Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task3_fold1

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
c3d12dc
·
verified ·
1 Parent(s): e08175f

End of training

Browse files
Files changed (1) hide show
  1. README.md +87 -87
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_fold0
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_fold0
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: 0.2395
18
- - Qwk: 0.2008
19
- - Mse: 0.2396
20
 
21
  ## Model description
22
 
@@ -45,88 +45,88 @@ 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 | 0.125 | 2 | 0.6036 | 0.0322 | 0.6039 |
51
- | No log | 0.25 | 4 | 0.2956 | 0.1240 | 0.2957 |
52
- | No log | 0.375 | 6 | 0.2567 | 0.1067 | 0.2568 |
53
- | No log | 0.5 | 8 | 0.2551 | 0.0962 | 0.2553 |
54
- | No log | 0.625 | 10 | 0.2302 | 0.0791 | 0.2304 |
55
- | No log | 0.75 | 12 | 0.2219 | 0.1048 | 0.2221 |
56
- | No log | 0.875 | 14 | 0.2288 | 0.1179 | 0.2291 |
57
- | No log | 1.0 | 16 | 0.2285 | 0.1629 | 0.2287 |
58
- | No log | 1.125 | 18 | 0.2532 | 0.2761 | 0.2534 |
59
- | No log | 1.25 | 20 | 0.2397 | 0.2284 | 0.2399 |
60
- | No log | 1.375 | 22 | 0.2317 | 0.1215 | 0.2320 |
61
- | No log | 1.5 | 24 | 0.2340 | 0.1485 | 0.2342 |
62
- | No log | 1.625 | 26 | 0.2412 | 0.2448 | 0.2414 |
63
- | No log | 1.75 | 28 | 0.2819 | 0.2575 | 0.2820 |
64
- | No log | 1.875 | 30 | 0.2502 | 0.2245 | 0.2503 |
65
- | No log | 2.0 | 32 | 0.2449 | 0.2115 | 0.2452 |
66
- | No log | 2.125 | 34 | 0.2459 | 0.2412 | 0.2461 |
67
- | No log | 2.25 | 36 | 0.2526 | 0.2570 | 0.2528 |
68
- | No log | 2.375 | 38 | 0.2460 | 0.2406 | 0.2462 |
69
- | No log | 2.5 | 40 | 0.2535 | 0.2576 | 0.2536 |
70
- | No log | 2.625 | 42 | 0.2448 | 0.1981 | 0.2449 |
71
- | No log | 2.75 | 44 | 0.2294 | 0.2076 | 0.2296 |
72
- | No log | 2.875 | 46 | 0.2305 | 0.2211 | 0.2306 |
73
- | No log | 3.0 | 48 | 0.2436 | 0.3108 | 0.2438 |
74
- | No log | 3.125 | 50 | 0.2515 | 0.2985 | 0.2516 |
75
- | No log | 3.25 | 52 | 0.2389 | 0.2228 | 0.2391 |
76
- | No log | 3.375 | 54 | 0.2444 | 0.2286 | 0.2445 |
77
- | No log | 3.5 | 56 | 0.2431 | 0.1981 | 0.2433 |
78
- | No log | 3.625 | 58 | 0.2417 | 0.1722 | 0.2418 |
79
- | No log | 3.75 | 60 | 0.2397 | 0.1740 | 0.2398 |
80
- | No log | 3.875 | 62 | 0.2456 | 0.1383 | 0.2457 |
81
- | No log | 4.0 | 64 | 0.2512 | 0.1025 | 0.2513 |
82
- | No log | 4.125 | 66 | 0.2350 | 0.1347 | 0.2351 |
83
- | No log | 4.25 | 68 | 0.2301 | 0.2110 | 0.2302 |
84
- | No log | 4.375 | 70 | 0.2327 | 0.2653 | 0.2328 |
85
- | No log | 4.5 | 72 | 0.2250 | 0.2641 | 0.2252 |
86
- | No log | 4.625 | 74 | 0.2301 | 0.2694 | 0.2303 |
87
- | No log | 4.75 | 76 | 0.2409 | 0.3036 | 0.2411 |
88
- | No log | 4.875 | 78 | 0.2453 | 0.2611 | 0.2454 |
89
- | No log | 5.0 | 80 | 0.2448 | 0.2241 | 0.2450 |
90
- | No log | 5.125 | 82 | 0.2464 | 0.1904 | 0.2466 |
91
- | No log | 5.25 | 84 | 0.2462 | 0.1493 | 0.2465 |
92
- | No log | 5.375 | 86 | 0.2336 | 0.1137 | 0.2338 |
93
- | No log | 5.5 | 88 | 0.2304 | 0.1648 | 0.2306 |
94
- | No log | 5.625 | 90 | 0.2297 | 0.1804 | 0.2298 |
95
- | No log | 5.75 | 92 | 0.2240 | 0.1481 | 0.2242 |
96
- | No log | 5.875 | 94 | 0.2360 | 0.1350 | 0.2362 |
97
- | No log | 6.0 | 96 | 0.2435 | 0.1401 | 0.2438 |
98
- | No log | 6.125 | 98 | 0.2332 | 0.1773 | 0.2334 |
99
- | No log | 6.25 | 100 | 0.2361 | 0.1842 | 0.2363 |
100
- | No log | 6.375 | 102 | 0.2427 | 0.1902 | 0.2429 |
101
- | No log | 6.5 | 104 | 0.2452 | 0.2024 | 0.2454 |
102
- | No log | 6.625 | 106 | 0.2452 | 0.1985 | 0.2454 |
103
- | No log | 6.75 | 108 | 0.2439 | 0.2049 | 0.2441 |
104
- | No log | 6.875 | 110 | 0.2397 | 0.2015 | 0.2399 |
105
- | No log | 7.0 | 112 | 0.2346 | 0.2150 | 0.2347 |
106
- | No log | 7.125 | 114 | 0.2303 | 0.2182 | 0.2304 |
107
- | No log | 7.25 | 116 | 0.2253 | 0.2061 | 0.2254 |
108
- | No log | 7.375 | 118 | 0.2231 | 0.2023 | 0.2232 |
109
- | No log | 7.5 | 120 | 0.2230 | 0.1999 | 0.2231 |
110
- | No log | 7.625 | 122 | 0.2268 | 0.2027 | 0.2270 |
111
- | No log | 7.75 | 124 | 0.2309 | 0.2117 | 0.2310 |
112
- | No log | 7.875 | 126 | 0.2333 | 0.2069 | 0.2334 |
113
- | No log | 8.0 | 128 | 0.2363 | 0.2151 | 0.2364 |
114
- | No log | 8.125 | 130 | 0.2387 | 0.2141 | 0.2389 |
115
- | No log | 8.25 | 132 | 0.2410 | 0.2151 | 0.2412 |
116
- | No log | 8.375 | 134 | 0.2430 | 0.1999 | 0.2432 |
117
- | No log | 8.5 | 136 | 0.2449 | 0.1974 | 0.2450 |
118
- | No log | 8.625 | 138 | 0.2463 | 0.1906 | 0.2465 |
119
- | No log | 8.75 | 140 | 0.2479 | 0.1963 | 0.2480 |
120
- | No log | 8.875 | 142 | 0.2460 | 0.2045 | 0.2462 |
121
- | No log | 9.0 | 144 | 0.2447 | 0.2161 | 0.2448 |
122
- | No log | 9.125 | 146 | 0.2444 | 0.2145 | 0.2446 |
123
- | No log | 9.25 | 148 | 0.2431 | 0.2145 | 0.2432 |
124
- | No log | 9.375 | 150 | 0.2414 | 0.2036 | 0.2416 |
125
- | No log | 9.5 | 152 | 0.2400 | 0.2000 | 0.2401 |
126
- | No log | 9.625 | 154 | 0.2390 | 0.2044 | 0.2392 |
127
- | No log | 9.75 | 156 | 0.2391 | 0.2044 | 0.2392 |
128
- | No log | 9.875 | 158 | 0.2394 | 0.2008 | 0.2395 |
129
- | No log | 10.0 | 160 | 0.2395 | 0.2008 | 0.2396 |
130
 
131
 
132
  ### Framework versions
 
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: 0.1458
18
+ - Qwk: 0.0595
19
+ - Mse: 0.1458
20
 
21
  ## Model description
22
 
 
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
50
+ | No log | 0.125 | 2 | 0.7079 | -0.0000 | 0.7079 |
51
+ | No log | 0.25 | 4 | 0.1912 | 0.0157 | 0.1912 |
52
+ | No log | 0.375 | 6 | 0.1659 | 0.0284 | 0.1659 |
53
+ | No log | 0.5 | 8 | 0.3128 | 0.0094 | 0.3128 |
54
+ | No log | 0.625 | 10 | 0.2898 | 0.0076 | 0.2898 |
55
+ | No log | 0.75 | 12 | 0.2065 | 0.0185 | 0.2065 |
56
+ | No log | 0.875 | 14 | 0.1447 | 0.0270 | 0.1447 |
57
+ | No log | 1.0 | 16 | 0.1501 | 0.0387 | 0.1501 |
58
+ | No log | 1.125 | 18 | 0.2147 | 0.0278 | 0.2147 |
59
+ | No log | 1.25 | 20 | 0.2330 | 0.0260 | 0.2330 |
60
+ | No log | 1.375 | 22 | 0.1773 | 0.0402 | 0.1773 |
61
+ | No log | 1.5 | 24 | 0.1419 | 0.0853 | 0.1419 |
62
+ | No log | 1.625 | 26 | 0.1384 | 0.0553 | 0.1384 |
63
+ | No log | 1.75 | 28 | 0.1481 | 0.0342 | 0.1481 |
64
+ | No log | 1.875 | 30 | 0.1586 | 0.0376 | 0.1586 |
65
+ | No log | 2.0 | 32 | 0.1665 | 0.0463 | 0.1665 |
66
+ | No log | 2.125 | 34 | 0.1964 | 0.0423 | 0.1964 |
67
+ | No log | 2.25 | 36 | 0.1779 | 0.0511 | 0.1779 |
68
+ | No log | 2.375 | 38 | 0.1542 | 0.1019 | 0.1542 |
69
+ | No log | 2.5 | 40 | 0.1505 | 0.1356 | 0.1505 |
70
+ | No log | 2.625 | 42 | 0.1422 | 0.1332 | 0.1422 |
71
+ | No log | 2.75 | 44 | 0.1427 | 0.0769 | 0.1427 |
72
+ | No log | 2.875 | 46 | 0.1755 | 0.0359 | 0.1755 |
73
+ | No log | 3.0 | 48 | 0.2548 | 0.0300 | 0.2548 |
74
+ | No log | 3.125 | 50 | 0.2939 | 0.0263 | 0.2939 |
75
+ | No log | 3.25 | 52 | 0.2512 | 0.0263 | 0.2512 |
76
+ | No log | 3.375 | 54 | 0.1646 | 0.0268 | 0.1646 |
77
+ | No log | 3.5 | 56 | 0.1283 | 0.1045 | 0.1283 |
78
+ | No log | 3.625 | 58 | 0.1365 | 0.1428 | 0.1365 |
79
+ | No log | 3.75 | 60 | 0.1354 | 0.1127 | 0.1354 |
80
+ | No log | 3.875 | 62 | 0.1424 | 0.0619 | 0.1424 |
81
+ | No log | 4.0 | 64 | 0.2058 | 0.0376 | 0.2058 |
82
+ | No log | 4.125 | 66 | 0.2354 | 0.0359 | 0.2354 |
83
+ | No log | 4.25 | 68 | 0.1903 | 0.0376 | 0.1903 |
84
+ | No log | 4.375 | 70 | 0.1417 | 0.0497 | 0.1417 |
85
+ | No log | 4.5 | 72 | 0.1346 | 0.0775 | 0.1346 |
86
+ | No log | 4.625 | 74 | 0.1423 | 0.0729 | 0.1423 |
87
+ | No log | 4.75 | 76 | 0.1585 | 0.0451 | 0.1585 |
88
+ | No log | 4.875 | 78 | 0.1582 | 0.0399 | 0.1582 |
89
+ | No log | 5.0 | 80 | 0.1374 | 0.0729 | 0.1374 |
90
+ | No log | 5.125 | 82 | 0.1284 | 0.1045 | 0.1284 |
91
+ | No log | 5.25 | 84 | 0.1284 | 0.1110 | 0.1284 |
92
+ | No log | 5.375 | 86 | 0.1307 | 0.0769 | 0.1307 |
93
+ | No log | 5.5 | 88 | 0.1473 | 0.0351 | 0.1473 |
94
+ | No log | 5.625 | 90 | 0.1726 | 0.0389 | 0.1726 |
95
+ | No log | 5.75 | 92 | 0.1734 | 0.0441 | 0.1734 |
96
+ | No log | 5.875 | 94 | 0.1544 | 0.0547 | 0.1544 |
97
+ | No log | 6.0 | 96 | 0.1361 | 0.1029 | 0.1361 |
98
+ | No log | 6.125 | 98 | 0.1362 | 0.1379 | 0.1362 |
99
+ | No log | 6.25 | 100 | 0.1358 | 0.1551 | 0.1358 |
100
+ | No log | 6.375 | 102 | 0.1338 | 0.1029 | 0.1338 |
101
+ | No log | 6.5 | 104 | 0.1417 | 0.0744 | 0.1417 |
102
+ | No log | 6.625 | 106 | 0.1467 | 0.0647 | 0.1467 |
103
+ | No log | 6.75 | 108 | 0.1456 | 0.0627 | 0.1456 |
104
+ | No log | 6.875 | 110 | 0.1429 | 0.0609 | 0.1429 |
105
+ | No log | 7.0 | 112 | 0.1442 | 0.0609 | 0.1442 |
106
+ | No log | 7.125 | 114 | 0.1423 | 0.0669 | 0.1423 |
107
+ | No log | 7.25 | 116 | 0.1407 | 0.0554 | 0.1407 |
108
+ | No log | 7.375 | 118 | 0.1417 | 0.0675 | 0.1417 |
109
+ | No log | 7.5 | 120 | 0.1453 | 0.0634 | 0.1453 |
110
+ | No log | 7.625 | 122 | 0.1508 | 0.0661 | 0.1508 |
111
+ | No log | 7.75 | 124 | 0.1573 | 0.0603 | 0.1573 |
112
+ | No log | 7.875 | 126 | 0.1579 | 0.0547 | 0.1579 |
113
+ | No log | 8.0 | 128 | 0.1512 | 0.0591 | 0.1512 |
114
+ | No log | 8.125 | 130 | 0.1432 | 0.0733 | 0.1432 |
115
+ | No log | 8.25 | 132 | 0.1387 | 0.0861 | 0.1387 |
116
+ | No log | 8.375 | 134 | 0.1376 | 0.0883 | 0.1376 |
117
+ | No log | 8.5 | 136 | 0.1388 | 0.0738 | 0.1388 |
118
+ | No log | 8.625 | 138 | 0.1432 | 0.0811 | 0.1432 |
119
+ | No log | 8.75 | 140 | 0.1486 | 0.0669 | 0.1486 |
120
+ | No log | 8.875 | 142 | 0.1523 | 0.0591 | 0.1523 |
121
+ | No log | 9.0 | 144 | 0.1538 | 0.0610 | 0.1538 |
122
+ | No log | 9.125 | 146 | 0.1533 | 0.0534 | 0.1533 |
123
+ | No log | 9.25 | 148 | 0.1515 | 0.0592 | 0.1515 |
124
+ | No log | 9.375 | 150 | 0.1492 | 0.0574 | 0.1492 |
125
+ | No log | 9.5 | 152 | 0.1465 | 0.0534 | 0.1465 |
126
+ | No log | 9.625 | 154 | 0.1454 | 0.0595 | 0.1454 |
127
+ | No log | 9.75 | 156 | 0.1453 | 0.0595 | 0.1453 |
128
+ | No log | 9.875 | 158 | 0.1457 | 0.0595 | 0.1457 |
129
+ | No log | 10.0 | 160 | 0.1458 | 0.0595 | 0.1458 |
130
 
131
 
132
  ### Framework versions