Files
rta/all_results.json
ModelHub XC d1323322ae 初始化项目,由ModelHub XC社区提供模型
Model: babylm-anon/rta
Source: Original Platform
2026-06-05 15:06:17 +08:00

16 lines
494 B
JSON

{
"epoch": 9.728622631848438,
"eval_accuracy": 0.45214562944577746,
"eval_loss": 3.0628035068511963,
"eval_runtime": 95.1631,
"eval_samples": 33544,
"eval_samples_per_second": 352.49,
"eval_steps_per_second": 22.036,
"perplexity": 21.38743300660324,
"total_flos": 7.9413964701696e+16,
"train_loss": 2.775124670731394,
"train_runtime": 3271.669,
"train_samples": 31240,
"train_samples_per_second": 92.919,
"train_steps_per_second": 5.807
}