seq2seq-imlla-test
This model is a fine-tuned version of on the iva_mt_wslot dataset. It achieves the following results on the evaluation set:
- Loss: 6.0849
- Bleu: 0.0032
- Gen Len: 5.1554
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
---|---|---|---|---|---|
7.3868 | 0.9992 | 636 | 7.0446 | 0.0 | 2.7952 |
6.5132 | 2.0 | 1273 | 6.4775 | 0.0504 | 7.3246 |
6.0691 | 2.9992 | 1909 | 6.2289 | 0.0007 | 3.6667 |
5.8713 | 4.0 | 2546 | 6.1236 | 0.0096 | 6.216 |
5.7608 | 4.9961 | 3180 | 6.0849 | 0.0032 | 5.1554 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 4