Edit model card

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: 6.0821
  • 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
Downloads last month
12
Safetensors
Model size
27.4M params
Tensor type
F32
·
Inference API
Unable to determine this model’s pipeline type. Check the docs .