Hugging Face's logo

mjobe105
/
qlora70b

PEFT
Safetensors
llama
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
qlora70b / README.md
mjobe105's picture
mjobe105
Upload folder using huggingface_hub
772843e verified
preview code
|
raw
history blame
3.28 kB
metadata
license: llama3
library_name: peft
tags:
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-70B-Instruct
model-index:
  - name: workspace/data/out/qlora
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: meta-llama/Meta-Llama-3-70B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer  # PreTrainedTokenizerFast

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: /workspace/data/out/qlora

adapter: qlora
lora_model_dir:

sequence_len: 512
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: true

lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00001

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

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

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

workspace/data/out/qlora

This model is a fine-tuned version of meta-llama/Meta-Llama-3-70B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0845

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: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • 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: 10
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.1589 0.0339 1 1.1304
1.1859 0.2712 8 1.1284
1.0445 0.5424 16 1.1105
1.1946 0.8136 24 1.0845

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.1.2+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1