Update README.md

README.md

@@ -15,7 +15,7 @@ tags:
 
 TeenyTinyLlama is a series of small foundational models trained on Portuguese.
 
-This repository contains a version of [TeenyTinyLlama-162m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-162m) fine-tuned on the [FAQUAD dataset](https://huggingface.co/datasets/ruanchaves/faquad-nli).
+This repository contains a version of [TeenyTinyLlama-162m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-162m) fine-tuned on the [FaQuAD-NLI dataset](https://huggingface.co/datasets/ruanchaves/faquad-nli).
 
 ## Reproducing
 
@@ -25,46 +25,24 @@ This repository contains a version of [TeenyTinyLlama-162m](https://huggingface.
 
 import evaluate
 import numpy as np
-from huggingface_hub import login
 from datasets import load_dataset, Dataset, DatasetDict
 from transformers import AutoTokenizer, DataCollatorWithPadding
 from transformers import AutoModelForSequenceClassification, TrainingArguments, Trainer
 
-# Basic fine-tuning arguments
-token="your_token"
-task="ruanchaves/faquad-nli"
-model_name="nicholasKluge/Teeny-tiny-llama-162m"
-output_dir="checkpoint"
-learning_rate=4e-5
-per_device_train_batch_size=16
-per_device_eval_batch_size=16
-num_train_epochs=3
-weight_decay=0.01
-evaluation_strategy="epoch"
-save_strategy="epoch"
-hub_model_id="nicholasKluge/Teeny-tiny-llama-162m-faquad"
-
-# Login on the hub to load and push
-login(token=token)
-
 # Load the task
-dataset = load_dataset(task)
+dataset = load_dataset("ruanchaves/faquad-nli)
 
 # Create a `ModelForSequenceClassification`
 model = AutoModelForSequenceClassification.from_pretrained(
-    model_name, 
+    "nicholasKluge/TeenyTinyLlama-162m", 
     num_labels=2, 
     id2label={0: "UNSUITABLE", 1: "SUITABLE"}, 
     label2id={"UNSUITABLE": 0, "SUITABLE": 1}
 )
 
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-# If model does not have a pad_token, we need to add it
-#tokenizer.pad_token = tokenizer._eos_token
-#model.config.pad_token_id = model.config.eos_token_id
+tokenizer = AutoTokenizer.from_pretrained("nicholasKluge/TeenyTinyLlama-162m")
 
-# Preprocess if needed
+# Format the dataset
 train = dataset['train'].to_pandas()
 train['text'] = train['question'] + tokenizer.bos_token + train['answer'] + tokenizer.eos_token
 train = train[['text', 'label']]
@@ -82,7 +60,7 @@ dataset = DatasetDict({
     "test": test                  
 })
 
-# Pre process the dataset
+# Preprocess the dataset
 def preprocess_function(examples):
     return tokenizer(examples["text"], truncation=True)
 
@@ -102,20 +80,18 @@ def compute_metrics(eval_pred):
 
 # Define training arguments
 training_args = TrainingArguments(
-    output_dir=output_dir,
-    learning_rate=learning_rate,
-    per_device_train_batch_size=per_device_train_batch_size,
-    per_device_eval_batch_size=per_device_eval_batch_size,
-    num_train_epochs=num_train_epochs,
-    weight_decay=weight_decay,
-    evaluation_strategy=evaluation_strategy,
-    save_strategy=save_strategy,
+    output_dir="checkpoints",
+    learning_rate=4e-5,
+    per_device_train_batch_size=16,
+    per_device_eval_batch_size=16,
+    num_train_epochs=3,
+    weight_decay=0.01,
+    evaluation_strategy="epochs",
+    save_strategy="epochs",
     load_best_model_at_end=True,
     push_to_hub=True,
-    hub_token=token,
-    hub_private_repo=True,
-    hub_model_id=hub_model_id,
-    tf32=True,
+    hub_token="your_token_here",
+    hub_model_id="username/model-ID"
 )
 
 # Define the Trainer