update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: bert_large_subjqa_model_v3
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# bert_large_subjqa_model_v3
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [bert-large-uncased-whole-word-masking-finetuned-squad](https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 8.8423
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 2e-05
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 15
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| No log | 1.0 | 410 | 2.3971 |
|
| 49 |
+
| 2.5672 | 2.0 | 820 | 2.7380 |
|
| 50 |
+
| 1.6385 | 3.0 | 1230 | 3.1387 |
|
| 51 |
+
| 0.8467 | 4.0 | 1640 | 4.0478 |
|
| 52 |
+
| 0.4177 | 5.0 | 2050 | 4.9824 |
|
| 53 |
+
| 0.4177 | 6.0 | 2460 | 5.5992 |
|
| 54 |
+
| 0.2208 | 7.0 | 2870 | 6.2417 |
|
| 55 |
+
| 0.1469 | 8.0 | 3280 | 7.1139 |
|
| 56 |
+
| 0.0966 | 9.0 | 3690 | 8.0166 |
|
| 57 |
+
| 0.0746 | 10.0 | 4100 | 7.7937 |
|
| 58 |
+
| 0.0589 | 11.0 | 4510 | 7.8738 |
|
| 59 |
+
| 0.0589 | 12.0 | 4920 | 8.3362 |
|
| 60 |
+
| 0.0439 | 13.0 | 5330 | 8.6546 |
|
| 61 |
+
| 0.0388 | 14.0 | 5740 | 8.8050 |
|
| 62 |
+
| 0.029 | 15.0 | 6150 | 8.8423 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.28.0
|
| 68 |
+
- Pytorch 1.13.0a0+d321be6
|
| 69 |
+
- Datasets 2.12.0
|
| 70 |
+
- Tokenizers 0.13.3
|