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_v2_sst2")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_km_20_v2_sst2")Quick Links
tiny_bert_km_20_v2_sst2
This model is a fine-tuned version of Hartunka/tiny_bert_km_20_v2 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4649
- Accuracy: 0.7833
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 |
|---|---|---|---|---|
| 0.448 | 1.0 | 264 | 0.4649 | 0.7833 |
| 0.249 | 2.0 | 528 | 0.5035 | 0.7890 |
| 0.1908 | 3.0 | 792 | 0.5273 | 0.8050 |
| 0.1571 | 4.0 | 1056 | 0.5578 | 0.7844 |
| 0.1298 | 5.0 | 1320 | 0.6701 | 0.7856 |
| 0.1096 | 6.0 | 1584 | 0.7886 | 0.7695 |
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_v2_sst2
Base model
Hartunka/tiny_bert_km_20_v2Dataset used to train Hartunka/tiny_bert_km_20_v2_sst2
Evaluation results
- Accuracy on GLUE SST2self-reported0.783
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_km_20_v2_sst2")