Commit
•
e41fa8a
1
Parent(s):
8a8e5fa
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: kaz_legal_bert_5
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# kaz_legal_bert_5
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 4.8262
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 4
|
| 37 |
+
- eval_batch_size: 4
|
| 38 |
+
- seed: 42
|
| 39 |
+
- gradient_accumulation_steps: 8
|
| 40 |
+
- total_train_batch_size: 32
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 5
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| 8.1161 | 0.08 | 1000 | 7.7116 |
|
| 50 |
+
| 7.6258 | 0.17 | 2000 | 7.4606 |
|
| 51 |
+
| 7.4268 | 0.25 | 3000 | 7.3184 |
|
| 52 |
+
| 7.2837 | 0.34 | 4000 | 7.2020 |
|
| 53 |
+
| 7.1969 | 0.42 | 5000 | 7.1236 |
|
| 54 |
+
| 7.1201 | 0.5 | 6000 | 7.0599 |
|
| 55 |
+
| 7.0683 | 0.59 | 7000 | 6.9990 |
|
| 56 |
+
| 6.9956 | 0.67 | 8000 | 6.9369 |
|
| 57 |
+
| 6.9392 | 0.76 | 9000 | 6.8828 |
|
| 58 |
+
| 6.8949 | 0.84 | 10000 | 6.8263 |
|
| 59 |
+
| 6.8437 | 0.92 | 11000 | 6.7913 |
|
| 60 |
+
| 6.8027 | 1.01 | 12000 | 6.7392 |
|
| 61 |
+
| 6.7539 | 1.09 | 13000 | 6.7010 |
|
| 62 |
+
| 6.7316 | 1.18 | 14000 | 6.6663 |
|
| 63 |
+
| 6.6853 | 1.26 | 15000 | 6.6338 |
|
| 64 |
+
| 6.6449 | 1.34 | 16000 | 6.6004 |
|
| 65 |
+
| 6.6188 | 1.43 | 17000 | 6.5463 |
|
| 66 |
+
| 6.5831 | 1.51 | 18000 | 6.5042 |
|
| 67 |
+
| 6.5498 | 1.6 | 19000 | 6.4581 |
|
| 68 |
+
| 6.5116 | 1.68 | 20000 | 6.4205 |
|
| 69 |
+
| 6.4579 | 1.77 | 21000 | 6.3473 |
|
| 70 |
+
| 6.3996 | 1.85 | 22000 | 6.2794 |
|
| 71 |
+
| 6.3358 | 1.93 | 23000 | 6.2082 |
|
| 72 |
+
| 6.2827 | 2.02 | 24000 | 6.1448 |
|
| 73 |
+
| 6.2381 | 2.1 | 25000 | 6.0923 |
|
| 74 |
+
| 6.1947 | 2.19 | 26000 | 6.0460 |
|
| 75 |
+
| 6.1479 | 2.27 | 27000 | 6.0002 |
|
| 76 |
+
| 6.1095 | 2.35 | 28000 | 5.9537 |
|
| 77 |
+
| 6.0669 | 2.44 | 29000 | 5.9139 |
|
| 78 |
+
| 6.0411 | 2.52 | 30000 | 5.8827 |
|
| 79 |
+
| 6.0081 | 2.61 | 31000 | 5.8454 |
|
| 80 |
+
| 5.9939 | 2.69 | 32000 | 5.8276 |
|
| 81 |
+
| 5.9714 | 2.77 | 33000 | 5.8060 |
|
| 82 |
+
| 5.9524 | 2.86 | 34000 | 5.7878 |
|
| 83 |
+
| 5.9357 | 2.94 | 35000 | 5.7772 |
|
| 84 |
+
| 5.9705 | 3.03 | 36000 | 5.7964 |
|
| 85 |
+
| 5.9276 | 3.11 | 37000 | 5.7410 |
|
| 86 |
+
| 5.8802 | 3.19 | 38000 | 5.6813 |
|
| 87 |
+
| 5.8342 | 3.28 | 39000 | 5.6268 |
|
| 88 |
+
| 5.786 | 3.36 | 40000 | 5.5729 |
|
| 89 |
+
| 5.7328 | 3.45 | 41000 | 5.5030 |
|
| 90 |
+
| 5.6604 | 3.53 | 42000 | 5.4495 |
|
| 91 |
+
| 5.6102 | 3.61 | 43000 | 5.3746 |
|
| 92 |
+
| 5.5296 | 3.7 | 44000 | 5.3149 |
|
| 93 |
+
| 5.4876 | 3.78 | 45000 | 5.2536 |
|
| 94 |
+
| 5.417 | 3.87 | 46000 | 5.2004 |
|
| 95 |
+
| 5.3665 | 3.95 | 47000 | 5.1488 |
|
| 96 |
+
| 5.3131 | 4.03 | 48000 | 5.0948 |
|
| 97 |
+
| 5.2697 | 4.12 | 49000 | 5.0538 |
|
| 98 |
+
| 5.2307 | 4.2 | 50000 | 5.0139 |
|
| 99 |
+
| 5.1975 | 4.29 | 51000 | 4.9757 |
|
| 100 |
+
| 5.1506 | 4.37 | 52000 | 4.9439 |
|
| 101 |
+
| 5.1285 | 4.45 | 53000 | 4.9238 |
|
| 102 |
+
| 5.1009 | 4.54 | 54000 | 4.8900 |
|
| 103 |
+
| 5.072 | 4.62 | 55000 | 4.8735 |
|
| 104 |
+
| 5.0533 | 4.71 | 56000 | 4.8548 |
|
| 105 |
+
| 5.0412 | 4.79 | 57000 | 4.8421 |
|
| 106 |
+
| 5.0319 | 4.88 | 58000 | 4.8326 |
|
| 107 |
+
| 5.0119 | 4.96 | 59000 | 4.8262 |
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
### Framework versions
|
| 111 |
+
|
| 112 |
+
- Transformers 4.28.1
|
| 113 |
+
- Pytorch 2.0.0+cu118
|
| 114 |
+
- Datasets 2.11.0
|
| 115 |
+
- Tokenizers 0.13.3
|