tangledgroup
/

tangled-llama-33m-32k-base-v0.1

Text Generation

Inference Endpoints

Model card Files Files and versions Community

mtasic85 commited on 23 days ago

Commit

7911b8f

•

1 Parent(s): b347636

model

Files changed (1) hide show

scripts/model.yaml +2 -2

scripts/model.yaml CHANGED Viewed

@@ -62,11 +62,11 @@ train:
   lr_warmup_steps: 2000
   # Number of epochs to train on (type: Optional[int], default: null)
-  epochs: 3
   # Total number of tokens to train on (type: Optional[int], default: 3000000000000)
   # max_tokens: 3000000000000
-  max_tokens: 3260735571 # 1591379 * 2049
   # Limits the number of optimizer steps to run. (type: Optional[int], default: null)
   max_steps:

   lr_warmup_steps: 2000
   # Number of epochs to train on (type: Optional[int], default: null)
+  epochs:
   # Total number of tokens to train on (type: Optional[int], default: 3000000000000)
   # max_tokens: 3000000000000
+  max_tokens: 9782206713 # 1591379 * 2049 * 3
   # Limits the number of optimizer steps to run. (type: Optional[int], default: null)
   max_steps: