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_Development_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_Development_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: 0.2774
|
24 |
+
- Negref Precision: 0.5671
|
25 |
+
- Negref Recall: 0.5899
|
26 |
+
- Negref F1: 0.5782
|
27 |
+
- Neg Precision: 0.9511
|
28 |
+
- Neg Recall: 0.9771
|
29 |
+
- Neg F1: 0.9639
|
30 |
+
- Nsco Precision: 0.8734
|
31 |
+
- Nsco Recall: 0.9181
|
32 |
+
- Nsco F1: 0.8952
|
33 |
+
- Precision: 0.8399
|
34 |
+
- Recall: 0.8727
|
35 |
+
- F1: 0.8560
|
36 |
+
- Accuracy: 0.9615
|
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 |
+
| 0.1739 | 1.0 | 1729 | 0.1433 | 0.4553 | 0.4419 | 0.4485 | 0.9216 | 0.9629 | 0.9418 | 0.7944 | 0.8717 | 0.8313 | 0.7799 | 0.8180 | 0.7985 | 0.9555 |
|
68 |
+
| 0.1189 | 2.0 | 3458 | 0.1388 | 0.4859 | 0.5476 | 0.5149 | 0.9230 | 0.9683 | 0.9451 | 0.7951 | 0.8895 | 0.8397 | 0.7779 | 0.8494 | 0.8121 | 0.9569 |
|
69 |
+
| 0.0944 | 3.0 | 5187 | 0.1374 | 0.5771 | 0.5539 | 0.5653 | 0.9495 | 0.9640 | 0.9567 | 0.8535 | 0.8860 | 0.8695 | 0.8375 | 0.8476 | 0.8425 | 0.9615 |
|
70 |
+
| 0.0703 | 4.0 | 6916 | 0.1524 | 0.5415 | 0.6068 | 0.5723 | 0.9410 | 0.9749 | 0.9576 | 0.8476 | 0.8848 | 0.8658 | 0.8164 | 0.8628 | 0.8390 | 0.9602 |
|
71 |
+
| 0.0472 | 5.0 | 8645 | 0.1812 | 0.5306 | 0.5687 | 0.5490 | 0.9368 | 0.9716 | 0.9539 | 0.8440 | 0.8931 | 0.8679 | 0.8139 | 0.8566 | 0.8347 | 0.9585 |
|
72 |
+
| 0.0371 | 6.0 | 10374 | 0.2231 | 0.5371 | 0.5814 | 0.5584 | 0.9286 | 0.9803 | 0.9538 | 0.8448 | 0.9181 | 0.8799 | 0.8129 | 0.8723 | 0.8415 | 0.9588 |
|
73 |
+
| 0.031 | 7.0 | 12103 | 0.2036 | 0.5362 | 0.5793 | 0.5569 | 0.9509 | 0.9716 | 0.9611 | 0.8830 | 0.9145 | 0.8985 | 0.8340 | 0.8669 | 0.8501 | 0.9617 |
|
74 |
+
| 0.0226 | 8.0 | 13832 | 0.2390 | 0.5392 | 0.5666 | 0.5526 | 0.9507 | 0.9694 | 0.9600 | 0.8751 | 0.9157 | 0.8950 | 0.8335 | 0.8637 | 0.8483 | 0.9589 |
|
75 |
+
| 0.0174 | 9.0 | 15561 | 0.2462 | 0.5355 | 0.5899 | 0.5614 | 0.9443 | 0.9803 | 0.9620 | 0.8694 | 0.9169 | 0.8925 | 0.8258 | 0.8736 | 0.8491 | 0.9599 |
|
76 |
+
| 0.0098 | 10.0 | 17290 | 0.2751 | 0.5796 | 0.5772 | 0.5784 | 0.9490 | 0.9749 | 0.9618 | 0.8740 | 0.9145 | 0.8938 | 0.8443 | 0.8678 | 0.8559 | 0.9621 |
|
77 |
+
| 0.008 | 11.0 | 19019 | 0.2760 | 0.5611 | 0.5729 | 0.5669 | 0.9461 | 0.9771 | 0.9613 | 0.8695 | 0.9181 | 0.8931 | 0.8365 | 0.8691 | 0.8525 | 0.9606 |
|
78 |
+
| 0.0041 | 12.0 | 20748 | 0.2774 | 0.5671 | 0.5899 | 0.5782 | 0.9511 | 0.9771 | 0.9639 | 0.8734 | 0.9181 | 0.8952 | 0.8399 | 0.8727 | 0.8560 | 0.9615 |
|
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
|