Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: HBERTv1_emb_compress_48_L12_H512_A8
|
| 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 |
+
# HBERTv1_emb_compress_48_L12_H512_A8
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 6.0433
|
| 19 |
+
- Accuracy: 0.1510
|
| 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: 56
|
| 40 |
+
- eval_batch_size: 56
|
| 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 |
+
| 7.102 | 0.1 | 10000 | 7.0825 | 0.0834 |
|
| 53 |
+
| 6.6803 | 0.19 | 20000 | 6.6756 | 0.1066 |
|
| 54 |
+
| 6.5348 | 0.29 | 30000 | 6.5298 | 0.1196 |
|
| 55 |
+
| 6.4394 | 0.38 | 40000 | 6.4389 | 0.1274 |
|
| 56 |
+
| 6.3686 | 0.48 | 50000 | 6.3726 | 0.1332 |
|
| 57 |
+
| 6.3213 | 0.57 | 60000 | 6.3189 | 0.1358 |
|
| 58 |
+
| 6.281 | 0.67 | 70000 | 6.2812 | 0.1382 |
|
| 59 |
+
| 6.2506 | 0.76 | 80000 | 6.2467 | 0.1401 |
|
| 60 |
+
| 6.221 | 0.86 | 90000 | 6.2216 | 0.1423 |
|
| 61 |
+
| 6.206 | 0.96 | 100000 | 6.1978 | 0.1431 |
|
| 62 |
+
| 6.1831 | 1.05 | 110000 | 6.1796 | 0.1449 |
|
| 63 |
+
| 6.1609 | 1.15 | 120000 | 6.1630 | 0.1457 |
|
| 64 |
+
| 6.153 | 1.24 | 130000 | 6.1505 | 0.1464 |
|
| 65 |
+
| 6.142 | 1.34 | 140000 | 6.1380 | 0.1471 |
|
| 66 |
+
| 6.1281 | 1.43 | 150000 | 6.1257 | 0.1477 |
|
| 67 |
+
| 6.1173 | 1.53 | 160000 | 6.1173 | 0.1481 |
|
| 68 |
+
| 6.1102 | 1.62 | 170000 | 6.1083 | 0.1489 |
|
| 69 |
+
| 6.1011 | 1.72 | 180000 | 6.1001 | 0.1487 |
|
| 70 |
+
| 6.0869 | 1.82 | 190000 | 6.0933 | 0.1493 |
|
| 71 |
+
| 6.0838 | 1.91 | 200000 | 6.0864 | 0.1494 |
|
| 72 |
+
| 6.0745 | 2.01 | 210000 | 6.0805 | 0.1499 |
|
| 73 |
+
| 6.0757 | 2.1 | 220000 | 6.0723 | 0.1503 |
|
| 74 |
+
| 6.0695 | 2.2 | 230000 | 6.0701 | 0.1502 |
|
| 75 |
+
| 6.0595 | 2.29 | 240000 | 6.0623 | 0.1506 |
|
| 76 |
+
| 6.0579 | 2.39 | 250000 | 6.0582 | 0.1506 |
|
| 77 |
+
| 6.0534 | 2.49 | 260000 | 6.0526 | 0.1509 |
|
| 78 |
+
| 6.0465 | 2.58 | 270000 | 6.0433 | 0.1510 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.33.2
|
| 84 |
+
- Pytorch 1.14.0a0+410ce96
|
| 85 |
+
- Datasets 2.14.5
|
| 86 |
+
- Tokenizers 0.13.3
|