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
9be1438
·
verified ·
1 Parent(s): 184bea2

Model save

Browse files
Files changed (2) hide show
  1. README.md +19 -14
  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: 0.4086
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
 
@@ -45,17 +45,22 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 5
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
53
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
54
- | No log | 1.0 | 25 | 0.5450 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 |
55
- | No log | 2.0 | 50 | 0.4290 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
56
- | No log | 3.0 | 75 | 0.4142 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
57
- | No log | 4.0 | 100 | 0.4093 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
58
- | No log | 5.0 | 125 | 0.4086 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
 
 
 
 
 
59
 
60
 
61
  ### 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: 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
 
 
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
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e425b638ef6ee30620c3230fa4fac5fa0c32ada5e185d5716918b5fd91622ec4
3
  size 957880412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306e4bebaf119211fd3bb104d5f8634708bce8f16840331032b82644df4f28c9
3
  size 957880412