Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Hartunka/tiny_bert_km_20_v1_cola")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_km_20_v1_cola")Quick Links
tiny_bert_km_20_v1_cola
This model is a fine-tuned version of Hartunka/tiny_bert_km_20_v1 on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6210
- Matthews Correlation: 0.0
- Accuracy: 0.6913
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: 256
- eval_batch_size: 256
- seed: 10
- 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation | Accuracy |
|---|---|---|---|---|---|
| 0.6189 | 1.0 | 34 | 0.6210 | 0.0 | 0.6913 |
| 0.6054 | 2.0 | 68 | 0.6222 | 0.0 | 0.6913 |
| 0.5963 | 3.0 | 102 | 0.6258 | -0.0293 | 0.6894 |
| 0.5762 | 4.0 | 136 | 0.6421 | 0.0071 | 0.6587 |
| 0.5409 | 5.0 | 170 | 0.6646 | 0.0571 | 0.6807 |
| 0.4934 | 6.0 | 204 | 0.7105 | 0.0380 | 0.6453 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Downloads last month
- 3
Model tree for Hartunka/tiny_bert_km_20_v1_cola
Base model
Hartunka/tiny_bert_km_20_v1Dataset used to train Hartunka/tiny_bert_km_20_v1_cola
Evaluation results
- Matthews Correlation on GLUE COLAself-reported0.000
- Accuracy on GLUE COLAself-reported0.691
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_km_20_v1_cola")