{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "a825ba6b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"===================================BUG REPORT===================================\n",
"Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
"For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link\n",
"================================================================================\n",
"CUDA SETUP: CUDA runtime path found: /home/sourab/miniconda3/envs/ml/lib/libcudart.so\n",
"CUDA SETUP: Highest compute capability among GPUs detected: 7.5\n",
"CUDA SETUP: Detected CUDA version 117\n",
"CUDA SETUP: Loading binary /home/sourab/miniconda3/envs/ml/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda117.so...\n"
]
}
],
"source": [
"import argparse\n",
"import os\n",
"\n",
"import torch\n",
"from torch.optim import AdamW\n",
"from torch.utils.data import DataLoader\n",
"from peft import (\n",
" get_peft_config,\n",
" get_peft_model,\n",
" get_peft_model_state_dict,\n",
" set_peft_model_state_dict,\n",
" PeftType,\n",
" PrefixTuningConfig,\n",
" PromptEncoderConfig,\n",
")\n",
"\n",
"import evaluate\n",
"from datasets import load_dataset\n",
"from transformers import AutoModelForSequenceClassification, AutoTokenizer, get_linear_schedule_with_warmup, set_seed\n",
"from tqdm import tqdm"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "2bd7cbb2",
"metadata": {},
"outputs": [],
"source": [
"batch_size = 32\n",
"model_name_or_path = \"roberta-large\"\n",
"task = \"mrpc\"\n",
"peft_type = PeftType.P_TUNING\n",
"device = \"cuda\"\n",
"num_epochs = 20"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "33d9b62e",
"metadata": {},
"outputs": [],
"source": [
"peft_config = PromptEncoderConfig(task_type=\"SEQ_CLS\", num_virtual_tokens=20, encoder_hidden_size=128)\n",
"lr = 1e-3"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "152b6177",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Found cached dataset glue (/home/sourab/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad)\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a451b90675e0451489cc6426465afa32",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/3 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading cached processed dataset at /home/sourab/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad/cache-9fa7887f9eaa03ae.arrow\n",
"Loading cached processed dataset at /home/sourab/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad/cache-dc593149bbeafe80.arrow\n",
"Loading cached processed dataset at /home/sourab/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad/cache-140ebe5b70e09817.arrow\n"
]
}
],
"source": [
"if any(k in model_name_or_path for k in (\"gpt\", \"opt\", \"bloom\")):\n",
" padding_side = \"left\"\n",
"else:\n",
" padding_side = \"right\"\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side=padding_side)\n",
"if getattr(tokenizer, \"pad_token_id\") is None:\n",
" tokenizer.pad_token_id = tokenizer.eos_token_id\n",
"\n",
"datasets = load_dataset(\"glue\", task)\n",
"metric = evaluate.load(\"glue\", task)\n",
"\n",
"\n",
"def tokenize_function(examples):\n",
" # max_length=None => use the model max length (it's actually the default)\n",
" outputs = tokenizer(examples[\"sentence1\"], examples[\"sentence2\"], truncation=True, max_length=None)\n",
" return outputs\n",
"\n",
"\n",
"tokenized_datasets = datasets.map(\n",
" tokenize_function,\n",
" batched=True,\n",
" remove_columns=[\"idx\", \"sentence1\", \"sentence2\"],\n",
")\n",
"\n",
"# We also rename the 'label' column to 'labels' which is the expected name for labels by the models of the\n",
"# transformers library\n",
"tokenized_datasets = tokenized_datasets.rename_column(\"label\", \"labels\")\n",
"\n",
"\n",
"def collate_fn(examples):\n",
" return tokenizer.pad(examples, padding=\"longest\", return_tensors=\"pt\")\n",
"\n",
"\n",
"# Instantiate dataloaders.\n",
"train_dataloader = DataLoader(tokenized_datasets[\"train\"], shuffle=True, collate_fn=collate_fn, batch_size=batch_size)\n",
"eval_dataloader = DataLoader(\n",
" tokenized_datasets[\"validation\"], shuffle=False, collate_fn=collate_fn, batch_size=batch_size\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f6bc8144",
"metadata": {},
"outputs": [],
"source": [
"model = AutoModelForSequenceClassification.from_pretrained(model_name_or_path, return_dict=True)\n",
"model = get_peft_model(model, peft_config)\n",
"model.print_trainable_parameters()\n",
"model"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "af41c571",
"metadata": {},
"outputs": [],
"source": [
"optimizer = AdamW(params=model.parameters(), lr=lr)\n",
"\n",
"# Instantiate scheduler\n",
"lr_scheduler = get_linear_schedule_with_warmup(\n",
" optimizer=optimizer,\n",
" num_warmup_steps=0, # 0.06*(len(train_dataloader) * num_epochs),\n",
" num_training_steps=(len(train_dataloader) * num_epochs),\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "90993c93",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/115 [00:00<?, ?it/s]You're using a RobertaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n",
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:32<00:00, 3.54it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.91it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 0: {'accuracy': 0.6985294117647058, 'f1': 0.8172362555720655}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.61it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.87it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 1: {'accuracy': 0.6936274509803921, 'f1': 0.806201550387597}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.61it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.88it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 2: {'accuracy': 0.7132352941176471, 'f1': 0.8224582701062216}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.61it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.87it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 3: {'accuracy': 0.7083333333333334, 'f1': 0.8199697428139183}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.61it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.90it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 4: {'accuracy': 0.7205882352941176, 'f1': 0.8246153846153846}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.62it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.90it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 5: {'accuracy': 0.7009803921568627, 'f1': 0.8200589970501474}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:32<00:00, 3.59it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.89it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 6: {'accuracy': 0.7254901960784313, 'f1': 0.8292682926829268}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.60it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.86it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 7: {'accuracy': 0.7230392156862745, 'f1': 0.8269525267993874}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:34<00:00, 3.34it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.88it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 8: {'accuracy': 0.7254901960784313, 'f1': 0.8297872340425533}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.60it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.77it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 9: {'accuracy': 0.7230392156862745, 'f1': 0.828006088280061}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:32<00:00, 3.58it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.88it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 10: {'accuracy': 0.7181372549019608, 'f1': 0.8183254344391785}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.60it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.87it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 11: {'accuracy': 0.7132352941176471, 'f1': 0.803361344537815}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.59it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.85it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 12: {'accuracy': 0.7107843137254902, 'f1': 0.8206686930091186}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:32<00:00, 3.59it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.85it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 13: {'accuracy': 0.7181372549019608, 'f1': 0.8254931714719272}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:32<00:00, 3.59it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.87it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 14: {'accuracy': 0.7156862745098039, 'f1': 0.8253012048192772}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:32<00:00, 3.59it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.84it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 15: {'accuracy': 0.7230392156862745, 'f1': 0.8242612752721618}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:32<00:00, 3.49it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:02<00:00, 5.84it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 16: {'accuracy': 0.7181372549019608, 'f1': 0.8200312989045383}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:32<00:00, 3.49it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.84it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 17: {'accuracy': 0.7107843137254902, 'f1': 0.8217522658610272}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.60it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.88it/s]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 18: {'accuracy': 0.7254901960784313, 'f1': 0.8292682926829268}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|████████████████████████████████████████████████████████████████████████████████████████| 115/115 [00:31<00:00, 3.61it/s]\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 6.89it/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"epoch 19: {'accuracy': 0.7107843137254902, 'f1': 0.8206686930091186}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"model.to(device)\n",
"for epoch in range(num_epochs):\n",
" model.train()\n",
" for step, batch in enumerate(tqdm(train_dataloader)):\n",
" batch.to(device)\n",
" outputs = model(**batch)\n",
" loss = outputs.loss\n",
" loss.backward()\n",
" optimizer.step()\n",
" lr_scheduler.step()\n",
" optimizer.zero_grad()\n",
"\n",
" model.eval()\n",
" for step, batch in enumerate(tqdm(eval_dataloader)):\n",
" batch.to(device)\n",
" with torch.no_grad():\n",
" outputs = model(**batch)\n",
" predictions = outputs.logits.argmax(dim=-1)\n",
" predictions, references = predictions, batch[\"labels\"]\n",
" metric.add_batch(\n",
" predictions=predictions,\n",
" references=references,\n",
" )\n",
"\n",
" eval_metric = metric.compute()\n",
" print(f\"epoch {epoch}:\", eval_metric)"
]
},
{
"cell_type": "markdown",
"id": "a43bd9fb",
"metadata": {},
"source": [
"## Share adapters on the 🤗 Hub"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "871b75aa",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"CommitInfo(commit_url='https://huggingface.co/smangrul/roberta-large-peft-p-tuning/commit/fa7abe613f498c76df5e16c85d9c19c3019587a7', commit_message='Upload model', commit_description='', oid='fa7abe613f498c76df5e16c85d9c19c3019587a7', pr_url=None, pr_revision=None, pr_num=None)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.push_to_hub(\"smangrul/roberta-large-peft-p-tuning\", use_auth_token=True)"
]
},
{
"cell_type": "markdown",
"id": "1c6a9036",
"metadata": {},
"source": [
"## Load adapters from the Hub\n",
"\n",
"You can also directly load adapters from the Hub using the commands below:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "91b0b8f5",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Some weights of the model checkpoint at roberta-large were not used when initializing RobertaForSequenceClassification: ['lm_head.decoder.weight', 'lm_head.layer_norm.bias', 'lm_head.dense.bias', 'roberta.pooler.dense.weight', 'lm_head.layer_norm.weight', 'roberta.pooler.dense.bias', 'lm_head.dense.weight', 'lm_head.bias']\n",
"- This IS expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
"- This IS NOT expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
"Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at roberta-large and are newly initialized: ['classifier.dense.weight', 'classifier.dense.bias', 'classifier.out_proj.weight', 'classifier.out_proj.bias']\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e650799d58ec4bd1b21b6bc28ddf2069",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading: 0%| | 0.00/4.29M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
" 0%| | 0/13 [00:00<?, ?it/s]You're using a RobertaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n",
"100%|██████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:01<00:00, 7.18it/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'accuracy': 0.7107843137254902, 'f1': 0.8206686930091186}\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"import torch\n",
"from peft import PeftModel, PeftConfig\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer\n",
"\n",
"peft_model_id = \"smangrul/roberta-large-peft-p-tuning\"\n",
"config = PeftConfig.from_pretrained(peft_model_id)\n",
"inference_model = AutoModelForSequenceClassification.from_pretrained(config.base_model_name_or_path)\n",
"tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
"\n",
"# Load the Lora model\n",
"inference_model = PeftModel.from_pretrained(inference_model, peft_model_id)\n",
"\n",
"inference_model.to(device)\n",
"inference_model.eval()\n",
"for step, batch in enumerate(tqdm(eval_dataloader)):\n",
" batch.to(device)\n",
" with torch.no_grad():\n",
" outputs = inference_model(**batch)\n",
" predictions = outputs.logits.argmax(dim=-1)\n",
" predictions, references = predictions, batch[\"labels\"]\n",
" metric.add_batch(\n",
" predictions=predictions,\n",
" references=references,\n",
" )\n",
"\n",
"eval_metric = metric.compute()\n",
"print(eval_metric)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1a8d69d1",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.5 (v3.10.5:f377153967, Jun 6 2022, 12:36:10) [Clang 13.0.0 (clang-1300.0.29.30)]"
},
"vscode": {
"interpreter": {
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}