rename

dev_scripts/sample_jsons/py36-sample-data.json

@@ -0,0 +1,24 @@
+{
+    "name": "sample_dataset_name",
+    "version": [3, 6],
+    "save_to_dir": "./save_dir/",
+    "huggingface_user": "sample_user",
+
+    "data_requests":
+    [
+        {
+            "name": "dataset",
+            "source_path": "./dataset",
+            "num_train": 200,
+            "num_test": 200,
+            "num_valid": 200
+        },
+        {
+            "name": "dataset2",
+            "source_path": "./dataset2",
+            "num_train": 200,
+            "num_test": 200,
+            "num_valid": 200
+        }
+    ]
+}

dev_scripts/sample_jsons/py36-sample-segmentation.json

@@ -0,0 +1,18 @@
+{
+    "base_repo_name": "sample_user/sample_segmenter_name",
+    "dataset_repo_name": "sample_user/segmentation-sample_dataset_name",
+    "pretrained_mlm_repo_name": "",
+    "cache_dir": "./cache-dir/",
+    "max_token_length": 512,
+    "dataset_percentage": 100,
+    "mlm_training_parameters": {
+        "batch_size": 48,
+        "epochs": 2,
+        "learning_rate": 5e-5
+    },
+    "segmentation_training_parameters": {
+        "batch_size": 48,
+        "epochs": 2,
+        "learning_rate": 2e-5
+    }
+}

dev_scripts/sample_jsons/py36-sample-statement.json

@@ -0,0 +1,16 @@
+{
+    "base_repo_name": "sample_user/sample_name",
+    "dataset_repo_name": "sample_user/statement-sample_dataset_name",
+    "tokenizer_repo_name": "sample_user/sample_name-tok",
+    "pretrained_seq2seq_repo_name": "Salesforce/codet5-base",
+    "cache_dir": "./cache-dir/",
+    "max_token_length": 256,
+    "dataset_percentage": 100,
+    "do_eval": true,
+    "fp16": true,
+    "statement_training_parameters": {
+        "batch_size": 24,
+        "epochs": 2,
+        "learning_rate": 2e-5
+    }
+}