Commit
·
3ea237f
1
Parent(s):
06759de
Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: flaubert/flaubert_small_cased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: bank-transactions-statements-classification
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# bank-transactions-statements-classification
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [flaubert/flaubert_small_cased](https://huggingface.co/flaubert/flaubert_small_cased) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.6723
|
| 21 |
+
- Accuracy: 0.8336
|
| 22 |
+
- F1 Macro: 0.8170
|
| 23 |
+
- F1 Weighted: 0.8313
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 32
|
| 44 |
+
- eval_batch_size: 32
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 10
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|
|
| 54 |
+
| No log | 1.0 | 172 | 3.1714 | 0.2004 | 0.0629 | 0.1727 |
|
| 55 |
+
| No log | 2.0 | 344 | 2.5067 | 0.3875 | 0.2393 | 0.3428 |
|
| 56 |
+
| 3.328 | 3.0 | 516 | 1.8384 | 0.5632 | 0.4761 | 0.5379 |
|
| 57 |
+
| 3.328 | 4.0 | 688 | 1.5105 | 0.6298 | 0.6035 | 0.6124 |
|
| 58 |
+
| 3.328 | 5.0 | 860 | 1.2893 | 0.6811 | 0.6673 | 0.6669 |
|
| 59 |
+
| 1.8671 | 6.0 | 1032 | 1.2444 | 0.6917 | 0.6996 | 0.6847 |
|
| 60 |
+
| 1.8671 | 7.0 | 1204 | 1.1941 | 0.7104 | 0.7196 | 0.6999 |
|
| 61 |
+
| 1.8671 | 8.0 | 1376 | 1.1427 | 0.7324 | 0.7397 | 0.7255 |
|
| 62 |
+
| 1.3422 | 9.0 | 1548 | 1.0971 | 0.7443 | 0.7567 | 0.7387 |
|
| 63 |
+
| 1.3422 | 10.0 | 1720 | 1.1076 | 0.7450 | 0.7577 | 0.7390 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.34.0
|
| 69 |
+
- Pytorch 2.0.1+cu118
|
| 70 |
+
- Datasets 2.14.5
|
| 71 |
+
- Tokenizers 0.14.1
|