Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task3_fold6

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
1c0aeca
·
verified ·
1 Parent(s): 0ae0fe5

End of training

Browse files
Files changed (1) hide show
  1. README.md +38 -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_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_task3_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: 0.1927
18
- - Qwk: 0.3583
19
- - Mse: 0.1927
20
 
21
  ## Model description
22
 
@@ -47,37 +47,39 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
50
- | No log | 0.0317 | 2 | 0.7649 | 0.0249 | 0.7649 |
51
- | No log | 0.0635 | 4 | 0.4874 | 0.1486 | 0.4874 |
52
- | No log | 0.0952 | 6 | 0.3246 | 0.3768 | 0.3246 |
53
- | No log | 0.1270 | 8 | 0.4428 | 0.4187 | 0.4428 |
54
- | No log | 0.1587 | 10 | 0.3587 | 0.2702 | 0.3587 |
55
- | No log | 0.1905 | 12 | 0.2865 | 0.2527 | 0.2865 |
56
- | No log | 0.2222 | 14 | 0.2562 | 0.2830 | 0.2562 |
57
- | No log | 0.2540 | 16 | 0.2311 | 0.2998 | 0.2311 |
58
- | No log | 0.2857 | 18 | 0.2125 | 0.3152 | 0.2125 |
59
- | No log | 0.3175 | 20 | 0.2154 | 0.3860 | 0.2154 |
60
- | No log | 0.3492 | 22 | 0.2502 | 0.5544 | 0.2502 |
61
- | No log | 0.3810 | 24 | 0.2642 | 0.6590 | 0.2642 |
62
- | No log | 0.4127 | 26 | 0.2431 | 0.6239 | 0.2431 |
63
- | No log | 0.4444 | 28 | 0.2115 | 0.4874 | 0.2115 |
64
- | No log | 0.4762 | 30 | 0.1950 | 0.4156 | 0.1950 |
65
- | No log | 0.5079 | 32 | 0.1937 | 0.3883 | 0.1937 |
66
- | No log | 0.5397 | 34 | 0.1952 | 0.3613 | 0.1952 |
67
- | No log | 0.5714 | 36 | 0.1955 | 0.3557 | 0.1955 |
68
- | No log | 0.6032 | 38 | 0.1939 | 0.3547 | 0.1939 |
69
- | No log | 0.6349 | 40 | 0.1915 | 0.3536 | 0.1915 |
70
- | No log | 0.6667 | 42 | 0.1923 | 0.3536 | 0.1923 |
71
- | No log | 0.6984 | 44 | 0.1919 | 0.3490 | 0.1919 |
72
- | No log | 0.7302 | 46 | 0.1928 | 0.3490 | 0.1928 |
73
- | No log | 0.7619 | 48 | 0.1923 | 0.3490 | 0.1923 |
74
- | No log | 0.7937 | 50 | 0.1945 | 0.3468 | 0.1945 |
75
- | No log | 0.8254 | 52 | 0.1988 | 0.3305 | 0.1988 |
76
- | No log | 0.8571 | 54 | 0.2000 | 0.3305 | 0.2000 |
77
- | No log | 0.8889 | 56 | 0.1995 | 0.3363 | 0.1995 |
78
- | No log | 0.9206 | 58 | 0.1967 | 0.3363 | 0.1967 |
79
- | No log | 0.9524 | 60 | 0.1943 | 0.3408 | 0.1943 |
80
- | No log | 0.9841 | 62 | 0.1927 | 0.3583 | 0.1927 |
 
 
81
 
82
 
83
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_cross_relevance_task3_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_task3_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: 0.3083
18
+ - Qwk: 0.2354
19
+ - Mse: 0.3090
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
50
+ | No log | 0.0299 | 2 | 1.6498 | 0.0 | 1.6481 |
51
+ | No log | 0.0597 | 4 | 0.5644 | 0.1146 | 0.5641 |
52
+ | No log | 0.0896 | 6 | 0.2749 | 0.1588 | 0.2742 |
53
+ | No log | 0.1194 | 8 | 0.3064 | 0.1012 | 0.3054 |
54
+ | No log | 0.1493 | 10 | 0.2890 | 0.1187 | 0.2882 |
55
+ | No log | 0.1791 | 12 | 0.2842 | 0.2003 | 0.2837 |
56
+ | No log | 0.2090 | 14 | 0.3266 | 0.2050 | 0.3261 |
57
+ | No log | 0.2388 | 16 | 0.3931 | 0.1809 | 0.3897 |
58
+ | No log | 0.2687 | 18 | 0.3763 | 0.1896 | 0.3731 |
59
+ | No log | 0.2985 | 20 | 0.3147 | 0.2173 | 0.3125 |
60
+ | No log | 0.3284 | 22 | 0.3526 | 0.2076 | 0.3492 |
61
+ | No log | 0.3582 | 24 | 0.3678 | 0.2313 | 0.3642 |
62
+ | No log | 0.3881 | 26 | 0.3518 | 0.3051 | 0.3497 |
63
+ | No log | 0.4179 | 28 | 0.3659 | 0.2615 | 0.3636 |
64
+ | No log | 0.4478 | 30 | 0.3513 | 0.2287 | 0.3494 |
65
+ | No log | 0.4776 | 32 | 0.3355 | 0.2393 | 0.3340 |
66
+ | No log | 0.5075 | 34 | 0.3257 | 0.2449 | 0.3250 |
67
+ | No log | 0.5373 | 36 | 0.3077 | 0.2412 | 0.3076 |
68
+ | No log | 0.5672 | 38 | 0.3002 | 0.2291 | 0.3005 |
69
+ | No log | 0.5970 | 40 | 0.3033 | 0.2330 | 0.3037 |
70
+ | No log | 0.6269 | 42 | 0.3014 | 0.2330 | 0.3019 |
71
+ | No log | 0.6567 | 44 | 0.3067 | 0.2330 | 0.3072 |
72
+ | No log | 0.6866 | 46 | 0.3179 | 0.2330 | 0.3186 |
73
+ | No log | 0.7164 | 48 | 0.3217 | 0.2392 | 0.3224 |
74
+ | No log | 0.7463 | 50 | 0.3119 | 0.2543 | 0.3125 |
75
+ | No log | 0.7761 | 52 | 0.3115 | 0.2543 | 0.3122 |
76
+ | No log | 0.8060 | 54 | 0.3159 | 0.2385 | 0.3166 |
77
+ | No log | 0.8358 | 56 | 0.3075 | 0.2480 | 0.3081 |
78
+ | No log | 0.8657 | 58 | 0.3073 | 0.2354 | 0.3079 |
79
+ | No log | 0.8955 | 60 | 0.3057 | 0.2354 | 0.3064 |
80
+ | No log | 0.9254 | 62 | 0.3067 | 0.2354 | 0.3073 |
81
+ | No log | 0.9552 | 64 | 0.3081 | 0.2354 | 0.3088 |
82
+ | No log | 0.9851 | 66 | 0.3083 | 0.2354 | 0.3090 |
83
 
84
 
85
  ### Framework versions