Hugging Face's logo

salbatarni
/
arabert_baseline_relevance_task1_fold0

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
742d77f
•
1 Parent(s): 18d10f2

End of training

Browse files
Files changed (1) hide show
  1. README.md +22 -23
README.md CHANGED
@@ -1,6 +1,5 @@
1
  ---
2
- license: apache-2.0
3
- base_model: google-bert/bert-base-cased
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,11 +12,11 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # arabert_baseline_relevance_task1_fold0
15
 
16
- This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1825
19
- - Qwk: 0.0
20
- - Mse: 0.1897
21
 
22
  ## Model description
23
 
@@ -46,23 +45,23 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
50
- |:-------------:|:------:|:----:|:---------------:|:---:|:------:|
51
- | No log | 0.3333 | 2 | 2.4969 | 0.0 | 2.4904 |
52
- | No log | 0.6667 | 4 | 1.3473 | 0.0 | 1.3409 |
53
- | No log | 1.0 | 6 | 0.3427 | 0.0 | 0.3425 |
54
- | No log | 1.3333 | 8 | 0.2309 | 0.0 | 0.2317 |
55
- | No log | 1.6667 | 10 | 0.2296 | 0.0 | 0.2295 |
56
- | No log | 2.0 | 12 | 0.1857 | 0.0 | 0.1892 |
57
- | No log | 2.3333 | 14 | 0.2129 | 0.0 | 0.2222 |
58
- | No log | 2.6667 | 16 | 0.2062 | 0.0 | 0.2174 |
59
- | No log | 3.0 | 18 | 0.1648 | 0.0 | 0.1739 |
60
- | No log | 3.3333 | 20 | 0.1714 | 0.0 | 0.1786 |
61
- | No log | 3.6667 | 22 | 0.1879 | 0.0 | 0.1941 |
62
- | No log | 4.0 | 24 | 0.1893 | 0.0 | 0.1957 |
63
- | No log | 4.3333 | 26 | 0.1901 | 0.0 | 0.1966 |
64
- | No log | 4.6667 | 28 | 0.1926 | 0.0 | 0.1991 |
65
- | No log | 5.0 | 30 | 0.1825 | 0.0 | 0.1897 |
66
 
67
 
68
  ### Framework versions
 
1
  ---
2
+ base_model: aubmindlab/bert-base-arabertv02
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
 
12
 
13
  # arabert_baseline_relevance_task1_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: 0.2514
18
+ - Qwk: 0.0808
19
+ - Mse: 0.2559
20
 
21
  ## Model description
22
 
 
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
49
+ |:-------------:|:------:|:----:|:---------------:|:-------:|:------:|
50
+ | No log | 0.3333 | 2 | 1.1076 | -0.0049 | 1.0949 |
51
+ | No log | 0.6667 | 4 | 0.2779 | 0.0 | 0.2800 |
52
+ | No log | 1.0 | 6 | 0.2271 | 0.3467 | 0.2294 |
53
+ | No log | 1.3333 | 8 | 0.2361 | 0.1667 | 0.2359 |
54
+ | No log | 1.6667 | 10 | 0.1985 | 0.1250 | 0.2028 |
55
+ | No log | 2.0 | 12 | 0.2232 | 0.0 | 0.2304 |
56
+ | No log | 2.3333 | 14 | 0.2167 | 0.0 | 0.2237 |
57
+ | No log | 2.6667 | 16 | 0.2206 | 0.0 | 0.2259 |
58
+ | No log | 3.0 | 18 | 0.2075 | 0.0 | 0.2127 |
59
+ | No log | 3.3333 | 20 | 0.2078 | 0.0 | 0.2132 |
60
+ | No log | 3.6667 | 22 | 0.2183 | 0.0 | 0.2235 |
61
+ | No log | 4.0 | 24 | 0.2326 | 0.0 | 0.2375 |
62
+ | No log | 4.3333 | 26 | 0.2498 | 0.0392 | 0.2543 |
63
+ | No log | 4.6667 | 28 | 0.2547 | 0.0392 | 0.2590 |
64
+ | No log | 5.0 | 30 | 0.2514 | 0.0808 | 0.2559 |
65
 
66
 
67
  ### Framework versions