Fine-tuning completed
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: FacebookAI/xlm-roberta-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- precision
|
| 8 |
+
- recall
|
| 9 |
+
- f1
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: RE_NegREF_NSD_Nubes_Training_Test_dataset_xlm_RoBERTa_base_fine_tuned
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# RE_NegREF_NSD_Nubes_Training_Test_dataset_xlm_RoBERTa_base_fine_tuned
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.3660
|
| 24 |
+
- Negref Precision: 0.5752
|
| 25 |
+
- Negref Recall: 0.5786
|
| 26 |
+
- Negref F1: 0.5769
|
| 27 |
+
- Neg Precision: 0.9489
|
| 28 |
+
- Neg Recall: 0.9642
|
| 29 |
+
- Neg F1: 0.9565
|
| 30 |
+
- Nsco Precision: 0.8852
|
| 31 |
+
- Nsco Recall: 0.9039
|
| 32 |
+
- Nsco F1: 0.8945
|
| 33 |
+
- Precision: 0.8507
|
| 34 |
+
- Recall: 0.8643
|
| 35 |
+
- F1: 0.8574
|
| 36 |
+
- Accuracy: 0.9575
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 2e-05
|
| 56 |
+
- train_batch_size: 8
|
| 57 |
+
- eval_batch_size: 8
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- num_epochs: 12
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Negref Precision | Negref Recall | Negref F1 | Neg Precision | Neg Recall | Neg F1 | Nsco Precision | Nsco Recall | Nsco F1 | Precision | Recall | F1 | Accuracy |
|
| 66 |
+
|:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------:|:-------------:|:----------:|:------:|:--------------:|:-----------:|:-------:|:---------:|:------:|:------:|:--------:|
|
| 67 |
+
| 0.0268 | 1.0 | 1729 | 0.2889 | 0.5289 | 0.5639 | 0.5458 | 0.9560 | 0.9459 | 0.9509 | 0.8616 | 0.8616 | 0.8616 | 0.8302 | 0.8375 | 0.8338 | 0.9537 |
|
| 68 |
+
| 0.0233 | 2.0 | 3458 | 0.3034 | 0.5161 | 0.5419 | 0.5287 | 0.9448 | 0.9614 | 0.9530 | 0.8731 | 0.8949 | 0.8838 | 0.8301 | 0.8523 | 0.8411 | 0.9522 |
|
| 69 |
+
| 0.0205 | 3.0 | 5187 | 0.2748 | 0.5591 | 0.5624 | 0.5608 | 0.9502 | 0.9649 | 0.9575 | 0.8645 | 0.8926 | 0.8783 | 0.8401 | 0.8570 | 0.8485 | 0.9557 |
|
| 70 |
+
| 0.012 | 4.0 | 6916 | 0.2915 | 0.5238 | 0.5653 | 0.5438 | 0.9525 | 0.9586 | 0.9555 | 0.8693 | 0.8858 | 0.8775 | 0.8310 | 0.8523 | 0.8415 | 0.9558 |
|
| 71 |
+
| 0.0105 | 5.0 | 8645 | 0.3158 | 0.5526 | 0.5786 | 0.5653 | 0.9515 | 0.9635 | 0.9574 | 0.8663 | 0.9017 | 0.8836 | 0.8377 | 0.8631 | 0.8502 | 0.9559 |
|
| 72 |
+
| 0.0095 | 6.0 | 10374 | 0.3048 | 0.5424 | 0.6197 | 0.5785 | 0.9504 | 0.9684 | 0.9593 | 0.8786 | 0.9085 | 0.8933 | 0.8348 | 0.8760 | 0.8549 | 0.9584 |
|
| 73 |
+
| 0.0073 | 7.0 | 12103 | 0.3238 | 0.5511 | 0.6021 | 0.5754 | 0.9528 | 0.9642 | 0.9585 | 0.8751 | 0.8956 | 0.8852 | 0.8386 | 0.8658 | 0.8520 | 0.9558 |
|
| 74 |
+
| 0.0072 | 8.0 | 13832 | 0.3561 | 0.5737 | 0.5712 | 0.5725 | 0.9547 | 0.9614 | 0.9580 | 0.88 | 0.8986 | 0.8892 | 0.8510 | 0.8596 | 0.8553 | 0.9557 |
|
| 75 |
+
| 0.0048 | 9.0 | 15561 | 0.3452 | 0.5739 | 0.5815 | 0.5777 | 0.9447 | 0.9719 | 0.9581 | 0.8767 | 0.9092 | 0.8927 | 0.8457 | 0.8701 | 0.8578 | 0.9573 |
|
| 76 |
+
| 0.0039 | 10.0 | 17290 | 0.3492 | 0.5700 | 0.5742 | 0.5721 | 0.9528 | 0.9642 | 0.9585 | 0.8825 | 0.9032 | 0.8927 | 0.85 | 0.8631 | 0.8565 | 0.9586 |
|
| 77 |
+
| 0.0019 | 11.0 | 19019 | 0.3629 | 0.5796 | 0.5771 | 0.5784 | 0.9502 | 0.9656 | 0.9579 | 0.8824 | 0.9077 | 0.8949 | 0.8516 | 0.8661 | 0.8588 | 0.9567 |
|
| 78 |
+
| 0.0007 | 12.0 | 20748 | 0.3660 | 0.5752 | 0.5786 | 0.5769 | 0.9489 | 0.9642 | 0.9565 | 0.8852 | 0.9039 | 0.8945 | 0.8507 | 0.8643 | 0.8574 | 0.9575 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.38.2
|
| 84 |
+
- Pytorch 2.2.1+cu121
|
| 85 |
+
- Datasets 2.18.0
|
| 86 |
+
- Tokenizers 0.15.2
|