|
--- |
|
library_name: transformers |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- iva_mt_wslot |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: seq2seq-imlla-test |
|
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. --> |
|
|
|
# seq2seq-imlla-test |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the iva_mt_wslot dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 6.0821 |
|
- Bleu: 0.009 |
|
- Gen Len: 5.5922 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- 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: 500 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:------:|:----:|:---------------:|:------:|:-------:| |
|
| 7.4016 | 0.9992 | 636 | 7.0495 | 0.0009 | 3.7101 | |
|
| 6.5244 | 2.0 | 1273 | 6.4803 | 0.0268 | 7.1527 | |
|
| 6.101 | 2.9992 | 1909 | 6.2219 | 0.0068 | 5.5162 | |
|
| 5.919 | 4.0 | 2546 | 6.1188 | 0.0106 | 5.9943 | |
|
| 5.7827 | 4.9961 | 3180 | 6.0821 | 0.009 | 5.5922 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.19.1 |
|
|
