Commit ·
b1cc851
1
Parent(s): 16625a5
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: roberta-mc-4
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# roberta-mc-4
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.4442
|
| 19 |
+
- Accuracy: 0.5
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.001
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 30
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 50 |
+
| 1.6061 | 1.0 | 24 | 1.5920 | 0.7 |
|
| 51 |
+
| 1.6032 | 2.0 | 48 | 1.5838 | 0.6 |
|
| 52 |
+
| 1.6104 | 3.0 | 72 | 1.5750 | 0.7 |
|
| 53 |
+
| 1.5851 | 4.0 | 96 | 1.5584 | 0.6 |
|
| 54 |
+
| 1.5653 | 5.0 | 120 | 1.5059 | 0.7 |
|
| 55 |
+
| 1.5485 | 6.0 | 144 | 1.4743 | 0.6 |
|
| 56 |
+
| 1.5175 | 7.0 | 168 | 1.4500 | 0.7 |
|
| 57 |
+
| 1.5025 | 8.0 | 192 | 1.4298 | 0.5 |
|
| 58 |
+
| 1.466 | 9.0 | 216 | 1.4559 | 0.5 |
|
| 59 |
+
| 1.4444 | 10.0 | 240 | 1.4010 | 0.5 |
|
| 60 |
+
| 1.4223 | 11.0 | 264 | 1.4699 | 0.4 |
|
| 61 |
+
| 1.3804 | 12.0 | 288 | 1.4915 | 0.4 |
|
| 62 |
+
| 1.3884 | 13.0 | 312 | 1.4624 | 0.4 |
|
| 63 |
+
| 1.3699 | 14.0 | 336 | 1.4798 | 0.5 |
|
| 64 |
+
| 1.3705 | 15.0 | 360 | 1.3615 | 0.5 |
|
| 65 |
+
| 1.3383 | 16.0 | 384 | 1.3814 | 0.7 |
|
| 66 |
+
| 1.3306 | 17.0 | 408 | 1.5099 | 0.4 |
|
| 67 |
+
| 1.2886 | 18.0 | 432 | 1.5039 | 0.4 |
|
| 68 |
+
| 1.2964 | 19.0 | 456 | 1.4033 | 0.5 |
|
| 69 |
+
| 1.285 | 20.0 | 480 | 1.4596 | 0.4 |
|
| 70 |
+
| 1.311 | 21.0 | 504 | 1.4100 | 0.4 |
|
| 71 |
+
| 1.218 | 22.0 | 528 | 1.3952 | 0.5 |
|
| 72 |
+
| 1.2193 | 23.0 | 552 | 1.2449 | 0.7 |
|
| 73 |
+
| 1.2618 | 24.0 | 576 | 1.2691 | 0.7 |
|
| 74 |
+
| 1.236 | 25.0 | 600 | 1.3427 | 0.7 |
|
| 75 |
+
| 1.1773 | 26.0 | 624 | 1.3669 | 0.5 |
|
| 76 |
+
| 1.1873 | 27.0 | 648 | 1.5114 | 0.5 |
|
| 77 |
+
| 1.1519 | 28.0 | 672 | 1.4285 | 0.6 |
|
| 78 |
+
| 1.1172 | 29.0 | 696 | 1.4485 | 0.5 |
|
| 79 |
+
| 1.0677 | 30.0 | 720 | 1.4442 | 0.5 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.31.0
|
| 85 |
+
- Pytorch 2.0.1+cu117
|
| 86 |
+
- Datasets 2.14.4
|
| 87 |
+
- Tokenizers 0.13.3
|