update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: deberta-v3-large__sst2__train-8-9
|
| 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 |
+
# deberta-v3-large__sst2__train-8-9
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6013
|
| 20 |
+
- Accuracy: 0.7210
|
| 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: 2e-05
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 4
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 50
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 0.6757 | 1.0 | 3 | 0.7810 | 0.25 |
|
| 53 |
+
| 0.6506 | 2.0 | 6 | 0.8102 | 0.25 |
|
| 54 |
+
| 0.6463 | 3.0 | 9 | 0.8313 | 0.25 |
|
| 55 |
+
| 0.5813 | 4.0 | 12 | 0.8858 | 0.25 |
|
| 56 |
+
| 0.4635 | 5.0 | 15 | 0.8220 | 0.25 |
|
| 57 |
+
| 0.3992 | 6.0 | 18 | 0.7226 | 0.5 |
|
| 58 |
+
| 0.3281 | 7.0 | 21 | 0.6707 | 0.75 |
|
| 59 |
+
| 0.2276 | 8.0 | 24 | 0.7515 | 0.75 |
|
| 60 |
+
| 0.1674 | 9.0 | 27 | 0.6971 | 0.75 |
|
| 61 |
+
| 0.0873 | 10.0 | 30 | 0.5419 | 0.75 |
|
| 62 |
+
| 0.0525 | 11.0 | 33 | 0.5025 | 0.75 |
|
| 63 |
+
| 0.0286 | 12.0 | 36 | 0.5229 | 0.75 |
|
| 64 |
+
| 0.0149 | 13.0 | 39 | 0.5660 | 0.75 |
|
| 65 |
+
| 0.0082 | 14.0 | 42 | 0.6954 | 0.75 |
|
| 66 |
+
| 0.006 | 15.0 | 45 | 0.8649 | 0.75 |
|
| 67 |
+
| 0.0043 | 16.0 | 48 | 1.0011 | 0.75 |
|
| 68 |
+
| 0.0035 | 17.0 | 51 | 1.0909 | 0.75 |
|
| 69 |
+
| 0.0021 | 18.0 | 54 | 1.1615 | 0.75 |
|
| 70 |
+
| 0.0017 | 19.0 | 57 | 1.2147 | 0.75 |
|
| 71 |
+
| 0.0013 | 20.0 | 60 | 1.2585 | 0.75 |
|
| 72 |
+
| 0.0016 | 21.0 | 63 | 1.2917 | 0.75 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.15.0
|
| 78 |
+
- Pytorch 1.10.2+cu102
|
| 79 |
+
- Datasets 1.18.2
|
| 80 |
+
- Tokenizers 0.10.3
|