Hugging Face's logo

ooliverz
/
git-large-r-coco-IDB_ADv1_COCOv6-rv2

Image-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Model card Files Metrics Community
ooliverz commited on
Commit
940d2d9
·
verified ·
1 Parent(s): f785cc8

End of training

Browse files
Files changed (4) hide show
  1. README.md +214 -0
  2. generation_config.json +7 -0
  3. model.safetensors +1 -1
  4. runs/Jul17_20-31-43_OZPC/events.out.tfevents.1752805911.OZPC.23060.0 +2 -2
README.md ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/git-large-r-coco
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ model-index:
10
+ - name: git-large-r-coco-IDB_ADv1_COCOv6-rv2
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # git-large-r-coco-IDB_ADv1_COCOv6-rv2
18
+
19
+ This model is a fine-tuned version of [microsoft/git-large-r-coco](https://huggingface.co/microsoft/git-large-r-coco) on the imagefolder dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0562
22
+ - Meteor Score: {'meteor': 0.6854432045391942}
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
+ - train_batch_size: 6
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 24
47
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine_with_restarts
49
+ - lr_scheduler_warmup_steps: 15
50
+ - num_epochs: 250
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Meteor Score |
56
+ |:-------------:|:--------:|:----:|:---------------:|:-------------------------------:|
57
+ | 46.026 | 1.5385 | 5 | 11.3774 | {'meteor': 0.05088714844688596} |
58
+ | 41.6878 | 3.0769 | 10 | 9.6334 | {'meteor': 0.05193787687993993} |
59
+ | 38.0023 | 4.6154 | 15 | 8.8416 | {'meteor': 0.07106313249972736} |
60
+ | 34.067 | 6.1538 | 20 | 7.7779 | {'meteor': 0.07158293882919625} |
61
+ | 30.2747 | 7.6923 | 25 | 6.9889 | {'meteor': 0.08590984809221183} |
62
+ | 27.3711 | 9.2308 | 30 | 6.3494 | {'meteor': 0.14479869967756545} |
63
+ | 24.9649 | 10.7692 | 35 | 5.7517 | {'meteor': 0.16695219166518863} |
64
+ | 22.6772 | 12.3077 | 40 | 5.1726 | {'meteor': 0.29661551096386696} |
65
+ | 20.2788 | 13.8462 | 45 | 4.6056 | {'meteor': 0.4011995652548773} |
66
+ | 18.0862 | 15.3846 | 50 | 4.0436 | {'meteor': 0.4115578798833052} |
67
+ | 15.8365 | 16.9231 | 55 | 3.4858 | {'meteor': 0.44510778846575855} |
68
+ | 13.6319 | 18.4615 | 60 | 2.9356 | {'meteor': 0.4586674871529475} |
69
+ | 11.4894 | 20.0 | 65 | 2.3989 | {'meteor': 0.4717170244373202} |
70
+ | 9.3617 | 21.5385 | 70 | 1.8855 | {'meteor': 0.4752386861645344} |
71
+ | 7.3203 | 23.0769 | 75 | 1.4120 | {'meteor': 0.48201666726951187} |
72
+ | 5.4859 | 24.6154 | 80 | 0.9993 | {'meteor': 0.486282552361079} |
73
+ | 3.8702 | 26.1538 | 85 | 0.6672 | {'meteor': 0.49594611513353365} |
74
+ | 2.6478 | 27.6923 | 90 | 0.4243 | {'meteor': 0.5382779195282617} |
75
+ | 1.6473 | 29.2308 | 95 | 0.2634 | {'meteor': 0.558817288226803} |
76
+ | 1.0753 | 30.7692 | 100 | 0.1644 | {'meteor': 0.5843576345268957} |
77
+ | 0.6843 | 32.3077 | 105 | 0.1147 | {'meteor': 0.5924151890140636} |
78
+ | 0.4652 | 33.8462 | 110 | 0.0754 | {'meteor': 0.5959032639443036} |
79
+ | 0.2912 | 35.3846 | 115 | 0.0561 | {'meteor': 0.6601199915025338} |
80
+ | 0.2564 | 36.9231 | 120 | 0.0578 | {'meteor': 0.5909665046931879} |
81
+ | 0.1751 | 38.4615 | 125 | 0.0435 | {'meteor': 0.5748658205681807} |
82
+ | 0.1192 | 40.0 | 130 | 0.0384 | {'meteor': 0.5848408474038058} |
83
+ | 0.0987 | 41.5385 | 135 | 0.0383 | {'meteor': 0.8046547926731353} |
84
+ | 0.0842 | 43.0769 | 140 | 0.0365 | {'meteor': 0.572425517722608} |
85
+ | 0.064 | 44.6154 | 145 | 0.0380 | {'meteor': 0.5707872460600325} |
86
+ | 0.0621 | 46.1538 | 150 | 0.0381 | {'meteor': 0.6246946049122446} |
87
+ | 0.0496 | 47.6923 | 155 | 0.0363 | {'meteor': 0.5572132897597559} |
88
+ | 0.0442 | 49.2308 | 160 | 0.0369 | {'meteor': 0.5474106491110476} |
89
+ | 0.04 | 50.7692 | 165 | 0.0370 | {'meteor': 0.5483744828996165} |
90
+ | 0.035 | 52.3077 | 170 | 0.0378 | {'meteor': 0.588307720981884} |
91
+ | 0.0362 | 53.8462 | 175 | 0.0386 | {'meteor': 0.5649523271276219} |
92
+ | 0.0331 | 55.3846 | 180 | 0.0373 | {'meteor': 0.5718803899947165} |
93
+ | 0.0325 | 56.9231 | 185 | 0.0361 | {'meteor': 0.5761223485127048} |
94
+ | 0.029 | 58.4615 | 190 | 0.0367 | {'meteor': 0.5675804653306711} |
95
+ | 0.0271 | 60.0 | 195 | 0.0375 | {'meteor': 0.5644692070507746} |
96
+ | 0.0262 | 61.5385 | 200 | 0.0373 | {'meteor': 0.5842776065293741} |
97
+ | 0.0269 | 63.0769 | 205 | 0.0374 | {'meteor': 0.5943250777114298} |
98
+ | 0.0253 | 64.6154 | 210 | 0.0385 | {'meteor': 0.5977497567755445} |
99
+ | 0.0282 | 66.1538 | 215 | 0.0387 | {'meteor': 0.580357812042276} |
100
+ | 0.024 | 67.6923 | 220 | 0.0406 | {'meteor': 0.5907528267445488} |
101
+ | 0.0275 | 69.2308 | 225 | 0.0389 | {'meteor': 0.5894449671022485} |
102
+ | 0.0247 | 70.7692 | 230 | 0.0397 | {'meteor': 0.6073460683162627} |
103
+ | 0.0257 | 72.3077 | 235 | 0.0404 | {'meteor': 0.6053564983740379} |
104
+ | 0.0245 | 73.8462 | 240 | 0.0404 | {'meteor': 0.5872634486208339} |
105
+ | 0.0224 | 75.3846 | 245 | 0.0408 | {'meteor': 0.5799506119739742} |
106
+ | 0.0227 | 76.9231 | 250 | 0.0399 | {'meteor': 0.5927459291222391} |
107
+ | 0.0222 | 78.4615 | 255 | 0.0409 | {'meteor': 0.5738392966875464} |
108
+ | 0.0205 | 80.0 | 260 | 0.0412 | {'meteor': 0.5769466116635588} |
109
+ | 0.0203 | 81.5385 | 265 | 0.0429 | {'meteor': 0.5942867488871455} |
110
+ | 0.0192 | 83.0769 | 270 | 0.0428 | {'meteor': 0.567709705729504} |
111
+ | 0.0186 | 84.6154 | 275 | 0.0409 | {'meteor': 0.6105469316602737} |
112
+ | 0.0182 | 86.1538 | 280 | 0.0421 | {'meteor': 0.6271779272454462} |
113
+ | 0.0149 | 87.6923 | 285 | 0.0428 | {'meteor': 0.6486679889311551} |
114
+ | 0.0143 | 89.2308 | 290 | 0.0439 | {'meteor': 0.6574516821312635} |
115
+ | 0.0156 | 90.7692 | 295 | 0.0448 | {'meteor': 0.6551861131146999} |
116
+ | 0.0141 | 92.3077 | 300 | 0.0461 | {'meteor': 0.6836597527939646} |
117
+ | 0.0161 | 93.8462 | 305 | 0.0451 | {'meteor': 0.5792770442276292} |
118
+ | 0.0148 | 95.3846 | 310 | 0.0454 | {'meteor': 0.5805499899344333} |
119
+ | 0.0149 | 96.9231 | 315 | 0.0459 | {'meteor': 0.5840463038906877} |
120
+ | 0.0119 | 98.4615 | 320 | 0.0457 | {'meteor': 0.6423925591085345} |
121
+ | 0.0101 | 100.0 | 325 | 0.0469 | {'meteor': 0.648657500717218} |
122
+ | 0.0102 | 101.5385 | 330 | 0.0477 | {'meteor': 0.6548160286104844} |
123
+ | 0.0093 | 103.0769 | 335 | 0.0496 | {'meteor': 0.6598075629219063} |
124
+ | 0.008 | 104.6154 | 340 | 0.0504 | {'meteor': 0.6442515463118447} |
125
+ | 0.0071 | 106.1538 | 345 | 0.0491 | {'meteor': 0.6406633137185896} |
126
+ | 0.0061 | 107.6923 | 350 | 0.0512 | {'meteor': 0.6466090119249169} |
127
+ | 0.0054 | 109.2308 | 355 | 0.0505 | {'meteor': 0.641863940194757} |
128
+ | 0.0052 | 110.7692 | 360 | 0.0520 | {'meteor': 0.6761788186217903} |
129
+ | 0.0047 | 112.3077 | 365 | 0.0499 | {'meteor': 0.6885671179281707} |
130
+ | 0.006 | 113.8462 | 370 | 0.0527 | {'meteor': 0.6808393937100298} |
131
+ | 0.0049 | 115.3846 | 375 | 0.0513 | {'meteor': 0.6908413583555519} |
132
+ | 0.0037 | 116.9231 | 380 | 0.0518 | {'meteor': 0.6409631450941362} |
133
+ | 0.0037 | 118.4615 | 385 | 0.0533 | {'meteor': 0.6514537532385479} |
134
+ | 0.004 | 120.0 | 390 | 0.0518 | {'meteor': 0.6544197813728431} |
135
+ | 0.0027 | 121.5385 | 395 | 0.0526 | {'meteor': 0.6388186435412143} |
136
+ | 0.0027 | 123.0769 | 400 | 0.0537 | {'meteor': 0.665650431188932} |
137
+ | 0.0022 | 124.6154 | 405 | 0.0535 | {'meteor': 0.6355591650827974} |
138
+ | 0.002 | 126.1538 | 410 | 0.0552 | {'meteor': 0.6678358007579323} |
139
+ | 0.0022 | 127.6923 | 415 | 0.0556 | {'meteor': 0.6796121441261359} |
140
+ | 0.0019 | 129.2308 | 420 | 0.0553 | {'meteor': 0.6608598185540852} |
141
+ | 0.0018 | 130.7692 | 425 | 0.0550 | {'meteor': 0.6586368510244033} |
142
+ | 0.0018 | 132.3077 | 430 | 0.0553 | {'meteor': 0.6639901408782352} |
143
+ | 0.0017 | 133.8462 | 435 | 0.0556 | {'meteor': 0.6562165511086661} |
144
+ | 0.0016 | 135.3846 | 440 | 0.0557 | {'meteor': 0.6448202417404666} |
145
+ | 0.0016 | 136.9231 | 445 | 0.0558 | {'meteor': 0.64710008953244} |
146
+ | 0.0016 | 138.4615 | 450 | 0.0560 | {'meteor': 0.6577135107336829} |
147
+ | 0.0016 | 140.0 | 455 | 0.0561 | {'meteor': 0.66889495248023} |
148
+ | 0.0016 | 141.5385 | 460 | 0.0560 | {'meteor': 0.67202651497677} |
149
+ | 0.0016 | 143.0769 | 465 | 0.0559 | {'meteor': 0.6743446360550206} |
150
+ | 0.0016 | 144.6154 | 470 | 0.0558 | {'meteor': 0.6744510467744238} |
151
+ | 0.0015 | 146.1538 | 475 | 0.0556 | {'meteor': 0.6722527142138234} |
152
+ | 0.0015 | 147.6923 | 480 | 0.0556 | {'meteor': 0.6683674950712598} |
153
+ | 0.0015 | 149.2308 | 485 | 0.0557 | {'meteor': 0.6679976104591758} |
154
+ | 0.0015 | 150.7692 | 490 | 0.0558 | {'meteor': 0.668944017355972} |
155
+ | 0.0015 | 152.3077 | 495 | 0.0559 | {'meteor': 0.6690020191026127} |
156
+ | 0.0015 | 153.8462 | 500 | 0.0559 | {'meteor': 0.6708222623224297} |
157
+ | 0.0015 | 155.3846 | 505 | 0.0559 | {'meteor': 0.6711871050474919} |
158
+ | 0.0014 | 156.9231 | 510 | 0.0559 | {'meteor': 0.67132026161785} |
159
+ | 0.0015 | 158.4615 | 515 | 0.0559 | {'meteor': 0.6729876732575589} |
160
+ | 0.0014 | 160.0 | 520 | 0.0559 | {'meteor': 0.6741118962721234} |
161
+ | 0.0014 | 161.5385 | 525 | 0.0558 | {'meteor': 0.67568339360887} |
162
+ | 0.0014 | 163.0769 | 530 | 0.0558 | {'meteor': 0.6773855597376159} |
163
+ | 0.0014 | 164.6154 | 535 | 0.0557 | {'meteor': 0.6781045908798891} |
164
+ | 0.0014 | 166.1538 | 540 | 0.0557 | {'meteor': 0.675177627685291} |
165
+ | 0.0014 | 167.6923 | 545 | 0.0558 | {'meteor': 0.6753527282763256} |
166
+ | 0.0014 | 169.2308 | 550 | 0.0559 | {'meteor': 0.6782811108562654} |
167
+ | 0.0014 | 170.7692 | 555 | 0.0560 | {'meteor': 0.677637698755014} |
168
+ | 0.0014 | 172.3077 | 560 | 0.0560 | {'meteor': 0.6776245866213522} |
169
+ | 0.0014 | 173.8462 | 565 | 0.0561 | {'meteor': 0.6774040781251898} |
170
+ | 0.0014 | 175.3846 | 570 | 0.0560 | {'meteor': 0.6770094023097326} |
171
+ | 0.0014 | 176.9231 | 575 | 0.0560 | {'meteor': 0.6762372567103689} |
172
+ | 0.0014 | 178.4615 | 580 | 0.0560 | {'meteor': 0.6766565944173913} |
173
+ | 0.0014 | 180.0 | 585 | 0.0560 | {'meteor': 0.6765455231787992} |
174
+ | 0.0014 | 181.5385 | 590 | 0.0560 | {'meteor': 0.6756097354879012} |
175
+ | 0.0013 | 183.0769 | 595 | 0.0560 | {'meteor': 0.6753887356118259} |
176
+ | 0.0013 | 184.6154 | 600 | 0.0560 | {'meteor': 0.6763324975755339} |
177
+ | 0.0014 | 186.1538 | 605 | 0.0560 | {'meteor': 0.6772080508755527} |
178
+ | 0.0014 | 187.6923 | 610 | 0.0561 | {'meteor': 0.6782436365897533} |
179
+ | 0.0014 | 189.2308 | 615 | 0.0561 | {'meteor': 0.67960672490007} |
180
+ | 0.0013 | 190.7692 | 620 | 0.0561 | {'meteor': 0.681546292616501} |
181
+ | 0.0014 | 192.3077 | 625 | 0.0561 | {'meteor': 0.682163842150726} |
182
+ | 0.0014 | 193.8462 | 630 | 0.0561 | {'meteor': 0.6825819961946236} |
183
+ | 0.0013 | 195.3846 | 635 | 0.0561 | {'meteor': 0.6825568341398264} |
184
+ | 0.0014 | 196.9231 | 640 | 0.0562 | {'meteor': 0.6831512952725652} |
185
+ | 0.0013 | 198.4615 | 645 | 0.0562 | {'meteor': 0.6844159259835707} |
186
+ | 0.0013 | 200.0 | 650 | 0.0562 | {'meteor': 0.6847053542663126} |
187
+ | 0.0013 | 201.5385 | 655 | 0.0562 | {'meteor': 0.6846814142939927} |
188
+ | 0.0013 | 203.0769 | 660 | 0.0562 | {'meteor': 0.684929233491412} |
189
+ | 0.0013 | 204.6154 | 665 | 0.0562 | {'meteor': 0.6849484299274977} |
190
+ | 0.0014 | 206.1538 | 670 | 0.0562 | {'meteor': 0.6845109878486707} |
191
+ | 0.0013 | 207.6923 | 675 | 0.0562 | {'meteor': 0.684688580357372} |
192
+ | 0.0013 | 209.2308 | 680 | 0.0562 | {'meteor': 0.6846340094956547} |
193
+ | 0.0014 | 210.7692 | 685 | 0.0562 | {'meteor': 0.6854646963875228} |
194
+ | 0.0013 | 212.3077 | 690 | 0.0562 | {'meteor': 0.6849762161382118} |
195
+ | 0.0013 | 213.8462 | 695 | 0.0562 | {'meteor': 0.685499068377835} |
196
+ | 0.0013 | 215.3846 | 700 | 0.0562 | {'meteor': 0.6857857422415214} |
197
+ | 0.0014 | 216.9231 | 705 | 0.0562 | {'meteor': 0.6857307488166687} |
198
+ | 0.0014 | 218.4615 | 710 | 0.0562 | {'meteor': 0.685411285579246} |
199
+ | 0.0014 | 220.0 | 715 | 0.0562 | {'meteor': 0.6853985828745355} |
200
+ | 0.0013 | 221.5385 | 720 | 0.0562 | {'meteor': 0.6851741738387203} |
201
+ | 0.0013 | 223.0769 | 725 | 0.0562 | {'meteor': 0.6860650447176031} |
202
+ | 0.0013 | 224.6154 | 730 | 0.0562 | {'meteor': 0.6855126499437735} |
203
+ | 0.0014 | 226.1538 | 735 | 0.0562 | {'meteor': 0.6854709168183638} |
204
+ | 0.0013 | 227.6923 | 740 | 0.0562 | {'meteor': 0.6862522303272603} |
205
+ | 0.0014 | 229.2308 | 745 | 0.0562 | {'meteor': 0.6860192747251472} |
206
+ | 0.0013 | 230.7692 | 750 | 0.0562 | {'meteor': 0.6854432045391942} |
207
+
208
+
209
+ ### Framework versions
210
+
211
+ - Transformers 4.46.1
212
+ - Pytorch 2.2.1+cu121
213
+ - Datasets 2.18.0
214
+ - Tokenizers 0.20.2
generation_config.json ADDED
@@ -0,0 +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": "4.46.1"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c0590c0c28de214b1dc8e01a65d426ff6e9e74b839cb87241781ab47687371d
3
  size 1576851440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d74fd045924c3591186798842cee51003239900089771d2ab7cd61735380a7e6
3
  size 1576851440
runs/Jul17_20-31-43_OZPC/events.out.tfevents.1752805911.OZPC.23060.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20cf2401da26c6c984665711073e185ce1e50c4707899587099f0ac70ea0e65a
3
- size 76543
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd6e21d629ef4fe08ae7ef355be9e1fca4de0c4ca579958685a8bd3fac4c572
3
+ size 77861