qwen2.5-14B-scipy-lora / all_results.json
zgce's picture
Upload 12 files
c34aa36 verified
raw
history blame contribute delete
262 Bytes
{
"epoch": 0.9997864616698697,
"num_input_tokens_seen": 74083488,
"total_flos": 4.6864422704480256e+17,
"train_loss": 0.692321076499046,
"train_runtime": 65496.9949,
"train_samples_per_second": 1.144,
"train_steps_per_second": 0.036
}