Hugging Face's logo

ChayanM
/
ViT-RadBert_Mimic

Image-Text-to-Text
Transformers
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
ChayanM commited on
Commit
7054bee
•
1 Parent(s): 7420cd5

Model save

Browse files
Files changed (2) hide show
  1. README.md +23 -11
  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: 0.3546
19
- - Rouge1: 2.0126
20
  - Rouge2: 0.0
21
- - Rougel: 1.9996
22
- - Rougelsum: 2.0291
23
- - Gen Len: 14.66
24
 
25
  ## Model description
26
 
@@ -45,15 +45,27 @@ 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: 3
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
53
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
54
- | 0.3204 | 1.0 | 1750 | 0.5844 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
55
- | 0.2785 | 2.0 | 3500 | 0.3453 | 13.8451 | 0.7829 | 13.8799 | 13.8866 | 14.142 |
56
- | 0.2708 | 3.0 | 5250 | 0.3546 | 2.0126 | 0.0 | 1.9996 | 2.0291 | 14.66 |
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### 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: 0.7877
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
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 15
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
54
+ | 0.2467 | 1.0 | 1750 | 0.2455 | 15.3883 | 0.0 | 15.4185 | 15.4293 | 12.065 |
55
+ | 0.2303 | 2.0 | 3500 | 0.2513 | 13.5368 | 0.0 | 13.5094 | 13.4921 | 14.028 |
56
+ | 0.233 | 3.0 | 5250 | 0.2487 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
57
+ | 0.2317 | 4.0 | 7000 | 0.2515 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
58
+ | 0.229 | 5.0 | 8750 | 0.2563 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
59
+ | 0.2334 | 6.0 | 10500 | 0.5032 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
60
+ | 0.216 | 7.0 | 12250 | 0.6445 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
61
+ | 0.2154 | 8.0 | 14000 | 0.7287 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
62
+ | 0.2065 | 9.0 | 15750 | 0.7666 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
63
+ | 0.206 | 10.0 | 17500 | 0.6641 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
64
+ | 0.2014 | 11.0 | 19250 | 0.7032 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
65
+ | 0.1784 | 12.0 | 21000 | 0.7845 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
66
+ | 0.1854 | 13.0 | 22750 | 0.8179 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
67
+ | 0.1801 | 14.0 | 24500 | 0.7788 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
68
+ | 0.1743 | 15.0 | 26250 | 0.7877 | 0.0 | 0.0 | 0.0 | 0.0 | 20.0 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a87d3457935fa4e05998d757f625b3275b8932289a3ca25cc1e06d35d377b45e
3
  size 959047772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e727795e93ab2fce6ec588a105599a58f33f0baa9b908afc256f15663f53450
3
  size 959047772