Applied fixes to dagshub logger

.gitignore

@@ -95,3 +95,4 @@ coverage.xml
 
 summarization-dagshub/
 /models
+default/

dvc.lock

@@ -10,22 +10,22 @@ stages:
       md5: 0900e2bb330df94cb045faddd0b945d1
       size: 1138285
     - path: params.yml
-      md5: 8ac76f9483ae2d78cf89a2e2be4e8446
+      md5: 200ce3c4d9f2e8b9eb040ef93eb22757
       size: 189
     - path: src/models/train_model.py
       md5: d57b5ff84bc29a8ea75e191027d70148
       size: 988
     outs:
     - path: models
-      md5: b8dd7baa6b7b85a7b4c2fcfbe3d831bf.dir
-      size: 243476333
-      nfiles: 5
+      md5: ff6de43e1d1f4d7c3d0bb3b551c1085f.dir
+      size: 486952666
+      nfiles: 10
     - path: reports/training_metrics.csv
-      md5: f0c89a07561ca8aea8ab3f4764b648e7
-      size: 26
+      md5: 62f71f6ba5390e07bc70e90ac3f1f0e8
+      size: 727
     - path: reports/training_params.yml
-      md5: 8a80554c91d9fca8acb82f023de02f11
-      size: 3
+      md5: 075736962fab2a5e5b3ff189c13e101b
+      size: 16
   eval:
     cmd: python src/models/evaluate_model.py
     deps:
@@ -33,32 +33,32 @@ stages:
       md5: 3cb7b63891f12d53b3ef3e81a2e93f8e
       size: 986944
     - path: models
-      md5: 688745a9fb1cc7c8580887bae3873a39.dir
+      md5: ff6de43e1d1f4d7c3d0bb3b551c1085f.dir
       size: 486952666
       nfiles: 10
     - path: params.yml
-      md5: d0f3e81bc9191e752a69761045a449d9
-      size: 196
+      md5: 200ce3c4d9f2e8b9eb040ef93eb22757
+      size: 189
     - path: src/models/evaluate_model.py
-      md5: aa01b1564d737fef54ae45d25c5018d1
-      size: 615
+      md5: 55d3aac9c8f024f7d2eb8ad5e0ae87ae
+      size: 688
     outs:
-    - path: reports/metrics.txt
-      md5: 27d21366dca75caa1bb3777575cb126b
-      size: 1596
+    - path: reports/metrics.csv
+      md5: e618e8c26e0def4e33abcad08ac35ac9
+      size: 1690
   process_data:
     cmd: python src/data/process_data.py
     deps:
     - path: data/raw
-      md5: d751713988987e9331980363e24189ce.dir
-      size: 0
-      nfiles: 0
+      md5: 2ab20ac1b58df875a590b07d0e04eb5b.dir
+      size: 1358833013
+      nfiles: 3
     - path: params.yml
-      md5: 8ac76f9483ae2d78cf89a2e2be4e8446
+      md5: 200ce3c4d9f2e8b9eb040ef93eb22757
       size: 189
     - path: src/data/process_data.py
-      md5: ba3ba7b7c8a905b736b6b0a28d2334c4
-      size: 623
+      md5: 7633b8978c523858d18b1ce9a5d3c8b7
+      size: 516
     outs:
     - path: data/processed/test.csv
       md5: 3cb7b63891f12d53b3ef3e81a2e93f8e
@@ -73,7 +73,7 @@ stages:
     cmd: python src/data/make_dataset.py
     deps:
     - path: params.yml
-      md5: 8ac76f9483ae2d78cf89a2e2be4e8446
+      md5: 200ce3c4d9f2e8b9eb040ef93eb22757
       size: 189
     - path: src/data/make_dataset.py
       md5: 9de71de0f8df5d0a7beb235ef7c7777d

reports/metrics.csv

@@ -0,0 +1,5 @@
+Name,Value,Timestamp,Step
+"Rouge 1","{'Rouge_1 Low Precision': 0.34885388166790793, 'Rouge_1 Low recall': 0.28871556132198656, 'Rouge_1 Low F1': 0.31058637096822267, 'Rouge_1 Mid Precision': 0.412435004251884, 'Rouge_1 Mid recall': 0.3386352228897427, 'Rouge_1 Mid F1': 0.3517931748124066, 'Rouge_1 High Precision': 0.47625451117848977, 'Rouge_1 High recall': 0.39086727645312935, 'Rouge_1 High F1': 0.3959993953753958}",1627559683895,1
+"Rouge 2","{'Rouge_2 Low Precision': 0.1259156300716482, 'Rouge_2 Low recall': 0.10333119800163641, 'Rouge_2 Low F1': 0.10992592662502373, 'Rouge_2 Mid Precision': 0.16879303949162833, 'Rouge_2 Mid recall': 0.13805319188028575, 'Rouge_2 Mid F1': 0.14400796293585816, 'Rouge_2 High Precision': 0.21844214485938712, 'Rouge_2 High recall': 0.1777722350788, 'Rouge_2 High F1': 0.18342627795315522}",1627559683895,1
+"Rouge L","{'Rouge_L Low Precision': 0.2322041975032734, 'Rouge_L Low recall': 0.194000575085051, 'Rouge_L Low F1': 0.20468107864660212, 'Rouge_L Mid Precision': 0.2797360675037497, 'Rouge_L Mid recall': 0.22647774162854406, 'Rouge_L Mid F1': 0.2361293941929179, 'Rouge_L High Precision': 0.3357160682858357, 'Rouge_L High recall': 0.2622222798536235, 'Rouge_L High F1': 0.27267217209978356}",1627559683895,1
+"rougeLsum","{'rougeLsum Low Precision': 0.29651536760563263, 'rougeLsum Low recall': 0.2432094838451322, 'rougeLsum Low F1': 0.26048483356867896, 'rougeLsum Mid Precision': 0.35317671791338556, 'rougeLsum Mid recall': 0.286187817596869, 'rougeLsum Mid F1': 0.2985727815225495, 'rougeLsum High Precision': 0.4134539668577922, 'rougeLsum High recall': 0.3365998852405162, 'rougeLsum High F1': 0.3454898564714797}",1627559683895,1

reports/metrics.txt

@@ -1 +0,0 @@
-{"Rouge 1": {"Rouge_1 Low Precision": 0.34885388166790793, "Rouge_1 Low recall": 0.28871556132198656, "Rouge_1 Low F1": 0.31058637096822267, "Rouge_1 Mid Precision": 0.412435004251884, "Rouge_1 Mid recall": 0.3386352228897427, "Rouge_1 Mid F1": 0.3517931748124066, "Rouge_1 High Precision": 0.47625451117848977, "Rouge_1 High recall": 0.39086727645312935, "Rouge_1 High F1": 0.3959993953753958}, "Rouge 2": {"Rouge_2 Low Precision": 0.1259156300716482, "Rouge_2 Low recall": 0.10333119800163641, "Rouge_2 Low F1": 0.10992592662502373, "Rouge_2 Mid Precision": 0.16879303949162833, "Rouge_2 Mid recall": 0.13805319188028575, "Rouge_2 Mid F1": 0.14400796293585816, "Rouge_2 High Precision": 0.21844214485938712, "Rouge_2 High recall": 0.1777722350788, "Rouge_2 High F1": 0.18342627795315522}, "Rouge L": {"Rouge_L Low Precision": 0.2322041975032734, "Rouge_L Low recall": 0.194000575085051, "Rouge_L Low F1": 0.20468107864660212, "Rouge_L Mid Precision": 0.2797360675037497, "Rouge_L Mid recall": 0.22647774162854406, "Rouge_L Mid F1": 0.2361293941929179, "Rouge_L High Precision": 0.3357160682858357, "Rouge_L High recall": 0.2622222798536235, "Rouge_L High F1": 0.27267217209978356}, "rougeLsum": {"rougeLsum Low Precision": 0.29651536760563263, "rougeLsum Low recall": 0.2432094838451322, "rougeLsum Low F1": 0.26048483356867896, "rougeLsum Mid Precision": 0.35317671791338556, "rougeLsum Mid recall": 0.286187817596869, "rougeLsum Mid F1": 0.2985727815225495, "rougeLsum High Precision": 0.4134539668577922, "rougeLsum High recall": 0.3365998852405162, "rougeLsum High F1": 0.3454898564714797}}

reports/training_metrics.csv

@@ -0,0 +1,19 @@
+Name,Value,Timestamp,Step
+"train_loss",4.101656913757324,1627559482684,49
+"epoch",0,1627559482684,49
+"val_loss",2.6896562576293945,1627559491036,57
+"epoch",0,1627559491036,57
+"train_loss",4.598623752593994,1627559499092,99
+"epoch",1,1627559499092,99
+"val_loss",2.472928047180176,1627559505946,115
+"epoch",1,1627559505946,115
+"train_loss",1.4196646213531494,1627559515636,149
+"epoch",2,1627559515636,149
+"val_loss",2.311669111251831,1627559521015,173
+"epoch",2,1627559521015,173
+"train_loss",0.9744294881820679,1627559532066,199
+"epoch",3,1627559532066,199
+"val_loss",2.2401840686798096,1627559535896,231
+"epoch",3,1627559535896,231
+"train_loss",2.785480260848999,1627559548623,249
+"epoch",4,1627559548623,249

reports/training_metrics.txt

@@ -1 +0,0 @@
-{"train_loss": 2.785480260848999, "epoch": 4, "trainer/global_step": 289, "_runtime": 88, "_timestamp": 1627353229, "_step": 9, "val_loss": 2.181020975112915}

requirements.txt

@@ -3,7 +3,7 @@ datasets==1.10.2
 pytorch_lightning==1.3.5
 transformers==4.9.0
 torch==1.9.0
-dagshub==0.1.6
+dagshub==0.1.7
 pandas==1.1.5
 rouge_score
 pyyaml

src/data/process_data.py

@@ -11,8 +11,6 @@ def process_data(split='train'):
     df = pd.read_csv('data/raw/{}.csv'.format(split))
     df.columns = ['Unnamed: 0', 'input_text', 'output_text']
     df = df.sample(frac=params['split'], replace=True, random_state=1)
-    if os.path.exists("data/raw/{}.csv".format(split)):
-        os.remove("data/raw/{}.csv".format(split))
     df.to_csv('data/processed/{}.csv'.format(split))
 
 

src/models/evaluate_model.py

@@ -18,7 +18,7 @@ def evaluate_model():
     model.load_model(model_type=params['model_type'], model_dir=params['model_dir'])
     results = model.evaluate(test_df=test_df, metrics=params['metric'])
 
-    with dagshub_logger(should_log_hparams=False) as logger:
+    with dagshub_logger(metrics_path='reports/metrics.csv', should_log_hparams=False) as logger:
         logger.log_metrics(results)