metadata
library_name: transformers
license: apache-2.0
base_model: MohamedAshraf701/custom-T5
tags:
- generated_from_trainer
model-index:
- name: Testing-t5
results: []
Testing-t5
This model is a fine-tuned version of MohamedAshraf701/custom-T5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3965
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 282 | 0.5618 |
| 0.5827 | 2.0 | 564 | 0.5009 |
| 0.5827 | 3.0 | 846 | 0.4711 |
| 0.4765 | 4.0 | 1128 | 0.4537 |
| 0.4765 | 5.0 | 1410 | 0.4418 |
| 0.4466 | 6.0 | 1692 | 0.4337 |
| 0.4466 | 7.0 | 1974 | 0.4263 |
| 0.4229 | 8.0 | 2256 | 0.4197 |
| 0.4152 | 9.0 | 2538 | 0.4153 |
| 0.4152 | 10.0 | 2820 | 0.4105 |
| 0.3981 | 11.0 | 3102 | 0.4083 |
| 0.3981 | 12.0 | 3384 | 0.4053 |
| 0.3974 | 13.0 | 3666 | 0.4032 |
| 0.3974 | 14.0 | 3948 | 0.4008 |
| 0.3933 | 15.0 | 4230 | 0.3995 |
| 0.3885 | 16.0 | 4512 | 0.3988 |
| 0.3885 | 17.0 | 4794 | 0.3978 |
| 0.3814 | 18.0 | 5076 | 0.3972 |
| 0.3814 | 19.0 | 5358 | 0.3966 |
| 0.3855 | 20.0 | 5640 | 0.3965 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1