See axolotl config

axolotl version: 0.14.0

base_model: unsloth/Llama-3.2-1B-Instruct
model_type: AutoModelForCausalLM
adapter: qlora
load_in_4bit: true
bnb_4bit_quant_type: nf4
bnb_4bit_use_double_quant: true
bnb_4bit_compute_dtype: bfloat16
lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
datasets:
- path: yahma/alpaca-cleaned
  type: alpaca
sequence_len: 2048
micro_batch_size: 1
gradient_accumulation_steps: 4
num_epochs: 1
max_steps: 10
learning_rate: 0.0002
optimizer: adamw_bnb_8bit
lr_scheduler_type: cosine
warmup_steps: 10
flash_attention: false
gradient_checkpointing: true
bf16: auto
logging_steps: 10
save_steps: 100
output_dir: /app/results/7a775f96-133a-44da-975d-d4875774c579
push_to_hub: true
hub_model_id: HarrySoteriou/smoke-test-output
hf_use_auth_token: true

smoke-test-output

This model is a fine-tuned version of unsloth/Llama-3.2-1B-Instruct on the yahma/alpaca-cleaned 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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• 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: 10
• training_steps: 10

Training results

Framework versions

• PEFT 0.18.1
• Transformers 4.57.6
• Pytorch 2.9.1+cu128
• Datasets 4.3.0
• Tokenizers 0.22.2