metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tiny-mlm-glue-mnli-from-scratch-custom-tokenizer-target-glue-qnli
results: []
tiny-mlm-glue-mnli-from-scratch-custom-tokenizer-target-glue-qnli
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mnli-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6517
- Accuracy: 0.6171
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 |
|---|---|---|---|---|
| 0.6918 | 0.15 | 500 | 0.6854 | 0.5684 |
| 0.6778 | 0.31 | 1000 | 0.6610 | 0.6006 |
| 0.6692 | 0.46 | 1500 | 0.6550 | 0.6121 |
| 0.6613 | 0.61 | 2000 | 0.6553 | 0.6114 |
| 0.6597 | 0.76 | 2500 | 0.6529 | 0.6132 |
| 0.6582 | 0.92 | 3000 | 0.6488 | 0.6185 |
| 0.6484 | 1.07 | 3500 | 0.6517 | 0.6200 |
| 0.6461 | 1.22 | 4000 | 0.6484 | 0.6233 |
| 0.6422 | 1.37 | 4500 | 0.6493 | 0.6176 |
| 0.6456 | 1.53 | 5000 | 0.6517 | 0.6171 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2