Hugging Face's logo

Trkkk
/
git-base-bdd100k

Image-Text-to-Text
Transformers
Safetensors
git
Generated from Trainer
Inference Endpoints
Model card Files Community
Trkkk commited on
Commit
6787816
•
1 Parent(s): e835cf6

End of training

Browse files
Files changed (2) hide show
  1. README.md +100 -109
  2. model.safetensors +1 -1
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: 0.4161
20
- - Wer Score: 2.3730
21
 
22
  ## Model description
23
 
@@ -37,11 +37,11 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 5e-05
40
- - train_batch_size: 25
41
- - eval_batch_size: 25
42
  - seed: 42
43
  - gradient_accumulation_steps: 2
44
- - total_train_batch_size: 50
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - num_epochs: 100
@@ -49,113 +49,104 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer Score |
53
- |:-------------:|:-----:|:----:|:---------------:|:---------:|
54
- | 10.5754 | 1.0 | 3 | 9.3460 | 6.9161 |
55
- | 9.2089 | 2.0 | 6 | 8.8317 | 7.6376 |
56
- | 8.694 | 3.0 | 9 | 8.2760 | 6.6661 |
57
- | 8.1805 | 4.0 | 12 | 7.8390 | 6.1320 |
58
- | 7.7782 | 5.0 | 15 | 7.4904 | 8.3372 |
59
- | 7.4422 | 6.0 | 18 | 7.1838 | 8.7640 |
60
- | 7.1465 | 7.0 | 21 | 6.9029 | 8.6650 |
61
- | 6.8738 | 8.0 | 24 | 6.6334 | 8.4883 |
62
- | 6.6096 | 9.0 | 27 | 6.3706 | 8.4497 |
63
- | 6.3498 | 10.0 | 30 | 6.1129 | 6.2287 |
64
- | 6.0934 | 11.0 | 33 | 5.8568 | 3.5906 |
65
- | 5.8399 | 12.0 | 36 | 5.6030 | 2.8328 |
66
- | 5.5876 | 13.0 | 39 | 5.3507 | 2.8227 |
67
- | 5.3365 | 14.0 | 42 | 5.1022 | 2.7740 |
68
- | 5.0873 | 15.0 | 45 | 4.8551 | 2.7008 |
69
- | 4.8379 | 16.0 | 48 | 4.6113 | 2.5162 |
70
- | 4.592 | 17.0 | 51 | 4.3680 | 2.5235 |
71
- | 4.3471 | 18.0 | 54 | 4.1294 | 2.6834 |
72
- | 4.1038 | 19.0 | 57 | 3.8936 | 2.6583 |
73
- | 3.8678 | 20.0 | 60 | 3.6622 | 2.6454 |
74
- | 3.6309 | 21.0 | 63 | 3.4319 | 2.5201 |
75
- | 3.3979 | 22.0 | 66 | 3.2060 | 2.6728 |
76
- | 3.1669 | 23.0 | 69 | 2.9855 | 2.6611 |
77
- | 2.9417 | 24.0 | 72 | 2.7673 | 2.6023 |
78
- | 2.7208 | 25.0 | 75 | 2.5581 | 2.5034 |
79
- | 2.5046 | 26.0 | 78 | 2.3538 | 2.6320 |
80
- | 2.2961 | 27.0 | 81 | 2.1537 | 2.5414 |
81
- | 2.0931 | 28.0 | 84 | 1.9672 | 2.5682 |
82
- | 1.8979 | 29.0 | 87 | 1.7863 | 2.5207 |
83
- | 1.7123 | 30.0 | 90 | 1.6167 | 2.5872 |
84
- | 1.5355 | 31.0 | 93 | 1.4592 | 2.5900 |
85
- | 1.371 | 32.0 | 96 | 1.3143 | 2.5649 |
86
- | 1.2175 | 33.0 | 99 | 1.1803 | 2.6079 |
87
- | 1.0761 | 34.0 | 102 | 1.0583 | 2.6555 |
88
- | 0.9483 | 35.0 | 105 | 0.9517 | 2.6264 |
89
- | 0.8327 | 36.0 | 108 | 0.8592 | 2.6751 |
90
- | 0.7304 | 37.0 | 111 | 0.7763 | 2.6465 |
91
- | 0.6411 | 38.0 | 114 | 0.7093 | 2.8428 |
92
- | 0.5596 | 39.0 | 117 | 0.6482 | 2.6230 |
93
- | 0.4931 | 40.0 | 120 | 0.5953 | 2.7919 |
94
- | 0.4341 | 41.0 | 123 | 0.5551 | 2.9049 |
95
- | 0.3849 | 42.0 | 126 | 0.5176 | 2.4620 |
96
- | 0.3397 | 43.0 | 129 | 0.4873 | 2.9083 |
97
- | 0.3027 | 44.0 | 132 | 0.4661 | 2.7567 |
98
- | 0.267 | 45.0 | 135 | 0.4511 | 2.7058 |
99
- | 0.2371 | 46.0 | 138 | 0.4321 | 2.8031 |
100
- | 0.2105 | 47.0 | 141 | 0.4201 | 2.4413 |
101
- | 0.1883 | 48.0 | 144 | 0.4155 | 2.8026 |
102
- | 0.1693 | 49.0 | 147 | 0.4023 | 2.5039 |
103
- | 0.1543 | 50.0 | 150 | 0.3999 | 2.6532 |
104
- | 0.1372 | 51.0 | 153 | 0.3925 | 2.4983 |
105
- | 0.1249 | 52.0 | 156 | 0.3915 | 2.4866 |
106
- | 0.1161 | 53.0 | 159 | 0.3911 | 2.3602 |
107
- | 0.1054 | 54.0 | 162 | 0.3923 | 2.3054 |
108
- | 0.0937 | 55.0 | 165 | 0.3859 | 2.3758 |
109
- | 0.0849 | 56.0 | 168 | 0.3896 | 2.3126 |
110
- | 0.0772 | 57.0 | 171 | 0.3902 | 2.3708 |
111
- | 0.0703 | 58.0 | 174 | 0.3858 | 2.2416 |
112
- | 0.0636 | 59.0 | 177 | 0.3896 | 2.1974 |
113
- | 0.0576 | 60.0 | 180 | 0.3856 | 2.2411 |
114
- | 0.053 | 61.0 | 183 | 0.3913 | 2.3647 |
115
- | 0.0485 | 62.0 | 186 | 0.3932 | 2.2634 |
116
- | 0.0447 | 63.0 | 189 | 0.3928 | 2.3730 |
117
- | 0.0398 | 64.0 | 192 | 0.3920 | 2.4418 |
118
- | 0.0368 | 65.0 | 195 | 0.3940 | 2.3742 |
119
- | 0.0337 | 66.0 | 198 | 0.3922 | 2.2942 |
120
- | 0.032 | 67.0 | 201 | 0.3969 | 2.2634 |
121
- | 0.0293 | 68.0 | 204 | 0.3965 | 2.3026 |
122
- | 0.0276 | 69.0 | 207 | 0.3995 | 2.3859 |
123
- | 0.0258 | 70.0 | 210 | 0.4017 | 2.2668 |
124
- | 0.0245 | 71.0 | 213 | 0.4058 | 2.2332 |
125
- | 0.024 | 72.0 | 216 | 0.4019 | 2.4049 |
126
- | 0.0225 | 73.0 | 219 | 0.4058 | 2.4055 |
127
- | 0.0215 | 74.0 | 222 | 0.4048 | 2.3322 |
128
- | 0.0201 | 75.0 | 225 | 0.4058 | 2.3070 |
129
- | 0.0197 | 76.0 | 228 | 0.4071 | 2.3702 |
130
- | 0.0186 | 77.0 | 231 | 0.4061 | 2.3753 |
131
- | 0.0181 | 78.0 | 234 | 0.4076 | 2.3893 |
132
- | 0.0175 | 79.0 | 237 | 0.4091 | 2.3853 |
133
- | 0.017 | 80.0 | 240 | 0.4103 | 2.3798 |
134
- | 0.0167 | 81.0 | 243 | 0.4128 | 2.3647 |
135
- | 0.016 | 82.0 | 246 | 0.4129 | 2.3496 |
136
- | 0.0159 | 83.0 | 249 | 0.4116 | 2.3255 |
137
- | 0.0152 | 84.0 | 252 | 0.4127 | 2.3490 |
138
- | 0.0152 | 85.0 | 255 | 0.4129 | 2.3820 |
139
- | 0.0148 | 86.0 | 258 | 0.4134 | 2.3725 |
140
- | 0.0143 | 87.0 | 261 | 0.4140 | 2.3389 |
141
- | 0.0141 | 88.0 | 264 | 0.4149 | 2.3255 |
142
- | 0.0139 | 89.0 | 267 | 0.4151 | 2.3786 |
143
- | 0.0137 | 90.0 | 270 | 0.4150 | 2.4116 |
144
- | 0.0135 | 91.0 | 273 | 0.4153 | 2.4027 |
145
- | 0.0132 | 92.0 | 276 | 0.4158 | 2.4016 |
146
- | 0.0134 | 93.0 | 279 | 0.4158 | 2.3803 |
147
- | 0.0131 | 94.0 | 282 | 0.4156 | 2.3758 |
148
- | 0.0131 | 95.0 | 285 | 0.4155 | 2.3647 |
149
- | 0.013 | 96.0 | 288 | 0.4154 | 2.3669 |
150
- | 0.0128 | 97.0 | 291 | 0.4157 | 2.3602 |
151
- | 0.0127 | 98.0 | 294 | 0.4160 | 2.3669 |
152
- | 0.0127 | 99.0 | 297 | 0.4161 | 2.3730 |
153
- | 0.0127 | 100.0 | 300 | 0.4161 | 2.3730 |
154
 
155
 
156
  ### Framework versions
157
 
158
  - Transformers 4.45.2
159
- - Pytorch 2.1.0+cu118
160
- - Datasets 3.0.1
161
  - Tokenizers 0.20.1
 
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: 0.4505
20
+ - Wer Score: 2.0146
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 5e-05
40
+ - train_batch_size: 20
41
+ - eval_batch_size: 20
42
  - seed: 42
43
  - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 40
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - num_epochs: 100
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer Score |
53
+ |:-------------:|:-------:|:----:|:---------------:|:---------:|
54
+ | 10.7599 | 0.9091 | 5 | 9.0648 | 7.4053 |
55
+ | 7.8749 | 2.0 | 11 | 7.9846 | 5.4869 |
56
+ | 8.5483 | 2.9091 | 16 | 7.3958 | 5.9978 |
57
+ | 6.5899 | 4.0 | 22 | 6.8122 | 7.3117 |
58
+ | 7.3362 | 4.9091 | 27 | 6.3566 | 5.4206 |
59
+ | 5.6682 | 6.0 | 33 | 5.8240 | 2.6977 |
60
+ | 6.2659 | 6.9091 | 38 | 5.3805 | 2.3248 |
61
+ | 4.7822 | 8.0 | 44 | 4.8517 | 2.4497 |
62
+ | 5.2042 | 8.9091 | 49 | 4.4194 | 2.3350 |
63
+ | 3.9022 | 10.0 | 55 | 3.9023 | 2.0637 |
64
+ | 4.1582 | 10.9091 | 60 | 3.4813 | 2.4832 |
65
+ | 3.0413 | 12.0 | 66 | 2.9854 | 2.5313 |
66
+ | 3.1438 | 12.9091 | 71 | 2.5871 | 2.4395 |
67
+ | 2.2196 | 14.0 | 77 | 2.1313 | 2.5160 |
68
+ | 2.199 | 14.9091 | 82 | 1.7799 | 2.4064 |
69
+ | 1.4819 | 16.0 | 88 | 1.4052 | 2.3929 |
70
+ | 1.3977 | 16.9091 | 93 | 1.1385 | 2.4009 |
71
+ | 0.9006 | 18.0 | 99 | 0.8846 | 2.3711 |
72
+ | 0.8222 | 18.9091 | 104 | 0.7261 | 2.5171 |
73
+ | 0.5272 | 20.0 | 110 | 0.5892 | 2.5583 |
74
+ | 0.4908 | 20.9091 | 115 | 0.5160 | 2.5098 |
75
+ | 0.3346 | 22.0 | 121 | 0.4587 | 2.3434 |
76
+ | 0.3306 | 22.9091 | 126 | 0.4197 | 2.3015 |
77
+ | 0.2313 | 24.0 | 132 | 0.3966 | 2.0754 |
78
+ | 0.237 | 24.9091 | 137 | 0.3828 | 2.2418 |
79
+ | 0.1691 | 26.0 | 143 | 0.3792 | 1.7196 |
80
+ | 0.1745 | 26.9091 | 148 | 0.3729 | 2.2782 |
81
+ | 0.1261 | 28.0 | 154 | 0.3665 | 1.8682 |
82
+ | 0.1294 | 28.9091 | 159 | 0.3745 | 1.8237 |
83
+ | 0.0916 | 30.0 | 165 | 0.3762 | 2.3332 |
84
+ | 0.0944 | 30.9091 | 170 | 0.3758 | 1.9060 |
85
+ | 0.0682 | 32.0 | 176 | 0.3796 | 2.1471 |
86
+ | 0.0703 | 32.9091 | 181 | 0.3846 | 1.8350 |
87
+ | 0.0512 | 34.0 | 187 | 0.3891 | 2.0670 |
88
+ | 0.0537 | 34.9091 | 192 | 0.3909 | 2.0998 |
89
+ | 0.0392 | 36.0 | 198 | 0.3944 | 2.2658 |
90
+ | 0.0418 | 36.9091 | 203 | 0.3999 | 2.1865 |
91
+ | 0.0314 | 38.0 | 209 | 0.3970 | 2.2338 |
92
+ | 0.0344 | 38.9091 | 214 | 0.4057 | 2.0838 |
93
+ | 0.0252 | 40.0 | 220 | 0.4073 | 2.2542 |
94
+ | 0.0285 | 40.9091 | 225 | 0.4079 | 2.2538 |
95
+ | 0.022 | 42.0 | 231 | 0.4121 | 2.0579 |
96
+ | 0.0237 | 42.9091 | 236 | 0.4097 | 2.1475 |
97
+ | 0.0182 | 44.0 | 242 | 0.4185 | 2.1577 |
98
+ | 0.0203 | 44.9091 | 247 | 0.4151 | 2.2378 |
99
+ | 0.0157 | 46.0 | 253 | 0.4212 | 2.0703 |
100
+ | 0.0177 | 46.9091 | 258 | 0.4212 | 2.0237 |
101
+ | 0.0136 | 48.0 | 264 | 0.4208 | 1.9676 |
102
+ | 0.0155 | 48.9091 | 269 | 0.4229 | 2.0262 |
103
+ | 0.0123 | 50.0 | 275 | 0.4253 | 2.0612 |
104
+ | 0.0144 | 50.9091 | 280 | 0.4284 | 2.0663 |
105
+ | 0.0112 | 52.0 | 286 | 0.4315 | 2.0706 |
106
+ | 0.0129 | 52.9091 | 291 | 0.4301 | 2.0568 |
107
+ | 0.0107 | 54.0 | 297 | 0.4301 | 2.0087 |
108
+ | 0.0121 | 54.9091 | 302 | 0.4311 | 2.0022 |
109
+ | 0.0095 | 56.0 | 308 | 0.4313 | 1.9996 |
110
+ | 0.0109 | 56.9091 | 313 | 0.4333 | 2.0546 |
111
+ | 0.0086 | 58.0 | 319 | 0.4338 | 2.0787 |
112
+ | 0.0102 | 58.9091 | 324 | 0.4359 | 2.0091 |
113
+ | 0.0082 | 60.0 | 330 | 0.4369 | 2.0430 |
114
+ | 0.0095 | 60.9091 | 335 | 0.4366 | 1.9592 |
115
+ | 0.0076 | 62.0 | 341 | 0.4388 | 1.9905 |
116
+ | 0.0089 | 62.9091 | 346 | 0.4395 | 2.0295 |
117
+ | 0.0072 | 64.0 | 352 | 0.4404 | 2.0200 |
118
+ | 0.0084 | 64.9091 | 357 | 0.4393 | 2.0641 |
119
+ | 0.0067 | 66.0 | 363 | 0.4408 | 2.0798 |
120
+ | 0.0078 | 66.9091 | 368 | 0.4422 | 2.0601 |
121
+ | 0.0063 | 68.0 | 374 | 0.4420 | 2.0408 |
122
+ | 0.0076 | 68.9091 | 379 | 0.4427 | 2.0273 |
123
+ | 0.0063 | 70.0 | 385 | 0.4438 | 2.0306 |
124
+ | 0.0072 | 70.9091 | 390 | 0.4436 | 2.0462 |
125
+ | 0.006 | 72.0 | 396 | 0.4456 | 2.0160 |
126
+ | 0.007 | 72.9091 | 401 | 0.4472 | 2.0382 |
127
+ | 0.0057 | 74.0 | 407 | 0.4466 | 2.0532 |
128
+ | 0.0066 | 74.9091 | 412 | 0.4459 | 2.0612 |
129
+ | 0.0055 | 76.0 | 418 | 0.4469 | 2.0229 |
130
+ | 0.0065 | 76.9091 | 423 | 0.4474 | 1.9632 |
131
+ | 0.0054 | 78.0 | 429 | 0.4481 | 1.9519 |
132
+ | 0.0064 | 78.9091 | 434 | 0.4475 | 1.9836 |
133
+ | 0.0052 | 80.0 | 440 | 0.4475 | 2.0149 |
134
+ | 0.0062 | 80.9091 | 445 | 0.4482 | 2.0197 |
135
+ | 0.0052 | 82.0 | 451 | 0.4490 | 2.0208 |
136
+ | 0.0061 | 82.9091 | 456 | 0.4496 | 2.0324 |
137
+ | 0.0049 | 84.0 | 462 | 0.4498 | 2.0240 |
138
+ | 0.006 | 84.9091 | 467 | 0.4496 | 2.0168 |
139
+ | 0.0049 | 86.0 | 473 | 0.4499 | 2.0 |
140
+ | 0.0059 | 86.9091 | 478 | 0.4505 | 1.9822 |
141
+ | 0.005 | 88.0 | 484 | 0.4506 | 1.9978 |
142
+ | 0.0058 | 88.9091 | 489 | 0.4505 | 2.0117 |
143
+ | 0.0049 | 90.0 | 495 | 0.4505 | 2.0135 |
144
+ | 0.0053 | 90.9091 | 500 | 0.4505 | 2.0146 |
 
 
 
 
 
 
 
 
 
145
 
146
 
147
  ### Framework versions
148
 
149
  - Transformers 4.45.2
150
+ - Pytorch 2.1.1+cu121
151
+ - Datasets 3.0.2
152
  - Tokenizers 0.20.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:787eebe5cdd4baa3ce4bb7cde30a3784e3b8e8017a64cd3560b78fc984cc2bed
3
  size 706516040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1066ea568b9174feb002ea482b4be011852254bd38d56a3239fae07600a10b06
3
  size 706516040