bertweet-base_3epoch5 – AI Model by dianamihalache27 | AlphaNeural AI

You can deploy this model and start earning money today!

dianamihalache27/
bertweet-base_3epoch5

like

0

text-classification

generated_from_trainer

vinai/bertweet-base

autotrain_compatible

endpoints_compatible

Views

No views yet

bertweet-base_3epoch5

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

Loss: 1.0827
Accuracy: 0.7464
F1: 0.4094
Precision: 0.6162
Recall: 0.3065
Precision Sarcastic: 0.6162
Recall Sarcastic: 0.3065
F1 Sarcastic: 0.4094

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Precision Sarcastic	Recall Sarcastic	F1 Sarcastic
No log	1.0	347	0.7068	0.7147	0.01	1.0	0.0050	1.0	0.0050	0.01
0.52	2.0	694	0.5626	0.7478	0.4957	0.5811	0.4322	0.5811	0.4322	0.4957
0.3534	3.0	1041	0.8067	0.7651	0.4475	0.6875	0.3317	0.6875	0.3317	0.4475
0.3534	4.0	1388	0.9764	0.7378	0.4709	0.5586	0.4070	0.5586	0.4070	0.4709
0.1664	5.0	1735	1.0827	0.7464	0.4094	0.6162	0.3065	0.6162	0.3065	0.4094

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1