Hugging Face's logo

svenbl80
/
finetune_colpali_v1_2-german-4bit

Transformers
Safetensors
ColPali
Generated from Trainer
Inference Endpoints
Model card Files Community
svenbl80 commited on
Commit
8b2f73f
•
1 Parent(s): 3789192

End of training

Browse files
Files changed (3) hide show
  1. README.md +22 -9
  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 vidore/vdsid_french dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1351
21
- - Model Preparation Time: 0.0074
22
 
23
  ## Model description
24
 
@@ -46,18 +46,31 @@ 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: 3
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
54
  |:-------------:|:------:|:----:|:---------------:|:----------------------:|
55
- | No log | 0.0533 | 1 | 0.2922 | 0.0074 |
56
- | 1.9646 | 0.5333 | 10 | 0.2693 | 0.0074 |
57
- | 1.1176 | 1.0667 | 20 | 0.2259 | 0.0074 |
58
- | 1.1675 | 1.6 | 30 | 0.1884 | 0.0074 |
59
- | 0.6123 | 2.1333 | 40 | 0.1618 | 0.0074 |
60
- | 0.4301 | 2.6667 | 50 | 0.1351 | 0.0074 |
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### 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 vidore/vdsid_french dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0594
21
+ - Model Preparation Time: 0.0095
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 | 0.0533 | 1 | 0.2735 | 0.0095 |
56
+ | 1.7269 | 0.5333 | 10 | 0.2216 | 0.0095 |
57
+ | 1.568 | 1.0667 | 20 | 0.1536 | 0.0095 |
58
+ | 0.8782 | 1.6 | 30 | 0.1232 | 0.0095 |
59
+ | 0.7092 | 2.1333 | 40 | 0.1032 | 0.0095 |
60
+ | 0.4526 | 2.6667 | 50 | 0.0762 | 0.0095 |
61
+ | 0.5601 | 3.2 | 60 | 0.0663 | 0.0095 |
62
+ | 0.3721 | 3.7333 | 70 | 0.0591 | 0.0095 |
63
+ | 0.2704 | 4.2667 | 80 | 0.0456 | 0.0095 |
64
+ | 0.3564 | 4.8 | 90 | 0.0435 | 0.0095 |
65
+ | 0.2019 | 5.3333 | 100 | 0.0390 | 0.0095 |
66
+ | 0.1092 | 5.8667 | 110 | 0.0337 | 0.0095 |
67
+ | 0.0884 | 6.4 | 120 | 0.0344 | 0.0095 |
68
+ | 0.2341 | 6.9333 | 130 | 0.0433 | 0.0095 |
69
+ | 0.1872 | 7.4667 | 140 | 0.0448 | 0.0095 |
70
+ | 0.1533 | 8.0 | 150 | 0.0485 | 0.0095 |
71
+ | 0.1681 | 8.5333 | 160 | 0.0525 | 0.0095 |
72
+ | 0.2414 | 9.0667 | 170 | 0.0590 | 0.0095 |
73
+ | 0.1814 | 9.6 | 180 | 0.0594 | 0.0095 |
74
 
75
 
76
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab3283ccb3ed495f50aa5cfe9731baf4b6140acb46fd272fde2dbb7eaa28e9aa
3
  size 157071680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649b38b9a644337585ae1d9fdbcf355961ea171eb5d6a2d381ea9f3df5b54ef2
3
  size 157071680
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f34cbef05c6112a7520d4cb8009ae56261a6a6db795a14dc79a376775afb5afe
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0560019392421fe2199c17a53c2019b0e26834c8eca6f6aa8f07d5badbe34692
3
  size 5240