base_model: meta-llama/Llama-3.2-1B
# Automatically upload checkpoint and final model to HF
hub_model_id: minpeter/LoRA-Llama-3.2-1B-Alpaca

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: alpaca

datasets:
  - path: minpeter/stanford-alpaca-regen-llama-3.3
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./output

adapter: lora
lora_model_dir:

sequence_len: 2048
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

lora_r: 16
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: "axolotl"
wandb_entity: "kasfiekfs-e"
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|end_of_text|>"

LoRA-Llama-3.2-1B-Alpaca

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the minpeter/stanford-alpaca-regen-llama-3.3 dataset. It achieves the following results on the evaluation set:

Loss: 1.2509

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: 2
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_8BIT 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
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.711	0.0021	1	1.6925
1.353	0.2516	121	1.3002
1.145	0.5031	242	1.2688
1.3371	0.7547	363	1.2509

Framework versions

PEFT 0.14.0
Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0