Delete distillbert-baseline.py

distillbert-baseline.py

@@ -1,68 +0,0 @@
-from datasets import load_dataset
-from transformers import TrainingArguments
-from transformers import DistilBertForSequenceClassification, DistilBertTokenizerFast
-
-
-
-
-dataset = load_dataset("quotaclimat/frugalaichallenge-text-train")
-
-# %% [markdown]
-# 
-
-# %%
-LABEL_MAPPING = {
-        "0_not_relevant": 0,
-        "1_not_happening": 1,
-        "2_not_human": 2,
-        "3_not_bad": 3,
-        "4_solutions_harmful_unnecessary": 4,
-        "5_science_unreliable": 5,
-        "6_proponents_biased": 6,
-        "7_fossil_fuels_needed": 7
-    }
-
-# %%
-dataset = dataset.map(lambda x: {"label": LABEL_MAPPING[x["label"]]})
-
-# %%
-print(dataset)
-
-# %%
-
-tokenizer = DistilBertTokenizerFast.from_pretrained("distilbert-base-uncased")
-# Tokenize the datasets
-def tokenize_function(examples):
-    return tokenizer(examples["quote"], padding="max_length", truncation=True)
-
-train_dataset = dataset["train"].map(tokenize_function, batched=True)
-test_dataset = dataset["test"].map(tokenize_function, batched=True)
-
-
-model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased", num_labels=8)  # Set num_labels for your classification task
-
-# %%
-
-# Define training arguments
-training_args = TrainingArguments(
-    output_dir="./results",            # Output directory for saved models
-    eval_strategy="epoch",       # Evaluation strategy (can be "steps" or "epoch")
-    per_device_train_batch_size=16,    # Batch size for training
-    per_device_eval_batch_size=64,     # Batch size for evaluation
-    num_train_epochs=3,                # Number of training epochs
-    logging_dir="./logs",              # Directory for logs
-    logging_steps=10,                  # How often to log
-)
-
-
-# %%
-
-trainer = Trainer(
-    model=model,                       # The model to train
-    args=training_args,                # The training arguments
-    train_dataset=train_dataset,       # The training dataset
-    eval_dataset=test_dataset          # The evaluation dataset
-)
-trainer.train()
-results = trainer.evaluate()
-print(results)