|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: mt5-teste-full-length |
|
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-teste-full-length |
|
|
|
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5996 |
|
- Rouge1: 0.5083 |
|
- Rouge2: 0.2820 |
|
- Rougel: 0.4095 |
|
- Rougelsum: 0.4108 |
|
|
|
## 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: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 9.1442 | 0.16 | 100 | 9.7852 | 0.0531 | 0.0 | 0.0524 | 0.0 | |
|
| 1.0643 | 0.33 | 200 | 0.9089 | 0.3623 | 0.1853 | 0.3252 | 0.3261 | |
|
| 0.8283 | 0.49 | 300 | 0.8361 | 0.4184 | 0.2112 | 0.3535 | 0.3548 | |
|
| 0.7754 | 0.65 | 400 | 0.7522 | 0.4407 | 0.2575 | 0.3802 | 0.3828 | |
|
| 0.8012 | 0.82 | 500 | 0.7226 | 0.4643 | 0.2638 | 0.3866 | 0.3866 | |
|
| 0.7758 | 0.98 | 600 | 0.7265 | 0.4624 | 0.2458 | 0.3840 | 0.3847 | |
|
| 0.6744 | 1.15 | 700 | 0.7018 | 0.4477 | 0.2469 | 0.3732 | 0.3741 | |
|
| 0.6636 | 1.31 | 800 | 0.6955 | 0.4786 | 0.2632 | 0.4027 | 0.4038 | |
|
| 0.6839 | 1.47 | 900 | 0.6737 | 0.4773 | 0.2689 | 0.3909 | 0.3898 | |
|
| 0.6264 | 1.64 | 1000 | 0.6504 | 0.4457 | 0.2533 | 0.3747 | 0.3767 | |
|
| 0.6641 | 1.8 | 1100 | 0.6442 | 0.4582 | 0.2428 | 0.3661 | 0.3659 | |
|
| 0.6492 | 1.96 | 1200 | 0.6500 | 0.5004 | 0.2751 | 0.3984 | 0.3993 | |
|
| 0.5823 | 2.13 | 1300 | 0.6344 | 0.4917 | 0.2743 | 0.4000 | 0.4016 | |
|
| 0.5585 | 2.29 | 1400 | 0.6373 | 0.4749 | 0.2490 | 0.3834 | 0.3849 | |
|
| 0.5748 | 2.45 | 1500 | 0.6168 | 0.5036 | 0.2915 | 0.4128 | 0.4145 | |
|
| 0.5452 | 2.62 | 1600 | 0.6135 | 0.5004 | 0.2864 | 0.4038 | 0.4044 | |
|
| 0.5735 | 2.78 | 1700 | 0.6164 | 0.4904 | 0.2689 | 0.4001 | 0.3993 | |
|
| 0.5394 | 2.95 | 1800 | 0.6153 | 0.4864 | 0.2884 | 0.4091 | 0.4089 | |
|
| 0.4816 | 3.11 | 1900 | 0.6070 | 0.5027 | 0.2765 | 0.4042 | 0.4031 | |
|
| 0.5328 | 3.27 | 2000 | 0.6095 | 0.4896 | 0.2783 | 0.4026 | 0.4031 | |
|
| 0.5157 | 3.44 | 2100 | 0.6021 | 0.5165 | 0.2853 | 0.4137 | 0.4145 | |
|
| 0.5295 | 3.6 | 2200 | 0.6063 | 0.4926 | 0.2721 | 0.3965 | 0.3980 | |
|
| 0.5027 | 3.76 | 2300 | 0.6004 | 0.5120 | 0.2885 | 0.4092 | 0.4103 | |
|
| 0.4943 | 3.93 | 2400 | 0.5996 | 0.5083 | 0.2820 | 0.4095 | 0.4108 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 1.13.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.2 |
|
|
