metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_20_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_base_lda_20_v1_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.542723493120609
bert_base_lda_20_v1_stsb
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_20_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 1.6651
- Pearson: 0.5451
- Spearmanr: 0.5427
- Combined Score: 0.5439
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 |
|---|---|---|---|---|---|---|
| 2.9133 | 1.0 | 23 | 2.4317 | 0.0791 | 0.0962 | 0.0877 |
| 1.7921 | 2.0 | 46 | 2.1686 | 0.4521 | 0.4592 | 0.4557 |
| 1.4021 | 3.0 | 69 | 1.9879 | 0.4763 | 0.4810 | 0.4787 |
| 1.0503 | 4.0 | 92 | 1.9337 | 0.4942 | 0.4986 | 0.4964 |
| 0.8246 | 5.0 | 115 | 1.7137 | 0.5360 | 0.5325 | 0.5342 |
| 0.6757 | 6.0 | 138 | 1.6651 | 0.5451 | 0.5427 | 0.5439 |
| 0.5303 | 7.0 | 161 | 1.7657 | 0.5456 | 0.5387 | 0.5421 |
| 0.4539 | 8.0 | 184 | 1.9938 | 0.5482 | 0.5505 | 0.5494 |
| 0.399 | 9.0 | 207 | 1.7298 | 0.5402 | 0.5311 | 0.5356 |
| 0.3663 | 10.0 | 230 | 1.8046 | 0.5614 | 0.5599 | 0.5607 |
| 0.2964 | 11.0 | 253 | 1.7391 | 0.5470 | 0.5401 | 0.5435 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3