Skip to main content
zhehuaic
Projects
canary-v0_speechllm
Reports
canary dataset main experiments
Log in
Sign up
Share
Comment
Star
Share
Comment
Star
canary dataset main experiments
Zhehuai Chen
Created on June 13
|
Last edited on July 15
Comment
Section 1
covost_v2.es_en.dev.es_val_sacreBLEU
covost_v2.es_en.dev.es_val_sacreBLEU
Select runs that logged covost_v2.es_en.dev.es_val_sacreBLEU
to visualize data in this line chart.
validation_bleu_covost_v2.es_en.dev.es
validation_bleu_covost_v2.es_en.dev.es
500
1k
1.5k
2k
2.5k
Step
33
34
35
36
37
38
train_loss
train_loss
Select runs that logged train_loss
to visualize data in this line chart.
train_step_timing in s
train_step_timing in s
50k
100k
150k
global_step
1
2
3
4
5
6
reduced_train_loss
reduced_train_loss
50k
100k
150k
global_step
2
4
6
Run: crossbmg4egc_lhmain3cross_oci_FC-GPT_llama_tiny_canaryset_b6s4kf-ASR-AST_lr1e-4wd1e-3_CosineAnnealing_warmup2000_minlr1e-6_gbs1024_mbs16_ep200
436
Run set 2
Run set 5
™
Add a comment