resolving comments and running jupyter black

examples/sequence_classification/LoRA.ipynb

@@ -29,13 +29,21 @@
     "import torch\n",
     "from torch.optim import AdamW\n",
     "from torch.utils.data import DataLoader\n",
-    "from peft import get_peft_config,get_peft_model, get_peft_model_state_dict, set_peft_model_state_dict, LoraConfig, PeftType, \\\n",
-    "PrefixTuningConfig, PromptEncoderConfig\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",
+    "    LoraConfig,\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\n"
+    "from tqdm import tqdm"
    ]
   },
   {
@@ -60,13 +68,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "peft_config = LoraConfig(\n",
-    "    task_type=\"SEQ_CLS\",\n",
-    "    inference_mode=False,\n",
-    "    r=8,\n",
-    "    lora_alpha=16,\n",
-    "    lora_dropout=0.1\n",
-    ")\n",
+    "peft_config = LoraConfig(task_type=\"SEQ_CLS\", inference_mode=False, r=8, lora_alpha=16, lora_dropout=0.1)\n",
     "lr = 3e-4"
    ]
   },
@@ -159,19 +161,21 @@
     "    padding_side = \"left\"\n",
     "else:\n",
     "    padding_side = \"right\"\n",
-    "    \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",
+    "\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",
@@ -182,16 +186,16 @@
     "# 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(\n",
-    "    tokenized_datasets[\"train\"], shuffle=True, collate_fn=collate_fn, batch_size=batch_size\n",
-    ")\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",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -219,7 +223,7 @@
     "# Instantiate scheduler\n",
     "lr_scheduler = get_linear_schedule_with_warmup(\n",
     "    optimizer=optimizer,\n",
-    "    num_warmup_steps=0.06*(len(train_dataloader) * num_epochs),\n",
+    "    num_warmup_steps=0.06 * (len(train_dataloader) * num_epochs),\n",
     "    num_training_steps=(len(train_dataloader) * num_epochs),\n",
     ")"
    ]
@@ -668,7 +672,7 @@
     "    )\n",
     "\n",
     "eval_metric = metric.compute()\n",
-    "print(eval_metric)\n"
+    "print(eval_metric)"
    ]
   },
   {

examples/sequence_classification/P_Tuning.ipynb

@@ -29,13 +29,20 @@
     "import torch\n",
     "from torch.optim import AdamW\n",
     "from torch.utils.data import DataLoader\n",
-    "from peft import get_peft_config,get_peft_model, get_peft_model_state_dict, set_peft_model_state_dict, PeftType, \\\n",
-    "PrefixTuningConfig, PromptEncoderConfig\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\n"
+    "from tqdm import tqdm"
    ]
   },
   {
@@ -60,12 +67,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "\n",
-    "peft_config = PromptEncoderConfig(\n",
-    "    task_type=\"SEQ_CLS\",\n",
-    "    num_virtual_tokens=20,\n",
-    "    encoder_hidden_size=128\n",
-    ")\n",
+    "peft_config = PromptEncoderConfig(task_type=\"SEQ_CLS\", num_virtual_tokens=20, encoder_hidden_size=128)\n",
     "lr = 1e-3"
    ]
   },
@@ -111,19 +113,21 @@
     "    padding_side = \"left\"\n",
     "else:\n",
     "    padding_side = \"right\"\n",
-    "    \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",
+    "\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",
@@ -134,16 +138,16 @@
     "# 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(\n",
-    "    tokenized_datasets[\"train\"], shuffle=True, collate_fn=collate_fn, batch_size=batch_size\n",
-    ")\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",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -171,7 +175,7 @@
     "# 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_warmup_steps=0,  # 0.06*(len(train_dataloader) * num_epochs),\n",
     "    num_training_steps=(len(train_dataloader) * num_epochs),\n",
     ")"
    ]
@@ -640,7 +644,7 @@
     "    )\n",
     "\n",
     "eval_metric = metric.compute()\n",
-    "print(eval_metric)\n"
+    "print(eval_metric)"
    ]
   },
   {

examples/sequence_classification/Prompt_Tuning.ipynb

@@ -29,13 +29,21 @@
     "import torch\n",
     "from torch.optim import AdamW\n",
     "from torch.utils.data import DataLoader\n",
-    "from peft import get_peft_config,get_peft_model, get_peft_model_state_dict, set_peft_model_state_dict, PeftType, \\\n",
-    "PrefixTuningConfig, PromptEncoderConfig, PromptTuningConfig\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",
+    "    PromptTuningConfig,\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\n"
+    "from tqdm import tqdm"
    ]
   },
   {
@@ -60,11 +68,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "peft_config = PromptTuningConfig(\n",
-    "    task_type=\"SEQ_CLS\",\n",
-    "    num_virtual_tokens=10\n",
-    ")\n",
-    "lr = 1e-3\n"
+    "peft_config = PromptTuningConfig(task_type=\"SEQ_CLS\", num_virtual_tokens=10)\n",
+    "lr = 1e-3"
    ]
   },
   {
@@ -109,19 +114,21 @@
     "    padding_side = \"left\"\n",
     "else:\n",
     "    padding_side = \"right\"\n",
-    "    \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",
+    "\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",
@@ -132,16 +139,16 @@
     "# 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(\n",
-    "    tokenized_datasets[\"train\"], shuffle=True, collate_fn=collate_fn, batch_size=batch_size\n",
-    ")\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",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -169,7 +176,7 @@
     "# Instantiate scheduler\n",
     "lr_scheduler = get_linear_schedule_with_warmup(\n",
     "    optimizer=optimizer,\n",
-    "    num_warmup_steps=0.06*(len(train_dataloader) * num_epochs),\n",
+    "    num_warmup_steps=0.06 * (len(train_dataloader) * num_epochs),\n",
     "    num_training_steps=(len(train_dataloader) * num_epochs),\n",
     ")"
    ]
@@ -652,7 +659,7 @@
     "    )\n",
     "\n",
     "eval_metric = metric.compute()\n",
-    "print(eval_metric)\n"
+    "print(eval_metric)"
    ]
   }
  ],

examples/sequence_classification/prefix_tuning.ipynb

@@ -29,13 +29,20 @@
     "import torch\n",
     "from torch.optim import AdamW\n",
     "from torch.utils.data import DataLoader\n",
-    "from peft import get_peft_config,get_peft_model, get_peft_model_state_dict, set_peft_model_state_dict, PeftType, \\\n",
-    "PrefixTuningConfig, PromptEncoderConfig\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\n"
+    "from tqdm import tqdm"
    ]
   },
   {
@@ -60,10 +67,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "peft_config = PrefixTuningConfig(\n",
-    "    task_type=\"SEQ_CLS\",\n",
-    "    num_virtual_tokens=20\n",
-    ")\n",
+    "peft_config = PrefixTuningConfig(task_type=\"SEQ_CLS\", num_virtual_tokens=20)\n",
     "lr = 1e-2"
    ]
   },
@@ -128,19 +132,21 @@
     "    padding_side = \"left\"\n",
     "else:\n",
     "    padding_side = \"right\"\n",
-    "    \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",
+    "\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",
@@ -151,16 +157,16 @@
     "# 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(\n",
-    "    tokenized_datasets[\"train\"], shuffle=True, collate_fn=collate_fn, batch_size=batch_size\n",
-    ")\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",
-    ")\n"
+    ")"
    ]
   },
   {
@@ -188,7 +194,7 @@
     "# Instantiate scheduler\n",
     "lr_scheduler = get_linear_schedule_with_warmup(\n",
     "    optimizer=optimizer,\n",
-    "    num_warmup_steps=0.06*(len(train_dataloader) * num_epochs),\n",
+    "    num_warmup_steps=0.06 * (len(train_dataloader) * num_epochs),\n",
     "    num_training_steps=(len(train_dataloader) * num_epochs),\n",
     ")"
    ]
@@ -671,7 +677,7 @@
     "    )\n",
     "\n",
     "eval_metric = metric.compute()\n",
-    "print(eval_metric)\n"
+    "print(eval_metric)"
    ]
   }
  ],