Hi, I'm tring to read the training code of SEARC, I wonder where is the loss and it se

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

Is SEARC's training loss same with paper? about easyedit HOT 5 CLOSED

Luoyang144 commented on August 16, 2024

Is SEARC's training loss same with paper?

from easyedit.

Comments (5)

XeeKee commented on August 16, 2024

The training loss of the counterfact model is NLL. The masked_log_probs is just an entry point, and the actual execution is at

EasyEdit/easyeditor/trainer/losses.py

Line 55 in 38c5c34

    
           def multiclass_log_probs(config, pred, targ, shift=False, eps=torch.finfo(torch.float32).eps, exact_match=False, **kwargs):

, where we calculate the NLL.

from easyedit.

zxlzr commented on August 16, 2024

Hi, do you have any further questions?

from easyedit.

Luoyang144 commented on August 16, 2024

@XeeKee Hi, thanks for reply, which function is the execution of scope classifier's loss?

from easyedit.

XeeKee commented on August 16, 2024

Here, we referenced the source code from SERAC. The classifier and the small model are trained together.

from easyedit.

zxlzr commented on August 16, 2024

Hi, do you have any further questions?

from easyedit.

Related Issues (20)

Evaluation Question HOT 4
locality and portability evaluation HOT 8
GRACE sequential edit result HOT 15
IKE fluency HOT 2
ccks gpt2-xl 模型为什么用roberta模型加载？ HOT 2
R-ROME has poor performance when using GPT2-xl HOT 2
WISE CONTEXT_TEMPLATES_CACHE HOT 7
WISE tokenize HOT 7
what is the meaning of archive HOT 2
[Wise] Editing loss = nan + 0 HOT 2
AttributeError: Can't pickle local object 'length_collation.<locals>.collate_fn' HOT 8
Issue with KN batch editing HOT 2
Question about ZSRE experiment, how to reproduce results in your WISE paper? HOT 6
PermissionError: [Errno 13] Permission denied: './results/models/MEND/gpt2-xl' HOT 3
Using MEND with monkeypatch from higher HOT 10
CCKS2024 ROME Question HOT 6
WISE errors HOT 3
Use EasyEdit with KnowEdit HOT 13
Error calculation "adj_k" to edit LLAMA-3-8B using MEMIT HOT 4
关于wise.py HOT 3

Is SEARC's training loss same with paper? about easyedit HOT 5 CLOSED

Comments (5)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent