learning_rate: 0.0003
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
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
lr_scheduler_warmup_steps: 2
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
15.4233	0.3636	2	7.9121
13.0588	0.7273	4	7.9121
8.4646	1.0	6	7.9121
4.474	1.3636	8	3.3942
1.7662	1.7273	10	0.6550
0.7863	2.0	12	0.5941
1.1458	2.3636	14	0.5240
0.8619	2.7273	16	0.4977
0.7108	3.0	18	0.4929
0.8382	3.3636	20	0.4984
0.5416	3.7273	22	0.4854
0.2726	4.0	24	0.4787
0.4561	4.3636	26	0.4806
0.5203	4.7273	28	0.4890
0.233	5.0	30	0.4989
0.4509	5.3636	32	0.4978
0.3384	5.7273	34	0.4999
0.1781	6.0	36	0.5054
0.3225	6.3636	38	0.5101
0.2737	6.7273	40	0.5159
0.0695	7.0	42	0.5239
0.2417	7.3636	44	0.5263
0.3237	7.7273	46	0.5253
0.1458	8.0	48	0.5249
0.2153	8.3636	50	0.5252

Waghya/english-marathi-colloquial-translator1

english-marathi-colloquial-translator1