spell_correction_M04_verification – AI Model by monideep2255 | AlphaNeural AI

You can deploy this model and start earning money today!

monideep2255/
spell_correction_M04_verification

like

0

text2text-generation

generated_from_trainer

endpoints_compatible

Views

No views yet

spell_correction_M04_verification

This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0588

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	269	0.3070
1.8826	2.0	538	0.0769
1.8826	3.0	807	0.0592
0.0711	4.0	1076	0.0577
0.0711	5.0	1345	0.0563
0.04	6.0	1614	0.0562
0.04	7.0	1883	0.0560
0.0265	8.0	2152	0.0544
0.0265	9.0	2421	0.0540
0.0196	10.0	2690	0.0534
0.0196	11.0	2959	0.0548
0.015	12.0	3228	0.0552
0.015	13.0	3497	0.0578
0.0123	14.0	3766	0.0591
0.0116	15.0	4035	0.0578
0.0116	16.0	4304	0.0580
0.0091	17.0	4573	0.0592
0.0091	18.0	4842	0.0596
0.0088	19.0	5111	0.0605
0.0088	20.0	5380	0.0569
0.0074	21.0	5649	0.0598
0.0074	22.0	5918	0.0587
0.0078	23.0	6187	0.0589
0.0078	24.0	6456	0.0586
0.0068	25.0	6725	0.0588
0.0068	26.0	6994	0.0591
0.0076	27.0	7263	0.0590
0.0072	28.0	7532	0.0587
0.0072	29.0	7801	0.0587
0.0059	30.0	8070	0.0588

Framework versions

Transformers 4.28.0
Pytorch 1.12.1+cu102
Datasets 2.13.1
Tokenizers 0.13.3