hfht/Meta-Llama-3-8B-Instruct-peft-for-humor

See axolotl config

axolotl version: 0.13.0.dev0

adapter: qlora
base_model: NousResearch/Meta-Llama-3-8B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: last_run_prepared
datasets:
- path: hfht/peft-for-humor-train-dataset
  split: train
  type: chat_template
do_causal_lm_eval: false
evals_per_epoch: 1
flash_attention: true
gradient_accumulation_steps: 4
gradient_checkpointing: true
learning_rate: 0.0006
load_in_4bit: true
load_in_8bit: false
logging_steps: 1
lora_alpha: 64
lora_dropout: 0
lora_mlp_kernel: true
lora_model_dir: null
lora_modules_to_save:
- embed_tokens
- lm_head
lora_o_kernel: true
lora_qkv_kernel: true
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
output_dir: ./out/loras/humor
resume_from_checkpoint: null
sample_packing: true
save_strategy: 'no'
save_total_limit: 1
saves_per_epoch: 0
sequence_len: 4096
special_tokens:
  pad_token: <|finetune_right_pad_id|>
tf32: false
train_on_inputs: false
val_set_size: 0.005
warmup_steps: 5
weight_decay: 0.0

out/loras/humor

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Instruct on the hfht/peft-for-humor-train-dataset dataset. It achieves the following results on the evaluation set:

• Loss: 2.9864
• Memory/max Active (gib): 18.36
• Memory/max Allocated (gib): 18.36
• Memory/device Reserved (gib): 32.49

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: 0.0006
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 5
• training_steps: 32

Training results

Training Loss	Epoch	Step	Validation Loss	Active (gib)	Allocated (gib)	Reserved (gib)
No log	0	0	4.1906	13.02	13.02	13.12
2.9843	0.9143	8	2.9981	18.36	18.36	32.49
1.6393	1.8	16	3.0203	18.36	18.36	32.49
0.9789	2.6857	24	2.9846	18.36	18.36	32.49
0.6715	3.5714	32	2.9864	18.36	18.36	32.49

Framework versions

• PEFT 0.18.0
• Transformers 4.57.1
• Pytorch 2.8.0+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1