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.

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

Standardizing data loader and pulling from split for adding custom dataset dwmw17 #268

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open
Changes from 1 commit
Commits
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
Prev Previous commit
Adding experiment for dwmw17
Harsh Karia authored and Harsh Karia committed Apr 19, 2023
commit ceca3d0032bf3e95c95bcfe872abd3d1ddc886be
68 changes: 68 additions & 0 deletions experiments/classification_protoverb_dwmw17.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,68 @@
dataset:
name: dwmw17
path: datasets/TextClassification/dwmw17

plm:
model_name: roberta
model_path: roberta-large
optimize:
freeze_para: False
lr: 0.00003
weight_decay: 0.01
scheduler:
type:
num_warmup_steps: 500

checkpoint:
save_latest: False
save_best: False

train:
batch_size: 2
num_epochs: 5
train_verblizer: post
clean: True

test:
batch_size: 2

template: manual_template
verbalizer: proto_verbalizer

manual_template:
choice: 0
file_path: scripts/TextClassification/dwmw17/manual_template.txt

proto_verbalizer:
parent_config: dwmw17
choice: 0
file_path: scripts/TextClassification/dwmw17/icl_verbalizer.json
lr: 0.01
mid_dim: 128
epochs: 30
multi_verb: multi



environment:
num_gpus: 1
cuda_visible_devices:
- 0
local_rank: 0

learning_setting: few_shot

few_shot:
parent_config: learning_setting
few_shot_sampling: sampling_from_train

sampling_from_train:
parent_config: few_shot_sampling
num_examples_per_label: 1
also_sample_dev: True
num_examples_per_label_dev: 1
seed:
- 123

reproduce: # seed for reproduction
seed: 123 # a seed for all random part