<!-- 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. -->
small-mlm-glue-sst2-target-glue-qqp
This model is a fine-tuned version of muhtasham/small-mlm-glue-sst2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3294
- Accuracy: 0.8517
- F1: 0.8131
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4741 | 0.04 | 500 | 0.4233 | 0.7913 | 0.7483 |
| 0.4192 | 0.09 | 1000 | 0.3860 | 0.8136 | 0.7685 |
| 0.401 | 0.13 | 1500 | 0.3733 | 0.8232 | 0.7802 |
| 0.3857 | 0.18 | 2000 | 0.3747 | 0.8202 | 0.7877 |
| 0.3808 | 0.22 | 2500 | 0.3617 | 0.8343 | 0.7962 |
| 0.3626 | 0.26 | 3000 | 0.3507 | 0.8359 | 0.7972 |
| 0.3604 | 0.31 | 3500 | 0.3355 | 0.8476 | 0.8010 |
| 0.3533 | 0.35 | 4000 | 0.3353 | 0.8474 | 0.8087 |
| 0.3585 | 0.4 | 4500 | 0.3316 | 0.8473 | 0.8073 |
| 0.3461 | 0.44 | 5000 | 0.3294 | 0.8517 | 0.8131 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
