|
--- |
|
base_model: amagzari/pegasus-cnn_dailymail-finetuned-samsum-v2 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pegasus-model |
|
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. --> |
|
|
|
# pegasus-model |
|
|
|
This model is a fine-tuned version of [amagzari/pegasus-cnn_dailymail-finetuned-samsum-v2](https://huggingface.co/amagzari/pegasus-cnn_dailymail-finetuned-samsum-v2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1602 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.2222 | 0.8 | 10 | 1.6816 | |
|
| 2.2663 | 1.61 | 20 | 1.6594 | |
|
| 2.0153 | 2.41 | 30 | 1.6221 | |
|
| 2.1572 | 3.22 | 40 | 1.5758 | |
|
| 2.0548 | 4.02 | 50 | 1.5208 | |
|
| 1.9995 | 4.82 | 60 | 1.4627 | |
|
| 1.8907 | 5.63 | 70 | 1.4151 | |
|
| 1.9159 | 6.43 | 80 | 1.3653 | |
|
| 1.7551 | 7.24 | 90 | 1.3158 | |
|
| 1.7168 | 8.04 | 100 | 1.2606 | |
|
| 1.5976 | 8.84 | 110 | 1.2106 | |
|
| 1.4944 | 9.65 | 120 | 1.1602 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
