|
--- |
|
base_model: google/pegasus-x-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: PACSUM |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# PACSUM |
|
|
|
This model is a fine-tuned version of [google/pegasus-x-base](https://huggingface.co/google/pegasus-x-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0047 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 8.6563 | 0.1 | 10 | 8.4046 | |
|
| 7.9827 | 0.2 | 20 | 7.5165 | |
|
| 7.4924 | 0.3 | 30 | 6.8226 | |
|
| 6.4399 | 0.4 | 40 | 6.1135 | |
|
| 5.9354 | 0.5 | 50 | 5.2600 | |
|
| 5.0654 | 0.6 | 60 | 3.9574 | |
|
| 4.0233 | 0.7 | 70 | 2.7544 | |
|
| 3.0571 | 0.8 | 80 | 1.8116 | |
|
| 2.2512 | 0.9 | 90 | 1.4997 | |
|
| 1.8324 | 1.0 | 100 | 1.4224 | |
|
| 1.68 | 1.1 | 110 | 1.3573 | |
|
| 1.3785 | 1.2 | 120 | 1.2742 | |
|
| 1.4391 | 1.3 | 130 | 1.2275 | |
|
| 1.1567 | 1.4 | 140 | 1.1928 | |
|
| 1.167 | 1.5 | 150 | 1.1607 | |
|
| 1.2516 | 1.6 | 160 | 1.1298 | |
|
| 1.2057 | 1.7 | 170 | 1.1119 | |
|
| 1.2158 | 1.8 | 180 | 1.1022 | |
|
| 1.1413 | 1.9 | 190 | 1.0905 | |
|
| 1.0672 | 2.0 | 200 | 1.0803 | |
|
| 1.087 | 2.1 | 210 | 1.0707 | |
|
| 1.1339 | 2.2 | 220 | 1.0680 | |
|
| 1.1307 | 2.3 | 230 | 1.0570 | |
|
| 1.1404 | 2.4 | 240 | 1.0506 | |
|
| 1.1626 | 2.5 | 250 | 1.0481 | |
|
| 1.2482 | 2.6 | 260 | 1.0486 | |
|
| 0.9977 | 2.7 | 270 | 1.0406 | |
|
| 0.9627 | 2.8 | 280 | 1.0340 | |
|
| 1.1333 | 2.9 | 290 | 1.0319 | |
|
| 1.0409 | 3.0 | 300 | 1.0269 | |
|
| 1.0247 | 3.1 | 310 | 1.0224 | |
|
| 1.1111 | 3.2 | 320 | 1.0222 | |
|
| 1.0543 | 3.3 | 330 | 1.0201 | |
|
| 1.0024 | 3.4 | 340 | 1.0190 | |
|
| 1.0748 | 3.5 | 350 | 1.0171 | |
|
| 1.0088 | 3.6 | 360 | 1.0155 | |
|
| 0.9376 | 3.7 | 370 | 1.0130 | |
|
| 1.032 | 3.8 | 380 | 1.0122 | |
|
| 1.085 | 3.9 | 390 | 1.0107 | |
|
| 0.9086 | 4.0 | 400 | 1.0091 | |
|
| 1.0712 | 4.1 | 410 | 1.0074 | |
|
| 0.9856 | 4.2 | 420 | 1.0067 | |
|
| 0.9824 | 4.3 | 430 | 1.0068 | |
|
| 0.8748 | 4.4 | 440 | 1.0074 | |
|
| 0.9619 | 4.5 | 450 | 1.0069 | |
|
| 1.0256 | 4.6 | 460 | 1.0061 | |
|
| 1.0318 | 4.7 | 470 | 1.0053 | |
|
| 1.0897 | 4.8 | 480 | 1.0049 | |
|
| 1.0297 | 4.9 | 490 | 1.0048 | |
|
| 0.9533 | 5.0 | 500 | 1.0047 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
