Amna100 commited on
Commit
3e85c96
1 Parent(s): 52a7c06

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -16,24 +16,21 @@ model-index:
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wbresearch/FineTuning-ADE-DropOUT/runs/rw6sjeap)
20
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wbresearch/FineTuning-ADE-DropOUT/runs/g4pyaj7k)
21
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wbresearch/FineTuning-ADE-DropOUT/runs/t4il24wd)
22
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wbresearch/FineTuning-ADE-DropOUT/runs/qf2ywrxq)
23
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wbresearch/FineTuning-ADE-DropOUT/runs/9xmjfnoc)
24
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wbresearch/FineTuning-ADE-DropOUT/runs/vp363qmp)
25
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/wbresearch/FineTuning-ADE-DropOUT/runs/10xzvwgi)
26
  # fold_3
27
 
28
  This model is a fine-tuned version of [Amna100/PreTraining-MLM](https://huggingface.co/Amna100/PreTraining-MLM) on the None dataset.
29
  It achieves the following results on the evaluation set:
30
- - Loss: 0.0125
31
- - Precision: 0.6887
32
- - Recall: 0.6744
33
- - F1: 0.6814
34
- - Accuracy: 0.9992
35
- - Roc Auc: 0.9939
36
- - Pr Auc: 0.9998
37
 
38
  ## Model description
39
 
@@ -64,14 +61,12 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Roc Auc | Pr Auc |
66
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------:|:------:|
67
- | 0.0286 | 1.0 | 632 | 0.0159 | 0.5908 | 0.5035 | 0.5436 | 0.9988 | 0.9931 | 0.9998 |
68
- | 0.0115 | 2.0 | 1264 | 0.0125 | 0.6887 | 0.6744 | 0.6814 | 0.9992 | 0.9939 | 0.9998 |
69
- | 0.0079 | 3.0 | 1896 | 0.0170 | 0.8419 | 0.5289 | 0.6496 | 0.9992 | 0.9859 | 0.9995 |
70
- | 0.0035 | 4.0 | 2528 | 0.0150 | 0.7146 | 0.7344 | 0.7244 | 0.9992 | 0.9903 | 0.9997 |
71
- | 0.002 | 5.0 | 3160 | 0.0166 | 0.6471 | 0.7621 | 0.6999 | 0.9991 | 0.9917 | 0.9997 |
72
- | 0.0017 | 6.0 | 3792 | 0.0196 | 0.8300 | 0.6651 | 0.7385 | 0.9993 | 0.9865 | 0.9995 |
73
- | 0.0012 | 7.0 | 4424 | 0.0175 | 0.7143 | 0.7621 | 0.7374 | 0.9993 | 0.9920 | 0.9997 |
74
- | 0.0004 | 8.0 | 5056 | 0.0176 | 0.7262 | 0.7413 | 0.7337 | 0.9992 | 0.9920 | 0.9997 |
75
 
76
 
77
  ### Framework versions
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amnasaeed100/FineTuning-ADE-Repeatedfold/runs/lvieenf2)
20
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amnasaeed100/FineTuning-ADE-Repeatedfold/runs/fgis28rc)
21
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amnasaeed100/FineTuning-ADE-Repeatedfold/runs/9tw0vsla)
22
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amnasaeed100/FineTuning-ADE-Repeatedfold/runs/ccjl3n87)
 
 
 
23
  # fold_3
24
 
25
  This model is a fine-tuned version of [Amna100/PreTraining-MLM](https://huggingface.co/Amna100/PreTraining-MLM) on the None dataset.
26
  It achieves the following results on the evaluation set:
27
+ - Loss: 0.0107
28
+ - Precision: 0.7923
29
+ - Recall: 0.6297
30
+ - F1: 0.7017
31
+ - Accuracy: 0.9993
32
+ - Roc Auc: 0.9951
33
+ - Pr Auc: 0.9999
34
 
35
  ## Model description
36
 
 
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Roc Auc | Pr Auc |
63
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------:|:------:|
64
+ | 0.0275 | 1.0 | 632 | 0.0138 | 0.6206 | 0.4976 | 0.5524 | 0.9991 | 0.9926 | 0.9998 |
65
+ | 0.0096 | 2.0 | 1264 | 0.0136 | 0.5756 | 0.7358 | 0.6460 | 0.9991 | 0.9958 | 0.9998 |
66
+ | 0.006 | 3.0 | 1896 | 0.0107 | 0.7923 | 0.6297 | 0.7017 | 0.9993 | 0.9951 | 0.9999 |
67
+ | 0.0023 | 4.0 | 2528 | 0.0137 | 0.7813 | 0.6910 | 0.7334 | 0.9994 | 0.9898 | 0.9998 |
68
+ | 0.0011 | 5.0 | 3160 | 0.0141 | 0.7978 | 0.6887 | 0.7392 | 0.9994 | 0.9943 | 0.9999 |
69
+ | 0.001 | 6.0 | 3792 | 0.0159 | 0.7812 | 0.7075 | 0.7426 | 0.9993 | 0.9865 | 0.9998 |
 
 
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6cc7f0c12633671cbf45e1768f723f73315e1f807c2f12d5a2d5d5645a3fde3
3
  size 554446244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f599f8ceea6cb1933781563e847023b2e7476f9aceabc51ae24fbffa7bc891
3
  size 554446244