Hugging Face's logo

svenbl80
/
finetune_colpali_v1_2-german_ver3-4bit

Transformers
Safetensors
ColPali
Generated from Trainer
Model card Files Community
1
svenbl80 commited on
Commit
d10507e
·
verified ·
1 Parent(s): 7091b8c

End of training

Browse files
Files changed (3) hide show
  1. README.md +23 -23
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [vidore/colpaligemma-3b-pt-448-base](https://huggingface.co/vidore/colpaligemma-3b-pt-448-base) on the German_docx dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0992
21
- - Model Preparation Time: 0.007
22
 
23
  ## Model description
24
 
@@ -52,27 +52,27 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
54
  |:-------------:|:------:|:----:|:---------------:|:----------------------:|
55
- | No log | 0.0146 | 1 | 0.3248 | 0.007 |
56
- | 1.8501 | 0.1460 | 10 | 0.3090 | 0.007 |
57
- | 1.3107 | 0.2920 | 20 | 0.2642 | 0.007 |
58
- | 0.9799 | 0.4380 | 30 | 0.2404 | 0.007 |
59
- | 0.6309 | 0.5839 | 40 | 0.2107 | 0.007 |
60
- | 0.9043 | 0.7299 | 50 | 0.1864 | 0.007 |
61
- | 1.015 | 0.8759 | 60 | 0.1617 | 0.007 |
62
- | 0.9035 | 1.0219 | 70 | 0.1585 | 0.007 |
63
- | 0.6689 | 1.1679 | 80 | 0.1586 | 0.007 |
64
- | 0.3336 | 1.3139 | 90 | 0.1477 | 0.007 |
65
- | 0.377 | 1.4599 | 100 | 0.1408 | 0.007 |
66
- | 0.5013 | 1.6058 | 110 | 0.1442 | 0.007 |
67
- | 0.2791 | 1.7518 | 120 | 0.1277 | 0.007 |
68
- | 0.3665 | 1.8978 | 130 | 0.1164 | 0.007 |
69
- | 0.4709 | 2.0438 | 140 | 0.1106 | 0.007 |
70
- | 0.2456 | 2.1898 | 150 | 0.1061 | 0.007 |
71
- | 0.152 | 2.3358 | 160 | 0.1045 | 0.007 |
72
- | 0.1813 | 2.4818 | 170 | 0.1007 | 0.007 |
73
- | 0.1594 | 2.6277 | 180 | 0.1010 | 0.007 |
74
- | 0.1856 | 2.7737 | 190 | 0.1005 | 0.007 |
75
- | 0.1788 | 2.9197 | 200 | 0.0992 | 0.007 |
76
 
77
 
78
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [vidore/colpaligemma-3b-pt-448-base](https://huggingface.co/vidore/colpaligemma-3b-pt-448-base) on the German_docx dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0815
21
+ - Model Preparation Time: 0.0061
22
 
23
  ## Model description
24
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
54
  |:-------------:|:------:|:----:|:---------------:|:----------------------:|
55
+ | No log | 0.0146 | 1 | 0.3622 | 0.0061 |
56
+ | 1.6392 | 0.1460 | 10 | 0.3430 | 0.0061 |
57
+ | 1.1999 | 0.2920 | 20 | 0.3049 | 0.0061 |
58
+ | 1.2826 | 0.4380 | 30 | 0.2768 | 0.0061 |
59
+ | 0.7583 | 0.5839 | 40 | 0.2492 | 0.0061 |
60
+ | 0.603 | 0.7299 | 50 | 0.2258 | 0.0061 |
61
+ | 1.014 | 0.8759 | 60 | 0.1958 | 0.0061 |
62
+ | 0.8131 | 1.0219 | 70 | 0.1688 | 0.0061 |
63
+ | 0.6346 | 1.1679 | 80 | 0.1591 | 0.0061 |
64
+ | 0.5089 | 1.3139 | 90 | 0.1502 | 0.0061 |
65
+ | 0.4616 | 1.4599 | 100 | 0.1341 | 0.0061 |
66
+ | 0.4498 | 1.6058 | 110 | 0.1136 | 0.0061 |
67
+ | 0.4422 | 1.7518 | 120 | 0.1062 | 0.0061 |
68
+ | 0.3519 | 1.8978 | 130 | 0.0989 | 0.0061 |
69
+ | 0.2382 | 2.0438 | 140 | 0.0925 | 0.0061 |
70
+ | 0.242 | 2.1898 | 150 | 0.0894 | 0.0061 |
71
+ | 0.3462 | 2.3358 | 160 | 0.0907 | 0.0061 |
72
+ | 0.1371 | 2.4818 | 170 | 0.0862 | 0.0061 |
73
+ | 0.2691 | 2.6277 | 180 | 0.0838 | 0.0061 |
74
+ | 0.0869 | 2.7737 | 190 | 0.0833 | 0.0061 |
75
+ | 0.3401 | 2.9197 | 200 | 0.0815 | 0.0061 |
76
 
77
 
78
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4be353554a330dd46816122f19fc605554389d29a473861df0f75960705845c2
3
  size 157071680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ebcef182f505e54adc721326488e7508050c7df376f6debfad18f155bc49ab2
3
  size 157071680
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:406d37c978018a5a9dd13a26f63f4df32571eb8f47b65d85ce7a74f2ca2ef4f5
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669ba7c5243f079413201308d424089324b69c5a9c0b207e1d78881c731c29c6
3
  size 5240