Training in progress, step 500
Browse files- README.md +315 -0
- config.json +32 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
base_model: aubmindlab/bert-base-arabertv02
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k12_task1_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 |
+
# ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k12_task1_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: 0.6173
|
19 |
+
- Qwk: 0.7260
|
20 |
+
- Mse: 0.6173
|
21 |
+
- Rmse: 0.7857
|
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 | 0.0222 | 2 | 7.2624 | 0.0219 | 7.2624 | 2.6949 |
|
53 |
+
| No log | 0.0444 | 4 | 4.7398 | 0.0543 | 4.7398 | 2.1771 |
|
54 |
+
| No log | 0.0667 | 6 | 2.8761 | 0.0732 | 2.8761 | 1.6959 |
|
55 |
+
| No log | 0.0889 | 8 | 2.3242 | 0.0952 | 2.3242 | 1.5245 |
|
56 |
+
| No log | 0.1111 | 10 | 1.9969 | 0.2154 | 1.9969 | 1.4131 |
|
57 |
+
| No log | 0.1333 | 12 | 1.4286 | 0.2430 | 1.4286 | 1.1952 |
|
58 |
+
| No log | 0.1556 | 14 | 1.3395 | 0.2883 | 1.3395 | 1.1574 |
|
59 |
+
| No log | 0.1778 | 16 | 1.5975 | 0.2243 | 1.5975 | 1.2639 |
|
60 |
+
| No log | 0.2 | 18 | 1.7762 | 0.0893 | 1.7762 | 1.3328 |
|
61 |
+
| No log | 0.2222 | 20 | 1.5454 | 0.2703 | 1.5454 | 1.2431 |
|
62 |
+
| No log | 0.2444 | 22 | 1.2929 | 0.2857 | 1.2929 | 1.1371 |
|
63 |
+
| No log | 0.2667 | 24 | 1.5764 | 0.3582 | 1.5764 | 1.2555 |
|
64 |
+
| No log | 0.2889 | 26 | 1.7510 | 0.3404 | 1.7510 | 1.3233 |
|
65 |
+
| No log | 0.3111 | 28 | 2.1623 | 0.2162 | 2.1623 | 1.4705 |
|
66 |
+
| No log | 0.3333 | 30 | 1.6836 | 0.3741 | 1.6836 | 1.2975 |
|
67 |
+
| No log | 0.3556 | 32 | 1.1744 | 0.3833 | 1.1744 | 1.0837 |
|
68 |
+
| No log | 0.3778 | 34 | 1.1673 | 0.3214 | 1.1673 | 1.0804 |
|
69 |
+
| No log | 0.4 | 36 | 1.0594 | 0.3793 | 1.0594 | 1.0293 |
|
70 |
+
| No log | 0.4222 | 38 | 0.9748 | 0.5124 | 0.9748 | 0.9873 |
|
71 |
+
| No log | 0.4444 | 40 | 0.9613 | 0.5238 | 0.9613 | 0.9804 |
|
72 |
+
| No log | 0.4667 | 42 | 1.0245 | 0.5630 | 1.0245 | 1.0122 |
|
73 |
+
| No log | 0.4889 | 44 | 0.9542 | 0.5630 | 0.9542 | 0.9768 |
|
74 |
+
| No log | 0.5111 | 46 | 0.8967 | 0.5522 | 0.8967 | 0.9469 |
|
75 |
+
| No log | 0.5333 | 48 | 0.8702 | 0.6131 | 0.8702 | 0.9328 |
|
76 |
+
| No log | 0.5556 | 50 | 0.8310 | 0.6620 | 0.8310 | 0.9116 |
|
77 |
+
| No log | 0.5778 | 52 | 0.8709 | 0.6383 | 0.8709 | 0.9332 |
|
78 |
+
| No log | 0.6 | 54 | 0.8868 | 0.6712 | 0.8868 | 0.9417 |
|
79 |
+
| No log | 0.6222 | 56 | 0.8083 | 0.6986 | 0.8083 | 0.8991 |
|
80 |
+
| No log | 0.6444 | 58 | 0.8564 | 0.6887 | 0.8564 | 0.9254 |
|
81 |
+
| No log | 0.6667 | 60 | 0.8735 | 0.6803 | 0.8735 | 0.9346 |
|
82 |
+
| No log | 0.6889 | 62 | 0.9220 | 0.6803 | 0.9220 | 0.9602 |
|
83 |
+
| No log | 0.7111 | 64 | 0.9508 | 0.6323 | 0.9508 | 0.9751 |
|
84 |
+
| No log | 0.7333 | 66 | 0.8882 | 0.6486 | 0.8882 | 0.9425 |
|
85 |
+
| No log | 0.7556 | 68 | 1.1405 | 0.5526 | 1.1405 | 1.0679 |
|
86 |
+
| No log | 0.7778 | 70 | 1.5102 | 0.4737 | 1.5102 | 1.2289 |
|
87 |
+
| No log | 0.8 | 72 | 1.3329 | 0.4203 | 1.3329 | 1.1545 |
|
88 |
+
| No log | 0.8222 | 74 | 0.8832 | 0.6849 | 0.8832 | 0.9398 |
|
89 |
+
| No log | 0.8444 | 76 | 0.8065 | 0.7075 | 0.8065 | 0.8981 |
|
90 |
+
| No log | 0.8667 | 78 | 0.8231 | 0.7075 | 0.8231 | 0.9072 |
|
91 |
+
| No log | 0.8889 | 80 | 0.7361 | 0.6944 | 0.7361 | 0.8579 |
|
92 |
+
| No log | 0.9111 | 82 | 0.7535 | 0.7211 | 0.7535 | 0.8681 |
|
93 |
+
| No log | 0.9333 | 84 | 1.0202 | 0.6622 | 1.0202 | 1.0101 |
|
94 |
+
| No log | 0.9556 | 86 | 0.9464 | 0.6757 | 0.9464 | 0.9728 |
|
95 |
+
| No log | 0.9778 | 88 | 0.7653 | 0.7368 | 0.7653 | 0.8748 |
|
96 |
+
| No log | 1.0 | 90 | 0.7603 | 0.7260 | 0.7603 | 0.8719 |
|
97 |
+
| No log | 1.0222 | 92 | 0.9302 | 0.6571 | 0.9302 | 0.9645 |
|
98 |
+
| No log | 1.0444 | 94 | 0.8352 | 0.6711 | 0.8352 | 0.9139 |
|
99 |
+
| No log | 1.0667 | 96 | 0.7305 | 0.75 | 0.7305 | 0.8547 |
|
100 |
+
| No log | 1.0889 | 98 | 0.7193 | 0.7702 | 0.7193 | 0.8481 |
|
101 |
+
| No log | 1.1111 | 100 | 0.7922 | 0.7375 | 0.7922 | 0.8901 |
|
102 |
+
| No log | 1.1333 | 102 | 0.8129 | 0.7143 | 0.8129 | 0.9016 |
|
103 |
+
| No log | 1.1556 | 104 | 0.6995 | 0.7133 | 0.6995 | 0.8364 |
|
104 |
+
| No log | 1.1778 | 106 | 0.6944 | 0.7172 | 0.6944 | 0.8333 |
|
105 |
+
| No log | 1.2 | 108 | 0.8171 | 0.7470 | 0.8171 | 0.9039 |
|
106 |
+
| No log | 1.2222 | 110 | 0.8385 | 0.7283 | 0.8385 | 0.9157 |
|
107 |
+
| No log | 1.2444 | 112 | 0.7787 | 0.7176 | 0.7787 | 0.8825 |
|
108 |
+
| No log | 1.2667 | 114 | 0.7250 | 0.7 | 0.7250 | 0.8515 |
|
109 |
+
| No log | 1.2889 | 116 | 0.6743 | 0.7879 | 0.6743 | 0.8211 |
|
110 |
+
| No log | 1.3111 | 118 | 0.6613 | 0.7857 | 0.6613 | 0.8132 |
|
111 |
+
| No log | 1.3333 | 120 | 0.6886 | 0.7647 | 0.6886 | 0.8298 |
|
112 |
+
| No log | 1.3556 | 122 | 0.6933 | 0.7456 | 0.6933 | 0.8326 |
|
113 |
+
| No log | 1.3778 | 124 | 0.7089 | 0.7771 | 0.7089 | 0.8420 |
|
114 |
+
| No log | 1.4 | 126 | 0.6595 | 0.8166 | 0.6595 | 0.8121 |
|
115 |
+
| No log | 1.4222 | 128 | 0.9806 | 0.6784 | 0.9806 | 0.9903 |
|
116 |
+
| No log | 1.4444 | 130 | 1.2395 | 0.5896 | 1.2395 | 1.1133 |
|
117 |
+
| No log | 1.4667 | 132 | 1.1813 | 0.6076 | 1.1813 | 1.0869 |
|
118 |
+
| No log | 1.4889 | 134 | 0.9423 | 0.6761 | 0.9423 | 0.9707 |
|
119 |
+
| No log | 1.5111 | 136 | 0.8261 | 0.6475 | 0.8261 | 0.9089 |
|
120 |
+
| No log | 1.5333 | 138 | 0.7595 | 0.7083 | 0.7595 | 0.8715 |
|
121 |
+
| No log | 1.5556 | 140 | 0.7291 | 0.7172 | 0.7291 | 0.8539 |
|
122 |
+
| No log | 1.5778 | 142 | 0.7345 | 0.7785 | 0.7345 | 0.8570 |
|
123 |
+
| No log | 1.6 | 144 | 0.8410 | 0.7152 | 0.8410 | 0.9170 |
|
124 |
+
| No log | 1.6222 | 146 | 0.9274 | 0.6757 | 0.9274 | 0.9630 |
|
125 |
+
| No log | 1.6444 | 148 | 0.8409 | 0.6757 | 0.8409 | 0.9170 |
|
126 |
+
| No log | 1.6667 | 150 | 0.6592 | 0.7639 | 0.6592 | 0.8119 |
|
127 |
+
| No log | 1.6889 | 152 | 0.5849 | 0.7484 | 0.5849 | 0.7648 |
|
128 |
+
| No log | 1.7111 | 154 | 0.5685 | 0.7826 | 0.5685 | 0.7540 |
|
129 |
+
| No log | 1.7333 | 156 | 0.5206 | 0.8409 | 0.5206 | 0.7215 |
|
130 |
+
| No log | 1.7556 | 158 | 0.5118 | 0.8466 | 0.5118 | 0.7154 |
|
131 |
+
| No log | 1.7778 | 160 | 0.5119 | 0.8306 | 0.5119 | 0.7155 |
|
132 |
+
| No log | 1.8 | 162 | 0.5769 | 0.8432 | 0.5769 | 0.7595 |
|
133 |
+
| No log | 1.8222 | 164 | 0.5484 | 0.7904 | 0.5484 | 0.7405 |
|
134 |
+
| No log | 1.8444 | 166 | 0.6217 | 0.8050 | 0.6217 | 0.7885 |
|
135 |
+
| No log | 1.8667 | 168 | 0.6661 | 0.7871 | 0.6661 | 0.8161 |
|
136 |
+
| No log | 1.8889 | 170 | 0.7173 | 0.7550 | 0.7173 | 0.8470 |
|
137 |
+
| No log | 1.9111 | 172 | 0.7976 | 0.7083 | 0.7976 | 0.8931 |
|
138 |
+
| No log | 1.9333 | 174 | 0.9803 | 0.6846 | 0.9803 | 0.9901 |
|
139 |
+
| No log | 1.9556 | 176 | 1.0944 | 0.5806 | 1.0944 | 1.0461 |
|
140 |
+
| No log | 1.9778 | 178 | 1.0164 | 0.6144 | 1.0164 | 1.0081 |
|
141 |
+
| No log | 2.0 | 180 | 0.8587 | 0.7114 | 0.8587 | 0.9267 |
|
142 |
+
| No log | 2.0222 | 182 | 0.6971 | 0.7368 | 0.6971 | 0.8349 |
|
143 |
+
| No log | 2.0444 | 184 | 0.6072 | 0.7871 | 0.6072 | 0.7792 |
|
144 |
+
| No log | 2.0667 | 186 | 0.6111 | 0.7792 | 0.6111 | 0.7817 |
|
145 |
+
| No log | 2.0889 | 188 | 0.6450 | 0.72 | 0.6450 | 0.8031 |
|
146 |
+
| No log | 2.1111 | 190 | 0.7101 | 0.7333 | 0.7101 | 0.8427 |
|
147 |
+
| No log | 2.1333 | 192 | 0.7961 | 0.7421 | 0.7961 | 0.8923 |
|
148 |
+
| No log | 2.1556 | 194 | 0.7637 | 0.7436 | 0.7637 | 0.8739 |
|
149 |
+
| No log | 2.1778 | 196 | 0.7167 | 0.7320 | 0.7167 | 0.8466 |
|
150 |
+
| No log | 2.2 | 198 | 0.7633 | 0.7436 | 0.7633 | 0.8737 |
|
151 |
+
| No log | 2.2222 | 200 | 0.8554 | 0.7097 | 0.8554 | 0.9249 |
|
152 |
+
| No log | 2.2444 | 202 | 0.8010 | 0.7097 | 0.8010 | 0.8950 |
|
153 |
+
| No log | 2.2667 | 204 | 0.7448 | 0.7059 | 0.7448 | 0.8630 |
|
154 |
+
| No log | 2.2889 | 206 | 0.6726 | 0.7785 | 0.6726 | 0.8201 |
|
155 |
+
| No log | 2.3111 | 208 | 0.6818 | 0.7550 | 0.6818 | 0.8257 |
|
156 |
+
| No log | 2.3333 | 210 | 0.7865 | 0.7051 | 0.7865 | 0.8869 |
|
157 |
+
| No log | 2.3556 | 212 | 0.8267 | 0.7125 | 0.8267 | 0.9092 |
|
158 |
+
| No log | 2.3778 | 214 | 0.7408 | 0.7211 | 0.7408 | 0.8607 |
|
159 |
+
| No log | 2.4 | 216 | 0.7033 | 0.7211 | 0.7033 | 0.8386 |
|
160 |
+
| No log | 2.4222 | 218 | 0.6876 | 0.7211 | 0.6876 | 0.8292 |
|
161 |
+
| No log | 2.4444 | 220 | 0.6608 | 0.7432 | 0.6608 | 0.8129 |
|
162 |
+
| No log | 2.4667 | 222 | 0.6511 | 0.7320 | 0.6511 | 0.8069 |
|
163 |
+
| No log | 2.4889 | 224 | 0.6117 | 0.7711 | 0.6117 | 0.7821 |
|
164 |
+
| No log | 2.5111 | 226 | 0.5687 | 0.8199 | 0.5687 | 0.7541 |
|
165 |
+
| No log | 2.5333 | 228 | 0.5762 | 0.8125 | 0.5762 | 0.7591 |
|
166 |
+
| No log | 2.5556 | 230 | 0.6182 | 0.8054 | 0.6182 | 0.7863 |
|
167 |
+
| No log | 2.5778 | 232 | 0.6600 | 0.7838 | 0.6600 | 0.8124 |
|
168 |
+
| No log | 2.6 | 234 | 0.6508 | 0.7582 | 0.6508 | 0.8067 |
|
169 |
+
| No log | 2.6222 | 236 | 0.5808 | 0.7871 | 0.5808 | 0.7621 |
|
170 |
+
| No log | 2.6444 | 238 | 0.5343 | 0.8199 | 0.5343 | 0.7309 |
|
171 |
+
| No log | 2.6667 | 240 | 0.5178 | 0.8199 | 0.5178 | 0.7196 |
|
172 |
+
| No log | 2.6889 | 242 | 0.6239 | 0.7957 | 0.6239 | 0.7899 |
|
173 |
+
| No log | 2.7111 | 244 | 0.7466 | 0.7784 | 0.7466 | 0.8640 |
|
174 |
+
| No log | 2.7333 | 246 | 0.6549 | 0.7784 | 0.6549 | 0.8093 |
|
175 |
+
| No log | 2.7556 | 248 | 0.5389 | 0.8121 | 0.5389 | 0.7341 |
|
176 |
+
| No log | 2.7778 | 250 | 0.5386 | 0.7975 | 0.5386 | 0.7339 |
|
177 |
+
| No log | 2.8 | 252 | 0.5477 | 0.8024 | 0.5477 | 0.7401 |
|
178 |
+
| No log | 2.8222 | 254 | 0.6508 | 0.7665 | 0.6508 | 0.8067 |
|
179 |
+
| No log | 2.8444 | 256 | 0.7856 | 0.7030 | 0.7856 | 0.8863 |
|
180 |
+
| No log | 2.8667 | 258 | 0.7296 | 0.7485 | 0.7296 | 0.8541 |
|
181 |
+
| No log | 2.8889 | 260 | 0.6381 | 0.7632 | 0.6381 | 0.7988 |
|
182 |
+
| No log | 2.9111 | 262 | 0.5975 | 0.7651 | 0.5975 | 0.7730 |
|
183 |
+
| No log | 2.9333 | 264 | 0.5636 | 0.7843 | 0.5636 | 0.7507 |
|
184 |
+
| No log | 2.9556 | 266 | 0.5521 | 0.8025 | 0.5521 | 0.7431 |
|
185 |
+
| No log | 2.9778 | 268 | 0.5662 | 0.7975 | 0.5662 | 0.7525 |
|
186 |
+
| No log | 3.0 | 270 | 0.5702 | 0.8140 | 0.5702 | 0.7551 |
|
187 |
+
| No log | 3.0222 | 272 | 0.5860 | 0.8121 | 0.5860 | 0.7655 |
|
188 |
+
| No log | 3.0444 | 274 | 0.5652 | 0.8 | 0.5652 | 0.7518 |
|
189 |
+
| No log | 3.0667 | 276 | 0.5478 | 0.7843 | 0.5478 | 0.7401 |
|
190 |
+
| No log | 3.0889 | 278 | 0.5594 | 0.7733 | 0.5594 | 0.7479 |
|
191 |
+
| No log | 3.1111 | 280 | 0.5759 | 0.7619 | 0.5759 | 0.7589 |
|
192 |
+
| No log | 3.1333 | 282 | 0.5981 | 0.7671 | 0.5981 | 0.7734 |
|
193 |
+
| No log | 3.1556 | 284 | 0.6472 | 0.7517 | 0.6472 | 0.8045 |
|
194 |
+
| No log | 3.1778 | 286 | 0.7560 | 0.75 | 0.7560 | 0.8695 |
|
195 |
+
| No log | 3.2 | 288 | 0.7286 | 0.7753 | 0.7286 | 0.8536 |
|
196 |
+
| No log | 3.2222 | 290 | 0.5843 | 0.8242 | 0.5843 | 0.7644 |
|
197 |
+
| No log | 3.2444 | 292 | 0.5556 | 0.7875 | 0.5556 | 0.7454 |
|
198 |
+
| No log | 3.2667 | 294 | 0.5819 | 0.7925 | 0.5819 | 0.7628 |
|
199 |
+
| No log | 3.2889 | 296 | 0.6621 | 0.7582 | 0.6621 | 0.8137 |
|
200 |
+
| No log | 3.3111 | 298 | 0.7140 | 0.7067 | 0.7140 | 0.8450 |
|
201 |
+
| No log | 3.3333 | 300 | 0.7657 | 0.7211 | 0.7657 | 0.8750 |
|
202 |
+
| No log | 3.3556 | 302 | 0.7675 | 0.7083 | 0.7675 | 0.8761 |
|
203 |
+
| No log | 3.3778 | 304 | 0.7604 | 0.7248 | 0.7604 | 0.8720 |
|
204 |
+
| No log | 3.4 | 306 | 0.7135 | 0.7436 | 0.7135 | 0.8447 |
|
205 |
+
| No log | 3.4222 | 308 | 0.7100 | 0.775 | 0.7100 | 0.8426 |
|
206 |
+
| No log | 3.4444 | 310 | 0.6417 | 0.7925 | 0.6417 | 0.8010 |
|
207 |
+
| No log | 3.4667 | 312 | 0.5774 | 0.7949 | 0.5774 | 0.7599 |
|
208 |
+
| No log | 3.4889 | 314 | 0.6050 | 0.7692 | 0.6050 | 0.7778 |
|
209 |
+
| No log | 3.5111 | 316 | 0.6024 | 0.7871 | 0.6024 | 0.7761 |
|
210 |
+
| No log | 3.5333 | 318 | 0.5771 | 0.7947 | 0.5771 | 0.7597 |
|
211 |
+
| No log | 3.5556 | 320 | 0.5543 | 0.7895 | 0.5543 | 0.7445 |
|
212 |
+
| No log | 3.5778 | 322 | 0.5335 | 0.8025 | 0.5335 | 0.7304 |
|
213 |
+
| No log | 3.6 | 324 | 0.5302 | 0.7975 | 0.5302 | 0.7281 |
|
214 |
+
| No log | 3.6222 | 326 | 0.5439 | 0.8025 | 0.5439 | 0.7375 |
|
215 |
+
| No log | 3.6444 | 328 | 0.5975 | 0.7799 | 0.5975 | 0.7730 |
|
216 |
+
| No log | 3.6667 | 330 | 0.7568 | 0.7317 | 0.7568 | 0.8699 |
|
217 |
+
| No log | 3.6889 | 332 | 0.7934 | 0.7037 | 0.7934 | 0.8907 |
|
218 |
+
| No log | 3.7111 | 334 | 0.7354 | 0.7215 | 0.7354 | 0.8575 |
|
219 |
+
| No log | 3.7333 | 336 | 0.6950 | 0.7123 | 0.6950 | 0.8336 |
|
220 |
+
| No log | 3.7556 | 338 | 0.6652 | 0.7568 | 0.6652 | 0.8156 |
|
221 |
+
| No log | 3.7778 | 340 | 0.6494 | 0.7785 | 0.6494 | 0.8059 |
|
222 |
+
| No log | 3.8 | 342 | 0.6475 | 0.7682 | 0.6475 | 0.8047 |
|
223 |
+
| No log | 3.8222 | 344 | 0.6096 | 0.7895 | 0.6096 | 0.7807 |
|
224 |
+
| No log | 3.8444 | 346 | 0.5969 | 0.7722 | 0.5969 | 0.7726 |
|
225 |
+
| No log | 3.8667 | 348 | 0.5646 | 0.7952 | 0.5646 | 0.7514 |
|
226 |
+
| No log | 3.8889 | 350 | 0.5350 | 0.8132 | 0.5350 | 0.7314 |
|
227 |
+
| No log | 3.9111 | 352 | 0.5285 | 0.8242 | 0.5285 | 0.7270 |
|
228 |
+
| No log | 3.9333 | 354 | 0.5314 | 0.8208 | 0.5314 | 0.7289 |
|
229 |
+
| No log | 3.9556 | 356 | 0.5504 | 0.8208 | 0.5504 | 0.7419 |
|
230 |
+
| No log | 3.9778 | 358 | 0.5841 | 0.8148 | 0.5841 | 0.7643 |
|
231 |
+
| No log | 4.0 | 360 | 0.6387 | 0.7755 | 0.6387 | 0.7992 |
|
232 |
+
| No log | 4.0222 | 362 | 0.6940 | 0.7432 | 0.6940 | 0.8330 |
|
233 |
+
| No log | 4.0444 | 364 | 0.6814 | 0.7517 | 0.6814 | 0.8255 |
|
234 |
+
| No log | 4.0667 | 366 | 0.6320 | 0.7639 | 0.6320 | 0.7950 |
|
235 |
+
| No log | 4.0889 | 368 | 0.6044 | 0.7778 | 0.6044 | 0.7775 |
|
236 |
+
| No log | 4.1111 | 370 | 0.5482 | 0.8075 | 0.5482 | 0.7404 |
|
237 |
+
| No log | 4.1333 | 372 | 0.5389 | 0.7811 | 0.5389 | 0.7341 |
|
238 |
+
| No log | 4.1556 | 374 | 0.6219 | 0.8 | 0.6219 | 0.7886 |
|
239 |
+
| No log | 4.1778 | 376 | 0.6480 | 0.7978 | 0.6480 | 0.8050 |
|
240 |
+
| No log | 4.2 | 378 | 0.5938 | 0.7882 | 0.5938 | 0.7706 |
|
241 |
+
| No log | 4.2222 | 380 | 0.5884 | 0.7467 | 0.5884 | 0.7671 |
|
242 |
+
| No log | 4.2444 | 382 | 0.6221 | 0.7606 | 0.6221 | 0.7887 |
|
243 |
+
| No log | 4.2667 | 384 | 0.6581 | 0.7413 | 0.6581 | 0.8112 |
|
244 |
+
| No log | 4.2889 | 386 | 0.6661 | 0.7172 | 0.6661 | 0.8162 |
|
245 |
+
| No log | 4.3111 | 388 | 0.6185 | 0.7465 | 0.6185 | 0.7864 |
|
246 |
+
| No log | 4.3333 | 390 | 0.5820 | 0.7755 | 0.5820 | 0.7629 |
|
247 |
+
| No log | 4.3556 | 392 | 0.5812 | 0.7815 | 0.5812 | 0.7624 |
|
248 |
+
| No log | 4.3778 | 394 | 0.5578 | 0.8 | 0.5578 | 0.7469 |
|
249 |
+
| No log | 4.4 | 396 | 0.5572 | 0.8025 | 0.5572 | 0.7465 |
|
250 |
+
| No log | 4.4222 | 398 | 0.6486 | 0.7545 | 0.6486 | 0.8054 |
|
251 |
+
| No log | 4.4444 | 400 | 0.7744 | 0.7725 | 0.7744 | 0.8800 |
|
252 |
+
| No log | 4.4667 | 402 | 0.7493 | 0.7755 | 0.7493 | 0.8656 |
|
253 |
+
| No log | 4.4889 | 404 | 0.5712 | 0.7929 | 0.5712 | 0.7558 |
|
254 |
+
| No log | 4.5111 | 406 | 0.4740 | 0.8395 | 0.4740 | 0.6884 |
|
255 |
+
| No log | 4.5333 | 408 | 0.4674 | 0.8293 | 0.4674 | 0.6836 |
|
256 |
+
| No log | 4.5556 | 410 | 0.4764 | 0.8302 | 0.4764 | 0.6902 |
|
257 |
+
| No log | 4.5778 | 412 | 0.4930 | 0.8302 | 0.4930 | 0.7021 |
|
258 |
+
| No log | 4.6 | 414 | 0.5065 | 0.8199 | 0.5065 | 0.7117 |
|
259 |
+
| No log | 4.6222 | 416 | 0.5293 | 0.8050 | 0.5293 | 0.7275 |
|
260 |
+
| No log | 4.6444 | 418 | 0.5324 | 0.8125 | 0.5324 | 0.7296 |
|
261 |
+
| No log | 4.6667 | 420 | 0.5528 | 0.7925 | 0.5528 | 0.7435 |
|
262 |
+
| No log | 4.6889 | 422 | 0.5482 | 0.7875 | 0.5482 | 0.7404 |
|
263 |
+
| No log | 4.7111 | 424 | 0.5289 | 0.8098 | 0.5289 | 0.7273 |
|
264 |
+
| No log | 4.7333 | 426 | 0.5328 | 0.8144 | 0.5328 | 0.7299 |
|
265 |
+
| No log | 4.7556 | 428 | 0.5332 | 0.8193 | 0.5332 | 0.7302 |
|
266 |
+
| No log | 4.7778 | 430 | 0.5349 | 0.8098 | 0.5349 | 0.7314 |
|
267 |
+
| No log | 4.8 | 432 | 0.5603 | 0.8 | 0.5603 | 0.7486 |
|
268 |
+
| No log | 4.8222 | 434 | 0.5778 | 0.8025 | 0.5778 | 0.7601 |
|
269 |
+
| No log | 4.8444 | 436 | 0.5574 | 0.7949 | 0.5574 | 0.7466 |
|
270 |
+
| No log | 4.8667 | 438 | 0.5789 | 0.8125 | 0.5789 | 0.7608 |
|
271 |
+
| No log | 4.8889 | 440 | 0.5882 | 0.8199 | 0.5882 | 0.7669 |
|
272 |
+
| No log | 4.9111 | 442 | 0.5674 | 0.7975 | 0.5674 | 0.7532 |
|
273 |
+
| No log | 4.9333 | 444 | 0.5677 | 0.7922 | 0.5677 | 0.7534 |
|
274 |
+
| No log | 4.9556 | 446 | 0.6019 | 0.7297 | 0.6019 | 0.7758 |
|
275 |
+
| No log | 4.9778 | 448 | 0.5958 | 0.7347 | 0.5958 | 0.7719 |
|
276 |
+
| No log | 5.0 | 450 | 0.5951 | 0.7432 | 0.5951 | 0.7714 |
|
277 |
+
| No log | 5.0222 | 452 | 0.6146 | 0.7550 | 0.6146 | 0.7840 |
|
278 |
+
| No log | 5.0444 | 454 | 0.5848 | 0.7432 | 0.5848 | 0.7647 |
|
279 |
+
| No log | 5.0667 | 456 | 0.5423 | 0.7763 | 0.5423 | 0.7364 |
|
280 |
+
| No log | 5.0889 | 458 | 0.5328 | 0.8 | 0.5328 | 0.7300 |
|
281 |
+
| No log | 5.1111 | 460 | 0.5244 | 0.7922 | 0.5244 | 0.7241 |
|
282 |
+
| No log | 5.1333 | 462 | 0.5406 | 0.7871 | 0.5406 | 0.7353 |
|
283 |
+
| No log | 5.1556 | 464 | 0.5746 | 0.7550 | 0.5746 | 0.7580 |
|
284 |
+
| No log | 5.1778 | 466 | 0.6013 | 0.7432 | 0.6013 | 0.7754 |
|
285 |
+
| No log | 5.2 | 468 | 0.6313 | 0.7222 | 0.6313 | 0.7945 |
|
286 |
+
| No log | 5.2222 | 470 | 0.6886 | 0.7152 | 0.6886 | 0.8298 |
|
287 |
+
| No log | 5.2444 | 472 | 0.6994 | 0.7089 | 0.6994 | 0.8363 |
|
288 |
+
| No log | 5.2667 | 474 | 0.6543 | 0.7531 | 0.6543 | 0.8089 |
|
289 |
+
| No log | 5.2889 | 476 | 0.5718 | 0.7792 | 0.5718 | 0.7562 |
|
290 |
+
| No log | 5.3111 | 478 | 0.5183 | 0.8025 | 0.5183 | 0.7199 |
|
291 |
+
| No log | 5.3333 | 480 | 0.4942 | 0.8313 | 0.4942 | 0.7030 |
|
292 |
+
| No log | 5.3556 | 482 | 0.4847 | 0.8284 | 0.4847 | 0.6962 |
|
293 |
+
| No log | 5.3778 | 484 | 0.4990 | 0.8221 | 0.4990 | 0.7064 |
|
294 |
+
| No log | 5.4 | 486 | 0.5632 | 0.7975 | 0.5632 | 0.7505 |
|
295 |
+
| No log | 5.4222 | 488 | 0.5871 | 0.8025 | 0.5871 | 0.7662 |
|
296 |
+
| No log | 5.4444 | 490 | 0.5931 | 0.7922 | 0.5931 | 0.7701 |
|
297 |
+
| No log | 5.4667 | 492 | 0.5709 | 0.8077 | 0.5709 | 0.7556 |
|
298 |
+
| No log | 5.4889 | 494 | 0.5305 | 0.8125 | 0.5305 | 0.7284 |
|
299 |
+
| No log | 5.5111 | 496 | 0.5092 | 0.8075 | 0.5092 | 0.7135 |
|
300 |
+
| No log | 5.5333 | 498 | 0.5161 | 0.8075 | 0.5161 | 0.7184 |
|
301 |
+
| 0.4158 | 5.5556 | 500 | 0.5493 | 0.8075 | 0.5493 | 0.7412 |
|
302 |
+
| 0.4158 | 5.5778 | 502 | 0.5714 | 0.8228 | 0.5714 | 0.7559 |
|
303 |
+
| 0.4158 | 5.6 | 504 | 0.5910 | 0.7662 | 0.5910 | 0.7688 |
|
304 |
+
| 0.4158 | 5.6222 | 506 | 0.6224 | 0.7248 | 0.6224 | 0.7889 |
|
305 |
+
| 0.4158 | 5.6444 | 508 | 0.6607 | 0.7368 | 0.6607 | 0.8128 |
|
306 |
+
| 0.4158 | 5.6667 | 510 | 0.6526 | 0.7260 | 0.6526 | 0.8078 |
|
307 |
+
| 0.4158 | 5.6889 | 512 | 0.6173 | 0.7260 | 0.6173 | 0.7857 |
|
308 |
+
|
309 |
+
|
310 |
+
### Framework versions
|
311 |
+
|
312 |
+
- Transformers 4.44.2
|
313 |
+
- Pytorch 2.4.0+cu118
|
314 |
+
- Datasets 2.21.0
|
315 |
+
- 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 sha256:5b533b845d56ce311069e291dbfa443b083f1b26ce2634aa2d1ac0f3c15a8a3e
|
3 |
+
size 540799996
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bfe54f4dc2d30ff12ae9286a62e3ea849b1a7ab61d99ab467b6cb187e3afc82
|
3 |
+
size 5304
|