metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_50_v1_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_lda_50_v1_book_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.5018050541516246
bert_base_lda_50_v1_book_rte
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_50_v1_book on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6885
- Accuracy: 0.5018
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 | Accuracy |
|---|---|---|---|---|
| 0.7099 | 1.0 | 10 | 0.7059 | 0.5343 |
| 0.6998 | 2.0 | 20 | 0.6954 | 0.4657 |
| 0.6965 | 3.0 | 30 | 0.6918 | 0.5271 |
| 0.6924 | 4.0 | 40 | 0.6914 | 0.5271 |
| 0.6932 | 5.0 | 50 | 0.6946 | 0.5271 |
| 0.6962 | 6.0 | 60 | 0.6998 | 0.4765 |
| 0.6918 | 7.0 | 70 | 0.6885 | 0.5018 |
| 0.6802 | 8.0 | 80 | 0.7132 | 0.5523 |
| 0.6651 | 9.0 | 90 | 0.6924 | 0.5523 |
| 0.6437 | 10.0 | 100 | 0.8075 | 0.5054 |
| 0.6004 | 11.0 | 110 | 0.7967 | 0.5451 |
| 0.518 | 12.0 | 120 | 0.8455 | 0.5451 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3