snli-distilbert-base-uncased-alum | vat Workspace – Weights & Biases

Skip to main content

Arampacha's group workspace

Group: snli-distilbert-base-uncased-alum

eval/accuracy

-

1-1

of 1

Tags

Notes

Simple finetuning distilbert-base-uncased with RAdam lr=2e-5

Tags

alum

distilbert-base-uncased

radam

snli

Author

State

Crashed

Start time

April 18th, 2021 3:20:41 PM

Runtime

3h 54m 21s

Tracked hours

3h 54m 21s

Run path

fastai_community/vat/el2l5xt4

OS

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

Python version

3.7.10

Command

_vat_lm_finetuning_fastai_blurr_nli.ipynb

System Hardware

CPU count	2
GPU count	1
GPU type	Tesla T4

W&B CLI Version

0.10.26

Group

snli-distilbert-base-uncased-alum

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 20 keys
- ▶
  ALUMCallback:{} 3 keys
  - alpha:
    1
  - m:
    "Embeddings( (word_embeddings): Embedding(30522, 768, padding_idx=0) (position_embeddings): Embedding(512, 768) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) )"
  - start_epoch:
    1
- batch per epoch:
  34,335
- batch size:
  16
- dataset.tfms:
  "[Pipeline: get_x, Pipeline: ItemGetter -> Categorize -- {'vocab': [0, 1, 2], '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:
  66,955,779
- 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:{} 30 keys
- accuracy:
  0.8933143615722656
- beta_0:
  0
- beta_1:
  0
- beta_2:
  0
- beta_3:
  0
- epoch:
  3.8612203291108367
- eps_0:
  0.00001
- eps_1:
  0.00001
- eps_2:
  0.00001
- eps_3:
  0.00001
- ▶
  graph_0:{} 4 keys
  - _type:
    "graph-file"
  - path:
    "media/graph/graph_0_summary_2adf0cdc.graph.json"
  - sha256:
    "2adf0cdc9c8c534e84494868c1c0f1d9e99b2d2e496fc2ff345bfe085245227c"
  - size:
    13,326
- lr_0:
  0.00000015849153256739
- lr_1:
  0.00000015849153256739
- lr_2:
  0.00000015849153256739
- lr_3:
  0.00000015849153256739
- mom_0:
  0.9494726896183382
- mom_1:
  0.9494726896183382
- mom_2:
  0.9494726896183382
- mom_3:
  0.9494726896183382
- raw_loss:
  0.3408297300338745
- sqr_mom_0:
  0.99
- sqr_mom_1:
  0.99
- sqr_mom_2:
  0.99
- sqr_mom_3:
  0.99
- train_loss:
  0.3262258470058441
- valid_loss:
  0.3239525258541107
- wd_0:
  0
- wd_1:
  0
- wd_2:
  0
- wd_3:
  0

This run produced these artifacts as outputs. Total: 14. Learn more