Hugging Face's logo

svenbl80
/
finetune_colpali_v1_2-german_ver2-4bit

Transformers
Safetensors
ColPali
Generated from Trainer
Inference Endpoints
Model card Files Community
svenbl80 commited on
Commit
7283dc8
·
verified ·
1 Parent(s): 0f3a7a4

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -10
  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: 0.0498
21
- - Model Preparation Time: 0.0105
22
 
23
  ## Model description
24
 
@@ -46,19 +46,25 @@ The following hyperparameters were used during training:
46
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 100
49
- - num_epochs: 5
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
54
  |:-------------:|:------:|:----:|:---------------:|:----------------------:|
55
- | No log | 0.0816 | 1 | 0.4190 | 0.0105 |
56
- | 1.6183 | 0.8163 | 10 | 0.3540 | 0.0105 |
57
- | 1.4293 | 1.6327 | 20 | 0.2496 | 0.0105 |
58
- | 0.9161 | 2.4490 | 30 | 0.1681 | 0.0105 |
59
- | 0.6 | 3.2653 | 40 | 0.1203 | 0.0105 |
60
- | 0.5019 | 4.0816 | 50 | 0.0785 | 0.0105 |
61
- | 0.3168 | 4.8980 | 60 | 0.0498 | 0.0105 |
 
 
 
 
 
 
62
 
63
 
64
  ### 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: 0.0559
21
+ - Model Preparation Time: 0.0099
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 100
49
+ - num_epochs: 10
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
54
  |:-------------:|:------:|:----:|:---------------:|:----------------------:|
55
+ | No log | 0.0816 | 1 | 0.3744 | 0.0099 |
56
+ | 1.6073 | 0.8163 | 10 | 0.3027 | 0.0099 |
57
+ | 1.2318 | 1.6327 | 20 | 0.2157 | 0.0099 |
58
+ | 0.6498 | 2.4490 | 30 | 0.1428 | 0.0099 |
59
+ | 0.5073 | 3.2653 | 40 | 0.1181 | 0.0099 |
60
+ | 0.5106 | 4.0816 | 50 | 0.1069 | 0.0099 |
61
+ | 0.2965 | 4.8980 | 60 | 0.0969 | 0.0099 |
62
+ | 0.3175 | 5.7143 | 70 | 0.0922 | 0.0099 |
63
+ | 0.1775 | 6.5306 | 80 | 0.1089 | 0.0099 |
64
+ | 0.1966 | 7.3469 | 90 | 0.0649 | 0.0099 |
65
+ | 0.1317 | 8.1633 | 100 | 0.0477 | 0.0099 |
66
+ | 0.1287 | 8.9796 | 110 | 0.0503 | 0.0099 |
67
+ | 0.2576 | 9.7959 | 120 | 0.0559 | 0.0099 |
68
 
69
 
70
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc7177378a29cec59150a5fe82718603abdcd21ce20281fbc17c97831296ff76
3
  size 157071680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41cd561324e90bea3b6299164fff0b8c3533317d8b840ce1ba6e0b054d2430b
3
  size 157071680
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60c34bae146fbeee74ebe3278dac731e092fbf0e4a644692b81f1bb7a92a316d
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9efbb09f8ead2cf0b2af3d07d1e8c747582d21fc0baf2dcd98f95260d284625f
3
  size 5240