distilbert_sst5_padding10model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
distilbert_sst5_padding10model

like

0

text-classification

generated_from_trainer

distilbert/distilbert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

distilbert_sst5_padding10model

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 4.0781
Accuracy: 0.5036

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: 2e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2838	1.0	534	1.2476	0.4281
1.0188	2.0	1068	1.1170	0.5231
0.8166	3.0	1602	1.2120	0.5131
0.6648	4.0	2136	1.3360	0.5172
0.501	5.0	2670	1.6498	0.4896
0.3858	6.0	3204	1.7835	0.5023
0.2878	7.0	3738	2.0075	0.5063
0.2136	8.0	4272	2.1988	0.4982
0.1796	9.0	4806	2.4884	0.5086
0.1443	10.0	5340	2.8428	0.4946
0.1189	11.0	5874	3.0841	0.4923
0.096	12.0	6408	3.2575	0.5041
0.0774	13.0	6942	3.5018	0.4977
0.064	14.0	7476	3.6108	0.5086
0.0469	15.0	8010	3.7317	0.5054
0.0364	16.0	8544	3.9036	0.4923
0.0292	17.0	9078	3.9546	0.5036
0.0244	18.0	9612	4.0218	0.5054
0.0256	19.0	10146	4.0257	0.5068
0.021	20.0	10680	4.0781	0.5036

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3