4
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.0056731700897217,
      "learning_rate": 2.2857142857142858e-05,
      "loss": 9.9816,
      "step": 5
    },
    {
      "epoch": 0.768,
      "grad_norm": 2.313743829727173,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 10.0497,
      "step": 6
    },
    {
      "epoch": 0.896,
      "grad_norm": 2.3521242141723633,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 10.0357,
      "step": 7
    },
    {
      "epoch": 1.024,
      "grad_norm": 2.3931469917297363,
      "learning_rate": 1.8571428571428572e-05,
      "loss": 9.918,
      "step": 8
    },
    {
      "epoch": 1.152,
      "grad_norm": 2.519587516784668,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 9.8211,
      "step": 9
    },
    {
      "epoch": 1.28,
      "grad_norm": 2.6767983436584473,
      "learning_rate": 1.5714285714285715e-05,
      "loss": 9.7817,
      "step": 10
    },
    {
      "epoch": 1.408,
      "grad_norm": 2.6999528408050537,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 9.6886,
      "step": 11
    },
    {
      "epoch": 1.536,
      "grad_norm": 3.005337953567505,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 9.6439,
      "step": 12
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 3.042705774307251,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 9.6661,
      "step": 13
    },
    {
      "epoch": 1.792,
      "grad_norm": 3.1823525428771973,
      "learning_rate": 9.999999999999999e-06,
      "loss": 9.5694,
      "step": 14
    },
    {
      "epoch": 1.92,
      "grad_norm": 3.1568336486816406,
      "learning_rate": 8.571428571428571e-06,
      "loss": 9.5277,
      "step": 15
    },
    {
      "epoch": 2.048,
      "grad_norm": 3.230482339859009,
      "learning_rate": 7.142857142857143e-06,
      "loss": 9.5726,
      "step": 16
    },
    {
      "epoch": 2.176,
      "grad_norm": 3.065131425857544,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 9.4275,
      "step": 17
    },
    {
      "epoch": 2.304,
      "grad_norm": 3.3117969036102295,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 9.4209,
      "step": 18
    },
    {
      "epoch": 2.432,
      "grad_norm": 3.5407657623291016,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 9.4978,
      "step": 19
    },
    {
      "epoch": 2.56,
      "grad_norm": 3.7619757652282715,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 9.4477,
      "step": 20
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 3.2933194637298584,
      "learning_rate": 0.0,
      "loss": 9.3319,
      "step": 21
    },
    {
      "epoch": 2.6879999999999997,
      "step": 21,
      "total_flos": 284409215227248.0,
      "train_loss": 9.75504275730678,
      "train_runtime": 2860.8048,
      "train_samples_per_second": 0.131,
      "train_steps_per_second": 0.007
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 21,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 284409215227248.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}