Hugging Face's logo

pabRomero
/
BERT-full-finetuned-ner-pablo

Token Classification
Transformers
TensorBoard
ONNX
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
pabRomero commited on
Commit
2a6197a
•
1 Parent(s): 91411ec

Training complete

Browse files
Files changed (2) hide show
  1. README.md +17 -15
  2. runs/Aug23_13-54-39_ee1898c059d7/events.out.tfevents.1724421280.ee1898c059d7.1664.4 +2 -2
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.7097
25
- - Precision: 0.0
26
- - Recall: 0.0
27
- - F1: 0.0
28
- - Accuracy: 0.8695
29
 
30
  ## Model description
31
 
@@ -44,10 +44,12 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 0.0004
48
- - train_batch_size: 512
49
- - eval_batch_size: 512
50
  - seed: 42
 
 
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_ratio: 0.05
@@ -56,13 +58,13 @@ The following hyperparameters were used during training:
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
61
- | No log | 1.0 | 32 | 0.7111 | 0.0 | 0.0 | 0.0 | 0.8695 |
62
- | No log | 2.0 | 64 | 0.7154 | 0.0 | 0.0 | 0.0 | 0.8695 |
63
- | No log | 3.0 | 96 | 0.7107 | 0.0 | 0.0 | 0.0 | 0.8695 |
64
- | No log | 4.0 | 128 | 0.7107 | 0.0 | 0.0 | 0.0 | 0.8695 |
65
- | No log | 5.0 | 160 | 0.7097 | 0.0 | 0.0 | 0.0 | 0.8695 |
66
 
67
 
68
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.1111
25
+ - Precision: 0.8022
26
+ - Recall: 0.7972
27
+ - F1: 0.7997
28
+ - Accuracy: 0.9747
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 0.0002
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
  - seed: 42
51
+ - gradient_accumulation_steps: 4
52
+ - total_train_batch_size: 64
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
  - lr_scheduler_warmup_ratio: 0.05
 
58
 
59
  ### Training results
60
 
61
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
62
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
63
+ | No log | 0.9970 | 252 | 0.0973 | 0.7590 | 0.7702 | 0.7646 | 0.9726 |
64
+ | 0.164 | 1.9980 | 505 | 0.0867 | 0.7999 | 0.7776 | 0.7886 | 0.9751 |
65
+ | 0.164 | 2.9990 | 758 | 0.0903 | 0.8044 | 0.7862 | 0.7952 | 0.9747 |
66
+ | 0.0439 | 4.0 | 1011 | 0.0970 | 0.8032 | 0.7960 | 0.7996 | 0.9746 |
67
+ | 0.0439 | 4.9852 | 1260 | 0.1111 | 0.8022 | 0.7972 | 0.7997 | 0.9747 |
68
 
69
 
70
  ### Framework versions
runs/Aug23_13-54-39_ee1898c059d7/events.out.tfevents.1724421280.ee1898c059d7.1664.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b03bbacae291621ec8215a080ba00fe31dfdb961d6dfd289f63668ad7997c43
3
- size 8053
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841eb39355f627a882744dbf9312bdc0a65695d5d80c9df1e01e0e3c772e8b04
3
+ size 8879