update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- glue
|
| 6 |
+
metrics:
|
| 7 |
+
- matthews_correlation
|
| 8 |
+
model-index:
|
| 9 |
+
- name: cola-pixel-handwritten-mean-vatrpp-256-128-4-3e-5-15000-420
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# cola-pixel-handwritten-mean-vatrpp-256-128-4-3e-5-15000-420
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [noniewiem/pixel-handwritten](https://huggingface.co/noniewiem/pixel-handwritten) on the glue dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6172
|
| 21 |
+
- Matthews Correlation: 0.0
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 3e-05
|
| 41 |
+
- train_batch_size: 128
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 420
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 512
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 200
|
| 49 |
+
- training_steps: 15000
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
|
| 56 |
+
| 0.651 | 6.24 | 100 | 0.6248 | 0.0 |
|
| 57 |
+
| 0.6339 | 12.48 | 200 | 0.6229 | 0.0 |
|
| 58 |
+
| 0.6347 | 18.72 | 300 | 0.6188 | 0.0 |
|
| 59 |
+
| 0.6348 | 24.96 | 400 | 0.6178 | 0.0 |
|
| 60 |
+
| 0.6383 | 31.24 | 500 | 0.6179 | 0.0 |
|
| 61 |
+
| 0.633 | 37.48 | 600 | 0.6183 | 0.0 |
|
| 62 |
+
| 0.633 | 43.72 | 700 | 0.6159 | 0.0 |
|
| 63 |
+
| 0.6333 | 49.96 | 800 | 0.6181 | 0.0 |
|
| 64 |
+
| 0.6369 | 56.24 | 900 | 0.6213 | 0.0 |
|
| 65 |
+
| 0.6359 | 62.48 | 1000 | 0.6191 | 0.0 |
|
| 66 |
+
| 0.6348 | 68.72 | 1100 | 0.6172 | 0.0 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.17.0
|
| 72 |
+
- Pytorch 2.3.0+cu121
|
| 73 |
+
- Datasets 2.0.0
|
| 74 |
+
- Tokenizers 0.13.3
|