Commit
•
5bdd196
1
Parent(s):
d8dd70d
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
- f1
|
| 8 |
+
model-index:
|
| 9 |
+
- name: fine-tuned-NLI-idk-mrc-nli-keep-with-xlm-roberta-large
|
| 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 |
+
# fine-tuned-NLI-idk-mrc-nli-keep-with-xlm-roberta-large
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1080
|
| 21 |
+
- Accuracy: 0.9830
|
| 22 |
+
- F1: 0.9830
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 16
|
| 46 |
+
- total_train_batch_size: 128
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 55 |
+
| 1.3752 | 0.49 | 39 | 0.6866 | 0.5183 | 0.3749 |
|
| 56 |
+
| 0.7598 | 0.99 | 78 | 0.2098 | 0.9332 | 0.9331 |
|
| 57 |
+
| 0.3228 | 1.49 | 117 | 0.1063 | 0.9634 | 0.9633 |
|
| 58 |
+
| 0.1461 | 1.99 | 156 | 0.0813 | 0.9725 | 0.9725 |
|
| 59 |
+
| 0.1461 | 2.49 | 195 | 0.0719 | 0.9777 | 0.9777 |
|
| 60 |
+
| 0.1154 | 2.99 | 234 | 0.0704 | 0.9777 | 0.9777 |
|
| 61 |
+
| 0.0881 | 3.49 | 273 | 0.0625 | 0.9830 | 0.9830 |
|
| 62 |
+
| 0.0551 | 3.99 | 312 | 0.0738 | 0.9817 | 0.9817 |
|
| 63 |
+
| 0.0474 | 4.49 | 351 | 0.0779 | 0.9843 | 0.9843 |
|
| 64 |
+
| 0.0474 | 4.99 | 390 | 0.0860 | 0.9791 | 0.9791 |
|
| 65 |
+
| 0.0425 | 5.49 | 429 | 0.0801 | 0.9856 | 0.9856 |
|
| 66 |
+
| 0.0316 | 5.99 | 468 | 0.0947 | 0.9817 | 0.9817 |
|
| 67 |
+
| 0.0185 | 6.49 | 507 | 0.0953 | 0.9856 | 0.9856 |
|
| 68 |
+
| 0.0185 | 6.99 | 546 | 0.0979 | 0.9817 | 0.9817 |
|
| 69 |
+
| 0.0264 | 7.49 | 585 | 0.0923 | 0.9830 | 0.9830 |
|
| 70 |
+
| 0.0156 | 7.99 | 624 | 0.1080 | 0.9830 | 0.9830 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.26.1
|
| 76 |
+
- Pytorch 1.13.1+cu117
|
| 77 |
+
- Datasets 2.2.0
|
| 78 |
+
- Tokenizers 0.13.2
|