Rasooli commited on
Commit
9f8384e
·
verified ·
1 Parent(s): 14d45aa

Sentiment Fa

Browse files
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  library_name: transformers
3
- base_model: HooshvareLab/bert-base-parsbert-uncased
 
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -16,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # Bert-Sentiment-Fa
18
 
19
- This model is a fine-tuned version of [HooshvareLab/bert-base-parsbert-uncased](https://huggingface.co/HooshvareLab/bert-base-parsbert-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.1461
22
- - Accuracy: 0.8208
23
- - F1: 0.8230
24
 
25
  ## Model description
26
 
@@ -51,21 +52,21 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
- | No log | 1.0 | 68 | 0.4975 | 0.7917 | 0.7896 |
55
- | No log | 2.0 | 136 | 0.5646 | 0.8125 | 0.8163 |
56
- | No log | 3.0 | 204 | 0.6853 | 0.8167 | 0.8072 |
57
- | No log | 4.0 | 272 | 0.9142 | 0.8 | 0.7987 |
58
- | No log | 5.0 | 340 | 0.8389 | 0.8375 | 0.8393 |
59
- | No log | 6.0 | 408 | 0.8732 | 0.8208 | 0.8148 |
60
- | No log | 7.0 | 476 | 0.9233 | 0.825 | 0.8226 |
61
- | 0.1198 | 8.0 | 544 | 0.9971 | 0.8042 | 0.7896 |
62
- | 0.1198 | 9.0 | 612 | 1.0807 | 0.8167 | 0.8154 |
63
- | 0.1198 | 10.0 | 680 | 1.0949 | 0.825 | 0.8242 |
64
- | 0.1198 | 11.0 | 748 | 1.0613 | 0.8083 | 0.8098 |
65
- | 0.1198 | 12.0 | 816 | 1.0842 | 0.8083 | 0.8095 |
66
- | 0.1198 | 13.0 | 884 | 1.1327 | 0.8167 | 0.8195 |
67
- | 0.1198 | 14.0 | 952 | 1.1332 | 0.8125 | 0.8130 |
68
- | 0.0073 | 15.0 | 1020 | 1.1461 | 0.8208 | 0.8230 |
69
 
70
 
71
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model: HooshvareLab/bert-fa-base-uncased
5
  tags:
6
  - generated_from_trainer
7
  metrics:
 
17
 
18
  # Bert-Sentiment-Fa
19
 
20
+ This model is a fine-tuned version of [HooshvareLab/bert-fa-base-uncased](https://huggingface.co/HooshvareLab/bert-fa-base-uncased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.1790
23
+ - Accuracy: 0.8167
24
+ - F1: 0.8174
25
 
26
  ## Model description
27
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | No log | 1.0 | 68 | 0.6093 | 0.7583 | 0.7592 |
56
+ | No log | 2.0 | 136 | 0.5057 | 0.8125 | 0.8093 |
57
+ | No log | 3.0 | 204 | 0.5610 | 0.8125 | 0.8172 |
58
+ | No log | 4.0 | 272 | 0.7870 | 0.7958 | 0.7862 |
59
+ | No log | 5.0 | 340 | 0.8404 | 0.8042 | 0.8105 |
60
+ | No log | 6.0 | 408 | 0.8729 | 0.8208 | 0.8256 |
61
+ | No log | 7.0 | 476 | 0.9832 | 0.8292 | 0.8322 |
62
+ | 0.1891 | 8.0 | 544 | 1.0597 | 0.825 | 0.8288 |
63
+ | 0.1891 | 9.0 | 612 | 1.1262 | 0.8208 | 0.8184 |
64
+ | 0.1891 | 10.0 | 680 | 1.1224 | 0.8208 | 0.8260 |
65
+ | 0.1891 | 11.0 | 748 | 1.1524 | 0.8167 | 0.8188 |
66
+ | 0.1891 | 12.0 | 816 | 1.1460 | 0.8042 | 0.8055 |
67
+ | 0.1891 | 13.0 | 884 | 1.1633 | 0.8167 | 0.8202 |
68
+ | 0.1891 | 14.0 | 952 | 1.1620 | 0.8167 | 0.8177 |
69
+ | 0.0077 | 15.0 | 1020 | 1.1790 | 0.8167 | 0.8174 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:397bf883fc179aed75bce1358a20313da523731d7275cf7fc685cfe95353a57d
3
  size 651398148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae06a048afcaacad352a73431fc81de76701ebb10261ddf230fd21b716718c8
3
  size 651398148
runs/Sep07_06-36-23_bf72b4a04449/events.out.tfevents.1725691006.bf72b4a04449.2864.15 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f274964b93b57eff7be194bbb8788b4d06b3fa2aae234c58bdce45e37e2c3ce9
3
- size 10988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b07ad7ed72a4976d9c1755d95a0c0827b7032bc8688171fcb376df2ac31a44
3
+ size 11342