mistral_llama_2_code_math_4_full / train_results.json
CharlesLi's picture
Model save
7bb756d verified
raw
history blame contribute delete
227 Bytes
{
"epoch": 1.0,
"total_flos": 4763387166720.0,
"train_loss": 0.6139289477597112,
"train_runtime": 257.2977,
"train_samples": 7980,
"train_samples_per_second": 5.705,
"train_steps_per_second": 0.179
}