metadata
library_name: transformers
tags:
- generated_from_trainer
datasets:
- iva_mt_wslot
metrics:
- bleu
model-index:
- name: seq2seq-imlla-test
results: []
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: 6.0627
- Bleu: 0.0253
- Gen Len: 5.1184
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 |
|---|---|---|---|---|---|
| 7.4078 | 0.9992 | 636 | 7.0700 | 0.0 | 3.9948 |
| 6.525 | 2.0 | 1273 | 6.4606 | 0.0225 | 6.3877 |
| 6.082 | 2.9992 | 1909 | 6.2044 | 0.0103 | 4.9663 |
| 5.8782 | 4.0 | 2546 | 6.1041 | 0.0248 | 5.9008 |
| 5.756 | 4.9961 | 3180 | 6.0627 | 0.0253 | 5.1184 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1