|
---
|
|
base_model: MarcBrun/ixambert-finetuned-squad-eu
|
|
tags:
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: NeurIXA_From_Ixambert-finetuned-squad-eu
|
|
results: []
|
|
---
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
# NeurIXA_From_Ixambert-finetuned-squad-eu
|
|
|
|
This model is a fine-tuned version of [MarcBrun/ixambert-finetuned-squad-eu](https://huggingface.co/MarcBrun/ixambert-finetuned-squad-eu) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.4553
|
|
|
|
## 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: 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: 15
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:-----:|:----:|:---------------:|
|
|
| No log | 1.0 | 3 | 4.5910 |
|
|
| No log | 2.0 | 6 | 3.6086 |
|
|
| No log | 3.0 | 9 | 3.0027 |
|
|
| No log | 4.0 | 12 | 2.4933 |
|
|
| No log | 5.0 | 15 | 2.0479 |
|
|
| No log | 6.0 | 18 | 1.6777 |
|
|
| No log | 7.0 | 21 | 1.3752 |
|
|
| No log | 8.0 | 24 | 1.1311 |
|
|
| No log | 9.0 | 27 | 0.9425 |
|
|
| No log | 10.0 | 30 | 0.7820 |
|
|
| No log | 11.0 | 33 | 0.6559 |
|
|
| No log | 12.0 | 36 | 0.5652 |
|
|
| No log | 13.0 | 39 | 0.5052 |
|
|
| No log | 14.0 | 42 | 0.4691 |
|
|
| No log | 15.0 | 45 | 0.4553 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.37.2
|
|
- Pytorch 2.3.0
|
|
- Datasets 2.19.1
|
|
- Tokenizers 0.15.1
|
|
|
