|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-large |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: models |
|
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. --> |
|
|
|
# models |
|
|
|
This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2777 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 9.9229 | 0.0699 | 500 | 0.9269 | |
|
| 0.6121 | 0.1398 | 1000 | 0.4268 | |
|
| 0.4573 | 0.2097 | 1500 | 0.3790 | |
|
| 0.4395 | 0.2796 | 2000 | 0.3563 | |
|
| 0.3979 | 0.3495 | 2500 | 0.3520 | |
|
| 0.3914 | 0.4193 | 3000 | 0.3390 | |
|
| 0.375 | 0.4892 | 3500 | 0.3214 | |
|
| 0.3856 | 0.5591 | 4000 | 0.3217 | |
|
| 0.3482 | 0.6290 | 4500 | 0.3143 | |
|
| 0.3643 | 0.6989 | 5000 | 0.3090 | |
|
| 0.3541 | 0.7688 | 5500 | 0.3067 | |
|
| 0.3471 | 0.8387 | 6000 | 0.3024 | |
|
| 0.3374 | 0.9086 | 6500 | 0.2975 | |
|
| 0.3675 | 0.9785 | 7000 | 0.2936 | |
|
| 0.3261 | 1.0484 | 7500 | 0.2915 | |
|
| 0.3206 | 1.1183 | 8000 | 0.2928 | |
|
| 0.3258 | 1.1881 | 8500 | 0.2848 | |
|
| 0.3244 | 1.2580 | 9000 | 0.2866 | |
|
| 0.3006 | 1.3279 | 9500 | 0.2853 | |
|
| 0.3204 | 1.3978 | 10000 | 0.2821 | |
|
| 0.3088 | 1.4677 | 10500 | 0.2827 | |
|
| 0.2958 | 1.5376 | 11000 | 0.2820 | |
|
| 0.3031 | 1.6075 | 11500 | 0.2789 | |
|
| 0.3153 | 1.6774 | 12000 | 0.2812 | |
|
| 0.2941 | 1.7473 | 12500 | 0.2786 | |
|
| 0.3025 | 1.8172 | 13000 | 0.2790 | |
|
| 0.2983 | 1.8871 | 13500 | 0.2775 | |
|
| 0.3019 | 1.9569 | 14000 | 0.2777 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.19.1 |
|
|
