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/bert_base_km_10_v2_stsb")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/bert_base_km_10_v2_stsb")Quick Links
bert_base_km_10_v2_stsb
This model is a fine-tuned version of Hartunka/bert_base_km_10_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2654
- Pearson: 0.2097
- Spearmanr: 0.1923
- Combined Score: 0.2010
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 |
|---|---|---|---|---|---|---|
| 2.711 | 1.0 | 23 | 2.3545 | 0.1112 | 0.1020 | 0.1066 |
| 1.9988 | 2.0 | 46 | 2.2654 | 0.2097 | 0.1923 | 0.2010 |
| 1.8048 | 3.0 | 69 | 2.2942 | 0.2306 | 0.2124 | 0.2215 |
| 1.5374 | 4.0 | 92 | 2.5475 | 0.2700 | 0.2536 | 0.2618 |
| 1.2573 | 5.0 | 115 | 2.6120 | 0.2696 | 0.2640 | 0.2668 |
| 0.9617 | 6.0 | 138 | 2.5692 | 0.2949 | 0.2881 | 0.2915 |
| 0.7474 | 7.0 | 161 | 2.6657 | 0.3060 | 0.3096 | 0.3078 |
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/bert_base_km_10_v2_stsb
Base model
Hartunka/bert_base_km_10_v2Dataset used to train Hartunka/bert_base_km_10_v2_stsb
Evaluation results
- Spearmanr on GLUE STSBself-reported0.192
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/bert_base_km_10_v2_stsb")