Files
titulm-llama-3.2-1b-v2.0-In…/train_results.json

8 lines
218 B
JSON
Raw Normal View History

{
"epoch": 4.9965635738831615,
"total_flos": 96622779432960.0,
"train_loss": 1.8076569943592466,
"train_runtime": 4607.1316,
"train_samples_per_second": 12.617,
"train_steps_per_second": 0.126
}