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_5_v2_stsb")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/distilbert_rand_5_v2_stsb")Quick Links
distilbert_rand_5_v2_stsb
This model is a fine-tuned version of Hartunka/distilbert_rand_5_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2658
- Pearson: 0.2859
- Spearmanr: 0.2725
- Combined Score: 0.2792
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 |
|---|---|---|---|---|---|---|
| 2.6404 | 1.0 | 23 | 2.4147 | 0.1257 | 0.1083 | 0.1170 |
| 1.8953 | 2.0 | 46 | 2.4776 | 0.2028 | 0.1802 | 0.1915 |
| 1.6258 | 3.0 | 69 | 2.2658 | 0.2859 | 0.2725 | 0.2792 |
| 1.3145 | 4.0 | 92 | 2.3222 | 0.3224 | 0.3227 | 0.3226 |
| 0.9743 | 5.0 | 115 | 2.4189 | 0.3225 | 0.3123 | 0.3174 |
| 0.7528 | 6.0 | 138 | 2.4692 | 0.3326 | 0.3285 | 0.3305 |
| 0.5989 | 7.0 | 161 | 2.3821 | 0.3625 | 0.3590 | 0.3607 |
| 0.4902 | 8.0 | 184 | 2.4665 | 0.3652 | 0.3618 | 0.3635 |
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/distilbert_rand_5_v2_stsb
Base model
Hartunka/distilbert_rand_5_v2Dataset used to train Hartunka/distilbert_rand_5_v2_stsb
Evaluation results
- Spearmanr on GLUE STSBself-reported0.272
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/distilbert_rand_5_v2_stsb")