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/tiny_bert_rand_100_v2_stsb")
model = AutoModelForSequenceClassification.from_pretrained("Hartunka/tiny_bert_rand_100_v2_stsb")Quick Links
tiny_bert_rand_100_v2_stsb
This model is a fine-tuned version of Hartunka/tiny_bert_rand_100_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.3571
- Pearson: 0.1904
- Spearmanr: 0.1746
- Combined Score: 0.1825
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 |
|---|---|---|---|---|---|---|
| 3.0934 | 1.0 | 23 | 2.4179 | 0.1274 | 0.1252 | 0.1263 |
| 2.0262 | 2.0 | 46 | 2.8227 | 0.0906 | 0.0700 | 0.0803 |
| 1.8632 | 3.0 | 69 | 2.3571 | 0.1904 | 0.1746 | 0.1825 |
| 1.6504 | 4.0 | 92 | 2.4674 | 0.2405 | 0.2359 | 0.2382 |
| 1.376 | 5.0 | 115 | 2.4109 | 0.2443 | 0.2405 | 0.2424 |
| 1.1686 | 6.0 | 138 | 2.5538 | 0.2573 | 0.2599 | 0.2586 |
| 0.9782 | 7.0 | 161 | 2.6227 | 0.2622 | 0.2656 | 0.2639 |
| 0.8135 | 8.0 | 184 | 3.0193 | 0.2305 | 0.2377 | 0.2341 |
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/tiny_bert_rand_100_v2_stsb
Base model
Hartunka/tiny_bert_rand_100_v2Dataset used to train Hartunka/tiny_bert_rand_100_v2_stsb
Evaluation results
- Spearmanr on GLUE STSBself-reported0.175
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hartunka/tiny_bert_rand_100_v2_stsb")