update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: bert-small-juman-bpe
|
| 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 |
+
# bert-small-juman-bpe
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Accuracy: 0.6317
|
| 19 |
+
- Loss: 1.7829
|
| 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: 0.0001
|
| 39 |
+
- train_batch_size: 256
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 3
|
| 44 |
+
- total_train_batch_size: 768
|
| 45 |
+
- total_eval_batch_size: 24
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.01
|
| 49 |
+
- num_epochs: 14
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:------:|:--------:|:---------------:|
|
| 56 |
+
| 2.3892 | 1.0 | 69472 | 0.5637 | 2.2498 |
|
| 57 |
+
| 2.2219 | 2.0 | 138944 | 0.5873 | 2.0785 |
|
| 58 |
+
| 2.1453 | 3.0 | 208416 | 0.5984 | 2.0019 |
|
| 59 |
+
| 2.1 | 4.0 | 277888 | 0.6059 | 1.9531 |
|
| 60 |
+
| 2.068 | 5.0 | 347360 | 0.6106 | 1.9169 |
|
| 61 |
+
| 2.0405 | 6.0 | 416832 | 0.6146 | 1.8921 |
|
| 62 |
+
| 2.0174 | 7.0 | 486304 | 0.6175 | 1.8711 |
|
| 63 |
+
| 2.0002 | 8.0 | 555776 | 0.6205 | 1.8527 |
|
| 64 |
+
| 1.9838 | 9.0 | 625248 | 0.6225 | 1.8381 |
|
| 65 |
+
| 1.9691 | 10.0 | 694720 | 0.6248 | 1.8239 |
|
| 66 |
+
| 1.9551 | 11.0 | 764192 | 0.6265 | 1.8125 |
|
| 67 |
+
| 1.9406 | 12.0 | 833664 | 0.6288 | 1.8002 |
|
| 68 |
+
| 1.9293 | 13.0 | 903136 | 0.6310 | 1.7871 |
|
| 69 |
+
| 1.9247 | 14.0 | 972608 | 0.6317 | 1.7829 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.19.2
|
| 75 |
+
- Pytorch 1.12.0+cu116
|
| 76 |
+
- Datasets 2.2.2
|
| 77 |
+
- Tokenizers 0.12.1
|