Qwen2-0.5B-Instruct-ru-lora / train_results.json
sikoraaxd's picture
Qwen2-0.5B-Instruct-ru-lora
812a61a verified
raw
history blame
203 Bytes
{
"epoch": 1.0,
"total_flos": 5010632390737920.0,
"train_loss": 1.4269454736503766,
"train_runtime": 555.1964,
"train_samples_per_second": 2.003,
"train_steps_per_second": 0.501
}