distilbert-base-uncased-finetuned_emotion – AI Model by Kyuyun | AlphaNeural AI

You can deploy this model and start earning money today!

Kyuyun/
distilbert-base-uncased-finetuned_emotion

like

0

text-classification

generated_from_trainer

distilbert/distilbert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

distilbert-base-uncased-finetuned_emotion

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

Loss: 0.2683
Accuracy: 0.9445
F1: 0.9445

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.0629	1.0	250	0.1692	0.9375	0.9376
0.0427	2.0	500	0.1811	0.939	0.9394
0.0282	3.0	750	0.2094	0.945	0.9452
0.0388	4.0	1000	0.2002	0.938	0.9381
0.0264	5.0	1250	0.2197	0.9415	0.9418
0.0214	6.0	1500	0.2363	0.9425	0.9426
0.0167	7.0	1750	0.2517	0.9445	0.9445
0.0125	8.0	2000	0.2599	0.9415	0.9416
0.0106	9.0	2250	0.2683	0.945	0.9452
0.0093	10.0	2500	0.2683	0.9445	0.9445

Framework versions

Transformers 4.43.1
Pytorch 2.2.2+cu118
Datasets 2.20.0
Tokenizers 0.19.1