Hugging Face's logo

ooliverz
/
git-large-r-coco-IDB_ADv1_COCO

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Model card Files
xet
 Metrics Community
ooliverz commited on
Commit
d0e534c
·
verified ·
1 Parent(s): 41e84b2

End of training

Browse files
Files changed (1) hide show
  1. README.md +43 -23
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: 4.7575
22
- - Meteor Score: {'meteor': 0.44741221632780354}
23
 
24
  ## Model description
25
 
@@ -46,33 +46,53 @@ The following hyperparameters were used during training:
46
  - total_train_batch_size: 1024
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
- - num_epochs: 100
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Meteor Score |
55
  |:-------------:|:-----:|:----:|:---------------:|:-------------------------------:|
56
- | 11.2864 | 5.0 | 5 | 9.7914 | {'meteor': 0.04785905013283249} |
57
- | 9.5446 | 10.0 | 10 | 8.8688 | {'meteor': 0.06898572959442757} |
58
- | 8.5964 | 15.0 | 15 | 7.9379 | {'meteor': 0.09355329647609742} |
59
- | 7.8313 | 20.0 | 20 | 7.3407 | {'meteor': 0.11334545855859698} |
60
- | 7.3003 | 25.0 | 25 | 6.9032 | {'meteor': 0.15999516391015553} |
61
- | 6.8931 | 30.0 | 30 | 6.5469 | {'meteor': 0.186323487530305} |
62
- | 6.5514 | 35.0 | 35 | 6.2431 | {'meteor': 0.21803131978135007} |
63
- | 6.2571 | 40.0 | 40 | 5.9791 | {'meteor': 0.23221717283346363} |
64
- | 5.9994 | 45.0 | 45 | 5.7449 | {'meteor': 0.2811991986842099} |
65
- | 5.7716 | 50.0 | 50 | 5.5381 | {'meteor': 0.3320404999594528} |
66
- | 5.5727 | 55.0 | 55 | 5.3578 | {'meteor': 0.38961711439431945} |
67
- | 5.4006 | 60.0 | 60 | 5.2035 | {'meteor': 0.41465764293498697} |
68
- | 5.256 | 65.0 | 65 | 5.0758 | {'meteor': 0.43295611927196415} |
69
- | 5.1374 | 70.0 | 70 | 4.9732 | {'meteor': 0.43822389602945405} |
70
- | 5.0437 | 75.0 | 75 | 4.8945 | {'meteor': 0.44028335974497207} |
71
- | 4.9731 | 80.0 | 80 | 4.8369 | {'meteor': 0.44568543666821964} |
72
- | 4.9224 | 85.0 | 85 | 4.7976 | {'meteor': 0.44726915255893274} |
73
- | 4.8891 | 90.0 | 90 | 4.7739 | {'meteor': 0.44619071947824196} |
74
- | 4.8705 | 95.0 | 95 | 4.7618 | {'meteor': 0.4463902471662178} |
75
- | 4.8613 | 100.0 | 100 | 4.7575 | {'meteor': 0.44741221632780354} |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### 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: 0.1340
22
+ - Meteor Score: {'meteor': 0.5103395242652348}
23
 
24
  ## Model description
25
 
 
46
  - total_train_batch_size: 1024
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
+ - num_epochs: 200
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Meteor Score |
55
  |:-------------:|:-----:|:----:|:---------------:|:-------------------------------:|
56
+ | 4.8755 | 5.0 | 5 | 4.6208 | {'meteor': 0.41234022080924504} |
57
+ | 4.577 | 10.0 | 10 | 4.2632 | {'meteor': 0.462553330633559} |
58
+ | 4.228 | 15.0 | 15 | 3.9351 | {'meteor': 0.4637035445872813} |
59
+ | 3.8968 | 20.0 | 20 | 3.6117 | {'meteor': 0.4716545164583618} |
60
+ | 3.5731 | 25.0 | 25 | 3.2943 | {'meteor': 0.4775515760416854} |
61
+ | 3.2551 | 30.0 | 30 | 2.9844 | {'meteor': 0.4827646049987953} |
62
+ | 2.9433 | 35.0 | 35 | 2.6819 | {'meteor': 0.4820540318646651} |
63
+ | 2.6406 | 40.0 | 40 | 2.3893 | {'meteor': 0.48387008867521647} |
64
+ | 2.348 | 45.0 | 45 | 2.1093 | {'meteor': 0.48688764217538394} |
65
+ | 2.0685 | 50.0 | 50 | 1.8438 | {'meteor': 0.48840003275775357} |
66
+ | 1.8052 | 55.0 | 55 | 1.5954 | {'meteor': 0.49229450416352066} |
67
+ | 1.5592 | 60.0 | 60 | 1.3681 | {'meteor': 0.49462336346473573} |
68
+ | 1.3335 | 65.0 | 65 | 1.1642 | {'meteor': 0.4943789886645904} |
69
+ | 1.1308 | 70.0 | 70 | 0.9838 | {'meteor': 0.4932081022324161} |
70
+ | 0.9511 | 75.0 | 75 | 0.8281 | {'meteor': 0.4949580448605414} |
71
+ | 0.7953 | 80.0 | 80 | 0.6959 | {'meteor': 0.4945236890902709} |
72
+ | 0.6629 | 85.0 | 85 | 0.5849 | {'meteor': 0.49613363555493917} |
73
+ | 0.5518 | 90.0 | 90 | 0.4970 | {'meteor': 0.49476521946537905} |
74
+ | 0.4599 | 95.0 | 95 | 0.4203 | {'meteor': 0.49694213467111825} |
75
+ | 0.3856 | 100.0 | 100 | 0.3609 | {'meteor': 0.5023234677593583} |
76
+ | 0.3248 | 105.0 | 105 | 0.3137 | {'meteor': 0.49291655975794224} |
77
+ | 0.2756 | 110.0 | 110 | 0.2757 | {'meteor': 0.49187607478517975} |
78
+ | 0.236 | 115.0 | 115 | 0.2432 | {'meteor': 0.4999076360911653} |
79
+ | 0.2039 | 120.0 | 120 | 0.2196 | {'meteor': 0.5054381333125716} |
80
+ | 0.1782 | 125.0 | 125 | 0.2006 | {'meteor': 0.4998272338605217} |
81
+ | 0.1576 | 130.0 | 130 | 0.1864 | {'meteor': 0.5095656338179543} |
82
+ | 0.1411 | 135.0 | 135 | 0.1755 | {'meteor': 0.5030929069103355} |
83
+ | 0.1279 | 140.0 | 140 | 0.1653 | {'meteor': 0.5097532440481348} |
84
+ | 0.1173 | 145.0 | 145 | 0.1576 | {'meteor': 0.5126165420799782} |
85
+ | 0.1088 | 150.0 | 150 | 0.1516 | {'meteor': 0.5168283983418568} |
86
+ | 0.1023 | 155.0 | 155 | 0.1462 | {'meteor': 0.5145210432669091} |
87
+ | 0.097 | 160.0 | 160 | 0.1424 | {'meteor': 0.5135483205500848} |
88
+ | 0.0929 | 165.0 | 165 | 0.1399 | {'meteor': 0.5099977164420265} |
89
+ | 0.0899 | 170.0 | 170 | 0.1384 | {'meteor': 0.5093303675700068} |
90
+ | 0.0876 | 175.0 | 175 | 0.1369 | {'meteor': 0.5097771482308939} |
91
+ | 0.086 | 180.0 | 180 | 0.1357 | {'meteor': 0.5080664663529372} |
92
+ | 0.085 | 185.0 | 185 | 0.1347 | {'meteor': 0.5101483486776783} |
93
+ | 0.0843 | 190.0 | 190 | 0.1342 | {'meteor': 0.5110798690668398} |
94
+ | 0.0839 | 195.0 | 195 | 0.1340 | {'meteor': 0.5102824562761434} |
95
+ | 0.0838 | 200.0 | 200 | 0.1340 | {'meteor': 0.5103395242652348} |
96
 
97
 
98
  ### Framework versions