Model save
Browse files
README.md
CHANGED
|
@@ -16,6 +16,29 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# DeepSeek-R1-Distill-Qwen-1.5B-2-contract-sections-classification-v4-10
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -43,6 +66,22 @@ The following hyperparameters were used during training:
|
|
| 43 |
- num_epochs: 10
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- PEFT 0.14.0
|
|
|
|
| 16 |
# DeepSeek-R1-Distill-Qwen-1.5B-2-contract-sections-classification-v4-10
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.5912
|
| 21 |
+
- Accuracy Evaluate: 0.2065
|
| 22 |
+
- Precision Evaluate: 0.2225
|
| 23 |
+
- Recall Evaluate: 0.2011
|
| 24 |
+
- F1 Evaluate: 0.2053
|
| 25 |
+
- Accuracy Sklearn: 0.2065
|
| 26 |
+
- Precision Sklearn: 0.2227
|
| 27 |
+
- Recall Sklearn: 0.2065
|
| 28 |
+
- F1 Sklearn: 0.2079
|
| 29 |
+
- Acuracia Rotulo Objeto: 0.2355
|
| 30 |
+
- Acuracia Rotulo Obrigacoes: 0.2290
|
| 31 |
+
- Acuracia Rotulo Valor: 0.2808
|
| 32 |
+
- Acuracia Rotulo Vigencia: 0.1969
|
| 33 |
+
- Acuracia Rotulo Rescisao: 0.1939
|
| 34 |
+
- Acuracia Rotulo Foro: 0.1538
|
| 35 |
+
- Acuracia Rotulo Reajuste: 0.1886
|
| 36 |
+
- Acuracia Rotulo Fiscalizacao: 0.0662
|
| 37 |
+
- Acuracia Rotulo Publicacao: 0.3892
|
| 38 |
+
- Acuracia Rotulo Pagamento: 0.0616
|
| 39 |
+
- Acuracia Rotulo Casos Omissos: 0.5616
|
| 40 |
+
- Acuracia Rotulo Sancoes: 0.0183
|
| 41 |
+
- Acuracia Rotulo Dotacao Orcamentaria: 0.0385
|
| 42 |
|
| 43 |
## Model description
|
| 44 |
|
|
|
|
| 66 |
- num_epochs: 10
|
| 67 |
- mixed_precision_training: Native AMP
|
| 68 |
|
| 69 |
+
### Training results
|
| 70 |
+
|
| 71 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy Evaluate | Precision Evaluate | Recall Evaluate | F1 Evaluate | Accuracy Sklearn | Precision Sklearn | Recall Sklearn | F1 Sklearn | Acuracia Rotulo Objeto | Acuracia Rotulo Obrigacoes | Acuracia Rotulo Valor | Acuracia Rotulo Vigencia | Acuracia Rotulo Rescisao | Acuracia Rotulo Foro | Acuracia Rotulo Reajuste | Acuracia Rotulo Fiscalizacao | Acuracia Rotulo Publicacao | Acuracia Rotulo Pagamento | Acuracia Rotulo Casos Omissos | Acuracia Rotulo Sancoes | Acuracia Rotulo Dotacao Orcamentaria |
|
| 72 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-----------------:|:------------------:|:---------------:|:-----------:|:----------------:|:-----------------:|:--------------:|:----------:|:----------------------:|:--------------------------:|:---------------------:|:------------------------:|:------------------------:|:--------------------:|:------------------------:|:----------------------------:|:--------------------------:|:-------------------------:|:-----------------------------:|:-----------------------:|:------------------------------------:|
|
| 73 |
+
| 3.7843 | 1.0 | 1000 | 3.6004 | 0.0655 | 0.0875 | 0.0674 | 0.0486 | 0.0655 | 0.1125 | 0.0655 | 0.0557 | 0.0744 | 0.0337 | 0.1203 | 0.0394 | 0.0388 | 0.2923 | 0.0890 | 0.0032 | 0.0 | 0.0 | 0.0 | 0.0092 | 0.1758 |
|
| 74 |
+
| 3.235 | 2.0 | 2000 | 3.2248 | 0.0762 | 0.0869 | 0.0680 | 0.0601 | 0.0762 | 0.1029 | 0.0762 | 0.0721 | 0.1178 | 0.0825 | 0.1662 | 0.0787 | 0.0499 | 0.1731 | 0.0854 | 0.0063 | 0.0148 | 0.0109 | 0.0049 | 0.0275 | 0.0659 |
|
| 75 |
+
| 2.8811 | 3.0 | 3000 | 3.0158 | 0.125 | 0.1463 | 0.1190 | 0.1212 | 0.125 | 0.1467 | 0.125 | 0.1250 | 0.1426 | 0.1650 | 0.2407 | 0.1601 | 0.0471 | 0.1308 | 0.0569 | 0.0063 | 0.0148 | 0.0145 | 0.5074 | 0.0275 | 0.0330 |
|
| 76 |
+
| 2.681 | 4.0 | 4000 | 2.8826 | 0.1635 | 0.1933 | 0.1554 | 0.1597 | 0.1635 | 0.1936 | 0.1635 | 0.1638 | 0.1446 | 0.2323 | 0.2951 | 0.1601 | 0.1330 | 0.1077 | 0.1210 | 0.0568 | 0.1527 | 0.0145 | 0.5419 | 0.0275 | 0.0330 |
|
| 77 |
+
| 2.495 | 5.0 | 5000 | 2.7849 | 0.1777 | 0.1958 | 0.1675 | 0.1711 | 0.1777 | 0.1985 | 0.1777 | 0.1774 | 0.1612 | 0.2525 | 0.2980 | 0.1654 | 0.1801 | 0.1038 | 0.1423 | 0.0631 | 0.2020 | 0.0217 | 0.5419 | 0.0183 | 0.0275 |
|
| 78 |
+
| 2.3573 | 6.0 | 6000 | 2.7106 | 0.197 | 0.2106 | 0.1877 | 0.1907 | 0.197 | 0.2128 | 0.197 | 0.1963 | 0.2211 | 0.2576 | 0.2865 | 0.1680 | 0.1967 | 0.1077 | 0.1708 | 0.0662 | 0.3202 | 0.0326 | 0.5616 | 0.0183 | 0.0330 |
|
| 79 |
+
| 2.2544 | 7.0 | 7000 | 2.6566 | 0.201 | 0.2131 | 0.1950 | 0.1969 | 0.201 | 0.2139 | 0.201 | 0.2001 | 0.2231 | 0.2441 | 0.2865 | 0.1601 | 0.1911 | 0.1308 | 0.1851 | 0.0662 | 0.3842 | 0.0507 | 0.5616 | 0.0183 | 0.0330 |
|
| 80 |
+
| 2.198 | 8.0 | 8000 | 2.6198 | 0.2015 | 0.2157 | 0.1961 | 0.1994 | 0.2015 | 0.2156 | 0.2015 | 0.2019 | 0.2335 | 0.2357 | 0.2865 | 0.1549 | 0.1884 | 0.1423 | 0.1851 | 0.0662 | 0.3842 | 0.0543 | 0.5616 | 0.0183 | 0.0385 |
|
| 81 |
+
| 2.1718 | 9.0 | 9000 | 2.5984 | 0.206 | 0.2216 | 0.2004 | 0.2046 | 0.206 | 0.2219 | 0.206 | 0.2073 | 0.2335 | 0.2290 | 0.2808 | 0.2021 | 0.1939 | 0.15 | 0.1886 | 0.0662 | 0.3842 | 0.0580 | 0.5616 | 0.0183 | 0.0385 |
|
| 82 |
+
| 2.1267 | 10.0 | 10000 | 2.5912 | 0.2065 | 0.2225 | 0.2011 | 0.2053 | 0.2065 | 0.2227 | 0.2065 | 0.2079 | 0.2355 | 0.2290 | 0.2808 | 0.1969 | 0.1939 | 0.1538 | 0.1886 | 0.0662 | 0.3892 | 0.0616 | 0.5616 | 0.0183 | 0.0385 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
### Framework versions
|
| 86 |
|
| 87 |
- PEFT 0.14.0
|