metadata
library_name: transformers
base_model: gokulsrinivasagan/distilbert_lda_5_v1
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert_lda_5_v1_rte
results: []
distilbert_lda_5_v1_rte
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_5_v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4545
- Accuracy: 0.5199
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 |
|---|---|---|---|---|
| 0.7504 | 1.0 | 10 | 0.7092 | 0.4729 |
| 0.6796 | 2.0 | 20 | 0.7039 | 0.5162 |
| 0.6429 | 3.0 | 30 | 0.6961 | 0.5090 |
| 0.5697 | 4.0 | 40 | 0.7391 | 0.5415 |
| 0.4539 | 5.0 | 50 | 0.8574 | 0.5307 |
| 0.3105 | 6.0 | 60 | 1.0425 | 0.5523 |
| 0.2107 | 7.0 | 70 | 1.4041 | 0.5054 |
| 0.1354 | 8.0 | 80 | 1.4545 | 0.5199 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3