Qwen-2.5-7B-Simple-RL-sequential / train_results.json
MatchaLwc's picture
Model save
f0b5245 verified
{
"total_flos": 0.0,
"train_loss": 1.2875895330618168,
"train_runtime": 16023.0623,
"train_samples": 7500,
"train_samples_per_second": 0.468,
"train_steps_per_second": 0.004
}