Training setup
Num train steps 10000
Max seq len 256
Batch size 512
Total data points seen 5.1 mil
Total tokens seen 450 mil
Checkpoint step 9800
Learning rate 5e-4
Metric Val Test
BLEU 36.8 34.4
chrf++ 53.8 51.9
Downloads last month
4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support