update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: model_from_berturk_1401_v3
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# model_from_berturk_1401_v3
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.4042
|
| 23 |
+
- Precision: 0.8896
|
| 24 |
+
- Recall: 0.8841
|
| 25 |
+
- F1: 0.8868
|
| 26 |
+
- Accuracy: 0.9198
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 2e-05
|
| 46 |
+
- train_batch_size: 32
|
| 47 |
+
- eval_batch_size: 32
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 15
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 57 |
+
| No log | 1.0 | 244 | 0.3948 | 0.8565 | 0.8508 | 0.8536 | 0.8932 |
|
| 58 |
+
| No log | 2.0 | 488 | 0.3331 | 0.8724 | 0.8663 | 0.8693 | 0.9060 |
|
| 59 |
+
| 0.6019 | 3.0 | 732 | 0.3061 | 0.8855 | 0.8746 | 0.8800 | 0.9147 |
|
| 60 |
+
| 0.6019 | 4.0 | 976 | 0.3025 | 0.8881 | 0.8828 | 0.8855 | 0.9177 |
|
| 61 |
+
| 0.2753 | 5.0 | 1220 | 0.3137 | 0.8807 | 0.8819 | 0.8813 | 0.9148 |
|
| 62 |
+
| 0.2753 | 6.0 | 1464 | 0.3140 | 0.8876 | 0.8854 | 0.8865 | 0.9178 |
|
| 63 |
+
| 0.1963 | 7.0 | 1708 | 0.3210 | 0.8871 | 0.8840 | 0.8855 | 0.9182 |
|
| 64 |
+
| 0.1963 | 8.0 | 1952 | 0.3304 | 0.8908 | 0.8855 | 0.8882 | 0.9208 |
|
| 65 |
+
| 0.1431 | 9.0 | 2196 | 0.3452 | 0.8907 | 0.8843 | 0.8875 | 0.9206 |
|
| 66 |
+
| 0.1431 | 10.0 | 2440 | 0.3584 | 0.8896 | 0.8835 | 0.8865 | 0.9201 |
|
| 67 |
+
| 0.1061 | 11.0 | 2684 | 0.3770 | 0.8883 | 0.8849 | 0.8866 | 0.9191 |
|
| 68 |
+
| 0.1061 | 12.0 | 2928 | 0.3852 | 0.8876 | 0.8834 | 0.8855 | 0.9186 |
|
| 69 |
+
| 0.082 | 13.0 | 3172 | 0.3941 | 0.8894 | 0.8833 | 0.8863 | 0.9195 |
|
| 70 |
+
| 0.082 | 14.0 | 3416 | 0.3973 | 0.8893 | 0.8842 | 0.8867 | 0.9197 |
|
| 71 |
+
| 0.0694 | 15.0 | 3660 | 0.4042 | 0.8896 | 0.8841 | 0.8868 | 0.9198 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.25.1
|
| 77 |
+
- Pytorch 1.13.0+cu116
|
| 78 |
+
- Datasets 2.8.0
|
| 79 |
+
- Tokenizers 0.13.2
|