ooliverz commited on
Commit
d5002c8
·
verified ·
1 Parent(s): f603f6a

End of training

Browse files
Files changed (3) hide show
  1. README.md +119 -0
  2. generation_config.json +7 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_COCOv2
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_COCOv2
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: 0.0707
22
+ - Meteor Score: {'meteor': 0.6046359366263345}
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: 128
43
+ - eval_batch_size: 128
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 8
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: 280
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Meteor Score |
55
+ |:-------------:|:-----:|:----:|:---------------:|:-------------------------------:|
56
+ | 0.0897 | 5.0 | 5 | 0.0587 | {'meteor': 0.4933296543916349} |
57
+ | 0.0213 | 10.0 | 10 | 0.0519 | {'meteor': 0.5073906049291329} |
58
+ | 0.0139 | 15.0 | 15 | 0.0534 | {'meteor': 0.5026388184030599} |
59
+ | 0.0109 | 20.0 | 20 | 0.0548 | {'meteor': 0.4959687986841175} |
60
+ | 0.0093 | 25.0 | 25 | 0.0543 | {'meteor': 0.4949189450882494} |
61
+ | 0.0082 | 30.0 | 30 | 0.0545 | {'meteor': 0.49958464676936615} |
62
+ | 0.0078 | 35.0 | 35 | 0.0550 | {'meteor': 0.5008859034272045} |
63
+ | 0.0071 | 40.0 | 40 | 0.0559 | {'meteor': 0.5053584986760098} |
64
+ | 0.0066 | 45.0 | 45 | 0.0567 | {'meteor': 0.5094590295434717} |
65
+ | 0.0063 | 50.0 | 50 | 0.0575 | {'meteor': 0.5059584506393162} |
66
+ | 0.0065 | 55.0 | 55 | 0.0573 | {'meteor': 0.5201908757902923} |
67
+ | 0.0055 | 60.0 | 60 | 0.0586 | {'meteor': 0.5200515565029338} |
68
+ | 0.0045 | 65.0 | 65 | 0.0598 | {'meteor': 0.5131378851174205} |
69
+ | 0.0049 | 70.0 | 70 | 0.0621 | {'meteor': 0.5499937139983992} |
70
+ | 0.0038 | 75.0 | 75 | 0.0624 | {'meteor': 0.539570315557215} |
71
+ | 0.0028 | 80.0 | 80 | 0.0617 | {'meteor': 0.548512504053465} |
72
+ | 0.0018 | 85.0 | 85 | 0.0631 | {'meteor': 0.5439640184191283} |
73
+ | 0.0012 | 90.0 | 90 | 0.0660 | {'meteor': 0.557925085228612} |
74
+ | 0.0008 | 95.0 | 95 | 0.0675 | {'meteor': 0.5620817011869172} |
75
+ | 0.0006 | 100.0 | 100 | 0.0674 | {'meteor': 0.5503094290454951} |
76
+ | 0.0006 | 105.0 | 105 | 0.0684 | {'meteor': 0.546181368312395} |
77
+ | 0.0005 | 110.0 | 110 | 0.0684 | {'meteor': 0.5463336233044072} |
78
+ | 0.0005 | 115.0 | 115 | 0.0691 | {'meteor': 0.5576619024543746} |
79
+ | 0.0004 | 120.0 | 120 | 0.0694 | {'meteor': 0.5546954942704183} |
80
+ | 0.0004 | 125.0 | 125 | 0.0696 | {'meteor': 0.5497222879420277} |
81
+ | 0.0004 | 130.0 | 130 | 0.0698 | {'meteor': 0.544311547059304} |
82
+ | 0.0004 | 135.0 | 135 | 0.0699 | {'meteor': 0.5493033925122285} |
83
+ | 0.0004 | 140.0 | 140 | 0.0700 | {'meteor': 0.5530207777515885} |
84
+ | 0.0004 | 145.0 | 145 | 0.0700 | {'meteor': 0.5564099668780601} |
85
+ | 0.0004 | 150.0 | 150 | 0.0700 | {'meteor': 0.5679492768564564} |
86
+ | 0.0004 | 155.0 | 155 | 0.0703 | {'meteor': 0.578595211309698} |
87
+ | 0.0004 | 160.0 | 160 | 0.0702 | {'meteor': 0.5902028331000073} |
88
+ | 0.0004 | 165.0 | 165 | 0.0702 | {'meteor': 0.5908341919060666} |
89
+ | 0.0004 | 170.0 | 170 | 0.0704 | {'meteor': 0.5835439636956574} |
90
+ | 0.0004 | 175.0 | 175 | 0.0702 | {'meteor': 0.5801775330047455} |
91
+ | 0.0004 | 180.0 | 180 | 0.0704 | {'meteor': 0.5793751931617782} |
92
+ | 0.0003 | 185.0 | 185 | 0.0708 | {'meteor': 0.5819164373295177} |
93
+ | 0.0004 | 190.0 | 190 | 0.0713 | {'meteor': 0.5854992116937614} |
94
+ | 0.0003 | 195.0 | 195 | 0.0713 | {'meteor': 0.5884835599643219} |
95
+ | 0.0004 | 200.0 | 200 | 0.0710 | {'meteor': 0.5936486621664319} |
96
+ | 0.0003 | 205.0 | 205 | 0.0708 | {'meteor': 0.5968246892960577} |
97
+ | 0.0003 | 210.0 | 210 | 0.0707 | {'meteor': 0.5955436943329665} |
98
+ | 0.0003 | 215.0 | 215 | 0.0707 | {'meteor': 0.5961895790422306} |
99
+ | 0.0003 | 220.0 | 220 | 0.0708 | {'meteor': 0.5978139647588809} |
100
+ | 0.0003 | 225.0 | 225 | 0.0708 | {'meteor': 0.6004561333768053} |
101
+ | 0.0003 | 230.0 | 230 | 0.0708 | {'meteor': 0.6002254020289525} |
102
+ | 0.0003 | 235.0 | 235 | 0.0707 | {'meteor': 0.6008501002566073} |
103
+ | 0.0003 | 240.0 | 240 | 0.0707 | {'meteor': 0.6021241487964467} |
104
+ | 0.0003 | 245.0 | 245 | 0.0707 | {'meteor': 0.6036197856196621} |
105
+ | 0.0003 | 250.0 | 250 | 0.0707 | {'meteor': 0.6036786254584352} |
106
+ | 0.0003 | 255.0 | 255 | 0.0707 | {'meteor': 0.6044847886434006} |
107
+ | 0.0003 | 260.0 | 260 | 0.0707 | {'meteor': 0.6046523048220338} |
108
+ | 0.0003 | 265.0 | 265 | 0.0707 | {'meteor': 0.6046132052320912} |
109
+ | 0.0003 | 270.0 | 270 | 0.0707 | {'meteor': 0.6045385775257441} |
110
+ | 0.0003 | 275.0 | 275 | 0.0707 | {'meteor': 0.6046099750473335} |
111
+ | 0.0003 | 280.0 | 280 | 0.0707 | {'meteor': 0.6046359366263345} |
112
+
113
+
114
+ ### Framework versions
115
+
116
+ - Transformers 4.46.1
117
+ - Pytorch 2.2.1+cu121
118
+ - Datasets 2.18.0
119
+ - 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 sha256:7367dcb5b880e3942ebebaf140bd9db103479506fe6315f7a16a8d1d76898f63
3
  size 1576851440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d902fec91d789e742daedc425c93b3a08e566034311244de31cc94707ce1ad5b
3
  size 1576851440