First Version of Instruction Tuned Bloomz-7B1 model on ChatGPT dataset (85k data) using HF Deepspeed
Base Model: bigscience/bloomz-7b1
Training Details :
- Epochs: 5
- Batch Size : 5 instantaneous per device x 2 gradient accumulation steps x 8 gpus = 80
- Max Length : 512
- Weight Decay : 0
- Learning Rate : 5e-5
- Learning Rate Scheduler Type : Linear
- Number of warmup steps : 0
- Machine : 8xA100 80GB
Dataset Details :
Dataset : iamplus/Instruction_Tuning
Files :
- chat_gpt_v1.csv