Hugging Face's logo

PuppetLover
/
scenegraph_image_captioning_vi

Transformers
PyTorch
mbart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
PuppetLover commited on
Commit
116de8b
·
verified ·
1 Parent(s): 8aa470a

Training complete!

Browse files
Files changed (2) hide show
  1. README.md +81 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: facebook/mbart-large-50
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: scenegraph_image_captioning_vi
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # scenegraph_image_captioning_vi
16
+
17
+ This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 3.1815
20
+ - Bleu4: 16.1492
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
+ - train_batch_size: 48
41
+ - eval_batch_size: 48
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 96
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 350
48
+ - num_epochs: 30
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Bleu4 | Validation Loss |
53
+ |:-------------:|:-----:|:-----:|:-------:|:---------------:|
54
+ | 3.5137 | 1.0 | 3083 | 11.8025 | 3.4747 |
55
+ | 3.3145 | 2.0 | 6166 | 13.309 | 3.3252 |
56
+ | 3.1957 | 3.0 | 9249 | 14.2144 | 3.2632 |
57
+ | 3.1449 | 4.0 | 12332 | 14.8718 | 3.2247 |
58
+ | 3.1078 | 5.0 | 15415 | 15.1815 | 3.1963 |
59
+ | 3.0352 | 6.0 | 18498 | 15.2137 | 3.1796 |
60
+ | 3.0147 | 7.0 | 21581 | 15.7702 | 3.1697 |
61
+ | 2.971 | 8.0 | 24664 | 16.0201 | 3.1662 |
62
+ | 2.9144 | 9.0 | 27747 | 16.1495 | 3.1623 |
63
+ | 2.9037 | 10.0 | 30830 | 16.0747 | 3.1611 |
64
+ | 2.9178 | 11.0 | 33913 | 16.2077 | 3.1575 |
65
+ | 2.8687 | 12.0 | 36996 | 16.1345 | 3.1594 |
66
+ | 2.8426 | 13.0 | 40079 | 16.2958 | 3.1618 |
67
+ | 2.8058 | 14.0 | 43162 | 16.2391 | 3.1639 |
68
+ | 2.814 | 15.0 | 46245 | 16.341 | 3.1722 |
69
+ | 2.782 | 16.0 | 49328 | 3.1683 | 16.0129 |
70
+ | 2.7853 | 17.0 | 52411 | 3.1772 | 16.1951 |
71
+ | 2.7313 | 18.0 | 55494 | 3.1846 | 16.0554 |
72
+ | 2.7525 | 19.0 | 58577 | 3.1876 | 16.0271 |
73
+ | 2.7183 | 20.0 | 61660 | 3.1815 | 16.1492 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.51.0
79
+ - Pytorch 2.11.0+cu128
80
+ - Datasets 4.0.0
81
+ - Tokenizers 0.21.4
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13420323dc55020f70b8915f0d387f8df28f0ef31a385c53060f7241175976f9
3
  size 6140680585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2150d83a1a866cb5a0b7c38dbdb92675c556dc99fbd44bc5256820f575c9781
3
  size 6140680585