Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("psj0919/bert-base-banking77-pt2_model_BertForSequenceClassification")
model = AutoModelForSequenceClassification.from_pretrained("psj0919/bert-base-banking77-pt2_model_BertForSequenceClassification", device_map="auto")Quick Links
bert-base-banking77-pt2_model_BertForSequenceClassification
This model is a fine-tuned version of bert-base-uncased on the banking77 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2937
- F1: 0.9327
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.1254 | 1.0 | 626 | 0.8005 | 0.8480 |
| 0.3798 | 2.0 | 1252 | 0.3632 | 0.9218 |
| 0.1754 | 3.0 | 1878 | 0.2937 | 0.9327 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.2.0.dev20231010+cu121
- Datasets 2.9.0
- Tokenizers 0.13.3
- Downloads last month
- 4
Dataset used to train psj0919/bert-base-banking77-pt2_model_BertForSequenceClassification
Evaluation results
- F1 on banking77test set self-reported0.933
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="psj0919/bert-base-banking77-pt2_model_BertForSequenceClassification")