salbatarni commited on
Commit
b862ae2
1 Parent(s): ae9d6b8

End of training

Browse files
Files changed (1) hide show
  1. README.md +37 -36
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_task1_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_task1_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: 0.3646
18
- - Qwk: 0.0454
19
- - Mse: 0.3647
20
 
21
  ## Model description
22
 
@@ -47,37 +47,38 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
50
- | No log | 0.0323 | 2 | 0.3884 | -0.0193 | 0.3901 |
51
- | No log | 0.0645 | 4 | 0.5676 | 0.0570 | 0.5677 |
52
- | No log | 0.0968 | 6 | 0.6160 | 0.1181 | 0.6161 |
53
- | No log | 0.1290 | 8 | 0.3914 | 0.0326 | 0.3913 |
54
- | No log | 0.1613 | 10 | 0.2970 | 0.0245 | 0.2972 |
55
- | No log | 0.1935 | 12 | 0.3016 | 0.0122 | 0.3018 |
56
- | No log | 0.2258 | 14 | 0.2905 | 0.0122 | 0.2908 |
57
- | No log | 0.2581 | 16 | 0.3013 | 0.0491 | 0.3016 |
58
- | No log | 0.2903 | 18 | 0.3427 | 0.0284 | 0.3429 |
59
- | No log | 0.3226 | 20 | 0.4170 | 0.0059 | 0.4170 |
60
- | No log | 0.3548 | 22 | 0.4971 | 0.0518 | 0.4971 |
61
- | No log | 0.3871 | 24 | 0.4934 | 0.0958 | 0.4933 |
62
- | No log | 0.4194 | 26 | 0.4203 | -0.0430 | 0.4203 |
63
- | No log | 0.4516 | 28 | 0.3668 | -0.0521 | 0.3669 |
64
- | No log | 0.4839 | 30 | 0.3462 | -0.0092 | 0.3463 |
65
- | No log | 0.5161 | 32 | 0.3500 | -0.0092 | 0.3500 |
66
- | No log | 0.5484 | 34 | 0.3623 | -0.0010 | 0.3623 |
67
- | No log | 0.5806 | 36 | 0.3911 | -0.0188 | 0.3911 |
68
- | No log | 0.6129 | 38 | 0.3635 | -0.0135 | 0.3634 |
69
- | No log | 0.6452 | 40 | 0.3500 | -0.0092 | 0.3500 |
70
- | No log | 0.6774 | 42 | 0.3369 | -0.0048 | 0.3369 |
71
- | No log | 0.7097 | 44 | 0.3357 | -0.0048 | 0.3358 |
72
- | No log | 0.7419 | 46 | 0.3574 | 0.0537 | 0.3574 |
73
- | No log | 0.7742 | 48 | 0.3901 | 0.0370 | 0.3901 |
74
- | No log | 0.8065 | 50 | 0.3986 | 0.0723 | 0.3985 |
75
- | No log | 0.8387 | 52 | 0.3875 | 0.0544 | 0.3875 |
76
- | No log | 0.8710 | 54 | 0.3792 | 0.0586 | 0.3792 |
77
- | No log | 0.9032 | 56 | 0.3727 | 0.0412 | 0.3727 |
78
- | No log | 0.9355 | 58 | 0.3667 | 0.0454 | 0.3667 |
79
- | No log | 0.9677 | 60 | 0.3648 | 0.0454 | 0.3648 |
80
- | No log | 1.0 | 62 | 0.3646 | 0.0454 | 0.3647 |
 
81
 
82
 
83
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_cross_relevance_task1_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_task1_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: 0.2831
18
+ - Qwk: 0.0
19
+ - Mse: 0.2831
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
50
+ | No log | 0.0308 | 2 | 1.7758 | 0.0 | 1.7758 |
51
+ | No log | 0.0615 | 4 | 0.4260 | 0.0230 | 0.4260 |
52
+ | No log | 0.0923 | 6 | 0.2683 | 0.0357 | 0.2683 |
53
+ | No log | 0.1231 | 8 | 0.4228 | 0.1279 | 0.4228 |
54
+ | No log | 0.1538 | 10 | 0.3603 | -0.0238 | 0.3603 |
55
+ | No log | 0.1846 | 12 | 0.2737 | 0.0 | 0.2737 |
56
+ | No log | 0.2154 | 14 | 0.2624 | 0.0 | 0.2624 |
57
+ | No log | 0.2462 | 16 | 0.2619 | 0.0 | 0.2619 |
58
+ | No log | 0.2769 | 18 | 0.2688 | 0.0 | 0.2688 |
59
+ | No log | 0.3077 | 20 | 0.2704 | 0.0 | 0.2704 |
60
+ | No log | 0.3385 | 22 | 0.2624 | 0.0 | 0.2624 |
61
+ | No log | 0.3692 | 24 | 0.2623 | 0.0 | 0.2623 |
62
+ | No log | 0.4 | 26 | 0.2679 | 0.0 | 0.2679 |
63
+ | No log | 0.4308 | 28 | 0.2721 | 0.0 | 0.2721 |
64
+ | No log | 0.4615 | 30 | 0.2703 | 0.0 | 0.2703 |
65
+ | No log | 0.4923 | 32 | 0.2734 | 0.0 | 0.2734 |
66
+ | No log | 0.5231 | 34 | 0.2751 | 0.0 | 0.2751 |
67
+ | No log | 0.5538 | 36 | 0.2768 | 0.0 | 0.2768 |
68
+ | No log | 0.5846 | 38 | 0.2791 | 0.0 | 0.2791 |
69
+ | No log | 0.6154 | 40 | 0.2794 | 0.0 | 0.2794 |
70
+ | No log | 0.6462 | 42 | 0.2773 | 0.0 | 0.2773 |
71
+ | No log | 0.6769 | 44 | 0.2716 | 0.0 | 0.2716 |
72
+ | No log | 0.7077 | 46 | 0.2703 | 0.0 | 0.2703 |
73
+ | No log | 0.7385 | 48 | 0.2738 | 0.0 | 0.2738 |
74
+ | No log | 0.7692 | 50 | 0.2740 | 0.0 | 0.2740 |
75
+ | No log | 0.8 | 52 | 0.2800 | 0.0 | 0.2800 |
76
+ | No log | 0.8308 | 54 | 0.2820 | 0.0 | 0.2820 |
77
+ | No log | 0.8615 | 56 | 0.2816 | 0.0 | 0.2816 |
78
+ | No log | 0.8923 | 58 | 0.2830 | 0.0 | 0.2830 |
79
+ | No log | 0.9231 | 60 | 0.2845 | 0.0 | 0.2845 |
80
+ | No log | 0.9538 | 62 | 0.2838 | 0.0 | 0.2838 |
81
+ | No log | 0.9846 | 64 | 0.2831 | 0.0 | 0.2831 |
82
 
83
 
84
  ### Framework versions