Fine-tuning completed
Browse files
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: PlanTL-GOB-ES/roberta-base-bne
|
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_RoBERTa_base_bne_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_RoBERTa_base_bne_fine_tuned
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3480
|
24 |
+
- Negref Precision: 0.5338
|
25 |
+
- Negref Recall: 0.5565
|
26 |
+
- Negref F1: 0.5449
|
27 |
+
- Neg Precision: 0.9552
|
28 |
+
- Neg Recall: 0.9593
|
29 |
+
- Neg F1: 0.9573
|
30 |
+
- Nsco Precision: 0.8862
|
31 |
+
- Nsco Recall: 0.9070
|
32 |
+
- Nsco F1: 0.8964
|
33 |
+
- Precision: 0.8428
|
34 |
+
- Recall: 0.8591
|
35 |
+
- F1: 0.8509
|
36 |
+
- Accuracy: 0.9569
|
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 |
+
| 0.0092 | 1.0 | 1729 | 0.3395 | 0.5044 | 0.5051 | 0.5048 | 0.9546 | 0.9600 | 0.9573 | 0.8681 | 0.8911 | 0.8794 | 0.8323 | 0.8430 | 0.8376 | 0.9552 |
|
68 |
+
| 0.0096 | 2.0 | 3458 | 0.2674 | 0.4694 | 0.5962 | 0.5252 | 0.9483 | 0.9663 | 0.9572 | 0.8717 | 0.8888 | 0.8801 | 0.8070 | 0.8629 | 0.8340 | 0.9545 |
|
69 |
+
| 0.0069 | 3.0 | 5187 | 0.2922 | 0.5054 | 0.5477 | 0.5257 | 0.9488 | 0.9628 | 0.9557 | 0.8740 | 0.8865 | 0.8802 | 0.8275 | 0.8509 | 0.8390 | 0.9559 |
|
70 |
+
| 0.0066 | 4.0 | 6916 | 0.2958 | 0.5371 | 0.5639 | 0.5501 | 0.9533 | 0.9614 | 0.9573 | 0.8714 | 0.8971 | 0.8841 | 0.8368 | 0.8576 | 0.8471 | 0.9559 |
|
71 |
+
| 0.0042 | 5.0 | 8645 | 0.2978 | 0.5475 | 0.5419 | 0.5446 | 0.9584 | 0.9551 | 0.9567 | 0.8850 | 0.8964 | 0.8906 | 0.8491 | 0.8503 | 0.8497 | 0.9558 |
|
72 |
+
| 0.0072 | 6.0 | 10374 | 0.2875 | 0.5068 | 0.5477 | 0.5265 | 0.9547 | 0.9614 | 0.9580 | 0.8791 | 0.8911 | 0.8850 | 0.8319 | 0.8521 | 0.8419 | 0.9561 |
|
73 |
+
| 0.0045 | 7.0 | 12103 | 0.3203 | 0.5551 | 0.5624 | 0.5587 | 0.9561 | 0.9628 | 0.9594 | 0.8744 | 0.9002 | 0.8871 | 0.8448 | 0.8591 | 0.8519 | 0.9567 |
|
74 |
+
| 0.0019 | 8.0 | 13832 | 0.3412 | 0.5339 | 0.5433 | 0.5386 | 0.9565 | 0.9579 | 0.9572 | 0.8921 | 0.9009 | 0.8965 | 0.8468 | 0.8535 | 0.8502 | 0.9560 |
|
75 |
+
| 0.0013 | 9.0 | 15561 | 0.3270 | 0.5033 | 0.5551 | 0.5279 | 0.9533 | 0.9600 | 0.9566 | 0.8900 | 0.9062 | 0.8981 | 0.8335 | 0.8588 | 0.8459 | 0.9574 |
|
76 |
+
| 0.0009 | 10.0 | 17290 | 0.3257 | 0.5285 | 0.5580 | 0.5429 | 0.9513 | 0.9593 | 0.9552 | 0.8826 | 0.9039 | 0.8931 | 0.8381 | 0.8582 | 0.8480 | 0.9567 |
|
77 |
+
| 0.0007 | 11.0 | 19019 | 0.3303 | 0.5299 | 0.5595 | 0.5443 | 0.9586 | 0.9586 | 0.9586 | 0.8859 | 0.9047 | 0.8952 | 0.8423 | 0.8585 | 0.8503 | 0.9574 |
|
78 |
+
| 0.0 | 12.0 | 20748 | 0.3480 | 0.5338 | 0.5565 | 0.5449 | 0.9552 | 0.9593 | 0.9573 | 0.8862 | 0.9070 | 0.8964 | 0.8428 | 0.8591 | 0.8509 | 0.9569 |
|
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
|