hf roberta base epoch1 (fix)

hf_roberta_base/02_load_dataset.py

@@ -1,26 +1,38 @@
 import pickle
-from datasets import load_dataset
+from datasets import load_dataset, Dataset
 from transformers import AutoTokenizer
 from tqdm import tqdm
 from sklearn.preprocessing import MinMaxScaler
 import numpy as np
 
-dataset = load_dataset('csv', sep='\t', data_files={'train': ['./train_huggingface_format.csv'], 'test': ['./dev-0_huggingface_format.csv']})
-test_dataset_A = load_dataset('csv', sep='\t', data_files='test-A_huggingface_format.csv')
-
+#dataset = load_dataset('csv', sep='\t', data_files={'train': ['./train_huggingface_format.csv'], 'test': ['./dev-0_huggingface_format.csv']})
+#test_dataset_A = load_dataset('csv', sep='\t', data_files='test-A_huggingface_format.csv')
+#
 tokenizer = AutoTokenizer.from_pretrained('roberta-base')
-
+#
 def tokenize_function(examples):
     t = tokenizer(examples["text"], padding="max_length", truncation=True, max_length=512)
     return t
+#
+#test_tokenized_datasets_A = test_dataset_A.map(tokenize_function, batched=True)
+#tokenized_datasets = dataset.map(tokenize_function, batched=True)
 
-test_tokenized_datasets_A = test_dataset_A.map(tokenize_function, batched=True)
-tokenized_datasets = dataset.map(tokenize_function, batched=True)
+def get_dataset_dict(dataset):
+    with open(dataset) as f_in:
+        next(f_in)
+        d = dict()
+        d['year'] = list()
+        d['text'] = list()
+        for l in f_in:
+            y,t = l.rstrip().split('\t')
+            d['year'].append(y)
+            d['text'].append(t)
+    return d
 
-train_dataset = tokenized_datasets["train"].shuffle(seed=42)
-eval_dataset_full = tokenized_datasets["test"]
-eval_dataset_small = tokenized_datasets["test"].select(range(2000))
-test_dataset_A = test_tokenized_datasets_A["train"]
+train_dataset = Dataset.from_dict(get_dataset_dict('train_huggingface_format.csv')).map(tokenize_function, batched=True).shuffle(seed=42)
+eval_dataset_full = Dataset.from_dict(get_dataset_dict('dev-0_huggingface_format.csv')).map(tokenize_function, batched=True).shuffle(seed=42)
+eval_dataset_small = eval_dataset_full.select(range(2000))
+test_dataset_A = Dataset.from_dict(get_dataset_dict('test-A_huggingface_format.csv')).map(tokenize_function, batched=True).shuffle(seed=42)
 
 
 scalers = dict()
@@ -34,7 +46,7 @@ def add_scaled(example):
 train_dataset = train_dataset.map(add_scaled)
 eval_dataset_full = eval_dataset_full.map(add_scaled)
 eval_dataset_small = eval_dataset_small.map(add_scaled)
-#test_dataset_A = test_dataset_A.map(add_scaled)
+test_dataset_A = test_dataset_A.map(add_scaled)
 
 
 with open('train_dataset.pickle','wb') as f_p:

hf_roberta_base/03_train_pytorch_regression.py

@@ -10,7 +10,6 @@ from tqdm.auto import tqdm
 
 BATCH_SIZE = 4
 
-
 with open('train_dataset.pickle','rb') as f_p:
     train_dataset = pickle.load(f_p)
 
@@ -29,14 +28,14 @@ model = AutoModelForSequenceClassification.from_pretrained('roberta-base', num_l
 optimizer = AdamW(model.parameters(), lr=1e-6)
 
 
-num_epochs = 3
+num_epochs = 1
 num_training_steps = num_epochs * len(train_dataloader)
-lr_scheduler = get_scheduler(
-    "linear",
-    optimizer=optimizer,
-    num_warmup_steps=0,
-    num_training_steps=num_training_steps
-)
+#lr_scheduler = get_scheduler(
+#    "linear",
+#    optimizer=optimizer,
+#    num_warmup_steps=0,
+#    num_training_steps=num_training_steps
+#)
 
 
 device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
@@ -71,7 +70,7 @@ def eval():
         outputs = model(**batch)
         loss = outputs.loss
         eval_loss += loss.item()
-    print(f'eval loss: {eval_loss /  i }')
+    print(f'epoch {epoch} eval loss: {eval_loss /  i }')
     model.train()
 
 
@@ -84,14 +83,14 @@ for epoch in range(num_epochs):
         loss.backward()
 
         optimizer.step()
-        lr_scheduler.step()
+        #lr_scheduler.step()
         optimizer.zero_grad()
         progress_bar.update(1)
 
         train_loss += loss.item()
         #import pdb; pdb.set_trace()
         if i % 5000 == 0 and i > 1 :
-            print(f'train loss: {train_loss /  5000 }', end = '\t\t')
+            print(f' epoch {epoch} train loss: {train_loss /  5000 }', end = '\t\t')
             train_loss = 0.0
             eval()
 

hf_roberta_base/04_predict.py

@@ -20,7 +20,7 @@ with open('eval_dataset_full.pickle','rb') as f_p:
     eval_dataset_full = pickle.load(f_p)
 
 device = 'cuda'
-model = AutoModelForSequenceClassification.from_pretrained('./roberta_year_prediction')
+model = AutoModelForSequenceClassification.from_pretrained('./roberta_year_prediction/epoch_0')
 model.eval()
 model.to(device)
 
@@ -46,7 +46,7 @@ def predict(dataset, out_f):
             del batch[c]
         outputs.extend(model(**batch).logits.tolist())
         progress_bar.update(1)
-        outputs_transformed = scalers['year'].inverse_transform(outputs)
+    outputs_transformed = scalers['year'].inverse_transform(outputs)
 
     with open(out_f,'w') as f_out: