Merge branch 'master' of https://dagshub.com/gagan3012/summarization

.gitignore

@@ -94,4 +94,5 @@ coverage.xml
 /data
 
 wandb/
-summarization-dagshub/
+summarization-dagshub/
+/models

data.dvc

@@ -1,14 +1,14 @@
 deps:
 - path: params.yml
-  md5: 0d9abcc4df44299e22f5e75f88b493eb
-  size: 170
+  md5: 1c81ba3474bff51c4e36e59af83ba4eb
+  size: 188
 - path: src/data/make_dataset.py
-  md5: dfb6390a95395535b92a5c59b3e3b559
-  size: 672
+  md5: 9de71de0f8df5d0a7beb235ef7c7777d
+  size: 772
 cmd: python src/data/make_dataset.py
 outs:
-- md5: 2ab20ac1b58df875a590b07d0e04eb5b.dir
-  nfiles: 3
+- md5: d751713988987e9331980363e24189ce.dir
+  nfiles: 0
   path: data/raw
-  size: 1359144987
-md5: 158faff967ee7ee05e381cb6c9c7e217
+  size: 0
+md5: 93aa72cba714454669e300543686901e

dvc.lock

@@ -1,34 +1,68 @@
-train:
-  cmd: python src/models/train_model.py
-  deps:
-  - path: data/processed
-    md5: d751713988987e9331980363e24189ce.dir
-  - path: src/models/train_model.py
-    md5: d41d8cd98f00b204e9800998ecf8427e
-  outs:
-  - path: models
-    md5: d751713988987e9331980363e24189ce.dir
-  - path: reports/training_metrics.txt
-    md5: d41d8cd98f00b204e9800998ecf8427e
-eval:
-  cmd: python src/models/predict_model.py
-  deps:
-  - path: data/processed
-    md5: d751713988987e9331980363e24189ce.dir
-  - path: models
-    md5: d751713988987e9331980363e24189ce.dir
-  - path: src/models/predict_model.py
-    md5: d41d8cd98f00b204e9800998ecf8427e
-  outs:
-  - path: reports/metrics.txt
-    md5: d41d8cd98f00b204e9800998ecf8427e
-process_data:
-  cmd: python src/data/make_dataset.py
-  deps:
-  - path: data/raw
-    md5: d751713988987e9331980363e24189ce.dir
-  - path: src/data/make_dataset.py
-    md5: d41d8cd98f00b204e9800998ecf8427e
-  outs:
-  - path: data/processed
-    md5: d751713988987e9331980363e24189ce.dir
+schema: '2.0'
+stages:
+  train:
+    cmd: python src/models/train_model.py
+    deps:
+    - path: data/processed/train.csv
+      md5: 707c5ed455a15ec48965daf92fed7df6
+      size: 12653913
+    - path: data/processed/validation.csv
+      md5: 1e021dc163cc87a32cef74a98e4a0d51
+      size: 558403
+    - path: params.yml
+      md5: 1c81ba3474bff51c4e36e59af83ba4eb
+      size: 188
+    - path: src/models/train_model.py
+      md5: fca8acf70f09cecd679ca1ddb2eef6a9
+      size: 1198
+    outs:
+    - path: models
+      md5: 889c9e429c8c0d7aeb66c6204c983645.dir
+      size: 243476333
+      nfiles: 5
+    - path: reports/training_metrics.txt
+      md5: 35f2808d4380b428f3de8f4c6b2c119e
+      size: 124
+  eval:
+    cmd: python src/models/evaluate_model.py
+    deps:
+    - path: data/processed/test.csv
+      md5: 5f2bfb37d55a13ead3c81564dbee2fd5
+      size: 508508
+    - path: models
+      md5: 889c9e429c8c0d7aeb66c6204c983645.dir
+      size: 243476333
+      nfiles: 5
+    - path: params.yml
+      md5: 1c81ba3474bff51c4e36e59af83ba4eb
+      size: 188
+    - path: src/models/evaluate_model.py
+      md5: aa01b1564d737fef54ae45d25c5018d1
+      size: 615
+    outs:
+    - path: reports/metrics.txt
+      md5: d9557204b6599a6b0db7d5f1ea80559d
+      size: 1604
+  process_data:
+    cmd: python src/data/process_data.py
+    deps:
+    - path: data/raw
+      md5: d751713988987e9331980363e24189ce.dir
+      size: 0
+      nfiles: 0
+    - path: params.yml
+      md5: 1c81ba3474bff51c4e36e59af83ba4eb
+      size: 188
+    - path: src/data/process_data.py
+      md5: ba3ba7b7c8a905b736b6b0a28d2334c4
+      size: 623
+    outs:
+    - path: data/processed/test.csv
+      md5: 5f2bfb37d55a13ead3c81564dbee2fd5
+      size: 508508
+    - path: data/processed/train.csv
+      md5: 707c5ed455a15ec48965daf92fed7df6
+      size: 12653913
+    - path: data/processed/validation.csv
+      md5: 1e021dc163cc87a32cef74a98e4a0d51
+      size: 558403

reports/metrics.txt

@@ -1 +1 @@
-{"Rouge 1": {"Rouge_1 Low Precision": 0.2647863247863248, "Rouge_1 Low recall": 0.2538409703504043, "Rouge_1 Low F1": 0.2597478425026969, "Rouge_1 Mid Precision": 0.40009586509586514, "Rouge_1 Mid recall": 0.3587281883955171, "Rouge_1 Mid F1": 0.36263654600041045, "Rouge_1 High Precision": 0.5354054054054054, "Rouge_1 High recall": 0.47236842105263166, "Rouge_1 High F1": 0.4228560800505895}, "Rouge 2": {"Rouge_2 Low Precision": 0.077807881773399, "Rouge_2 Low recall": 0.07660141531109273, "Rouge_2 Low F1": 0.08017595307917888, "Rouge_2 Mid Precision": 0.15999684223822153, "Rouge_2 Mid recall": 0.13308241243725116, "Rouge_2 Mid F1": 0.1380390874401532, "Rouge_2 High Precision": 0.26981684981684984, "Rouge_2 High recall": 0.18956340956340956, "Rouge_2 High F1": 0.19602951806216276}, "Rouge L": {"Rouge_L Low Precision": 0.16650675675675689, "Rouge_L Low recall": 0.16954887218045112, "Rouge_L Low F1": 0.1716514336917564, "Rouge_L Mid Precision": 0.2852702702702703, "Rouge_L Mid recall": 0.24812030075187969, "Rouge_L Mid F1": 0.2572047855522077, "Rouge_L High Precision": 0.4217567567567567, "Rouge_L High recall": 0.3095829195630586, "Rouge_L High F1": 0.3204671857619578}, "rougeLsum": {"rougeLsum Low Precision": 0.23108108108108105, "rougeLsum Low recall": 0.22690452546460493, "rougeLsum Low F1": 0.23205253679924837, "rougeLsum Mid Precision": 0.353987063987064, "rougeLsum Mid recall": 0.3173180592991914, "rougeLsum Mid F1": 0.31927588996763756, "rougeLsum High Precision": 0.4851282051282051, "rougeLsum High recall": 0.4197616683217477, "rougeLsum High F1": 0.3816091954022988}}
+{"Rouge 1": {"Rouge_1 Low Precision": 0.35879412940695404, "Rouge_1 Low recall": 0.273733478679664, "Rouge_1 Low F1": 0.30242065341410873, "Rouge_1 Mid Precision": 0.4338533395974997, "Rouge_1 Mid recall": 0.32042622316817226, "Rouge_1 Mid F1": 0.358115556137624, "Rouge_1 High Precision": 0.5280148017181922, "Rouge_1 High recall": 0.37164701807593853, "Rouge_1 High F1": 0.4196716488587748}, "Rouge 2": {"Rouge_2 Low Precision": 0.14079866776770866, "Rouge_2 Low recall": 0.10234397527752646, "Rouge_2 Low F1": 0.11454339253852734, "Rouge_2 Mid Precision": 0.20278273142043576, "Rouge_2 Mid recall": 0.1437386638831592, "Rouge_2 Mid F1": 0.1626240666356349, "Rouge_2 High Precision": 0.2834076711211276, "Rouge_2 High recall": 0.19964227594691578, "Rouge_2 High F1": 0.22508874620349306}, "Rouge L": {"Rouge_L Low Precision": 0.24715297672294737, "Rouge_L Low recall": 0.19726701009989336, "Rouge_L Low F1": 0.21458962512439578, "Rouge_L Mid Precision": 0.31881722334892215, "Rouge_L Mid recall": 0.23988574061697504, "Rouge_L Mid F1": 0.26443860973621613, "Rouge_L High Precision": 0.40068438045602844, "Rouge_L High recall": 0.2924354094810886, "Rouge_L High F1": 0.32317934985902896}, "rougeLsum": {"rougeLsum Low Precision": 0.313922368347619, "rougeLsum Low recall": 0.24053636172149256, "rougeLsum Low F1": 0.26759225635037753, "rougeLsum Mid Precision": 0.38675681843219567, "rougeLsum Mid recall": 0.28576071040262474, "rougeLsum Mid F1": 0.319041888317666, "rougeLsum High Precision": 0.46780971284574424, "rougeLsum High recall": 0.3329834309090794, "rougeLsum High F1": 0.37448259921289817}}

reports/training_metrics.txt

@@ -1 +1 @@
-{"val_loss": 3.1214792728424072, "epoch": 9, "trainer/global_step": 149, "_runtime": 159, "_timestamp": 1627289013, "_step": 12, "train_loss": 2.0990500450134277}
+{"val_loss": 4.544037818908691, "epoch": 2, "trainer/global_step": 44, "_runtime": 31, "_timestamp": 1627346856, "_step": 2}