Hugging Face's logo

ooliverz
/
git-large-r-coco-IDB_ADv1_COCOv4

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Model card Files Metrics Community
ooliverz commited on
Commit
e3cf02b
·
verified ·
1 Parent(s): ff15f62

End of training

Browse files
Files changed (1) hide show
  1. README.md +46 -46
README.md CHANGED
@@ -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: 4.8925
22
- - Meteor Score: {'meteor': 0.49738575469694446}
23
 
24
  ## Model description
25
 
@@ -42,8 +42,8 @@ The following hyperparameters were used during training:
42
  - train_batch_size: 128
43
  - eval_batch_size: 128
44
  - seed: 42
45
- - gradient_accumulation_steps: 32
46
- - total_train_batch_size: 4096
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: 500
@@ -52,48 +52,48 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Meteor Score |
56
- |:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|
57
- | 11.5498 | 5.0 | 5 | 11.6368 | {'meteor': 0.04057736839473623} |
58
- | 11.5396 | 10.0 | 10 | 11.5854 | {'meteor': 0.04210192880646877} |
59
- | 11.3968 | 15.0 | 15 | 10.9694 | {'meteor': 0.04885116407250206} |
60
- | 10.7679 | 20.0 | 20 | 10.3653 | {'meteor': 0.04171232748864934} |
61
- | 10.2996 | 25.0 | 25 | 10.1527 | {'meteor': 0.03915047079432611} |
62
- | 10.087 | 30.0 | 30 | 9.9125 | {'meteor': 0.03866636323496256} |
63
- | 9.8783 | 35.0 | 35 | 9.6739 | {'meteor': 0.044214535908854505} |
64
- | 9.6578 | 40.0 | 40 | 9.4339 | {'meteor': 0.05733813462913385} |
65
- | 9.4429 | 45.0 | 45 | 9.2090 | {'meteor': 0.0636647048537248} |
66
- | 9.2341 | 50.0 | 50 | 9.0053 | {'meteor': 0.06677407453205089} |
67
- | 9.0339 | 55.0 | 55 | 8.8031 | {'meteor': 0.06645317953768891} |
68
- | 8.8446 | 60.0 | 60 | 8.6144 | {'meteor': 0.06658107336980087} |
69
- | 8.6628 | 65.0 | 65 | 8.4298 | {'meteor': 0.06651694418226604} |
70
- | 8.4847 | 70.0 | 70 | 8.2459 | {'meteor': 0.07565438732128155} |
71
- | 8.3094 | 75.0 | 75 | 8.0639 | {'meteor': 0.08184129209195753} |
72
- | 8.1399 | 80.0 | 80 | 7.8926 | {'meteor': 0.0864126929837702} |
73
- | 7.976 | 85.0 | 85 | 7.7308 | {'meteor': 0.09471633023590777} |
74
- | 7.8252 | 90.0 | 90 | 7.5844 | {'meteor': 0.10421409652325833} |
75
- | 7.681 | 95.0 | 95 | 7.4421 | {'meteor': 0.1065553432613849} |
76
- | 7.5468 | 100.0 | 100 | 7.3095 | {'meteor': 0.11355806803783441} |
77
- | 7.4168 | 105.0 | 105 | 7.1903 | {'meteor': 0.14908623263393064} |
78
- | 7.2919 | 110.0 | 110 | 7.0671 | {'meteor': 0.17284710379866022} |
79
- | 7.1721 | 115.0 | 115 | 6.9458 | {'meteor': 0.19076241982732184} |
80
- | 7.0521 | 120.0 | 120 | 6.8317 | {'meteor': 0.19635863400135706} |
81
- | 6.9362 | 125.0 | 125 | 6.7196 | {'meteor': 0.2017261622184529} |
82
- | 6.8222 | 130.0 | 130 | 6.6086 | {'meteor': 0.20636072449739054} |
83
- | 6.7065 | 135.0 | 135 | 6.4999 | {'meteor': 0.20994549164361168} |
84
- | 6.5983 | 140.0 | 140 | 6.3877 | {'meteor': 0.22359260559859548} |
85
- | 6.4816 | 145.0 | 145 | 6.2813 | {'meteor': 0.22323979120192516} |
86
- | 6.3655 | 150.0 | 150 | 6.1633 | {'meteor': 0.2684308873626845} |
87
- | 6.2467 | 155.0 | 155 | 6.0486 | {'meteor': 0.2524548427830646} |
88
- | 6.1265 | 160.0 | 160 | 5.9288 | {'meteor': 0.3122403391680057} |
89
- | 6.0037 | 165.0 | 165 | 5.8089 | {'meteor': 0.3349654611963042} |
90
- | 5.8805 | 170.0 | 170 | 5.6851 | {'meteor': 0.3851037886544085} |
91
- | 5.7527 | 175.0 | 175 | 5.5604 | {'meteor': 0.39881323064424296} |
92
- | 5.6228 | 180.0 | 180 | 5.4312 | {'meteor': 0.4647834621772476} |
93
- | 5.4903 | 185.0 | 185 | 5.3029 | {'meteor': 0.483038473685656} |
94
- | 5.3565 | 190.0 | 190 | 5.1694 | {'meteor': 0.4816435935392071} |
95
- | 5.217 | 195.0 | 195 | 5.0304 | {'meteor': 0.4984632216969969} |
96
- | 5.0758 | 200.0 | 200 | 4.8925 | {'meteor': 0.49738575469694446} |
97
 
98
 
99
  ### Framework versions
 
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: 2.3179
22
+ - Meteor Score: {'meteor': 0.5631808848167792}
23
 
24
  ## Model description
25
 
 
42
  - train_batch_size: 128
43
  - eval_batch_size: 128
44
  - seed: 42
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 256
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: 500
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Meteor Score |
56
+ |:-------------:|:-----:|:----:|:---------------:|:------------------------------:|
57
+ | 4.9891 | 5.0 | 5 | 4.8898 | {'meteor': 0.4977448904730416} |
58
+ | 4.9871 | 10.0 | 10 | 4.8871 | {'meteor': 0.4986783896823098} |
59
+ | 4.9807 | 15.0 | 15 | 4.8787 | {'meteor': 0.5039923089582024} |
60
+ | 4.9703 | 20.0 | 20 | 4.8695 | {'meteor': 0.5007229587447326} |
61
+ | 4.9552 | 25.0 | 25 | 4.8554 | {'meteor': 0.5040915299837979} |
62
+ | 4.937 | 30.0 | 30 | 4.8380 | {'meteor': 0.5048006043123706} |
63
+ | 4.9144 | 35.0 | 35 | 4.8172 | {'meteor': 0.5053354754203138} |
64
+ | 4.8884 | 40.0 | 40 | 4.7941 | {'meteor': 0.5052519582427984} |
65
+ | 4.8595 | 45.0 | 45 | 4.7648 | {'meteor': 0.5155678605148059} |
66
+ | 4.8273 | 50.0 | 50 | 4.7351 | {'meteor': 0.5141758460997891} |
67
+ | 4.7906 | 55.0 | 55 | 4.7006 | {'meteor': 0.5161210615484346} |
68
+ | 4.7514 | 60.0 | 60 | 4.6661 | {'meteor': 0.5227861070655556} |
69
+ | 4.7102 | 65.0 | 65 | 4.6277 | {'meteor': 0.5254243476755014} |
70
+ | 4.6657 | 70.0 | 70 | 4.5848 | {'meteor': 0.5268576504702123} |
71
+ | 4.6174 | 75.0 | 75 | 4.5400 | {'meteor': 0.5327203741360704} |
72
+ | 4.5668 | 80.0 | 80 | 4.4927 | {'meteor': 0.5328385720589747} |
73
+ | 4.5133 | 85.0 | 85 | 4.4344 | {'meteor': 0.5379080722700745} |
74
+ | 4.4563 | 90.0 | 90 | 4.3847 | {'meteor': 0.5351712288811252} |
75
+ | 4.3961 | 95.0 | 95 | 4.3223 | {'meteor': 0.5459124584203718} |
76
+ | 4.3328 | 100.0 | 100 | 4.2619 | {'meteor': 0.5450854025913955} |
77
+ | 4.2664 | 105.0 | 105 | 4.1984 | {'meteor': 0.5396980345283648} |
78
+ | 4.1973 | 110.0 | 110 | 4.1254 | {'meteor': 0.5436701507478281} |
79
+ | 4.1255 | 115.0 | 115 | 4.0597 | {'meteor': 0.5443380961541314} |
80
+ | 4.0497 | 120.0 | 120 | 3.9792 | {'meteor': 0.5501741486578466} |
81
+ | 3.9694 | 125.0 | 125 | 3.9008 | {'meteor': 0.549708872514102} |
82
+ | 3.8871 | 130.0 | 130 | 3.8238 | {'meteor': 0.548104982356801} |
83
+ | 3.8014 | 135.0 | 135 | 3.7364 | {'meteor': 0.5554349932565801} |
84
+ | 3.7128 | 140.0 | 140 | 3.6483 | {'meteor': 0.55742212703008} |
85
+ | 3.6206 | 145.0 | 145 | 3.5535 | {'meteor': 0.554548892112528} |
86
+ | 3.5247 | 150.0 | 150 | 3.4614 | {'meteor': 0.5577247301342534} |
87
+ | 3.4264 | 155.0 | 155 | 3.3604 | {'meteor': 0.5567178684938024} |
88
+ | 3.3247 | 160.0 | 160 | 3.2577 | {'meteor': 0.5542593803491448} |
89
+ | 3.2182 | 165.0 | 165 | 3.1494 | {'meteor': 0.5517431992593748} |
90
+ | 3.1093 | 170.0 | 170 | 3.0413 | {'meteor': 0.5609162269594461} |
91
+ | 2.997 | 175.0 | 175 | 2.9274 | {'meteor': 0.5595566101373656} |
92
+ | 2.8804 | 180.0 | 180 | 2.8130 | {'meteor': 0.5594850153568144} |
93
+ | 2.7608 | 185.0 | 185 | 2.6924 | {'meteor': 0.5605989110400809} |
94
+ | 2.6389 | 190.0 | 190 | 2.5684 | {'meteor': 0.5608506949746257} |
95
+ | 2.5144 | 195.0 | 195 | 2.4447 | {'meteor': 0.5655230759592001} |
96
+ | 2.3862 | 200.0 | 200 | 2.3179 | {'meteor': 0.5631808848167792} |
97
 
98
 
99
  ### Framework versions