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("tbochens/test-train")
model = AutoModelForSequenceClassification.from_pretrained("tbochens/test-train")Quick Links
test-train
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.7268
- Accuracy: 0.8456
- F1: 0.8927
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 459 | 0.3470 | 0.8627 | 0.9014 |
| 0.4987 | 2.0 | 918 | 0.5782 | 0.8382 | 0.8914 |
| 0.2796 | 3.0 | 1377 | 0.7268 | 0.8456 | 0.8927 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu102
- Datasets 1.17.0
- Tokenizers 0.10.3
- Downloads last month
- 1
Dataset used to train tbochens/test-train
Evaluation results
- Accuracy on glueself-reported0.846
- F1 on glueself-reported0.893
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tbochens/test-train")