update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-sst2
|
| 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-sst2
|
| 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: 0.5008
|
| 20 |
+
- Accuracy: 0.8211
|
| 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 |
+
| 0.5757 | 0.24 | 500 | 0.4901 | 0.7775 |
|
| 52 |
+
| 0.4436 | 0.48 | 1000 | 0.4673 | 0.7833 |
|
| 53 |
+
| 0.3947 | 0.71 | 1500 | 0.4434 | 0.7970 |
|
| 54 |
+
| 0.3751 | 0.95 | 2000 | 0.4601 | 0.7970 |
|
| 55 |
+
| 0.3326 | 1.19 | 2500 | 0.4463 | 0.8005 |
|
| 56 |
+
| 0.316 | 1.43 | 3000 | 0.4510 | 0.8005 |
|
| 57 |
+
| 0.2981 | 1.66 | 3500 | 0.4367 | 0.8142 |
|
| 58 |
+
| 0.2929 | 1.9 | 4000 | 0.4383 | 0.8108 |
|
| 59 |
+
| 0.2746 | 2.14 | 4500 | 0.4873 | 0.8016 |
|
| 60 |
+
| 0.256 | 2.38 | 5000 | 0.4395 | 0.8165 |
|
| 61 |
+
| 0.246 | 2.61 | 5500 | 0.4444 | 0.8280 |
|
| 62 |
+
| 0.2522 | 2.85 | 6000 | 0.4478 | 0.8245 |
|
| 63 |
+
| 0.2371 | 3.09 | 6500 | 0.4556 | 0.8291 |
|
| 64 |
+
| 0.2299 | 3.33 | 7000 | 0.4655 | 0.8326 |
|
| 65 |
+
| 0.2143 | 3.56 | 7500 | 0.4581 | 0.8314 |
|
| 66 |
+
| 0.2153 | 3.8 | 8000 | 0.4869 | 0.8291 |
|
| 67 |
+
| 0.2134 | 4.04 | 8500 | 0.5008 | 0.8211 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.26.0.dev0
|
| 73 |
+
- Pytorch 1.13.0+cu116
|
| 74 |
+
- Datasets 2.8.1.dev0
|
| 75 |
+
- Tokenizers 0.13.2
|