Safetensors
modernbert
SparseModernBERT-alpha1.5 / train_results.json
mtreviso's picture
Upload SparseModernBERT α=1.5 checkpoints
7fb25b6
Raw History Blame Contribute Delete
231 Bytes
{
"epoch": 1.0,
"total_flos": 1.0909051256832e+18,
"train_loss": 1.0107983074951172,
"train_runtime": 153234.8237,
"train_samples": 0,
"train_samples_per_second": 1.305,
"train_steps_per_second": 0.653
}