|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: flan-t5-large-da-multiwoz_250 |
|
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. --> |
|
|
|
# flan-t5-large-da-multiwoz_250 |
|
|
|
This model was trained from scratch on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3959 |
|
- Accuracy: 38.8681 |
|
- Num: 3689 |
|
- Gen Len: 15.6736 |
|
|
|
## 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: 24 |
|
- seed: 1799 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:-------:| |
|
| 0.4158 | 0.93 | 200 | 0.4439 | 34.537 | 3689 | 15.8452 | |
|
| 0.3487 | 1.86 | 400 | 0.4358 | 35.7656 | 3689 | 15.6495 | |
|
| 0.3596 | 2.79 | 600 | 0.4304 | 35.4046 | 3689 | 14.8946 | |
|
| 0.3676 | 3.72 | 800 | 0.4186 | 36.5036 | 3689 | 15.0016 | |
|
| 0.4259 | 4.65 | 1000 | 0.4082 | 36.491 | 3689 | 15.4118 | |
|
| 0.4005 | 5.58 | 1200 | 0.4039 | 37.4827 | 3689 | 15.8615 | |
|
| 0.3922 | 6.51 | 1400 | 0.4009 | 38.1076 | 3689 | 15.4286 | |
|
| 0.3656 | 7.44 | 1600 | 0.3998 | 38.8275 | 3689 | 15.7021 | |
|
| 0.3709 | 8.37 | 1800 | 0.3959 | 38.8681 | 3689 | 15.6736 | |
|
| 0.3564 | 9.3 | 2000 | 0.3981 | 38.6742 | 3689 | 15.8406 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 2.5.1 |
|
- Tokenizers 0.12.1 |
|
|
