finetune-clip-flickr8-vi

duythanh1022/finetune-clip-flickr8-vi

finetune-clip-flickr8-vi is a machine learning model from duythanh1022. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

13% of all-time downloads

All-time downloads

Public

Repo size

33.4 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors8.3 MB · 63%

At a glance

Library: peft
Access: Public
Created: May 26, 2025
Updated: May 26, 2025
SHA: df3b32cd

Base models

ybelkada/blip2-opt-2.7b-fp16-sharded

Model card

From the Hugging Face model README

finetune-clip-flickr8-vi

This model is a fine-tuned version of ybelkada/blip2-opt-2.7b-fp16-sharded on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8792

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: 0.0001
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.1292	0.5	200	1.0219
1.0023	1.0	400	0.9269
0.951	1.5	600	0.8907
0.9298	2.0	800	0.8792

Framework versions

PEFT 0.15.2.dev0
Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

Library: peft
Created: May 26, 2025
Updated: May 26, 2025