update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- rouge
|
| 6 |
+
model-index:
|
| 7 |
+
- name: pegasus-large-commentaries_hd
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# pegasus-large-commentaries_hd
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.5453
|
| 19 |
+
- Rouge1: 26.3475
|
| 20 |
+
- Rouge2: 9.5095
|
| 21 |
+
- Rougel: 22.6367
|
| 22 |
+
- Rougelsum: 22.8127
|
| 23 |
+
- Gen Len: 14.4789
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 1
|
| 44 |
+
- eval_batch_size: 1
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 5
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
|
| 55 |
+
| 2.5718 | 1.0 | 4710 | 2.5277 | 25.1384 | 8.6528 | 21.3443 | 21.5289 | 15.3268 |
|
| 56 |
+
| 2.4034 | 2.0 | 9420 | 2.4973 | 25.9298 | 9.2238 | 22.3192 | 22.4817 | 14.2243 |
|
| 57 |
+
| 2.2093 | 3.0 | 14130 | 2.5013 | 26.6036 | 9.7482 | 22.8409 | 23.0077 | 14.2263 |
|
| 58 |
+
| 2.0518 | 4.0 | 18840 | 2.5272 | 26.4723 | 9.6599 | 22.7439 | 22.9201 | 14.38 |
|
| 59 |
+
| 1.9906 | 5.0 | 23550 | 2.5453 | 26.3475 | 9.5095 | 22.6367 | 22.8127 | 14.4789 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.15.0
|
| 65 |
+
- Pytorch 1.10.0+cu111
|
| 66 |
+
- Datasets 1.17.0
|
| 67 |
+
- Tokenizers 0.10.3
|