From 6a4a7ba9da32e2961c10372e21cbcb91daaa6235 Mon Sep 17 00:00:00 2001
From: Huseyin ABANOZ <habanoz@users.noreply.huggingface.co>
Date: Wed, 22 Nov 2023 16:38:10 +0000
Subject: [PATCH] Create README.md

---
 README.md | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..eccb5a8
--- /dev/null
+++ b/README.md
@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+datasets:
+- habanoz/airoboros-3.1-no-mathjson-max-1k
+language:
+- en
+pipeline_tag: text-generation
+---
+
+TinyLlama-1.1B-intermediate-step-715k-1.5T finetuned using airoboros-3.1-no-mathjson-max-1k dataset. 
+
+Qlora is used. Adapter is merged.
+
+SFT code:
+https://github.com/habanoz/qlora.git
+
+Command used:
+```bash
+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 1 \
+  --logging_steps 1 \
+  --save_strategy steps \
+  --save_steps 120 \
+  --save_total_limit 2 \
+  --data_seed 11422 \
+  --evaluation_strategy steps \
+  --per_device_eval_batch_size 4 \
+  --eval_dataset_size 0.01 \
+  --eval_steps 120 \
+  --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 habanoz/airoboros-3.1-no-mathjson-max-1k \
+  --dataset_format airoboros_chat \
+  --model_max_len 1024 \
+  --per_device_train_batch_size 1 \
+  --gradient_accumulation_steps 16 \
+  --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 False \
+  --use_flash_attention_2 \
+  --ddp_find_unused_parameters False \
+  --trust_remote_code True
+  ```
\ No newline at end of file