distilbert_base_train_rte
This model is a fine-tuned version of gokulsrinivasagan/distilbert_base_train on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6828
- Accuracy: 0.5704
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 |
|---|---|---|---|---|
| 0.6997 | 1.0 | 10 | 0.6828 | 0.5704 |
| 0.6546 | 2.0 | 20 | 0.7107 | 0.5379 |
| 0.5898 | 3.0 | 30 | 0.7532 | 0.5162 |
| 0.479 | 4.0 | 40 | 0.9313 | 0.4982 |
| 0.3475 | 5.0 | 50 | 1.1322 | 0.5090 |
| 0.2361 | 6.0 | 60 | 1.2963 | 0.5487 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Downloads last month
- 17
Model tree for gokulsrinivasagan/distilbert_base_train_rte
Base model
distilbert/distilbert-base-uncased Finetuned
gokulsrinivasagan/distilbert_base_trainDataset used to train gokulsrinivasagan/distilbert_base_train_rte
Evaluation results
- Accuracy on GLUE RTEself-reported0.570