diff --git a/.vscode/launch.json b/.vscode/launch.json index 0705eb8..e0c9bdf 100644 --- a/.vscode/launch.json +++ b/.vscode/launch.json @@ -17,11 +17,11 @@ "env.train.id=BreakoutNoFrameskip-v4", // # make it start early "training.tokenizer.start_after_epochs=1", - "training.world_model.start_after_epochs=1", - "training.actor_critic.start_after_epochs=1", - "training.tokenizer.steps_per_epoch=20", - "training.world_model.steps_per_epoch=10", - "training.actor_critic.steps_per_epoch=20", + "training.world_model.start_after_epochs=2", + "training.actor_critic.start_after_epochs=3", + "training.tokenizer.steps_per_epoch=40", + "training.world_model.steps_per_epoch=40", + "training.actor_critic.steps_per_epoch=40", ] } ] diff --git a/research_journal.md b/research_journal.md index 243c94c..689861b 100644 --- a/research_journal.md +++ b/research_journal.md @@ -102,3 +102,12 @@ Debugging: So I got it training, but during imagination it passes in a single token with no past steps. But the slicer seems to need at least on block? And so I get none? hmm it's because num_kept_tokens is 16 not 1. So there should be a whole block passed in ? + +wait apparently it's also a problem in the normal repo.... I confuse! maybe it's my config! maybe I need >larger than block size. nope + +hmm it still happens in the original repo with my debug params. maybe it's my debug params + + +... trying a full run without my debug params... + +note trains.world_model.batch_num_samples:4 fill 20GB gpu ram for the 3b stability ai llm