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 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
3.0812	1.9941	420	0.4395	53.4455	33.5321
1.2481	3.9845	840	0.2439	68.2833	36.6101
0.5980	5.9750	1260	0.2333	74.0715	37.4358
0.3184	7.9655	1680	0.2656	74.7345	37.445
0.2239	9.9560	2100	0.2351	77.5073	37.6422
0.1788	11.9465	2520	0.3110	74.8554	37.0
0.1477	13.9370	2940	0.2845	77.1494	37.3853
0.1343	15.9275	3360	0.2478	78.0687	37.3119
0.1266	17.9180	3780	0.2438	78.2725	39.3716
0.1301	19.9084	4200	0.2342	77.3823	37.2248
0.1299	21.8989	4620	0.2580	79.0047	37.367
0.1243	23.8894	5040	0.3013	75.2974	37.5734
0.1282	25.8799	5460	0.5167	74.9527	37.2982
0.1245	27.8704	5880	0.3371	74.6308	36.5459

Tsedeniya/finetuned_glosslm_ain

finetuned_glosslm_ain