Commit
•
b4411f5
1
Parent(s):
316bec5
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: legal-german-roberta-base
|
| 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 |
+
# legal-german-roberta-base
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.7080
|
| 19 |
+
- Accuracy: 0.8387
|
| 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: 1024
|
| 40 |
+
- eval_batch_size: 512
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 45 |
+
- training_steps: 1000000
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:-------:|:--------:|:---------------:|
|
| 51 |
+
| 2.1008 | 0.05 | 50000 | 0.6533 | 2.0523 |
|
| 52 |
+
| 1.5248 | 0.1 | 100000 | 0.7661 | 1.1575 |
|
| 53 |
+
| 1.3152 | 0.15 | 150000 | 0.7674 | 1.1281 |
|
| 54 |
+
| 1.1239 | 0.2 | 200000 | 0.7971 | 0.9458 |
|
| 55 |
+
| 0.9472 | 0.25 | 250000 | 0.7876 | 0.9979 |
|
| 56 |
+
| 0.961 | 0.3 | 300000 | 0.8075 | 0.8798 |
|
| 57 |
+
| 1.0179 | 0.35 | 350000 | 0.8018 | 0.9102 |
|
| 58 |
+
| 1.037 | 0.4 | 400000 | 0.8195 | 0.8107 |
|
| 59 |
+
| 1.1206 | 0.45 | 450000 | 0.8152 | 0.8323 |
|
| 60 |
+
| 1.0865 | 0.5 | 500000 | 0.8242 | 0.7829 |
|
| 61 |
+
| 0.9616 | 0.55 | 550000 | 0.8224 | 0.7895 |
|
| 62 |
+
| 0.7727 | 0.6 | 600000 | 0.8285 | 0.7585 |
|
| 63 |
+
| 0.9871 | 1.04 | 650000 | 0.8320 | 0.7391 |
|
| 64 |
+
| 1.0679 | 1.09 | 700000 | 0.8311 | 0.7436 |
|
| 65 |
+
| 0.9203 | 1.14 | 750000 | 0.8355 | 0.7187 |
|
| 66 |
+
| 0.9626 | 1.19 | 800000 | 0.8353 | 0.7242 |
|
| 67 |
+
| 0.7263 | 1.24 | 850000 | 0.7094 | 0.8378 |
|
| 68 |
+
| 0.8578 | 1.29 | 900000 | 0.7140 | 0.8368 |
|
| 69 |
+
| 0.7693 | 1.34 | 950000 | 0.7091 | 0.8377 |
|
| 70 |
+
| 1.0488 | 1.39 | 1000000 | 0.7080 | 0.8387 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.20.1
|
| 76 |
+
- Pytorch 1.10.0+cu113
|
| 77 |
+
- Datasets 2.8.0
|
| 78 |
+
- Tokenizers 0.12.1
|