learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 100

Training Loss	Epoch	Step	Validation Loss	Chrf++	Gen Len
0.2321	1.9888	222	0.0651	88.2352	134.827
0.1476	3.9708	444	0.0689	88.5517	134.827
0.1137	5.9528	666	0.0740	88.8945	134.8674
0.0878	7.9348	888	0.0834	88.6376	136.3596
0.0656	9.9169	1110	0.0844	89.2557	133.7618
0.0508	11.8989	1332	0.0926	88.864	134.764
0.0464	13.8809	1554	0.0877	89.0326	132.9865
0.0452	15.8629	1776	0.0935	88.7379	133.2337

Tsedeniya/finetuned_glosslm_ddo_joint

finetuned_glosslm_ddo_joint