metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/distilbert_lda_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: distilbert_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: 0.771403455042343
distilbert_lda_5_v1_stsb
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_5_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 0.9149
- Pearson: 0.7745
- Spearmanr: 0.7714
- Combined Score: 0.7730
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 |
|---|---|---|---|---|---|---|
| 2.4726 | 1.0 | 23 | 1.7690 | 0.5073 | 0.5038 | 0.5056 |
| 1.3012 | 2.0 | 46 | 1.3896 | 0.7004 | 0.7125 | 0.7064 |
| 0.8284 | 3.0 | 69 | 0.9456 | 0.7721 | 0.7714 | 0.7718 |
| 0.5881 | 4.0 | 92 | 0.9819 | 0.7670 | 0.7671 | 0.7670 |
| 0.4537 | 5.0 | 115 | 0.9149 | 0.7745 | 0.7714 | 0.7730 |
| 0.3479 | 6.0 | 138 | 1.1078 | 0.7723 | 0.7729 | 0.7726 |
| 0.2723 | 7.0 | 161 | 0.9508 | 0.7747 | 0.7725 | 0.7736 |
| 0.2507 | 8.0 | 184 | 0.9537 | 0.7685 | 0.7651 | 0.7668 |
| 0.2101 | 9.0 | 207 | 1.0716 | 0.7639 | 0.7611 | 0.7625 |
| 0.1713 | 10.0 | 230 | 1.0893 | 0.7716 | 0.7719 | 0.7718 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3