Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task2_fold6

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
10bd4fe
·
verified ·
1 Parent(s): e99d034

End of training

Browse files
Files changed (1) hide show
  1. README.md +35 -33
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_task2_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_task2_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: 0.2016
18
- - Qwk: 0.3467
19
- - Mse: 0.2016
20
 
21
  ## Model description
22
 
@@ -47,34 +47,36 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
50
- | No log | 0.0351 | 2 | 0.4956 | 0.1759 | 0.4956 |
51
- | No log | 0.0702 | 4 | 0.3937 | 0.2727 | 0.3937 |
52
- | No log | 0.1053 | 6 | 0.3006 | 0.3553 | 0.3006 |
53
- | No log | 0.1404 | 8 | 0.2240 | 0.3547 | 0.2240 |
54
- | No log | 0.1754 | 10 | 0.2449 | 0.3533 | 0.2449 |
55
- | No log | 0.2105 | 12 | 0.2074 | 0.3561 | 0.2074 |
56
- | No log | 0.2456 | 14 | 0.2202 | 0.3186 | 0.2202 |
57
- | No log | 0.2807 | 16 | 0.2130 | 0.3156 | 0.2130 |
58
- | No log | 0.3158 | 18 | 0.1954 | 0.3355 | 0.1954 |
59
- | No log | 0.3509 | 20 | 0.1862 | 0.3566 | 0.1862 |
60
- | No log | 0.3860 | 22 | 0.1952 | 0.3540 | 0.1952 |
61
- | No log | 0.4211 | 24 | 0.2114 | 0.3598 | 0.2114 |
62
- | No log | 0.4561 | 26 | 0.2080 | 0.3590 | 0.2080 |
63
- | No log | 0.4912 | 28 | 0.2035 | 0.3620 | 0.2035 |
64
- | No log | 0.5263 | 30 | 0.1922 | 0.3522 | 0.1922 |
65
- | No log | 0.5614 | 32 | 0.1859 | 0.3539 | 0.1859 |
66
- | No log | 0.5965 | 34 | 0.1885 | 0.3548 | 0.1885 |
67
- | No log | 0.6316 | 36 | 0.1940 | 0.3539 | 0.1940 |
68
- | No log | 0.6667 | 38 | 0.1965 | 0.3539 | 0.1965 |
69
- | No log | 0.7018 | 40 | 0.1998 | 0.3529 | 0.1998 |
70
- | No log | 0.7368 | 42 | 0.2035 | 0.3519 | 0.2035 |
71
- | No log | 0.7719 | 44 | 0.2046 | 0.3509 | 0.2046 |
72
- | No log | 0.8070 | 46 | 0.2050 | 0.3499 | 0.2050 |
73
- | No log | 0.8421 | 48 | 0.2060 | 0.3509 | 0.2060 |
74
- | No log | 0.8772 | 50 | 0.2059 | 0.3499 | 0.2059 |
75
- | No log | 0.9123 | 52 | 0.2044 | 0.3489 | 0.2044 |
76
- | No log | 0.9474 | 54 | 0.2026 | 0.3467 | 0.2026 |
77
- | No log | 0.9825 | 56 | 0.2016 | 0.3467 | 0.2016 |
 
 
78
 
79
 
80
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_cross_relevance_task2_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_task2_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: 0.3731
18
+ - Qwk: 0.2015
19
+ - Mse: 0.3740
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
50
+ | No log | 0.0328 | 2 | 0.3728 | 0.0488 | 0.3746 |
51
+ | No log | 0.0656 | 4 | 0.4013 | 0.2050 | 0.4011 |
52
+ | No log | 0.0984 | 6 | 0.3850 | 0.2744 | 0.3837 |
53
+ | No log | 0.1311 | 8 | 0.3889 | 0.1783 | 0.3869 |
54
+ | No log | 0.1639 | 10 | 0.4111 | 0.1429 | 0.4096 |
55
+ | No log | 0.1967 | 12 | 0.3212 | 0.2348 | 0.3207 |
56
+ | No log | 0.2295 | 14 | 0.2701 | 0.2399 | 0.2703 |
57
+ | No log | 0.2623 | 16 | 0.2550 | 0.2436 | 0.2551 |
58
+ | No log | 0.2951 | 18 | 0.2577 | 0.2547 | 0.2579 |
59
+ | No log | 0.3279 | 20 | 0.2669 | 0.2820 | 0.2671 |
60
+ | No log | 0.3607 | 22 | 0.2805 | 0.2755 | 0.2808 |
61
+ | No log | 0.3934 | 24 | 0.3053 | 0.2543 | 0.3054 |
62
+ | No log | 0.4262 | 26 | 0.3392 | 0.2263 | 0.3390 |
63
+ | No log | 0.4590 | 28 | 0.3752 | 0.2215 | 0.3749 |
64
+ | No log | 0.4918 | 30 | 0.3683 | 0.2299 | 0.3680 |
65
+ | No log | 0.5246 | 32 | 0.3274 | 0.2226 | 0.3272 |
66
+ | No log | 0.5574 | 34 | 0.2787 | 0.2170 | 0.2786 |
67
+ | No log | 0.5902 | 36 | 0.2643 | 0.2325 | 0.2643 |
68
+ | No log | 0.6230 | 38 | 0.2611 | 0.2393 | 0.2611 |
69
+ | No log | 0.6557 | 40 | 0.2645 | 0.2530 | 0.2648 |
70
+ | No log | 0.6885 | 42 | 0.2728 | 0.2412 | 0.2732 |
71
+ | No log | 0.7213 | 44 | 0.2938 | 0.2367 | 0.2944 |
72
+ | No log | 0.7541 | 46 | 0.3280 | 0.2350 | 0.3286 |
73
+ | No log | 0.7869 | 48 | 0.3701 | 0.2015 | 0.3708 |
74
+ | No log | 0.8197 | 50 | 0.4045 | 0.1860 | 0.4053 |
75
+ | No log | 0.8525 | 52 | 0.4285 | 0.1751 | 0.4293 |
76
+ | No log | 0.8852 | 54 | 0.4202 | 0.1751 | 0.4211 |
77
+ | No log | 0.9180 | 56 | 0.4025 | 0.1860 | 0.4034 |
78
+ | No log | 0.9508 | 58 | 0.3839 | 0.2015 | 0.3847 |
79
+ | No log | 0.9836 | 60 | 0.3731 | 0.2015 | 0.3740 |
80
 
81
 
82
  ### Framework versions