bert-finetuned-sst2

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

• Loss: 0.3812
• Accuracy: 0.9083

Load model directly

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("execbat/bert-finetuned-sst2")
model = AutoModelForSequenceClassification.from_pretrained("execbat/bert-finetuned-sst2")

Use a pipeline as a high-level helper

from transformers import pipeline

label_tags = {'LABEL_0' : "NEGATIVE",
             'LABEL_1' : "POSITIVE"}

pipe = pipeline("text-classification", model="execbat/bert-finetuned-sst2")
result = pipe(["what a horrible day!", "what a wonderfull day!"])
encoded_result = [label_tags[i["label"]] for i in result]
print(encoded_result)

['NEGATIVE', 'POSITIVE']

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.269	1.0	8419	0.5041	0.8716
0.1854	2.0	16838	0.4296	0.8968
0.0993	3.0	25257	0.3812	0.9083

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0
• Datasets 3.3.2
• Tokenizers 0.21.0