See axolotl config
axolotl version: 0.15.0
adapter: lora
base_model: Qwen/Qwen3.5-9B
bf16: auto
datasets:
- path: godzillaxz/polymarket-trading-data
type: chat_template
field: messages
gradient_accumulation_steps: 1
gradient_checkpointing: true
learning_rate: 0.00002
load_in_4bit: true
lora_alpha: 32
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: 3
optimizer: adamw_bnb_8bit
output_dir: ./outputs/mymodel
sequence_len: 2048
train_on_inputs: false
warmup_ratio: 0.1
outputs/mymodel
This model is a fine-tuned version of Qwen/Qwen3.5-9B on the godzillaxz/polymarket-trading-data 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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- 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: 65
- training_steps: 650
Training results
Framework versions
- PEFT 0.18.1
- Transformers 5.3.0
- Pytorch 2.8.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.1
- Downloads last month
- 19