|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: mt5-small-finetuned-b8-10 |
|
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-small-finetuned-b8-10 |
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.6458 |
|
- Rouge1: 0.1334 |
|
- Rouge2: 0.1033 |
|
- Rougel: 0.1296 |
|
- Rougelsum: 0.1296 |
|
- Gen Len: 15.4277 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 5.1916 | 1.0 | 1357 | 3.8497 | 0.1095 | 0.086 | 0.1067 | 0.1064 | 12.6442 | |
|
| 4.5138 | 2.0 | 2714 | 3.7329 | 0.1228 | 0.0959 | 0.1198 | 0.1195 | 14.4008 | |
|
| 4.3429 | 3.0 | 4071 | 3.6736 | 0.1291 | 0.1 | 0.1255 | 0.1255 | 15.0502 | |
|
| 4.3195 | 4.0 | 5428 | 3.6458 | 0.1334 | 0.1033 | 0.1296 | 0.1296 | 15.4277 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|
