{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001313010843281214,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.3767028109373806e-05,
      "eval_loss": NaN,
      "eval_runtime": 574.1566,
      "eval_samples_per_second": 16.757,
      "eval_steps_per_second": 8.379,
      "step": 1
    },
    {
      "epoch": 0.0001313010843281214,
      "grad_norm": 6.389786720275879,
      "learning_rate": 6e-05,
      "loss": 5.1832,
      "step": 3
    },
    {
      "epoch": 0.0002626021686562428,
      "grad_norm": 12.411738395690918,
      "learning_rate": 0.00012,
      "loss": 5.8454,
      "step": 6
    },
    {
      "epoch": 0.00035013622487499045,
      "eval_loss": NaN,
      "eval_runtime": 575.616,
      "eval_samples_per_second": 16.714,
      "eval_steps_per_second": 8.358,
      "step": 8
    },
    {
      "epoch": 0.0003939032529843642,
      "grad_norm": 8.358622550964355,
      "learning_rate": 0.00018,
      "loss": 5.2012,
      "step": 9
    },
    {
      "epoch": 0.0005252043373124856,
      "grad_norm": 23.96495246887207,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.6261,
      "step": 12
    },
    {
      "epoch": 0.000656505421640607,
      "grad_norm": 223.2547607421875,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.8547,
      "step": 15
    },
    {
      "epoch": 0.0007002724497499809,
      "eval_loss": NaN,
      "eval_runtime": 575.3241,
      "eval_samples_per_second": 16.723,
      "eval_steps_per_second": 8.362,
      "step": 16
    },
    {
      "epoch": 0.0007878065059687284,
      "grad_norm": 26.633174896240234,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.0006,
      "step": 18
    },
    {
      "epoch": 0.0009191075902968499,
      "grad_norm": 12.103179931640625,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.3108,
      "step": 21
    },
    {
      "epoch": 0.0010504086746249712,
      "grad_norm": 6.6597771644592285,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.0378,
      "step": 24
    },
    {
      "epoch": 0.0010504086746249712,
      "eval_loss": NaN,
      "eval_runtime": 575.268,
      "eval_samples_per_second": 16.724,
      "eval_steps_per_second": 8.363,
      "step": 24
    },
    {
      "epoch": 0.0011817097589530926,
      "grad_norm": 10.91389274597168,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.5704,
      "step": 27
    },
    {
      "epoch": 0.001313010843281214,
      "grad_norm": 6.193813800811768,
      "learning_rate": 0.0,
      "loss": 2.1611,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2698605370540032.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}