metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_olda_book_10_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_tiny_olda_book_10_v1_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.7894827878783358
bert_tiny_olda_book_10_v1_stsb
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_olda_book_10_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 0.8800
- Pearson: 0.7899
- Spearmanr: 0.7895
- Combined Score: 0.7897
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 OptimizerNames.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 |
|---|---|---|---|---|---|---|
| 3.0028 | 1.0 | 23 | 2.5219 | 0.1644 | 0.1637 | 0.1641 |
| 1.7825 | 2.0 | 46 | 1.7353 | 0.6315 | 0.6561 | 0.6438 |
| 1.2017 | 3.0 | 69 | 1.1421 | 0.7243 | 0.7369 | 0.7306 |
| 0.8992 | 4.0 | 92 | 1.0970 | 0.7550 | 0.7677 | 0.7613 |
| 0.6849 | 5.0 | 115 | 0.8800 | 0.7899 | 0.7895 | 0.7897 |
| 0.5834 | 6.0 | 138 | 0.8918 | 0.7965 | 0.7978 | 0.7972 |
| 0.4852 | 7.0 | 161 | 0.9756 | 0.7948 | 0.7965 | 0.7957 |
| 0.4346 | 8.0 | 184 | 0.8957 | 0.7867 | 0.7860 | 0.7864 |
| 0.3871 | 9.0 | 207 | 0.9086 | 0.7900 | 0.7882 | 0.7891 |
| 0.3449 | 10.0 | 230 | 1.0219 | 0.7874 | 0.7899 | 0.7886 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1