metadata
license: apache-2.0
tags:
- StepLaw
- causal-lm
language:
- en
library_name: transformers
pipeline_tag: text-generation
model-index:
- name: step2v2_0618_h768_ffnh6416_numh12_numl7_lr3.906e-03_bs64_ti30517_mlr1e-5
results: []
Wandb Model Name: step2v2_0618_h768_ffnh6416_numh12_numl7_lr3.906e-03_bs64_ti30517_mlr1e-5
This model is part of the StepLaw-N_119M-D_3.0B collection.
Model Specifications
Architecture
- Hidden size (H): 768
- Feed-forward network size (FFN): 6416
- Attention heads: 12
- Layers: 7
- Parameter count: 119M
Training Parameters
- Learning rate (lr): 3.906e-03
- Batch size (bs): 131072
- Training iterations: 30517
- Training tokens (D): 4.0B
Model Description
StepLaw models are trained with various hyperparameter settings to enable research on scaling laws and hyperparameter optimization. This specific model was trained with learning rate 3.906e-03 and batch size 131072 for 30517 iterations, using a total of 4.0B training tokens.
Usage Example
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "StepLaw/StepLaw-N_119M-D_3.0B-LR3.906e-03-BS131072"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
# Generate text
inputs = tokenizer("A long time ago in a galaxy far, far away", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))