Skip to main content
zhehuaic
Projects
canary-v0_speechllm
Reports
p2i systems

p2i systems

Zhehuai Chen
Created on October 12|Last edited on October 15

Section 1


1k2k3k4k5k6kStep0246
bestow_s_lorah_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs16_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorac_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2h_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
1k2k3k4k5k6kStep020406080
bestow_s_lorah_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs16_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorac_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2h_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
50k100k150ktrainer/global_step020406080
bestow_s_lorah_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs16_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorac_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2h_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
50k100k150ktrainer/global_step020406080
bestow_s_lorah_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs16_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorac_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2h_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
50k100k150ktrainer/global_step0102030
bestow_s_lorah_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs16_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorac_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2h_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
1k2k3k4k5k6kStep0102030
bestow_s_lorah_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs16_mbs16_ep200
bestow_s_lorag_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2j_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
prompt_lorac_lhmerge5_p2i_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
bestow_s_lorae_lhmerge5_p2h_oci_FC-GPT_gemma-2b-it-v1.1_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr1e-4wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs2048_mbs16_ep200
Run set
461



Created with ❤️ on Weights & Biases.

https://wandb.ai/zhehuaic/canary-v0_speechllm/reports/p2i-systems--Vmlldzo5Njk3MTg2
Made with Weights & Biases. Sign up or log in to create reports like this one.