bart-finetuned-idl-new
This model is a fine-tuned version of rohitsan/bart-finetuned-idl-new on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2981
- eval_bleu: 18.5188
- eval_gen_len: 19.3843
- eval_runtime: 257.315
- eval_samples_per_second: 24.464
- eval_steps_per_second: 3.059
- epoch: 8.0
- step: 56648
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 35
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2