DeepSeek-R1-7B-tuned / train_results.json
ZMC2019's picture
Model save
96e7624 verified
raw
history blame contribute delete
218 Bytes
{
"total_flos": 9.145616827248804e+17,
"train_loss": 0.3807801652267185,
"train_runtime": 28315.9454,
"train_samples": 93733,
"train_samples_per_second": 0.604,
"train_steps_per_second": 0.038
}