Edit model card

TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T finetuned using OpenAssistant/oasst_top1_2023-08-25 dataset.

Trained for 5 epochs using Qlora. Adapter is merged.

SFT code: https://github.com/habanoz/qlora.git

Command used:

accelerate launch $BASE_DIR/qlora/train.py \
  --model_name_or_path $BASE_MODEL \
  --working_dir $BASE_DIR/$OUTPUT_NAME-checkpoints \
  --output_dir $BASE_DIR/$OUTPUT_NAME-peft \
  --merged_output_dir $BASE_DIR/$OUTPUT_NAME \
  --final_output_dir $BASE_DIR/$OUTPUT_NAME-final \
  --num_train_epochs 5 \
  --logging_steps 1 \
  --save_strategy steps \
  --save_steps 75 \
  --save_total_limit 2 \
  --data_seed 11422 \
  --evaluation_strategy steps \
  --per_device_eval_batch_size 4 \
  --eval_dataset_size 0.01 \
  --eval_steps 75 \
  --max_new_tokens 1024 \
  --dataloader_num_workers 3 \
  --logging_strategy steps \
  --do_train \
  --do_eval \
  --lora_r 64 \
  --lora_alpha 16 \
  --lora_modules all \
  --bits 4 \
  --double_quant \
  --quant_type nf4 \
  --lr_scheduler_type constant \
  --dataset oasst1-top1 \
  --dataset_format oasst1 \
  --model_max_len 1024 \
  --per_device_train_batch_size 4 \
  --gradient_accumulation_steps 4 \
  --learning_rate 1e-5 \
  --adam_beta2 0.999 \
  --max_grad_norm 0.3 \
  --lora_dropout 0.0 \
  --weight_decay 0.0 \
  --seed 11422 \
  --gradient_checkpointing \
  --use_flash_attention_2 \
  --ddp_find_unused_parameters False

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 34.53
AI2 Reasoning Challenge (25-Shot) 31.06
HellaSwag (10-Shot) 55.02
MMLU (5-Shot) 26.41
TruthfulQA (0-shot) 35.08
Winogrande (5-shot) 58.01
GSM8k (5-shot) 1.59
Downloads last month
12
Safetensors
Model size
1.1B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1

Finetuned
(8)
this model
Quantizations
1 model

Dataset used to train habanoz/TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1

Evaluation results