<!-- 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_logit_kd_data_aug_mnli_256
This model is a fine-tuned version of distilbert-base-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.5082
- Accuracy: 0.6312
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 |
---|---|---|---|---|
0.5216 | 1.0 | 31440 | 0.5047 | 0.6315 |
0.4566 | 2.0 | 62880 | 0.5097 | 0.6383 |
0.4188 | 3.0 | 94320 | 0.5243 | 0.6361 |
0.3943 | 4.0 | 125760 | 0.5328 | 0.6346 |
0.3777 | 5.0 | 157200 | 0.5345 | 0.6300 |
0.3658 | 6.0 | 188640 | 0.5392 | 0.6318 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2