{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003420352809392289,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.420352809392289e-05,
      "grad_norm": 1.608834147453308,
      "learning_rate": 2e-05,
      "loss": 2.8211,
      "step": 1
    },
    {
      "epoch": 3.420352809392289e-05,
      "eval_loss": 3.4762773513793945,
      "eval_runtime": 495.8449,
      "eval_samples_per_second": 12.415,
      "eval_steps_per_second": 12.415,
      "step": 1
    },
    {
      "epoch": 6.840705618784578e-05,
      "grad_norm": 1.8106151819229126,
      "learning_rate": 4e-05,
      "loss": 2.7652,
      "step": 2
    },
    {
      "epoch": 0.00010261058428176866,
      "grad_norm": 1.0310214757919312,
      "learning_rate": 6e-05,
      "loss": 2.0629,
      "step": 3
    },
    {
      "epoch": 0.00010261058428176866,
      "eval_loss": 3.469648838043213,
      "eval_runtime": 487.5743,
      "eval_samples_per_second": 12.626,
      "eval_steps_per_second": 12.626,
      "step": 3
    },
    {
      "epoch": 0.00013681411237569156,
      "grad_norm": 1.9326692819595337,
      "learning_rate": 8e-05,
      "loss": 2.6316,
      "step": 4
    },
    {
      "epoch": 0.00017101764046961444,
      "grad_norm": 1.1122183799743652,
      "learning_rate": 0.0001,
      "loss": 2.4229,
      "step": 5
    },
    {
      "epoch": 0.00020522116856353732,
      "grad_norm": 1.5624297857284546,
      "learning_rate": 0.00012,
      "loss": 2.8127,
      "step": 6
    },
    {
      "epoch": 0.00020522116856353732,
      "eval_loss": 3.4261391162872314,
      "eval_runtime": 486.5579,
      "eval_samples_per_second": 12.652,
      "eval_steps_per_second": 12.652,
      "step": 6
    },
    {
      "epoch": 0.00023942469665746023,
      "grad_norm": 1.452165126800537,
      "learning_rate": 0.00014,
      "loss": 2.7906,
      "step": 7
    },
    {
      "epoch": 0.00027362822475138313,
      "grad_norm": 0.8821212649345398,
      "learning_rate": 0.00016,
      "loss": 1.7472,
      "step": 8
    },
    {
      "epoch": 0.000307831752845306,
      "grad_norm": 1.6044913530349731,
      "learning_rate": 0.00018,
      "loss": 2.2277,
      "step": 9
    },
    {
      "epoch": 0.000307831752845306,
      "eval_loss": 3.3249192237854004,
      "eval_runtime": 490.1703,
      "eval_samples_per_second": 12.559,
      "eval_steps_per_second": 12.559,
      "step": 9
    },
    {
      "epoch": 0.0003420352809392289,
      "grad_norm": 2.75307559967041,
      "learning_rate": 0.0002,
      "loss": 3.7808,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1849565254778880.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}