{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.100418410041841,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033472803347280333,
      "eval_loss": 2.7768068313598633,
      "eval_runtime": 26.3797,
      "eval_samples_per_second": 4.776,
      "eval_steps_per_second": 2.388,
      "step": 1
    },
    {
      "epoch": 0.0100418410041841,
      "grad_norm": 0.8868265748023987,
      "learning_rate": 6e-05,
      "loss": 11.1003,
      "step": 3
    },
    {
      "epoch": 0.0200836820083682,
      "grad_norm": 1.2802834510803223,
      "learning_rate": 0.00012,
      "loss": 11.1195,
      "step": 6
    },
    {
      "epoch": 0.026778242677824266,
      "eval_loss": 2.699099063873291,
      "eval_runtime": 26.0773,
      "eval_samples_per_second": 4.832,
      "eval_steps_per_second": 2.416,
      "step": 8
    },
    {
      "epoch": 0.0301255230125523,
      "grad_norm": 2.6453027725219727,
      "learning_rate": 0.00018,
      "loss": 10.9085,
      "step": 9
    },
    {
      "epoch": 0.0401673640167364,
      "grad_norm": 3.5189645290374756,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.7948,
      "step": 12
    },
    {
      "epoch": 0.0502092050209205,
      "grad_norm": 2.799543857574463,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.5927,
      "step": 15
    },
    {
      "epoch": 0.05355648535564853,
      "eval_loss": 2.6082403659820557,
      "eval_runtime": 26.4424,
      "eval_samples_per_second": 4.765,
      "eval_steps_per_second": 2.383,
      "step": 16
    },
    {
      "epoch": 0.0602510460251046,
      "grad_norm": 2.3582141399383545,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.6795,
      "step": 18
    },
    {
      "epoch": 0.07029288702928871,
      "grad_norm": 2.2527294158935547,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.5256,
      "step": 21
    },
    {
      "epoch": 0.0803347280334728,
      "grad_norm": 2.0313010215759277,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.2404,
      "step": 24
    },
    {
      "epoch": 0.0803347280334728,
      "eval_loss": 2.5820364952087402,
      "eval_runtime": 25.7551,
      "eval_samples_per_second": 4.892,
      "eval_steps_per_second": 2.446,
      "step": 24
    },
    {
      "epoch": 0.09037656903765691,
      "grad_norm": 2.1284682750701904,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 10.0193,
      "step": 27
    },
    {
      "epoch": 0.100418410041841,
      "grad_norm": 2.1313133239746094,
      "learning_rate": 0.0,
      "loss": 10.319,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9818930738626560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}