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 8800
Learning rate 3e-4
Metric Val Test
BLEU 30.0 27.3
chrf++ 48.2 46.3
Downloads last month
10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support