Hyperparameters
- 3 epoch
- 1e-4 -> 1e-5 with cosine lr decay
- batch size 128
- max sequence length 2048
- AdamW(weigth decay=0.01, b1=0.9, b2=0.99, grad_clip=1.0)
- no warmup
- BF16
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("heegyu/WizardVicuna-pythia-410m-deduped")
model = AutoModelForCausalLM.from_pretrained("heegyu/WizardVicuna-pythia-410m-deduped")
inputs = tokenizer(["Human: Hi\n\nAssistant: "], return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=16)
print(tokenizer.batch_decode(outputs, skip_special_tokens=False))
output: ['Human: Hi\n\nAssistant: Hello! How can I assist you today?<|endoftext|>']