metadata
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_km_50_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: tiny_bert_km_50_v2_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.060441972646093724
tiny_bert_km_50_v2_stsb
This model is a fine-tuned version of Hartunka/tiny_bert_km_50_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2703
- Pearson: 0.0633
- Spearmanr: 0.0604
- Combined Score: 0.0619
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 |
|---|---|---|---|---|---|---|
| 3.769 | 1.0 | 23 | 2.2703 | 0.0633 | 0.0604 | 0.0619 |
| 2.1015 | 2.0 | 46 | 2.4637 | 0.0982 | 0.0916 | 0.0949 |
| 1.9322 | 3.0 | 69 | 2.4902 | 0.1389 | 0.1233 | 0.1311 |
| 1.7867 | 4.0 | 92 | 2.2723 | 0.2538 | 0.2474 | 0.2506 |
| 1.5685 | 5.0 | 115 | 2.7302 | 0.2094 | 0.2023 | 0.2059 |
| 1.3328 | 6.0 | 138 | 2.6151 | 0.2652 | 0.2647 | 0.2649 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1