|
--- |
|
base_model: google/pegasus-xsum |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: LLM_Teached_Pegasus_50k |
|
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. --> |
|
|
|
# LLM_Teached_Pegasus_50k |
|
|
|
This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7193 |
|
- Rouge1: 0.4541 |
|
- Rouge2: 0.2071 |
|
- Rougel: 0.3708 |
|
- Rougelsum: 0.3708 |
|
- Gen Len: 26.4531 |
|
- Precision: 0.9082 |
|
- Recall: 0.9061 |
|
- F1: 0.907 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:---------:|:------:|:------:| |
|
| No log | 1.0 | 390 | 1.8258 | 0.4338 | 0.1906 | 0.3496 | 0.3498 | 26.2967 | 0.9049 | 0.9023 | 0.9034 | |
|
| 2.1621 | 2.0 | 781 | 1.7537 | 0.4449 | 0.2005 | 0.3633 | 0.3633 | 26.2727 | 0.9068 | 0.9044 | 0.9054 | |
|
| 1.8794 | 3.0 | 1172 | 1.7268 | 0.4518 | 0.2061 | 0.3696 | 0.3695 | 26.4345 | 0.9078 | 0.9058 | 0.9066 | |
|
| 1.8271 | 3.99 | 1560 | 1.7193 | 0.4541 | 0.2071 | 0.3708 | 0.3708 | 26.4531 | 0.9082 | 0.9061 | 0.907 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.15.0 |
|
|