If train the GPT-2 [architecture] from scratch on enwik9 for your benchmark Matt, don't we throw away the model once done the file? There is no problem with size then during training. So why isn't GPT-2 put against your contenst? ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tcc6753a33ad48f78-Me2a89c94513fc84cc8017412 Delivery options: https://agi.topicbox.com/groups/agi/subscription
- [agi] Artemiy Margaritov Wins €9000 In the First 10... James Bowery
- [agi] Re: Artemiy Margaritov Wins €9000 In the... immortal . discoveries
- Re: [agi] Re: Artemiy Margaritov Wins €900... Matt Mahoney
- Re: [agi] Re: Artemiy Margaritov Wins ... immortal . discoveries
- Re: [agi] Re: Artemiy Margaritov W... immortal . discoveries
- Re: [agi] Re: Artemiy Margari... immortal . discoveries
- [agi] Re: Artemiy Margaritov Wins €9000 In... immortal . discoveries
- Re: [agi] Re: Artemiy Margaritov Wins ... Matt Mahoney
- Re: [agi] Re: Artemiy Margaritov W... immortal . discoveries
