| { | |
| "sourceFile": "trainml.py", | |
| "activeCommit": 0, | |
| "commits": [ | |
| { | |
| "activePatchIndex": 15, | |
| "patches": [ | |
| { | |
| "date": 1708166375103, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n" | |
| }, | |
| { | |
| "date": 1708166792627, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -83,4 +83,7 @@\n metric.add_batch(predictions=predictions, references=batch[\"labels\"]) # We compare our robot's answers to the correct answers.\n \n final_score = metric.compute() # We calculate how well our robot did.\n print(final_score) # We print out the score to see how well our robot solved the puzzles!\n+\n+model.save_pretrained(\"path/to/save/model\")\n+tokenizer.save_pretrained(\"path/to/save/tokenizer\")\n\\ No newline at end of file\n" | |
| }, | |
| { | |
| "date": 1708167245700, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -8,8 +8,9 @@\n from tqdm.auto import tqdm # This is our progress bar, showing us how far we've come in solving the book.\n import evaluate # This tells us how well we did in solving puzzles.\n from accelerate import Accelerator # This makes everything go super fast, like a rocket!\n \n+def train_and_save_model():\n # Now, let's pick up the book we're going to solve today.\n raw_datasets = load_dataset(\"glue\", \"mrpc\") # This is a book filled with puzzles about matching sentences.\n \n # Before we start solving puzzles, we need to understand the language they're written in.\n" | |
| }, | |
| { | |
| "date": 1708167252023, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -86,5 +86,5 @@\n final_score = metric.compute() # We calculate how well our robot did.\n print(final_score) # We print out the score to see how well our robot solved the puzzles!\n \n model.save_pretrained(\"path/to/save/model\")\n-tokenizer.save_pretrained(\"path/to/save/tokenizer\")\n\\ No newline at end of file\n+tokenizer.save_pretrained(\"path/to/save/tokenizer\")\n" | |
| }, | |
| { | |
| "date": 1708167259383, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -9,82 +9,82 @@\n import evaluate # This tells us how well we did in solving puzzles.\n from accelerate import Accelerator # This makes everything go super fast, like a rocket!\n \n def train_and_save_model():\n-# Now, let's pick up the book we're going to solve today.\n-raw_datasets = load_dataset(\"glue\", \"mrpc\") # This is a book filled with puzzles about matching sentences.\n+ # Now, let's pick up the book we're going to solve today.\n+ raw_datasets = load_dataset(\"glue\", \"mrpc\") # This is a book filled with puzzles about matching sentences.\n \n-# Before we start solving puzzles, we need to understand the language they're written in.\n-checkpoint = \"bert-base-uncased\" # This is a guidebook to help us understand the puzzles' language.\n-tokenizer = AutoTokenizer.from_pretrained(checkpoint) # This tool helps us read and understand the language in our book.\n+ # Before we start solving puzzles, we need to understand the language they're written in.\n+ checkpoint = \"bert-base-uncased\" # This is a guidebook to help us understand the puzzles' language.\n+ tokenizer = AutoTokenizer.from_pretrained(checkpoint) # This tool helps us read and understand the language in our book.\n \n-# To solve puzzles, we need to make sure we understand each sentence properly.\n-def tokenize_function(example): # This is like reading each sentence carefully and understanding each word.\n- return tokenizer(example[\"sentence1\"], example[\"sentence2\"], truncation=True)\n+ # To solve puzzles, we need to make sure we understand each sentence properly.\n+ def tokenize_function(example): # This is like reading each sentence carefully and understanding each word.\n+ return tokenizer(example[\"sentence1\"], example[\"sentence2\"], truncation=True)\n \n-# We prepare all puzzles in the book so they're ready to solve.\n-tokenized_datasets = raw_datasets.map(tokenize_function, batched=True) # This is like marking all the important parts of the sentences.\n+ # We prepare all puzzles in the book so they're ready to solve.\n+ tokenized_datasets = raw_datasets.map(tokenize_function, batched=True) # This is like marking all the important parts of the sentences.\n \n-# Puzzles can be different sizes, but our puzzle solver works best when all puzzles are the same size.\n-data_collator = DataCollatorWithPadding(tokenizer=tokenizer) # This adds extra paper to smaller puzzles to make them all the same size.\n+ # Puzzles can be different sizes, but our puzzle solver works best when all puzzles are the same size.\n+ data_collator = DataCollatorWithPadding(tokenizer=tokenizer) # This adds extra paper to smaller puzzles to make them all the same size.\n \n-# We're setting up our puzzle pages, making sure we're ready to solve them one by one.\n-tokenized_datasets = tokenized_datasets.remove_columns([\"sentence1\", \"sentence2\", \"idx\"]) # We remove stuff we don't need.\n-tokenized_datasets = tokenized_datasets.rename_column(\"label\", \"labels\") # We make sure the puzzle answers are labeled correctly.\n-tokenized_datasets.set_format(\"torch\") # We make sure our puzzles are in the right format for our brain to understand.\n+ # We're setting up our puzzle pages, making sure we're ready to solve them one by one.\n+ tokenized_datasets = tokenized_datasets.remove_columns([\"sentence1\", \"sentence2\", \"idx\"]) # We remove stuff we don't need.\n+ tokenized_datasets = tokenized_datasets.rename_column(\"label\", \"labels\") # We make sure the puzzle answers are labeled correctly.\n+ tokenized_datasets.set_format(\"torch\") # We make sure our puzzles are in the right format for our brain to understand.\n \n-# Now, we're ready to start solving puzzles, one page at a time.\n-train_dataloader = DataLoader(\n- tokenized_datasets[\"train\"], shuffle=True, batch_size=8, collate_fn=data_collator\n-) # This is our training puzzles.\n-eval_dataloader = DataLoader(\n- tokenized_datasets[\"validation\"], batch_size=8, collate_fn=data_collator\n-) # These are puzzles we use to check our progress.\n+ # Now, we're ready to start solving puzzles, one page at a time.\n+ train_dataloader = DataLoader(\n+ tokenized_datasets[\"train\"], shuffle=True, batch_size=8, collate_fn=data_collator\n+ ) # This is our training puzzles.\n+ eval_dataloader = DataLoader(\n+ tokenized_datasets[\"validation\"], batch_size=8, collate_fn=data_collator\n+ ) # These are puzzles we use to check our progress.\n \n-# We need a puzzle solver, which is specially trained to solve these types of puzzles.\n-model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2) # This is our puzzle-solving robot.\n+ # We need a puzzle solver, which is specially trained to solve these types of puzzles.\n+ model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2) # This is our puzzle-solving robot.\n \n-# Our robot needs instructions on how to get better at solving puzzles.\n-optimizer = AdamW(model.parameters(), lr=5e-5) # This tells our robot how to improve.\n-num_epochs = 3 # This is how many times we'll go through the whole book of puzzles.\n-num_training_steps = num_epochs * len(train_dataloader) # This is the total number of puzzles we'll solve.\n-lr_scheduler = get_scheduler(\n- \"linear\",\n- optimizer=optimizer,\n- num_warmup_steps=0,\n- num_training_steps=num_training_steps,\n-) # This adjusts how quickly our robot learns over time.\n+ # Our robot needs instructions on how to get better at solving puzzles.\n+ optimizer = AdamW(model.parameters(), lr=5e-5) # This tells our robot how to improve.\n+ num_epochs = 3 # This is how many times we'll go through the whole book of puzzles.\n+ num_training_steps = num_epochs * len(train_dataloader) # This is the total number of puzzles we'll solve.\n+ lr_scheduler = get_scheduler(\n+ \"linear\",\n+ optimizer=optimizer,\n+ num_warmup_steps=0,\n+ num_training_steps=num_training_steps,\n+ ) # This adjusts how quickly our robot learns over time.\n \n-# To solve puzzles super fast, we're going to use a rocket!\n-accelerator = Accelerator() # This is our rocket that makes everything go faster.\n-model, optimizer, train_dataloader, eval_dataloader = accelerator.prepare(\n- model, optimizer, train_dataloader, eval_dataloader\n-) # We make sure our robot, our puzzles, and our instructions are all ready for the rocket.\n+ # To solve puzzles super fast, we're going to use a rocket!\n+ accelerator = Accelerator() # This is our rocket that makes everything go faster.\n+ model, optimizer, train_dataloader, eval_dataloader = accelerator.prepare(\n+ model, optimizer, train_dataloader, eval_dataloader\n+ ) # We make sure our robot, our puzzles, and our instructions are all ready for the rocket.\n \n-# It's time to start solving puzzles!\n-progress_bar = tqdm(range(num_training_steps)) # This shows us our progress.\n-model.train() # We tell our robot it's time to start learning.\n-for epoch in range(num_epochs): # We go through our book of puzzles multiple times to get really good.\n- for batch in train_dataloader: # Each time, we take a page of puzzles to solve.\n- outputs = model(**batch) # Our robot tries to solve the puzzles.\n- loss = outputs.loss # We check how many mistakes it made.\n- accelerator.backward(loss) # We give feedback to our robot so it can learn from its mistakes.\n- optimizer.step() # We update our robot's puzzle-solving strategy.\n- lr_scheduler.step() # We adjust how quickly our robot is learning.\n- optimizer.zero_grad() # We reset some settings to make sure our robot is ready for the next page.\n- progress_bar.update(1) # We update our progress bar to show how many puzzles we've solved.\n+ # It's time to start solving puzzles!\n+ progress_bar = tqdm(range(num_training_steps)) # This shows us our progress.\n+ model.train() # We tell our robot it's time to start learning.\n+ for epoch in range(num_epochs): # We go through our book of puzzles multiple times to get really good.\n+ for batch in train_dataloader: # Each time, we take a page of puzzles to solve.\n+ outputs = model(**batch) # Our robot tries to solve the puzzles.\n+ loss = outputs.loss # We check how many mistakes it made.\n+ accelerator.backward(loss) # We give feedback to our robot so it can learn from its mistakes.\n+ optimizer.step() # We update our robot's puzzle-solving strategy.\n+ lr_scheduler.step() # We adjust how quickly our robot is learning.\n+ optimizer.zero_grad() # We reset some settings to make sure our robot is ready for the next page.\n+ progress_bar.update(1) # We update our progress bar to show how many puzzles we've solved.\n \n-# After all that practice, it's time to test how good our robot has become at solving puzzles.\n-metric = evaluate.load(\"glue\", \"mrpc\") # This is like the answer key to check our robot's work.\n-model.eval() # We tell our robot it's time to show what it's learned.\n-for batch in eval_dataloader: # We take a page of puzzles we haven't solved yet.\n- with torch.no_grad(): # We make sure we're just testing, not learning anymore.\n- outputs = model(**batch) # Our robot solves the puzzles.\n- logits = outputs.logits # We look at our robot's answers.\n- predictions = torch.argmax(logits, dim=-1) # We decide which answer our robot thinks is right.\n- metric.add_batch(predictions=predictions, references=batch[\"labels\"]) # We compare our robot's answers to the correct answers.\n+ # After all that practice, it's time to test how good our robot has become at solving puzzles.\n+ metric = evaluate.load(\"glue\", \"mrpc\") # This is like the answer key to check our robot's work.\n+ model.eval() # We tell our robot it's time to show what it's learned.\n+ for batch in eval_dataloader: # We take a page of puzzles we haven't solved yet.\n+ with torch.no_grad(): # We make sure we're just testing, not learning anymore.\n+ outputs = model(**batch) # Our robot solves the puzzles.\n+ logits = outputs.logits # We look at our robot's answers.\n+ predictions = torch.argmax(logits, dim=-1) # We decide which answer our robot thinks is right.\n+ metric.add_batch(predictions=predictions, references=batch[\"labels\"]) # We compare our robot's answers to the correct answers.\n \n-final_score = metric.compute() # We calculate how well our robot did.\n-print(final_score) # We print out the score to see how well our robot solved the puzzles!\n+ final_score = metric.compute() # We calculate how well our robot did.\n+ print(final_score) # We print out the score to see how well our robot solved the puzzles!\n \n-model.save_pretrained(\"path/to/save/model\")\n-tokenizer.save_pretrained(\"path/to/save/tokenizer\")\n+ model.save_pretrained(\"path/to/save/model\")\n+ tokenizer.save_pretrained(\"path/to/save/tokenizer\")\n" | |
| }, | |
| { | |
| "date": 1708167281057, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -87,4 +87,8 @@\n print(final_score) # We print out the score to see how well our robot solved the puzzles!\n \n model.save_pretrained(\"path/to/save/model\")\n tokenizer.save_pretrained(\"path/to/save/tokenizer\")\n+\n+if __name__ == \"__main__\":\n+ train_and_save_model()\n+\n" | |
| }, | |
| { | |
| "date": 1708176288213, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -44,9 +44,9 @@\n model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2) # This is our puzzle-solving robot.\n \n # Our robot needs instructions on how to get better at solving puzzles.\n optimizer = AdamW(model.parameters(), lr=5e-5) # This tells our robot how to improve.\n- num_epochs = 3 # This is how many times we'll go through the whole book of puzzles.\n+ num_epochs = 1 # This is how many times we'll go through the whole book of puzzles.\n num_training_steps = num_epochs * len(train_dataloader) # This is the total number of puzzles we'll solve.\n lr_scheduler = get_scheduler(\n \"linear\",\n optimizer=optimizer,\n" | |
| }, | |
| { | |
| "date": 1708257203286, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -10,9 +10,9 @@\n from accelerate import Accelerator # This makes everything go super fast, like a rocket!\n \n def train_and_save_model():\n # Now, let's pick up the book we're going to solve today.\n- raw_datasets = load_dataset(\"glue\", \"mrpc\") # This is a book filled with puzzles about matching sentences.\n+ raw_datasets = load_dataset(\"glue\") # This is a book filled with puzzles about matching sentences.\n \n # Before we start solving puzzles, we need to understand the language they're written in.\n checkpoint = \"bert-base-uncased\" # This is a guidebook to help us understand the puzzles' language.\n tokenizer = AutoTokenizer.from_pretrained(checkpoint) # This tool helps us read and understand the language in our book.\n" | |
| }, | |
| { | |
| "date": 1708257209627, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -73,9 +73,9 @@\n optimizer.zero_grad() # We reset some settings to make sure our robot is ready for the next page.\n progress_bar.update(1) # We update our progress bar to show how many puzzles we've solved.\n \n # After all that practice, it's time to test how good our robot has become at solving puzzles.\n- metric = evaluate.load(\"glue\", \"mrpc\") # This is like the answer key to check our robot's work.\n+ metric = evaluate.load(\"glue\") # This is like the answer key to check our robot's work.\n model.eval() # We tell our robot it's time to show what it's learned.\n for batch in eval_dataloader: # We take a page of puzzles we haven't solved yet.\n with torch.no_grad(): # We make sure we're just testing, not learning anymore.\n outputs = model(**batch) # Our robot solves the puzzles.\n" | |
| }, | |
| { | |
| "date": 1708259156708, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -73,9 +73,9 @@\n optimizer.zero_grad() # We reset some settings to make sure our robot is ready for the next page.\n progress_bar.update(1) # We update our progress bar to show how many puzzles we've solved.\n \n # After all that practice, it's time to test how good our robot has become at solving puzzles.\n- metric = evaluate.load(\"glue\") # This is like the answer key to check our robot's work.\n+ metric = evaluate.load(\"glue\", \"mrpc\") # This is like the answer key to check our robot's work.\n model.eval() # We tell our robot it's time to show what it's learned.\n for batch in eval_dataloader: # We take a page of puzzles we haven't solved yet.\n with torch.no_grad(): # We make sure we're just testing, not learning anymore.\n outputs = model(**batch) # Our robot solves the puzzles.\n" | |
| }, | |
| { | |
| "date": 1708259164291, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -10,9 +10,9 @@\n from accelerate import Accelerator # This makes everything go super fast, like a rocket!\n \n def train_and_save_model():\n # Now, let's pick up the book we're going to solve today.\n- raw_datasets = load_dataset(\"glue\") # This is a book filled with puzzles about matching sentences.\n+ raw_datasets = load_dataset(\"glue\", \"mrpc\") # This is a book filled with puzzles about matching sentences.\n \n # Before we start solving puzzles, we need to understand the language they're written in.\n checkpoint = \"bert-base-uncased\" # This is a guidebook to help us understand the puzzles' language.\n tokenizer = AutoTokenizer.from_pretrained(checkpoint) # This tool helps us read and understand the language in our book.\n@@ -44,9 +44,9 @@\n model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2) # This is our puzzle-solving robot.\n \n # Our robot needs instructions on how to get better at solving puzzles.\n optimizer = AdamW(model.parameters(), lr=5e-5) # This tells our robot how to improve.\n- num_epochs = 1 # This is how many times we'll go through the whole book of puzzles.\n+ num_epochs = # This is how many times we'll go through the whole book of puzzles.\n num_training_steps = num_epochs * len(train_dataloader) # This is the total number of puzzles we'll solve.\n lr_scheduler = get_scheduler(\n \"linear\",\n optimizer=optimizer,\n" | |
| }, | |
| { | |
| "date": 1708259362403, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -13,9 +13,9 @@\n # Now, let's pick up the book we're going to solve today.\n raw_datasets = load_dataset(\"glue\", \"mrpc\") # This is a book filled with puzzles about matching sentences.\n \n # Before we start solving puzzles, we need to understand the language they're written in.\n- checkpoint = \"bert-base-uncased\" # This is a guidebook to help us understand the puzzles' language.\n+ checkpoint = \"bert\"-base-uncased # This is a guidebook to help us understand the puzzles' language.\n tokenizer = AutoTokenizer.from_pretrained(checkpoint) # This tool helps us read and understand the language in our book.\n \n # To solve puzzles, we need to make sure we understand each sentence properly.\n def tokenize_function(example): # This is like reading each sentence carefully and understanding each word.\n" | |
| }, | |
| { | |
| "date": 1708259368829, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -13,9 +13,9 @@\n # Now, let's pick up the book we're going to solve today.\n raw_datasets = load_dataset(\"glue\", \"mrpc\") # This is a book filled with puzzles about matching sentences.\n \n # Before we start solving puzzles, we need to understand the language they're written in.\n- checkpoint = \"bert\"-base-uncased # This is a guidebook to help us understand the puzzles' language.\n+ checkpoint = \"distilbert-base-uncased\" # This is a guidebook to help us understand the puzzles' language.\n tokenizer = AutoTokenizer.from_pretrained(checkpoint) # This tool helps us read and understand the language in our book.\n \n # To solve puzzles, we need to make sure we understand each sentence properly.\n def tokenize_function(example): # This is like reading each sentence carefully and understanding each word.\n" | |
| }, | |
| { | |
| "date": 1708259574161, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -54,9 +54,9 @@\n num_training_steps=num_training_steps,\n ) # This adjusts how quickly our robot learns over time.\n \n # To solve puzzles super fast, we're going to use a rocket!\n- accelerator = Accelerator() # This is our rocket that makes everything go faster.\n+ accelerator = Accelerator(fp16=True) # This is our rocket that makes everything go faster.\n model, optimizer, train_dataloader, eval_dataloader = accelerator.prepare(\n model, optimizer, train_dataloader, eval_dataloader\n ) # We make sure our robot, our puzzles, and our instructions are all ready for the rocket.\n \n" | |
| }, | |
| { | |
| "date": 1708259707398, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -44,9 +44,9 @@\n model = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2) # This is our puzzle-solving robot.\n \n # Our robot needs instructions on how to get better at solving puzzles.\n optimizer = AdamW(model.parameters(), lr=5e-5) # This tells our robot how to improve.\n- num_epochs = # This is how many times we'll go through the whole book of puzzles.\n+ num_epochs = 1 # This is how many times we'll go through the whole book of puzzles.\n num_training_steps = num_epochs * len(train_dataloader) # This is the total number of puzzles we'll solve.\n lr_scheduler = get_scheduler(\n \"linear\",\n optimizer=optimizer,\n" | |
| }, | |
| { | |
| "date": 1708262141106, | |
| "content": "Index: \n===================================================================\n--- \n+++ \n@@ -54,9 +54,9 @@\n num_training_steps=num_training_steps,\n ) # This adjusts how quickly our robot learns over time.\n \n # To solve puzzles super fast, we're going to use a rocket!\n- accelerator = Accelerator(fp16=True) # This is our rocket that makes everything go faster.\n+ accelerator = Accelerator() # This is our rocket that makes everything go faster.\n model, optimizer, train_dataloader, eval_dataloader = accelerator.prepare(\n model, optimizer, train_dataloader, eval_dataloader\n ) # We make sure our robot, our puzzles, and our instructions are all ready for the rocket.\n \n" | |
| } | |
| ], | |
| "date": 1708166375103, | |
| "name": "Commit-0", | |
| "content": "# First, we grab tools from our toolbox. These tools help us with different tasks like reading books (datasets),\n# learning new languages (tokenization), and solving puzzles (models).\nfrom datasets import load_dataset # This tool helps us get our book, where the puzzles are.\nfrom transformers import AutoTokenizer, AutoModelForSequenceClassification, AdamW, get_scheduler # These help us understand and solve puzzles.\nfrom transformers import DataCollatorWithPadding # This makes sure all puzzle pieces are the same size.\nfrom torch.utils.data import DataLoader # This helps us handle one page of puzzles at a time.\nimport torch # This is like the brain of our operations, helping us think through puzzles.\nfrom tqdm.auto import tqdm # This is our progress bar, showing us how far we've come in solving the book.\nimport evaluate # This tells us how well we did in solving puzzles.\nfrom accelerate import Accelerator # This makes everything go super fast, like a rocket!\n\n# Now, let's pick up the book we're going to solve today.\nraw_datasets = load_dataset(\"glue\", \"mrpc\") # This is a book filled with puzzles about matching sentences.\n\n# Before we start solving puzzles, we need to understand the language they're written in.\ncheckpoint = \"bert-base-uncased\" # This is a guidebook to help us understand the puzzles' language.\ntokenizer = AutoTokenizer.from_pretrained(checkpoint) # This tool helps us read and understand the language in our book.\n\n# To solve puzzles, we need to make sure we understand each sentence properly.\ndef tokenize_function(example): # This is like reading each sentence carefully and understanding each word.\n return tokenizer(example[\"sentence1\"], example[\"sentence2\"], truncation=True)\n\n# We prepare all puzzles in the book so they're ready to solve.\ntokenized_datasets = raw_datasets.map(tokenize_function, batched=True) # This is like marking all the important parts of the sentences.\n\n# Puzzles can be different sizes, but our puzzle solver works best when all puzzles are the same size.\ndata_collator = DataCollatorWithPadding(tokenizer=tokenizer) # This adds extra paper to smaller puzzles to make them all the same size.\n\n# We're setting up our puzzle pages, making sure we're ready to solve them one by one.\ntokenized_datasets = tokenized_datasets.remove_columns([\"sentence1\", \"sentence2\", \"idx\"]) # We remove stuff we don't need.\ntokenized_datasets = tokenized_datasets.rename_column(\"label\", \"labels\") # We make sure the puzzle answers are labeled correctly.\ntokenized_datasets.set_format(\"torch\") # We make sure our puzzles are in the right format for our brain to understand.\n\n# Now, we're ready to start solving puzzles, one page at a time.\ntrain_dataloader = DataLoader(\n tokenized_datasets[\"train\"], shuffle=True, batch_size=8, collate_fn=data_collator\n) # This is our training puzzles.\neval_dataloader = DataLoader(\n tokenized_datasets[\"validation\"], batch_size=8, collate_fn=data_collator\n) # These are puzzles we use to check our progress.\n\n# We need a puzzle solver, which is specially trained to solve these types of puzzles.\nmodel = AutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=2) # This is our puzzle-solving robot.\n\n# Our robot needs instructions on how to get better at solving puzzles.\noptimizer = AdamW(model.parameters(), lr=5e-5) # This tells our robot how to improve.\nnum_epochs = 3 # This is how many times we'll go through the whole book of puzzles.\nnum_training_steps = num_epochs * len(train_dataloader) # This is the total number of puzzles we'll solve.\nlr_scheduler = get_scheduler(\n \"linear\",\n optimizer=optimizer,\n num_warmup_steps=0,\n num_training_steps=num_training_steps,\n) # This adjusts how quickly our robot learns over time.\n\n# To solve puzzles super fast, we're going to use a rocket!\naccelerator = Accelerator() # This is our rocket that makes everything go faster.\nmodel, optimizer, train_dataloader, eval_dataloader = accelerator.prepare(\n model, optimizer, train_dataloader, eval_dataloader\n) # We make sure our robot, our puzzles, and our instructions are all ready for the rocket.\n\n# It's time to start solving puzzles!\nprogress_bar = tqdm(range(num_training_steps)) # This shows us our progress.\nmodel.train() # We tell our robot it's time to start learning.\nfor epoch in range(num_epochs): # We go through our book of puzzles multiple times to get really good.\n for batch in train_dataloader: # Each time, we take a page of puzzles to solve.\n outputs = model(**batch) # Our robot tries to solve the puzzles.\n loss = outputs.loss # We check how many mistakes it made.\n accelerator.backward(loss) # We give feedback to our robot so it can learn from its mistakes.\n optimizer.step() # We update our robot's puzzle-solving strategy.\n lr_scheduler.step() # We adjust how quickly our robot is learning.\n optimizer.zero_grad() # We reset some settings to make sure our robot is ready for the next page.\n progress_bar.update(1) # We update our progress bar to show how many puzzles we've solved.\n\n# After all that practice, it's time to test how good our robot has become at solving puzzles.\nmetric = evaluate.load(\"glue\", \"mrpc\") # This is like the answer key to check our robot's work.\nmodel.eval() # We tell our robot it's time to show what it's learned.\nfor batch in eval_dataloader: # We take a page of puzzles we haven't solved yet.\n with torch.no_grad(): # We make sure we're just testing, not learning anymore.\n outputs = model(**batch) # Our robot solves the puzzles.\n logits = outputs.logits # We look at our robot's answers.\n predictions = torch.argmax(logits, dim=-1) # We decide which answer our robot thinks is right.\n metric.add_batch(predictions=predictions, references=batch[\"labels\"]) # We compare our robot's answers to the correct answers.\n\nfinal_score = metric.compute() # We calculate how well our robot did.\nprint(final_score) # We print out the score to see how well our robot solved the puzzles!\n" | |
| } | |
| ] | |
| } |