<!-- 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-xl-mind2web-adafactor
This model is a fine-tuned version of google/flan-t5-xl on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3172
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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2208 | 0.43 | 100 | 0.2627 |
| 0.1868 | 0.87 | 200 | 0.2550 |
| 0.1369 | 1.3 | 300 | 0.1846 |
| 0.1308 | 1.74 | 400 | 0.2246 |
| 0.1056 | 2.17 | 500 | 0.2025 |
| 0.0944 | 2.6 | 600 | 0.2573 |
| 0.0911 | 3.04 | 700 | 0.2562 |
| 0.066 | 3.47 | 800 | 0.2266 |
| 0.0646 | 3.9 | 900 | 0.2240 |
| 0.0497 | 4.34 | 1000 | 0.3204 |
| 0.0517 | 4.77 | 1100 | 0.3172 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
