<!-- 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_add_GLUE_Experiment_logit_kd_sst2_96
This model is a fine-tuned version of distilbert-base-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0319
- Accuracy: 0.7718
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 |
---|---|---|---|---|
1.6039 | 1.0 | 264 | 1.4673 | 0.5092 |
1.6026 | 2.0 | 528 | 1.4652 | 0.5092 |
1.6015 | 3.0 | 792 | 1.4665 | 0.5092 |
1.4093 | 4.0 | 1056 | 1.0858 | 0.7408 |
0.8595 | 5.0 | 1320 | 1.0319 | 0.7718 |
0.6673 | 6.0 | 1584 | 1.0754 | 0.7695 |
0.5834 | 7.0 | 1848 | 1.0825 | 0.7913 |
0.5205 | 8.0 | 2112 | 1.2536 | 0.7546 |
0.4789 | 9.0 | 2376 | 1.1961 | 0.7661 |
0.4457 | 10.0 | 2640 | 1.2203 | 0.7661 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2