You can deploy this model and start earning money today!

Rizzz10/
english-telugu-colloquial-translator

Name: english-telugu-colloquial-translator
Availability: InStock

Views

No views yet

english-telugu-colloquial-translator

This model is a fine-tuned version of AI4Bharat/indic-bert on the None dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

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
0.3418	0.2667	2	0.3626
0.3448	0.5333	4	0.3438
0.4101	0.8	6	0.3329
0.1544	1.0	8	0.3248
0.3081	1.2667	10	0.3185
0.3086	1.5333	12	0.3130
0.303	1.8	14	0.3081
0.1693	2.0	16	0.3026
0.2908	2.2667	18	0.2971
0.3024	2.5333	20	0.2912
0.3063	2.8	22	0.2846
0.1373	3.0	24	0.2776
0.2709	3.2667	26	0.2702
0.2673	3.5333	28	0.2623
0.2528	3.8	30	0.2530
0.1211	4.0	32	0.2432
0.2385	4.2667	34	0.2333
0.2459	4.5333	36	0.2235
0.2108	4.8	38	0.2136
0.099	5.0	40	0.2038
0.1906	5.2667	42	0.1939
0.1844	5.5333	44	0.1837
0.1821	5.8	46	0.1733
0.0763	6.0	48	0.1632
0.1608	6.2667	50	0.1538
0.1488	6.5333	52	0.1456
0.1335	6.8	54	0.1385
0.0664	7.0	56	0.1325
0.1298	7.2667	58	0.1274
0.1424	7.5333	60	0.1228
0.1161	7.8	62	0.1191
0.0564	8.0	64	0.1162
0.1103	8.2667	66	0.1141
0.1096	8.5333	68	0.1127
0.1113	8.8	70	0.1121