|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: mt5-summarize |
|
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-summarize |
|
|
|
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: 3.1534 |
|
- Rouge1: 0.3153 |
|
- Rouge2: 0.1594 |
|
- Rougel: 0.2511 |
|
- Rougelsum: 0.3397 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 90 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 4.3806 | 1.0667 | 100 | 3.4709 | 0.2568 | 0.1258 | 0.2214 | 0.2662 | |
|
| 3.7757 | 2.1333 | 200 | 3.2899 | 0.2759 | 0.1388 | 0.2381 | 0.2946 | |
|
| 3.5195 | 3.2 | 300 | 3.1951 | 0.2951 | 0.1523 | 0.2466 | 0.3217 | |
|
| 3.4319 | 4.2667 | 400 | 3.1715 | 0.2813 | 0.1323 | 0.2331 | 0.3011 | |
|
| 3.2402 | 5.3333 | 500 | 3.1704 | 0.3058 | 0.1548 | 0.2513 | 0.3366 | |
|
| 3.2313 | 6.4 | 600 | 3.1657 | 0.3077 | 0.1534 | 0.2461 | 0.3335 | |
|
| 3.1444 | 7.4667 | 700 | 3.1719 | 0.2957 | 0.1453 | 0.2378 | 0.3191 | |
|
| 3.116 | 8.5333 | 800 | 3.1639 | 0.3144 | 0.1540 | 0.2501 | 0.3453 | |
|
| 2.9937 | 9.6 | 900 | 3.1534 | 0.3153 | 0.1594 | 0.2511 | 0.3397 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
