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/distilbert_rand_20_v2_stsb")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/distilbert_rand_20_v2_stsb")Quick Links
distilbert_rand_20_v2_stsb
This model is a fine-tuned version of Hartunka/distilbert_rand_20_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.3318
- Pearson: 0.3011
- Spearmanr: 0.2937
- Combined Score: 0.2974
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 |
|---|---|---|---|---|---|---|
| 2.8409 | 1.0 | 23 | 2.6483 | 0.1073 | 0.0837 | 0.0955 |
| 1.937 | 2.0 | 46 | 2.4296 | 0.1982 | 0.1718 | 0.1850 |
| 1.7127 | 3.0 | 69 | 2.4168 | 0.2334 | 0.2205 | 0.2270 |
| 1.3482 | 4.0 | 92 | 2.3318 | 0.3011 | 0.2937 | 0.2974 |
| 0.9691 | 5.0 | 115 | 2.5006 | 0.3014 | 0.2903 | 0.2959 |
| 0.7285 | 6.0 | 138 | 2.4679 | 0.3349 | 0.3254 | 0.3302 |
| 0.572 | 7.0 | 161 | 2.5069 | 0.3510 | 0.3474 | 0.3492 |
| 0.4434 | 8.0 | 184 | 2.4404 | 0.3636 | 0.3552 | 0.3594 |
| 0.3722 | 9.0 | 207 | 2.3603 | 0.3501 | 0.3421 | 0.3461 |
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/distilbert_rand_20_v2_stsb
Base model
Hartunka/distilbert_rand_20_v2Dataset used to train Hartunka/distilbert_rand_20_v2_stsb
Evaluation results
- Spearmanr on GLUE STSBself-reported0.294
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/distilbert_rand_20_v2_stsb")