Commit
•
d5fa73a
1
Parent(s):
6571834
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: kaz_legal_distilbert_full_corpus_10.0_16
|
| 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 |
+
# kaz_legal_distilbert_full_corpus_10.0_16
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [kaisar-barlybay-sse/kaz_legal_distilbert_full_corpus_10.0](https://huggingface.co/kaisar-barlybay-sse/kaz_legal_distilbert_full_corpus_10.0) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 4.0806
|
| 19 |
+
- Accuracy: 0.4351
|
| 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: 5e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 16
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 50 |
+
| 1.4013 | 1.0 | 501 | 1.3849 | 0.3473 |
|
| 51 |
+
| 1.3954 | 2.0 | 1002 | 1.3853 | 0.3234 |
|
| 52 |
+
| 1.3874 | 3.0 | 1503 | 1.3864 | 0.2216 |
|
| 53 |
+
| 1.3995 | 4.0 | 2004 | 1.3863 | 0.3513 |
|
| 54 |
+
| 1.3944 | 5.0 | 2505 | 1.3862 | 0.3473 |
|
| 55 |
+
| 1.3829 | 6.0 | 3006 | 1.3858 | 0.3713 |
|
| 56 |
+
| 1.2411 | 7.0 | 3507 | 1.4126 | 0.3972 |
|
| 57 |
+
| 0.9506 | 8.0 | 4008 | 1.7895 | 0.3992 |
|
| 58 |
+
| 0.7435 | 9.0 | 4509 | 1.5649 | 0.4212 |
|
| 59 |
+
| 0.5988 | 10.0 | 5010 | 2.6088 | 0.4371 |
|
| 60 |
+
| 0.4972 | 11.0 | 5511 | 2.8238 | 0.4371 |
|
| 61 |
+
| 0.4111 | 12.0 | 6012 | 3.2902 | 0.4431 |
|
| 62 |
+
| 0.3471 | 13.0 | 6513 | 3.5568 | 0.4212 |
|
| 63 |
+
| 0.3065 | 14.0 | 7014 | 3.9031 | 0.4351 |
|
| 64 |
+
| 0.3015 | 15.0 | 7515 | 4.0874 | 0.4311 |
|
| 65 |
+
| 0.2873 | 16.0 | 8016 | 4.0806 | 0.4351 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.28.1
|
| 71 |
+
- Pytorch 2.0.0+cu118
|
| 72 |
+
- Datasets 2.12.0
|
| 73 |
+
- Tokenizers 0.13.3
|