MiniCPM-V-2_6_ft_20240908_220534_ft_upsampled_new

muhtasham/MiniCPM-V-2_6_ft_20240908_220534_ft_upsampled_new

MiniCPM-V-2_6_ft_20240908_220534_ft_upsampled_new is a machine learning model from muhtasham. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

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

Downloads · 30 days

5% of all-time downloads

All-time downloads

143

Public

Parameters

8.1B

32.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors16.2 GB · 100%

At a glance

Model type: minicpmv
Access: Public
Created: Sep 13, 2024
Updated: Sep 18, 2024
SHA: 76ec4d97

Base models

muhtasham/MiniCPM-V-2_6_ft_20240908_220534

Model card

From the Hugging Face model README

MiniCPM-V-2_6_ft_20240908_220534_ft_upsampled_new

This model is a fine-tuned version of muhtasham/MiniCPM-V-2_6_ft_20240908_220534 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3133

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: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
training_steps: 10000
mixed_precision_training: Native AMP
label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss
0.0543	0.2430	100	0.2796
0.0791	0.4860	200	0.3113
0.0233	0.7290	300	0.3244
0.1447	0.9721	400	0.3133

Framework versions

Transformers 4.40.0
Pytorch 2.1.2+cu121
Tokenizers 0.19.1

Type: minicpmv
Created: Sep 13, 2024
Updated: Sep 18, 2024