<!-- 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. -->
olm-bert-tiny-december-2022-target-glue-sst2
This model is a fine-tuned version of muhtasham/olm-bert-tiny-december-2022 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4126
- Accuracy: 0.8280
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 |
---|---|---|---|---|
0.5968 | 0.24 | 500 | 0.4910 | 0.7718 |
0.4845 | 0.48 | 1000 | 0.4722 | 0.7810 |
0.4455 | 0.71 | 1500 | 0.4468 | 0.7924 |
0.4397 | 0.95 | 2000 | 0.4488 | 0.7901 |
0.4028 | 1.19 | 2500 | 0.4262 | 0.8119 |
0.3898 | 1.43 | 3000 | 0.4375 | 0.7936 |
0.3768 | 1.66 | 3500 | 0.4207 | 0.8050 |
0.3725 | 1.9 | 4000 | 0.4228 | 0.8245 |
0.3515 | 2.14 | 4500 | 0.4336 | 0.8085 |
0.3326 | 2.38 | 5000 | 0.4126 | 0.8280 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2