Hugging Face's logo

FuturisticVibes
/
Qwen2-7B-TestToxicFineTune-LORA

PEFT
Safetensors
qwen2
Generated from Trainer
Model card Files Community
Qwen2-7B-TestToxicFineTune-LORA / README.md
FuturisticVibes's picture
FuturisticVibes
Update README.md
5231e84 verified
preview code
|
raw
history blame
4.39 kB
metadata
base_model: Qwen/Qwen2-7B
library_name: peft
tags:
  - generated_from_trainer
model-index:
  - name: workspace/data/outputs/Qwen2-7B-TestFinetune-LORA
    results: []
datasets:
  - NobodyExistsOnTheInternet/ToxicQAFinal

If I thought I had no idea what I was doing with quantization, I REALLY have no idea what I’m doing with LORA Fine Tuning... This works in my 10 second testing, but I have no idea beyond that, nor did do anything other than asking it to do horrible things and seeing if it complied.

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: /workspace/data/models/Qwen2-7B
model_type: Qwen2ForCausalLM
tokenizer_type: Qwen2Tokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NobodyExistsOnTheInternet/ToxicQAFinal
    type: sharegpt
#  - path: /workspace/data/SystemChat_filtered_sharegpt.jsonl
#    type: sharegpt
#    conversation: chatml
#  - path: /workspace/data/Opus_Instruct-v2-6.5K-Filtered-v2.json
#    type:
#      field_system: system
#      field_instruction: prompt
#      field_output: response
#      format: "[INST] {instruction} [/INST]"
#      no_input_format: "[INST] {instruction} [/INST]"
#  - path: Undi95/orthogonal-activation-steering-TOXIC
#    type:
#      field_instruction: goal
#      field_output: target
#      format: "[INST] {instruction} [/INST]"
#      no_input_format: "[INST] {instruction} [/INST]"
#    split: test
#  - path: cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered
#    type: alpaca
#    split: train

dataset_prepared_path: /workspace/data/last_run_prepared
val_set_size: 0.15
output_dir: /workspace/data/outputs/Qwen2-7B-TestFinetune-LORA

chat_template: chatml

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 3e-5

train_on_inputs: false
group_by_length: true
bf16: true
fp16: false
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: 2
eval_table_size:
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|endoftext|>"
  eos_token: "<|im_end|>"

workspace/data/outputs/Qwen2-7B-TestFinetune-LORA

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0055

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: 3e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 8
  • 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: 4

Training results

Training Loss Epoch Step Validation Loss
1.1751 0.0169 1 1.1860
1.1007 0.5063 30 1.0912
1.0418 1.0127 60 1.0428
1.0105 1.5042 90 1.0232
1.0082 2.0105 120 1.0127
0.9946 2.5042 150 1.0074
0.9826 3.0105 180 1.0057
0.9898 3.5021 210 1.0055

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.3
  • Pytorch 2.1.2+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1