base_model: NousResearch/Meta-Llama-3-8B
# optionally might have model_type or tokenizer_type
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

load_in_8bit: true
load_in_4bit: false

datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/lora-out

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

adapter: lora
lora_model_dir:
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_modules_to_save:
  - embed_tokens
  - lm_head

wandb_project: llama3-lora
wandb_entity: your_username
wandb_name: llama3-alpaca2k-run1
wandb_watch: gradients
wandb_log_model: None


gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: false

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.01
special_tokens:
   pad_token: <|end_of_text|>

outputs/lora-out

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B on the mhenrichsen/alpaca_2k_test dataset. It achieves the following results on the evaluation set:

Loss: 1.0495

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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
num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.1188	0.0930	1	1.0755
1.0276	0.2791	3	1.0557
1.0467	0.5581	6	1.0094
1.0644	0.8372	9	1.0095
0.7988	1.0930	12	1.0279
0.6768	1.3721	15	1.0479
0.6719	1.6512	18	1.0495

Framework versions

PEFT 0.15.1
Transformers 4.51.0
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.1

krisx2/lamma3-fine-tuned

outputs/lora-out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

krisx2/
lamma3-fine-tuned