bert_sentiment_trainer – AI Model by dhanushbitra | AlphaNeural AI

You can deploy this model and start earning money today!

dhanushbitra/
bert_sentiment_trainer

like

0

text-classification

generated_from_trainer

google-bert/bert-base-cased

autotrain_compatible

endpoints_compatible

Views

No views yet

bert_sentiment_trainer

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

Loss: 0.5985
Accuracy: 0.8947

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: 2.754984679344267e-05
train_batch_size: 16
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4398	0.33	250	0.4395	0.8427
0.4888	0.65	500	0.4044	0.8466
0.3046	0.98	750	0.3619	0.8778
0.2825	1.3	1000	0.3664	0.8824
0.2357	1.63	1250	0.3898	0.8775
0.2887	1.95	1500	0.3673	0.8856
0.1013	2.28	1750	0.4906	0.8814
0.1938	2.6	2000	0.5679	0.8697
0.1344	2.93	2250	0.4986	0.8791
0.1249	3.25	2500	0.6146	0.8830
0.0943	3.58	2750	0.6913	0.8788
0.1291	3.9	3000	0.5985	0.8947

Framework versions

Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2