{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 92,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 1.8726082360074983,
      "learning_rate": 9.888278119998573e-06,
      "loss": 1.6731,
      "step": 10
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 1.005060254013473,
      "learning_rate": 9.223529979274411e-06,
      "loss": 1.3361,
      "step": 20
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.7598547309353446,
      "learning_rate": 8.037969601624495e-06,
      "loss": 1.0931,
      "step": 30
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.6120146086851695,
      "learning_rate": 6.477790894828422e-06,
      "loss": 0.9842,
      "step": 40
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.624439383060422,
      "learning_rate": 4.7353827293991845e-06,
      "loss": 0.8722,
      "step": 50
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.5877210574506252,
      "learning_rate": 3.0256050681470446e-06,
      "loss": 0.8083,
      "step": 60
    },
    {
      "epoch": 0.7671232876712328,
      "grad_norm": 0.5223729686194356,
      "learning_rate": 1.5592941387706562e-06,
      "loss": 0.8208,
      "step": 70
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.5974310506451916,
      "learning_rate": 5.172637815658583e-07,
      "loss": 0.7781,
      "step": 80
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 0.48379253622577745,
      "learning_rate": 2.8008919960090253e-08,
      "loss": 0.8185,
      "step": 90
    },
    {
      "epoch": 1.0,
      "step": 92,
      "total_flos": 3089409638400.0,
      "train_loss": 1.0096283658691074,
      "train_runtime": 1873.0809,
      "train_samples_per_second": 3.117,
      "train_steps_per_second": 0.049
    }
  ],
  "logging_steps": 10,
  "max_steps": 92,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3089409638400.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}