metadata
library_name: peft
license: mit
base_model: numind/NuExtract-v1.5
tags:
- axolotl
- generated_from_trainer
model-index:
- name: e78cbcf5-a7ab-476b-b2ad-a344475d3d47
results: []
e78cbcf5-a7ab-476b-b2ad-a344475d3d47
This model is a fine-tuned version of numind/NuExtract-v1.5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7836
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: 0.00021
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0001 | 1 | 1.9060 |
| 4.0056 | 0.0062 | 50 | 1.8324 |
| 3.799 | 0.0124 | 100 | 1.8217 |
| 3.9889 | 0.0186 | 150 | 1.8094 |
| 3.8805 | 0.0248 | 200 | 1.8063 |
| 3.9561 | 0.0309 | 250 | 1.8012 |
| 3.9048 | 0.0371 | 300 | 1.7920 |
| 3.9272 | 0.0433 | 350 | 1.7879 |
| 3.79 | 0.0495 | 400 | 1.7847 |
| 3.8634 | 0.0557 | 450 | 1.7835 |
| 3.8812 | 0.0619 | 500 | 1.7836 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1