{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 9980,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.22615130876182502,
      "eval_loss": 4.766125679016113,
      "eval_runtime": 6.8593,
      "eval_samples_per_second": 33.385,
      "eval_steps_per_second": 1.166,
      "step": 998
    },
    {
      "epoch": 1.002004008016032,
      "grad_norm": 11396.599609375,
      "learning_rate": 0.0005993999999999999,
      "loss": 1.2399,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.26749502217588594,
      "eval_loss": 4.338047504425049,
      "eval_runtime": 6.3687,
      "eval_samples_per_second": 35.957,
      "eval_steps_per_second": 1.256,
      "step": 1996
    },
    {
      "epoch": 2.004008016032064,
      "grad_norm": 10861.8779296875,
      "learning_rate": 0.0005332516703786191,
      "loss": 1.0378,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2781343200676813,
      "eval_loss": 4.19285249710083,
      "eval_runtime": 5.938,
      "eval_samples_per_second": 38.565,
      "eval_steps_per_second": 1.347,
      "step": 2994
    },
    {
      "epoch": 3.006012024048096,
      "grad_norm": 10864.8798828125,
      "learning_rate": 0.00046643652561247214,
      "loss": 0.9739,
      "step": 3000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.286568847793948,
      "eval_loss": 4.103455066680908,
      "eval_runtime": 6.2421,
      "eval_samples_per_second": 36.687,
      "eval_steps_per_second": 1.282,
      "step": 3992
    },
    {
      "epoch": 4.008016032064128,
      "grad_norm": 10894.2529296875,
      "learning_rate": 0.00039962138084632514,
      "loss": 0.9423,
      "step": 4000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.29784906724549004,
      "eval_loss": 4.001025676727295,
      "eval_runtime": 6.0982,
      "eval_samples_per_second": 37.552,
      "eval_steps_per_second": 1.312,
      "step": 4990
    },
    {
      "epoch": 5.01002004008016,
      "grad_norm": 11722.3232421875,
      "learning_rate": 0.00033280623608017814,
      "loss": 0.9155,
      "step": 5000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.30403609670224496,
      "eval_loss": 3.937136650085449,
      "eval_runtime": 6.0876,
      "eval_samples_per_second": 37.618,
      "eval_steps_per_second": 1.314,
      "step": 5988
    },
    {
      "epoch": 6.012024048096192,
      "grad_norm": 10417.4404296875,
      "learning_rate": 0.0002659910913140312,
      "loss": 0.8943,
      "step": 6000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3146412121108538,
      "eval_loss": 3.859510898590088,
      "eval_runtime": 6.1124,
      "eval_samples_per_second": 37.465,
      "eval_steps_per_second": 1.309,
      "step": 6986
    },
    {
      "epoch": 7.014028056112225,
      "grad_norm": 10313.73828125,
      "learning_rate": 0.00019917594654788416,
      "loss": 0.8736,
      "step": 7000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.32122988574504996,
      "eval_loss": 3.8007497787475586,
      "eval_runtime": 6.1187,
      "eval_samples_per_second": 37.426,
      "eval_steps_per_second": 1.307,
      "step": 7984
    },
    {
      "epoch": 8.016032064128256,
      "grad_norm": 9752.1123046875,
      "learning_rate": 0.00013236080178173718,
      "loss": 0.8539,
      "step": 8000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.32736564147702507,
      "eval_loss": 3.7534029483795166,
      "eval_runtime": 4.519,
      "eval_samples_per_second": 50.675,
      "eval_steps_per_second": 1.77,
      "step": 8982
    },
    {
      "epoch": 9.01803607214429,
      "grad_norm": 9999.22265625,
      "learning_rate": 6.554565701559019e-05,
      "loss": 0.8352,
      "step": 9000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.3312282620770986,
      "eval_loss": 3.730226755142212,
      "eval_runtime": 6.1123,
      "eval_samples_per_second": 37.465,
      "eval_steps_per_second": 1.309,
      "step": 9980
    },
    {
      "epoch": 10.0,
      "step": 9980,
      "total_flos": 8.34436104192e+16,
      "train_loss": 0.9392847890605429,
      "train_runtime": 9744.779,
      "train_samples_per_second": 32.771,
      "train_steps_per_second": 1.024
    }
  ],
  "logging_steps": 1000,
  "max_steps": 9980,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.34436104192e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}