jawbreaker-minicpm5-1b-lora-v2 – AI Model by build-small-hackathon | AlphaNeural AI

You can deploy this model and start earning money today!

build-small-hackathon/
jawbreaker-minicpm5-1b-lora-v2

like

0

text-generation

openbmb/MiniCPM5-1B

Views

No views yet

jawbreaker-minicpm5-1b-lora-v2

This model is a fine-tuned version of openbmb/MiniCPM5-1B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0012

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: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.0307	0.6452	50	0.0295
0.0058	1.2839	100	0.0067
0.0029	1.9290	150	0.0022
0.001	2.5677	200	0.0012

Framework versions

PEFT 0.19.1
Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 4.8.5
Tokenizers 0.22.2