metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: >-
tiny-mlm-glue-cola-from-scratch-custom-tokenizer-expand-vocab-target-glue-mrpc
results: []
tiny-mlm-glue-cola-from-scratch-custom-tokenizer-expand-vocab-target-glue-mrpc
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-cola-from-scratch-custom-tokenizer-expand-vocab on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9173
- Accuracy: 0.6495
- F1: 0.7496
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 |
|---|---|---|---|---|---|
| 0.6309 | 4.35 | 500 | 0.6176 | 0.6936 | 0.8164 |
| 0.5707 | 8.7 | 1000 | 0.6353 | 0.6593 | 0.7608 |
| 0.4316 | 13.04 | 1500 | 0.7746 | 0.6495 | 0.7395 |
| 0.3118 | 17.39 | 2000 | 0.9173 | 0.6495 | 0.7496 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2