Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("EmincanY/bert-base-cased")
model = AutoModelForSequenceClassification.from_pretrained("EmincanY/bert-base-cased")Quick Links
bert-base-cased
This model was trained from scratch on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.0491
- Matthews Correlation: 0.5758
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: 2e-06
- 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 | Matthews Correlation |
|---|---|---|---|---|
| 0.1532 | 1.0 | 535 | 0.9255 | 0.5757 |
| 0.1194 | 2.0 | 1070 | 0.9947 | 0.5653 |
| 0.098 | 3.0 | 1605 | 0.9838 | 0.5771 |
| 0.0915 | 4.0 | 2140 | 1.0381 | 0.5758 |
| 0.0857 | 5.0 | 2675 | 1.0491 | 0.5758 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 3
Dataset used to train EmincanY/bert-base-cased
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.576
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="EmincanY/bert-base-cased")