utils: add trainer script
Browse files- trainer.py +61 -0
trainer.py
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from datasets import load_dataset
|
2 |
+
from transformers import TrainingArguments
|
3 |
+
from span_marker import SpanMarkerModel, Trainer
|
4 |
+
|
5 |
+
def perform_training(learning_rate: float, seed: int) -> None:
|
6 |
+
# Load the dataset, ensure "tokens" and "ner_tags" columns, and get a list of labels
|
7 |
+
dataset = load_dataset("gwlms/germeval2014")
|
8 |
+
labels = dataset["train"].features["ner_tags"].feature.names
|
9 |
+
|
10 |
+
# Initialize a SpanMarker model using a pretrained BERT-style encoder
|
11 |
+
model_name = "gwlms/span-marker-teams-germeval14"
|
12 |
+
model = SpanMarkerModel.from_pretrained(
|
13 |
+
model_name,
|
14 |
+
labels=labels,
|
15 |
+
# SpanMarker hyperparameters:
|
16 |
+
model_max_length=256,
|
17 |
+
marker_max_length=128,
|
18 |
+
entity_max_length=8,
|
19 |
+
)
|
20 |
+
|
21 |
+
# Prepare the 🤗 transformers training arguments
|
22 |
+
args = TrainingArguments(
|
23 |
+
output_dir=f"./span_marker-{model_name}-bs16-lr{learning_rate}-{seed}",
|
24 |
+
# Training Hyperparameters:
|
25 |
+
learning_rate=learning_rate,
|
26 |
+
per_device_train_batch_size=16,
|
27 |
+
per_device_eval_batch_size=16,
|
28 |
+
num_train_epochs=3,
|
29 |
+
weight_decay=0.01,
|
30 |
+
warmup_ratio=0.1,
|
31 |
+
fp16=True, # Replace `bf16` with `fp16` if your hardware can't use bf16.
|
32 |
+
# Other Training parameters
|
33 |
+
logging_first_step=True,
|
34 |
+
logging_steps=50,
|
35 |
+
evaluation_strategy="epoch",
|
36 |
+
save_strategy="epoch",
|
37 |
+
save_total_limit=11,
|
38 |
+
dataloader_num_workers=2,
|
39 |
+
seed=seed,
|
40 |
+
load_best_model_at_end=True,
|
41 |
+
)
|
42 |
+
|
43 |
+
# Initialize the trainer using our model, training args & dataset, and train
|
44 |
+
trainer = Trainer(
|
45 |
+
model=model,
|
46 |
+
args=args,
|
47 |
+
train_dataset=dataset["train"],
|
48 |
+
eval_dataset=dataset["validation"],
|
49 |
+
)
|
50 |
+
trainer.train()
|
51 |
+
trainer.save_model(f"./span_marker-{model_name}-bs16-lr{learning_rate}-{seed}/best-checkpoint")
|
52 |
+
|
53 |
+
# Compute & save the metrics on the test set
|
54 |
+
metrics = trainer.evaluate(dataset["test"], metric_key_prefix="test")
|
55 |
+
trainer.save_metrics("test", metrics)
|
56 |
+
|
57 |
+
|
58 |
+
if __name__ == "__main__":
|
59 |
+
for learning_rate in [5e-05]:
|
60 |
+
for seed in [1,2,3,4,5]:
|
61 |
+
perform_training(learning_rate, seed)
|