adding trainer code

trainer_code.py

@@ -0,0 +1,187 @@
+from huggingface_hub import *
+
+# create_repo(repo_id="test-model")
+import pandas as pd
+
+from datasets import load_dataset
+
+
+df_train = pd.read_csv("/home/prafull/apps_all/flan_tuning/FlanT5-train-test-idiomSimplifier.csv")
+complex_sentences = df_train["Idiom sentences"].to_list()
+simple_sentences = df_train["English casual"].to_list()
+
+data_dict = {
+    "dialogue": complex_sentences,
+    "summary": simple_sentences
+}
+
+df_train_new = pd.DataFrame(data_dict)
+# random shuffling
+df_train_shuffled = df_train_new.sample(frac = 1, random_state=1)
+# # Save pre-processed final data
+df_train_shuffled.head(1000).to_csv("dialog_summary.csv", encoding="utf-8", index=False)
+
+dataset = load_dataset("csv", data_files="dialog_summary.csv", split='train') 
+
+dataset = dataset.train_test_split(test_size=0.05)
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+model_id="google/flan-t5-base"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+from datasets import concatenate_datasets
+
+# The maximum total input sequence length after tokenization.
+# Sequences longer than this will be truncated, sequences shorter will be padded.
+tokenized_inputs = concatenate_datasets([dataset["train"], dataset["test"]]).map(lambda x: tokenizer(x["dialogue"], truncation=True), batched=True, remove_columns=["dialogue", "summary"])
+max_source_length = max([len(x) for x in tokenized_inputs["input_ids"]])
+print(f"Max source length: {max_source_length}")
+
+max_target_length = max_source_length + 10
+print(f"Max Target length: {max_target_length}")
+
+
+def preprocess_function(sample,padding="max_length"):
+    # add prefix to the input for t5
+    inputs = ["Easy to understand Sentence without idioms and jargons: " + item for item in sample["dialogue"]]
+
+    # tokenize inputs
+    model_inputs = tokenizer(inputs, max_length=max_source_length, padding=padding, truncation=True)
+
+    # Tokenize targets with the `text_target` keyword argument
+    labels = tokenizer(text_target=sample["summary"], max_length=max_target_length, padding=padding, truncation=True)
+
+    # If we are padding here, replace all tokenizer.pad_token_id in the labels by -100 when we want to ignore
+    # padding in the loss.
+    if padding == "max_length":
+        labels["input_ids"] = [
+            [(l if l != tokenizer.pad_token_id else -100) for l in label] for label in labels["input_ids"]
+        ]
+
+    model_inputs["labels"] = labels["input_ids"]
+    return model_inputs
+
+tokenized_dataset = dataset.map(preprocess_function, batched=True, remove_columns=["dialogue", "summary"])
+print(f"Keys of tokenized dataset: {list(tokenized_dataset['train'].features)}")
+
+
+from transformers import AutoModelForSeq2SeqLM
+
+# huggingface hub model id
+model_id="google/flan-t5-base"
+
+# load model from the hub
+model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
+
+import evaluate
+import nltk
+import numpy as np
+from nltk.tokenize import sent_tokenize
+
+# Metric
+metric = evaluate.load("rouge")
+
+# helper function to postprocess text
+def postprocess_text(preds, labels):
+    preds = [pred.strip() for pred in preds]
+    labels = [label.strip() for label in labels]
+
+    # rougeLSum expects newline after each sentence
+    preds = ["\n".join(sent_tokenize(pred)) for pred in preds]
+    labels = ["\n".join(sent_tokenize(label)) for label in labels]
+
+    return preds, labels
+
+def compute_metrics(eval_preds):
+    preds, labels = eval_preds
+    if isinstance(preds, tuple):
+        preds = preds[0]
+    decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True)
+    # Replace -100 in the labels as we can't decode them.
+    labels = np.where(labels != -100, labels, tokenizer.pad_token_id)
+    decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)
+
+    # Some simple post-processing
+    decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels)
+
+    result = metric.compute(predictions=decoded_preds, references=decoded_labels, use_stemmer=True)
+    result = {k: round(v * 100, 4) for k, v in result.items()}
+    prediction_lens = [np.count_nonzero(pred != tokenizer.pad_token_id) for pred in preds]
+    result["gen_len"] = np.mean(prediction_lens)
+    return result
+
+
+from transformers import DataCollatorForSeq2Seq
+
+# we want to ignore tokenizer pad token in the loss
+label_pad_token_id = -100
+# Data collator
+data_collator = DataCollatorForSeq2Seq(
+    tokenizer,
+    model=model,
+    label_pad_token_id=label_pad_token_id,
+    pad_to_multiple_of=8
+)
+
+import torch
+
+torch.cuda.set_device(0)
+print(torch.cuda.current_device())
+
+from huggingface_hub import HfFolder
+from transformers import Seq2SeqTrainer, Seq2SeqTrainingArguments
+
+
+
+repository_id = f"flan-tuning"
+
+
+# Define training args
+training_args = Seq2SeqTrainingArguments(
+    overwrite_output_dir=True,
+    output_dir=repository_id,
+    per_device_train_batch_size=8,
+    per_device_eval_batch_size=8,
+    predict_with_generate=True,
+    fp16=False, # Overflows with fp16
+    learning_rate=5e-5,
+    num_train_epochs=1,
+    # logging & evaluation strategies
+    logging_dir=f"{repository_id}/logs",
+    logging_strategy="steps",
+    logging_steps=500,
+    evaluation_strategy="epoch",
+    save_strategy="epoch",
+    save_total_limit=2,
+    load_best_model_at_end=True,
+    # metric_for_best_model="overall_f1",
+    # push to hub parameters
+    report_to="tensorboard",
+    push_to_hub=False,
+    hub_strategy="every_save",
+    hub_model_id=repository_id,
+    hub_token=HfFolder.get_token(),
+)
+
+# Create Trainer instance
+trainer = Seq2SeqTrainer(
+    model=model,
+    args=training_args,
+    data_collator=data_collator,
+    train_dataset=tokenized_dataset["train"],
+    eval_dataset=tokenized_dataset["test"],
+    compute_metrics=compute_metrics,
+)
+
+trainer.train()
+
+# trainer.model.save_pretrained("/home/prafull/apps_all/ChatGPT_Playground/Flan_models/flan-t5-LARGE-IDIOM-24k", from_pt=True)
+# tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")
+
+
+# PUSH TO HUB ------------
+
+# Save our tokenizer and create model card
+tokenizer.save_pretrained(repository_id)
+trainer.create_model_card()
+# Push the results to the hub
+trainer.push_to_hub()