Hugging Face's logo

Aleksandar
/
electra-srb-ner-setimes

Token Classification
Transformers
PyTorch
Safetensors
electra
Generated from Trainer
Inference Endpoints
Model card Files Community
1
Aleksandar commited on
Commit
866c201
•
1 Parent(s): 139e999

add model

Browse files
Files changed (3) hide show
  1. README.md +27 -12
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ model_index:
17
  metric:
18
  name: Accuracy
19
  type: accuracy
20
- value: 0.9411086738297951
21
  ---
22
 
23
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,11 +27,11 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  This model was trained from scratch on the None dataset.
29
  It achieves the following results on the evaluation set:
30
- - Loss: 0.2071
31
- - Precision: 0.7502
32
- - Recall: 0.7385
33
- - F1: 0.7443
34
- - Accuracy: 0.9411
35
 
36
  ## Model description
37
 
@@ -56,17 +56,32 @@ The following hyperparameters were used during training:
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
- - num_epochs: 5
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
64
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
65
- | No log | 1.0 | 104 | 0.3002 | 0.6859 | 0.5930 | 0.6361 | 0.9171 |
66
- | No log | 2.0 | 208 | 0.2449 | 0.7509 | 0.6422 | 0.6923 | 0.9287 |
67
- | No log | 3.0 | 312 | 0.2165 | 0.7557 | 0.7062 | 0.7301 | 0.9378 |
68
- | No log | 4.0 | 416 | 0.2148 | 0.7402 | 0.7398 | 0.7400 | 0.9388 |
69
- | 0.2565 | 5.0 | 520 | 0.2071 | 0.7502 | 0.7385 | 0.7443 | 0.9411 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
 
17
  metric:
18
  name: Accuracy
19
  type: accuracy
20
+ value: 0.9546789604788638
21
  ---
22
 
23
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
27
 
28
  This model was trained from scratch on the None dataset.
29
  It achieves the following results on the evaluation set:
30
+ - Loss: 0.2804
31
+ - Precision: 0.8286
32
+ - Recall: 0.8081
33
+ - F1: 0.8182
34
+ - Accuracy: 0.9547
35
 
36
  ## Model description
37
 
 
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
+ - num_epochs: 20
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
64
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
65
+ | No log | 1.0 | 104 | 0.2981 | 0.6737 | 0.6113 | 0.6410 | 0.9174 |
66
+ | No log | 2.0 | 208 | 0.2355 | 0.7279 | 0.6701 | 0.6978 | 0.9307 |
67
+ | No log | 3.0 | 312 | 0.2079 | 0.7707 | 0.7062 | 0.7371 | 0.9402 |
68
+ | No log | 4.0 | 416 | 0.2078 | 0.7689 | 0.7479 | 0.7582 | 0.9449 |
69
+ | 0.2391 | 5.0 | 520 | 0.2089 | 0.8083 | 0.7476 | 0.7767 | 0.9484 |
70
+ | 0.2391 | 6.0 | 624 | 0.2199 | 0.7981 | 0.7726 | 0.7851 | 0.9487 |
71
+ | 0.2391 | 7.0 | 728 | 0.2528 | 0.8205 | 0.7749 | 0.7971 | 0.9511 |
72
+ | 0.2391 | 8.0 | 832 | 0.2265 | 0.8074 | 0.8003 | 0.8038 | 0.9524 |
73
+ | 0.2391 | 9.0 | 936 | 0.2843 | 0.8265 | 0.7716 | 0.7981 | 0.9504 |
74
+ | 0.0378 | 10.0 | 1040 | 0.2450 | 0.8024 | 0.8019 | 0.8021 | 0.9520 |
75
+ | 0.0378 | 11.0 | 1144 | 0.2550 | 0.8116 | 0.7986 | 0.8051 | 0.9519 |
76
+ | 0.0378 | 12.0 | 1248 | 0.2706 | 0.8208 | 0.7957 | 0.8081 | 0.9532 |
77
+ | 0.0378 | 13.0 | 1352 | 0.2664 | 0.8040 | 0.8035 | 0.8038 | 0.9530 |
78
+ | 0.0378 | 14.0 | 1456 | 0.2571 | 0.8011 | 0.8110 | 0.8060 | 0.9529 |
79
+ | 0.0099 | 15.0 | 1560 | 0.2673 | 0.8051 | 0.8129 | 0.8090 | 0.9534 |
80
+ | 0.0099 | 16.0 | 1664 | 0.2733 | 0.8074 | 0.8087 | 0.8081 | 0.9529 |
81
+ | 0.0099 | 17.0 | 1768 | 0.2835 | 0.8254 | 0.8074 | 0.8163 | 0.9543 |
82
+ | 0.0099 | 18.0 | 1872 | 0.2771 | 0.8222 | 0.8081 | 0.8151 | 0.9545 |
83
+ | 0.0099 | 19.0 | 1976 | 0.2776 | 0.8237 | 0.8084 | 0.8160 | 0.9546 |
84
+ | 0.0044 | 20.0 | 2080 | 0.2804 | 0.8286 | 0.8081 | 0.8182 | 0.9547 |
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:ec7b9a76d0659ac4fa7dfd90789ea31addd81861c9cb485282eb9607256138da
3
  size 435681969
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a93758f8fd881ec10a826ef45e06c444d60b82c29d7a9a59c47eda5e04a834
3
  size 435681969
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b35accb70711230c2bc8838c7735dc30698cdca306d100123e49278684e1394
3
  size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b3b47be07efeba22d50f43ae9a9a313348e7d7cbd3ae3d618305ada3403472
3
  size 2671