pycache

finetune_classification_large_mt5.gin

@@ -0,0 +1,34 @@
+from __gin__ import dynamic_registration
+import tasks
+import seqio 
+
+import __main__ as train_script
+from t5.data import mixtures
+from t5x import models
+from t5x import partitioning
+from t5x import utils
+
+include 't5x/examples/t5/mt5/large.gin'
+include "t5x/configs/runs/finetune.gin"
+
+MIXTURE_OR_TASK_NAME = %gin.REQUIRED
+TASK_FEATURE_LENGTHS = {"inputs": 512, "targets": 512}
+INITIAL_CHECKPOINT_PATH = %gin.REQUIRED
+TRAIN_STEPS = %gin.REQUIRED  # 1000000 pre-trained steps + 10000 fine-tuning steps.
+USE_CACHED_TASKS = False
+DROPOUT_RATE = 0.1
+RANDOM_SEED = 0
+
+#Fixing a small error
+infer_eval/utils.DatasetConfig:
+  task_feature_lengths = %TASK_FEATURE_LENGTHS
+
+#Saving every 1000 steps
+utils.SaveCheckpointConfig:
+  period = 1000
+  keep = 1  # number of checkpoints to keep
+
+# Might have to ba changed based on architecture
+# partitioning.PjitPartitioner.num_partitions = 1
+
+

finetune_classification_large_scand.gin

@@ -0,0 +1,37 @@
+from __gin__ import dynamic_registration
+import tasks
+import seqio
+
+import __main__ as train_script
+from t5.data import mixtures
+from t5x import models
+from t5x import partitioning
+from t5x import utils
+
+include "t5x/examples/t5/t5_1_1/large.gin"
+include "t5x/configs/runs/finetune.gin"
+
+MIXTURE_OR_TASK_NAME = %gin.REQUIRED
+TASK_FEATURE_LENGTHS = {"inputs": 512, "targets": 512}
+INITIAL_CHECKPOINT_PATH = %gin.REQUIRED
+TRAIN_STEPS = %gin.REQUIRED  # 1000000 pre-trained steps + 10000 fine-tuning steps.
+USE_CACHED_TASKS = False
+DROPOUT_RATE = 0.1
+RANDOM_SEED = 0
+
+#Fixing a small error
+infer_eval/utils.DatasetConfig:
+  task_feature_lengths = %TASK_FEATURE_LENGTHS
+
+#Saving every 1000 steps
+utils.SaveCheckpointConfig:
+  period = 1000
+  keep = 1  # number of checkpoints to keep
+
+# Might have to ba changed based on architecture
+# partitioning.PjitPartitioner.num_partitions = 1
+
+VOCABULARY = @seqio.SentencePieceVocabulary()
+seqio.SentencePieceVocabulary.sentencepiece_model_file = "gs://nb-t5/t5/vocabs/wikipedia/no-da-en-sv-nn-is_32000_unigram.sp.model"
+seqio.SentencePieceVocabulary.extra_ids = 100
+