metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/distilbert_lda_50_v1_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: distilbert_lda_50_v1_book_stsb
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE STSB
type: glue
args: stsb
metrics:
- name: Spearmanr
type: spearmanr
value: 0.8025650669509531
distilbert_lda_50_v1_book_stsb
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_50_v1_book on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 0.7989
- Pearson: 0.8047
- Spearmanr: 0.8026
- Combined Score: 0.8036
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 |
|---|---|---|---|---|---|---|
| 2.7588 | 1.0 | 23 | 2.3855 | 0.2412 | 0.2400 | 0.2406 |
| 1.3932 | 2.0 | 46 | 1.0838 | 0.7225 | 0.7294 | 0.7260 |
| 0.8739 | 3.0 | 69 | 0.9564 | 0.7766 | 0.7839 | 0.7803 |
| 0.6995 | 4.0 | 92 | 1.0132 | 0.7843 | 0.7951 | 0.7897 |
| 0.5789 | 5.0 | 115 | 0.7989 | 0.8047 | 0.8026 | 0.8036 |
| 0.4663 | 6.0 | 138 | 0.9842 | 0.7990 | 0.8045 | 0.8017 |
| 0.3577 | 7.0 | 161 | 0.8651 | 0.8077 | 0.8095 | 0.8086 |
| 0.2967 | 8.0 | 184 | 0.8846 | 0.8140 | 0.8160 | 0.8150 |
| 0.2521 | 9.0 | 207 | 0.8503 | 0.8081 | 0.8117 | 0.8099 |
| 0.2194 | 10.0 | 230 | 0.9103 | 0.8183 | 0.8194 | 0.8188 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3