update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: ALL_mt5-base_15_wikiSQL
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# ALL_mt5-base_15_wikiSQL
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.2022
|
| 18 |
+
- Rouge2 Precision: 0.7669
|
| 19 |
+
- Rouge2 Recall: 0.6952
|
| 20 |
+
- Rouge2 Fmeasure: 0.7236
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 40
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 15
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:|
|
| 51 |
+
| 0.322 | 1.0 | 3239 | 0.2649 | 0.7077 | 0.6357 | 0.6638 |
|
| 52 |
+
| 0.2728 | 2.0 | 6478 | 0.2361 | 0.7294 | 0.657 | 0.6857 |
|
| 53 |
+
| 0.2353 | 3.0 | 9717 | 0.2220 | 0.7396 | 0.6677 | 0.6962 |
|
| 54 |
+
| 0.2192 | 4.0 | 12956 | 0.2159 | 0.7491 | 0.6752 | 0.7046 |
|
| 55 |
+
| 0.2044 | 5.0 | 16195 | 0.2106 | 0.7521 | 0.6797 | 0.7084 |
|
| 56 |
+
| 0.1916 | 6.0 | 19434 | 0.2076 | 0.7558 | 0.6841 | 0.7125 |
|
| 57 |
+
| 0.1815 | 7.0 | 22673 | 0.2059 | 0.759 | 0.6869 | 0.7155 |
|
| 58 |
+
| 0.1713 | 8.0 | 25912 | 0.2050 | 0.7612 | 0.6896 | 0.7179 |
|
| 59 |
+
| 0.1705 | 9.0 | 29151 | 0.2034 | 0.7644 | 0.6917 | 0.7206 |
|
| 60 |
+
| 0.1652 | 10.0 | 32390 | 0.2042 | 0.7649 | 0.6928 | 0.7214 |
|
| 61 |
+
| 0.16 | 11.0 | 35629 | 0.2026 | 0.7661 | 0.6938 | 0.7225 |
|
| 62 |
+
| 0.1534 | 12.0 | 38868 | 0.2022 | 0.7659 | 0.694 | 0.7225 |
|
| 63 |
+
| 0.1516 | 13.0 | 42107 | 0.2024 | 0.7671 | 0.695 | 0.7236 |
|
| 64 |
+
| 0.1517 | 14.0 | 45346 | 0.2024 | 0.7667 | 0.6951 | 0.7235 |
|
| 65 |
+
| 0.1503 | 15.0 | 48585 | 0.2022 | 0.7669 | 0.6952 | 0.7236 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.26.1
|
| 71 |
+
- Pytorch 2.0.1+cu117
|
| 72 |
+
- Datasets 2.14.7.dev0
|
| 73 |
+
- Tokenizers 0.13.3
|