Hugging Face's logo

isabelkim
/
git-base-pokemon

Image-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Model card Files
xet
Metrics Community
isabelkim commited on
Commit
5820a8c
·
verified ·
1 Parent(s): 0c48245

End of training

Browse files
Files changed (3) hide show
  1. README.md +21 -9
  2. model.safetensors +1 -1
  3. runs/Oct02_05-00-35_67bb1d30543c/events.out.tfevents.1727845239.67bb1d30543c.706.11 +2 -2
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.0431
20
- - Wer Score: 1.1979
21
 
22
  ## Model description
23
 
@@ -37,21 +37,33 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 5e-05
40
- - train_batch_size: 8
41
- - eval_batch_size: 8
42
  - seed: 42
43
  - gradient_accumulation_steps: 2
44
- - total_train_batch_size: 16
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 10
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer Score |
53
- |:-------------:|:------:|:----:|:---------------:|:---------:|
54
- | 0.0043 | 8.3333 | 50 | 0.0431 | 1.1979 |
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
 
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: 0.0627
20
+ - Wer Score: 8.5567
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 5e-05
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 4
42
  - seed: 42
43
  - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 8
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 30
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer Score |
53
+ |:-------------:|:-------:|:----:|:---------------:|:---------:|
54
+ | 2.2863 | 2.1277 | 50 | 0.3771 | 0.4680 |
55
+ | 0.1088 | 4.2553 | 100 | 0.0445 | 0.4631 |
56
+ | 0.0219 | 6.3830 | 150 | 0.0438 | 0.4483 |
57
+ | 0.0152 | 8.5106 | 200 | 0.0437 | 0.4532 |
58
+ | 0.0124 | 10.6383 | 250 | 0.0474 | 0.4877 |
59
+ | 0.0101 | 12.7660 | 300 | 0.0499 | 2.7241 |
60
+ | 0.008 | 14.8936 | 350 | 0.0512 | 4.0493 |
61
+ | 0.0064 | 17.0213 | 400 | 0.0535 | 5.2857 |
62
+ | 0.0039 | 19.1489 | 450 | 0.0574 | 7.3103 |
63
+ | 0.0025 | 21.2766 | 500 | 0.0587 | 7.6847 |
64
+ | 0.0015 | 23.4043 | 550 | 0.0620 | 8.0443 |
65
+ | 0.0011 | 25.5319 | 600 | 0.0617 | 9.0788 |
66
+ | 0.0009 | 27.6596 | 650 | 0.0627 | 8.5567 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b36584469887ae33939a1e5197f8c5a8797640436d90e398b9600251eba097b
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b54c4ee58e89c866217abb67359b3b31b46e252d9a28b6540dc55576b03e572e
3
  size 706516040
runs/Oct02_05-00-35_67bb1d30543c/events.out.tfevents.1727845239.67bb1d30543c.706.11 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:102467b5c3fa1194b9061216af7a3388aef320f04cb7ccb4e188282fc84bc57e
3
- size 12062
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea8a31a71dfdffb77d5382a7a138ee62f07911f817507eae643a7a426fef065
3
+ size 12416