metadata
library_name: peft
license: apache-2.0
base_model: muchad/idt5-base
tags:
- generated_from_trainer
metrics:
- rouge
- bleu
model-index:
- name: idt5-base-ae_adapter_v2
results: []
idt5-base-ae_adapter_v2
This model is a fine-tuned version of muchad/idt5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6189
- Rouge1: 0.2865
- Rouge2: 0.1723
- Rougel: 0.2835
- Rougelsum: 0.2833
- Bleu: 0.1327
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: 0.0001
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu |
|---|---|---|---|---|---|---|---|---|
| 2.3292 | 1.0 | 3235 | 1.8863 | 0.2475 | 0.1449 | 0.2451 | 0.2454 | 0.1103 |
| 2.0895 | 2.0 | 6470 | 1.6991 | 0.2761 | 0.1678 | 0.2725 | 0.2727 | 0.1388 |
| 1.9092 | 3.0 | 9705 | 1.6346 | 0.2798 | 0.1671 | 0.2773 | 0.2775 | 0.1278 |
| 1.9178 | 4.0 | 12940 | 1.6246 | 0.2839 | 0.1705 | 0.2813 | 0.2809 | 0.1227 |
| 1.9038 | 5.0 | 16175 | 1.6189 | 0.2865 | 0.1723 | 0.2835 | 0.2833 | 0.1327 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 3.0.2
- Tokenizers 0.20.1