training_log.json

{
  "base_model_name": "TheBloke_Llama-2-13B-fp16",
  "base_model_class": "LlamaForCausalLM",
  "base_loaded_in_4bit": false,
  "base_loaded_in_8bit": true,
  "projections": "q, v",
  "train_runtime": 4689.4141,
  "train_samples_per_second": 0.053,
  "train_steps_per_second": 0.001,
  "total_flos": 2.311238235193344e+16,
  "train_loss": 2.563081423441569,
  "epoch": 0.77,
  "current_steps": 95
}