metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/distilbert_lda_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: distilbert_lda_5_v1_rte
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE RTE
type: glue
args: rte
metrics:
- name: Accuracy
type: accuracy
value: 0.5270758122743683
distilbert_lda_5_v1_rte
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_5_v1 on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6916
- Accuracy: 0.5271
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: 0.001
- 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 |
|---|---|---|---|---|
| 0.9449 | 1.0 | 10 | 0.7022 | 0.5271 |
| 0.7042 | 2.0 | 20 | 0.7000 | 0.4729 |
| 0.7004 | 3.0 | 30 | 0.6919 | 0.5271 |
| 0.6962 | 4.0 | 40 | 0.6929 | 0.5271 |
| 0.6965 | 5.0 | 50 | 0.6996 | 0.5271 |
| 0.6965 | 6.0 | 60 | 0.6918 | 0.5271 |
| 0.6947 | 7.0 | 70 | 0.6916 | 0.5271 |
| 0.6949 | 8.0 | 80 | 0.6938 | 0.4729 |
| 0.6948 | 9.0 | 90 | 0.6991 | 0.4729 |
| 0.6957 | 10.0 | 100 | 0.6920 | 0.5271 |
| 0.6941 | 11.0 | 110 | 0.6956 | 0.4729 |
| 0.6944 | 12.0 | 120 | 0.6935 | 0.4729 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3