small-mlm-glue-mrpc-target-glue-qnli
This model is a fine-tuned version of muhtasham/small-mlm-glue-mrpc on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3483
- Accuracy: 0.8607
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 |
---|---|---|---|---|
0.4922 | 0.15 | 500 | 0.3954 | 0.8243 |
0.4468 | 0.31 | 1000 | 0.3839 | 0.8343 |
0.4228 | 0.46 | 1500 | 0.3578 | 0.8481 |
0.4132 | 0.61 | 2000 | 0.3697 | 0.8407 |
0.4094 | 0.76 | 2500 | 0.3400 | 0.8558 |
0.3946 | 0.92 | 3000 | 0.3316 | 0.8583 |
0.3523 | 1.07 | 3500 | 0.3481 | 0.8536 |
0.3151 | 1.22 | 4000 | 0.3473 | 0.8594 |
0.3139 | 1.37 | 4500 | 0.3502 | 0.8567 |
0.3203 | 1.53 | 5000 | 0.3483 | 0.8607 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 4