Commit
·
3ab2185
1
Parent(s):
072f751
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: t5-small-github-repo-tag-generation
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# t5-small-github-repo-tag-generation
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.5366
|
| 20 |
+
- Rouge1: 20.3802
|
| 21 |
+
- Rouge2: 4.7145
|
| 22 |
+
- Rougel: 18.411
|
| 23 |
+
- Rougelsum: 18.3921
|
| 24 |
+
- Gen Len: 19.0
|
| 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: 2e-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 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
|
| 56 |
+
| 1.4594 | 1.0 | 66 | 0.9943 | 3.9283 | 0.0 | 3.7797 | 3.7332 | 19.0 |
|
| 57 |
+
| 0.9732 | 2.0 | 132 | 0.8077 | 1.3301 | 0.0 | 1.2269 | 1.2141 | 19.0 |
|
| 58 |
+
| 0.8414 | 3.0 | 198 | 0.7334 | 4.3519 | 0.3755 | 4.2376 | 4.2974 | 19.0 |
|
| 59 |
+
| 0.7843 | 4.0 | 264 | 0.6971 | 17.7535 | 1.5237 | 16.2304 | 16.1943 | 19.0 |
|
| 60 |
+
| 0.7463 | 5.0 | 330 | 0.6655 | 19.3128 | 2.2678 | 16.5655 | 16.5492 | 19.0 |
|
| 61 |
+
| 0.7182 | 6.0 | 396 | 0.6412 | 19.8633 | 3.3647 | 17.5046 | 17.4973 | 19.0 |
|
| 62 |
+
| 0.6959 | 7.0 | 462 | 0.6286 | 20.274 | 3.1415 | 17.8527 | 17.9039 | 19.0 |
|
| 63 |
+
| 0.6793 | 8.0 | 528 | 0.6121 | 19.9915 | 3.5137 | 18.1718 | 18.2166 | 19.0 |
|
| 64 |
+
| 0.6666 | 9.0 | 594 | 0.6021 | 20.073 | 3.6482 | 18.3466 | 18.3829 | 19.0 |
|
| 65 |
+
| 0.6561 | 10.0 | 660 | 0.5923 | 20.6227 | 3.8946 | 18.6466 | 18.694 | 19.0 |
|
| 66 |
+
| 0.6471 | 11.0 | 726 | 0.5867 | 20.3914 | 4.1584 | 18.5822 | 18.5744 | 19.0 |
|
| 67 |
+
| 0.638 | 12.0 | 792 | 0.5776 | 20.9846 | 4.6568 | 18.8597 | 18.8979 | 19.0 |
|
| 68 |
+
| 0.6343 | 13.0 | 858 | 0.5715 | 19.7497 | 4.4363 | 18.262 | 18.2526 | 19.0 |
|
| 69 |
+
| 0.6267 | 14.0 | 924 | 0.5670 | 19.5839 | 4.2251 | 17.9116 | 17.9491 | 19.0 |
|
| 70 |
+
| 0.6211 | 15.0 | 990 | 0.5602 | 19.4954 | 4.4755 | 17.9726 | 17.9203 | 19.0 |
|
| 71 |
+
| 0.6169 | 16.0 | 1056 | 0.5557 | 19.6247 | 4.2106 | 18.0385 | 18.0922 | 19.0 |
|
| 72 |
+
| 0.6103 | 17.0 | 1122 | 0.5532 | 19.8744 | 4.4672 | 18.1794 | 18.1689 | 19.0 |
|
| 73 |
+
| 0.6062 | 18.0 | 1188 | 0.5505 | 19.8744 | 4.3368 | 18.1794 | 18.1689 | 19.0 |
|
| 74 |
+
| 0.6016 | 19.0 | 1254 | 0.5461 | 20.083 | 4.3446 | 18.4196 | 18.383 | 19.0 |
|
| 75 |
+
| 0.5987 | 20.0 | 1320 | 0.5426 | 20.029 | 4.5884 | 18.189 | 18.1371 | 19.0 |
|
| 76 |
+
| 0.5968 | 21.0 | 1386 | 0.5407 | 19.5394 | 4.0665 | 17.8456 | 17.7709 | 19.0 |
|
| 77 |
+
| 0.5957 | 22.0 | 1452 | 0.5387 | 19.6368 | 4.5837 | 18.0482 | 18.0676 | 19.0 |
|
| 78 |
+
| 0.5923 | 23.0 | 1518 | 0.5366 | 20.0744 | 4.8413 | 18.3513 | 18.2666 | 19.0 |
|
| 79 |
+
| 0.588 | 24.0 | 1584 | 0.5366 | 20.3802 | 4.7145 | 18.411 | 18.3921 | 19.0 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.26.1
|
| 85 |
+
- Pytorch 1.13.1+cu116
|
| 86 |
+
- Datasets 2.10.0
|
| 87 |
+
- Tokenizers 0.13.2
|