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
14.6163	0.2667	2	9.2468
14.5969	0.5333	4	9.2468
14.676	0.8	6	9.2468
14.5883	1.0	8	9.2468
14.6246	1.2667	10	9.2468
14.5945	1.5333	12	9.2468
14.6381	1.8	14	9.2468
14.5547	2.0	16	9.2468
12.8615	2.2667	18	9.2478
9.3963	2.5333	20	9.2486
13.8496	2.8	22	9.2491
9.2063	3.0	24	9.2487
6.4105	3.2667	26	9.2479
5.6432	3.5333	28	9.2472
5.2603	3.8	30	9.2459
4.8088	4.0	32	9.2440
4.5624	4.2667	34	9.2414
4.313	4.5333	36	9.2390
4.1646	4.8	38	9.2368
4.0837	5.0	40	9.2344
3.9956	5.2667	42	9.2319
3.9756	5.5333	44	9.2298
3.8652	5.8	46	9.2285
3.9191	6.0	48	9.2272
3.8893	6.2667	50	9.2251
3.8461	6.5333	52	9.2231
3.7788	6.8	54	9.2219
3.8249	7.0	56	9.2203
3.7855	7.2667	58	9.2183
3.7378	7.5333	60	9.2165
3.7678	7.8	62	9.2157
3.7418	8.0	64	9.2151
3.726	8.2667	66	9.2143
3.6778	8.5333	68	9.2134
3.7152	8.8	70	9.2129

Bhavyasree09/telugu-colloquial-translator

telugu-colloquial-translator