metadata
base_model: yhavinga/ul2-large-dutch
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: ul2-large-dutch-finetuned-oba-book-search
results: []
ul2-large-dutch-finetuned-oba-book-search
This model is a fine-tuned version of yhavinga/ul2-large-dutch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.4663
- Top-5-accuracy: 0.4179
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: 0.03
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss | Top-5-accuracy |
---|---|---|---|---|
6.6127 | 0.0170 | 200 | 4.9957 | 0.0199 |
6.3546 | 0.0339 | 400 | 4.6613 | 0.0796 |
6.3036 | 0.0509 | 600 | 4.7338 | 0.0 |
6.0421 | 0.0678 | 800 | 4.7298 | 0.0 |
6.0575 | 0.0848 | 1000 | 4.5229 | 0.0597 |
5.9802 | 0.1017 | 1200 | 4.6572 | 0.0398 |
5.8962 | 0.1187 | 1400 | 4.5695 | 0.0199 |
5.7797 | 0.1357 | 1600 | 4.5181 | 0.0199 |
5.7508 | 0.1526 | 1800 | 4.5089 | 0.0995 |
5.6505 | 0.1696 | 2000 | 4.5137 | 0.0199 |
5.705 | 0.1865 | 2200 | 4.4988 | 0.0796 |
5.6986 | 0.2035 | 2400 | 4.4908 | 0.0199 |
5.6822 | 0.2205 | 2600 | 4.4318 | 0.0199 |
5.6889 | 0.2374 | 2800 | 4.5502 | 0.0199 |
5.674 | 0.2544 | 3000 | 4.4749 | 0.0199 |
5.682 | 0.2713 | 3200 | 4.5109 | 0.0199 |
5.6252 | 0.2883 | 3400 | 4.5060 | 0.0796 |
5.4972 | 0.3052 | 3600 | 4.4417 | 0.1194 |
5.478 | 0.3222 | 3800 | 4.4351 | 0.0597 |
5.5038 | 0.3392 | 4000 | 4.4616 | 0.0 |
5.6091 | 0.3561 | 4200 | 4.4631 | 0.0995 |
5.4895 | 0.3731 | 4400 | 4.4339 | 0.0796 |
5.6013 | 0.3900 | 4600 | 4.4692 | 0.0995 |
5.4743 | 0.4070 | 4800 | 4.5731 | 0.0796 |
5.4131 | 0.4239 | 5000 | 4.5185 | 0.0995 |
5.4779 | 0.4409 | 5200 | 4.4901 | 0.0995 |
5.5093 | 0.4579 | 5400 | 4.5193 | 0.0995 |
5.527 | 0.4748 | 5600 | 4.5322 | 0.1194 |
5.5443 | 0.4918 | 5800 | 4.5358 | 0.0796 |
5.557 | 0.5087 | 6000 | 4.5574 | 0.0995 |
5.5324 | 0.5257 | 6200 | 4.4957 | 0.2786 |
5.4958 | 0.5426 | 6400 | 4.5618 | 0.1592 |
5.4376 | 0.5596 | 6600 | 4.4751 | 0.1194 |
5.5136 | 0.5766 | 6800 | 4.4994 | 0.1393 |
5.4284 | 0.5935 | 7000 | 4.5029 | 0.2587 |
5.4333 | 0.6105 | 7200 | 4.4864 | 0.2189 |
5.3516 | 0.6274 | 7400 | 4.5141 | 0.1990 |
5.4294 | 0.6444 | 7600 | 4.4527 | 0.1990 |
5.4383 | 0.6614 | 7800 | 4.4698 | 0.0199 |
5.3333 | 0.6783 | 8000 | 4.4169 | 0.2189 |
5.3708 | 0.6953 | 8200 | 4.4541 | 0.2587 |
5.3639 | 0.7122 | 8400 | 4.4613 | 0.2587 |
5.3746 | 0.7292 | 8600 | 4.4467 | 0.2786 |
5.3916 | 0.7461 | 8800 | 4.4134 | 0.4378 |
5.3416 | 0.7631 | 9000 | 4.4772 | 0.4179 |
5.3148 | 0.7801 | 9200 | 4.4603 | 0.3980 |
5.3646 | 0.7970 | 9400 | 4.4700 | 0.3582 |
5.2917 | 0.8140 | 9600 | 4.4439 | 0.3781 |
5.386 | 0.8309 | 9800 | 4.4418 | 0.3582 |
5.3907 | 0.8479 | 10000 | 4.4431 | 0.4179 |
5.4036 | 0.8648 | 10200 | 4.4557 | 0.3980 |
5.3439 | 0.8818 | 10400 | 4.4373 | 0.4179 |
5.2866 | 0.8988 | 10600 | 4.4616 | 0.4179 |
5.3447 | 0.9157 | 10800 | 4.4669 | 0.3980 |
5.3031 | 0.9327 | 11000 | 4.4639 | 0.4179 |
5.4083 | 0.9496 | 11200 | 4.4726 | 0.4179 |
5.2586 | 0.9666 | 11400 | 4.4771 | 0.3980 |
5.3988 | 0.9836 | 11600 | 4.4663 | 0.4179 |
Framework versions
- PEFT 0.11.0
- Transformers 4.44.2
- Pytorch 1.13.0+cu116
- Datasets 3.0.0
- Tokenizers 0.19.1