metadata
language:
- en
base_model: Hartunka/tiny_bert_km_50_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: tiny_bert_km_50_v1_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.18233475301431837
tiny_bert_km_50_v1_stsb
This model is a fine-tuned version of Hartunka/tiny_bert_km_50_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.2276
- Pearson: 0.1924
- Spearmanr: 0.1823
- Combined Score: 0.1873
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 3.8515 | 1.0 | 23 | 2.2276 | 0.1924 | 0.1823 | 0.1873 |
| 2.1315 | 2.0 | 46 | 2.2514 | 0.2165 | 0.2014 | 0.2089 |
| 1.9864 | 3.0 | 69 | 2.2711 | 0.1966 | 0.1884 | 0.1925 |
| 1.8498 | 4.0 | 92 | 2.3629 | 0.2217 | 0.2164 | 0.2190 |
| 1.6182 | 5.0 | 115 | 2.3719 | 0.2448 | 0.2459 | 0.2454 |
| 1.3745 | 6.0 | 138 | 2.4489 | 0.2402 | 0.2417 | 0.2409 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1