learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
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
48.7577	1.95	78	2.5475	1.5622	188.7794
42.8632	3.9	156	2.2680	3.8267	174.1103
25.4418	5.85	234	1.9726	9.8447	69.7059
15.8853	7.8	312	1.7343	12.8467	63.0
15.8853	9.75	390	1.5931	15.3871	76.6103
9.1618	11.7	468	1.7401	13.6139	63.4632
5.1908	13.65	546	1.7250	15.5031	67.8088
3.1814	15.6	624	1.8031	15.0582	68.0294
2.2269	17.55	702	1.9544	14.0302	69.2574
2.2269	19.5	780	1.9020	15.7158	71.75
1.7093	21.45	858	2.3497	13.081	63.2059
0.8736	23.4	936	2.1892	16.0727	84.4265
0.5933	25.35	1014	2.2902	15.967	81.3676
0.5933	27.3	1092	2.4482	14.3712	70.1103
0.4890	29.25	1170	2.4014	15.2621	76.6397
0.3773	31.2	1248	2.4113	16.2256	97.4559
0.3456	33.15	1326	2.3849	14.5841	67.2132
0.3113	35.1	1404	2.4765	14.9839	70.6544
0.3113	37.05	1482	2.5203	14.8593	78.0294
0.2773	39.0	1560	2.7440	14.253	66.6985
0.2784	40.95	1638	2.6710	13.2348	59.8015
0.2584	42.9	1716	2.6858	13.7903	69.9044
0.2584	44.85	1794	2.7568	13.7125	79.3971
0.2362	46.8	1872	2.7122	12.8156	62.7794
0.2606	48.75	1950	2.7471	13.342	65.7279
0.2382	50.7	2028	2.8493	13.7868	72.3015
0.2144	52.65	2106	2.9971	12.142	69.4779
0.2144	54.6	2184	2.7501	13.5739	67.4191
0.2091	56.55	2262	2.9991	11.8738	56.9338
0.2165	58.5	2340	2.7530	12.3322	60.5441
0.2311	60.45	2418	2.7733	13.1964	80.625

Tsedeniya/finetuned_byT5large_per

finetuned_byT5large_per