Hugging Face's logo

ChayanM
/
ViT-RadBert_Mimic

Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
Generated from Trainer
Model card Files
xet
Community
ChayanM commited on
Commit
d8fbb08
·
verified ·
1 Parent(s): 780d08d

Model save

Browse files
Files changed (2) hide show
  1. README.md +41 -21
  2. model.safetensors +1 -1
README.md CHANGED
@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0887
19
- - Rouge1: 32.8977
20
- - Rouge2: 21.8288
21
- - Rougel: 32.302
22
- - Rougelsum: 32.7773
23
- - Gen Len: 18.79
24
 
25
  ## Model description
26
 
@@ -40,27 +40,47 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 5e-05
43
- - train_batch_size: 8
44
- - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 10
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
53
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
54
- | 0.2426 | 1.0 | 625 | 0.1040 | 27.5188 | 21.3864 | 27.3549 | 27.4573 | 19.258 |
55
- | 0.0954 | 2.0 | 1250 | 0.0891 | 19.0537 | 14.7729 | 18.9993 | 19.0513 | 19.666 |
56
- | 0.0809 | 3.0 | 1875 | 0.0857 | 28.2601 | 21.7315 | 28.0709 | 28.3266 | 19.416 |
57
- | 0.0679 | 4.0 | 2500 | 0.0858 | 30.8838 | 23.7439 | 30.6859 | 30.936 | 18.792 |
58
- | 0.0635 | 5.0 | 3125 | 0.0861 | 32.0132 | 23.2768 | 31.5703 | 31.8913 | 18.796 |
59
- | 0.0596 | 6.0 | 3750 | 0.0880 | 34.1984 | 23.726 | 33.7241 | 34.2367 | 18.59 |
60
- | 0.056 | 7.0 | 4375 | 0.0904 | 34.6439 | 23.7097 | 34.0416 | 34.5722 | 18.91 |
61
- | 0.0471 | 8.0 | 5000 | 0.0858 | 34.0822 | 22.9515 | 33.3727 | 33.8493 | 18.79 |
62
- | 0.0442 | 9.0 | 5625 | 0.0874 | 34.2676 | 23.6976 | 33.7124 | 34.2363 | 18.782 |
63
- | 0.0412 | 10.0 | 6250 | 0.0887 | 32.8977 | 21.8288 | 32.302 | 32.7773 | 18.79 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 24.4199
19
+ - Rouge1: 0.0
20
+ - Rouge2: 0.0
21
+ - Rougel: 0.0
22
+ - Rougelsum: 0.0
23
+ - Gen Len: 20.0
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 5e-05
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 4
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 30
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
53
+ |:-------------:|:-----:|:-------:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
54
+ | 0.2872 | 1.0 | 48913 | 9.6292 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
55
+ | 0.2786 | 2.0 | 97826 | 19.9417 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
56
+ | 0.267 | 3.0 | 146739 | 20.0859 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
57
+ | 0.2658 | 4.0 | 195652 | 21.5540 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
58
+ | 0.2852 | 5.0 | 244565 | 23.4539 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
59
+ | 0.2845 | 6.0 | 293478 | 22.8548 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
60
+ | 0.2769 | 7.0 | 342391 | 24.3758 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
61
+ | 0.2871 | 8.0 | 391304 | 24.4345 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
62
+ | 0.2747 | 9.0 | 440217 | 20.6148 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
63
+ | 0.2705 | 10.0 | 489130 | 21.4447 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
64
+ | 0.2709 | 11.0 | 538043 | 24.5166 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
65
+ | 0.2745 | 12.0 | 586956 | 25.3361 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
66
+ | 0.2687 | 13.0 | 635869 | 27.1382 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
67
+ | 0.2704 | 14.0 | 684782 | 24.3621 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
68
+ | 0.2699 | 15.0 | 733695 | 25.0646 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
69
+ | 0.2588 | 16.0 | 782608 | 25.5271 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
70
+ | 0.2656 | 17.0 | 831521 | 25.8602 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
71
+ | 0.2622 | 18.0 | 880434 | 27.6951 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
72
+ | 0.2528 | 19.0 | 929347 | 25.5126 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
73
+ | 0.2668 | 20.0 | 978260 | 27.6786 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
74
+ | 0.2651 | 21.0 | 1027173 | 28.1278 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
75
+ | 0.2535 | 22.0 | 1076086 | 27.4651 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
76
+ | 0.256 | 23.0 | 1124999 | 25.5766 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
77
+ | 0.2596 | 24.0 | 1173912 | 26.1662 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
78
+ | 0.2415 | 25.0 | 1222825 | 25.7623 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
79
+ | 0.2401 | 26.0 | 1271738 | 24.2354 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
80
+ | 0.2588 | 27.0 | 1320651 | 23.6133 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
81
+ | 0.2343 | 28.0 | 1369564 | 24.4396 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
82
+ | 0.2545 | 29.0 | 1418477 | 24.1665 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
83
+ | 0.2316 | 30.0 | 1467390 | 24.4199 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
84
 
85
 
86
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4811cae012110a591b93dd16cc3a27f1d01aaeb60a91c6c67f59345d8df3903
3
  size 1834458276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd333b650df0abea8e89862c007d396d9a54ea9361ac931776d2f8f804f822a1
3
  size 1834458276