update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- glue
|
| 7 |
+
metrics:
|
| 8 |
+
- matthews_correlation
|
| 9 |
+
model-index:
|
| 10 |
+
- name: electra-base-discriminator-CoLA
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Text Classification
|
| 14 |
+
type: text-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: glue
|
| 17 |
+
type: glue
|
| 18 |
+
config: cola
|
| 19 |
+
split: validation
|
| 20 |
+
args: cola
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Matthews Correlation
|
| 23 |
+
type: matthews_correlation
|
| 24 |
+
value: 0.6750024002589107
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# electra-base-discriminator-CoLA
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the glue dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.6292
|
| 35 |
+
- Matthews Correlation: 0.6750
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 8e-05
|
| 55 |
+
- train_batch_size: 128
|
| 56 |
+
- eval_batch_size: 16
|
| 57 |
+
- seed: 22165
|
| 58 |
+
- distributed_type: multi-GPU
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: cosine
|
| 61 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 62 |
+
- num_epochs: 8.0
|
| 63 |
+
- mixed_precision_training: Native AMP
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
|
| 69 |
+
| 0.4004 | 1.0 | 67 | 0.3569 | 0.6340 |
|
| 70 |
+
| 0.2843 | 2.0 | 134 | 0.3542 | 0.6580 |
|
| 71 |
+
| 0.1228 | 3.0 | 201 | 0.4201 | 0.6412 |
|
| 72 |
+
| 0.0989 | 4.0 | 268 | 0.4780 | 0.6757 |
|
| 73 |
+
| 0.0681 | 5.0 | 335 | 0.4900 | 0.6925 |
|
| 74 |
+
| 0.0506 | 6.0 | 402 | 0.5837 | 0.6785 |
|
| 75 |
+
| 0.0093 | 7.0 | 469 | 0.6298 | 0.6652 |
|
| 76 |
+
| 0.0244 | 8.0 | 536 | 0.6292 | 0.6750 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.27.0.dev0
|
| 82 |
+
- Pytorch 1.13.1+cu117
|
| 83 |
+
- Datasets 2.8.0
|
| 84 |
+
- Tokenizers 0.13.1
|