Hugging Face's logo

gp-tar4
/
QA_FineTuned

Question Answering
Transformers
Safetensors
Arabic
electra
Generated from Trainer
Inference Endpoints
Model card Files Community
Omar-youssef commited on
Commit
81b144b
·
verified ·
1 Parent(s): bfefdd1

End of training

Browse files
Files changed (2) hide show
  1. README.md +14 -16
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,20 +3,18 @@ base_model: zohaib99k/Bert_Arabic-SQuADv2-QA
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
- - name: QA_Fine_Tune
7
  results: []
8
- language:
9
- - ar
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
- # QA_Fine_Tune
16
 
17
  This model is a fine-tuned version of [zohaib99k/Bert_Arabic-SQuADv2-QA](https://huggingface.co/zohaib99k/Bert_Arabic-SQuADv2-QA) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.4536
20
 
21
  ## Model description
22
 
@@ -50,16 +48,16 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 2.8288 | 0.46 | 10 | 2.0264 |
54
- | 2.0278 | 0.92 | 20 | 1.8868 |
55
- | 1.4114 | 1.38 | 30 | 1.9024 |
56
- | 1.1806 | 1.84 | 40 | 1.8939 |
57
- | 0.822 | 2.3 | 50 | 2.1289 |
58
- | 0.7035 | 2.76 | 60 | 2.0242 |
59
- | 0.5329 | 3.22 | 70 | 2.1802 |
60
- | 0.4005 | 3.68 | 80 | 2.4024 |
61
- | 0.3332 | 4.14 | 90 | 2.3627 |
62
- | 0.2356 | 4.6 | 100 | 2.4536 |
63
 
64
 
65
  ### Framework versions
@@ -67,4 +65,4 @@ The following hyperparameters were used during training:
67
  - Transformers 4.39.3
68
  - Pytorch 2.1.2
69
  - Datasets 2.18.0
70
- - Tokenizers 0.15.2
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
6
+ - name: QA_FineTuned_Arabert
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
+ # QA_FineTuned_Arabert
14
 
15
  This model is a fine-tuned version of [zohaib99k/Bert_Arabic-SQuADv2-QA](https://huggingface.co/zohaib99k/Bert_Arabic-SQuADv2-QA) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 3.3343
18
 
19
  ## Model description
20
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.1603 | 0.46 | 10 | 2.7965 |
52
+ | 0.3055 | 0.92 | 20 | 3.0322 |
53
+ | 0.3091 | 1.38 | 30 | 2.8940 |
54
+ | 0.2692 | 1.84 | 40 | 2.9621 |
55
+ | 0.2198 | 2.3 | 50 | 2.9107 |
56
+ | 0.2112 | 2.76 | 60 | 3.1322 |
57
+ | 0.1576 | 3.22 | 70 | 3.2085 |
58
+ | 0.1392 | 3.68 | 80 | 3.1323 |
59
+ | 0.1474 | 4.14 | 90 | 3.2893 |
60
+ | 0.0905 | 4.6 | 100 | 3.3343 |
61
 
62
 
63
  ### Framework versions
 
65
  - Transformers 4.39.3
66
  - Pytorch 2.1.2
67
  - Datasets 2.18.0
68
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:616d401616e349cc22f6b9fbe3bc6c976a8ebf987cd436691efe8e55b4720950
3
  size 538441104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be09259436b9e14acffe7d9ae5658f77c82a69d4ca6cc9cc68b0cb06ee0c331f
3
  size 538441104