See axolotl config
axolotl version: 0.11.0.dev0
adapter: lora
base_model: unsloth/Llama-3.2-1B-Instruct
bf16: true
fp16: false
load_in_4bit: false
load_in_8bit: false
datasets:
- path: mx003/viper
type: chat_template
field_messages: messages
chat_template: llama3
val_set_size: 0.05
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
gradient_accumulation_steps: 8
gradient_checkpointing: true
micro_batch_size: 2
num_epochs: 2
learning_rate: 0.0002
optimizer: adamw_torch_fused
lr_scheduler: cosine
warmup_ratio: 0.03
output_dir: ./outputs/mymodel-1b
sequence_len: 4096
save_steps: 10
logging_steps: 5
flash_attention: false
sample_packing: true
group_by_length: false
train_on_inputs: false
special_tokens:
pad_token: <|end_of_text|>
outputs/mymodel-1b
This model is a fine-tuned version of unsloth/Llama-3.2-1B-Instruct on the mx003/viper 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- training_steps: 32
Training results
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for mx003/viper-llama-3_2-1B
Base model
meta-llama/Llama-3.2-1B-Instruct Finetuned
unsloth/Llama-3.2-1B-Instruct