README.md

metadata

license: apache-2.0
tags:
  - StepLaw
  - causal-lm
language:
  - en
library_name: transformers
pipeline_tag: text-generation
model-index:
  - name: step2v2_0618_h960_ffnh9368_numh15_numl7_lr3.906e-03_bs512_ti7629_mlr1e-5
    results: []

Wandb Model Name: step2v2_0618_h960_ffnh9368_numh15_numl7_lr3.906e-03_bs512_ti7629_mlr1e-5

This model is part of the StepLaw-N_214M-D_7.0B collection.

Model Specifications

Architecture

• Hidden size (H): 960
• Feed-forward network size (FFN): 9368
• Attention heads: 15
• Layers: 7
• Parameter count: 214M

Training Parameters

• Learning rate (lr): 3.906e-03
• Batch size (bs): 1048576
• Training iterations: 7629
• Training tokens (D): 8.0B

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 1048576 for 7629 iterations, using a total of 8.0B training tokens.

Usage Example

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "StepLaw/StepLaw-N_214M-D_7.0B-LR3.906e-03-BS1048576"
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))