Training complete
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google-bert/bert-base-cased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- precision
|
| 8 |
+
- recall
|
| 9 |
+
- f1
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: bert-all-deep
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# bert-all-deep
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.8570
|
| 24 |
+
- Precision: 0.6195
|
| 25 |
+
- Recall: 0.7039
|
| 26 |
+
- F1: 0.6590
|
| 27 |
+
- Accuracy: 0.8148
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 2e-05
|
| 47 |
+
- train_batch_size: 8
|
| 48 |
+
- eval_batch_size: 8
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 10
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| No log | 1.0 | 363 | 0.5960 | 0.5756 | 0.6524 | 0.6116 | 0.8019 |
|
| 59 |
+
| 0.7348 | 2.0 | 726 | 0.5768 | 0.5826 | 0.6904 | 0.6319 | 0.8102 |
|
| 60 |
+
| 0.422 | 3.0 | 1089 | 0.5991 | 0.6155 | 0.6880 | 0.6497 | 0.8185 |
|
| 61 |
+
| 0.422 | 4.0 | 1452 | 0.6229 | 0.6145 | 0.7043 | 0.6564 | 0.8169 |
|
| 62 |
+
| 0.2916 | 5.0 | 1815 | 0.6857 | 0.6163 | 0.7080 | 0.6590 | 0.8159 |
|
| 63 |
+
| 0.2032 | 6.0 | 2178 | 0.7307 | 0.6277 | 0.6987 | 0.6613 | 0.8182 |
|
| 64 |
+
| 0.1531 | 7.0 | 2541 | 0.7933 | 0.6168 | 0.7103 | 0.6603 | 0.8132 |
|
| 65 |
+
| 0.1531 | 8.0 | 2904 | 0.8186 | 0.6238 | 0.6992 | 0.6594 | 0.8158 |
|
| 66 |
+
| 0.119 | 9.0 | 3267 | 0.8438 | 0.6159 | 0.7082 | 0.6589 | 0.8149 |
|
| 67 |
+
| 0.1 | 10.0 | 3630 | 0.8570 | 0.6195 | 0.7039 | 0.6590 | 0.8148 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.40.1
|
| 73 |
+
- Pytorch 2.2.1+cu121
|
| 74 |
+
- Datasets 2.19.1
|
| 75 |
+
- Tokenizers 0.19.1
|