|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flux-dsum-small |
|
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. --> |
|
|
|
# flux-dsum-small |
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8477 |
|
- Rouge1: 0.3156 |
|
- Rouge2: 0.1379 |
|
- Rougel: 0.2767 |
|
- Rougelsum: 0.2765 |
|
- Gen Len: 17.5537 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 2.5294 | 1.0 | 21753 | 1.9915 | 0.3065 | 0.1264 | 0.27 | 0.2699 | 17.385 | |
|
| 2.336 | 2.0 | 43506 | 1.8991 | 0.3085 | 0.1345 | 0.2702 | 0.2701 | 17.6597 | |
|
| 2.2611 | 3.0 | 65259 | 1.8602 | 0.3138 | 0.1363 | 0.2765 | 0.2763 | 17.5347 | |
|
| 2.2107 | 4.0 | 87012 | 1.8477 | 0.3156 | 0.1379 | 0.2767 | 0.2765 | 17.5537 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
