k5nu8k69390a-Baseline | dchanda Workspace – Weights & Biases

Skip to main content

Dchanda's group workspace

Group: k5nu8k69390a-Baseline

5

1-1

of 1

Tags

Notes

Tags

k5nu8k69390a

margin-loss

roberta-base

Author

State

Finished

Start time

November 9th, 2021 8:07:21 AM

Runtime

34m 44s

Tracked hours

34m 41s

Run path

dchanda/Jigsaw/2kocz0r7

OS

Linux-5.10.68+-x86_64-with-debian-buster-sid

Python version

3.7.10

Command

kaggle.ipynb

System Hardware

CPU count	2
GPU count	1
GPU type	Tesla P100-PCIE-16GB

W&B CLI Version

0.12.6

Group

k5nu8k69390a-Baseline

Job Type

Train

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 19 keys
- device:
  "cuda:0"
- epochs:
  3
- group:
  "k5nu8k69390a-Baseline"
- hash_name:
  "k5nu8k69390a"
- learning_rate:
  0.0001
- margin:
  0.5
- max_length:
  128
- min_lr:
  0.000001
- model_name:
  "roberta-base"
- n_accumulate:
  1
- n_fold:
  5
- num_classes:
  1
- scheduler:
  "CosineAnnealingLR"
- seed:
  2,021
- T_max:
  500
- tokenizer:
  "PreTrainedTokenizerFast(name_or_path='roberta-base', vocab_size=50265, model_max_len=512, is_fast=True, padding_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>', 'sep_token': '</s>', 'pad_token': '<pad>', 'cls_token': '<s>', 'mask_token': AddedToken("<mask>", rstrip=False, lstrip=True, single_word=False, normalized=False)})"
- train_batch_size:
  32
- valid_batch_size:
  64
- weight_decay:
  0.000001

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 3 keys
- Best Loss:
  0.34013118115132324
- Train Loss:
  0.34680072549096447
- Valid Loss:
  0.3497176492848758

This run produced these artifacts as outputs. Total: 1. Learn more

run-2kocz0r7-history:v0

Loading...