ChiJuiChen commited on
Commit
71f579e
·
verified ·
1 Parent(s): a30a3e2

End of training

Browse files
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
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: 0.0551
19
- - Wer Score: 9.8
20
 
21
  ## Model description
22
 
@@ -43,26 +43,39 @@ The following hyperparameters were used during training:
43
  - total_train_batch_size: 4
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
- | 5.6909 | 3.7037 | 50 | 2.9342 | 11.0167 |
54
- | 1.1195 | 7.4074 | 100 | 0.1202 | 11.05 |
55
- | 0.036 | 11.1111 | 150 | 0.0471 | 0.3833 |
56
- | 0.0128 | 14.8148 | 200 | 0.0492 | 0.45 |
57
- | 0.0101 | 18.5185 | 250 | 0.0508 | 4.35 |
58
- | 0.0087 | 22.2222 | 300 | 0.0501 | 9.4 |
59
- | 0.0081 | 25.9259 | 350 | 0.0531 | 10.35 |
60
- | 0.0075 | 29.6296 | 400 | 0.0535 | 9.7833 |
61
- | 0.0068 | 33.3333 | 450 | 0.0525 | 7.0333 |
62
- | 0.0064 | 37.0370 | 500 | 0.0545 | 9.7333 |
63
- | 0.0059 | 40.7407 | 550 | 0.0537 | 9.7333 |
64
- | 0.0055 | 44.4444 | 600 | 0.0550 | 9.7833 |
65
- | 0.0051 | 48.1481 | 650 | 0.0551 | 9.8 |
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
15
 
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: 0.0698
19
+ - Wer Score: 5.7759
20
 
21
  ## Model description
22
 
 
43
  - total_train_batch_size: 4
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 100
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
52
  |:-------------:|:-------:|:----:|:---------------:|:---------:|
53
+ | 7.3056 | 3.7037 | 50 | 4.4313 | 24.2069 |
54
+ | 2.1534 | 7.4074 | 100 | 0.3158 | 0.4310 |
55
+ | 0.0855 | 11.1111 | 150 | 0.0458 | 0.4655 |
56
+ | 0.0153 | 14.8148 | 200 | 0.0447 | 0.4655 |
57
+ | 0.0109 | 18.5185 | 250 | 0.0492 | 0.4483 |
58
+ | 0.0098 | 22.2222 | 300 | 0.0529 | 0.4483 |
59
+ | 0.0077 | 25.9259 | 350 | 0.0547 | 0.4828 |
60
+ | 0.0069 | 29.6296 | 400 | 0.0567 | 0.4483 |
61
+ | 0.0058 | 33.3333 | 450 | 0.0595 | 0.7414 |
62
+ | 0.0042 | 37.0370 | 500 | 0.0620 | 2.5517 |
63
+ | 0.0036 | 40.7407 | 550 | 0.0654 | 3.1379 |
64
+ | 0.0032 | 44.4444 | 600 | 0.0614 | 9.7414 |
65
+ | 0.0026 | 48.1481 | 650 | 0.0664 | 6.5517 |
66
+ | 0.001 | 51.8519 | 700 | 0.0670 | 7.4828 |
67
+ | 0.0006 | 55.5556 | 750 | 0.0662 | 7.5172 |
68
+ | 0.0006 | 59.2593 | 800 | 0.0670 | 8.7586 |
69
+ | 0.0003 | 62.9630 | 850 | 0.0678 | 7.7414 |
70
+ | 0.0003 | 66.6667 | 900 | 0.0685 | 6.7931 |
71
+ | 0.0002 | 70.3704 | 950 | 0.0688 | 6.3103 |
72
+ | 0.0002 | 74.0741 | 1000 | 0.0689 | 6.4828 |
73
+ | 0.0002 | 77.7778 | 1050 | 0.0691 | 6.1724 |
74
+ | 0.0002 | 81.4815 | 1100 | 0.0694 | 6.0862 |
75
+ | 0.0002 | 85.1852 | 1150 | 0.0695 | 6.1034 |
76
+ | 0.0002 | 88.8889 | 1200 | 0.0697 | 5.9828 |
77
+ | 0.0002 | 92.5926 | 1250 | 0.0698 | 5.8276 |
78
+ | 0.0002 | 96.2963 | 1300 | 0.0698 | 5.7759 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4f4fe91804172b0696138babf54513804180778f7af402675f995f3ed9caa44
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e410f8fa5526e707c372586b996052716c25122f3412770f6e7793eec46b8b8d
3
  size 706516040
runs/May30_13-50-15_pcslab-MS-7A69/events.out.tfevents.1717048219.pcslab-MS-7A69.64042.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6c7ecfafc182bccc68b2989f36d59546e8d9f940d9980be985d25ff3da8be72
3
- size 17782
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c61cca209550a44755a1d9946d9550a7d47f4874d731c9d9bb81c72012af5b4
3
+ size 19206