Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task5_fold6

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
595ccda
·
verified ·
1 Parent(s): ce7147d

End of training

Browse files
Files changed (1) hide show
  1. README.md +37 -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_task5_fold5
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_task5_fold5
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: 0.1850
18
- - Qwk: 0.3218
19
- - Mse: 0.1850
20
 
21
  ## Model description
22
 
@@ -45,36 +45,38 @@ 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 | 1.6212 | -0.0017 | 1.6212 |
51
- | No log | 0.0702 | 4 | 0.4152 | 0.2892 | 0.4152 |
52
- | No log | 0.1053 | 6 | 0.1954 | 0.3371 | 0.1954 |
53
- | No log | 0.1404 | 8 | 0.2169 | 0.4091 | 0.2169 |
54
- | No log | 0.1754 | 10 | 0.2187 | 0.3071 | 0.2187 |
55
- | No log | 0.2105 | 12 | 0.2265 | 0.2875 | 0.2265 |
56
- | No log | 0.2456 | 14 | 0.2225 | 0.2856 | 0.2225 |
57
- | No log | 0.2807 | 16 | 0.2416 | 0.3293 | 0.2416 |
58
- | No log | 0.3158 | 18 | 0.2697 | 0.3623 | 0.2697 |
59
- | No log | 0.3509 | 20 | 0.2766 | 0.4106 | 0.2766 |
60
- | No log | 0.3860 | 22 | 0.2544 | 0.3125 | 0.2544 |
61
- | No log | 0.4211 | 24 | 0.2299 | 0.2434 | 0.2299 |
62
- | No log | 0.4561 | 26 | 0.2323 | 0.2606 | 0.2323 |
63
- | No log | 0.4912 | 28 | 0.2251 | 0.2770 | 0.2251 |
64
- | No log | 0.5263 | 30 | 0.2138 | 0.2909 | 0.2138 |
65
- | No log | 0.5614 | 32 | 0.2087 | 0.2728 | 0.2087 |
66
- | No log | 0.5965 | 34 | 0.2066 | 0.2882 | 0.2066 |
67
- | No log | 0.6316 | 36 | 0.2076 | 0.2882 | 0.2076 |
68
- | No log | 0.6667 | 38 | 0.2082 | 0.2862 | 0.2082 |
69
- | No log | 0.7018 | 40 | 0.2020 | 0.3073 | 0.2020 |
70
- | No log | 0.7368 | 42 | 0.1955 | 0.3089 | 0.1955 |
71
- | No log | 0.7719 | 44 | 0.1896 | 0.3089 | 0.1896 |
72
- | No log | 0.8070 | 46 | 0.1882 | 0.3218 | 0.1882 |
73
- | No log | 0.8421 | 48 | 0.1872 | 0.3218 | 0.1872 |
74
- | No log | 0.8772 | 50 | 0.1871 | 0.3218 | 0.1871 |
75
- | No log | 0.9123 | 52 | 0.1869 | 0.3218 | 0.1869 |
76
- | No log | 0.9474 | 54 | 0.1858 | 0.3218 | 0.1858 |
77
- | No log | 0.9825 | 56 | 0.1850 | 0.3218 | 0.1850 |
 
 
78
 
79
 
80
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_cross_relevance_task5_fold6
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_task5_fold6
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: 0.2705
18
+ - Qwk: 0.2603
19
+ - Mse: 0.2706
20
 
21
  ## Model description
22
 
 
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
+ |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
50
+ | No log | 0.0328 | 2 | 0.3383 | 0.0864 | 0.3385 |
51
+ | No log | 0.0656 | 4 | 0.3773 | 0.1304 | 0.3766 |
52
+ | No log | 0.0984 | 6 | 0.3324 | 0.0694 | 0.3308 |
53
+ | No log | 0.1311 | 8 | 0.3651 | 0.0942 | 0.3628 |
54
+ | No log | 0.1639 | 10 | 0.3821 | 0.1263 | 0.3813 |
55
+ | No log | 0.1967 | 12 | 0.3185 | 0.0967 | 0.3188 |
56
+ | No log | 0.2295 | 14 | 0.2905 | 0.0703 | 0.2911 |
57
+ | No log | 0.2623 | 16 | 0.3264 | 0.1381 | 0.3268 |
58
+ | No log | 0.2951 | 18 | 0.3480 | 0.1648 | 0.3482 |
59
+ | No log | 0.3279 | 20 | 0.3180 | 0.1381 | 0.3179 |
60
+ | No log | 0.3607 | 22 | 0.2907 | 0.0805 | 0.2904 |
61
+ | No log | 0.3934 | 24 | 0.2784 | 0.1094 | 0.2782 |
62
+ | No log | 0.4262 | 26 | 0.2763 | 0.1269 | 0.2762 |
63
+ | No log | 0.4590 | 28 | 0.2755 | 0.1455 | 0.2754 |
64
+ | No log | 0.4918 | 30 | 0.2737 | 0.2205 | 0.2737 |
65
+ | No log | 0.5246 | 32 | 0.2694 | 0.2104 | 0.2693 |
66
+ | No log | 0.5574 | 34 | 0.2712 | 0.2889 | 0.2712 |
67
+ | No log | 0.5902 | 36 | 0.2740 | 0.3051 | 0.2740 |
68
+ | No log | 0.6230 | 38 | 0.2751 | 0.2701 | 0.2752 |
69
+ | No log | 0.6557 | 40 | 0.2787 | 0.2819 | 0.2787 |
70
+ | No log | 0.6885 | 42 | 0.2795 | 0.2894 | 0.2795 |
71
+ | No log | 0.7213 | 44 | 0.2781 | 0.2856 | 0.2782 |
72
+ | No log | 0.7541 | 46 | 0.2805 | 0.2927 | 0.2806 |
73
+ | No log | 0.7869 | 48 | 0.2799 | 0.2927 | 0.2799 |
74
+ | No log | 0.8197 | 50 | 0.2752 | 0.2855 | 0.2752 |
75
+ | No log | 0.8525 | 52 | 0.2736 | 0.2642 | 0.2737 |
76
+ | No log | 0.8852 | 54 | 0.2719 | 0.2642 | 0.2720 |
77
+ | No log | 0.9180 | 56 | 0.2712 | 0.2642 | 0.2713 |
78
+ | No log | 0.9508 | 58 | 0.2711 | 0.2642 | 0.2711 |
79
+ | No log | 0.9836 | 60 | 0.2705 | 0.2603 | 0.2706 |
80
 
81
 
82
  ### Framework versions