Training in progress, step 500
Browse files- README.md +314 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k18_task2_organization
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k18_task2_organization
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.6260
|
19 |
+
- Qwk: 0.4721
|
20 |
+
- Mse: 0.6260
|
21 |
+
- Rmse: 0.7912
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 100
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
|
51 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|:------:|:------:|
|
52 |
+
| No log | 0.0211 | 2 | 4.2097 | -0.0149 | 4.2097 | 2.0517 |
|
53 |
+
| No log | 0.0421 | 4 | 2.5782 | 0.0587 | 2.5782 | 1.6057 |
|
54 |
+
| No log | 0.0632 | 6 | 1.3197 | 0.0773 | 1.3197 | 1.1488 |
|
55 |
+
| No log | 0.0842 | 8 | 1.0302 | -0.0011 | 1.0302 | 1.0150 |
|
56 |
+
| No log | 0.1053 | 10 | 1.0478 | -0.0444 | 1.0478 | 1.0236 |
|
57 |
+
| No log | 0.1263 | 12 | 0.8546 | 0.1340 | 0.8546 | 0.9244 |
|
58 |
+
| No log | 0.1474 | 14 | 0.8383 | 0.1842 | 0.8383 | 0.9156 |
|
59 |
+
| No log | 0.1684 | 16 | 0.9568 | 0.0212 | 0.9568 | 0.9782 |
|
60 |
+
| No log | 0.1895 | 18 | 1.0898 | -0.0175 | 1.0898 | 1.0439 |
|
61 |
+
| No log | 0.2105 | 20 | 1.4527 | 0.0210 | 1.4527 | 1.2053 |
|
62 |
+
| No log | 0.2316 | 22 | 1.4635 | 0.0 | 1.4635 | 1.2098 |
|
63 |
+
| No log | 0.2526 | 24 | 1.1380 | -0.0548 | 1.1380 | 1.0668 |
|
64 |
+
| No log | 0.2737 | 26 | 0.9040 | 0.0616 | 0.9040 | 0.9508 |
|
65 |
+
| No log | 0.2947 | 28 | 0.8778 | 0.0795 | 0.8778 | 0.9369 |
|
66 |
+
| No log | 0.3158 | 30 | 0.8393 | 0.1340 | 0.8393 | 0.9161 |
|
67 |
+
| No log | 0.3368 | 32 | 0.8704 | 0.0573 | 0.8704 | 0.9330 |
|
68 |
+
| No log | 0.3579 | 34 | 0.8873 | 0.0642 | 0.8873 | 0.9420 |
|
69 |
+
| No log | 0.3789 | 36 | 0.9541 | 0.1455 | 0.9541 | 0.9768 |
|
70 |
+
| No log | 0.4 | 38 | 1.0408 | 0.0283 | 1.0408 | 1.0202 |
|
71 |
+
| No log | 0.4211 | 40 | 1.0647 | 0.0058 | 1.0647 | 1.0318 |
|
72 |
+
| No log | 0.4421 | 42 | 1.0126 | 0.0737 | 1.0126 | 1.0063 |
|
73 |
+
| No log | 0.4632 | 44 | 1.1037 | 0.0071 | 1.1037 | 1.0505 |
|
74 |
+
| No log | 0.4842 | 46 | 1.1039 | 0.0893 | 1.1039 | 1.0507 |
|
75 |
+
| No log | 0.5053 | 48 | 0.9551 | 0.2100 | 0.9551 | 0.9773 |
|
76 |
+
| No log | 0.5263 | 50 | 0.9332 | 0.1881 | 0.9332 | 0.9660 |
|
77 |
+
| No log | 0.5474 | 52 | 0.9323 | 0.2176 | 0.9323 | 0.9655 |
|
78 |
+
| No log | 0.5684 | 54 | 0.9447 | 0.2197 | 0.9447 | 0.9720 |
|
79 |
+
| No log | 0.5895 | 56 | 0.9117 | 0.1971 | 0.9117 | 0.9548 |
|
80 |
+
| No log | 0.6105 | 58 | 0.8912 | 0.1461 | 0.8912 | 0.9440 |
|
81 |
+
| No log | 0.6316 | 60 | 0.8505 | 0.1416 | 0.8505 | 0.9222 |
|
82 |
+
| No log | 0.6526 | 62 | 0.8079 | 0.2140 | 0.8079 | 0.8988 |
|
83 |
+
| No log | 0.6737 | 64 | 0.8848 | 0.1982 | 0.8848 | 0.9406 |
|
84 |
+
| No log | 0.6947 | 66 | 0.9672 | 0.1261 | 0.9672 | 0.9834 |
|
85 |
+
| No log | 0.7158 | 68 | 1.1036 | -0.0481 | 1.1036 | 1.0505 |
|
86 |
+
| No log | 0.7368 | 70 | 1.2673 | -0.0635 | 1.2673 | 1.1257 |
|
87 |
+
| No log | 0.7579 | 72 | 1.1015 | 0.1101 | 1.1015 | 1.0495 |
|
88 |
+
| No log | 0.7789 | 74 | 0.8036 | 0.2688 | 0.8036 | 0.8965 |
|
89 |
+
| No log | 0.8 | 76 | 0.8736 | 0.2730 | 0.8736 | 0.9347 |
|
90 |
+
| No log | 0.8211 | 78 | 0.8582 | 0.2843 | 0.8582 | 0.9264 |
|
91 |
+
| No log | 0.8421 | 80 | 0.8516 | 0.2412 | 0.8516 | 0.9228 |
|
92 |
+
| No log | 0.8632 | 82 | 0.9163 | 0.2853 | 0.9163 | 0.9572 |
|
93 |
+
| No log | 0.8842 | 84 | 0.8865 | 0.2421 | 0.8865 | 0.9415 |
|
94 |
+
| No log | 0.9053 | 86 | 0.7909 | 0.3096 | 0.7909 | 0.8893 |
|
95 |
+
| No log | 0.9263 | 88 | 0.7728 | 0.2646 | 0.7728 | 0.8791 |
|
96 |
+
| No log | 0.9474 | 90 | 0.8157 | 0.2540 | 0.8157 | 0.9032 |
|
97 |
+
| No log | 0.9684 | 92 | 0.7664 | 0.2916 | 0.7664 | 0.8754 |
|
98 |
+
| No log | 0.9895 | 94 | 0.7379 | 0.3307 | 0.7379 | 0.8590 |
|
99 |
+
| No log | 1.0105 | 96 | 0.7555 | 0.3486 | 0.7555 | 0.8692 |
|
100 |
+
| No log | 1.0316 | 98 | 0.7372 | 0.3729 | 0.7372 | 0.8586 |
|
101 |
+
| No log | 1.0526 | 100 | 1.0513 | 0.2452 | 1.0513 | 1.0253 |
|
102 |
+
| No log | 1.0737 | 102 | 1.2066 | 0.2635 | 1.2066 | 1.0984 |
|
103 |
+
| No log | 1.0947 | 104 | 0.9465 | 0.3190 | 0.9465 | 0.9729 |
|
104 |
+
| No log | 1.1158 | 106 | 0.7233 | 0.5012 | 0.7233 | 0.8505 |
|
105 |
+
| No log | 1.1368 | 108 | 0.7298 | 0.4387 | 0.7298 | 0.8543 |
|
106 |
+
| No log | 1.1579 | 110 | 0.7545 | 0.4543 | 0.7545 | 0.8686 |
|
107 |
+
| No log | 1.1789 | 112 | 1.0095 | 0.3183 | 1.0095 | 1.0048 |
|
108 |
+
| No log | 1.2 | 114 | 1.0038 | 0.3231 | 1.0038 | 1.0019 |
|
109 |
+
| No log | 1.2211 | 116 | 0.7347 | 0.4328 | 0.7347 | 0.8571 |
|
110 |
+
| No log | 1.2421 | 118 | 0.7638 | 0.2997 | 0.7638 | 0.8739 |
|
111 |
+
| No log | 1.2632 | 120 | 0.9173 | 0.2788 | 0.9173 | 0.9578 |
|
112 |
+
| No log | 1.2842 | 122 | 0.9928 | 0.2731 | 0.9928 | 0.9964 |
|
113 |
+
| No log | 1.3053 | 124 | 0.8292 | 0.3495 | 0.8292 | 0.9106 |
|
114 |
+
| No log | 1.3263 | 126 | 0.6645 | 0.3885 | 0.6645 | 0.8152 |
|
115 |
+
| No log | 1.3474 | 128 | 0.7403 | 0.4690 | 0.7403 | 0.8604 |
|
116 |
+
| No log | 1.3684 | 130 | 0.7894 | 0.4238 | 0.7894 | 0.8885 |
|
117 |
+
| No log | 1.3895 | 132 | 0.6733 | 0.3970 | 0.6733 | 0.8206 |
|
118 |
+
| No log | 1.4105 | 134 | 0.6410 | 0.4080 | 0.6410 | 0.8006 |
|
119 |
+
| No log | 1.4316 | 136 | 0.8066 | 0.3832 | 0.8066 | 0.8981 |
|
120 |
+
| No log | 1.4526 | 138 | 0.8016 | 0.3678 | 0.8016 | 0.8953 |
|
121 |
+
| No log | 1.4737 | 140 | 0.6775 | 0.4304 | 0.6775 | 0.8231 |
|
122 |
+
| No log | 1.4947 | 142 | 0.6536 | 0.5012 | 0.6536 | 0.8085 |
|
123 |
+
| No log | 1.5158 | 144 | 0.6903 | 0.4669 | 0.6903 | 0.8309 |
|
124 |
+
| No log | 1.5368 | 146 | 0.7039 | 0.4357 | 0.7039 | 0.8390 |
|
125 |
+
| No log | 1.5579 | 148 | 0.7402 | 0.3687 | 0.7403 | 0.8604 |
|
126 |
+
| No log | 1.5789 | 150 | 0.8454 | 0.3297 | 0.8454 | 0.9194 |
|
127 |
+
| No log | 1.6 | 152 | 0.8778 | 0.3284 | 0.8778 | 0.9369 |
|
128 |
+
| No log | 1.6211 | 154 | 0.9024 | 0.3144 | 0.9024 | 0.9500 |
|
129 |
+
| No log | 1.6421 | 156 | 0.7700 | 0.3676 | 0.7700 | 0.8775 |
|
130 |
+
| No log | 1.6632 | 158 | 0.7262 | 0.3446 | 0.7262 | 0.8522 |
|
131 |
+
| No log | 1.6842 | 160 | 0.7249 | 0.2797 | 0.7249 | 0.8514 |
|
132 |
+
| No log | 1.7053 | 162 | 0.7517 | 0.2716 | 0.7517 | 0.8670 |
|
133 |
+
| No log | 1.7263 | 164 | 0.7267 | 0.3062 | 0.7267 | 0.8525 |
|
134 |
+
| No log | 1.7474 | 166 | 0.6821 | 0.3244 | 0.6821 | 0.8259 |
|
135 |
+
| No log | 1.7684 | 168 | 0.6691 | 0.4585 | 0.6691 | 0.8180 |
|
136 |
+
| No log | 1.7895 | 170 | 0.6660 | 0.4781 | 0.6660 | 0.8161 |
|
137 |
+
| No log | 1.8105 | 172 | 0.6748 | 0.5159 | 0.6748 | 0.8215 |
|
138 |
+
| No log | 1.8316 | 174 | 0.6465 | 0.4474 | 0.6465 | 0.8041 |
|
139 |
+
| No log | 1.8526 | 176 | 0.6373 | 0.4537 | 0.6373 | 0.7983 |
|
140 |
+
| No log | 1.8737 | 178 | 0.6940 | 0.4529 | 0.6940 | 0.8330 |
|
141 |
+
| No log | 1.8947 | 180 | 0.6828 | 0.4578 | 0.6828 | 0.8263 |
|
142 |
+
| No log | 1.9158 | 182 | 0.6647 | 0.5162 | 0.6647 | 0.8153 |
|
143 |
+
| No log | 1.9368 | 184 | 0.6667 | 0.5309 | 0.6667 | 0.8165 |
|
144 |
+
| No log | 1.9579 | 186 | 0.7051 | 0.4672 | 0.7051 | 0.8397 |
|
145 |
+
| No log | 1.9789 | 188 | 0.8478 | 0.3844 | 0.8478 | 0.9208 |
|
146 |
+
| No log | 2.0 | 190 | 0.8585 | 0.3759 | 0.8585 | 0.9266 |
|
147 |
+
| No log | 2.0211 | 192 | 0.7694 | 0.3995 | 0.7694 | 0.8771 |
|
148 |
+
| No log | 2.0421 | 194 | 0.7231 | 0.4761 | 0.7231 | 0.8504 |
|
149 |
+
| No log | 2.0632 | 196 | 0.7431 | 0.4644 | 0.7431 | 0.8620 |
|
150 |
+
| No log | 2.0842 | 198 | 0.7901 | 0.4451 | 0.7901 | 0.8889 |
|
151 |
+
| No log | 2.1053 | 200 | 0.7577 | 0.4987 | 0.7577 | 0.8705 |
|
152 |
+
| No log | 2.1263 | 202 | 0.7762 | 0.4852 | 0.7762 | 0.8810 |
|
153 |
+
| No log | 2.1474 | 204 | 0.7244 | 0.4557 | 0.7244 | 0.8511 |
|
154 |
+
| No log | 2.1684 | 206 | 0.6841 | 0.4130 | 0.6841 | 0.8271 |
|
155 |
+
| No log | 2.1895 | 208 | 0.6894 | 0.3373 | 0.6894 | 0.8303 |
|
156 |
+
| No log | 2.2105 | 210 | 0.6650 | 0.3532 | 0.6650 | 0.8155 |
|
157 |
+
| No log | 2.2316 | 212 | 0.7266 | 0.3969 | 0.7266 | 0.8524 |
|
158 |
+
| No log | 2.2526 | 214 | 0.8106 | 0.3769 | 0.8106 | 0.9003 |
|
159 |
+
| No log | 2.2737 | 216 | 0.8297 | 0.3616 | 0.8297 | 0.9109 |
|
160 |
+
| No log | 2.2947 | 218 | 0.7389 | 0.4336 | 0.7389 | 0.8596 |
|
161 |
+
| No log | 2.3158 | 220 | 0.7121 | 0.4198 | 0.7121 | 0.8439 |
|
162 |
+
| No log | 2.3368 | 222 | 0.7115 | 0.3672 | 0.7115 | 0.8435 |
|
163 |
+
| No log | 2.3579 | 224 | 0.7399 | 0.4270 | 0.7399 | 0.8602 |
|
164 |
+
| No log | 2.3789 | 226 | 0.9752 | 0.3976 | 0.9752 | 0.9875 |
|
165 |
+
| No log | 2.4 | 228 | 1.0765 | 0.3517 | 1.0765 | 1.0375 |
|
166 |
+
| No log | 2.4211 | 230 | 0.8772 | 0.3867 | 0.8772 | 0.9366 |
|
167 |
+
| No log | 2.4421 | 232 | 0.7032 | 0.4354 | 0.7032 | 0.8386 |
|
168 |
+
| No log | 2.4632 | 234 | 0.6810 | 0.3499 | 0.6810 | 0.8252 |
|
169 |
+
| No log | 2.4842 | 236 | 0.6927 | 0.4546 | 0.6927 | 0.8323 |
|
170 |
+
| No log | 2.5053 | 238 | 0.8415 | 0.3630 | 0.8415 | 0.9173 |
|
171 |
+
| No log | 2.5263 | 240 | 0.9222 | 0.3556 | 0.9222 | 0.9603 |
|
172 |
+
| No log | 2.5474 | 242 | 0.8166 | 0.3611 | 0.8166 | 0.9037 |
|
173 |
+
| No log | 2.5684 | 244 | 0.6657 | 0.4196 | 0.6657 | 0.8159 |
|
174 |
+
| No log | 2.5895 | 246 | 0.7061 | 0.4036 | 0.7061 | 0.8403 |
|
175 |
+
| No log | 2.6105 | 248 | 0.6788 | 0.4402 | 0.6788 | 0.8239 |
|
176 |
+
| No log | 2.6316 | 250 | 0.6703 | 0.4544 | 0.6703 | 0.8187 |
|
177 |
+
| No log | 2.6526 | 252 | 0.7386 | 0.3755 | 0.7386 | 0.8594 |
|
178 |
+
| No log | 2.6737 | 254 | 0.7893 | 0.3961 | 0.7893 | 0.8884 |
|
179 |
+
| No log | 2.6947 | 256 | 0.7305 | 0.4484 | 0.7305 | 0.8547 |
|
180 |
+
| No log | 2.7158 | 258 | 0.7320 | 0.3830 | 0.7320 | 0.8556 |
|
181 |
+
| No log | 2.7368 | 260 | 0.7651 | 0.4174 | 0.7651 | 0.8747 |
|
182 |
+
| No log | 2.7579 | 262 | 0.8126 | 0.3950 | 0.8126 | 0.9014 |
|
183 |
+
| No log | 2.7789 | 264 | 0.8648 | 0.4179 | 0.8648 | 0.9299 |
|
184 |
+
| No log | 2.8 | 266 | 0.7705 | 0.3847 | 0.7705 | 0.8778 |
|
185 |
+
| No log | 2.8211 | 268 | 0.7795 | 0.3750 | 0.7795 | 0.8829 |
|
186 |
+
| No log | 2.8421 | 270 | 0.7877 | 0.4347 | 0.7877 | 0.8875 |
|
187 |
+
| No log | 2.8632 | 272 | 0.7041 | 0.4229 | 0.7041 | 0.8391 |
|
188 |
+
| No log | 2.8842 | 274 | 0.8339 | 0.3898 | 0.8339 | 0.9132 |
|
189 |
+
| No log | 2.9053 | 276 | 0.9421 | 0.3376 | 0.9421 | 0.9706 |
|
190 |
+
| No log | 2.9263 | 278 | 0.8269 | 0.3658 | 0.8269 | 0.9094 |
|
191 |
+
| No log | 2.9474 | 280 | 0.6673 | 0.4418 | 0.6673 | 0.8169 |
|
192 |
+
| No log | 2.9684 | 282 | 0.7931 | 0.3983 | 0.7931 | 0.8906 |
|
193 |
+
| No log | 2.9895 | 284 | 1.0238 | 0.2709 | 1.0238 | 1.0118 |
|
194 |
+
| No log | 3.0105 | 286 | 0.9739 | 0.2852 | 0.9739 | 0.9868 |
|
195 |
+
| No log | 3.0316 | 288 | 0.7576 | 0.4356 | 0.7576 | 0.8704 |
|
196 |
+
| No log | 3.0526 | 290 | 0.6353 | 0.3241 | 0.6353 | 0.7971 |
|
197 |
+
| No log | 3.0737 | 292 | 0.7411 | 0.4093 | 0.7411 | 0.8609 |
|
198 |
+
| No log | 3.0947 | 294 | 0.8188 | 0.3670 | 0.8188 | 0.9049 |
|
199 |
+
| No log | 3.1158 | 296 | 0.7640 | 0.3758 | 0.7640 | 0.8741 |
|
200 |
+
| No log | 3.1368 | 298 | 0.6978 | 0.3798 | 0.6978 | 0.8353 |
|
201 |
+
| No log | 3.1579 | 300 | 0.6587 | 0.3644 | 0.6587 | 0.8116 |
|
202 |
+
| No log | 3.1789 | 302 | 0.6724 | 0.3188 | 0.6724 | 0.8200 |
|
203 |
+
| No log | 3.2 | 304 | 0.6651 | 0.3199 | 0.6651 | 0.8155 |
|
204 |
+
| No log | 3.2211 | 306 | 0.6479 | 0.3360 | 0.6479 | 0.8049 |
|
205 |
+
| No log | 3.2421 | 308 | 0.6698 | 0.3703 | 0.6698 | 0.8184 |
|
206 |
+
| No log | 3.2632 | 310 | 0.7515 | 0.3932 | 0.7515 | 0.8669 |
|
207 |
+
| No log | 3.2842 | 312 | 0.8026 | 0.3988 | 0.8026 | 0.8959 |
|
208 |
+
| No log | 3.3053 | 314 | 0.7554 | 0.3873 | 0.7554 | 0.8691 |
|
209 |
+
| No log | 3.3263 | 316 | 0.7466 | 0.3813 | 0.7466 | 0.8641 |
|
210 |
+
| No log | 3.3474 | 318 | 0.6728 | 0.4561 | 0.6728 | 0.8202 |
|
211 |
+
| No log | 3.3684 | 320 | 0.7147 | 0.4179 | 0.7147 | 0.8454 |
|
212 |
+
| No log | 3.3895 | 322 | 0.6946 | 0.4211 | 0.6946 | 0.8334 |
|
213 |
+
| No log | 3.4105 | 324 | 0.6398 | 0.4372 | 0.6398 | 0.7999 |
|
214 |
+
| No log | 3.4316 | 326 | 0.7547 | 0.3873 | 0.7547 | 0.8688 |
|
215 |
+
| No log | 3.4526 | 328 | 0.8605 | 0.4005 | 0.8605 | 0.9276 |
|
216 |
+
| No log | 3.4737 | 330 | 0.7764 | 0.3781 | 0.7764 | 0.8811 |
|
217 |
+
| No log | 3.4947 | 332 | 0.6440 | 0.4467 | 0.6440 | 0.8025 |
|
218 |
+
| No log | 3.5158 | 334 | 0.6857 | 0.3943 | 0.6857 | 0.8281 |
|
219 |
+
| No log | 3.5368 | 336 | 0.7939 | 0.3472 | 0.7939 | 0.8910 |
|
220 |
+
| No log | 3.5579 | 338 | 0.7265 | 0.3717 | 0.7265 | 0.8524 |
|
221 |
+
| No log | 3.5789 | 340 | 0.6277 | 0.4242 | 0.6277 | 0.7923 |
|
222 |
+
| No log | 3.6 | 342 | 0.6947 | 0.4548 | 0.6947 | 0.8335 |
|
223 |
+
| No log | 3.6211 | 344 | 0.7877 | 0.3959 | 0.7877 | 0.8875 |
|
224 |
+
| No log | 3.6421 | 346 | 0.8363 | 0.4228 | 0.8363 | 0.9145 |
|
225 |
+
| No log | 3.6632 | 348 | 0.7590 | 0.3833 | 0.7590 | 0.8712 |
|
226 |
+
| No log | 3.6842 | 350 | 0.6667 | 0.3235 | 0.6667 | 0.8165 |
|
227 |
+
| No log | 3.7053 | 352 | 0.6595 | 0.3144 | 0.6595 | 0.8121 |
|
228 |
+
| No log | 3.7263 | 354 | 0.6638 | 0.3686 | 0.6638 | 0.8147 |
|
229 |
+
| No log | 3.7474 | 356 | 0.6393 | 0.3557 | 0.6393 | 0.7996 |
|
230 |
+
| No log | 3.7684 | 358 | 0.6384 | 0.2974 | 0.6384 | 0.7990 |
|
231 |
+
| No log | 3.7895 | 360 | 0.6508 | 0.3170 | 0.6508 | 0.8068 |
|
232 |
+
| No log | 3.8105 | 362 | 0.6482 | 0.3362 | 0.6482 | 0.8051 |
|
233 |
+
| No log | 3.8316 | 364 | 0.6736 | 0.4040 | 0.6736 | 0.8207 |
|
234 |
+
| No log | 3.8526 | 366 | 0.7332 | 0.4153 | 0.7332 | 0.8563 |
|
235 |
+
| No log | 3.8737 | 368 | 0.7148 | 0.3641 | 0.7148 | 0.8454 |
|
236 |
+
| No log | 3.8947 | 370 | 0.6840 | 0.3528 | 0.6840 | 0.8271 |
|
237 |
+
| No log | 3.9158 | 372 | 0.6721 | 0.3564 | 0.6721 | 0.8198 |
|
238 |
+
| No log | 3.9368 | 374 | 0.6549 | 0.3588 | 0.6549 | 0.8093 |
|
239 |
+
| No log | 3.9579 | 376 | 0.6560 | 0.3373 | 0.6560 | 0.8099 |
|
240 |
+
| No log | 3.9789 | 378 | 0.6607 | 0.3418 | 0.6607 | 0.8128 |
|
241 |
+
| No log | 4.0 | 380 | 0.6800 | 0.3914 | 0.6800 | 0.8246 |
|
242 |
+
| No log | 4.0211 | 382 | 0.6647 | 0.4132 | 0.6647 | 0.8153 |
|
243 |
+
| No log | 4.0421 | 384 | 0.6203 | 0.4474 | 0.6203 | 0.7876 |
|
244 |
+
| No log | 4.0632 | 386 | 0.6266 | 0.4616 | 0.6266 | 0.7916 |
|
245 |
+
| No log | 4.0842 | 388 | 0.7167 | 0.4272 | 0.7167 | 0.8466 |
|
246 |
+
| No log | 4.1053 | 390 | 0.6939 | 0.4272 | 0.6939 | 0.8330 |
|
247 |
+
| No log | 4.1263 | 392 | 0.6092 | 0.5184 | 0.6092 | 0.7805 |
|
248 |
+
| No log | 4.1474 | 394 | 0.6887 | 0.4027 | 0.6887 | 0.8299 |
|
249 |
+
| No log | 4.1684 | 396 | 0.7666 | 0.4553 | 0.7666 | 0.8755 |
|
250 |
+
| No log | 4.1895 | 398 | 0.6921 | 0.3618 | 0.6921 | 0.8319 |
|
251 |
+
| No log | 4.2105 | 400 | 0.6369 | 0.4205 | 0.6369 | 0.7980 |
|
252 |
+
| No log | 4.2316 | 402 | 0.6484 | 0.4561 | 0.6484 | 0.8052 |
|
253 |
+
| No log | 4.2526 | 404 | 0.7014 | 0.3812 | 0.7014 | 0.8375 |
|
254 |
+
| No log | 4.2737 | 406 | 0.6990 | 0.3939 | 0.6990 | 0.8361 |
|
255 |
+
| No log | 4.2947 | 408 | 0.6831 | 0.4276 | 0.6831 | 0.8265 |
|
256 |
+
| No log | 4.3158 | 410 | 0.7152 | 0.4207 | 0.7152 | 0.8457 |
|
257 |
+
| No log | 4.3368 | 412 | 0.7372 | 0.4346 | 0.7372 | 0.8586 |
|
258 |
+
| No log | 4.3579 | 414 | 0.7056 | 0.3971 | 0.7056 | 0.8400 |
|
259 |
+
| No log | 4.3789 | 416 | 0.7290 | 0.4565 | 0.7290 | 0.8538 |
|
260 |
+
| No log | 4.4 | 418 | 0.7168 | 0.4565 | 0.7168 | 0.8466 |
|
261 |
+
| No log | 4.4211 | 420 | 0.7453 | 0.4365 | 0.7453 | 0.8633 |
|
262 |
+
| No log | 4.4421 | 422 | 0.7072 | 0.4387 | 0.7072 | 0.8409 |
|
263 |
+
| No log | 4.4632 | 424 | 0.6991 | 0.4244 | 0.6991 | 0.8361 |
|
264 |
+
| No log | 4.4842 | 426 | 0.6494 | 0.3804 | 0.6494 | 0.8059 |
|
265 |
+
| No log | 4.5053 | 428 | 0.6309 | 0.3513 | 0.6309 | 0.7943 |
|
266 |
+
| No log | 4.5263 | 430 | 0.6174 | 0.4199 | 0.6174 | 0.7857 |
|
267 |
+
| No log | 4.5474 | 432 | 0.6274 | 0.4315 | 0.6274 | 0.7921 |
|
268 |
+
| No log | 4.5684 | 434 | 0.6514 | 0.4499 | 0.6514 | 0.8071 |
|
269 |
+
| No log | 4.5895 | 436 | 0.6821 | 0.4036 | 0.6821 | 0.8259 |
|
270 |
+
| No log | 4.6105 | 438 | 0.6427 | 0.4209 | 0.6427 | 0.8017 |
|
271 |
+
| No log | 4.6316 | 440 | 0.6319 | 0.3924 | 0.6319 | 0.7949 |
|
272 |
+
| No log | 4.6526 | 442 | 0.6444 | 0.3879 | 0.6444 | 0.8027 |
|
273 |
+
| No log | 4.6737 | 444 | 0.6446 | 0.3268 | 0.6446 | 0.8028 |
|
274 |
+
| No log | 4.6947 | 446 | 0.6271 | 0.3479 | 0.6271 | 0.7919 |
|
275 |
+
| No log | 4.7158 | 448 | 0.6173 | 0.3587 | 0.6173 | 0.7857 |
|
276 |
+
| No log | 4.7368 | 450 | 0.6078 | 0.3606 | 0.6078 | 0.7796 |
|
277 |
+
| No log | 4.7579 | 452 | 0.6311 | 0.4183 | 0.6311 | 0.7944 |
|
278 |
+
| No log | 4.7789 | 454 | 0.6319 | 0.4679 | 0.6319 | 0.7949 |
|
279 |
+
| No log | 4.8 | 456 | 0.6251 | 0.3980 | 0.6251 | 0.7906 |
|
280 |
+
| No log | 4.8211 | 458 | 0.6283 | 0.4543 | 0.6283 | 0.7927 |
|
281 |
+
| No log | 4.8421 | 460 | 0.6463 | 0.4833 | 0.6463 | 0.8039 |
|
282 |
+
| No log | 4.8632 | 462 | 0.6245 | 0.4248 | 0.6245 | 0.7903 |
|
283 |
+
| No log | 4.8842 | 464 | 0.6091 | 0.3541 | 0.6091 | 0.7805 |
|
284 |
+
| No log | 4.9053 | 466 | 0.6028 | 0.3867 | 0.6028 | 0.7764 |
|
285 |
+
| No log | 4.9263 | 468 | 0.6079 | 0.4127 | 0.6079 | 0.7797 |
|
286 |
+
| No log | 4.9474 | 470 | 0.6053 | 0.4378 | 0.6053 | 0.7780 |
|
287 |
+
| No log | 4.9684 | 472 | 0.6196 | 0.3928 | 0.6196 | 0.7871 |
|
288 |
+
| No log | 4.9895 | 474 | 0.6466 | 0.4690 | 0.6466 | 0.8041 |
|
289 |
+
| No log | 5.0105 | 476 | 0.6386 | 0.4685 | 0.6386 | 0.7991 |
|
290 |
+
| No log | 5.0316 | 478 | 0.6699 | 0.4705 | 0.6699 | 0.8185 |
|
291 |
+
| No log | 5.0526 | 480 | 0.6630 | 0.4924 | 0.6630 | 0.8142 |
|
292 |
+
| No log | 5.0737 | 482 | 0.6278 | 0.5329 | 0.6278 | 0.7923 |
|
293 |
+
| No log | 5.0947 | 484 | 0.6128 | 0.4639 | 0.6128 | 0.7828 |
|
294 |
+
| No log | 5.1158 | 486 | 0.5971 | 0.4528 | 0.5971 | 0.7727 |
|
295 |
+
| No log | 5.1368 | 488 | 0.6146 | 0.4476 | 0.6146 | 0.7840 |
|
296 |
+
| No log | 5.1579 | 490 | 0.6708 | 0.4629 | 0.6708 | 0.8190 |
|
297 |
+
| No log | 5.1789 | 492 | 0.7083 | 0.4242 | 0.7083 | 0.8416 |
|
298 |
+
| No log | 5.2 | 494 | 0.7294 | 0.4543 | 0.7294 | 0.8540 |
|
299 |
+
| No log | 5.2211 | 496 | 0.6301 | 0.4880 | 0.6301 | 0.7938 |
|
300 |
+
| No log | 5.2421 | 498 | 0.6068 | 0.4938 | 0.6068 | 0.7790 |
|
301 |
+
| 0.4477 | 5.2632 | 500 | 0.6301 | 0.4843 | 0.6301 | 0.7938 |
|
302 |
+
| 0.4477 | 5.2842 | 502 | 0.7158 | 0.4787 | 0.7158 | 0.8460 |
|
303 |
+
| 0.4477 | 5.3053 | 504 | 0.7108 | 0.4797 | 0.7108 | 0.8431 |
|
304 |
+
| 0.4477 | 5.3263 | 506 | 0.6243 | 0.4351 | 0.6243 | 0.7901 |
|
305 |
+
| 0.4477 | 5.3474 | 508 | 0.5973 | 0.4747 | 0.5973 | 0.7728 |
|
306 |
+
| 0.4477 | 5.3684 | 510 | 0.6260 | 0.4721 | 0.6260 | 0.7912 |
|
307 |
+
|
308 |
+
|
309 |
+
### Framework versions
|
310 |
+
|
311 |
+
- Transformers 4.44.2
|
312 |
+
- Pytorch 2.4.0+cu118
|
313 |
+
- Datasets 2.21.0
|
314 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv02",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"problem_type": "regression",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.44.2",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 64000
|
32 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df789f04ceeaafc6e7e73fd714e20445070e381e208dab56d82667d2564c6e8e
|
3 |
+
size 540799996
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fc545263c53028a01af0f3e9800f4deb94795d5b54a64803a833f07b7e646ad
|
3 |
+
size 5240
|