Hugging Face's logo

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

Image-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Model card Files Metrics Community
ooliverz commited on
Commit
60674ab
·
verified ·
1 Parent(s): 51f56d1

End of training

Browse files
Files changed (3) hide show
  1. README.md +103 -29
  2. model.safetensors +1 -1
  3. runs/Jul17_17-25-24_OZPC/events.out.tfevents.1752794807.OZPC.22492.0 +2 -2
README.md CHANGED
@@ -1,11 +1,11 @@
1
  ---
2
- base_model: microsoft/git-large-r-coco
3
- datasets:
4
- - imagefolder
5
  library_name: transformers
6
  license: mit
 
7
  tags:
8
  - generated_from_trainer
 
 
9
  model-index:
10
  - name: git-large-r-coco-IDB_ADv1_COCOv6-r
11
  results: []
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.4382
22
- - Meteor Score: {'meteor': 0.6824076148140416}
23
 
24
  ## Model description
25
 
@@ -38,38 +38,112 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 5e-05
42
- - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 42
45
- - gradient_accumulation_steps: 12
46
- - total_train_batch_size: 96
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
49
- - lr_scheduler_warmup_steps: 8
50
- - num_epochs: 80
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Meteor Score |
56
- |:-------------:|:-----:|:----:|:---------------:|:-------------------------------:|
57
- | 27.8843 | 5.0 | 5 | 2.2779 | {'meteor': 0.42881843961238963} |
58
- | 26.945 | 10.0 | 10 | 2.0505 | {'meteor': 0.501440106486018} |
59
- | 23.3885 | 15.0 | 15 | 1.7544 | {'meteor': 0.5479716568094775} |
60
- | 19.76 | 20.0 | 20 | 1.4758 | {'meteor': 0.5955711928745901} |
61
- | 16.4691 | 25.0 | 25 | 1.2338 | {'meteor': 0.6204550135358564} |
62
- | 13.6022 | 30.0 | 30 | 1.0289 | {'meteor': 0.6345912561041426} |
63
- | 11.1047 | 35.0 | 35 | 0.8510 | {'meteor': 0.6561421187912199} |
64
- | 9.0826 | 40.0 | 40 | 0.7206 | {'meteor': 0.6457048205815358} |
65
- | 7.4764 | 45.0 | 45 | 0.6199 | {'meteor': 0.6633570447161818} |
66
- | 6.2926 | 50.0 | 50 | 0.5478 | {'meteor': 0.6755789926464999} |
67
- | 5.4384 | 55.0 | 55 | 0.5033 | {'meteor': 0.6715844748121845} |
68
- | 4.8435 | 60.0 | 60 | 0.4708 | {'meteor': 0.6776793022097405} |
69
- | 4.4628 | 65.0 | 65 | 0.4527 | {'meteor': 0.6824716486996648} |
70
- | 4.2404 | 70.0 | 70 | 0.4427 | {'meteor': 0.6877583553949453} |
71
- | 4.1204 | 75.0 | 75 | 0.4396 | {'meteor': 0.683676455787374} |
72
- | 4.0752 | 80.0 | 80 | 0.4382 | {'meteor': 0.6824076148140416} |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
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-r
11
  results: []
 
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: 0.0568
22
+ - Meteor Score: {'meteor': 0.7213608939819159}
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
+ - train_batch_size: 4
43
  - eval_batch_size: 8
44
  - seed: 42
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 32
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
49
+ - lr_scheduler_warmup_steps: 15
50
+ - num_epochs: 150
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Meteor Score |
56
+ |:-------------:|:--------:|:----:|:---------------:|:--------------------------------:|
57
+ | 91.9877 | 1.4815 | 5 | 11.4608 | {'meteor': 0.046723581008416726} |
58
+ | 84.6168 | 2.9630 | 10 | 9.8170 | {'meteor': 0.043886991456607405} |
59
+ | 77.4092 | 4.4444 | 15 | 9.1821 | {'meteor': 0.06849055586443556} |
60
+ | 71.3318 | 5.9259 | 20 | 8.3193 | {'meteor': 0.061564918769236095} |
61
+ | 65.2006 | 7.4074 | 25 | 7.6103 | {'meteor': 0.0754162033563066} |
62
+ | 60.1084 | 8.8889 | 30 | 7.0968 | {'meteor': 0.1078676449812926} |
63
+ | 56.3449 | 10.3704 | 35 | 6.6624 | {'meteor': 0.16409628582839803} |
64
+ | 53.0194 | 11.8519 | 40 | 6.2707 | {'meteor': 0.17640875038111917} |
65
+ | 49.885 | 13.3333 | 45 | 5.9076 | {'meteor': 0.20852663016362413} |
66
+ | 47.1535 | 14.8148 | 50 | 5.5612 | {'meteor': 0.21135425345585648} |
67
+ | 44.3251 | 16.2963 | 55 | 5.2211 | {'meteor': 0.25163567787871793} |
68
+ | 41.4631 | 17.7778 | 60 | 4.8845 | {'meteor': 0.36102118410159373} |
69
+ | 38.8862 | 19.2593 | 65 | 4.5516 | {'meteor': 0.40677731182809435} |
70
+ | 36.2603 | 20.7407 | 70 | 4.2228 | {'meteor': 0.42841296399868456} |
71
+ | 33.5914 | 22.2222 | 75 | 3.8960 | {'meteor': 0.4442706614076698} |
72
+ | 31.0193 | 23.7037 | 80 | 3.5716 | {'meteor': 0.44790686728484286} |
73
+ | 28.4252 | 25.1852 | 85 | 3.2513 | {'meteor': 0.4634788207419503} |
74
+ | 25.927 | 26.6667 | 90 | 2.9379 | {'meteor': 0.46009853575600396} |
75
+ | 23.4406 | 28.1481 | 95 | 2.6312 | {'meteor': 0.4702576268818571} |
76
+ | 21.0641 | 29.6296 | 100 | 2.3319 | {'meteor': 0.4724561426359612} |
77
+ | 18.6236 | 31.1111 | 105 | 2.0445 | {'meteor': 0.4759864205500001} |
78
+ | 16.4033 | 32.5926 | 110 | 1.7706 | {'meteor': 0.4905426072931855} |
79
+ | 14.1917 | 34.0741 | 115 | 1.5119 | {'meteor': 0.48899836960829424} |
80
+ | 12.1305 | 35.5556 | 120 | 1.2729 | {'meteor': 0.5241780827869041} |
81
+ | 10.2674 | 37.0370 | 125 | 1.0567 | {'meteor': 0.5097833762351499} |
82
+ | 8.5593 | 38.5185 | 130 | 0.8637 | {'meteor': 0.4997929450485001} |
83
+ | 7.013 | 40.0 | 135 | 0.6974 | {'meteor': 0.5105554674131357} |
84
+ | 5.666 | 41.4815 | 140 | 0.5584 | {'meteor': 0.5152670866288012} |
85
+ | 4.5962 | 42.9630 | 145 | 0.4444 | {'meteor': 0.5396604542862918} |
86
+ | 3.6125 | 44.4444 | 150 | 0.3520 | {'meteor': 0.5617093146804203} |
87
+ | 2.9293 | 45.9259 | 155 | 0.2796 | {'meteor': 0.5886004681488384} |
88
+ | 2.259 | 47.4074 | 160 | 0.2219 | {'meteor': 0.553105842439049} |
89
+ | 1.8309 | 48.8889 | 165 | 0.1785 | {'meteor': 0.5814978557330325} |
90
+ | 1.4494 | 50.3704 | 170 | 0.1458 | {'meteor': 0.6231566268972263} |
91
+ | 1.1158 | 51.8519 | 175 | 0.1248 | {'meteor': 0.6099620120504717} |
92
+ | 0.9661 | 53.3333 | 180 | 0.1060 | {'meteor': 0.6546451210304227} |
93
+ | 0.7271 | 54.8148 | 185 | 0.0880 | {'meteor': 0.6338177371529071} |
94
+ | 0.6177 | 56.2963 | 190 | 0.0775 | {'meteor': 0.6518057184133086} |
95
+ | 0.4962 | 57.7778 | 195 | 0.0698 | {'meteor': 0.6193332334649128} |
96
+ | 0.4415 | 59.2593 | 200 | 0.0652 | {'meteor': 0.7079004093008636} |
97
+ | 0.3629 | 60.7407 | 205 | 0.0632 | {'meteor': 0.6940804620155375} |
98
+ | 0.3219 | 62.2222 | 210 | 0.0595 | {'meteor': 0.6912091264820688} |
99
+ | 0.2679 | 63.7037 | 215 | 0.0545 | {'meteor': 0.7030913652832623} |
100
+ | 0.234 | 65.1852 | 220 | 0.0537 | {'meteor': 0.6676437817167338} |
101
+ | 0.2026 | 66.6667 | 225 | 0.0534 | {'meteor': 0.6811270764539213} |
102
+ | 0.1843 | 68.1481 | 230 | 0.0515 | {'meteor': 0.6779206905106651} |
103
+ | 0.1662 | 69.6296 | 235 | 0.0511 | {'meteor': 0.715690856984691} |
104
+ | 0.1432 | 71.1111 | 240 | 0.0502 | {'meteor': 0.7156957872649886} |
105
+ | 0.1331 | 72.5926 | 245 | 0.0495 | {'meteor': 0.6543089583737782} |
106
+ | 0.1156 | 74.0741 | 250 | 0.0494 | {'meteor': 0.6594307549550437} |
107
+ | 0.1021 | 75.5556 | 255 | 0.0485 | {'meteor': 0.6576803078677578} |
108
+ | 0.092 | 77.0370 | 260 | 0.0487 | {'meteor': 0.6811188428011016} |
109
+ | 0.0809 | 78.5185 | 265 | 0.0498 | {'meteor': 0.7035441241921582} |
110
+ | 0.0723 | 80.0 | 270 | 0.0506 | {'meteor': 0.7038905922785134} |
111
+ | 0.0649 | 81.4815 | 275 | 0.0502 | {'meteor': 0.7421547726024114} |
112
+ | 0.0608 | 82.9630 | 280 | 0.0507 | {'meteor': 0.730981066765409} |
113
+ | 0.0491 | 84.4444 | 285 | 0.0518 | {'meteor': 0.7443890531705978} |
114
+ | 0.0458 | 85.9259 | 290 | 0.0534 | {'meteor': 0.7176754184986865} |
115
+ | 0.0388 | 87.4074 | 295 | 0.0523 | {'meteor': 0.7176410382626139} |
116
+ | 0.0334 | 88.8889 | 300 | 0.0534 | {'meteor': 0.7026151957465668} |
117
+ | 0.026 | 90.3704 | 305 | 0.0520 | {'meteor': 0.7362294347533668} |
118
+ | 0.0241 | 91.8519 | 310 | 0.0531 | {'meteor': 0.7236102999038347} |
119
+ | 0.0211 | 93.3333 | 315 | 0.0542 | {'meteor': 0.7152270797326922} |
120
+ | 0.0182 | 94.8148 | 320 | 0.0547 | {'meteor': 0.7175103144573044} |
121
+ | 0.0175 | 96.2963 | 325 | 0.0547 | {'meteor': 0.7140333983909092} |
122
+ | 0.0158 | 97.7778 | 330 | 0.0558 | {'meteor': 0.7230279458318826} |
123
+ | 0.0153 | 99.2593 | 335 | 0.0560 | {'meteor': 0.7216506562988318} |
124
+ | 0.0133 | 100.7407 | 340 | 0.0558 | {'meteor': 0.7089953285495003} |
125
+ | 0.0137 | 102.2222 | 345 | 0.0557 | {'meteor': 0.7050918755935003} |
126
+ | 0.0127 | 103.7037 | 350 | 0.0561 | {'meteor': 0.7140423279140877} |
127
+ | 0.0118 | 105.1852 | 355 | 0.0563 | {'meteor': 0.716693515553002} |
128
+ | 0.0121 | 106.6667 | 360 | 0.0559 | {'meteor': 0.7213321747823379} |
129
+ | 0.0115 | 108.1481 | 365 | 0.0559 | {'meteor': 0.7244157912903824} |
130
+ | 0.0107 | 109.6296 | 370 | 0.0559 | {'meteor': 0.7258048026400388} |
131
+ | 0.0115 | 111.1111 | 375 | 0.0562 | {'meteor': 0.7249978244263323} |
132
+ | 0.0107 | 112.5926 | 380 | 0.0564 | {'meteor': 0.7261256725269803} |
133
+ | 0.0103 | 114.0741 | 385 | 0.0565 | {'meteor': 0.7222910388476055} |
134
+ | 0.0102 | 115.5556 | 390 | 0.0567 | {'meteor': 0.7209011950646473} |
135
+ | 0.0099 | 117.0370 | 395 | 0.0567 | {'meteor': 0.7221559565497234} |
136
+ | 0.0101 | 118.5185 | 400 | 0.0567 | {'meteor': 0.7234189947956161} |
137
+ | 0.0096 | 120.0 | 405 | 0.0567 | {'meteor': 0.7231619412067093} |
138
+ | 0.0097 | 121.4815 | 410 | 0.0567 | {'meteor': 0.7224063072061223} |
139
+ | 0.0103 | 122.9630 | 415 | 0.0567 | {'meteor': 0.7209850209026843} |
140
+ | 0.0101 | 124.4444 | 420 | 0.0567 | {'meteor': 0.7208576227726795} |
141
+ | 0.0095 | 125.9259 | 425 | 0.0567 | {'meteor': 0.7215621466948617} |
142
+ | 0.0093 | 127.4074 | 430 | 0.0568 | {'meteor': 0.7221874032851583} |
143
+ | 0.01 | 128.8889 | 435 | 0.0568 | {'meteor': 0.7207488272286875} |
144
+ | 0.0097 | 130.3704 | 440 | 0.0568 | {'meteor': 0.7213694074696705} |
145
+ | 0.0096 | 131.8519 | 445 | 0.0568 | {'meteor': 0.7213044564985146} |
146
+ | 0.0099 | 133.3333 | 450 | 0.0568 | {'meteor': 0.7213608939819159} |
147
 
148
 
149
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b17bb62f0a4f8ba81aa3b41d9103f9ca31adfb68227e7e95f0ca57cbe5ef45b4
3
  size 1576851440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4119def1891dd3656dd17da6b0a085be72af9da0fece23366636a71cc1bd4931
3
  size 1576851440
runs/Jul17_17-25-24_OZPC/events.out.tfevents.1752794807.OZPC.22492.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b814a451daa1eb71e63bb2286db958e39cc70d87081d4fb610e8a73263f60ef0
3
- size 48085
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c31c849e151742faa4423d232c4b21e8fcc55b629e4f95d88e171059aca411e
3
+ size 48921