Built with Axolotl

See axolotl config

axolotl version: 0.13.0.dev0

adapter: lora
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
bf16: auto
datasets:
- path: Janeodum/diagramify-tikz-dataset
  type: chat_template
gradient_accumulation_steps: 4
learning_rate: 0.0001
load_in_8bit: false
load_in_4bit: true
lora_alpha: 64
lora_dropout: 0.05
lora_r: 32
lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: ./outputs/mymodel
sequence_len: 2048
train_on_inputs: false

outputs/mymodel

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct on the Janeodum/diagramify-tikz-dataset dataset.

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 18
  • training_steps: 623

Training results

Framework versions

  • PEFT 0.17.1
  • Transformers 4.57.0
  • Pytorch 2.7.1+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.1
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Janeodum/diagramify-tikz-lora

Base model

Qwen/Qwen2.5-7B
Adapter
(377)
this model

Dataset used to train Janeodum/diagramify-tikz-lora