Hugging Face's logo

Luciano
/
bertimbau-large-lener_br

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
Portuguese
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
6
Luciano commited on
Commit
0023aa6
•
1 Parent(s): 8f9cef7

Commit using trainer.push_to_hub()

Browse files
Files changed (6) hide show
  1. README.md +24 -12
  2. pytorch_model.bin +1 -1
  3. runs/Jul07_12-50-16_8f73a8824ff0/1625662271.4580977/events.out.tfevents.1625662271.8f73a8824ff0.79.1 +0 -0
  4. runs/Jul07_12-50-16_8f73a8824ff0/events.out.tfevents.1625662271.8f73a8824ff0.79.0 +0 -0
  5. runs/Jul07_12-50-16_8f73a8824ff0/events.out.tfevents.1625669580.8f73a8824ff0.79.2 +0 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model_index:
22
  metric:
23
  name: Accuracy
24
  type: accuracy
25
- value: 0.9790177823152056
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,11 +32,11 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the lener_br dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.1064
36
- - Precision: 0.8676
37
- - Recall: 0.9204
38
- - F1: 0.8932
39
- - Accuracy: 0.9790
40
 
41
  ## Model description
42
 
@@ -61,15 +61,27 @@ The following hyperparameters were used during training:
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
- - num_epochs: 3
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
69
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
70
- | 0.0601 | 1.0 | 1957 | 0.1097 | 0.8223 | 0.9004 | 0.8596 | 0.9700 |
71
- | 0.0301 | 2.0 | 3914 | 0.1148 | 0.8070 | 0.9333 | 0.8656 | 0.9722 |
72
- | 0.0122 | 3.0 | 5871 | 0.1064 | 0.8676 | 0.9204 | 0.8932 | 0.9790 |
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metric:
23
  name: Accuracy
24
  type: accuracy
25
+ value: 0.9801301293674859
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the lener_br dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.1271
36
+ - Precision: 0.8965
37
+ - Recall: 0.9198
38
+ - F1: 0.9080
39
+ - Accuracy: 0.9801
40
 
41
  ## Model description
42
 
 
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
+ - num_epochs: 15
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
69
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
70
+ | 0.0674 | 1.0 | 1957 | 0.1349 | 0.7617 | 0.8710 | 0.8127 | 0.9594 |
71
+ | 0.0443 | 2.0 | 3914 | 0.1867 | 0.6862 | 0.9194 | 0.7858 | 0.9575 |
72
+ | 0.0283 | 3.0 | 5871 | 0.1185 | 0.8206 | 0.8766 | 0.8477 | 0.9678 |
73
+ | 0.0226 | 4.0 | 7828 | 0.1405 | 0.8072 | 0.8978 | 0.8501 | 0.9708 |
74
+ | 0.0141 | 5.0 | 9785 | 0.1898 | 0.7224 | 0.9194 | 0.8090 | 0.9629 |
75
+ | 0.01 | 6.0 | 11742 | 0.1655 | 0.9062 | 0.8856 | 0.8958 | 0.9741 |
76
+ | 0.012 | 7.0 | 13699 | 0.1271 | 0.8965 | 0.9198 | 0.9080 | 0.9801 |
77
+ | 0.0091 | 8.0 | 15656 | 0.1919 | 0.8890 | 0.8886 | 0.8888 | 0.9719 |
78
+ | 0.0042 | 9.0 | 17613 | 0.1725 | 0.8977 | 0.8985 | 0.8981 | 0.9744 |
79
+ | 0.0043 | 10.0 | 19570 | 0.1530 | 0.8878 | 0.9034 | 0.8955 | 0.9761 |
80
+ | 0.0042 | 11.0 | 21527 | 0.1635 | 0.8792 | 0.9108 | 0.8947 | 0.9774 |
81
+ | 0.0033 | 12.0 | 23484 | 0.2009 | 0.8155 | 0.9138 | 0.8619 | 0.9719 |
82
+ | 0.0008 | 13.0 | 25441 | 0.1766 | 0.8737 | 0.9135 | 0.8932 | 0.9755 |
83
+ | 0.0005 | 14.0 | 27398 | 0.1868 | 0.8616 | 0.9129 | 0.8865 | 0.9743 |
84
+ | 0.0014 | 15.0 | 29355 | 0.1910 | 0.8694 | 0.9101 | 0.8893 | 0.9746 |
85
 
86
 
87
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d7af9507f9f2e33a1b3b29bb8709e87345f3505cdbb95f6bea3c3a4ea75964f
3
  size 1333601457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383c5d43f45c580b317569cfdb9baed65f212f2be710aebbfffb7f1a0d545165
3
  size 1333601457
runs/Jul07_12-50-16_8f73a8824ff0/1625662271.4580977/events.out.tfevents.1625662271.8f73a8824ff0.79.1 ADDED
Binary file (4.24 kB). View file
 
runs/Jul07_12-50-16_8f73a8824ff0/events.out.tfevents.1625662271.8f73a8824ff0.79.0 ADDED
Binary file (20.5 kB). View file
 
runs/Jul07_12-50-16_8f73a8824ff0/events.out.tfevents.1625669580.8f73a8824ff0.79.2 ADDED
Binary file (521 Bytes). View file
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fde77b03eaba55b7e8cbf1fc6ad7e3091e69d1151b9825037d2098d45b5e61c
3
  size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb0c401f020911a7fd2ca37c6530ed5e0a5339f7f0da78700f9b56e57901680
3
  size 2671