Hugging Face's logo

adriansanz
/
test6_balanced

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
zero-shot_classification
Model card Files
xet
Metrics Community
adriansanz commited on
Commit
b6531ca
路
verified 路
1 Parent(s): e4ce9cd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -47
README.md CHANGED
@@ -3,78 +3,55 @@ license: apache-2.0
3
  base_model: ibaucells/RoBERTa-ca-CaWikiTC
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: test6_balanced
8
  results: []
9
  ---
10
 
11
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
- should probably proofread and complete it, then remove this comment. -->
13
 
14
  # test6_balanced
15
 
16
- This model is a fine-tuned version of [ibaucells/RoBERTa-ca-CaWikiTC](https://huggingface.co/ibaucells/RoBERTa-ca-CaWikiTC) on the None dataset.
17
- It achieves the following results on the evaluation set:
18
- - Loss: 1.6982
19
 
20
- ## Model description
21
 
22
- More information needed
23
 
24
- ## Intended uses & limitations
25
 
26
- More information needed
27
 
28
- ## Training and evaluation data
29
 
30
- More information needed
31
 
32
- ## Training procedure
33
 
34
- ### Training hyperparameters
35
 
36
- The following hyperparameters were used during training:
37
  - learning_rate: 5e-05
38
  - train_batch_size: 10
39
  - eval_batch_size: 10
40
  - seed: 42
41
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 500
44
  - num_epochs: 25
45
 
46
- ### Training results
47
-
48
- | Training Loss | Epoch | Step | Validation Loss |
49
- |:-------------:|:-----:|:----:|:---------------:|
50
- | 2.8358 | 1.0 | 63 | 2.8655 |
51
- | 2.8469 | 2.0 | 126 | 2.8447 |
52
- | 2.7935 | 3.0 | 189 | 2.8533 |
53
- | 2.8191 | 4.0 | 252 | 2.8142 |
54
- | 2.6885 | 5.0 | 315 | 2.8259 |
55
- | 2.5876 | 6.0 | 378 | 2.6759 |
56
- | 2.5032 | 7.0 | 441 | 2.6097 |
57
- | 2.3133 | 8.0 | 504 | 2.5192 |
58
- | 2.1289 | 9.0 | 567 | 2.5403 |
59
- | 1.9344 | 10.0 | 630 | 2.4371 |
60
- | 1.6321 | 11.0 | 693 | 2.2946 |
61
- | 1.4731 | 12.0 | 756 | 2.1326 |
62
- | 1.2114 | 13.0 | 819 | 2.0522 |
63
- | 1.1537 | 14.0 | 882 | 2.1146 |
64
- | 1.022 | 15.0 | 945 | 1.9946 |
65
- | 0.8745 | 16.0 | 1008 | 1.8565 |
66
- | 0.5796 | 17.0 | 1071 | 1.7965 |
67
- | 0.5599 | 18.0 | 1134 | 1.7063 |
68
- | 0.4366 | 19.0 | 1197 | 1.9333 |
69
- | 0.3558 | 20.0 | 1260 | 1.8851 |
70
- | 0.3272 | 21.0 | 1323 | 1.8570 |
71
- | 0.2594 | 22.0 | 1386 | 1.8596 |
72
- | 0.2432 | 23.0 | 1449 | 1.9433 |
73
- | 0.2298 | 24.0 | 1512 | 1.9467 |
74
- | 0.266 | 25.0 | 1575 | 1.9150 |
75
-
76
-
77
- ### Framework versions
78
 
79
  - Transformers 4.38.2
80
  - Pytorch 2.1.0+cu121
 
3
  base_model: ibaucells/RoBERTa-ca-CaWikiTC
4
  tags:
5
  - generated_from_trainer
6
+ - zero-shot_classification
7
  model-index:
8
  - name: test6_balanced
9
  results: []
10
  ---
11
 
12
+ <!-- Este modelo ha sido ajustado autom谩ticamente seg煤n la informaci贸n a la que el Trainer tuvo acceso. Deber铆as revisarlo y completarlo, luego elimina este comentario. -->
 
13
 
14
  # test6_balanced
15
 
16
+ Este modelo ha sido ajustado para la clasificaci贸n de cero disparos utilizando una versi贸n preentrenada de [ibaucells/RoBERTa-ca-CaWikiTC](https://huggingface.co/ibaucells/RoBERTa-ca-CaWikiTC) en el conjunto de datos None.
17
+ Logra los siguientes resultados en el conjunto de evaluaci贸n:
18
+ - P茅rdida: 1.6982
19
 
20
+ ## Descripci贸n del modelo
21
 
22
+ Se necesita m谩s informaci贸n sobre este modelo.
23
 
24
+ ## Usos previstos y limitaciones
25
 
26
+ Se necesita m谩s informaci贸n sobre los usos previstos y las limitaciones de este modelo.
27
 
28
+ ## Datos de entrenamiento y evaluaci贸n
29
 
30
+ Se necesita m谩s informaci贸n sobre los datos utilizados para entrenar y evaluar este modelo.
31
 
32
+ ## Procedimiento de entrenamiento
33
 
34
+ ### Hiperpar谩metros de entrenamiento
35
 
36
+ Se utilizaron los siguientes hiperpar谩metros durante el entrenamiento:
37
  - learning_rate: 5e-05
38
  - train_batch_size: 10
39
  - eval_batch_size: 10
40
  - seed: 42
41
+ - optimizer: Adam con betas=(0.9,0.999) y epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 500
44
  - num_epochs: 25
45
 
46
+ ### Resultados del entrenamiento
47
+
48
+ | P茅rdida de entrenamiento | 脡poca | Paso | P茅rdida de validaci贸n |
49
+ |:------------------------:|:-----:|:----:|:---------------------:|
50
+ | 2.8358 | 1.0 | 63 | 2.8655 |
51
+ | 2.8469 | 2.0 | 126 | 2.8447 |
52
+ | ... | ... | ... | ... |
53
+
54
+ ### Versiones del framework
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
  - Transformers 4.38.2
57
  - Pytorch 2.1.0+cu121