<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert_sa_GLUE_Experiment_rte
This model is a fine-tuned version of distilbert-base-uncased on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.6960
- Accuracy: 0.4693
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.7912 | 1.0 | 10 | 0.7427 | 0.4729 |
0.7025 | 2.0 | 20 | 0.7159 | 0.4729 |
0.6982 | 3.0 | 30 | 0.7001 | 0.4729 |
0.696 | 4.0 | 40 | 0.7030 | 0.4729 |
0.6929 | 5.0 | 50 | 0.6960 | 0.4693 |
0.6684 | 6.0 | 60 | 0.7082 | 0.5018 |
0.5463 | 7.0 | 70 | 1.0469 | 0.4838 |
0.3935 | 8.0 | 80 | 1.0870 | 0.5271 |
0.277 | 9.0 | 90 | 1.2738 | 0.4982 |
0.1839 | 10.0 | 100 | 1.5369 | 0.5162 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2