Hugging Face's logo

ChiJuiChen
/
GenerativeImage2Text-naruto

Image-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Model card Files
xet
Metrics Community
ChiJuiChen commited on
Commit
8ea5893
·
verified ·
1 Parent(s): fb7c050

End of training

Browse files
Files changed (3) hide show
  1. README.md +92 -29
  2. model.safetensors +1 -1
  3. runs/May30_14-11-54_pcslab-MS-7A69/events.out.tfevents.1717049514.pcslab-MS-7A69.64771.0 +2 -2
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: 0.0698
19
- - Wer Score: 5.7759
20
 
21
  ## Model description
22
 
@@ -43,39 +43,102 @@ 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: 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
 
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: 0.0424
19
+ - Wer Score: 20.4909
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: 30
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer Score |
52
  |:-------------:|:-------:|:----:|:---------------:|:---------:|
53
+ | 7.2788 | 0.3344 | 50 | 4.3352 | 10.2091 |
54
+ | 2.0251 | 0.6689 | 100 | 0.2388 | 0.5182 |
55
+ | 0.0807 | 1.0033 | 150 | 0.0401 | 0.5091 |
56
+ | 0.0303 | 1.3378 | 200 | 0.0333 | 0.4455 |
57
+ | 0.0284 | 1.6722 | 250 | 0.0324 | 1.1273 |
58
+ | 0.0287 | 2.0067 | 300 | 0.0316 | 23.6909 |
59
+ | 0.0239 | 2.3411 | 350 | 0.0331 | 23.7455 |
60
+ | 0.022 | 2.6756 | 400 | 0.0328 | 23.7364 |
61
+ | 0.0236 | 3.0100 | 450 | 0.0317 | 23.7 |
62
+ | 0.0208 | 3.3445 | 500 | 0.0325 | 23.7636 |
63
+ | 0.0206 | 3.6789 | 550 | 0.0324 | 19.4 |
64
+ | 0.0214 | 4.0134 | 600 | 0.0320 | 23.6818 |
65
+ | 0.0183 | 4.3478 | 650 | 0.0318 | 23.5636 |
66
+ | 0.0194 | 4.6823 | 700 | 0.0314 | 23.7 |
67
+ | 0.0203 | 5.0167 | 750 | 0.0339 | 23.7182 |
68
+ | 0.0179 | 5.3512 | 800 | 0.0307 | 23.6909 |
69
+ | 0.0178 | 5.6856 | 850 | 0.0323 | 23.7182 |
70
+ | 0.0192 | 6.0201 | 900 | 0.0323 | 23.7273 |
71
+ | 0.0166 | 6.3545 | 950 | 0.0330 | 23.7091 |
72
+ | 0.0181 | 6.6890 | 1000 | 0.0346 | 23.7182 |
73
+ | 0.0176 | 7.0234 | 1050 | 0.0335 | 23.7 |
74
+ | 0.016 | 7.3579 | 1100 | 0.0357 | 23.7182 |
75
+ | 0.0167 | 7.6923 | 1150 | 0.0341 | 23.7 |
76
+ | 0.0165 | 8.0268 | 1200 | 0.0341 | 23.6727 |
77
+ | 0.0152 | 8.3612 | 1250 | 0.0356 | 23.6727 |
78
+ | 0.0158 | 8.6957 | 1300 | 0.0327 | 23.6273 |
79
+ | 0.0158 | 9.0301 | 1350 | 0.0352 | 23.6909 |
80
+ | 0.0148 | 9.3645 | 1400 | 0.0350 | 23.6909 |
81
+ | 0.0153 | 9.6990 | 1450 | 0.0348 | 23.5182 |
82
+ | 0.0153 | 10.0334 | 1500 | 0.0349 | 23.6818 |
83
+ | 0.0142 | 10.3679 | 1550 | 0.0345 | 23.6818 |
84
+ | 0.0143 | 10.7023 | 1600 | 0.0340 | 23.5727 |
85
+ | 0.0152 | 11.0368 | 1650 | 0.0341 | 23.6818 |
86
+ | 0.0137 | 11.3712 | 1700 | 0.0374 | 23.6818 |
87
+ | 0.0142 | 11.7057 | 1750 | 0.0324 | 23.6545 |
88
+ | 0.0141 | 12.0401 | 1800 | 0.0353 | 23.7 |
89
+ | 0.0134 | 12.3746 | 1850 | 0.0362 | 23.1545 |
90
+ | 0.0138 | 12.7090 | 1900 | 0.0357 | 23.6818 |
91
+ | 0.0138 | 13.0435 | 1950 | 0.0359 | 22.8909 |
92
+ | 0.0124 | 13.3779 | 2000 | 0.0372 | 23.4182 |
93
+ | 0.0132 | 13.7124 | 2050 | 0.0370 | 23.6909 |
94
+ | 0.0137 | 14.0468 | 2100 | 0.0380 | 23.7182 |
95
+ | 0.0118 | 14.3813 | 2150 | 0.0358 | 23.6545 |
96
+ | 0.0129 | 14.7157 | 2200 | 0.0376 | 23.6909 |
97
+ | 0.013 | 15.0502 | 2250 | 0.0379 | 23.4636 |
98
+ | 0.0115 | 15.3846 | 2300 | 0.0384 | 23.3909 |
99
+ | 0.0125 | 15.7191 | 2350 | 0.0369 | 23.2364 |
100
+ | 0.0126 | 16.0535 | 2400 | 0.0392 | 22.8545 |
101
+ | 0.0115 | 16.3880 | 2450 | 0.0379 | 23.0455 |
102
+ | 0.0118 | 16.7224 | 2500 | 0.0384 | 22.9455 |
103
+ | 0.0119 | 17.0569 | 2550 | 0.0371 | 23.5636 |
104
+ | 0.0108 | 17.3913 | 2600 | 0.0383 | 23.6455 |
105
+ | 0.0116 | 17.7258 | 2650 | 0.0378 | 23.6818 |
106
+ | 0.0114 | 18.0602 | 2700 | 0.0391 | 23.2091 |
107
+ | 0.0101 | 18.3946 | 2750 | 0.0399 | 22.1545 |
108
+ | 0.0113 | 18.7291 | 2800 | 0.0398 | 23.7182 |
109
+ | 0.0108 | 19.0635 | 2850 | 0.0389 | 23.0 |
110
+ | 0.01 | 19.3980 | 2900 | 0.0382 | 22.0818 |
111
+ | 0.0107 | 19.7324 | 2950 | 0.0392 | 22.8636 |
112
+ | 0.0109 | 20.0669 | 3000 | 0.0399 | 23.1091 |
113
+ | 0.0096 | 20.4013 | 3050 | 0.0404 | 22.7273 |
114
+ | 0.01 | 20.7358 | 3100 | 0.0398 | 22.3364 |
115
+ | 0.0102 | 21.0702 | 3150 | 0.0402 | 22.3636 |
116
+ | 0.0092 | 21.4047 | 3200 | 0.0395 | 21.7636 |
117
+ | 0.0096 | 21.7391 | 3250 | 0.0396 | 21.8727 |
118
+ | 0.0095 | 22.0736 | 3300 | 0.0394 | 21.4909 |
119
+ | 0.0089 | 22.4080 | 3350 | 0.0407 | 20.3455 |
120
+ | 0.009 | 22.7425 | 3400 | 0.0390 | 21.3727 |
121
+ | 0.009 | 23.0769 | 3450 | 0.0398 | 20.9273 |
122
+ | 0.0085 | 23.4114 | 3500 | 0.0406 | 20.8364 |
123
+ | 0.0087 | 23.7458 | 3550 | 0.0399 | 21.8727 |
124
+ | 0.0086 | 24.0803 | 3600 | 0.0409 | 20.9818 |
125
+ | 0.0082 | 24.4147 | 3650 | 0.0412 | 20.8455 |
126
+ | 0.0082 | 24.7492 | 3700 | 0.0406 | 21.5273 |
127
+ | 0.0083 | 25.0836 | 3750 | 0.0409 | 21.4545 |
128
+ | 0.008 | 25.4181 | 3800 | 0.0408 | 21.2818 |
129
+ | 0.0077 | 25.7525 | 3850 | 0.0414 | 21.1273 |
130
+ | 0.0075 | 26.0870 | 3900 | 0.0422 | 21.6727 |
131
+ | 0.007 | 26.4214 | 3950 | 0.0421 | 20.6636 |
132
+ | 0.0074 | 26.7559 | 4000 | 0.0428 | 21.2818 |
133
+ | 0.0072 | 27.0903 | 4050 | 0.0429 | 20.8 |
134
+ | 0.0066 | 27.4247 | 4100 | 0.0424 | 19.6182 |
135
+ | 0.0066 | 27.7592 | 4150 | 0.0423 | 19.9364 |
136
+ | 0.0066 | 28.0936 | 4200 | 0.0423 | 20.8636 |
137
+ | 0.0059 | 28.4281 | 4250 | 0.0425 | 20.6545 |
138
+ | 0.0066 | 28.7625 | 4300 | 0.0422 | 20.4909 |
139
+ | 0.0065 | 29.0970 | 4350 | 0.0423 | 20.5091 |
140
+ | 0.0061 | 29.4314 | 4400 | 0.0423 | 20.5 |
141
+ | 0.0058 | 29.7659 | 4450 | 0.0424 | 20.4909 |
142
 
143
 
144
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8ca1705a33946c6619a27bf77289a431a78c92be1ea1549cc812574cae1986e
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d331d7062cf6d4ab657291fe32691a94b71b37da7156a8166df2ce140e03b01d
3
  size 706516040
runs/May30_14-11-54_pcslab-MS-7A69/events.out.tfevents.1717049514.pcslab-MS-7A69.64771.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eae8e8b760d8217b6cc6695c76c3670465c7a04ce410a2a5bf1513377240fadf
3
- size 52556
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9128acd0fba09ae09703bb49cfb85345eef24d9ab2aea2afd00676c8082ea4e
3
+ size 52910