mistral_7b_0_3-coding-gpt4o-100k / train_results.json
chansung's picture
Model save
0af15ae verified
raw
history blame contribute delete
253 Bytes
{
"epoch": 9.992193598750976,
"total_flos": 8.968401612833817e+18,
"train_loss": 0.34100163986906407,
"train_runtime": 19497.7947,
"train_samples": 116368,
"train_samples_per_second": 10.509,
"train_steps_per_second": 0.328
}