update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: bert_12_layer_model_v1_complete_training_new_48_KD
|
| 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_12_layer_model_v1_complete_training_new_48_KD
|
| 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 |
+
- Loss: 326.4413
|
| 19 |
+
- Accuracy: 0.3018
|
| 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: 1e-05
|
| 39 |
+
- train_batch_size: 36
|
| 40 |
+
- eval_batch_size: 36
|
| 41 |
+
- seed: 10
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 10000
|
| 46 |
+
- num_epochs: 5
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
| 52 |
+
| 849.2694 | 0.06 | 10000 | 802.2138 | 0.1435 |
|
| 53 |
+
| 603.4255 | 0.12 | 20000 | 597.5114 | 0.1445 |
|
| 54 |
+
| 552.5588 | 0.18 | 30000 | 549.1310 | 0.1454 |
|
| 55 |
+
| 525.5738 | 0.25 | 40000 | 523.0781 | 0.1460 |
|
| 56 |
+
| 508.5192 | 0.31 | 50000 | 507.5772 | 0.1463 |
|
| 57 |
+
| 496.0482 | 0.37 | 60000 | 494.5385 | 0.1457 |
|
| 58 |
+
| 487.2105 | 0.43 | 70000 | 484.7273 | 0.1464 |
|
| 59 |
+
| 476.1281 | 0.49 | 80000 | 473.3444 | 0.1490 |
|
| 60 |
+
| 456.0017 | 0.55 | 90000 | 445.0464 | 0.1662 |
|
| 61 |
+
| 421.6633 | 0.61 | 100000 | 404.1071 | 0.2046 |
|
| 62 |
+
| 382.6604 | 0.68 | 110000 | 369.2148 | 0.2446 |
|
| 63 |
+
| 358.6727 | 0.74 | 120000 | 341.1114 | 0.2776 |
|
| 64 |
+
| 339.9395 | 0.8 | 130000 | 326.4413 | 0.3018 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.30.1
|
| 70 |
+
- Pytorch 1.14.0a0+410ce96
|
| 71 |
+
- Datasets 2.12.0
|
| 72 |
+
- Tokenizers 0.13.3
|