<!-- 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. -->
first_t5-end2end-questions-generation
This model is a fine-tuned version of ThomasSimonini/t5-end2end-question-generation on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1966
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.5741 | 0.42 | 100 | 1.3270 |
1.4023 | 0.84 | 200 | 1.2798 |
1.3472 | 1.26 | 300 | 1.2579 |
1.3136 | 1.68 | 400 | 1.2402 |
1.2911 | 2.1 | 500 | 1.2323 |
1.2691 | 2.52 | 600 | 1.2216 |
1.2576 | 2.95 | 700 | 1.2154 |
1.2343 | 3.37 | 800 | 1.2126 |
1.2364 | 3.79 | 900 | 1.2076 |
1.2138 | 4.21 | 1000 | 1.2069 |
1.2094 | 4.63 | 1100 | 1.2022 |
1.2059 | 5.05 | 1200 | 1.1997 |
1.1927 | 5.47 | 1300 | 1.1977 |
1.1905 | 5.89 | 1400 | 1.1971 |
1.186 | 6.31 | 1500 | 1.1963 |
1.174 | 6.73 | 1600 | 1.1966 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2