base | whisper_finetuning Workspace – Weights & Biases

Skip to main content

Parambharat's group workspace

Group: base

10

1-1

of 1

Tags

Notes

Author

State

Crashed

Start time

December 12th, 2022 12:25:16 PM

Runtime

3d 12h 46m 20s

Tracked hours

1d 20h 48m 47s

Run path

parambharat/whisper_finetuning/20dsv01o

OS

Linux-5.15.0-56-generic-x86_64-with-glibc2.17

Python version

3.8.13

Command

whisper_base_ta

System Hardware

CPU count	10
Logical CPU count	20
GPU count	1
GPU type	NVIDIA GeForce RTX 3060

W&B CLI Version

0.13.6

Group

Job Type

fine-tuning

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 189 keys
- _name_or_path:
  "openai/whisper-base"
- activation_dropout:
  0
- activation_function:
  "gelu"
- adafactor:
  false
- adam_beta1:
  0.9
- adam_beta2:
  0.999
- adam_epsilon:
  0.00000001
- add_cross_attention:
  false
- ▶
  architectures:[] 1 item
  - 0:
    "WhisperForConditionalGeneration"
- attention_dropout:
  0
- auto_find_batch_size:
  false
- bad_words_ids:
  null
- ▶
  begin_suppress_tokens:[] 2 items
  - 0:
    220
  - 1:
    50,257
- bf16:
  false
- bf16_full_eval:
  false
- bos_token_id:
  50,257
- chunk_size_feed_forward:
  0
- cross_attention_hidden_size:
  null
- d_model:
  512
- data_seed:
  "None"
- dataloader_drop_last:
  false
- dataloader_num_workers:
  0
- dataloader_pin_memory:
  true
- ddp_bucket_cap_mb:
  "None"
- ddp_find_unused_parameters:
  "None"
- ddp_timeout:
  1,800
- debug:
  "[]"
- decoder_attention_heads:
  8
- decoder_ffn_dim:
  2,048
- decoder_layerdrop:
  0
- decoder_layers:
  6
- decoder_start_token_id:
  50,258
- deepspeed:
  "None"
- disable_tqdm:
  false
- diversity_penalty:
  0
- do_eval:
  true
- do_predict:
  false
- do_sample:
  false
- do_train:
  false
- dropout:
  0
- early_stopping:
  false
- encoder_attention_heads:
  8
- encoder_ffn_dim:
  2,048
- encoder_layerdrop:
  0
- encoder_layers:
  6
- encoder_no_repeat_ngram_size:
  0
- warmup_ratio:
  0
- warmup_steps:
  1,000
- weight_decay:
  0
- xpu_backend:
  "None"

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 15 keys
- eval/loss:
  1.8921992778778076
- eval/runtime:
  3,323.6424
- eval/samples_per_second:
  0.178
- eval/steps_per_second:
  0.006
- eval/wer:
  100.30248033877798
- sample_predictions:
  "table-file"
- train/epoch:
  0.4
- train/global_step:
  10,000
- train/learning_rate:
  0.00000000333333333333
- train/loss:
  0.2389
- train/total_flos:
  41,510,397,542,400,000,000
- train/train_loss:
  0.09611414756774904
- train/train_runtime:
  48,389.7135
- train/train_samples_per_second:
  13.226
- train/train_steps_per_second:
  0.207

This run produced these artifacts as outputs. Total: 62. Learn more

run-20dsv01o-sample_predictions:v0

run-20dsv01o-sample_predictions:v1

run-20dsv01o-sample_predictions:v2

run-20dsv01o-sample_predictions:v3

model-20dsv01o:v0

run-20dsv01o-sample_predictions:v4

run-20dsv01o-sample_predictions:v5

run-20dsv01o-sample_predictions:v6

run-20dsv01o-sample_predictions:v7

model-20dsv01o:v1

run-20dsv01o-sample_predictions:v8

run-20dsv01o-sample_predictions:v9

run-20dsv01o-sample_predictions:v10

run-20dsv01o-sample_predictions:v11

model-20dsv01o:v2

run-20dsv01o-sample_predictions:v12

run-20dsv01o-sample_predictions:v13

run-20dsv01o-sample_predictions:v14

run-20dsv01o-sample_predictions:v15

run-20dsv01o-sample_predictions:v16

Loading...