Commit
•
1ee1537
1
Parent(s):
838c574
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- govreport-summarization
|
| 6 |
+
model-index:
|
| 7 |
+
- name: Pegasus-x-base-govreport-12288-1024-numepoch-10
|
| 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-x-base-govreport-12288-1024-numepoch-10
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/pegasus-x-base](https://huggingface.co/google/pegasus-x-base) on the govreport-summarization dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.6234
|
| 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: 0.0001
|
| 38 |
+
- train_batch_size: 1
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 64
|
| 42 |
+
- total_train_batch_size: 64
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 10
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 2.1149 | 0.37 | 100 | 1.9237 |
|
| 52 |
+
| 1.9545 | 0.73 | 200 | 1.8380 |
|
| 53 |
+
| 1.8835 | 1.1 | 300 | 1.7574 |
|
| 54 |
+
| 1.862 | 1.46 | 400 | 1.7305 |
|
| 55 |
+
| 1.8536 | 1.83 | 500 | 1.7100 |
|
| 56 |
+
| 1.8062 | 2.19 | 600 | 1.6944 |
|
| 57 |
+
| 1.8161 | 2.56 | 700 | 1.6882 |
|
| 58 |
+
| 1.7611 | 2.92 | 800 | 1.6803 |
|
| 59 |
+
| 1.7878 | 3.29 | 900 | 1.6671 |
|
| 60 |
+
| 1.7299 | 3.65 | 1000 | 1.6599 |
|
| 61 |
+
| 1.7636 | 4.02 | 1100 | 1.6558 |
|
| 62 |
+
| 1.7262 | 4.38 | 1200 | 1.6547 |
|
| 63 |
+
| 1.715 | 4.75 | 1300 | 1.6437 |
|
| 64 |
+
| 1.7178 | 5.12 | 1400 | 1.6445 |
|
| 65 |
+
| 1.7163 | 5.48 | 1500 | 1.6386 |
|
| 66 |
+
| 1.7367 | 5.85 | 1600 | 1.6364 |
|
| 67 |
+
| 1.7114 | 6.21 | 1700 | 1.6365 |
|
| 68 |
+
| 1.6452 | 6.58 | 1800 | 1.6309 |
|
| 69 |
+
| 1.7251 | 6.94 | 1900 | 1.6301 |
|
| 70 |
+
| 1.6726 | 7.31 | 2000 | 1.6305 |
|
| 71 |
+
| 1.7104 | 7.67 | 2100 | 1.6285 |
|
| 72 |
+
| 1.6739 | 8.04 | 2200 | 1.6252 |
|
| 73 |
+
| 1.7082 | 8.4 | 2300 | 1.6246 |
|
| 74 |
+
| 1.6888 | 8.77 | 2400 | 1.6244 |
|
| 75 |
+
| 1.6609 | 9.13 | 2500 | 1.6256 |
|
| 76 |
+
| 1.6707 | 9.5 | 2600 | 1.6241 |
|
| 77 |
+
| 1.669 | 9.86 | 2700 | 1.6234 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.30.2
|
| 83 |
+
- Pytorch 2.0.1+cu117
|
| 84 |
+
- Datasets 2.13.1
|
| 85 |
+
- Tokenizers 0.13.3
|