{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 3,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10526315789473684,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": NaN,
      "eval_runtime": 1.6149,
      "eval_samples_per_second": 3.096,
      "eval_steps_per_second": 1.238,
      "step": 1
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.3157894736842105,
      "eval_loss": NaN,
      "eval_runtime": 1.1105,
      "eval_samples_per_second": 4.502,
      "eval_steps_per_second": 1.801,
      "step": 3
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": NaN,
      "learning_rate": 9.874639560909118e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.631578947368421,
      "eval_loss": NaN,
      "eval_runtime": 1.1106,
      "eval_samples_per_second": 4.502,
      "eval_steps_per_second": 1.801,
      "step": 6
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": NaN,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": NaN,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": NaN,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.9473684210526315,
      "eval_loss": NaN,
      "eval_runtime": 1.1101,
      "eval_samples_per_second": 4.504,
      "eval_steps_per_second": 1.802,
      "step": 9
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": NaN,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": NaN,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.263157894736842,
      "eval_loss": NaN,
      "eval_runtime": 1.1098,
      "eval_samples_per_second": 4.505,
      "eval_steps_per_second": 1.802,
      "step": 12
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": NaN,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": NaN,
      "learning_rate": 2.83058130441221e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": NaN,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.5789473684210527,
      "eval_loss": NaN,
      "eval_runtime": 1.1117,
      "eval_samples_per_second": 4.498,
      "eval_steps_per_second": 1.799,
      "step": 15
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": NaN,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": NaN,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": NaN,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.8947368421052633,
      "eval_loss": NaN,
      "eval_runtime": 1.1108,
      "eval_samples_per_second": 4.501,
      "eval_steps_per_second": 1.8,
      "step": 18
    },
    {
      "epoch": 2.0,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 19
    }
  ],
  "logging_steps": 1,
  "max_steps": 19,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3365335990206464e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}