<!-- 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. -->
t5-QG-2
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8743
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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 |
---|---|---|---|
2.4196 | 0.4 | 10 | 2.2206 |
1.8176 | 0.81 | 20 | 1.6716 |
1.4509 | 1.21 | 30 | 1.3951 |
1.1259 | 1.62 | 40 | 1.2469 |
0.8528 | 2.02 | 50 | 1.1312 |
0.8001 | 2.42 | 60 | 1.0782 |
0.7021 | 2.83 | 70 | 1.0161 |
0.6407 | 3.23 | 80 | 0.9279 |
0.5636 | 3.64 | 90 | 0.8877 |
0.633 | 4.04 | 100 | 0.8979 |
0.4598 | 4.44 | 110 | 0.8909 |
0.5543 | 4.85 | 120 | 0.8881 |
0.4215 | 5.25 | 130 | 0.8954 |
0.517 | 5.66 | 140 | 0.8753 |
0.4442 | 6.06 | 150 | 0.8747 |
0.4141 | 6.46 | 160 | 0.8743 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3