yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-08-04 06:42:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

ch06/03 fixes (#336)

Browse Source 
* fixed bash commands

* fixed help docstrings

* added missing logreg bash cmd

* Update train_bert_hf.py

* Update train_bert_hf_spam.py

* Update README.md

---------

Co-authored-by: Sebastian Raschka <mail@sebastianraschka.com>
This commit is contained in:
Daniel Kleine 2024-08-27 08:23:25 +02:00 committed by GitHub
parent 91cdfe3309
commit c7267c3b09
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 23 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
ch06/03_bonus_imdb-classification/README.md
View File

@ -56,7 +56,7 @@ Test accuracy: 91.88%
A 340M parameter encoder-style [BERT](https://arxiv.org/abs/1810.04805) model:
```bash
python train_bert_hf --trainable_layers "all" --num_epochs 1 --model "bert"
python train_bert_hf.py --trainable_layers "all" --num_epochs 1 --model "bert"
```
```
@ -114,7 +114,7 @@ A 355M parameter encoder-style [RoBERTa](https://arxiv.org/abs/1907.11692) model
```bash
python train_bert_hf.py --trainable_layers "last_block" --num_epochs 1 --bert_model "roberta"
python train_bert_hf.py --trainable_layers "last_block" --num_epochs 1 --model "roberta"
```
```
@ -140,7 +140,12 @@ Test accuracy: 92.95%
<br>
A scikit-learn logistic regression classifier as a baseline.
A scikit-learn logistic regression classifier as a baseline:
```bash
python train_sklearn_logreg.py
```
```
Dummy classifier:

14
ch06/03_bonus_imdb-classification/train_bert_hf.py
View File

@ -189,15 +189,15 @@ if __name__ == "__main__":
type=str,
default="true",
help=(
"Whether to use a attention mask for padding tokens. Options: 'true', 'false'"
"Whether to use a attention mask for padding tokens. Options: 'true', 'false'."
)
)
parser.add_argument(
"--bert_model",
"--model",
type=str,
default="distilbert",
help=(
"Which model to train. Options: 'distilbert', 'bert'."
"Which model to train. Options: 'distilbert', 'bert', 'roberta'."
)
)
parser.add_argument(
@ -223,7 +223,7 @@ if __name__ == "__main__":
###############################
torch.manual_seed(123)
if args.bert_model == "distilbert":
if args.model == "distilbert":
model = AutoModelForSequenceClassification.from_pretrained(
"distilbert-base-uncased", num_labels=2
@ -247,7 +247,7 @@ if __name__ == "__main__":
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
elif args.bert_model == "bert":
elif args.model == "bert":
model = AutoModelForSequenceClassification.from_pretrained(
"bert-base-uncased", num_labels=2
@ -272,7 +272,7 @@ if __name__ == "__main__":
raise ValueError("Invalid --trainable_layers argument.")
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
elif args.bert_model == "roberta":
elif args.model == "roberta":
model = AutoModelForSequenceClassification.from_pretrained(
"FacebookAI/roberta-large", num_labels=2
@ -296,7 +296,7 @@ if __name__ == "__main__":
tokenizer = AutoTokenizer.from_pretrained("FacebookAI/roberta-large")
else:
raise ValueError("Selected --bert_model not supported.")
raise ValueError("Selected --model {args.model} not supported.")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

14
ch06/03_bonus_imdb-classification/train_bert_hf_spam.py
View File

@ -280,15 +280,15 @@ if __name__ == "__main__":
type=str,
default="true",
help=(
"Whether to use a attention mask for padding tokens. Options: 'true', 'false'"
"Whether to use a attention mask for padding tokens. Options: 'true', 'false'."
)
)
parser.add_argument(
"--bert_model",
"--model",
type=str,
default="distilbert",
help=(
"Which model to train. Options: 'distilbert', 'bert'."
"Which model to train. Options: 'distilbert', 'bert', 'roberta'."
)
)
parser.add_argument(
@ -314,7 +314,7 @@ if __name__ == "__main__":
###############################
torch.manual_seed(123)
if args.bert_model == "distilbert":
if args.model == "distilbert":
model = AutoModelForSequenceClassification.from_pretrained(
"distilbert-base-uncased", num_labels=2
@ -338,7 +338,7 @@ if __name__ == "__main__":
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
elif args.bert_model == "bert":
elif args.model == "bert":
model = AutoModelForSequenceClassification.from_pretrained(
"bert-base-uncased", num_labels=2
@ -363,7 +363,7 @@ if __name__ == "__main__":
raise ValueError("Invalid --trainable_layers argument.")
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
elif args.bert_model == "roberta":
elif args.model == "roberta":
model = AutoModelForSequenceClassification.from_pretrained(
"FacebookAI/roberta-large", num_labels=2
@ -387,7 +387,7 @@ if __name__ == "__main__":
tokenizer = AutoTokenizer.from_pretrained("FacebookAI/roberta-large")
else:
raise ValueError("Selected --bert_model not supported.")
raise ValueError("Selected --model {args.model} not supported.")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)