nymiz-model-nuextract-pjcr-es-api
This model is a fine-tuned version of numind/NuExtract on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6077
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.6028 | 0.9905 | 26 | 0.6623 |
0.2973 | 1.9810 | 52 | 0.6077 |
0.2814 | 2.9714 | 78 | 0.6485 |
0.168 | 4.0 | 105 | 0.6724 |
0.0565 | 4.9905 | 131 | 0.7278 |
0.0445 | 5.9429 | 156 | 0.7434 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2