rxnn 0.1.65__py3-none-any.whl → 0.1.67__py3-none-any.whl

rxnn/training/dataset.py

@@ -15,7 +15,7 @@ class BaseDataset(Dataset):
             max_seq_len: int = 1024,
             hf_field: str = 'text',
             cache_tokenized: bool = False,
-            cache_remove_text: bool = False,
+            cache_remove_text: bool = True,
             *args,
             **kwargs
     ):
@@ -29,6 +29,9 @@ class BaseDataset(Dataset):
         self.cache_remove_text = cache_remove_text
         self.inputs = [] if self.cache_tokenized else None
 
+    def __len__(self):
+        return len(self.texts if not self.is_pre_tokenized else self.inputs)
+
     def get_tokenized_text(self, idx: int):
         if self.is_pre_tokenized:
             return self.inputs[idx]
@@ -63,8 +66,12 @@ class BaseDataset(Dataset):
 
     def get_subset(self, size: float, from_start: bool = False, use_hf_select: bool = False, **kwargs) -> "BaseDataset":
         split_point = int(len(self.texts) * ((1 - size) if not from_start else size))
-        subset = self.texts.select(range(split_point, len(self.texts))) if use_hf_select and not isinstance(self.texts, list) else self.texts[:split_point]
-        self.texts = self.texts.select(range(split_point)) if use_hf_select and not isinstance(self.texts, list) else self.texts[split_point:]
+        if use_hf_select and not isinstance(self.texts, list):
+            subset = self.texts.select(range(split_point, len(self.texts)) if not from_start else range(split_point))
+            self.texts = self.texts.select(range(split_point) if not from_start else range(split_point, len(self.texts)))
+        else:
+            subset = self.texts[split_point:-1] if not from_start else self.texts[0:split_point]
+            self.texts = self.texts[0:split_point] if not from_start else self.texts[split_point:-1]
         return self.__class__(subset, self.tokenizer, self.max_seq_len, self.hf_field, **kwargs)
 
     def pre_tokenize(self, remove_texts: bool = True):
@@ -209,9 +216,6 @@ class JointLMDataset(BaseDataset):
             'attention_mask': attention_mask,
         }
 
-    def __len__(self):
-        return len(self.texts)
-
 
 class MaskedLMDataset(BaseDataset):
     def __init__(
@@ -249,9 +253,6 @@ class MaskedLMDataset(BaseDataset):
             'labels': labels
         }
 
-    def __len__(self):
-        return len(self.texts)
-
 
 class AutoregressiveLMDataset(BaseDataset):
     def __init__(
@@ -277,6 +278,3 @@ class AutoregressiveLMDataset(BaseDataset):
             'attention_mask': attention_mask,
             'targets': targets
         }
-
-    def __len__(self):
-        return len(self.texts)

{rxnn-0.1.65.dist-info → rxnn-0.1.67.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rxnn
-Version: 0.1.65
+Version: 0.1.67
 Summary: RxNN: Reactive Neural Networks Platform
 License: Apache-2.0
 Keywords: deep-learning,ai,machine-learning

{rxnn-0.1.65.dist-info → rxnn-0.1.67.dist-info}/RECORD

@@ -12,7 +12,7 @@ rxnn/training/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 rxnn/training/base.py,sha256=xPMA2Bg9-oUZvSZg67ls2p7Gk9pZ9IHUiIJwUzSe2K8,11766
 rxnn/training/bml.py,sha256=S1ZaXTybzeJH7uVFamCr4TPl2bLyZ5xmn_lSsjThTiM,19162
 rxnn/training/callbacks.py,sha256=_YfMKY_eFdc-tubhO9nYH2PXDZDQwlSI74FVOoCXpQg,22108
-rxnn/training/dataset.py,sha256=fKTNtDOAMSuRPbSl0yy0-k_xQ5o-AF6pqwKw9tC-7Mw,11328
+rxnn/training/dataset.py,sha256=SdQj5gh3LeqK8Q1n_uDXizgaw1leHmkXX52ydWtlLPQ,11479
 rxnn/training/scheduler.py,sha256=ow6oALzWjWQmHSpcJEjv6tg4g4CDMvr73TypxfcefMc,712
 rxnn/training/tokenizer.py,sha256=umaLByMBx_NMrQElA45HLm9gkuzyKWDTFaKVd-CjXl0,8344
 rxnn/transformers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -25,7 +25,7 @@ rxnn/transformers/moe.py,sha256=j6jEx6Ip0zttlUZKKn82azxo95lkLZs-H2GLSMD88hY,5859
 rxnn/transformers/positional.py,sha256=2l38RS0Dini3f6Z3LUHr3XwWzg1UK7fO2C6wazWDAYU,4292
 rxnn/transformers/sampler.py,sha256=poWBpxg1iuK5gEJtxHkk5VVfS9V48hs2Olqdhy_Gw8c,6548
 rxnn/utils.py,sha256=d5U8i5ukovgDyqiycc2AoxObTz_eF_bgo2MKvdtJ98s,467
-rxnn-0.1.65.dist-info/LICENSE,sha256=C8coDFIUYuOcke4JLPwTqahQUCyXyGq6WOaigOkx8tY,11275
-rxnn-0.1.65.dist-info/METADATA,sha256=wFv7U3aEMscWvxERWl2x-qHO2aBc5LPF79uV9RUzbyQ,16579
-rxnn-0.1.65.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-rxnn-0.1.65.dist-info/RECORD,,
+rxnn-0.1.67.dist-info/LICENSE,sha256=C8coDFIUYuOcke4JLPwTqahQUCyXyGq6WOaigOkx8tY,11275
+rxnn-0.1.67.dist-info/METADATA,sha256=4qyjqZnjWKZfCZugnoGS_yAOAXQTCM8jUi9r2t_No50,16579
+rxnn-0.1.67.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+rxnn-0.1.67.dist-info/RECORD,,