Hugging Face's logo

winglian
/
llama-3.1-8b-talk-like-a-pirate

PEFT
llama
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
llama-3.1-8b-talk-like-a-pirate / README.md
winglian's picture
winglian
Upload folder using huggingface_hub
0602cc9 verified
preview code
|
raw
history blame contribute delete
3 kB
metadata
base_model: NousResearch/Meta-Llama-3.1-8B
library_name: peft
license: llama3.1
tags:
  - generated_from_trainer
model-index:
  - name: outputs/lora-out
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: NousResearch/Meta-Llama-3.1-8B

load_in_4bit: true
strict: false

chat_template: llama3
datasets:
  - path: winglian/pirate-ultrachat-10k
    type: chat_template
    message_field_role: role
    message_field_content: content
dataset_prepared_path: last_run_prepared
val_set_size: 0.005
output_dir: ./outputs/lora-out

sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: qlora
lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_modules_to_save:
  - embed_tokens
  - lm_head
peft_use_dora: true

wandb_project: pirate-ultrachat-llama31
wandb_entity: axolotl-ai

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

train_on_inputs: false
bf16: true
tf32: true

gradient_checkpointing: true
logging_steps: 1
flash_attention: true

warmup_ration: 0.1
evals_per_epoch: 1
saves_per_epoch: 1
weight_decay: 0.0
deepspeed: deepspeed_configs/zero2.json
special_tokens:
  pad_token: "<|finetune_right_pad_id|>"

outputs/lora-out

This model is a fine-tuned version of NousResearch/Meta-Llama-3.1-8B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1247

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
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 2
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
1.6022 0.0202 1 1.5845
1.2173 0.9899 49 1.1328
0.9676 1.9798 98 1.1247

Framework versions

  • PEFT 0.12.0
  • Transformers 4.45.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1