radm
/

Qwen2.5-32B-simpo-LoRA

Generated from Trainer

Model card Files Files and versions

radm_Qwen2.5-32B-simpo-LoRA

This model is a fine-tuned version of ../models/Qwen2.5-32B-Instruct on the custom dataset.

Full model (FP8): radm/Qwen2.5-32B-simpo-FP8

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 7e-07
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 16
num_epochs: 1.0

Training results

Framework versions

PEFT 0.11.1
Transformers 4.43.4
Pytorch 2.4.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 1

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for radm/Qwen2.5-32B-simpo-LoRA

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/Qwen2.5-32B-Instruct

Adapter

(175)

this model

Datasets used to train radm/Qwen2.5-32B-simpo-LoRA