Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task7_fold2

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
529c590
·
verified ·
1 Parent(s): e276169

End of training

Browse files
Files changed (1) hide show
  1. README.md +38 -35
README.md CHANGED
@@ -3,20 +3,20 @@ base_model: aubmindlab/bert-base-arabertv02
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
- - name: arabert_cross_relevance_task7_fold1
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
- # arabert_cross_relevance_task7_fold1
14
 
15
  This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.2223
18
- - Qwk: 0.0339
19
- - Mse: 0.2223
20
 
21
  ## Model description
22
 
@@ -45,36 +45,39 @@ The following hyperparameters were used during training:
45
 
46
  ### Training results
47
 
48
- | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
- |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
50
- | No log | 0.0351 | 2 | 0.4577 | 0.0305 | 0.4577 |
51
- | No log | 0.0702 | 4 | 0.2924 | 0.0268 | 0.2924 |
52
- | No log | 0.1053 | 6 | 0.6165 | 0.0339 | 0.6165 |
53
- | No log | 0.1404 | 8 | 1.1332 | 0.0071 | 1.1332 |
54
- | No log | 0.1754 | 10 | 1.0089 | 0.0084 | 1.0089 |
55
- | No log | 0.2105 | 12 | 0.6577 | 0.0383 | 0.6577 |
56
- | No log | 0.2456 | 14 | 0.3893 | 0.0245 | 0.3893 |
57
- | No log | 0.2807 | 16 | 0.2631 | 0.0199 | 0.2631 |
58
- | No log | 0.3158 | 18 | 0.2402 | 0.0199 | 0.2402 |
59
- | No log | 0.3509 | 20 | 0.2586 | 0.0199 | 0.2586 |
60
- | No log | 0.3860 | 22 | 0.3150 | 0.0288 | 0.3150 |
61
- | No log | 0.4211 | 24 | 0.4282 | 0.0399 | 0.4282 |
62
- | No log | 0.4561 | 26 | 0.4430 | 0.0382 | 0.4430 |
63
- | No log | 0.4912 | 28 | 0.4205 | 0.0399 | 0.4205 |
64
- | No log | 0.5263 | 30 | 0.3631 | 0.0433 | 0.3631 |
65
- | No log | 0.5614 | 32 | 0.3063 | 0.0507 | 0.3063 |
66
- | No log | 0.5965 | 34 | 0.3162 | 0.0488 | 0.3162 |
67
- | No log | 0.6316 | 36 | 0.3646 | 0.0451 | 0.3646 |
68
- | No log | 0.6667 | 38 | 0.3766 | 0.0433 | 0.3766 |
69
- | No log | 0.7018 | 40 | 0.3470 | 0.0469 | 0.3470 |
70
- | No log | 0.7368 | 42 | 0.3331 | 0.0436 | 0.3331 |
71
- | No log | 0.7719 | 44 | 0.3000 | 0.0495 | 0.3000 |
72
- | No log | 0.8070 | 46 | 0.2692 | 0.0439 | 0.2692 |
73
- | No log | 0.8421 | 48 | 0.2579 | 0.0381 | 0.2579 |
74
- | No log | 0.8772 | 50 | 0.2450 | 0.0401 | 0.2450 |
75
- | No log | 0.9123 | 52 | 0.2306 | 0.0339 | 0.2306 |
76
- | No log | 0.9474 | 54 | 0.2223 | 0.0339 | 0.2223 |
77
- | No log | 0.9825 | 56 | 0.2223 | 0.0339 | 0.2223 |
 
 
 
78
 
79
 
80
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_cross_relevance_task7_fold2
7
  results: []
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
+ # arabert_cross_relevance_task7_fold2
14
 
15
  This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.3216
18
+ - Qwk: 0.0122
19
+ - Mse: 0.3221
20
 
21
  ## Model description
22
 
 
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
+ |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
50
+ | No log | 0.0317 | 2 | 0.3702 | 0.0004 | 0.3710 |
51
+ | No log | 0.0635 | 4 | 0.6663 | 0.0876 | 0.6665 |
52
+ | No log | 0.0952 | 6 | 0.4892 | -0.0369 | 0.4902 |
53
+ | No log | 0.1270 | 8 | 0.3495 | 0.0201 | 0.3512 |
54
+ | No log | 0.1587 | 10 | 0.3025 | 0.0245 | 0.3043 |
55
+ | No log | 0.1905 | 12 | 0.2923 | 0.0122 | 0.2940 |
56
+ | No log | 0.2222 | 14 | 0.3016 | 0.0 | 0.3031 |
57
+ | No log | 0.2540 | 16 | 0.3279 | 0.0203 | 0.3288 |
58
+ | No log | 0.2857 | 18 | 0.3285 | 0.0080 | 0.3293 |
59
+ | No log | 0.3175 | 20 | 0.3021 | 0.0122 | 0.3033 |
60
+ | No log | 0.3492 | 22 | 0.3021 | 0.0 | 0.3033 |
61
+ | No log | 0.3810 | 24 | 0.3213 | -0.0005 | 0.3221 |
62
+ | No log | 0.4127 | 26 | 0.3319 | 0.0368 | 0.3326 |
63
+ | No log | 0.4444 | 28 | 0.3452 | 0.0619 | 0.3456 |
64
+ | No log | 0.4762 | 30 | 0.3248 | 0.0534 | 0.3253 |
65
+ | No log | 0.5079 | 32 | 0.3076 | 0.0080 | 0.3082 |
66
+ | No log | 0.5397 | 34 | 0.2862 | 0.0 | 0.2870 |
67
+ | No log | 0.5714 | 36 | 0.2769 | 0.0 | 0.2777 |
68
+ | No log | 0.6032 | 38 | 0.2750 | 0.0 | 0.2759 |
69
+ | No log | 0.6349 | 40 | 0.2747 | 0.0 | 0.2756 |
70
+ | No log | 0.6667 | 42 | 0.2748 | 0.0 | 0.2756 |
71
+ | No log | 0.6984 | 44 | 0.2760 | 0.0 | 0.2767 |
72
+ | No log | 0.7302 | 46 | 0.2797 | 0.0 | 0.2803 |
73
+ | No log | 0.7619 | 48 | 0.2898 | 0.0 | 0.2903 |
74
+ | No log | 0.7937 | 50 | 0.2997 | 0.0 | 0.3002 |
75
+ | No log | 0.8254 | 52 | 0.3072 | 0.0 | 0.3077 |
76
+ | No log | 0.8571 | 54 | 0.3115 | 0.0 | 0.3120 |
77
+ | No log | 0.8889 | 56 | 0.3144 | 0.0 | 0.3148 |
78
+ | No log | 0.9206 | 58 | 0.3154 | 0.0122 | 0.3159 |
79
+ | No log | 0.9524 | 60 | 0.3184 | 0.0122 | 0.3189 |
80
+ | No log | 0.9841 | 62 | 0.3216 | 0.0122 | 0.3221 |
81
 
82
 
83
  ### Framework versions