|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: MT5_large_NO_CNN-idun-final |
|
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. --> |
|
|
|
# MT5_large_NO_CNN-idun-final |
|
|
|
This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8492 |
|
- Rouge1: 31.9047 |
|
- Rouge2: 12.0487 |
|
- Rougel: 21.7323 |
|
- Rougelsum: 29.4557 |
|
- Gen Len: 98.7777 |
|
|
|
## 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 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:| |
|
| 2.246 | 1.0 | 6118 | 1.9772 | 30.9142 | 11.28 | 21.0914 | 28.4499 | 95.2396 | |
|
| 2.0899 | 2.0 | 12236 | 1.9070 | 31.3973 | 11.6219 | 21.3122 | 28.9365 | 100.0907 | |
|
| 1.9736 | 3.0 | 18354 | 1.8716 | 31.5752 | 11.7955 | 21.4748 | 29.1354 | 100.4973 | |
|
| 1.9189 | 4.0 | 24472 | 1.8547 | 31.9802 | 12.183 | 21.8505 | 29.5171 | 98.4764 | |
|
| 1.8697 | 5.0 | 30590 | 1.8492 | 31.9047 | 12.0487 | 21.7323 | 29.4557 | 98.7777 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.2 |
|
|
