FuturisticVibes/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.

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