update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- rouge
|
| 7 |
+
model-index:
|
| 8 |
+
- name: flan_t5_summarization
|
| 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 |
+
# flan_t5_summarization
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6162
|
| 20 |
+
- Rouge1: 15.9418
|
| 21 |
+
- Rouge2: 7.4447
|
| 22 |
+
- Rougel: 15.5655
|
| 23 |
+
- Rougelsum: 15.5835
|
| 24 |
+
- Gen Len: 18.7313
|
| 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: 5e-05
|
| 44 |
+
- train_batch_size: 12
|
| 45 |
+
- eval_batch_size: 12
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 10
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
|
| 55 |
+
| No log | 1.0 | 272 | 1.1200 | 9.2565 | 1.2805 | 9.2358 | 9.284 | 19.0 |
|
| 56 |
+
| 1.5343 | 2.0 | 544 | 0.8923 | 10.9045 | 2.9468 | 10.9112 | 10.8827 | 19.0 |
|
| 57 |
+
| 1.5343 | 3.0 | 816 | 0.7884 | 13.637 | 4.8447 | 13.3594 | 13.3459 | 19.0 |
|
| 58 |
+
| 0.9949 | 4.0 | 1088 | 0.7257 | 15.2005 | 6.3919 | 14.781 | 14.7204 | 18.9104 |
|
| 59 |
+
| 0.9949 | 5.0 | 1360 | 0.6852 | 15.1627 | 6.3116 | 14.7187 | 14.6983 | 18.7313 |
|
| 60 |
+
| 0.8504 | 6.0 | 1632 | 0.6581 | 16.0795 | 6.9284 | 15.3516 | 15.3571 | 18.7313 |
|
| 61 |
+
| 0.8504 | 7.0 | 1904 | 0.6392 | 16.0518 | 6.9377 | 15.3914 | 15.3748 | 18.9104 |
|
| 62 |
+
| 0.7841 | 8.0 | 2176 | 0.6258 | 16.1307 | 7.6286 | 15.7398 | 15.7627 | 18.8209 |
|
| 63 |
+
| 0.7841 | 9.0 | 2448 | 0.6200 | 15.9488 | 7.4447 | 15.5654 | 15.583 | 18.7313 |
|
| 64 |
+
| 0.7599 | 10.0 | 2720 | 0.6162 | 15.9418 | 7.4447 | 15.5655 | 15.5835 | 18.7313 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.26.0
|
| 70 |
+
- Pytorch 1.13.1+cu116
|
| 71 |
+
- Datasets 2.9.0
|
| 72 |
+
- Tokenizers 0.13.2
|