You can deploy this model and start earning money today!

wsklee/
distilbert-sentiment-cft-v4

Name: distilbert-sentiment-cft-v4
Availability: InStock

transformers

safetensors

distilbert

generated_from_trainer

distilbert/distilbert-base-uncased

finetune

apache-2.0

endpoints_compatible

Views

No views yet

distilbert-sentiment-cft-v4

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Accuracy: 0.9864
Pos Similarity: 0.9042
Neg Similarity: 0.3333
Loss: 3.5894

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: 32
eval_batch_size: 32
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Accuracy	Pos Similarity	Neg Similarity	Validation Loss
3.985	0.5682	200	0.9424	0.9554	0.7178	3.6664
3.6933	1.1364	400	0.9752	0.9346	0.4884	3.6099
3.6154	1.7045	600	0.9832	0.9375	0.4936	3.5742
3.5592	2.2727	800	0.9840	0.9442	0.3908	3.5588
3.5271	2.8409	1000	0.9840	0.9446	0.4732	3.5334
3.4787	3.4091	1200	0.9872	0.9074	0.2974	3.6162
3.4715	3.9773	1400	0.9864	0.9202	0.3613	3.5610
3.4343	4.5455	1600	0.9864	0.9042	0.3333	3.5894

Framework versions

Transformers 4.46.2
Pytorch 2.5.1
Datasets 3.1.0
Tokenizers 0.20.3

wsklee/distilbert-sentiment-cft-v4

distilbert-sentiment-cft-v4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

wsklee/
distilbert-sentiment-cft-v4