learning_rate: 0.0003
train_batch_size: 4
eval_batch_size: 4
seed: 42
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: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
No log	0.4	2	8.7783
No log	0.8	4	8.7783
No log	1.2	6	8.7783
No log	1.6	8	8.7783
No log	2.0	10	8.7783
No log	2.4	12	8.7783
No log	2.8	14	8.7783
No log	3.2	16	8.7783
No log	3.6	18	8.7783
No log	4.0	20	8.7783
No log	4.4	22	8.7783
No log	4.8	24	8.7783
No log	5.2	26	8.7783
No log	5.6	28	8.7783
No log	6.0	30	8.7783
No log	6.4	32	8.7783
No log	6.8	34	8.7783
No log	7.2	36	8.7783
No log	7.6	38	8.7783
No log	8.0	40	8.7783
No log	8.4	42	8.7783
No log	8.8	44	8.7783
No log	9.2	46	8.7783
No log	9.6	48	8.7783
No log	10.0	50	8.7783

srilekha27/english-telugu-colloquial-translator

english-telugu-colloquial-translator