update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: roberta-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: roberta_multiple_choice
|
| 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 |
+
# roberta_multiple_choice
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.4432
|
| 21 |
+
- Accuracy: 0.25
|
| 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: 5e-06
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 16
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 100
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 1.6169 | 1.0 | 12 | 1.6073 | 0.45 |
|
| 53 |
+
| 1.6077 | 2.0 | 24 | 1.6059 | 0.5 |
|
| 54 |
+
| 1.6014 | 3.0 | 36 | 1.6048 | 0.5 |
|
| 55 |
+
| 1.5922 | 4.0 | 48 | 1.6036 | 0.5 |
|
| 56 |
+
| 1.5952 | 5.0 | 60 | 1.6032 | 0.45 |
|
| 57 |
+
| 1.6069 | 6.0 | 72 | 1.6025 | 0.5 |
|
| 58 |
+
| 1.6041 | 7.0 | 84 | 1.5998 | 0.4 |
|
| 59 |
+
| 1.591 | 8.0 | 96 | 1.5953 | 0.4 |
|
| 60 |
+
| 1.5841 | 9.0 | 108 | 1.5818 | 0.4 |
|
| 61 |
+
| 1.5662 | 10.0 | 120 | 1.5708 | 0.45 |
|
| 62 |
+
| 1.5878 | 11.0 | 132 | 1.5746 | 0.4 |
|
| 63 |
+
| 1.5416 | 12.0 | 144 | 1.5477 | 0.3 |
|
| 64 |
+
| 1.5113 | 13.0 | 156 | 1.5409 | 0.35 |
|
| 65 |
+
| 1.5256 | 14.0 | 168 | 1.5296 | 0.45 |
|
| 66 |
+
| 1.5036 | 15.0 | 180 | 1.5060 | 0.45 |
|
| 67 |
+
| 1.5244 | 16.0 | 192 | 1.4890 | 0.4 |
|
| 68 |
+
| 1.4847 | 17.0 | 204 | 1.5103 | 0.3 |
|
| 69 |
+
| 1.4656 | 18.0 | 216 | 1.4753 | 0.4 |
|
| 70 |
+
| 1.4776 | 19.0 | 228 | 1.4732 | 0.35 |
|
| 71 |
+
| 1.4366 | 20.0 | 240 | 1.4535 | 0.4 |
|
| 72 |
+
| 1.3867 | 21.0 | 252 | 1.4895 | 0.4 |
|
| 73 |
+
| 1.361 | 22.0 | 264 | 1.4203 | 0.4 |
|
| 74 |
+
| 1.3703 | 23.0 | 276 | 1.4663 | 0.4 |
|
| 75 |
+
| 1.3296 | 24.0 | 288 | 1.4347 | 0.35 |
|
| 76 |
+
| 1.3401 | 25.0 | 300 | 1.4416 | 0.4 |
|
| 77 |
+
| 1.3673 | 26.0 | 312 | 1.4377 | 0.35 |
|
| 78 |
+
| 1.3152 | 27.0 | 324 | 1.4432 | 0.25 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.31.0
|
| 84 |
+
- Pytorch 2.0.1+cu117
|
| 85 |
+
- Datasets 2.14.4
|
| 86 |
+
- Tokenizers 0.13.3
|