salbatarni commited on
Commit
18d1445
·
verified ·
1 Parent(s): 66baad1

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -15
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_baseline_development_task4_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_baseline_development_task4_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: 0.4483
18
- - Qwk: 0.6
19
- - Mse: 0.4483
20
 
21
  ## Model description
22
 
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
50
- | No log | 1.0 | 2 | 3.6202 | -0.0256 | 3.6202 |
51
- | No log | 2.0 | 4 | 1.3484 | 0.0667 | 1.3484 |
52
- | No log | 3.0 | 6 | 0.4149 | 0.28 | 0.4149 |
53
- | No log | 4.0 | 8 | 0.4977 | 0.1765 | 0.4977 |
54
- | No log | 5.0 | 10 | 0.6053 | 0.1765 | 0.6053 |
55
- | No log | 6.0 | 12 | 0.6080 | 0.25 | 0.6080 |
56
- | No log | 7.0 | 14 | 0.5578 | 0.7143 | 0.5578 |
57
- | No log | 8.0 | 16 | 0.4912 | 0.6 | 0.4912 |
58
- | No log | 9.0 | 18 | 0.4606 | 0.6 | 0.4606 |
59
- | No log | 10.0 | 20 | 0.4483 | 0.6 | 0.4483 |
60
 
61
 
62
  ### Framework versions
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: arabert_baseline_development_task4_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_baseline_development_task4_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: 0.8082
18
+ - Qwk: 0.0
19
+ - Mse: 0.8082
20
 
21
  ## Model description
22
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|
50
+ | No log | 1.0 | 2 | 4.0751 | 0.0 | 4.0751 |
51
+ | No log | 2.0 | 4 | 2.8112 | 0.0 | 2.8112 |
52
+ | No log | 3.0 | 6 | 2.1818 | -0.0137 | 2.1818 |
53
+ | No log | 4.0 | 8 | 1.7217 | 0.0 | 1.7217 |
54
+ | No log | 5.0 | 10 | 1.0766 | 0.0 | 1.0766 |
55
+ | No log | 6.0 | 12 | 0.8885 | 0.0 | 0.8885 |
56
+ | No log | 7.0 | 14 | 0.8569 | -0.2121 | 0.8569 |
57
+ | No log | 8.0 | 16 | 0.8603 | 0.0 | 0.8603 |
58
+ | No log | 9.0 | 18 | 0.8317 | 0.0 | 0.8317 |
59
+ | No log | 10.0 | 20 | 0.8082 | 0.0 | 0.8082 |
60
 
61
 
62
  ### Framework versions