Qwen-1.5B-SFT-OpenR1-LR_1e-5 / train_results.json
a-F1's picture
Model save
a064c79 verified
raw
history blame contribute delete
215 Bytes
{
"total_flos": 487866325008384.0,
"train_loss": 0.6497107633399022,
"train_runtime": 52834.4362,
"train_samples": 93733,
"train_samples_per_second": 10.372,
"train_steps_per_second": 0.648
}