metadata
library_name: transformers
license: apache-2.0
base_model: T5-small
tags:
- generated_from_trainer
metrics:
- bleu
- rouge
model-index:
- name: T5-JSON-OM-IMP
results: []
T5-JSON-OM-IMP
This model is a fine-tuned version of T5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 9.1373
- Micro Precision: 0
- Micro Recall: 0
- Micro F1: 0
- Bleu: 0.0232
- Rouge1: 0.0129
- Rouge2: 0.0
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Micro Precision | Micro Recall | Micro F1 | Bleu | Rouge1 | Rouge2 |
|---|---|---|---|---|---|---|---|---|---|
| 22.4396 | 1.4286 | 10 | 23.3606 | 0 | 0 | 0 | 0.0254 | 0.0186 | 0.0 |
| 18.4466 | 2.8571 | 20 | 17.6608 | 0 | 0 | 0 | 0.0257 | 0.0187 | 0.0 |
| 14.8784 | 4.2857 | 30 | 14.9580 | 0 | 0 | 0 | 0.0233 | 0.0157 | 0.0 |
| 12.9381 | 5.7143 | 40 | 12.5760 | 0 | 0 | 0 | 0.0235 | 0.0155 | 0.0 |
| 10.9805 | 7.1429 | 50 | 10.9128 | 0 | 0 | 0 | 0.0234 | 0.0140 | 0.0 |
| 9.8316 | 8.5714 | 60 | 9.7909 | 0 | 0 | 0 | 0.0232 | 0.0129 | 0.0 |
| 9.0429 | 10.0 | 70 | 9.1373 | 0 | 0 | 0 | 0.0232 | 0.0129 | 0.0 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0