Qwen2.5-0.5B-sft-lora-rel-therapy / train_results.json
adarksky's picture
Initial model upload
4627470 verified
raw
history blame contribute delete
248 Bytes
{
"epoch": 9.98120873539868,
"total_flos": 2.0218089447773184e+16,
"train_loss": 1.1380672057469685,
"train_runtime": 8182.6752,
"train_samples": 7876,
"train_samples_per_second": 9.625,
"train_steps_per_second": 0.601
}