Files
d1_science_gpt_0.3k/train_results.json

8 lines
207 B
JSON
Raw Normal View History

{
"epoch": 13.0,
"total_flos": 3.2858174247665664e+16,
"train_loss": 0.2939408891905959,
"train_runtime": 1300.2962,
"train_samples_per_second": 3.159,
"train_steps_per_second": 0.1
}