Hugging Face's logo

rharris117
/
git-base-pokemon

Image-Text-to-Text
Transformers
PyTorch
TensorBoard
Safetensors
git
Generated from Trainer
Model card Files
xet
Metrics Community
rharris117 commited on
Commit
4c943ea
·
1 Parent(s): d398b9a

Model save

Browse files
Files changed (3) hide show
  1. README.md +16 -15
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
  This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
  - Loss: 0.0362
19
- - Wer Score: 1.9038
20
 
21
  ## Model description
22
 
@@ -44,28 +44,29 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - num_epochs: 50
 
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
51
  |:-------------:|:-----:|:----:|:---------------:|:---------:|
52
- | 7.303 | 4.17 | 50 | 4.4592 | 8.1747 |
53
- | 2.2819 | 8.33 | 100 | 0.4176 | 7.8949 |
54
- | 0.1266 | 12.5 | 150 | 0.0331 | 0.4367 |
55
- | 0.0158 | 16.67 | 200 | 0.0292 | 1.3658 |
56
- | 0.0045 | 20.83 | 250 | 0.0340 | 2.0152 |
57
- | 0.0023 | 25.0 | 300 | 0.0349 | 2.2013 |
58
- | 0.0016 | 29.17 | 350 | 0.0350 | 2.6532 |
59
- | 0.0013 | 33.33 | 400 | 0.0356 | 2.1709 |
60
- | 0.0012 | 37.5 | 450 | 0.0357 | 2.0532 |
61
- | 0.0011 | 41.67 | 500 | 0.0360 | 2.1177 |
62
- | 0.001 | 45.83 | 550 | 0.0360 | 1.9127 |
63
- | 0.001 | 50.0 | 600 | 0.0362 | 1.9038 |
64
 
65
 
66
  ### Framework versions
67
 
68
- - Transformers 4.34.0
69
  - Pytorch 2.1.0+cu121
70
  - Datasets 2.14.7
71
- - Tokenizers 0.14.1
 
16
  This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
  - Loss: 0.0362
19
+ - Wer Score: 3.5483
20
 
21
  ## Model description
22
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - num_epochs: 50
47
+ - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
52
  |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
+ | 7.2786 | 4.17 | 50 | 4.4614 | 21.6293 |
54
+ | 2.2929 | 8.33 | 100 | 0.4321 | 12.5212 |
55
+ | 0.1294 | 12.5 | 150 | 0.0356 | 1.1338 |
56
+ | 0.0142 | 16.67 | 200 | 0.0332 | 4.6898 |
57
+ | 0.0039 | 20.83 | 250 | 0.0339 | 3.2767 |
58
+ | 0.0021 | 25.0 | 300 | 0.0349 | 3.9781 |
59
+ | 0.0016 | 29.17 | 350 | 0.0354 | 3.8867 |
60
+ | 0.0013 | 33.33 | 400 | 0.0359 | 3.6744 |
61
+ | 0.0012 | 37.5 | 450 | 0.0360 | 3.6564 |
62
+ | 0.0011 | 41.67 | 500 | 0.0363 | 3.4659 |
63
+ | 0.001 | 45.83 | 550 | 0.0363 | 3.5495 |
64
+ | 0.001 | 50.0 | 600 | 0.0362 | 3.5483 |
65
 
66
 
67
  ### Framework versions
68
 
69
+ - Transformers 4.36.2
70
  - Pytorch 2.1.0+cu121
71
  - Datasets 2.14.7
72
+ - Tokenizers 0.15.0
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 101,
4
  "eos_token_id": 102,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.34.0"
7
  }
 
3
  "bos_token_id": 101,
4
  "eos_token_id": 102,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.36.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:668064e90d6d4bbad9e96f04957de2d7335dea57cb0bfcb50a3b40cf96dfb5b5
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f222a8ede5d1e4558721ca76a4c389fc3f8c4e07da0fa5b4fffdcea80b0e87
3
  size 706516040