Commit
•
2fc5157
1
Parent(s):
35ae0c5
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- fill-mask
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: deberta-v3-large-dapt-scientific-papers-pubmed
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# deberta-v3-large-dapt-scientific-papers-pubmed
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 4.4729
|
| 21 |
+
- Accuracy: 0.3510
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-06
|
| 41 |
+
- train_batch_size: 12
|
| 42 |
+
- eval_batch_size: 12
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 10000
|
| 47 |
+
- training_steps: 21600
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 54 |
+
| 12.0315 | 0.02 | 500 | 11.6840 | 0.0 |
|
| 55 |
+
| 11.0675 | 0.05 | 1000 | 8.9471 | 0.0226 |
|
| 56 |
+
| 8.6646 | 0.07 | 1500 | 8.0093 | 0.0344 |
|
| 57 |
+
| 8.3625 | 0.09 | 2000 | 7.9624 | 0.0274 |
|
| 58 |
+
| 8.2467 | 0.12 | 2500 | 7.6599 | 0.0376 |
|
| 59 |
+
| 7.9714 | 0.14 | 3000 | 7.6716 | 0.0316 |
|
| 60 |
+
| 7.9852 | 0.16 | 3500 | 7.4535 | 0.0385 |
|
| 61 |
+
| 7.7502 | 0.19 | 4000 | 7.4293 | 0.0429 |
|
| 62 |
+
| 7.7016 | 0.21 | 4500 | 7.3576 | 0.0397 |
|
| 63 |
+
| 7.5789 | 0.23 | 5000 | 7.3124 | 0.0513 |
|
| 64 |
+
| 7.4141 | 0.25 | 5500 | 7.1353 | 0.0634 |
|
| 65 |
+
| 7.2365 | 0.28 | 6000 | 6.8600 | 0.0959 |
|
| 66 |
+
| 7.0725 | 0.3 | 6500 | 6.5743 | 0.1150 |
|
| 67 |
+
| 6.934 | 0.32 | 7000 | 6.3674 | 0.1415 |
|
| 68 |
+
| 6.7219 | 0.35 | 7500 | 6.3467 | 0.1581 |
|
| 69 |
+
| 6.5039 | 0.37 | 8000 | 6.1312 | 0.1815 |
|
| 70 |
+
| 6.3096 | 0.39 | 8500 | 5.9080 | 0.2134 |
|
| 71 |
+
| 6.1835 | 0.42 | 9000 | 5.8414 | 0.2137 |
|
| 72 |
+
| 6.0939 | 0.44 | 9500 | 5.5137 | 0.2553 |
|
| 73 |
+
| 6.0457 | 0.46 | 10000 | 5.5881 | 0.2545 |
|
| 74 |
+
| 5.8851 | 0.49 | 10500 | 5.5134 | 0.2497 |
|
| 75 |
+
| 5.7277 | 0.51 | 11000 | 5.3023 | 0.2699 |
|
| 76 |
+
| 5.6183 | 0.53 | 11500 | 5.0074 | 0.3019 |
|
| 77 |
+
| 5.4978 | 0.56 | 12000 | 5.1822 | 0.2814 |
|
| 78 |
+
| 5.5916 | 0.58 | 12500 | 5.1211 | 0.2808 |
|
| 79 |
+
| 5.4749 | 0.6 | 13000 | 4.9126 | 0.2972 |
|
| 80 |
+
| 5.3765 | 0.62 | 13500 | 5.0468 | 0.2899 |
|
| 81 |
+
| 5.3529 | 0.65 | 14000 | 4.8160 | 0.3037 |
|
| 82 |
+
| 5.2993 | 0.67 | 14500 | 4.8598 | 0.3141 |
|
| 83 |
+
| 5.2929 | 0.69 | 15000 | 4.9669 | 0.3052 |
|
| 84 |
+
| 5.2649 | 0.72 | 15500 | 4.7849 | 0.3270 |
|
| 85 |
+
| 5.162 | 0.74 | 16000 | 4.6819 | 0.3357 |
|
| 86 |
+
| 5.1639 | 0.76 | 16500 | 4.6056 | 0.3275 |
|
| 87 |
+
| 5.1245 | 0.79 | 17000 | 4.5473 | 0.3311 |
|
| 88 |
+
| 5.1596 | 0.81 | 17500 | 4.7008 | 0.3212 |
|
| 89 |
+
| 5.1346 | 0.83 | 18000 | 4.7932 | 0.3192 |
|
| 90 |
+
| 5.1174 | 0.86 | 18500 | 4.7624 | 0.3208 |
|
| 91 |
+
| 5.1152 | 0.88 | 19000 | 4.6388 | 0.3274 |
|
| 92 |
+
| 5.0852 | 0.9 | 19500 | 4.5247 | 0.3305 |
|
| 93 |
+
| 5.0564 | 0.93 | 20000 | 4.6982 | 0.3161 |
|
| 94 |
+
| 5.0179 | 0.95 | 20500 | 4.5363 | 0.3389 |
|
| 95 |
+
| 5.07 | 0.97 | 21000 | 4.6647 | 0.3307 |
|
| 96 |
+
| 5.0781 | 1.0 | 21500 | 4.4729 | 0.3510 |
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
### Framework versions
|
| 100 |
+
|
| 101 |
+
- Transformers 4.18.0
|
| 102 |
+
- Pytorch 1.11.0
|
| 103 |
+
- Datasets 2.1.0
|
| 104 |
+
- Tokenizers 0.12.1
|