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
d339adb
·
verified ·
1 Parent(s): 4e7dc0f

Training complete

Browse files
Files changed (2) hide show
  1. README.md +16 -15
  2. runs/Aug21_15-05-05_e0ea3028ecfc/events.out.tfevents.1724252709.e0ea3028ecfc.330.4 +2 -2
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  license: apache-2.0
3
  base_model: google-bert/bert-base-uncased
4
  tags:
@@ -20,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  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.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1071
24
- - Precision: 0.7993
25
- - Recall: 0.7887
26
- - F1: 0.7940
27
- - Accuracy: 0.9768
28
 
29
  ## Model description
30
 
@@ -43,12 +44,12 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 0.0002
47
- - train_batch_size: 16
48
- - eval_batch_size: 16
49
  - seed: 42
50
  - gradient_accumulation_steps: 4
51
- - total_train_batch_size: 64
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
  - lr_scheduler_warmup_ratio: 0.05
@@ -59,16 +60,16 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
61
  |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
62
- | No log | 0.9923 | 97 | 0.1037 | 0.7655 | 0.7399 | 0.7525 | 0.9725 |
63
- | No log | 1.9949 | 195 | 0.0907 | 0.8123 | 0.7488 | 0.7792 | 0.9759 |
64
- | No log | 2.9974 | 293 | 0.0922 | 0.7739 | 0.7872 | 0.7805 | 0.9758 |
65
- | No log | 4.0 | 391 | 0.0986 | 0.7856 | 0.7895 | 0.7875 | 0.9760 |
66
- | No log | 4.9616 | 485 | 0.1071 | 0.7993 | 0.7887 | 0.7940 | 0.9768 |
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.44.0
72
  - Pytorch 2.4.0+cu121
73
  - Datasets 2.21.0
74
  - Tokenizers 0.19.1
 
1
  ---
2
+ library_name: transformers
3
  license: apache-2.0
4
  base_model: google-bert/bert-base-uncased
5
  tags:
 
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: 0.1008
25
+ - Precision: 0.7986
26
+ - Recall: 0.7968
27
+ - F1: 0.7977
28
+ - Accuracy: 0.9750
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 512
49
+ - eval_batch_size: 512
50
  - seed: 42
51
  - gradient_accumulation_steps: 4
52
+ - total_train_batch_size: 2048
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
 
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
62
  |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
63
+ | No log | 0.8696 | 5 | 0.0968 | 0.8048 | 0.7943 | 0.7995 | 0.9757 |
64
+ | No log | 1.9130 | 11 | 0.0984 | 0.8030 | 0.7966 | 0.7998 | 0.9754 |
65
+ | No log | 2.9565 | 17 | 0.1003 | 0.8008 | 0.7965 | 0.7987 | 0.9751 |
66
+ | No log | 4.0 | 23 | 0.1008 | 0.7986 | 0.7968 | 0.7977 | 0.9750 |
67
+ | No log | 4.3478 | 25 | 0.1008 | 0.7986 | 0.7968 | 0.7977 | 0.9750 |
68
 
69
 
70
  ### Framework versions
71
 
72
+ - Transformers 4.44.1
73
  - Pytorch 2.4.0+cu121
74
  - Datasets 2.21.0
75
  - Tokenizers 0.19.1
runs/Aug21_15-05-05_e0ea3028ecfc/events.out.tfevents.1724252709.e0ea3028ecfc.330.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7ce6f93005906fa65052b9995ef6a4556be75de49bb22671a5c2bb2b149f07b
3
- size 7637
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b613601997497602c2ef657f69d63c1d5dc12058bc1f10d7fcf90dd5b1784666
3
+ size 8448