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_rand_50_v1_stsb")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/bert_base_rand_50_v1_stsb")Quick Links
bert_base_rand_50_v1_stsb
This model is a fine-tuned version of Hartunka/bert_base_rand_50_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2715
- Pearson: 0.2635
- Spearmanr: 0.2600
- Combined Score: 0.2618
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 |
|---|---|---|---|---|---|---|
| 3.0174 | 1.0 | 23 | 2.9030 | 0.0773 | 0.0674 | 0.0724 |
| 2.0319 | 2.0 | 46 | 2.4340 | 0.1690 | 0.1495 | 0.1593 |
| 1.7905 | 3.0 | 69 | 2.3889 | 0.2034 | 0.1918 | 0.1976 |
| 1.467 | 4.0 | 92 | 2.2715 | 0.2635 | 0.2600 | 0.2618 |
| 1.1681 | 5.0 | 115 | 2.4279 | 0.2436 | 0.2402 | 0.2419 |
| 1.0229 | 6.0 | 138 | 2.8679 | 0.2669 | 0.2723 | 0.2696 |
| 0.7645 | 7.0 | 161 | 2.5480 | 0.2725 | 0.2734 | 0.2730 |
| 0.6161 | 8.0 | 184 | 2.8213 | 0.2753 | 0.2854 | 0.2804 |
| 0.4918 | 9.0 | 207 | 2.5409 | 0.2620 | 0.2639 | 0.2630 |
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/bert_base_rand_50_v1_stsb
Base model
Hartunka/bert_base_rand_50_v1Dataset used to train Hartunka/bert_base_rand_50_v1_stsb
Evaluation results
- Spearmanr on GLUE STSBself-reported0.260
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/bert_base_rand_50_v1_stsb")