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
3.1474	1.9967	840	0.3891	52.9998	38.0459
1.0776	3.9920	1680	0.3024	70.1531	37.9037
0.6590	5.9872	2520	0.2779	71.9695	37.4404
0.5623	7.9825	3360	0.2333	72.2824	41.4128
0.5351	9.9777	4200	0.2292	74.2861	40.9771
0.5165	11.9729	5040	0.3557	73.4879	39.0183
0.4939	13.9682	5880	0.2904	74.3393	37.6972
0.5855	15.9634	6720	0.3440	68.2892	40.1284
0.5339	17.9587	7560	0.3757	69.3906	44.633
0.5448	19.9539	8400	0.3809	73.2249	37.1009

Tsedeniya/finetuned_byT5large_ain

finetuned_byT5large_ain