Hugging Face's logo

pixelmelt
/
ArtificialStupidity-Llama-3-Instruct-8b

PEFT
Safetensors
Model card Files Community
ArtificialStupidity-Llama-3-Instruct-8b / RR_L3_V3 /README.md
pixelmelt's picture
pixelmelt
Upload 7 files
a1c4d90 verified
preview code
|
raw
history blame contribute delete
2.69 kB
metadata
license: llama3
library_name: peft
tags:
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model-index:
  - name: qlora-out
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: meta-llama/Meta-Llama-3-8B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: axo.jsonl
    type: sharegpt
    conversation: llama3
    name: RRL3-V3

dataset_prepared_path:
val_set_size: 0
output_dir: ./qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: gptRR
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 8
optimizer: paged_adamw_32bit
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

warmup_steps: 10
evals_per_epoch: 0
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|end_of_text|>"

qlora-out

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None 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: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 8

Training results

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0