model

scripts/model.yaml

@@ -38,7 +38,8 @@ initial_checkpoint_dir:
 # from the latest checkpoint in ``out_dir``. An error will be raised if no checkpoint is found. Passing
 # ``'auto'`` will resume from the latest checkpoint but not error if no checkpoint exists.
 # (type: Union[bool, Literal["auto"], Path], default: False)
-resume: false
+# resume: false
+resume: "auto"
 
 # Data-related arguments. If not provided, the default is ``litgpt.data.TinyLlama``.
 # data: LitData
@@ -61,10 +62,11 @@ train:
   lr_warmup_steps: 2000
 
   # Number of epochs to train on (type: Optional[int], default: null)
-  epochs: 
+  epochs: 3
 
   # Total number of tokens to train on (type: Optional[int], default: 3000000000000)
-  max_tokens: 3000000000000
+  # max_tokens: 3000000000000
+  max_tokens: 3260735571 # 1591379 * 2049
 
   # Limits the number of optimizer steps to run. (type: Optional[int], default: null)
   max_steps: