<!-- 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_mnli_384
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: 0.5196
- Accuracy: 0.6066
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 |
---|---|---|---|---|
0.5795 | 1.0 | 1534 | 0.5536 | 0.5297 |
0.5482 | 2.0 | 3068 | 0.5402 | 0.5549 |
0.5312 | 3.0 | 4602 | 0.5303 | 0.5781 |
0.5182 | 4.0 | 6136 | 0.5246 | 0.5927 |
0.5065 | 5.0 | 7670 | 0.5189 | 0.6056 |
0.4958 | 6.0 | 9204 | 0.5202 | 0.6018 |
0.4862 | 7.0 | 10738 | 0.5195 | 0.6089 |
0.4769 | 8.0 | 12272 | 0.5252 | 0.6065 |
0.4676 | 9.0 | 13806 | 0.5196 | 0.6164 |
0.459 | 10.0 | 15340 | 0.5223 | 0.6119 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2