update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- simplification
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: flan-t5-base-clara-med
|
| 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 |
+
# flan-t5-base-clara-med
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.2296
|
| 21 |
+
- Rouge1: 29.9558
|
| 22 |
+
- Rouge2: 16.9558
|
| 23 |
+
- Rougel: 28.1645
|
| 24 |
+
- Rougelsum: 28.1582
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5.6e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 30
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
| 55 |
+
| No log | 1.0 | 380 | 1.4310 | 27.8189 | 15.801 | 26.3299 | 26.2963 |
|
| 56 |
+
| No log | 2.0 | 760 | 1.3600 | 28.154 | 15.998 | 26.6032 | 26.606 |
|
| 57 |
+
| 1.6592 | 3.0 | 1140 | 1.3062 | 28.5836 | 16.3289 | 27.1685 | 27.1789 |
|
| 58 |
+
| 1.6592 | 4.0 | 1520 | 1.2747 | 29.1122 | 16.6792 | 27.5758 | 27.5733 |
|
| 59 |
+
| 1.3824 | 5.0 | 1900 | 1.2505 | 28.9849 | 16.4234 | 27.343 | 27.3457 |
|
| 60 |
+
| 1.3824 | 6.0 | 2280 | 1.2358 | 29.2208 | 16.7068 | 27.5005 | 27.4958 |
|
| 61 |
+
| 1.3824 | 7.0 | 2660 | 1.2317 | 29.4609 | 17.1435 | 27.7924 | 27.809 |
|
| 62 |
+
| 1.2296 | 8.0 | 3040 | 1.2215 | 29.9464 | 17.1933 | 28.1208 | 28.1532 |
|
| 63 |
+
| 1.2296 | 9.0 | 3420 | 1.2187 | 29.8723 | 17.2898 | 27.9957 | 28.0209 |
|
| 64 |
+
| 1.1295 | 10.0 | 3800 | 1.2143 | 29.76 | 17.2644 | 27.9598 | 27.9482 |
|
| 65 |
+
| 1.1295 | 11.0 | 4180 | 1.2044 | 29.5394 | 16.9554 | 27.7543 | 27.7495 |
|
| 66 |
+
| 1.1295 | 12.0 | 4560 | 1.2082 | 29.6155 | 17.0565 | 27.9131 | 27.9027 |
|
| 67 |
+
| 1.0493 | 13.0 | 4940 | 1.2047 | 30.0647 | 17.314 | 28.3498 | 28.3241 |
|
| 68 |
+
| 1.0493 | 14.0 | 5320 | 1.2073 | 29.8209 | 17.0308 | 27.9766 | 27.9716 |
|
| 69 |
+
| 0.9857 | 15.0 | 5700 | 1.2058 | 29.7392 | 17.0373 | 28.0291 | 28.029 |
|
| 70 |
+
| 0.9857 | 16.0 | 6080 | 1.2077 | 30.1819 | 17.298 | 28.3771 | 28.3706 |
|
| 71 |
+
| 0.9857 | 17.0 | 6460 | 1.2043 | 30.0708 | 17.2588 | 28.3525 | 28.3654 |
|
| 72 |
+
| 0.9331 | 18.0 | 6840 | 1.2103 | 29.9749 | 17.0748 | 28.1575 | 28.1827 |
|
| 73 |
+
| 0.9331 | 19.0 | 7220 | 1.2086 | 29.561 | 16.8513 | 27.7646 | 27.7808 |
|
| 74 |
+
| 0.8997 | 20.0 | 7600 | 1.2183 | 30.1109 | 17.186 | 28.3103 | 28.3078 |
|
| 75 |
+
| 0.8997 | 21.0 | 7980 | 1.2177 | 29.851 | 17.0093 | 28.0336 | 28.0348 |
|
| 76 |
+
| 0.8997 | 22.0 | 8360 | 1.2181 | 30.2841 | 17.5662 | 28.5167 | 28.526 |
|
| 77 |
+
| 0.8628 | 23.0 | 8740 | 1.2224 | 29.8959 | 17.0802 | 28.1386 | 28.1456 |
|
| 78 |
+
| 0.8628 | 24.0 | 9120 | 1.2244 | 29.9 | 17.1425 | 28.1456 | 28.1179 |
|
| 79 |
+
| 0.8369 | 25.0 | 9500 | 1.2234 | 30.0394 | 17.0066 | 28.2387 | 28.2345 |
|
| 80 |
+
| 0.8369 | 26.0 | 9880 | 1.2266 | 29.9758 | 17.1042 | 28.2635 | 28.2669 |
|
| 81 |
+
| 0.8369 | 27.0 | 10260 | 1.2263 | 29.893 | 16.993 | 28.0106 | 28.0009 |
|
| 82 |
+
| 0.8187 | 28.0 | 10640 | 1.2272 | 29.9718 | 17.0048 | 28.1821 | 28.1751 |
|
| 83 |
+
| 0.8187 | 29.0 | 11020 | 1.2279 | 29.973 | 17.0096 | 28.1837 | 28.1655 |
|
| 84 |
+
| 0.8181 | 30.0 | 11400 | 1.2296 | 29.9558 | 16.9558 | 28.1645 | 28.1582 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.25.1
|
| 90 |
+
- Pytorch 1.13.0
|
| 91 |
+
- Datasets 2.8.0
|
| 92 |
+
- Tokenizers 0.12.1
|