Ctrl+K
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_lower_lr_10k
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_lower_lr_20k
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_lower_lr_30k
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_lower_lr_40k
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_lower_lr_50k
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_step-10000
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_step-20000
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_step-30000
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_step-40000
- ocpython_14b_bsz-2m_seq16k_100raw_docmask_100B_2m_step-50000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_2_step-10000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_2_step-20000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_2_step-30000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_2_step-40000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_2_step-50000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_3_step-10000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_3_step-20000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_3_step-30000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_3_step-40000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_2m_new_3_step-50000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_step-10000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_step-20000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_step-30000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_step-40000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90dynamic-10raw_transsentinel_minsize0ent98line16ow16pack_100B_step-50000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90spm-10raw_transsentinel_pretok_opencodertokenizer_100B_2m_step-10000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90spm-10raw_transsentinel_pretok_opencodertokenizer_100B_2m_step-20000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90spm-10raw_transsentinel_pretok_opencodertokenizer_100B_2m_step-30000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90spm-10raw_transsentinel_pretok_opencodertokenizer_100B_2m_step-40000
- ocpython_14b_bsz-2m_seq16k_docmask_multipredc2r8_90spm-10raw_transsentinel_pretok_opencodertokenizer_100B_2m_step-50000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_2_step-10000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_2_step-20000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_2_step-30000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_2_step-40000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_2_step-50000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_3_step-10000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_3_step-20000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_3_step-30000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_3_step-40000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_new_3_step-50000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_step-10000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_step-20000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_step-30000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_step-40000
- ocpython_14b_bsz-2m_seq8k_tokenized_docmask_100B_2m_step-50000
- ocpython_1b5_bsz-2m_seq16k_docmask_fullyweightednocrosssamplemultipred3_90dynamic-10raw_transrandom_minsize1ent95line16ow16pack_200B_step-10000
- ocpython_1b5_bsz-2m_seq16k_docmask_fullyweightednocrosssamplemultipred3_90dynamic-10raw_transrandom_minsize1ent95line16ow16pack_200B_step-20000
- ocpython_1b5_bsz-2m_seq16k_docmask_fullyweightednocrosssamplemultipred3_90dynamic-10raw_transrandom_minsize1ent95line16ow16pack_200B_step-30000
- ocpython_1b5_bsz-2m_seq16k_docmask_fullyweightednocrosssamplemultipred3_90dynamic-10raw_transrandom_minsize1ent95line16ow16pack_200B_step-40000
- ocpython_1b5_bsz-2m_seq16k_docmask_fullyweightednocrosssamplemultipred3_90dynamic-10raw_transrandom_minsize1ent95line16ow16pack_200B_step-50000