metadata
library_name: transformers
license: apache-2.0
base_model: MohamedAshraf701/custom-T5
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
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: 0.9987
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9825 | 28 | 1.2638 |
| No log | 2.0 | 57 | 1.1696 |
| No log | 2.9825 | 85 | 1.1032 |
| No log | 4.0 | 114 | 1.0675 |
| No log | 4.9825 | 142 | 1.0436 |
| No log | 6.0 | 171 | 1.0258 |
| No log | 6.9825 | 199 | 1.0137 |
| No log | 8.0 | 228 | 1.0049 |
| No log | 8.9825 | 256 | 1.0000 |
| No log | 9.8246 | 280 | 0.9987 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1