turtleS_LittleTest_bart-base | celian-ringwald Overview – Weights & Biases

Skip to main content

Celian-ringwald's group workspace

Group: turtleS_LittleTest_bart-base

1-5

of 5

Tags

Notes

Author

celian-ringwald

State

Finished

Start time

October 17th, 2023 12:21:04 PM

Runtime

11m 57s

Tracked hours

11m 51s

Run path

celian-ringwald/SynthaxBartCV_1/j8zlipqc

OS

Linux-3.10.0-1160.42.2.el7.x86_64-x86_64-with-glibc2.17

Python version

3.11.5

Command

/home/cringwald/EXP_env/./src/train.py model=bart_base_model data=bart_turtleS train=dbpedia_train

System Hardware

CPU count	40
Logical CPU count	40
GPU count	1
GPU type	Tesla V100-SXM2-32GB

W&B CLI Version

0.15.11

Group

turtleS_LittleTest_bart-base

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 99 keys
- adafactor:
  false
- adam_beta1:
  0.9
- adam_beta2:
  0.999
- adam_epsilon:
  0.00000001
- amp_level:
  null
- apply_early_stopping:
  true
- attention_dropout:
  null
- cache_dir:
  null
- checkpoint_path:
  null
- classifier:
  false
- config_name:
  "facebook/bart-base"
- dataloader_drop_last:
  false
- dataloader_num_workers:
  4
- dataloader_pin_memory:
  true
- dataset_name:
  "/home/cringwald/EXP_env/datasets/dbpedia_test.py"
- decoder_layerdrop:
  null
- deepspeed:
  null
- disable_tqdm:
  null
- do_eval:
  true
- do_predict:
  true
- do_train:
  true
- dropout:
  0.1
- eval_accumulation_steps:
  null
- eval_batch_size:
  8
- eval_beams:
  3
- eval_steps:
  10
- evaluation_strategy:
  "no"
- finetune:
  false
- fp16_backend:
  "auto"
- fp16_opt_level:
  "O1"
- gpus:
  1
- gradient_acc_steps:
  8
- gradient_accumulation_steps:
  1
- gradient_clip_value:
  10
- greater_is_better:
  null
- group_by_length:
  false
- ignore_data_skip:
  false
- ignore_pad_token_for_loss:
  true
- label_names:
  null
- label_smoothing:
  0
- label_smoothing_factor:
  0
- learning_rate:
  0.00005
- load_best_model_at_end:
  false
- local_rank:
  -1
- lr_scheduler:
  "inverse_square_root"
- max_grad_norm:
  1
- val_percent_check:
  0.1
- validation_file:
  "/workspace/cringwald/exp1_out/BART_model/DS_turtleS_val_bart.json"
- warmup_steps:
  1,000
- weight_decay:
  0.01

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 24 keys
- epoch:
  4
- loss:
  0.007102637551724911
- lr-AdamW/pg1:
  0.00001995
- lr-AdamW/pg2:
  0.00001995
- test_F1_macro:
  99.9849510910459
- test_F1_micro:
  99.98450469970705
- test_loss:
  0.002935125259682536
- test_n_parsed:
  1,000
- test_n_subj_ok:
  1,000
- test_prec_macro:
  99.96992481203009
- test_prec_micro:
  99.96902465820312
- test_recall_macro:
  100
- test_recall_micro:
  100
- trainer/global_step:
  437
- Triplets:
  "table-file"
- val_F1_macro:
  100
- val_F1_micro:
  100
- val_loss:
  0.021515758708119392
- val_n_parsed:
  24
- val_n_subj_ok:
  24
- val_prec_macro:
  100
- val_prec_micro:
  100
- val_recall_macro:
  100
- val_recall_micro:
  100

This run produced these artifacts as outputs. Total: 12. Learn more

run-j8zlipqc-history:v0

Loading...