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 2e-3
Metric Val Test
BLEU 25.6 23.5
chrf++ 44.3 42.8
Downloads last month
8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support