Qwen2-7B-TestToxicFineTune-LORA

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 I do anything other than asking it to do horrible things and seeing if it complied.

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

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|>"

</details><br>

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

Framework versions

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