mistral_gsm8k_sft_0 / train_results.json
weijie210's picture
Model save
782b2cf verified
raw
history blame contribute delete
193 Bytes
{
"epoch": 1.0,
"train_loss": 0.8949506086307567,
"train_runtime": 3207.9973,
"train_samples": 7273,
"train_samples_per_second": 2.267,
"train_steps_per_second": 0.142
}