hypo-l | crowdsourced_vs_gpt_datasize_v2 Overview – Weights & Biases

Skip to main content

Ariannapera's group workspace

Group: hypo-l

1-50

of 152

Tags

Notes

Tags

round_2

Author

State

Finished

Start time

October 9th, 2023 12:09:52 PM

Runtime

3m 31s

Tracked hours

3m 20s

Run path

cocoons/crowdsourced_vs_gpt_datasize_v2/r7trhjmy

OS

Linux-3.10.0-1062.18.1.el7.x86_64-x86_64-with-glibc2.2.5

Python version

3.8.2

Git repository

git clone git@github.com:AGMoller/worker_vs_gpt.git

Git state

git checkout -b "llama-2-70b_balanced_size1.0" 38d93efe3591823d0351c45d3ab664cc25fc945c

Command

-m src.worker_vs_gpt.datasize_experiment

System Hardware

CPU count	24
Logical CPU count	48
GPU count	1
GPU type	Tesla V100-PCIE-32GB

W&B CLI Version

0.14.2

Group

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 192 keys
- _name_or_path:
  "intfloat/e5-base"
- adafactor:
  false
- adam_beta1:
  0.9
- adam_beta2:
  0.999
- adam_epsilon:
  0.00000001
- add_cross_attention:
  false
- ▶
  architectures:[] 1 item
  - 0:
    "BertModel"
- attention_probs_dropout_prob:
  0.1
- augmentation_model:
  "llama-2-70b"
- auto_find_batch_size:
  false
- bad_words_ids:
  null
- batch_size:
  16
- begin_suppress_tokens:
  null
- bf16:
  false
- bf16_full_eval:
  false
- bos_token_id:
  null
- chunk_size_feed_forward:
  0
- ckpt:
  "intfloat/e5-base"
- classifier_dropout:
  null
- cross_attention_hidden_size:
  null
- data_seed:
  null
- dataloader_drop_last:
  false
- dataloader_num_workers:
  0
- dataloader_pin_memory:
  true
- ddp_backend:
  null
- ddp_broadcast_buffers:
  null
- ddp_bucket_cap_mb:
  null
- ddp_find_unused_parameters:
  null
- ddp_timeout:
  1,800
- debug:[] 0 items
- decoder_start_token_id:
  null
- deepspeed:
  null
- disable_tqdm:
  false
- dispatch_batches:
  null
- diversity_penalty:
  0
- do_eval:
  true
- do_predict:
  false
- do_sample:
  false
- do_train:
  false
- early_stopping:
  false
- encoder_no_repeat_ngram_size:
  0
- eos_token_id:
  null
- eval_accumulation_steps:
  null
- eval_delay:
  0
- eval_steps:
  null
- evaluation_strategy:
  "epoch"
- vocab_size:
  30,522
- warmup_ratio:
  0
- warmup_steps:
  0
- weight_decay:
  0

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 24 keys
- classification_report:
  "table-file"
- eval/accuracy:
  0.9604743083003952
- eval/f1:
  0.9604736907886516
- eval/loss:
  0.3527873456478119
- eval/roc_auc:
  0.9952470293933708
- eval/runtime:
  0.4204
- eval/samples_per_second:
  601.855
- eval/steps_per_second:
  38.062
- test/accuracy:
  0.7120743034055728
- test/f1:
  0.6584342486781511
- test/loss:
  0.6011872887611389
- test/roc_auc:
  0.7210392762577229
- test/runtime:
  0.5984
- test/samples_per_second:
  539.741
- test/steps_per_second:
  35.092
- train/epoch:
  10
- train/global_step:
  1,610
- train/learning_rate:
  0
- train/loss:
  0.0007
- train/total_flos:
  976,172,848,712,400
- train/train_loss:
  0.08400135565525997
- train/train_runtime:
  198.3447
- train/train_samples_per_second:
  129.421
- train/train_steps_per_second:
  8.117

This run produced these artifacts as outputs. Total: 2. Learn more

run-r7trhjmy-classification_report:v0

run-r7trhjmy-history:v0

Loading...