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_stsb")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_km_20_v2_stsb")Quick Links
tiny_bert_km_20_v2_stsb
This model is a fine-tuned version of Hartunka/tiny_bert_km_20_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2511
- Pearson: 0.0929
- Spearmanr: 0.0866
- Combined Score: 0.0898
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 | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 3.587 | 1.0 | 23 | 2.2511 | 0.0929 | 0.0866 | 0.0898 |
| 2.048 | 2.0 | 46 | 2.4803 | 0.1373 | 0.1285 | 0.1329 |
| 1.919 | 3.0 | 69 | 2.3695 | 0.1598 | 0.1517 | 0.1558 |
| 1.8084 | 4.0 | 92 | 2.4825 | 0.2266 | 0.2217 | 0.2241 |
| 1.6039 | 5.0 | 115 | 2.5224 | 0.2052 | 0.2036 | 0.2044 |
| 1.3938 | 6.0 | 138 | 2.4211 | 0.2662 | 0.2640 | 0.2651 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Downloads last month
- 1
Model tree for Hartunka/tiny_bert_km_20_v2_stsb
Base model
Hartunka/tiny_bert_km_20_v2Dataset used to train Hartunka/tiny_bert_km_20_v2_stsb
Evaluation results
- Spearmanr on GLUE STSBself-reported0.087
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_km_20_v2_stsb")