update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- wikihow
|
| 7 |
+
metrics:
|
| 8 |
+
- rouge
|
| 9 |
+
model-index:
|
| 10 |
+
- name: t5-small-finetuned-wikihow_3epoch_b4_lr3e-3
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Sequence-to-sequence Language Modeling
|
| 14 |
+
type: text2text-generation
|
| 15 |
+
dataset:
|
| 16 |
+
name: wikihow
|
| 17 |
+
type: wikihow
|
| 18 |
+
args: all
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Rouge1
|
| 21 |
+
type: rouge
|
| 22 |
+
value: 26.7383
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# t5-small-finetuned-wikihow_3epoch_b4_lr3e-3
|
| 29 |
+
|
| 30 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the wikihow dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 2.3400
|
| 33 |
+
- Rouge1: 26.7383
|
| 34 |
+
- Rouge2: 10.1981
|
| 35 |
+
- Rougel: 22.8642
|
| 36 |
+
- Rougelsum: 26.0922
|
| 37 |
+
- Gen Len: 18.524
|
| 38 |
+
|
| 39 |
+
## Model description
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Intended uses & limitations
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training and evaluation data
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Training procedure
|
| 52 |
+
|
| 53 |
+
### Training hyperparameters
|
| 54 |
+
|
| 55 |
+
The following hyperparameters were used during training:
|
| 56 |
+
- learning_rate: 0.003
|
| 57 |
+
- train_batch_size: 4
|
| 58 |
+
- eval_batch_size: 4
|
| 59 |
+
- seed: 42
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- num_epochs: 3
|
| 63 |
+
- mixed_precision_training: Native AMP
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 68 |
+
|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 69 |
+
| 3.2548 | 0.13 | 5000 | 2.9708 | 22.0519 | 6.7142 | 18.7677 | 21.4627 | 17.9546 |
|
| 70 |
+
| 3.1153 | 0.25 | 10000 | 2.9099 | 20.2838 | 5.8365 | 17.5009 | 19.7112 | 18.4981 |
|
| 71 |
+
| 3.0478 | 0.38 | 15000 | 2.8763 | 22.8282 | 7.3649 | 19.6843 | 22.2312 | 18.1331 |
|
| 72 |
+
| 3.0146 | 0.51 | 20000 | 2.8484 | 23.2465 | 7.4295 | 19.621 | 22.6246 | 18.5115 |
|
| 73 |
+
| 2.9572 | 0.64 | 25000 | 2.7902 | 23.8681 | 7.9617 | 20.4984 | 23.2066 | 18.5544 |
|
| 74 |
+
| 2.9425 | 0.76 | 30000 | 2.7577 | 23.4402 | 7.5289 | 19.7382 | 22.7941 | 18.4613 |
|
| 75 |
+
| 2.9075 | 0.89 | 35000 | 2.7343 | 23.0082 | 7.5408 | 19.8426 | 22.3832 | 18.1218 |
|
| 76 |
+
| 2.8705 | 1.02 | 40000 | 2.7136 | 23.9492 | 7.8861 | 20.3675 | 23.3035 | 18.4869 |
|
| 77 |
+
| 2.7967 | 1.14 | 45000 | 2.6923 | 24.2394 | 8.2895 | 20.7275 | 23.6127 | 18.3486 |
|
| 78 |
+
| 2.7794 | 1.27 | 50000 | 2.6639 | 24.4062 | 8.2481 | 20.8957 | 23.8077 | 18.4258 |
|
| 79 |
+
| 2.7776 | 1.4 | 55000 | 2.6321 | 24.6213 | 8.4161 | 21.0528 | 23.968 | 18.351 |
|
| 80 |
+
| 2.7397 | 1.53 | 60000 | 2.6116 | 24.16 | 8.3605 | 20.618 | 23.5037 | 18.6049 |
|
| 81 |
+
| 2.7199 | 1.65 | 65000 | 2.5846 | 24.2606 | 8.3829 | 20.6274 | 23.6252 | 18.4742 |
|
| 82 |
+
| 2.7044 | 1.78 | 70000 | 2.5663 | 25.0452 | 8.896 | 21.4554 | 24.4748 | 18.3143 |
|
| 83 |
+
| 2.6928 | 1.91 | 75000 | 2.5365 | 25.1312 | 9.008 | 21.6376 | 24.4963 | 18.5605 |
|
| 84 |
+
| 2.6281 | 2.03 | 80000 | 2.5209 | 25.5311 | 9.1521 | 21.729 | 24.8864 | 18.2597 |
|
| 85 |
+
| 2.5333 | 2.16 | 85000 | 2.4860 | 25.4834 | 9.2969 | 21.7257 | 24.8802 | 18.3831 |
|
| 86 |
+
| 2.5308 | 2.29 | 90000 | 2.4619 | 26.0526 | 9.605 | 22.2178 | 25.4353 | 18.4235 |
|
| 87 |
+
| 2.5136 | 2.42 | 95000 | 2.4356 | 25.9434 | 9.6537 | 22.2957 | 25.312 | 18.4647 |
|
| 88 |
+
| 2.4801 | 2.54 | 100000 | 2.4098 | 26.1109 | 9.7637 | 22.3844 | 25.4771 | 18.5765 |
|
| 89 |
+
| 2.4494 | 2.67 | 105000 | 2.3835 | 26.332 | 9.9472 | 22.4243 | 25.6933 | 18.5985 |
|
| 90 |
+
| 2.4393 | 2.8 | 110000 | 2.3590 | 26.6896 | 10.2248 | 22.8743 | 26.0665 | 18.4883 |
|
| 91 |
+
| 2.4071 | 2.93 | 115000 | 2.3400 | 26.7383 | 10.1981 | 22.8642 | 26.0922 | 18.524 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
### Framework versions
|
| 95 |
+
|
| 96 |
+
- Transformers 4.18.0
|
| 97 |
+
- Pytorch 1.10.0+cu111
|
| 98 |
+
- Datasets 2.0.0
|
| 99 |
+
- Tokenizers 0.11.6
|