rxnn 0.2.6__py3-none-any.whl → 0.2.7__py3-none-any.whl

rxnn/training/mrl.py

@@ -283,7 +283,12 @@ class MRLTrainer:
         with torch.no_grad():
             # 2. Collect episode trajectories for all batches in dataset
             for batch_idx, batch in enumerate(dataloader):
-                if batch['query']['input_ids'].size(0) != batch_size:
+                print('first query size: ', batch['query']['input_ids'].size())
+                print('first answer size: ', batch['answer']['input_ids'].size())
+                print('next query size: ', batch['interactions'][0]['query']['input_ids'].size())
+                print('Interactions len: ', len(batch['interactions']))
+
+                if batch['query']['input_ids'].size(0) != batch_size or batch['interactions'][0]['query']['input_ids'].size(0) != batch_size:
                     print('Incorrect batch size: ', batch['query']['input_ids'].size(0))
                 else:
                     self._increment_steps('collect')
@@ -304,9 +309,11 @@ class MRLTrainer:
                     # 7. Run training strategy for follow-up interactions
                     episode_steps = []
                     episode_rewards = []
+
                     for i, interaction in enumerate(interactions):
                         # 8. Generate batch of answers based on batch of follow-up queries
                         next_query = self._move_batch(interaction['query'])
+                        print('first query: ', next_query['input_ids'].size())
                         generated_answer, log_probs = self.generate_answer(next_query)
 
                         is_last_interaction = (i + 1) == interactions_len

{rxnn-0.2.6.dist-info → rxnn-0.2.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rxnn
-Version: 0.2.6
+Version: 0.2.7
 Summary: RxNN: Reactive Neural Networks Platform
 License: Apache-2.0
 Keywords: deep-learning,ai,machine-learning

{rxnn-0.2.6.dist-info → rxnn-0.2.7.dist-info}/RECORD

@@ -16,7 +16,7 @@ rxnn/training/bml.py,sha256=FJszaQXOLx2ZHBa1CQpyMrG8i4Kj14E-gzDAEK_Ei5k,17272
 rxnn/training/callbacks.py,sha256=o68IPFJyWM1CGooPRDNU9DfNcy4H_o0PcKDTn_ZLnKA,35053
 rxnn/training/dataset.py,sha256=XeRzo0KUYyQ43XjZ3o6Jban9ePIRtpHsqUmeKAQPRQk,50305
 rxnn/training/models.py,sha256=renPa5YH443XNTMFI-YTCwi5vNp3QzwF5UXedNd5hDk,5187
-rxnn/training/mrl.py,sha256=G1sxKrnfkggHRqSInjk17PfpNhj5neqfh5Y2RUabJLk,39392
+rxnn/training/mrl.py,sha256=qGEz9C8O4Yq5P0_WTdvl0QWzdDtTZZVeoNTON6ICB74,39877
 rxnn/training/reward.py,sha256=i0nhrPCDgy1di89HWylRBS6cQ7rSSxJUiS3TX8fiiHE,5614
 rxnn/training/rl.py,sha256=FKrBOBAfNub_qzkceFQR-WUtCBffC6oGHE8wlPsz2YA,2682
 rxnn/training/scheduler.py,sha256=LcjU35mEwz2U5x3U6tLfeeYlBqMxbFSxYzJYuXkWbSY,1408
@@ -32,7 +32,7 @@ rxnn/transformers/moe.py,sha256=j6jEx6Ip0zttlUZKKn82azxo95lkLZs-H2GLSMD88hY,5859
 rxnn/transformers/positional.py,sha256=1PjcJybUzeQlIKJI4tahAGZcYgCRCL0otxs7mpsNuzM,4410
 rxnn/transformers/sampler.py,sha256=2dpUQv88ekZa_CMSPLrXvB6X684wxUE2bDVznsi5ACs,17429
 rxnn/utils.py,sha256=ihb6OTyDtPiocB_lOvnq7eOkjjpCkgs8wxvXUBNQ7mM,996
-rxnn-0.2.6.dist-info/LICENSE,sha256=C8coDFIUYuOcke4JLPwTqahQUCyXyGq6WOaigOkx8tY,11275
-rxnn-0.2.6.dist-info/METADATA,sha256=eoxdTixI_-XuziJ64YG3QGa8TD0f06q95stHWgNzSjE,25959
-rxnn-0.2.6.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-rxnn-0.2.6.dist-info/RECORD,,
+rxnn-0.2.7.dist-info/LICENSE,sha256=C8coDFIUYuOcke4JLPwTqahQUCyXyGq6WOaigOkx8tY,11275
+rxnn-0.2.7.dist-info/METADATA,sha256=xyc69x0B-y2j_ww61VhAeKoQL3pvMMXe2hUV2QNWKZI,25959
+rxnn-0.2.7.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+rxnn-0.2.7.dist-info/RECORD,,