<!-- 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. -->
flan-t5-QG-SQUAD-tarek-test
This model is a fine-tuned version of google/flan-t5-base on the squad dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.5632
- eval_rouge1: 52.9357
- eval_rouge2: 30.2806
- eval_rougeL: 48.9079
- eval_rougeLsum: 48.8755
- eval_gen_len: 14.3551
- eval_meteor: {'meteor': 0.4807566298868249}
- eval_bleu: {'bleu': 0.21467065200589103, 'precisions': [0.5298697100577371, 0.2711489429248886, 0.1735068216830882, 0.11647438392106155], 'brevity_penalty': 0.9247869207061962, 'length_ratio': 0.9274786591713512, 'translation_length': 111367, 'reference_length': 120075}
- eval_runtime: 950.2215
- eval_samples_per_second: 11.124
- eval_steps_per_second: 1.391
- epoch: 5.0
- step: 54750
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3