mt5-small-qa_v2 – AI Model by hawalurahman | AlphaNeural AI

You can deploy this model and start earning money today!

hawalurahman/
mt5-small-qa_v2

like

0

text2text-generation

generated_from_trainer

google/mt5-small

endpoints_compatible

Views

No views yet

mt5-small-qa_v2

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.2125
Rouge1: 0.5208
Rouge2: 0.2949
Rougel: 0.5202
Rougelsum: 0.5205
Bleu: 0.3351
Exact Match: 0.3348

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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu	Exact Match
1.7588	1.0	2100	1.4601	0.3420	0.1933	0.3424	0.3422	0.2016	0.2021
1.0552	2.0	4200	1.2083	0.4771	0.2737	0.4769	0.4763	0.3043	0.2933
0.7895	3.0	6300	1.1997	0.5159	0.2966	0.5154	0.5158	0.3256	0.3190
0.6471	4.0	8400	1.1878	0.5197	0.2932	0.5194	0.5192	0.3322	0.3319
0.5584	5.0	10500	1.2125	0.5208	0.2949	0.5202	0.5205	0.3351	0.3348

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0