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_100_v1_stsb")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/bert_base_rand_100_v1_stsb")Quick Links
bert_base_rand_100_v1_stsb
This model is a fine-tuned version of Hartunka/bert_base_rand_100_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2721
- Pearson: 0.1714
- Spearmanr: 0.1465
- Combined Score: 0.1590
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 |
|---|---|---|---|---|---|---|
| 2.928 | 1.0 | 23 | 2.4646 | 0.0973 | 0.0902 | 0.0937 |
| 1.9606 | 2.0 | 46 | 2.2721 | 0.1714 | 0.1465 | 0.1590 |
| 1.6768 | 3.0 | 69 | 2.3989 | 0.2291 | 0.2257 | 0.2274 |
| 1.3265 | 4.0 | 92 | 2.4733 | 0.2693 | 0.2725 | 0.2709 |
| 1.0076 | 5.0 | 115 | 2.8602 | 0.2450 | 0.2457 | 0.2454 |
| 0.7949 | 6.0 | 138 | 2.7485 | 0.2606 | 0.2643 | 0.2624 |
| 0.626 | 7.0 | 161 | 2.5590 | 0.2792 | 0.2811 | 0.2801 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Downloads last month
- 4
Model tree for Hartunka/bert_base_rand_100_v1_stsb
Base model
Hartunka/bert_base_rand_100_v1Dataset used to train Hartunka/bert_base_rand_100_v1_stsb
Evaluation results
- Spearmanr on GLUE STSBself-reported0.146
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/bert_base_rand_100_v1_stsb")