metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_tiny_lda_5_v1_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.3252056186475298
bert_tiny_lda_5_v1_stsb
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_5_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.1159
- Pearson: 0.3380
- Spearmanr: 0.3252
- Combined Score: 0.3316
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 |
|---|---|---|---|---|---|---|
| 3.1149 | 1.0 | 23 | 2.4272 | 0.0847 | 0.0635 | 0.0741 |
| 2.029 | 2.0 | 46 | 2.6006 | 0.1105 | 0.0974 | 0.1040 |
| 1.8675 | 3.0 | 69 | 2.2648 | 0.2521 | 0.2357 | 0.2439 |
| 1.6207 | 4.0 | 92 | 2.1159 | 0.3380 | 0.3252 | 0.3316 |
| 1.3084 | 5.0 | 115 | 2.1664 | 0.3564 | 0.3532 | 0.3548 |
| 1.0212 | 6.0 | 138 | 2.2510 | 0.3838 | 0.3847 | 0.3843 |
| 0.8086 | 7.0 | 161 | 2.1705 | 0.4049 | 0.4059 | 0.4054 |
| 0.6441 | 8.0 | 184 | 2.4279 | 0.3792 | 0.3746 | 0.3769 |
| 0.5485 | 9.0 | 207 | 2.3964 | 0.3827 | 0.3784 | 0.3805 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3