update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- precision
|
| 6 |
+
- recall
|
| 7 |
+
- f1
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: '5'
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# 5
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2255
|
| 22 |
+
- Precision: 0.6432
|
| 23 |
+
- Recall: 0.595
|
| 24 |
+
- F1: 0.6182
|
| 25 |
+
- Accuracy: 0.9709
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 5.5e-05
|
| 45 |
+
- train_batch_size: 32
|
| 46 |
+
- eval_batch_size: 8
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 32
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 56 |
+
| No log | 1.0 | 29 | 0.3210 | 0.0 | 0.0 | 0.0 | 0.9324 |
|
| 57 |
+
| No log | 2.0 | 58 | 0.2694 | 0.0 | 0.0 | 0.0 | 0.9324 |
|
| 58 |
+
| No log | 3.0 | 87 | 0.2216 | 0.0 | 0.0 | 0.0 | 0.9316 |
|
| 59 |
+
| No log | 4.0 | 116 | 0.2115 | 0.25 | 0.035 | 0.0614 | 0.9403 |
|
| 60 |
+
| No log | 5.0 | 145 | 0.1740 | 0.3465 | 0.175 | 0.2326 | 0.9512 |
|
| 61 |
+
| No log | 6.0 | 174 | 0.1589 | 0.42 | 0.315 | 0.36 | 0.9566 |
|
| 62 |
+
| No log | 7.0 | 203 | 0.1514 | 0.4797 | 0.295 | 0.3653 | 0.9584 |
|
| 63 |
+
| No log | 8.0 | 232 | 0.1686 | 0.4576 | 0.405 | 0.4297 | 0.9624 |
|
| 64 |
+
| No log | 9.0 | 261 | 0.1840 | 0.5971 | 0.415 | 0.4897 | 0.9646 |
|
| 65 |
+
| No log | 10.0 | 290 | 0.1571 | 0.5505 | 0.545 | 0.5477 | 0.9646 |
|
| 66 |
+
| No log | 11.0 | 319 | 0.1809 | 0.6158 | 0.545 | 0.5782 | 0.9700 |
|
| 67 |
+
| No log | 12.0 | 348 | 0.1763 | 0.6129 | 0.57 | 0.5907 | 0.9681 |
|
| 68 |
+
| No log | 13.0 | 377 | 0.1902 | 0.5571 | 0.61 | 0.5823 | 0.9655 |
|
| 69 |
+
| No log | 14.0 | 406 | 0.1916 | 0.5842 | 0.555 | 0.5692 | 0.9673 |
|
| 70 |
+
| No log | 15.0 | 435 | 0.1895 | 0.6335 | 0.605 | 0.6189 | 0.9697 |
|
| 71 |
+
| No log | 16.0 | 464 | 0.1951 | 0.5880 | 0.635 | 0.6106 | 0.9667 |
|
| 72 |
+
| No log | 17.0 | 493 | 0.1918 | 0.6324 | 0.585 | 0.6078 | 0.9702 |
|
| 73 |
+
| 0.0838 | 18.0 | 522 | 0.1957 | 0.6020 | 0.605 | 0.6035 | 0.9699 |
|
| 74 |
+
| 0.0838 | 19.0 | 551 | 0.1886 | 0.6 | 0.6 | 0.6 | 0.9681 |
|
| 75 |
+
| 0.0838 | 20.0 | 580 | 0.1992 | 0.6158 | 0.585 | 0.6 | 0.9702 |
|
| 76 |
+
| 0.0838 | 21.0 | 609 | 0.2043 | 0.625 | 0.6 | 0.6122 | 0.9706 |
|
| 77 |
+
| 0.0838 | 22.0 | 638 | 0.2110 | 0.6243 | 0.59 | 0.6067 | 0.9707 |
|
| 78 |
+
| 0.0838 | 23.0 | 667 | 0.2121 | 0.6421 | 0.61 | 0.6256 | 0.9714 |
|
| 79 |
+
| 0.0838 | 24.0 | 696 | 0.2112 | 0.6455 | 0.61 | 0.6272 | 0.9713 |
|
| 80 |
+
| 0.0838 | 25.0 | 725 | 0.2150 | 0.6392 | 0.62 | 0.6294 | 0.9711 |
|
| 81 |
+
| 0.0838 | 26.0 | 754 | 0.2229 | 0.6264 | 0.57 | 0.5969 | 0.9702 |
|
| 82 |
+
| 0.0838 | 27.0 | 783 | 0.2219 | 0.6339 | 0.58 | 0.6057 | 0.9706 |
|
| 83 |
+
| 0.0838 | 28.0 | 812 | 0.2239 | 0.6429 | 0.585 | 0.6126 | 0.9707 |
|
| 84 |
+
| 0.0838 | 29.0 | 841 | 0.2211 | 0.6402 | 0.605 | 0.6221 | 0.9713 |
|
| 85 |
+
| 0.0838 | 30.0 | 870 | 0.2230 | 0.6364 | 0.595 | 0.6150 | 0.9709 |
|
| 86 |
+
| 0.0838 | 31.0 | 899 | 0.2244 | 0.6432 | 0.595 | 0.6182 | 0.9709 |
|
| 87 |
+
| 0.0838 | 32.0 | 928 | 0.2255 | 0.6432 | 0.595 | 0.6182 | 0.9709 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- Transformers 4.28.1
|
| 93 |
+
- Pytorch 2.0.0+cu118
|
| 94 |
+
- Datasets 2.12.0
|
| 95 |
+
- Tokenizers 0.13.3
|