<!-- 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. -->
mobilebert_sa_GLUE_Experiment_logit_kd_data_aug_sst2_128
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4833
- Accuracy: 0.8544
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: 128
- eval_batch_size: 128
- 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
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5233 | 1.0 | 8748 | 0.5730 | 0.8291 |
0.3614 | 2.0 | 17496 | 0.5357 | 0.8394 |
0.3019 | 3.0 | 26244 | 0.5166 | 0.8509 |
0.268 | 4.0 | 34992 | 0.5172 | 0.8509 |
0.2465 | 5.0 | 43740 | 0.4833 | 0.8544 |
0.2313 | 6.0 | 52488 | 0.5422 | 0.8463 |
0.2201 | 7.0 | 61236 | 0.5778 | 0.8303 |
0.2113 | 8.0 | 69984 | 0.5364 | 0.8417 |
0.204 | 9.0 | 78732 | 0.5428 | 0.8314 |
0.198 | 10.0 | 87480 | 0.5442 | 0.8337 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2