Downloads · 30 days
146
3% of all-time downloads
RichardErkhov/habanoz_-_TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-gguf
habanoz_-_TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
146
3% of all-time downloads
All-time downloads
5.5K
Public
Repo size
12.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf14.7 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
TinyLlama-1.1B-step-2T-lr-5-5ep-oasst1-top1-instruct-V1 - GGUF
language:
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
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 |