{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 2,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 11935214993408.0,
      "learning_rate": 1e-05,
      "loss": 0.7163,
      "step": 1
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2096675946496.0,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.6972,
      "step": 2
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 0.5687638521194458,
      "eval_runtime": 0.2981,
      "eval_samples_per_second": 6.709,
      "eval_steps_per_second": 3.354,
      "step": 2
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 7390838128640.0,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.7795,
      "step": 3
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 3194177454080.0,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.6915,
      "step": 4
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 0.5684303045272827,
      "eval_runtime": 0.2966,
      "eval_samples_per_second": 6.743,
      "eval_steps_per_second": 3.371,
      "step": 4
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 131253493760.0,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.6744,
      "step": 5
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 491539005440.0,
      "learning_rate": 8.213938048432697e-06,
      "loss": 0.7911,
      "step": 6
    },
    {
      "epoch": 0.3157894736842105,
      "eval_loss": 0.5686608552932739,
      "eval_runtime": 0.2967,
      "eval_samples_per_second": 6.742,
      "eval_steps_per_second": 3.371,
      "step": 6
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 235763302400.0,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.5594,
      "step": 7
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 279532568576.0,
      "learning_rate": 6.710100716628345e-06,
      "loss": 0.7261,
      "step": 8
    },
    {
      "epoch": 0.42105263157894735,
      "eval_loss": 0.5699889063835144,
      "eval_runtime": 0.2966,
      "eval_samples_per_second": 6.744,
      "eval_steps_per_second": 3.372,
      "step": 8
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 175990996992.0,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.6122,
      "step": 9
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 10130321047552.0,
      "learning_rate": 5e-06,
      "loss": 0.86,
      "step": 10
    },
    {
      "epoch": 0.5263157894736842,
      "eval_loss": 0.568690836429596,
      "eval_runtime": 0.2978,
      "eval_samples_per_second": 6.715,
      "eval_steps_per_second": 3.358,
      "step": 10
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 3898177486848.0,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.7364,
      "step": 11
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 1318930219008.0,
      "learning_rate": 3.289899283371657e-06,
      "loss": 0.6903,
      "step": 12
    },
    {
      "epoch": 0.631578947368421,
      "eval_loss": 0.5691469311714172,
      "eval_runtime": 0.2973,
      "eval_samples_per_second": 6.728,
      "eval_steps_per_second": 3.364,
      "step": 12
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 137136914432.0,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.663,
      "step": 13
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 1604217339904.0,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.5994,
      "step": 14
    },
    {
      "epoch": 0.7368421052631579,
      "eval_loss": 0.5684089064598083,
      "eval_runtime": 0.2979,
      "eval_samples_per_second": 6.714,
      "eval_steps_per_second": 3.357,
      "step": 14
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 73108439040.0,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.7457,
      "step": 15
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 361255075840.0,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.7792,
      "step": 16
    },
    {
      "epoch": 0.8421052631578947,
      "eval_loss": 0.5695986747741699,
      "eval_runtime": 0.2976,
      "eval_samples_per_second": 6.72,
      "eval_steps_per_second": 3.36,
      "step": 16
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 222161354752.0,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.6121,
      "step": 17
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 4849853267968.0,
      "learning_rate": 7.59612349389599e-08,
      "loss": 0.7023,
      "step": 18
    },
    {
      "epoch": 0.9473684210526315,
      "eval_loss": 0.5688631534576416,
      "eval_runtime": 0.298,
      "eval_samples_per_second": 6.711,
      "eval_steps_per_second": 3.355,
      "step": 18
    },
    {
      "epoch": 1.0,
      "grad_norm": 994095661056.0,
      "learning_rate": 0.0,
      "loss": 0.7789,
      "step": 19
    },
    {
      "epoch": 1.0,
      "step": 19,
      "total_flos": 6341035089199104.0,
      "train_loss": 0.7060548631768477,
      "train_runtime": 53.6484,
      "train_samples_per_second": 2.759,
      "train_steps_per_second": 0.354
    }
  ],
  "logging_steps": 1,
  "max_steps": 19,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 19,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6341035089199104.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}