ooliverz commited on
Commit
90a8fbf
·
verified ·
1 Parent(s): 27a89c3

End of training

Browse files
Files changed (3) hide show
  1. README.md +103 -0
  2. generation_config.json +7 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_COCOv3
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_COCOv3
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: 0.0966
22
+ - Meteor Score: {'meteor': 0.5408938263795505}
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: 3e-05
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
+ - 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
+ | 3.2229 | 5.0 | 5 | 2.9789 | {'meteor': 0.41552282487414405} |
57
+ | 2.9387 | 10.0 | 10 | 2.6142 | {'meteor': 0.4685053939421483} |
58
+ | 2.592 | 15.0 | 15 | 2.2978 | {'meteor': 0.4849322756130674} |
59
+ | 2.2751 | 20.0 | 20 | 2.0019 | {'meteor': 0.47420638870259907} |
60
+ | 1.9738 | 25.0 | 25 | 1.7167 | {'meteor': 0.48640146159813924} |
61
+ | 1.6877 | 30.0 | 30 | 1.4518 | {'meteor': 0.4898083781551464} |
62
+ | 1.4214 | 35.0 | 35 | 1.2094 | {'meteor': 0.487939608237839} |
63
+ | 1.1769 | 40.0 | 40 | 0.9923 | {'meteor': 0.4980774326833536} |
64
+ | 0.9592 | 45.0 | 45 | 0.8040 | {'meteor': 0.488335711225997} |
65
+ | 0.7699 | 50.0 | 50 | 0.6462 | {'meteor': 0.4919465483035675} |
66
+ | 0.6114 | 55.0 | 55 | 0.5181 | {'meteor': 0.4887190822781368} |
67
+ | 0.481 | 60.0 | 60 | 0.4133 | {'meteor': 0.4908850956442714} |
68
+ | 0.3752 | 65.0 | 65 | 0.3325 | {'meteor': 0.49324244604306894} |
69
+ | 0.2921 | 70.0 | 70 | 0.2705 | {'meteor': 0.49568446461184845} |
70
+ | 0.2272 | 75.0 | 75 | 0.2250 | {'meteor': 0.49361056097084616} |
71
+ | 0.1776 | 80.0 | 80 | 0.1931 | {'meteor': 0.5018863491081054} |
72
+ | 0.1404 | 85.0 | 85 | 0.1653 | {'meteor': 0.506990680377092} |
73
+ | 0.1118 | 90.0 | 90 | 0.1468 | {'meteor': 0.5071567168395572} |
74
+ | 0.0913 | 95.0 | 95 | 0.1296 | {'meteor': 0.5019147249270115} |
75
+ | 0.0738 | 100.0 | 100 | 0.1212 | {'meteor': 0.5151563978937971} |
76
+ | 0.06 | 105.0 | 105 | 0.1144 | {'meteor': 0.5254092884094786} |
77
+ | 0.0494 | 110.0 | 110 | 0.1100 | {'meteor': 0.5258164560531304} |
78
+ | 0.0413 | 115.0 | 115 | 0.1046 | {'meteor': 0.5305386302193077} |
79
+ | 0.035 | 120.0 | 120 | 0.1005 | {'meteor': 0.5405955416808903} |
80
+ | 0.0301 | 125.0 | 125 | 0.1009 | {'meteor': 0.5326314473682981} |
81
+ | 0.0262 | 130.0 | 130 | 0.1016 | {'meteor': 0.5466195008617952} |
82
+ | 0.0233 | 135.0 | 135 | 0.0991 | {'meteor': 0.5463553955219586} |
83
+ | 0.0211 | 140.0 | 140 | 0.0987 | {'meteor': 0.543975966495889} |
84
+ | 0.0193 | 145.0 | 145 | 0.0979 | {'meteor': 0.5269418821882673} |
85
+ | 0.0179 | 150.0 | 150 | 0.0990 | {'meteor': 0.5384964361269092} |
86
+ | 0.0169 | 155.0 | 155 | 0.0985 | {'meteor': 0.5374634680447925} |
87
+ | 0.0161 | 160.0 | 160 | 0.0962 | {'meteor': 0.5296357754808179} |
88
+ | 0.0155 | 165.0 | 165 | 0.0968 | {'meteor': 0.5335376085825252} |
89
+ | 0.0151 | 170.0 | 170 | 0.0965 | {'meteor': 0.5426897117754873} |
90
+ | 0.0148 | 175.0 | 175 | 0.0971 | {'meteor': 0.5435169793620099} |
91
+ | 0.0146 | 180.0 | 180 | 0.0972 | {'meteor': 0.5432382041598678} |
92
+ | 0.0145 | 185.0 | 185 | 0.0969 | {'meteor': 0.5413175577245792} |
93
+ | 0.0144 | 190.0 | 190 | 0.0967 | {'meteor': 0.5412533872506878} |
94
+ | 0.0143 | 195.0 | 195 | 0.0966 | {'meteor': 0.5407676909570709} |
95
+ | 0.0143 | 200.0 | 200 | 0.0966 | {'meteor': 0.5408938263795505} |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.46.1
101
+ - Pytorch 2.2.1+cu121
102
+ - Datasets 2.18.0
103
+ - 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:b3d4fedb1db3ff41948a2a72b967ae7fb47e5e17d55f14f808e080a0fe4861be
3
  size 1576851440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806c1f9bda404a5ec974394416205f0a4234630fa1331efd855040d980dd27e7
3
  size 1576851440