Hugging Face's logo

rhaymison
/
bert-squad-portuguese

Question Answering
Transformers
TensorBoard
Safetensors
Portuguese
bert
Generated from Trainer
portuguese
qa
Inference Endpoints
Model card Files Metrics Community
rhaymison commited on
Commit
3f9876b
•
1 Parent(s): 118976d

rhaymison/bert-squad-portuguese

Browse files
Files changed (4) hide show
  1. README.md +37 -37
  2. model.safetensors +1 -1
  3. runs/Mar21_13-29-41_60dd32125665/events.out.tfevents.1711039849.60dd32125665.4249.2 +3 -0
  4. tokenizer.json +4 -13
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.5641
19
 
20
  ## Model description
21
 
@@ -46,42 +46,42 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:-----:|:---------------:|
49
- | 2.7626 | 0.08 | 500 | 2.5754 |
50
- | 2.5464 | 0.16 | 1000 | 2.3808 |
51
- | 2.4107 | 0.24 | 1500 | 2.2688 |
52
- | 2.2761 | 0.32 | 2000 | 2.1665 |
53
- | 2.2131 | 0.41 | 2500 | 2.0738 |
54
- | 2.1205 | 0.49 | 3000 | 1.9971 |
55
- | 2.0377 | 0.57 | 3500 | 1.9840 |
56
- | 2.0069 | 0.65 | 4000 | 1.8964 |
57
- | 1.9743 | 0.73 | 4500 | 1.8704 |
58
- | 1.9438 | 0.81 | 5000 | 1.8286 |
59
- | 1.9039 | 0.89 | 5500 | 1.8021 |
60
- | 1.8537 | 0.97 | 6000 | 1.7742 |
61
- | 1.6983 | 1.06 | 6500 | 1.7601 |
62
- | 1.6149 | 1.14 | 7000 | 1.7156 |
63
- | 1.5687 | 1.22 | 7500 | 1.7334 |
64
- | 1.6083 | 1.3 | 8000 | 1.6960 |
65
- | 1.6093 | 1.38 | 8500 | 1.6979 |
66
- | 1.6001 | 1.46 | 9000 | 1.6654 |
67
- | 1.5706 | 1.54 | 9500 | 1.6478 |
68
- | 1.5379 | 1.62 | 10000 | 1.6440 |
69
- | 1.5143 | 1.7 | 10500 | 1.6111 |
70
- | 1.4894 | 1.79 | 11000 | 1.6249 |
71
- | 1.5061 | 1.87 | 11500 | 1.5881 |
72
- | 1.4999 | 1.95 | 12000 | 1.5907 |
73
- | 1.3902 | 2.03 | 12500 | 1.5939 |
74
- | 1.2689 | 2.11 | 13000 | 1.6066 |
75
- | 1.2791 | 2.19 | 13500 | 1.5989 |
76
- | 1.2811 | 2.27 | 14000 | 1.6070 |
77
- | 1.2999 | 2.35 | 14500 | 1.5910 |
78
- | 1.248 | 2.44 | 15000 | 1.6142 |
79
- | 1.2373 | 2.52 | 15500 | 1.5919 |
80
- | 1.2767 | 2.6 | 16000 | 1.5836 |
81
- | 1.2809 | 2.68 | 16500 | 1.5665 |
82
- | 1.267 | 2.76 | 17000 | 1.5690 |
83
- | 1.2798 | 2.84 | 17500 | 1.5629 |
84
- | 1.26 | 2.92 | 18000 | 1.5641 |
85
 
86
 
87
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.6799
19
 
20
  ## Model description
21
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 1.3183 | 0.08 | 500 | 1.6474 |
50
+ | 1.335 | 0.16 | 1000 | 1.6289 |
51
+ | 1.3245 | 0.24 | 1500 | 1.6070 |
52
+ | 1.3055 | 0.32 | 2000 | 1.6563 |
53
+ | 1.3085 | 0.41 | 2500 | 1.5719 |
54
+ | 1.2918 | 0.49 | 3000 | 1.6650 |
55
+ | 1.2827 | 0.57 | 3500 | 1.5858 |
56
+ | 1.3122 | 0.65 | 4000 | 1.5870 |
57
+ | 1.2586 | 0.73 | 4500 | 1.5693 |
58
+ | 1.2943 | 0.81 | 5000 | 1.5659 |
59
+ | 1.2573 | 0.89 | 5500 | 1.5207 |
60
+ | 1.2564 | 0.97 | 6000 | 1.5355 |
61
+ | 1.0725 | 1.06 | 6500 | 1.6185 |
62
+ | 0.9957 | 1.14 | 7000 | 1.5904 |
63
+ | 0.972 | 1.22 | 7500 | 1.6978 |
64
+ | 0.9884 | 1.3 | 8000 | 1.6270 |
65
+ | 1.02 | 1.38 | 8500 | 1.5872 |
66
+ | 1.0234 | 1.46 | 9000 | 1.6245 |
67
+ | 1.0162 | 1.54 | 9500 | 1.6201 |
68
+ | 0.9969 | 1.62 | 10000 | 1.6262 |
69
+ | 0.998 | 1.7 | 10500 | 1.6099 |
70
+ | 0.9888 | 1.79 | 11000 | 1.6151 |
71
+ | 1.0034 | 1.87 | 11500 | 1.5837 |
72
+ | 1.0127 | 1.95 | 12000 | 1.5823 |
73
+ | 0.8975 | 2.03 | 12500 | 1.6466 |
74
+ | 0.7488 | 2.11 | 13000 | 1.7307 |
75
+ | 0.7538 | 2.19 | 13500 | 1.7256 |
76
+ | 0.7847 | 2.27 | 14000 | 1.7131 |
77
+ | 0.7876 | 2.35 | 14500 | 1.6858 |
78
+ | 0.7618 | 2.44 | 15000 | 1.7329 |
79
+ | 0.761 | 2.52 | 15500 | 1.7251 |
80
+ | 0.7887 | 2.6 | 16000 | 1.7077 |
81
+ | 0.8002 | 2.68 | 16500 | 1.6861 |
82
+ | 0.8038 | 2.76 | 17000 | 1.6818 |
83
+ | 0.802 | 2.84 | 17500 | 1.6932 |
84
+ | 0.8076 | 2.92 | 18000 | 1.6799 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51646d96c89d938829ea65ac9778511b50f2e7a6bbde549421f2ac54170cfd1e
3
  size 435596088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896aed7372717b83ac4d2a721f994fa4c07f2c3d4e44380a4273c41b37799353
3
  size 435596088
runs/Mar21_13-29-41_60dd32125665/events.out.tfevents.1711039849.60dd32125665.4249.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6430587df31a342845e45a516ede75547b23ff823ff163f8d9fd05b882fd2eb6
3
+ size 22346
tokenizer.json CHANGED
@@ -2,20 +2,11 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 384,
6
- "strategy": "OnlySecond",
7
- "stride": 128
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 384
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 0,
16
- "pad_type_id": 0,
17
- "pad_token": "[PAD]"
18
  },
 
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
 
 
 
 
 
 
 
 
 
 
8
  },
9
+ "padding": null,
10
  "added_tokens": [
11
  {
12
  "id": 0,