<!-- 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-xl-mind2web
This model is a fine-tuned version of google/t5-v1_1-xl on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2621
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 |
|---|---|---|---|
| 0.542 | 0.43 | 100 | 0.3799 |
| 0.3914 | 0.87 | 200 | 0.3942 |
| 0.3232 | 1.3 | 300 | 0.2925 |
| 0.2549 | 1.74 | 400 | 0.3207 |
| 0.2119 | 2.17 | 500 | 0.2758 |
| 0.1928 | 2.6 | 600 | 0.2919 |
| 0.1807 | 3.04 | 700 | 0.3321 |
| 0.1541 | 3.47 | 800 | 0.2577 |
| 0.3113 | 3.9 | 900 | 0.2536 |
| 0.1286 | 4.34 | 1000 | 0.2571 |
| 0.1602 | 4.77 | 1100 | 0.2621 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
