Commit
•
f2686b9
1
Parent(s):
7b87ede
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- samsum
|
| 6 |
+
model-index:
|
| 7 |
+
- name: pegasus-samsum-1
|
| 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-samsum-1
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/pegasus-cnn_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail) on the samsum dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.3783
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 1
|
| 39 |
+
- eval_batch_size: 1
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 2
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 500
|
| 46 |
+
- num_epochs: 1
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 1.7182 | 0.07 | 500 | 1.6019 |
|
| 53 |
+
| 1.805 | 0.14 | 1000 | 1.5057 |
|
| 54 |
+
| 1.7421 | 0.2 | 1500 | 1.4710 |
|
| 55 |
+
| 1.4131 | 0.27 | 2000 | 1.4522 |
|
| 56 |
+
| 1.5483 | 0.34 | 2500 | 1.4422 |
|
| 57 |
+
| 1.2689 | 0.41 | 3000 | 1.4297 |
|
| 58 |
+
| 2.0376 | 0.48 | 3500 | 1.4136 |
|
| 59 |
+
| 1.5208 | 0.54 | 4000 | 1.4089 |
|
| 60 |
+
| 1.6772 | 0.61 | 4500 | 1.3973 |
|
| 61 |
+
| 1.5757 | 0.68 | 5000 | 1.3951 |
|
| 62 |
+
| 1.8022 | 0.75 | 5500 | 1.3846 |
|
| 63 |
+
| 1.6937 | 0.81 | 6000 | 1.3833 |
|
| 64 |
+
| 1.4412 | 0.88 | 6500 | 1.3820 |
|
| 65 |
+
| 1.4339 | 0.95 | 7000 | 1.3783 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.25.1
|
| 71 |
+
- Pytorch 1.13.0+cu116
|
| 72 |
+
- Datasets 2.8.0
|
| 73 |
+
- Tokenizers 0.13.2
|