Hugging Face's logo

AiAF
/
Mistral-QLoRA-Test

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
Mistral-QLoRA-Test / README.md
AiAF's picture
AiAF
End of training
5bd5b0c verified
preview code
|
raw
history blame contribute delete
3.58 kB
metadata
library_name: peft
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
  - axolotl
  - generated_from_trainer
datasets:
  - mhenrichsen/alpaca_2k_test
model-index:
  - name: Mistral-QLoRA-Test
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.6.0

base_model: mistralai/Mistral-7B-v0.1
# optionally might have model_type or tokenizer_type
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: AiAF/Mistral-QLoRA-Test

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: 0.1
output_dir: ./outputs/qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: "LLM_QLoRA-Pretraining-Practice"
wandb_entity:
wandb_watch: "all"
wandb_name: "Mistral-QLoRA-Test-V1.0"
wandb_log_model: "false"

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0001

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

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

Mistral-QLoRA-Test

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the mhenrichsen/alpaca_2k_test dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8640

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: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1.0

Training results

Training Loss Epoch Step Validation Loss
0.8459 0.0417 1 0.9399
0.9812 0.25 6 0.9012
0.8706 0.5 12 0.8773
0.8565 0.75 18 0.8659
0.8565 1.0 24 0.8640

Framework versions

  • PEFT 0.14.0
  • Transformers 4.48.3
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0