Hugging Face's logo

KPOETA
/
Bert-Los-Muchachos

Token Classification
Transformers
TensorBoard
Safetensors
Spanish
bert
Inference Endpoints
Model card Files Metrics Community
KPOETA commited on
Commit
c359689
•
1 Parent(s): 83045fc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -12
README.md CHANGED
@@ -15,11 +15,11 @@ metrics:
15
  Este es modelo resultado de un finetuning de
16
  [FacebookAI/xlm-roberta-large-finetuned-conll03-english](https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-english) sobre el conll2002 dataset.
17
  Los siguientes son los resultados sobre el conjunto de evaluación:
18
- - Loss: 0.1364
19
- - Precision: 0.8806
20
- - Recall: 0.8897
21
- - F1: 0.8851
22
- - Accuracy: 0.9806
23
 
24
 
25
  ### Model Description
@@ -65,11 +65,21 @@ The following hyperparameters were used during training:
65
  - seed=42,
66
 
67
  ### Training results
 
 
 
 
 
 
 
 
 
 
 
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
70
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
71
- | 0.0743 | 1.0 | 2081 | 0.1131 | 0.8385 | 0.8587 | 0.8485 | 0.9771 |
72
- | 0.049 | 2.0 | 4162 | 0.1429 | 0.8492 | 0.8564 | 0.8528 | 0.9756 |
73
- | 0.031 | 3.0 | 6243 | 0.1298 | 0.8758 | 0.8817 | 0.8787 | 0.9800 |
74
- | 0.0185 | 4.0 | 8324 | 0.1279 | 0.8827 | 0.8890 | 0.8859 | 0.9808 |
75
- | 0.0125 | 5.0 | 10405 | 0.1364 | 0.8806 | 0.8897 | 0.8851 | 0.9806 |
 
15
  Este es modelo resultado de un finetuning de
16
  [FacebookAI/xlm-roberta-large-finetuned-conll03-english](https://huggingface.co/FacebookAI/xlm-roberta-large-finetuned-conll03-english) sobre el conll2002 dataset.
17
  Los siguientes son los resultados sobre el conjunto de evaluación:
18
+ - Loss: 0.17227034270763397
19
+ - Precision: 0.8140103176758078
20
+ - Recall: 0.8423714526552403
21
+ - F1: 0.8279480806407071
22
+ - Accuracy: 0.9781214374225526
23
 
24
 
25
  ### Model Description
 
65
  - seed=42,
66
 
67
  ### Training results
68
+ | Metric | Value |
69
+ |-----------------|-------------|
70
+ | eval_loss | 0.17227034270763397 |
71
+ | eval_precision | 0.8140103176758078 |
72
+ | eval_recall | 0.8423714526552403 |
73
+ | eval_f1 | 0.8279480806407071 |
74
+ | eval_accuracy | 0.9781214374225526 |
75
+ | eval_runtime | 7.6283 |
76
+ | eval_samples_per_second | 198.995 |
77
+ | eval_steps_per_second | 24.907 |
78
+ | epoch | 5.0 |
79
 
80
+ | Label | Precision | Recall | F1 | Number |
81
+ |--------|-----------|--------|------------|--------|
82
+ | LOC | 0.8303085299455535 | 0.8440959409594095 | 0.8371454711802379 | 1084 |
83
+ | MISC | 0.5976331360946746 | 0.5941176470588235 | 0.5958702064896756 | 340 |
84
+ | ORG | 0.7989276139410187 | 0.8514285714285714 | 0.8243430152143845 | 1400 |
85
+ | PER | 0.9174434087882823 | 0.9374149659863945 | 0.9273216689098251 | 735 |