Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task5_fold0

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
bbf6eb1
·
verified ·
1 Parent(s): 849a8fe

End of training

Browse files
Files changed (1) hide show
  1. README.md +35 -41
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_task4_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_task4_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: 0.2493
18
- - Qwk: 0.1995
19
- - Mse: 0.2499
20
 
21
  ## Model description
22
 
@@ -45,42 +45,36 @@ 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 | 0.0290 | 2 | 0.9661 | 0.0008 | 0.9646 |
51
- | No log | 0.0580 | 4 | 0.3848 | 0.0771 | 0.3829 |
52
- | No log | 0.0870 | 6 | 0.4443 | 0.1500 | 0.4425 |
53
- | No log | 0.1159 | 8 | 0.4586 | 0.1517 | 0.4581 |
54
- | No log | 0.1449 | 10 | 0.3891 | 0.0979 | 0.3886 |
55
- | No log | 0.1739 | 12 | 0.3011 | 0.0429 | 0.3007 |
56
- | No log | 0.2029 | 14 | 0.2904 | 0.1022 | 0.2903 |
57
- | No log | 0.2319 | 16 | 0.2988 | 0.1568 | 0.2989 |
58
- | No log | 0.2609 | 18 | 0.2760 | 0.1568 | 0.2762 |
59
- | No log | 0.2899 | 20 | 0.2581 | 0.1568 | 0.2582 |
60
- | No log | 0.3188 | 22 | 0.2522 | 0.1638 | 0.2523 |
61
- | No log | 0.3478 | 24 | 0.2553 | 0.2163 | 0.2553 |
62
- | No log | 0.3768 | 26 | 0.2573 | 0.2041 | 0.2573 |
63
- | No log | 0.4058 | 28 | 0.2622 | 0.2357 | 0.2623 |
64
- | No log | 0.4348 | 30 | 0.2861 | 0.2386 | 0.2863 |
65
- | No log | 0.4638 | 32 | 0.2800 | 0.2300 | 0.2803 |
66
- | No log | 0.4928 | 34 | 0.2632 | 0.2282 | 0.2634 |
67
- | No log | 0.5217 | 36 | 0.2642 | 0.1801 | 0.2643 |
68
- | No log | 0.5507 | 38 | 0.2968 | 0.1910 | 0.2969 |
69
- | No log | 0.5797 | 40 | 0.2947 | 0.1983 | 0.2949 |
70
- | No log | 0.6087 | 42 | 0.2738 | 0.1325 | 0.2739 |
71
- | No log | 0.6377 | 44 | 0.2632 | 0.125 | 0.2633 |
72
- | No log | 0.6667 | 46 | 0.2553 | 0.1615 | 0.2555 |
73
- | No log | 0.6957 | 48 | 0.2539 | 0.1615 | 0.2542 |
74
- | No log | 0.7246 | 50 | 0.2544 | 0.1939 | 0.2548 |
75
- | No log | 0.7536 | 52 | 0.2528 | 0.1939 | 0.2532 |
76
- | No log | 0.7826 | 54 | 0.2520 | 0.1858 | 0.2525 |
77
- | No log | 0.8116 | 56 | 0.2532 | 0.1915 | 0.2537 |
78
- | No log | 0.8406 | 58 | 0.2528 | 0.1970 | 0.2533 |
79
- | No log | 0.8696 | 60 | 0.2505 | 0.1970 | 0.2510 |
80
- | No log | 0.8986 | 62 | 0.2494 | 0.1970 | 0.2499 |
81
- | No log | 0.9275 | 64 | 0.2492 | 0.1970 | 0.2497 |
82
- | No log | 0.9565 | 66 | 0.2493 | 0.2049 | 0.2498 |
83
- | No log | 0.9855 | 68 | 0.2493 | 0.1995 | 0.2499 |
84
 
85
 
86
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_cross_relevance_task5_fold0
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_fold0
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: 0.2821
18
+ - Qwk: 0.0624
19
+ - Mse: 0.2820
20
 
21
  ## Model description
22
 
 
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
+ |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
50
+ | No log | 0.0351 | 2 | 1.4820 | -0.0183 | 1.4821 |
51
+ | No log | 0.0702 | 4 | 0.6837 | 0.0391 | 0.6838 |
52
+ | No log | 0.1053 | 6 | 0.3465 | 0.0562 | 0.3463 |
53
+ | No log | 0.1404 | 8 | 0.4761 | -0.0323 | 0.4757 |
54
+ | No log | 0.1754 | 10 | 0.4401 | -0.0362 | 0.4394 |
55
+ | No log | 0.2105 | 12 | 0.3074 | -0.0097 | 0.3072 |
56
+ | No log | 0.2456 | 14 | 0.2597 | 0.0101 | 0.2597 |
57
+ | No log | 0.2807 | 16 | 0.2629 | -0.0073 | 0.2629 |
58
+ | No log | 0.3158 | 18 | 0.2753 | 0.0010 | 0.2751 |
59
+ | No log | 0.3509 | 20 | 0.2789 | 0.0091 | 0.2788 |
60
+ | No log | 0.3860 | 22 | 0.2807 | 0.0055 | 0.2806 |
61
+ | No log | 0.4211 | 24 | 0.2657 | 0.0245 | 0.2656 |
62
+ | No log | 0.4561 | 26 | 0.2518 | 0.0116 | 0.2517 |
63
+ | No log | 0.4912 | 28 | 0.2590 | 0.0323 | 0.2590 |
64
+ | No log | 0.5263 | 30 | 0.2649 | 0.0144 | 0.2648 |
65
+ | No log | 0.5614 | 32 | 0.2691 | 0.0036 | 0.2689 |
66
+ | No log | 0.5965 | 34 | 0.2672 | 0.0071 | 0.2671 |
67
+ | No log | 0.6316 | 36 | 0.2663 | 0.0356 | 0.2661 |
68
+ | No log | 0.6667 | 38 | 0.2656 | 0.0628 | 0.2655 |
69
+ | No log | 0.7018 | 40 | 0.2632 | 0.0478 | 0.2631 |
70
+ | No log | 0.7368 | 42 | 0.2641 | 0.0517 | 0.2640 |
71
+ | No log | 0.7719 | 44 | 0.2671 | 0.0414 | 0.2671 |
72
+ | No log | 0.8070 | 46 | 0.2735 | 0.0598 | 0.2735 |
73
+ | No log | 0.8421 | 48 | 0.2820 | 0.0558 | 0.2820 |
74
+ | No log | 0.8772 | 50 | 0.2862 | 0.0624 | 0.2861 |
75
+ | No log | 0.9123 | 52 | 0.2852 | 0.0624 | 0.2851 |
76
+ | No log | 0.9474 | 54 | 0.2831 | 0.0624 | 0.2831 |
77
+ | No log | 0.9825 | 56 | 0.2821 | 0.0624 | 0.2820 |
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions