You can deploy this model and start earning money today!

dianamihalache27/
twitter-roberta-base_3epoch5

Name: twitter-roberta-base_3epoch5
Rating: 2.5 (8 reviews)

generated_from_trainer

cardiffnlp/twitter-roberta-base-irony

finetune

autotrain_compatible

endpoints_compatible

Views

No views yet

twitter-roberta-base_3epoch5

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

Loss: 1.7195
Accuracy: 0.7738
F1: 0.5341
Precision: 0.6522
Recall: 0.4523
Precision Sarcastic: 0.6522
Recall Sarcastic: 0.4523
F1 Sarcastic: 0.5341

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Precision Sarcastic	Recall Sarcastic	F1 Sarcastic
No log	1.0	174	1.9750	0.7695	0.4702	0.6893	0.3568	0.6893	0.3568	0.4702
No log	2.0	348	1.8774	0.7695	0.5062	0.656	0.4121	0.656	0.4121	0.5062
0.027	3.0	522	2.0072	0.7738	0.5016	0.6810	0.3970	0.6810	0.3970	0.5016
0.027	4.0	696	1.6484	0.7622	0.5299	0.6118	0.4673	0.6118	0.4673	0.5299
0.027	5.0	870	1.7195	0.7738	0.5341	0.6522	0.4523	0.6522	0.4523	0.5341

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

dianamihalache27/twitter-roberta-base_3epoch5

twitter-roberta-base_3epoch5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

dianamihalache27/
twitter-roberta-base_3epoch5