Hugging Face's logo

seeker317
/
finetune_colpali_v1_2_fm

Transformers
Safetensors
ColPali
Generated from Trainer
Inference Endpoints
Model card Files Community
1
seeker317 commited on
Commit
d590608
·
verified ·
1 Parent(s): d5e4ab1

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,10 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # finetune_colpali_v1_2_fm
19
 
20
- 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.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.4378
23
- - Model Preparation Time: 0.0047
24
 
25
  ## Model description
26
 
@@ -40,21 +39,22 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 5e-05
43
- - train_batch_size: 2
44
- - eval_batch_size: 2
45
  - seed: 42
46
  - gradient_accumulation_steps: 2
47
- - total_train_batch_size: 4
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 100
51
- - num_epochs: 1.5
 
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
56
- |:-------------:|:------:|:----:|:---------------:|:----------------------:|
57
- | No log | 0.6667 | 1 | 0.4405 | 0.0047 |
58
 
59
 
60
  ### Framework versions
 
17
 
18
  # finetune_colpali_v1_2_fm
19
 
20
+ 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 fm dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.1621
 
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 5e-05
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
  - seed: 42
45
  - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 64
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 100
50
+ - num_epochs: 5
51
+ - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | No log | 1.0 | 1 | 0.1707 |
58
 
59
 
60
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c9cfeb050762ee46ace2162e499be87df424de41dc7a40b592da67836061673
3
  size 157071680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b23bb08cc79fd18930b66a87c52be45db4a686f0da532f79ce6df83a8c6fa4
3
  size 157071680
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1d50868a52833b935c7316eeb89717899bcaf3cb178a5fe272c5f307863409f
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81aae7932a9bd677f1531729e04790c0825ad616de2c305a27d26ab08415a41a
3
  size 5240