IMDB-roberta-base-hard-plabels-lr2e-05 | vat Overview – Weights & Biases

Skip to main content

Arampacha's group workspace

Group: IMDB-roberta-base-hard-plabels-lr2e-05

eval/accuracy

-

1-1

of 1

Tags

Notes

Simple finetuning roberta-base with RAdam lr=2e-05

Tags

imdb

plabels

radam

roberta-base

unsup

Author

State

Crashed

Start time

April 26th, 2021 7:33:07 PM

Runtime

6h 36m 54s

Tracked hours

5h 36m 43s

Run path

fastai_community/vat/213pa8rj

OS

Linux-4.19.112+-x86_64-with-Ubuntu-18.04-bionic

Python version

3.7.10

Command

_self_training_imdb-roberta-alum.ipynb

System Hardware

CPU count	2
GPU count	1
GPU type	Tesla T4

W&B CLI Version

0.10.27

Group

IMDB-roberta-base-hard-plabels-lr2e-05

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 20 keys
- ▶
  ALUMCallback:{} 3 keys
  - alpha:
    0.7
  - m:
    "RobertaEmbeddings( (word_embeddings): Embedding(50265, 768, padding_idx=1) (position_embeddings): Embedding(514, 768, padding_idx=1) (token_type_embeddings): Embedding(1, 768) (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) )"
  - start_epoch:
    1
- batch per epoch:
  9,118
- batch size:
  8
- dataset.tfms:
  "[Pipeline: ItemGetter -> read_text, Pipeline: ItemGetter -> Categorize -- {'vocab': None, 'sort': True, 'add_na': False}]"
- device:
  "cuda"
- dls.after_batch:
  "Pipeline: HF_AfterBatchTransform"
- dls.after_item:
  "Pipeline: ToTensor"
- dls.before_batch:
  "Pipeline: HF_BeforeBatchTransform"
- frozen:
  false
- frozen idx:
  0
- HF_BaseModelCallback:
  true
- ▶
  Learner:{} 12 keys
- MixedPrecision:
  true
- model parameters:
  124,647,170
- n_inp:
  1
- ParamScheduler:
  true
- ProgressCallback:
  true
- ▶
  Recorder:{} 3 keys
  - add_time:
    true
  - train_metrics:
    false
  - valid_metrics:
    true
- TrainEvalCallback:
  true
- ▶
  WandbCallback:{} 9 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 24 keys
- accuracy:
  0.9576399922370912
- beta_0:
  0
- beta_1:
  0
- beta_2:
  0
- epoch:
  4
- eps_0:
  0.00001
- eps_1:
  0.00001
- eps_2:
  0.00001
- ▶
  graph_0:{} 4 keys
  - _type:
    "graph-file"
  - path:
    "media/graph/graph_0_summary_dcf71b03.graph.json"
  - sha256:
    "dcf71b03c15fab56b0a0e92e55ffdc8a533874ace48042399e07896a7fa4ccf7"
  - size:
    28,208
- lr_0:
  0.00000000020006587893
- lr_1:
  0.00000000020006587893
- lr_2:
  0.00000000020006587893
- mom_0:
  0.949999999670602
- mom_1:
  0.949999999670602
- mom_2:
  0.949999999670602
- raw_loss:
  0.02139529399573803
- sqr_mom_0:
  0.99
- sqr_mom_1:
  0.99
- sqr_mom_2:
  0.99
- train_loss:
  0.032125506550073624
- valid_loss:
  0.12217216938734056
- wd_0:
  0
- wd_1:
  0
- wd_2:
  0

This run produced these artifacts as outputs. Total: 7. Learn more

source-213pa8rj:v0

source-213pa8rj:v1

source-213pa8rj:v2

source-213pa8rj:v3

source-213pa8rj:v4

source-213pa8rj:v5

run-213pa8rj-history:v0

Loading...