Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task3_fold2

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
0dd7e2e
·
verified ·
1 Parent(s): fc4d640

End of training

Browse files
Files changed (1) hide show
  1. README.md +40 -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_task3_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_task3_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: 0.1822
18
- - Qwk: 0.0339
19
- - Mse: 0.1822
20
 
21
  ## Model description
22
 
@@ -47,37 +47,41 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
50
- | No log | 0.0317 | 2 | 2.4542 | 0.0 | 2.4542 |
51
- | No log | 0.0635 | 4 | 0.8783 | -0.0066 | 0.8783 |
52
- | No log | 0.0952 | 6 | 0.2377 | 0.0273 | 0.2377 |
53
- | No log | 0.1270 | 8 | 0.1469 | 0.0309 | 0.1469 |
54
- | No log | 0.1587 | 10 | 0.1407 | 0.0525 | 0.1407 |
55
- | No log | 0.1905 | 12 | 0.1587 | 0.0324 | 0.1587 |
56
- | No log | 0.2222 | 14 | 0.2430 | 0.0281 | 0.2430 |
57
- | No log | 0.2540 | 16 | 0.2746 | 0.0263 | 0.2746 |
58
- | No log | 0.2857 | 18 | 0.2674 | 0.0323 | 0.2674 |
59
- | No log | 0.3175 | 20 | 0.2025 | 0.0210 | 0.2025 |
60
- | No log | 0.3492 | 22 | 0.1672 | 0.0255 | 0.1672 |
61
- | No log | 0.3810 | 24 | 0.1603 | 0.0338 | 0.1603 |
62
- | No log | 0.4127 | 26 | 0.1690 | 0.0231 | 0.1690 |
63
- | No log | 0.4444 | 28 | 0.2034 | 0.0317 | 0.2034 |
64
- | No log | 0.4762 | 30 | 0.2417 | 0.0355 | 0.2417 |
65
- | No log | 0.5079 | 32 | 0.2238 | 0.0197 | 0.2238 |
66
- | No log | 0.5397 | 34 | 0.1733 | 0.0305 | 0.1733 |
67
- | No log | 0.5714 | 36 | 0.1577 | 0.0886 | 0.1577 |
68
- | No log | 0.6032 | 38 | 0.1991 | 0.0336 | 0.1991 |
69
- | No log | 0.6349 | 40 | 0.3197 | 0.0475 | 0.3197 |
70
- | No log | 0.6667 | 42 | 0.3799 | 0.0485 | 0.3799 |
71
- | No log | 0.6984 | 44 | 0.3225 | 0.0443 | 0.3225 |
72
- | No log | 0.7302 | 46 | 0.2743 | 0.0408 | 0.2743 |
73
- | No log | 0.7619 | 48 | 0.2547 | 0.0320 | 0.2547 |
74
- | No log | 0.7937 | 50 | 0.2281 | 0.0278 | 0.2281 |
75
- | No log | 0.8254 | 52 | 0.2172 | 0.0300 | 0.2172 |
76
- | No log | 0.8571 | 54 | 0.2071 | 0.0339 | 0.2071 |
77
- | No log | 0.8889 | 56 | 0.1969 | 0.0339 | 0.1969 |
78
- | No log | 0.9206 | 58 | 0.1881 | 0.0339 | 0.1881 |
79
- | No log | 0.9524 | 60 | 0.1839 | 0.0339 | 0.1839 |
80
- | No log | 0.9841 | 62 | 0.1822 | 0.0339 | 0.1822 |
 
 
 
 
81
 
82
 
83
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_cross_relevance_task3_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_task3_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: 0.2924
18
+ - Qwk: 0.0385
19
+ - Mse: 0.2924
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
50
+ | No log | 0.0282 | 2 | 1.9951 | 0.0 | 1.9951 |
51
+ | No log | 0.0563 | 4 | 0.8321 | -0.0021 | 0.8321 |
52
+ | No log | 0.0845 | 6 | 0.2802 | 0.0 | 0.2802 |
53
+ | No log | 0.1127 | 8 | 0.4458 | 0.0625 | 0.4458 |
54
+ | No log | 0.1408 | 10 | 0.4881 | 0.2089 | 0.4881 |
55
+ | No log | 0.1690 | 12 | 0.3011 | -0.0156 | 0.3011 |
56
+ | No log | 0.1972 | 14 | 0.2760 | 0.0 | 0.2760 |
57
+ | No log | 0.2254 | 16 | 0.2997 | 0.0 | 0.2997 |
58
+ | No log | 0.2535 | 18 | 0.2559 | 0.0 | 0.2559 |
59
+ | No log | 0.2817 | 20 | 0.2551 | 0.0 | 0.2551 |
60
+ | No log | 0.3099 | 22 | 0.2568 | 0.0101 | 0.2568 |
61
+ | No log | 0.3380 | 24 | 0.2555 | 0.0 | 0.2555 |
62
+ | No log | 0.3662 | 26 | 0.2788 | 0.0068 | 0.2788 |
63
+ | No log | 0.3944 | 28 | 0.3484 | 0.1190 | 0.3484 |
64
+ | No log | 0.4225 | 30 | 0.4157 | 0.1667 | 0.4157 |
65
+ | No log | 0.4507 | 32 | 0.4046 | 0.0517 | 0.4046 |
66
+ | No log | 0.4789 | 34 | 0.3355 | -0.0833 | 0.3355 |
67
+ | No log | 0.5070 | 36 | 0.3106 | 0.0299 | 0.3106 |
68
+ | No log | 0.5352 | 38 | 0.3088 | -0.0401 | 0.3088 |
69
+ | No log | 0.5634 | 40 | 0.3026 | -0.0069 | 0.3026 |
70
+ | No log | 0.5915 | 42 | 0.2826 | 0.0517 | 0.2826 |
71
+ | No log | 0.6197 | 44 | 0.2644 | 0.0306 | 0.2644 |
72
+ | No log | 0.6479 | 46 | 0.2643 | 0.0306 | 0.2643 |
73
+ | No log | 0.6761 | 48 | 0.2781 | 0.0411 | 0.2781 |
74
+ | No log | 0.7042 | 50 | 0.2873 | 0.0625 | 0.2873 |
75
+ | No log | 0.7324 | 52 | 0.3190 | -0.0039 | 0.3190 |
76
+ | No log | 0.7606 | 54 | 0.3488 | -0.0096 | 0.3488 |
77
+ | No log | 0.7887 | 56 | 0.3736 | 0.1316 | 0.3736 |
78
+ | No log | 0.8169 | 58 | 0.3688 | 0.1146 | 0.3688 |
79
+ | No log | 0.8451 | 60 | 0.3437 | 0.0238 | 0.3437 |
80
+ | No log | 0.8732 | 62 | 0.3162 | 0.0504 | 0.3162 |
81
+ | No log | 0.9014 | 64 | 0.3006 | 0.0328 | 0.3006 |
82
+ | No log | 0.9296 | 66 | 0.2955 | 0.0248 | 0.2955 |
83
+ | No log | 0.9577 | 68 | 0.2926 | 0.0385 | 0.2926 |
84
+ | No log | 0.9859 | 70 | 0.2924 | 0.0385 | 0.2924 |
85
 
86
 
87
  ### Framework versions