Skip to main content
zhehuaic
Projects
canary-v0_speechllm
Reports
Translation of zhehuaic's 7b SALMs

Translation of zhehuaic's 7b SALMs

Zhehuai Chen
Created on August 26|Last edited on August 26

Section 1


20k40k60k80k100k120ktrainer/global_step05101520
prompt_lora_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
prompt_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
20k40k60k80k100k120ktrainer/global_step00.511.52
prompt_lora_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
prompt_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
20k40k60k80k100k120ktrainer/global_step05101520
prompt_lora_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
prompt_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
20k40k60k80k100k120ktrainer/global_step0510152025
prompt_lora_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
prompt_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
20k40k60k80k100k120ktrainer/global_step01234
prompt_lora_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
prompt_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
20k40k60k80k100k120ktrainer/global_step05101520
prompt_lora_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
prompt_lhmerge5_12p_tp2f_oci_FC-GPT_alma7b_canaryset_b6s4kf-sunolong_noCC_langtemp0.5_dsettemp0.5_lr3e-5wd1e-3_CosineAnnealing_warmup2500_minlr1e-6_gbs768_mbs16_ep200
Run set
457



Run set
467


Created with ❤️ on Weights & Biases.

https://wandb.ai/zhehuaic/canary-v0_speechllm/reports/Translation-of-zhehuaic-s-7b-SALMs--Vmlldzo5MTUzMDkx
Made with Weights & Biases. Sign up or log in to create reports like this one.