Hugging Face's logo

SoDehghan
/
test-push-to-hf

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
SoDehghan commited on
Commit
44bdfec
·
verified ·
1 Parent(s): 9ada0a5

Model save

Browse files
Files changed (3) hide show
  1. README.md +35 -22
  2. runs/Nov26_18-27-20_dde002542bbe/events.out.tfevents.1732645641.dde002542bbe.43070.0 +2 -2
  3. tokenizer.json +1 -6
README.md CHANGED
@@ -19,10 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [dbmdz/bert-base-turkish-uncased](https://huggingface.co/dbmdz/bert-base-turkish-uncased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.3251
23
- - F1: 0.7503
24
- - Roc Auc: 0.8138
25
- - Accuracy: 0.6220
26
 
27
  ## Model description
28
 
@@ -42,7 +42,7 @@ More information needed
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 5e-06
45
- - train_batch_size: 64
46
  - eval_batch_size: 20
47
  - seed: 42
48
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
@@ -53,23 +53,36 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|:-------:|:--------:|
56
- | 0.5427 | 0.5814 | 100 | 0.4944 | 0.5869 | 0.7028 | 0.4144 |
57
- | 0.4675 | 1.1628 | 200 | 0.4084 | 0.6789 | 0.7613 | 0.5073 |
58
- | 0.4047 | 1.7442 | 300 | 0.3702 | 0.7146 | 0.7855 | 0.5638 |
59
- | 0.3777 | 2.3256 | 400 | 0.3540 | 0.7310 | 0.7975 | 0.5829 |
60
- | 0.353 | 2.9070 | 500 | 0.3486 | 0.7330 | 0.7992 | 0.5765 |
61
- | 0.3369 | 3.4884 | 600 | 0.3409 | 0.7413 | 0.8055 | 0.6011 |
62
- | 0.3324 | 4.0698 | 700 | 0.3327 | 0.7435 | 0.8071 | 0.6075 |
63
- | 0.3226 | 4.6512 | 800 | 0.3294 | 0.7424 | 0.8067 | 0.6038 |
64
- | 0.3024 | 5.2326 | 900 | 0.3304 | 0.7453 | 0.8092 | 0.6056 |
65
- | 0.3065 | 5.8140 | 1000 | 0.3275 | 0.7503 | 0.8133 | 0.6166 |
66
- | 0.2968 | 6.3953 | 1100 | 0.3267 | 0.7567 | 0.8179 | 0.6239 |
67
- | 0.2925 | 6.9767 | 1200 | 0.3275 | 0.7445 | 0.8097 | 0.6038 |
68
- | 0.292 | 7.5581 | 1300 | 0.3259 | 0.7502 | 0.8136 | 0.6166 |
69
- | 0.2794 | 8.1395 | 1400 | 0.3260 | 0.7519 | 0.8146 | 0.6257 |
70
- | 0.285 | 8.7209 | 1500 | 0.3250 | 0.7555 | 0.8173 | 0.6248 |
71
- | 0.2756 | 9.3023 | 1600 | 0.3261 | 0.7522 | 0.8153 | 0.6193 |
72
- | 0.2813 | 9.8837 | 1700 | 0.3251 | 0.7503 | 0.8138 | 0.6220 |
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [dbmdz/bert-base-turkish-uncased](https://huggingface.co/dbmdz/bert-base-turkish-uncased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.3270
23
+ - F1: 0.7593
24
+ - Roc Auc: 0.8207
25
+ - Accuracy: 0.6275
26
 
27
  ## Model description
28
 
 
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 5e-06
45
+ - train_batch_size: 36
46
  - eval_batch_size: 20
47
  - seed: 42
48
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
55
  |:-------------:|:------:|:----:|:---------------:|:------:|:-------:|:--------:|
56
+ | 0.5503 | 0.3279 | 100 | 0.5081 | 0.5765 | 0.6945 | 0.4208 |
57
+ | 0.4883 | 0.6557 | 200 | 0.4370 | 0.6477 | 0.7416 | 0.4645 |
58
+ | 0.431 | 0.9836 | 300 | 0.3909 | 0.6896 | 0.7684 | 0.5355 |
59
+ | 0.4004 | 1.3115 | 400 | 0.3718 | 0.7172 | 0.7880 | 0.5583 |
60
+ | 0.3723 | 1.6393 | 500 | 0.3573 | 0.7328 | 0.7985 | 0.5856 |
61
+ | 0.3678 | 1.9672 | 600 | 0.3489 | 0.7338 | 0.7989 | 0.5893 |
62
+ | 0.3516 | 2.2951 | 700 | 0.3420 | 0.7351 | 0.8006 | 0.5965 |
63
+ | 0.3409 | 2.6230 | 800 | 0.3372 | 0.7405 | 0.8055 | 0.6075 |
64
+ | 0.3269 | 2.9508 | 900 | 0.3325 | 0.7475 | 0.8103 | 0.6111 |
65
+ | 0.3168 | 3.2787 | 1000 | 0.3359 | 0.7459 | 0.8100 | 0.6029 |
66
+ | 0.3174 | 3.6066 | 1100 | 0.3304 | 0.7438 | 0.8081 | 0.6120 |
67
+ | 0.3162 | 3.9344 | 1200 | 0.3287 | 0.7538 | 0.8155 | 0.6102 |
68
+ | 0.3051 | 4.2623 | 1300 | 0.3266 | 0.7482 | 0.8116 | 0.6075 |
69
+ | 0.3035 | 4.5902 | 1400 | 0.3298 | 0.7531 | 0.8158 | 0.6075 |
70
+ | 0.2896 | 4.9180 | 1500 | 0.3239 | 0.7511 | 0.8135 | 0.6230 |
71
+ | 0.2774 | 5.2459 | 1600 | 0.3252 | 0.7497 | 0.8129 | 0.6239 |
72
+ | 0.2874 | 5.5738 | 1700 | 0.3238 | 0.7518 | 0.8146 | 0.6193 |
73
+ | 0.2852 | 5.9016 | 1800 | 0.3222 | 0.7535 | 0.8154 | 0.6257 |
74
+ | 0.274 | 6.2295 | 1900 | 0.3234 | 0.7560 | 0.8172 | 0.6302 |
75
+ | 0.2699 | 6.5574 | 2000 | 0.3226 | 0.7556 | 0.8175 | 0.6266 |
76
+ | 0.2696 | 6.8852 | 2100 | 0.3233 | 0.7574 | 0.8190 | 0.6248 |
77
+ | 0.271 | 7.2131 | 2200 | 0.3235 | 0.7591 | 0.8198 | 0.6266 |
78
+ | 0.2655 | 7.5410 | 2300 | 0.3252 | 0.7568 | 0.8182 | 0.6257 |
79
+ | 0.2593 | 7.8689 | 2400 | 0.3259 | 0.7552 | 0.8171 | 0.6248 |
80
+ | 0.2489 | 8.1967 | 2500 | 0.3277 | 0.7539 | 0.8168 | 0.6202 |
81
+ | 0.258 | 8.5246 | 2600 | 0.3275 | 0.7555 | 0.8173 | 0.6193 |
82
+ | 0.2513 | 8.8525 | 2700 | 0.3267 | 0.7563 | 0.8183 | 0.6220 |
83
+ | 0.2514 | 9.1803 | 2800 | 0.3265 | 0.7584 | 0.8200 | 0.6239 |
84
+ | 0.2498 | 9.5082 | 2900 | 0.3272 | 0.7578 | 0.8197 | 0.6248 |
85
+ | 0.2485 | 9.8361 | 3000 | 0.3270 | 0.7593 | 0.8207 | 0.6275 |
86
 
87
 
88
  ### Framework versions
runs/Nov26_18-27-20_dde002542bbe/events.out.tfevents.1732645641.dde002542bbe.43070.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aee203ddec91678801a0d9d2ec9595faddf9f49b98b8e61ca0834439c75ed81
3
- size 24331
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdcb4eff0754bb48f2eb90c432712f32100d81e5deef2f64d2d2ed9ee263cc54
3
+ size 24685
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {