<!-- 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. -->
MiniLMv2-L12-H384-sst2
This model is a fine-tuned version of nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.2195
- Accuracy: 0.9209
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: sagemaker_data_parallel
- num_devices: 8
- total_train_batch_size: 256
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5576 | 1.0 | 264 | 0.2690 | 0.8979 |
| 0.2854 | 2.0 | 528 | 0.2077 | 0.9117 |
| 0.2158 | 3.0 | 792 | 0.2195 | 0.9209 |
| 0.1789 | 4.0 | 1056 | 0.2260 | 0.9163 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.2+cu113
- Datasets 1.18.4
- Tokenizers 0.11.6
