Downloads · 30 days
0
alextsiak/llama8b-instruct-curriculum-fixed-easy-hard-checkpoint-500
llama8b-instruct-curriculum-fixed-easy-hard-checkpoint-500 is a machine learning model from alextsiak. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
curriculum learning - llama3-8b-instruct finetuned on easy/hard stages of clem games, with hard stage being the (game,exp,taskid) tuples the base model failed at.
Downloads · 30 days
0
Access
Public
Updated Sep 19, 2025
Repo size
5.2 GB
Likes
0
Public
Click a slice to open those files.
.pt3.4 GB · 66%
From the Hugging Face model README
curriculum learning - llama3-8b-instruct finetuned on easy/hard stages of clem games, with hard stage being the (game,exp,task_id) tuples the base model failed at.
this is the model trained on both the easy stage (successful task_ids of base model) and the hard stage (failed task_ids)
batch_size: 4 learning_rate: 0.0002 max_steps: 500 lora_r: 64 lora_alpha: 32 lora_dropout: 0.05