salbatarni commited on
Commit
1622806
1 Parent(s): 8d2fdb7

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_task5_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_task5_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: 0.3506
18
- - Qwk: -0.0164
19
- - Mse: 0.3512
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 | 0.0317 | 2 | 0.4906 | -0.0037 | 0.4920 |
51
- | No log | 0.0635 | 4 | 0.3371 | -0.0172 | 0.3371 |
52
- | No log | 0.0952 | 6 | 0.3335 | -0.0128 | 0.3335 |
53
- | No log | 0.1270 | 8 | 0.2836 | 0.0122 | 0.2837 |
54
- | No log | 0.1587 | 10 | 0.3153 | 0.0 | 0.3156 |
55
- | No log | 0.1905 | 12 | 0.2834 | 0.0 | 0.2838 |
56
- | No log | 0.2222 | 14 | 0.2992 | 0.0 | 0.2996 |
57
- | No log | 0.2540 | 16 | 0.3898 | 0.0454 | 0.3898 |
58
- | No log | 0.2857 | 18 | 0.4736 | 0.0608 | 0.4735 |
59
- | No log | 0.3175 | 20 | 0.4950 | -0.0251 | 0.4949 |
60
- | No log | 0.3492 | 22 | 0.4696 | -0.0281 | 0.4697 |
61
- | No log | 0.3810 | 24 | 0.4030 | -0.0521 | 0.4033 |
62
- | No log | 0.4127 | 26 | 0.3436 | 0.0122 | 0.3443 |
63
- | No log | 0.4444 | 28 | 0.3297 | 0.0122 | 0.3305 |
64
- | No log | 0.4762 | 30 | 0.3336 | 0.0122 | 0.3344 |
65
- | No log | 0.5079 | 32 | 0.3536 | 0.0122 | 0.3541 |
66
- | No log | 0.5397 | 34 | 0.3706 | -0.0042 | 0.3710 |
67
- | No log | 0.5714 | 36 | 0.3495 | 0.0 | 0.3500 |
68
- | No log | 0.6032 | 38 | 0.3317 | 0.0 | 0.3323 |
69
- | No log | 0.6349 | 40 | 0.3188 | 0.0 | 0.3196 |
70
- | No log | 0.6667 | 42 | 0.3182 | 0.0 | 0.3190 |
71
- | No log | 0.6984 | 44 | 0.3248 | 0.0 | 0.3256 |
72
- | No log | 0.7302 | 46 | 0.3286 | 0.0 | 0.3294 |
73
- | No log | 0.7619 | 48 | 0.3328 | -0.0164 | 0.3336 |
74
- | No log | 0.7937 | 50 | 0.3347 | -0.0164 | 0.3354 |
75
- | No log | 0.8254 | 52 | 0.3404 | -0.0164 | 0.3411 |
76
- | No log | 0.8571 | 54 | 0.3437 | -0.0164 | 0.3444 |
77
- | No log | 0.8889 | 56 | 0.3441 | -0.0164 | 0.3448 |
78
- | No log | 0.9206 | 58 | 0.3444 | -0.0164 | 0.3450 |
79
- | No log | 0.9524 | 60 | 0.3482 | -0.0164 | 0.3488 |
80
- | No log | 0.9841 | 62 | 0.3506 | -0.0164 | 0.3512 |
 
81
 
82
 
83
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_cross_relevance_task5_fold3
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_fold3
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: 0.2615
18
+ - Qwk: 0.0
19
+ - Mse: 0.2615
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
50
+ | No log | 0.0308 | 2 | 1.7894 | 0.0 | 1.7894 |
51
+ | No log | 0.0615 | 4 | 0.5746 | 0.0241 | 0.5746 |
52
+ | No log | 0.0923 | 6 | 0.2626 | 0.0101 | 0.2626 |
53
+ | No log | 0.1231 | 8 | 0.3467 | 0.0842 | 0.3467 |
54
+ | No log | 0.1538 | 10 | 0.3204 | -0.0484 | 0.3204 |
55
+ | No log | 0.1846 | 12 | 0.2946 | 0.0278 | 0.2946 |
56
+ | No log | 0.2154 | 14 | 0.3020 | 0.0 | 0.3020 |
57
+ | No log | 0.2462 | 16 | 0.3536 | 0.0 | 0.3536 |
58
+ | No log | 0.2769 | 18 | 0.3417 | 0.0 | 0.3417 |
59
+ | No log | 0.3077 | 20 | 0.3100 | 0.0 | 0.3100 |
60
+ | No log | 0.3385 | 22 | 0.3160 | 0.0 | 0.3160 |
61
+ | No log | 0.3692 | 24 | 0.3028 | 0.0 | 0.3028 |
62
+ | No log | 0.4 | 26 | 0.2898 | 0.0 | 0.2898 |
63
+ | No log | 0.4308 | 28 | 0.2803 | 0.0 | 0.2803 |
64
+ | No log | 0.4615 | 30 | 0.2760 | 0.0 | 0.2760 |
65
+ | No log | 0.4923 | 32 | 0.2736 | 0.0 | 0.2736 |
66
+ | No log | 0.5231 | 34 | 0.2752 | 0.0101 | 0.2752 |
67
+ | No log | 0.5538 | 36 | 0.2821 | -0.0069 | 0.2821 |
68
+ | No log | 0.5846 | 38 | 0.2933 | 0.0217 | 0.2933 |
69
+ | No log | 0.6154 | 40 | 0.2959 | 0.0672 | 0.2959 |
70
+ | No log | 0.6462 | 42 | 0.2871 | -0.0106 | 0.2871 |
71
+ | No log | 0.6769 | 44 | 0.2960 | 0.0267 | 0.2960 |
72
+ | No log | 0.7077 | 46 | 0.2930 | 0.0185 | 0.2930 |
73
+ | No log | 0.7385 | 48 | 0.2791 | 0.0035 | 0.2791 |
74
+ | No log | 0.7692 | 50 | 0.2677 | 0.0 | 0.2677 |
75
+ | No log | 0.8 | 52 | 0.2641 | 0.0 | 0.2641 |
76
+ | No log | 0.8308 | 54 | 0.2641 | 0.0 | 0.2641 |
77
+ | No log | 0.8615 | 56 | 0.2630 | 0.0 | 0.2630 |
78
+ | No log | 0.8923 | 58 | 0.2625 | 0.0 | 0.2625 |
79
+ | No log | 0.9231 | 60 | 0.2620 | 0.0 | 0.2620 |
80
+ | No log | 0.9538 | 62 | 0.2617 | 0.0 | 0.2617 |
81
+ | No log | 0.9846 | 64 | 0.2615 | 0.0 | 0.2615 |
82
 
83
 
84
  ### Framework versions