metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_base_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: 0.5611208690347649
bert_base_lda_5_v1_stsb
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_5_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 1.6191
- Pearson: 0.5646
- Spearmanr: 0.5611
- Combined Score: 0.5629
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 |
|---|---|---|---|---|---|---|
| 2.6199 | 1.0 | 23 | 2.5334 | 0.0881 | 0.0645 | 0.0763 |
| 1.9109 | 2.0 | 46 | 2.0478 | 0.3672 | 0.3623 | 0.3648 |
| 1.4094 | 3.0 | 69 | 1.7320 | 0.5080 | 0.4996 | 0.5038 |
| 0.9385 | 4.0 | 92 | 1.9694 | 0.5238 | 0.5276 | 0.5257 |
| 0.6759 | 5.0 | 115 | 1.6464 | 0.5449 | 0.5411 | 0.5430 |
| 0.5133 | 6.0 | 138 | 1.6191 | 0.5646 | 0.5611 | 0.5629 |
| 0.377 | 7.0 | 161 | 1.7543 | 0.5361 | 0.5316 | 0.5339 |
| 0.3223 | 8.0 | 184 | 1.6249 | 0.5752 | 0.5687 | 0.5720 |
| 0.2679 | 9.0 | 207 | 1.6797 | 0.5685 | 0.5621 | 0.5653 |
| 0.2156 | 10.0 | 230 | 1.6664 | 0.5592 | 0.5488 | 0.5540 |
| 0.1962 | 11.0 | 253 | 1.6273 | 0.5784 | 0.5728 | 0.5756 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3