Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
finetune_colpali_v1_2-vdsid_french-4bit – AI Model by tonywu71 | AlphaNeural AI
You can deploy this model and start earning money today!
tonywu71
/
finetune_colpali_v1_2-vdsid_french-4bit
like
0
transformers
safetensors
colpali
generated_from_trainer
vidore/colpaligemma-3b-pt-448-base
finetune
gemma
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
finetune_colpali_v1_2-vdsid_french-4bit
This model is a fine-tuned version of
vidore/colpaligemma-3b-pt-448-base
on an
vidore/vdsid_french
. It achieves the following results on the evaluation set:
Loss: 0.0316
Model Preparation Time: 0.0121
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 1.5
Training results
Training Loss
Epoch
Step
Validation Loss
Model Preparation Time
No log
0.0034
1
0.0489
0.0121
0.0171
0.3404
100
0.0215
0.0121
0.01
0.6809
200
0.0301
0.0121
0.009
1.0213
300
0.0318
0.0121
0.012
1.3617
400
0.0319
0.0121
Framework versions
Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1
