training_log.json

{
  "base_model_name": "jeiku_Rosa_v1_7B",
  "base_model_class": "MistralForCausalLM",
  "base_loaded_in_4bit": false,
  "base_loaded_in_8bit": false,
  "projections": "q, v",
  "loss": 2.093,
  "learning_rate": 0.0,
  "epoch": 9.8,
  "current_steps": 454,
  "train_runtime": 250.1064,
  "train_samples_per_second": 23.15,
  "train_steps_per_second": 0.06,
  "total_flos": 4.166767776419021e+16,
  "train_loss": 2.4269789377848308
}