Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task4_fold3

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
9d690b9
·
verified ·
1 Parent(s): 0785a90

End of training

Browse files
Files changed (1) hide show
  1. README.md +39 -42
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_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_task4_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: 0.3180
18
- - Qwk: 0.0326
19
- - Mse: 0.3185
20
 
21
  ## Model description
22
 
@@ -45,43 +45,40 @@ 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 | 0.0282 | 2 | 1.0877 | 0.0128 | 1.0825 |
51
- | No log | 0.0563 | 4 | 0.3592 | 0.0193 | 0.3590 |
52
- | No log | 0.0845 | 6 | 0.7857 | 0.1272 | 0.7866 |
53
- | No log | 0.1127 | 8 | 0.7311 | 0.1074 | 0.7317 |
54
- | No log | 0.1408 | 10 | 0.7894 | 0.0481 | 0.7899 |
55
- | No log | 0.1690 | 12 | 0.4933 | 0.0795 | 0.4934 |
56
- | No log | 0.1972 | 14 | 0.3343 | 0.0080 | 0.3342 |
57
- | No log | 0.2254 | 16 | 0.3064 | -0.0042 | 0.3064 |
58
- | No log | 0.2535 | 18 | 0.3228 | 0.0080 | 0.3226 |
59
- | No log | 0.2817 | 20 | 0.3574 | 0.0161 | 0.3573 |
60
- | No log | 0.3099 | 22 | 0.4018 | -0.0279 | 0.4017 |
61
- | No log | 0.3380 | 24 | 0.4407 | 0.0417 | 0.4406 |
62
- | No log | 0.3662 | 26 | 0.4990 | 0.0670 | 0.4990 |
63
- | No log | 0.3944 | 28 | 0.5469 | 0.0627 | 0.5469 |
64
- | No log | 0.4225 | 30 | 0.5179 | -0.0116 | 0.5179 |
65
- | No log | 0.4507 | 32 | 0.4679 | 0.0325 | 0.4680 |
66
- | No log | 0.4789 | 34 | 0.4229 | 0.1633 | 0.4230 |
67
- | No log | 0.5070 | 36 | 0.3960 | 0.0899 | 0.3961 |
68
- | No log | 0.5352 | 38 | 0.3963 | 0.1033 | 0.3964 |
69
- | No log | 0.5634 | 40 | 0.3915 | 0.0940 | 0.3917 |
70
- | No log | 0.5915 | 42 | 0.4068 | 0.1085 | 0.4070 |
71
- | No log | 0.6197 | 44 | 0.4341 | 0.1456 | 0.4343 |
72
- | No log | 0.6479 | 46 | 0.4311 | 0.1358 | 0.4312 |
73
- | No log | 0.6761 | 48 | 0.4057 | 0.0940 | 0.4059 |
74
- | No log | 0.7042 | 50 | 0.3862 | 0.0197 | 0.3866 |
75
- | No log | 0.7324 | 52 | 0.3708 | -0.0016 | 0.3712 |
76
- | No log | 0.7606 | 54 | 0.3510 | 0.0028 | 0.3515 |
77
- | No log | 0.7887 | 56 | 0.3311 | 0.0826 | 0.3316 |
78
- | No log | 0.8169 | 58 | 0.3203 | 0.0326 | 0.3207 |
79
- | No log | 0.8451 | 60 | 0.3146 | 0.0203 | 0.3150 |
80
- | No log | 0.8732 | 62 | 0.3110 | 0.0368 | 0.3114 |
81
- | No log | 0.9014 | 64 | 0.3110 | 0.0368 | 0.3115 |
82
- | No log | 0.9296 | 66 | 0.3134 | 0.0203 | 0.3139 |
83
- | No log | 0.9577 | 68 | 0.3161 | 0.0326 | 0.3165 |
84
- | No log | 0.9859 | 70 | 0.3180 | 0.0326 | 0.3185 |
85
 
86
 
87
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_cross_relevance_task4_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_task4_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: 0.3149
18
+ - Qwk: 0.3219
19
+ - Mse: 0.3149
20
 
21
  ## Model description
22
 
 
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
+ |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
50
+ | No log | 0.0308 | 2 | 0.6456 | 0.1075 | 0.6456 |
51
+ | No log | 0.0615 | 4 | 0.4575 | 0.2193 | 0.4575 |
52
+ | No log | 0.0923 | 6 | 0.4674 | 0.2535 | 0.4674 |
53
+ | No log | 0.1231 | 8 | 0.5729 | 0.1524 | 0.5729 |
54
+ | No log | 0.1538 | 10 | 0.3886 | 0.2903 | 0.3886 |
55
+ | No log | 0.1846 | 12 | 0.4032 | 0.2047 | 0.4032 |
56
+ | No log | 0.2154 | 14 | 0.4025 | 0.1193 | 0.4025 |
57
+ | No log | 0.2462 | 16 | 0.3963 | 0.0956 | 0.3963 |
58
+ | No log | 0.2769 | 18 | 0.3978 | 0.1280 | 0.3978 |
59
+ | No log | 0.3077 | 20 | 0.3869 | 0.1979 | 0.3869 |
60
+ | No log | 0.3385 | 22 | 0.3693 | 0.2273 | 0.3693 |
61
+ | No log | 0.3692 | 24 | 0.3556 | 0.2505 | 0.3556 |
62
+ | No log | 0.4 | 26 | 0.3417 | 0.2365 | 0.3417 |
63
+ | No log | 0.4308 | 28 | 0.3385 | 0.2571 | 0.3385 |
64
+ | No log | 0.4615 | 30 | 0.3433 | 0.2434 | 0.3433 |
65
+ | No log | 0.4923 | 32 | 0.3471 | 0.2503 | 0.3471 |
66
+ | No log | 0.5231 | 34 | 0.3537 | 0.2776 | 0.3537 |
67
+ | No log | 0.5538 | 36 | 0.3590 | 0.2907 | 0.3590 |
68
+ | No log | 0.5846 | 38 | 0.3558 | 0.2586 | 0.3558 |
69
+ | No log | 0.6154 | 40 | 0.3484 | 0.2718 | 0.3484 |
70
+ | No log | 0.6462 | 42 | 0.3430 | 0.2811 | 0.3430 |
71
+ | No log | 0.6769 | 44 | 0.3356 | 0.2875 | 0.3356 |
72
+ | No log | 0.7077 | 46 | 0.3309 | 0.2875 | 0.3309 |
73
+ | No log | 0.7385 | 48 | 0.3268 | 0.2889 | 0.3268 |
74
+ | No log | 0.7692 | 50 | 0.3226 | 0.3165 | 0.3226 |
75
+ | No log | 0.8 | 52 | 0.3203 | 0.3229 | 0.3203 |
76
+ | No log | 0.8308 | 54 | 0.3180 | 0.3288 | 0.3180 |
77
+ | No log | 0.8615 | 56 | 0.3175 | 0.3279 | 0.3175 |
78
+ | No log | 0.8923 | 58 | 0.3168 | 0.3279 | 0.3168 |
79
+ | No log | 0.9231 | 60 | 0.3158 | 0.3219 | 0.3158 |
80
+ | No log | 0.9538 | 62 | 0.3151 | 0.3219 | 0.3151 |
81
+ | No log | 0.9846 | 64 | 0.3149 | 0.3219 | 0.3149 |
 
 
 
82
 
83
 
84
  ### Framework versions