{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0896,
  "eval_steps": 500,
  "global_step": 14000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032,
      "grad_norm": 1.7230606079101562,
      "learning_rate": 4.99208e-05,
      "loss": 1.2281,
      "step": 500
    },
    {
      "epoch": 0.0064,
      "grad_norm": 3.655383348464966,
      "learning_rate": 4.9840800000000006e-05,
      "loss": 0.7566,
      "step": 1000
    },
    {
      "epoch": 0.0096,
      "grad_norm": 1.2925927639007568,
      "learning_rate": 4.97608e-05,
      "loss": 0.6764,
      "step": 1500
    },
    {
      "epoch": 0.0128,
      "grad_norm": 1.286004900932312,
      "learning_rate": 4.968080000000001e-05,
      "loss": 0.6304,
      "step": 2000
    },
    {
      "epoch": 0.016,
      "grad_norm": 1.2140214443206787,
      "learning_rate": 4.96008e-05,
      "loss": 0.5981,
      "step": 2500
    },
    {
      "epoch": 0.0192,
      "grad_norm": 1.2525482177734375,
      "learning_rate": 4.95208e-05,
      "loss": 0.5767,
      "step": 3000
    },
    {
      "epoch": 0.0224,
      "grad_norm": 1.2310410737991333,
      "learning_rate": 4.94408e-05,
      "loss": 0.5597,
      "step": 3500
    },
    {
      "epoch": 0.0256,
      "grad_norm": 1.1735206842422485,
      "learning_rate": 4.9360800000000004e-05,
      "loss": 0.5418,
      "step": 4000
    },
    {
      "epoch": 0.0288,
      "grad_norm": 1.114688754081726,
      "learning_rate": 4.9280800000000004e-05,
      "loss": 0.5335,
      "step": 4500
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.8874593377113342,
      "learning_rate": 4.9200800000000005e-05,
      "loss": 0.5237,
      "step": 5000
    },
    {
      "epoch": 0.0352,
      "grad_norm": 1.1261299848556519,
      "learning_rate": 4.91208e-05,
      "loss": 0.5135,
      "step": 5500
    },
    {
      "epoch": 0.0384,
      "grad_norm": 0.9994556307792664,
      "learning_rate": 4.9040800000000007e-05,
      "loss": 0.5059,
      "step": 6000
    },
    {
      "epoch": 0.0416,
      "grad_norm": 1.2349673509597778,
      "learning_rate": 4.89608e-05,
      "loss": 0.4939,
      "step": 6500
    },
    {
      "epoch": 0.0448,
      "grad_norm": 0.9770995378494263,
      "learning_rate": 4.88808e-05,
      "loss": 0.4824,
      "step": 7000
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.981966495513916,
      "learning_rate": 4.88008e-05,
      "loss": 0.4875,
      "step": 7500
    },
    {
      "epoch": 0.0512,
      "grad_norm": 1.0177415609359741,
      "learning_rate": 4.87208e-05,
      "loss": 0.4785,
      "step": 8000
    },
    {
      "epoch": 0.0544,
      "grad_norm": 1.0521667003631592,
      "learning_rate": 4.8640800000000004e-05,
      "loss": 0.4731,
      "step": 8500
    },
    {
      "epoch": 0.0576,
      "grad_norm": 0.8560615181922913,
      "learning_rate": 4.85608e-05,
      "loss": 0.4633,
      "step": 9000
    },
    {
      "epoch": 0.0608,
      "grad_norm": 1.0170217752456665,
      "learning_rate": 4.8480800000000005e-05,
      "loss": 0.4576,
      "step": 9500
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.9891325831413269,
      "learning_rate": 4.84008e-05,
      "loss": 0.4556,
      "step": 10000
    },
    {
      "epoch": 0.0672,
      "grad_norm": 1.0609711408615112,
      "learning_rate": 4.832080000000001e-05,
      "loss": 0.4493,
      "step": 10500
    },
    {
      "epoch": 0.0704,
      "grad_norm": 0.8623799681663513,
      "learning_rate": 4.82408e-05,
      "loss": 0.4459,
      "step": 11000
    },
    {
      "epoch": 0.0736,
      "grad_norm": 0.9587870240211487,
      "learning_rate": 4.81608e-05,
      "loss": 0.4418,
      "step": 11500
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.8939447999000549,
      "learning_rate": 4.80808e-05,
      "loss": 0.4327,
      "step": 12000
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.9886033535003662,
      "learning_rate": 4.80008e-05,
      "loss": 0.438,
      "step": 12500
    },
    {
      "epoch": 0.0832,
      "grad_norm": 0.9157513976097107,
      "learning_rate": 4.7920800000000004e-05,
      "loss": 0.4323,
      "step": 13000
    },
    {
      "epoch": 0.0864,
      "grad_norm": 0.9085854887962341,
      "learning_rate": 4.7840800000000005e-05,
      "loss": 0.4303,
      "step": 13500
    },
    {
      "epoch": 0.0896,
      "grad_norm": 0.9123984575271606,
      "learning_rate": 4.77608e-05,
      "loss": 0.4247,
      "step": 14000
    }
  ],
  "logging_steps": 500,
  "max_steps": 312500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 6.820328374272e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}