metadata

tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: twitter-roberta-base-sentiment-latest-finetuned-FG-CONCAT_SENTENCE-H-NEWS
    results: []

twitter-roberta-base-sentiment-latest-finetuned-FG-CONCAT_SENTENCE-H-NEWS

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

Loss: 3.6335
Accuracy: 0.5275
F1: 0.5198

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: 6e-05
train_batch_size: 12
eval_batch_size: 12
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	61	1.0568	0.4396	0.2684
No log	2.0	122	1.0518	0.4396	0.2684
No log	3.0	183	1.0584	0.4396	0.2684
No log	4.0	244	1.1720	0.3956	0.3223
No log	5.0	305	1.2473	0.5275	0.5196
No log	6.0	366	1.0789	0.5220	0.5301
No log	7.0	427	1.3556	0.5604	0.5426
No log	8.0	488	1.7314	0.5330	0.5158
0.8045	9.0	549	2.2774	0.5330	0.5161
0.8045	10.0	610	2.8362	0.4451	0.4512
0.8045	11.0	671	2.9130	0.5275	0.4931
0.8045	12.0	732	3.1023	0.5110	0.5010
0.8045	13.0	793	3.2670	0.5385	0.5208
0.8045	14.0	854	3.4151	0.4945	0.4856
0.8045	15.0	915	3.7614	0.4615	0.4458
0.8045	16.0	976	3.5224	0.5220	0.5122
0.0535	17.0	1037	3.5196	0.5165	0.5102
0.0535	18.0	1098	3.5791	0.5110	0.5039
0.0535	19.0	1159	3.6220	0.5220	0.5137
0.0535	20.0	1220	3.6335	0.5275	0.5198

Framework versions

Transformers 4.16.2
Pytorch 1.9.1
Datasets 1.18.4
Tokenizers 0.11.6