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_rte")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_km_20_v1_rte")Quick Links
tiny_bert_km_20_v1_rte
This model is a fine-tuned version of Hartunka/tiny_bert_km_20_v1 on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.7018
- Accuracy: 0.5054
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 | Accuracy |
|---|---|---|---|---|
| 0.7014 | 1.0 | 10 | 0.7018 | 0.5054 |
| 0.6872 | 2.0 | 20 | 0.7078 | 0.4874 |
| 0.6752 | 3.0 | 30 | 0.7020 | 0.5054 |
| 0.6556 | 4.0 | 40 | 0.7178 | 0.4838 |
| 0.6267 | 5.0 | 50 | 0.7247 | 0.5343 |
| 0.5808 | 6.0 | 60 | 0.7734 | 0.4801 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Downloads last month
- 2
Model tree for Hartunka/tiny_bert_km_20_v1_rte
Base model
Hartunka/tiny_bert_km_20_v1Dataset used to train Hartunka/tiny_bert_km_20_v1_rte
Evaluation results
- Accuracy on GLUE RTEself-reported0.505
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_km_20_v1_rte")