Hugging Face's logo

Trkkk
/
git-base-bdd100k

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Trkkk commited on
Commit
d719d45
·
verified ·
1 Parent(s): 9d24982

End of training

Browse files
Files changed (3) hide show
  1. README.md +56 -161
  2. generation_config.json +7 -7
  3. runs/Dec29_23-39-48_4d6eb9645fff/events.out.tfevents.1735515589.4d6eb9645fff.11139.0 +2 -2
README.md CHANGED
@@ -1,161 +1,56 @@
1
- ---
2
- library_name: transformers
3
- license: mit
4
- base_model: microsoft/git-base
5
- tags:
6
- - generated_from_trainer
7
- model-index:
8
- - name: git-base-bdd100k
9
- results: []
10
- ---
11
-
12
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
- should probably proofread and complete it, then remove this comment. -->
14
-
15
- # git-base-bdd100k
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: 0.4069
20
- - Wer Score: 1.7469
21
-
22
- ## Model description
23
-
24
- More information needed
25
-
26
- ## Intended uses & limitations
27
-
28
- More information needed
29
-
30
- ## Training and evaluation data
31
-
32
- More information needed
33
-
34
- ## Training procedure
35
-
36
- ### Training hyperparameters
37
-
38
- The following hyperparameters were used during training:
39
- - learning_rate: 5e-05
40
- - train_batch_size: 35
41
- - eval_batch_size: 35
42
- - seed: 42
43
- - gradient_accumulation_steps: 2
44
- - total_train_batch_size: 70
45
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
- - lr_scheduler_type: linear
47
- - num_epochs: 100
48
- - mixed_precision_training: Native AMP
49
-
50
- ### Training results
51
-
52
- | Training Loss | Epoch | Step | Validation Loss | Wer Score |
53
- |:-------------:|:-----:|:----:|:---------------:|:---------:|
54
- | 10.5843 | 1.0 | 3 | 9.3667 | 6.8626 |
55
- | 9.2401 | 2.0 | 6 | 8.8728 | 6.9596 |
56
- | 8.7545 | 3.0 | 9 | 8.2995 | 3.9543 |
57
- | 8.2253 | 4.0 | 12 | 7.8495 | 6.1327 |
58
- | 7.815 | 5.0 | 15 | 7.4921 | 6.4292 |
59
- | 7.4785 | 6.0 | 18 | 7.1823 | 5.6943 |
60
- | 7.1794 | 7.0 | 21 | 6.8969 | 6.7444 |
61
- | 6.9018 | 8.0 | 24 | 6.6233 | 7.2815 |
62
- | 6.633 | 9.0 | 27 | 6.3577 | 6.2946 |
63
- | 6.3716 | 10.0 | 30 | 6.0982 | 3.9794 |
64
- | 6.1145 | 11.0 | 33 | 5.8410 | 1.7244 |
65
- | 5.8587 | 12.0 | 36 | 5.5841 | 1.3375 |
66
- | 5.6036 | 13.0 | 39 | 5.3301 | 1.2846 |
67
- | 5.3508 | 14.0 | 42 | 5.0789 | 1.2795 |
68
- | 5.1004 | 15.0 | 45 | 4.8313 | 1.2645 |
69
- | 4.8522 | 16.0 | 48 | 4.5858 | 1.3498 |
70
- | 4.607 | 17.0 | 51 | 4.3436 | 1.3841 |
71
- | 4.363 | 18.0 | 54 | 4.1048 | 1.3598 |
72
- | 4.1205 | 19.0 | 57 | 3.8677 | 1.3941 |
73
- | 3.8822 | 20.0 | 60 | 3.6347 | 1.4838 |
74
- | 3.6467 | 21.0 | 63 | 3.4047 | 1.5396 |
75
- | 3.4146 | 22.0 | 66 | 3.1813 | 1.5850 |
76
- | 3.1857 | 23.0 | 69 | 2.9609 | 1.5897 |
77
- | 2.9594 | 24.0 | 72 | 2.7443 | 1.7628 |
78
- | 2.7404 | 25.0 | 75 | 2.5347 | 1.7511 |
79
- | 2.5251 | 26.0 | 78 | 2.3310 | 1.8832 |
80
- | 2.3179 | 27.0 | 81 | 2.1342 | 1.8400 |
81
- | 2.1174 | 28.0 | 84 | 1.9478 | 1.8548 |
82
- | 1.9222 | 29.0 | 87 | 1.7691 | 1.8977 |
83
- | 1.7389 | 30.0 | 90 | 1.6009 | 1.9543 |
84
- | 1.5638 | 31.0 | 93 | 1.4450 | 2.1109 |
85
- | 1.4006 | 32.0 | 96 | 1.3019 | 2.0713 |
86
- | 1.2486 | 33.0 | 99 | 1.1684 | 2.2235 |
87
- | 1.1087 | 34.0 | 102 | 1.0515 | 1.9969 |
88
- | 0.9815 | 35.0 | 105 | 0.9437 | 2.1112 |
89
- | 0.8688 | 36.0 | 108 | 0.8525 | 2.1831 |
90
- | 0.766 | 37.0 | 111 | 0.7711 | 2.0917 |
91
- | 0.6799 | 38.0 | 114 | 0.7014 | 2.2617 |
92
- | 0.6043 | 39.0 | 117 | 0.6455 | 2.3133 |
93
- | 0.5357 | 40.0 | 120 | 0.5936 | 1.9220 |
94
- | 0.4756 | 41.0 | 123 | 0.5531 | 2.4083 |
95
- | 0.424 | 42.0 | 126 | 0.5178 | 2.1998 |
96
- | 0.3795 | 43.0 | 129 | 0.4884 | 2.2793 |
97
- | 0.3425 | 44.0 | 132 | 0.4695 | 2.2614 |
98
- | 0.3132 | 45.0 | 135 | 0.4543 | 2.1388 |
99
- | 0.2835 | 46.0 | 138 | 0.4319 | 2.2199 |
100
- | 0.2573 | 47.0 | 141 | 0.4201 | 1.9774 |
101
- | 0.2339 | 48.0 | 144 | 0.4066 | 2.4571 |
102
- | 0.2144 | 49.0 | 147 | 0.4033 | 1.7444 |
103
- | 0.1966 | 50.0 | 150 | 0.3948 | 2.3091 |
104
- | 0.1811 | 51.0 | 153 | 0.3861 | 1.9247 |
105
- | 0.1687 | 52.0 | 156 | 0.3846 | 2.1204 |
106
- | 0.1549 | 53.0 | 159 | 0.3833 | 2.0151 |
107
- | 0.1441 | 54.0 | 162 | 0.3762 | 1.8776 |
108
- | 0.1339 | 55.0 | 165 | 0.3786 | 1.8495 |
109
- | 0.1231 | 56.0 | 168 | 0.3776 | 2.0407 |
110
- | 0.1123 | 57.0 | 171 | 0.3757 | 2.0056 |
111
- | 0.1042 | 58.0 | 174 | 0.3772 | 1.7985 |
112
- | 0.0957 | 59.0 | 177 | 0.3776 | 1.9055 |
113
- | 0.0881 | 60.0 | 180 | 0.3764 | 1.8409 |
114
- | 0.0801 | 61.0 | 183 | 0.3811 | 1.9128 |
115
- | 0.0743 | 62.0 | 186 | 0.3796 | 1.6321 |
116
- | 0.0693 | 63.0 | 189 | 0.3778 | 1.7338 |
117
- | 0.0634 | 64.0 | 192 | 0.3818 | 1.8191 |
118
- | 0.0594 | 65.0 | 195 | 0.3834 | 1.7001 |
119
- | 0.0543 | 66.0 | 198 | 0.3770 | 1.7305 |
120
- | 0.0506 | 67.0 | 201 | 0.3835 | 1.7450 |
121
- | 0.0466 | 68.0 | 204 | 0.3867 | 1.6380 |
122
- | 0.0447 | 69.0 | 207 | 0.3875 | 1.7717 |
123
- | 0.0413 | 70.0 | 210 | 0.3879 | 1.7280 |
124
- | 0.0395 | 71.0 | 213 | 0.3899 | 1.6834 |
125
- | 0.0366 | 72.0 | 216 | 0.3897 | 1.8994 |
126
- | 0.0352 | 73.0 | 219 | 0.3913 | 1.8119 |
127
- | 0.0326 | 74.0 | 222 | 0.3931 | 1.7511 |
128
- | 0.0314 | 75.0 | 225 | 0.3925 | 1.7907 |
129
- | 0.0298 | 76.0 | 228 | 0.3966 | 1.7662 |
130
- | 0.0287 | 77.0 | 231 | 0.3940 | 1.7327 |
131
- | 0.0272 | 78.0 | 234 | 0.3963 | 1.7745 |
132
- | 0.0267 | 79.0 | 237 | 0.3995 | 1.8200 |
133
- | 0.0253 | 80.0 | 240 | 0.3991 | 1.7899 |
134
- | 0.0249 | 81.0 | 243 | 0.4008 | 1.7910 |
135
- | 0.0237 | 82.0 | 246 | 0.3997 | 1.8565 |
136
- | 0.0231 | 83.0 | 249 | 0.4015 | 1.7687 |
137
- | 0.0225 | 84.0 | 252 | 0.4015 | 1.7093 |
138
- | 0.0217 | 85.0 | 255 | 0.4012 | 1.7667 |
139
- | 0.0212 | 86.0 | 258 | 0.4024 | 1.7938 |
140
- | 0.0205 | 87.0 | 261 | 0.4037 | 1.7821 |
141
- | 0.0203 | 88.0 | 264 | 0.4041 | 1.8085 |
142
- | 0.02 | 89.0 | 267 | 0.4041 | 1.8275 |
143
- | 0.0193 | 90.0 | 270 | 0.4051 | 1.7912 |
144
- | 0.0192 | 91.0 | 273 | 0.4059 | 1.7508 |
145
- | 0.0188 | 92.0 | 276 | 0.4059 | 1.7355 |
146
- | 0.0185 | 93.0 | 279 | 0.4055 | 1.7322 |
147
- | 0.0183 | 94.0 | 282 | 0.4055 | 1.7255 |
148
- | 0.0181 | 95.0 | 285 | 0.4060 | 1.7302 |
149
- | 0.0177 | 96.0 | 288 | 0.4065 | 1.7414 |
150
- | 0.0174 | 97.0 | 291 | 0.4067 | 1.7483 |
151
- | 0.0177 | 98.0 | 294 | 0.4069 | 1.7464 |
152
- | 0.0174 | 99.0 | 297 | 0.4069 | 1.7489 |
153
- | 0.0175 | 100.0 | 300 | 0.4069 | 1.7469 |
154
-
155
-
156
- ### Framework versions
157
-
158
- - Transformers 4.45.2
159
- - Pytorch 2.5.0+cu124
160
- - Datasets 3.0.2
161
- - Tokenizers 0.20.1
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/git-base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: git-base-bdd100k
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # git-base-bdd100k
16
+
17
+ This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 2
41
+ - total_train_batch_size: 16
42
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 15
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.47.1
54
+ - Pytorch 2.5.1+cu121
55
+ - Datasets 3.2.0
56
+ - Tokenizers 0.21.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json CHANGED
@@ -1,7 +1,7 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 101,
4
- "eos_token_id": 102,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.45.2"
7
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 101,
4
+ "eos_token_id": 102,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.47.1"
7
+ }
runs/Dec29_23-39-48_4d6eb9645fff/events.out.tfevents.1735515589.4d6eb9645fff.11139.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f6d38ccbcb89197812f472ad3b66ec1c7635e8f289b73676a602360e0239938
3
- size 8463
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ba7b73a23cf14d04fcaa9f5bd6ca0709c87fa475362f66910fbbf60b306083
3
+ size 8817