metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tiny-mlm-glue-sst2-target-glue-qnli
results: []
tiny-mlm-glue-sst2-target-glue-qnli
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-sst2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4704
- Accuracy: 0.7792
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
- num_epochs: 200
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6131 | 0.15 | 500 | 0.5383 | 0.7337 |
0.5434 | 0.31 | 1000 | 0.5325 | 0.7393 |
0.5218 | 0.46 | 1500 | 0.4985 | 0.7635 |
0.5155 | 0.61 | 2000 | 0.5256 | 0.7465 |
0.511 | 0.76 | 2500 | 0.4781 | 0.7759 |
0.5044 | 0.92 | 3000 | 0.4673 | 0.7824 |
0.4924 | 1.07 | 3500 | 0.4546 | 0.7904 |
0.4819 | 1.22 | 4000 | 0.4664 | 0.7836 |
0.4674 | 1.37 | 4500 | 0.4724 | 0.7789 |
0.4755 | 1.53 | 5000 | 0.4704 | 0.7792 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2