distilbert_sst5_padding50model – AI Model by Realgon | AlphaNeural AI

You can deploy this model and start earning money today!

Realgon/
distilbert_sst5_padding50model

like

0

text-classification

generated_from_trainer

distilbert/distilbert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

distilbert_sst5_padding50model

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: 4.0670
Accuracy: 0.5005

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
1.2884	1.0	534	1.3287	0.4136
1.0358	2.0	1068	1.1270	0.4986
0.8387	3.0	1602	1.1758	0.5145
0.6855	4.0	2136	1.3584	0.5127
0.5306	5.0	2670	1.5252	0.5077
0.3926	6.0	3204	1.8285	0.4896
0.3021	7.0	3738	1.9973	0.4973
0.2153	8.0	4272	2.2816	0.4986
0.1848	9.0	4806	2.4827	0.5005
0.1489	10.0	5340	2.8858	0.4955
0.1244	11.0	5874	3.1325	0.4946
0.1026	12.0	6408	3.1882	0.5113
0.0853	13.0	6942	3.5083	0.4991
0.0623	14.0	7476	3.6773	0.5081
0.0476	15.0	8010	3.7727	0.4995
0.0422	16.0	8544	3.8041	0.5072
0.0262	17.0	9078	3.9936	0.5009
0.0297	18.0	9612	4.0013	0.4964
0.021	19.0	10146	4.1473	0.5018
0.0222	20.0	10680	4.0670	0.5005

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3