update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: tiny-mlm-glue-qnli-target-glue-mnli
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# tiny-mlm-glue-qnli-target-glue-mnli
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [muhtasham/tiny-mlm-glue-qnli](https://huggingface.co/muhtasham/tiny-mlm-glue-qnli) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.7907
|
| 20 |
+
- Accuracy: 0.6507
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 32
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: constant
|
| 45 |
+
- num_epochs: 200
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 51 |
+
| 1.0753 | 0.04 | 500 | 1.0327 | 0.4677 |
|
| 52 |
+
| 1.0084 | 0.08 | 1000 | 0.9655 | 0.5434 |
|
| 53 |
+
| 0.962 | 0.12 | 1500 | 0.9232 | 0.5779 |
|
| 54 |
+
| 0.9358 | 0.16 | 2000 | 0.9087 | 0.5874 |
|
| 55 |
+
| 0.9241 | 0.2 | 2500 | 0.8928 | 0.5963 |
|
| 56 |
+
| 0.9157 | 0.24 | 3000 | 0.8772 | 0.5988 |
|
| 57 |
+
| 0.8992 | 0.29 | 3500 | 0.8687 | 0.6088 |
|
| 58 |
+
| 0.8928 | 0.33 | 4000 | 0.8571 | 0.6173 |
|
| 59 |
+
| 0.8757 | 0.37 | 4500 | 0.8529 | 0.6164 |
|
| 60 |
+
| 0.8774 | 0.41 | 5000 | 0.8438 | 0.6232 |
|
| 61 |
+
| 0.8694 | 0.45 | 5500 | 0.8372 | 0.6246 |
|
| 62 |
+
| 0.8653 | 0.49 | 6000 | 0.8350 | 0.6265 |
|
| 63 |
+
| 0.8677 | 0.53 | 6500 | 0.8268 | 0.6292 |
|
| 64 |
+
| 0.8584 | 0.57 | 7000 | 0.8270 | 0.6326 |
|
| 65 |
+
| 0.8508 | 0.61 | 7500 | 0.8134 | 0.6391 |
|
| 66 |
+
| 0.8521 | 0.65 | 8000 | 0.8110 | 0.6416 |
|
| 67 |
+
| 0.8447 | 0.69 | 8500 | 0.8264 | 0.6323 |
|
| 68 |
+
| 0.8466 | 0.73 | 9000 | 0.7951 | 0.6468 |
|
| 69 |
+
| 0.8379 | 0.77 | 9500 | 0.8089 | 0.6401 |
|
| 70 |
+
| 0.8277 | 0.81 | 10000 | 0.7941 | 0.6477 |
|
| 71 |
+
| 0.8307 | 0.86 | 10500 | 0.7999 | 0.6437 |
|
| 72 |
+
| 0.8289 | 0.9 | 11000 | 0.7874 | 0.6530 |
|
| 73 |
+
| 0.8228 | 0.94 | 11500 | 0.7835 | 0.6524 |
|
| 74 |
+
| 0.8228 | 0.98 | 12000 | 0.7851 | 0.6511 |
|
| 75 |
+
| 0.8078 | 1.02 | 12500 | 0.7907 | 0.6507 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.26.0.dev0
|
| 81 |
+
- Pytorch 1.13.0+cu116
|
| 82 |
+
- Datasets 2.8.1.dev0
|
| 83 |
+
- Tokenizers 0.13.2
|