Hugging Face's logo

ssalvo41
/
git-base-isg-288

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ssalvo41 commited on
Commit
9935ef9
·
verified ·
1 Parent(s): 1d32d73

End of training

Browse files
Files changed (2) hide show
  1. README.md +21 -13
  2. model.safetensors +1 -1
README.md CHANGED
@@ -5,19 +5,19 @@ base_model: microsoft/git-base
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
- - name: git-base-isg
9
  results: []
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
- # git-base-isg
16
 
17
  This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0798
20
- - Wer Score: 0.7179
21
 
22
  ## Model description
23
 
@@ -44,20 +44,28 @@ The following hyperparameters were used during training:
44
  - total_train_batch_size: 32
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
- - num_epochs: 50
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
52
  |:-------------:|:-------:|:----:|:---------------:|:---------:|
53
- | 13.5743 | 5.5882 | 50 | 4.4421 | 13.5929 |
54
- | 4.5444 | 11.1176 | 100 | 0.6092 | 10.0286 |
55
- | 0.4155 | 16.7059 | 150 | 0.0805 | 0.675 |
56
- | 0.0714 | 22.2353 | 200 | 0.0755 | 0.7179 |
57
- | 0.0427 | 27.8235 | 250 | 0.0777 | 0.7214 |
58
- | 0.0332 | 33.3529 | 300 | 0.0794 | 0.6786 |
59
- | 0.0287 | 38.9412 | 350 | 0.0799 | 0.7107 |
60
- | 0.0251 | 44.4706 | 400 | 0.0798 | 0.7179 |
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: git-base-isg-288
9
  results: []
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
+ # git-base-isg-288
16
 
17
  This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0937
20
+ - Wer Score: 2.7076
21
 
22
  ## Model description
23
 
 
44
  - total_train_batch_size: 32
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 100
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
52
  |:-------------:|:-------:|:----:|:---------------:|:---------:|
53
+ | 13.4828 | 5.5882 | 50 | 4.2850 | 16.7473 |
54
+ | 3.9992 | 11.1176 | 100 | 0.3655 | 0.7942 |
55
+ | 0.2368 | 16.7059 | 150 | 0.0692 | 0.6679 |
56
+ | 0.0533 | 22.2353 | 200 | 0.0733 | 0.7004 |
57
+ | 0.0339 | 27.8235 | 250 | 0.0765 | 0.8520 |
58
+ | 0.0249 | 33.3529 | 300 | 0.0795 | 1.8592 |
59
+ | 0.0165 | 38.9412 | 350 | 0.0821 | 2.3827 |
60
+ | 0.0074 | 44.4706 | 400 | 0.0861 | 2.0542 |
61
+ | 0.0034 | 50.0 | 450 | 0.0885 | 3.0361 |
62
+ | 0.0023 | 55.5882 | 500 | 0.0909 | 2.4946 |
63
+ | 0.0018 | 61.1176 | 550 | 0.0920 | 2.6426 |
64
+ | 0.0016 | 66.7059 | 600 | 0.0930 | 2.6354 |
65
+ | 0.0015 | 72.2353 | 650 | 0.0930 | 2.2527 |
66
+ | 0.0013 | 77.8235 | 700 | 0.0935 | 2.6859 |
67
+ | 0.0013 | 83.3529 | 750 | 0.0937 | 2.7726 |
68
+ | 0.0012 | 88.9412 | 800 | 0.0937 | 2.7076 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d86a5899d41f5fe59749b9696d5dd53b8b52e71323b1fe8d61a8c71d9537b9e6
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fc2dd0c3cfafbae6b063031ae96ad1c2cbbae6ef7aac0cfad4b139fc2742b64
3
  size 706516040