Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

adding whisper large peft+int8 training example #95

Merged
merged 2 commits into from
Feb 16, 2023
Merged

adding whisper large peft+int8 training example #95

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ca7b462
adding whisper large peft+int8 training example
pacman100 Feb 16, 2023
c1281b9
resolving comments and running `jupyter black`
pacman100 Feb 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
86 changes: 46 additions & 40 deletions examples/causal_language_modeling/peft_lora_clm_accelerate_big_model_inference.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@
"import os\n",
"from transformers import AutoTokenizer\n",
"from torch.utils.data import DataLoader\n",
"from transformers import default_data_collator,get_linear_schedule_with_warmup\n",
"from transformers import default_data_collator, get_linear_schedule_with_warmup\n",
"from tqdm import tqdm\n",
"from datasets import load_dataset\n",
"\n",
Expand All @@ -40,10 +40,10 @@
"dataset_name = \"twitter_complaints\"\n",
"text_column = \"Tweet text\"\n",
"label_column = \"text_label\"\n",
"max_length=64\n",
"max_length = 64\n",
"lr = 1e-3\n",
"num_epochs = 50\n",
"batch_size=8\n"
"batch_size = 8"
]
},
{
Expand All @@ -63,7 +63,6 @@
" lambda x: {\"text_label\": [classes[label] for label in x[\"Label\"]]},\n",
" batched=True,\n",
" num_proc=1,\n",
" \n",
")\n",
"print(dataset)\n",
"dataset[\"train\"][0]"
Expand Down Expand Up @@ -118,6 +117,8 @@
" tokenizer.pad_token_id = tokenizer.eos_token_id\n",
"target_max_length = max([len(tokenizer(class_label)[\"input_ids\"]) for class_label in classes])\n",
"print(target_max_length)\n",
"\n",
"\n",
"def preprocess_function(examples):\n",
" batch_size = len(examples[text_column])\n",
" inputs = [f\"{text_column} : {x} Label : \" for x in examples[text_column]]\n",
Expand All @@ -127,44 +128,43 @@
" for i in range(batch_size):\n",
" sample_input_ids = model_inputs[\"input_ids\"][i]\n",
" label_input_ids = labels[\"input_ids\"][i] + [tokenizer.pad_token_id]\n",
" #print(i, sample_input_ids, label_input_ids)\n",
" model_inputs[\"input_ids\"][i] = sample_input_ids + label_input_ids \n",
" # print(i, sample_input_ids, label_input_ids)\n",
" model_inputs[\"input_ids\"][i] = sample_input_ids + label_input_ids\n",
" labels[\"input_ids\"][i] = [-100] * len(sample_input_ids) + label_input_ids\n",
" model_inputs[\"attention_mask\"][i] = [1] * len(model_inputs[\"input_ids\"][i])\n",
" #print(model_inputs)\n",
" # print(model_inputs)\n",
" for i in range(batch_size):\n",
" sample_input_ids = model_inputs[\"input_ids\"][i]\n",
" label_input_ids = labels[\"input_ids\"][i]\n",
" model_inputs[\"input_ids\"][i] = [tokenizer.pad_token_id]*(max_length-len(sample_input_ids)) + sample_input_ids\n",
" model_inputs[\"attention_mask\"][i] = [0]*(max_length-len(sample_input_ids)) + model_inputs[\"attention_mask\"][i]\n",
" labels[\"input_ids\"][i] = [-100]*(max_length-len(sample_input_ids)) + label_input_ids \n",
" model_inputs[\"input_ids\"][i] = [tokenizer.pad_token_id] * (\n",
" max_length - len(sample_input_ids)\n",
" ) + sample_input_ids\n",
" model_inputs[\"attention_mask\"][i] = [0] * (max_length - len(sample_input_ids)) + model_inputs[\n",
" \"attention_mask\"\n",
" ][i]\n",
" labels[\"input_ids\"][i] = [-100] * (max_length - len(sample_input_ids)) + label_input_ids\n",
" model_inputs[\"input_ids\"][i] = torch.tensor(model_inputs[\"input_ids\"][i][:max_length])\n",
" model_inputs[\"attention_mask\"][i] = torch.tensor(model_inputs[\"attention_mask\"][i][:max_length])\n",
" labels[\"input_ids\"][i] = torch.tensor(labels[\"input_ids\"][i][:max_length]) \n",
" labels[\"input_ids\"][i] = torch.tensor(labels[\"input_ids\"][i][:max_length])\n",
" model_inputs[\"labels\"] = labels[\"input_ids\"]\n",
" return model_inputs\n",
"\n",
"\n",
"\n",
"processed_datasets = dataset.map(\n",
" preprocess_function,\n",
" batched=True,\n",
" num_proc=1,\n",
" remove_columns=dataset[\"train\"].column_names,\n",
" load_from_cache_file=False,\n",
" desc=\"Running tokenizer on dataset\",\n",
" )\n",
" preprocess_function,\n",
" batched=True,\n",
" num_proc=1,\n",
" remove_columns=dataset[\"train\"].column_names,\n",
" load_from_cache_file=False,\n",
" desc=\"Running tokenizer on dataset\",\n",
")\n",
"\n",
"train_dataset = processed_datasets[\"train\"]\n",
"\n",
"\n",
"train_dataloader = DataLoader(\n",
" train_dataset, shuffle=True, collate_fn=default_data_collator, batch_size=batch_size, pin_memory=True\n",
" )\n",
"\n",
"\n",
"\n",
" "
" train_dataset, shuffle=True, collate_fn=default_data_collator, batch_size=batch_size, pin_memory=True\n",
")"
]
},
{
Expand All @@ -178,23 +178,28 @@
" batch_size = len(examples[text_column])\n",
" inputs = [f\"{text_column} : {x} Label : \" for x in examples[text_column]]\n",
" model_inputs = tokenizer(inputs)\n",
" #print(model_inputs)\n",
" # print(model_inputs)\n",
" for i in range(batch_size):\n",
" sample_input_ids = model_inputs[\"input_ids\"][i]\n",
" model_inputs[\"input_ids\"][i] = [tokenizer.pad_token_id]*(max_length-len(sample_input_ids)) + sample_input_ids\n",
" model_inputs[\"attention_mask\"][i] = [0]*(max_length-len(sample_input_ids)) + model_inputs[\"attention_mask\"][i]\n",
" model_inputs[\"input_ids\"][i] = [tokenizer.pad_token_id] * (\n",
" max_length - len(sample_input_ids)\n",
" ) + sample_input_ids\n",
" model_inputs[\"attention_mask\"][i] = [0] * (max_length - len(sample_input_ids)) + model_inputs[\n",
" \"attention_mask\"\n",
" ][i]\n",
" model_inputs[\"input_ids\"][i] = torch.tensor(model_inputs[\"input_ids\"][i][:max_length])\n",
" model_inputs[\"attention_mask\"][i] = torch.tensor(model_inputs[\"attention_mask\"][i][:max_length])\n",
" return model_inputs\n",
"\n",
"\n",
"processed_datasets = dataset.map(\n",
" test_preprocess_function,\n",
" batched=True,\n",
" num_proc=1,\n",
" remove_columns=dataset[\"train\"].column_names,\n",
" load_from_cache_file=False,\n",
" desc=\"Running tokenizer on dataset\",\n",
" )\n",
" test_preprocess_function,\n",
" batched=True,\n",
" num_proc=1,\n",
" remove_columns=dataset[\"train\"].column_names,\n",
" load_from_cache_file=False,\n",
" desc=\"Running tokenizer on dataset\",\n",
")\n",
"\n",
"eval_dataset = processed_datasets[\"train\"]\n",
"test_dataset = processed_datasets[\"test\"]\n",
Expand Down Expand Up @@ -236,7 +241,8 @@
],
"source": [
"from peft import PeftModel, PeftConfig\n",
"max_memory={0: \"1GIB\", 1: \"1GIB\", 2: \"2GIB\", 3: \"10GIB\", \"cpu\":\"30GB\"}\n",
"\n",
"max_memory = {0: \"1GIB\", 1: \"1GIB\", 2: \"2GIB\", 3: \"10GIB\", \"cpu\": \"30GB\"}\n",
"peft_model_id = \"smangrul/twitter_complaints_bigscience_bloomz-7b1_LORA_CAUSAL_LM\"\n",
"\n",
"config = PeftConfig.from_pretrained(peft_model_id)\n",
Expand All @@ -251,7 +257,7 @@
"metadata": {},
"outputs": [],
"source": [
"#model"
"# model"
]
},
{
Expand Down Expand Up @@ -343,7 +349,7 @@
"with torch.no_grad():\n",
" outputs = model.generate(input_ids=inputs[\"input_ids\"], max_new_tokens=10)\n",
" print(outputs)\n",
" print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True))\n"
" print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True))"
]
},
{
Expand Down Expand Up @@ -397,7 +403,7 @@
"accuracy = correct / total * 100\n",
"print(f\"{accuracy=}\")\n",
"print(f\"{eval_preds[:10]=}\")\n",
"print(f\"{dataset['train'][label_column][:10]=}\")\n"
"print(f\"{dataset['train'][label_column][:10]=}\")"
]
},
{
Expand All @@ -416,7 +422,7 @@
" outputs = model.generate(**batch, max_new_tokens=10)\n",
" preds = outputs[:, max_length:].detach().cpu().numpy()\n",
" test_preds.extend(tokenizer.batch_decode(preds, skip_special_tokens=True))\n",
" if len(test_preds)>100:\n",
" if len(test_preds) > 100:\n",
" break\n",
"test_preds"
]
Expand Down
Loading