{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.175226586102719,
  "eval_steps": 500,
  "global_step": 464,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.02,
      "learning_rate": 2.4905660377358492e-05,
      "loss": 0.458,
      "step": 66
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.9811320754716985e-05,
      "loss": 0.15,
      "step": 132
    },
    {
      "epoch": 3.07,
      "learning_rate": 7.471698113207547e-05,
      "loss": 0.095,
      "step": 198
    },
    {
      "epoch": 4.1,
      "learning_rate": 9.962264150943397e-05,
      "loss": 0.0813,
      "step": 264
    },
    {
      "epoch": 5.12,
      "learning_rate": 9.727234578262695e-05,
      "loss": 0.0671,
      "step": 330
    },
    {
      "epoch": 6.15,
      "learning_rate": 9.450272765421738e-05,
      "loss": 0.0538,
      "step": 396
    },
    {
      "epoch": 7.17,
      "learning_rate": 9.173310952580781e-05,
      "loss": 0.0443,
      "step": 462
    }
  ],
  "logging_steps": 66,
  "max_steps": 2648,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "total_flos": 6.087184201285632e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}