qwen3.5-0.8b-ocr-handwriting

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.16.0.dev0

adapter: lora
base_model: Qwen/Qwen3.5-0.8B-Base
bf16: auto
datasets:
- path: leonnzhang/iam-line-qwen35-chat-v2
  split: train
  type: chat_template
  field_messages: messages

gradient_accumulation_steps: 1
learning_rate: 0.0002
load_in_8bit: true
lora_alpha: 16
lora_dropout: 0.05
lora_r: 8
lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
micro_batch_size: 16
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: ./outputs/mymodel
sequence_len: 4096
train_on_inputs: false

# Required for Qwen3.5 multimodal fine-tuning in Axolotl
trust_remote_code: true
processor_type: AutoProcessor
chat_template: qwen3_5
skip_prepare_dataset: true
remove_unused_columns: false
sample_packing: false

</details><br>

outputs/mymodel

This model is a fine-tuned version of Qwen/Qwen3.5-0.8B-Base on the leonnzhang/iam-line-qwen35-chat-v2 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: 0.0002
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• 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: 12
• training_steps: 406

Training results

Framework versions

• PEFT 0.18.1
• Transformers 5.5.0
• Pytorch 2.8.0+cu128
• Datasets 4.8.4
• Tokenizers 0.22.2