mt5_fill_puntuation – AI Model by jamie613 | AlphaNeural AI

You can deploy this model and start earning money today!

jamie613/
mt5_fill_puntuation

like

0

text2text-generation

generated_from_trainer

endpoints_compatible

Views

No views yet

mt5_fill_puntuation

This model is a fine-tuned version of jamie613/mt5_fill_puntuation on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0717

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: 5e-05
train_batch_size: 5
eval_batch_size: 5
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.0918	0.04	500	0.0803
0.0894	0.07	1000	0.0773
0.0905	0.11	1500	0.0822
0.0908	0.15	2000	0.0833
0.0868	0.18	2500	0.0840
0.09	0.22	3000	0.0811
0.0868	0.26	3500	0.0735
0.0869	0.29	4000	0.0805
0.0874	0.33	4500	0.0742
0.088	0.37	5000	0.0749
0.0884	0.4	5500	0.0730
0.0861	0.44	6000	0.0749
0.0804	0.48	6500	0.0739
0.0845	0.51	7000	0.0717
0.0861	0.55	7500	0.0743
0.0812	0.59	8000	0.0726
0.0824	0.62	8500	0.0729
0.0836	0.66	9000	0.0751
0.079	0.7	9500	0.0731
0.0806	0.73	10000	0.0725
0.0798	0.77	10500	0.0749
0.0794	0.81	11000	0.0725
0.0795	0.84	11500	0.0726
0.0755	0.88	12000	0.0732
0.0815	0.92	12500	0.0722
0.0776	0.95	13000	0.0719
0.0838	0.99	13500	0.0717

Framework versions

Transformers 4.20.1
Pytorch 1.11.0+cu113
Datasets 2.3.2
Tokenizers 0.12.1