Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: bert-pretrained-wikitext-2-raw-v1
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# bert-pretrained-wikitext-2-raw-v1
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 7.9307
|
| 17 |
+
- Masked ml accuracy: 0.1485
|
| 18 |
+
- Nsp accuracy: 0.7891
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 32
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 20
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss | Masked ml accuracy | Nsp accuracy |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------------------:|:------------:|
|
| 49 |
+
| 7.9726 | 1.0 | 564 | 7.5680 | 0.1142 | 0.5 |
|
| 50 |
+
| 7.5085 | 2.0 | 1128 | 7.4155 | 0.1329 | 0.5557 |
|
| 51 |
+
| 7.4112 | 3.0 | 1692 | 7.3729 | 0.1380 | 0.5675 |
|
| 52 |
+
| 7.3352 | 4.0 | 2256 | 7.2816 | 0.1398 | 0.6060 |
|
| 53 |
+
| 7.2823 | 5.0 | 2820 | 7.1709 | 0.1414 | 0.6884 |
|
| 54 |
+
| 7.1828 | 6.0 | 3384 | 7.1503 | 0.1417 | 0.7109 |
|
| 55 |
+
| 7.0796 | 7.0 | 3948 | 7.0909 | 0.1431 | 0.7430 |
|
| 56 |
+
| 6.8699 | 8.0 | 4512 | 7.1666 | 0.1422 | 0.7238 |
|
| 57 |
+
| 6.7819 | 9.0 | 5076 | 7.2507 | 0.1467 | 0.7345 |
|
| 58 |
+
| 6.7269 | 10.0 | 5640 | 7.2654 | 0.1447 | 0.7484 |
|
| 59 |
+
| 6.6701 | 11.0 | 6204 | 7.3642 | 0.1439 | 0.7784 |
|
| 60 |
+
| 6.613 | 12.0 | 6768 | 7.5089 | 0.1447 | 0.7677 |
|
| 61 |
+
| 6.5577 | 13.0 | 7332 | 7.7611 | 0.1469 | 0.7655 |
|
| 62 |
+
| 6.5197 | 14.0 | 7896 | 7.5984 | 0.1465 | 0.7827 |
|
| 63 |
+
| 6.4626 | 15.0 | 8460 | 7.6738 | 0.1449 | 0.8030 |
|
| 64 |
+
| 6.4026 | 16.0 | 9024 | 7.7009 | 0.1457 | 0.7869 |
|
| 65 |
+
| 6.3861 | 17.0 | 9588 | 7.7586 | 0.1503 | 0.7955 |
|
| 66 |
+
| 6.3779 | 18.0 | 10152 | 7.7792 | 0.1494 | 0.8019 |
|
| 67 |
+
| 6.357 | 19.0 | 10716 | 7.8532 | 0.1479 | 0.7966 |
|
| 68 |
+
| 6.3354 | 20.0 | 11280 | 7.9307 | 0.1485 | 0.7891 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.33.1
|
| 74 |
+
- Pytorch 2.0.1+cu118
|
| 75 |
+
- Datasets 2.14.5
|
| 76 |
+
- Tokenizers 0.13.3
|