metadata
library_name: transformers
language:
- en
base_model: Hartunka/distilbert_km_5_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: distilbert_km_5_v2_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.42646563812642424
distilbert_km_5_v2_stsb
This model is a fine-tuned version of Hartunka/distilbert_km_5_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 1.9509
- Pearson: 0.4293
- Spearmanr: 0.4265
- Combined Score: 0.4279
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 |
|---|---|---|---|---|---|---|
| 2.855 | 1.0 | 23 | 2.3396 | 0.1598 | 0.1539 | 0.1568 |
| 1.8792 | 2.0 | 46 | 2.2082 | 0.2599 | 0.2485 | 0.2542 |
| 1.531 | 3.0 | 69 | 2.1020 | 0.3665 | 0.3604 | 0.3634 |
| 1.1221 | 4.0 | 92 | 1.9509 | 0.4293 | 0.4265 | 0.4279 |
| 0.7863 | 5.0 | 115 | 2.1921 | 0.4221 | 0.4242 | 0.4231 |
| 0.5364 | 6.0 | 138 | 2.1038 | 0.4496 | 0.4501 | 0.4498 |
| 0.4273 | 7.0 | 161 | 2.0297 | 0.4535 | 0.4503 | 0.4519 |
| 0.3516 | 8.0 | 184 | 2.1971 | 0.4279 | 0.4217 | 0.4248 |
| 0.2901 | 9.0 | 207 | 2.0682 | 0.4296 | 0.4233 | 0.4265 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1