- dataset_column_name=raw_content, dataset_split=train, dataset_subset=sample, dataset_uri=togethercomputer_RedPajama-Data-V2
- dataset_shuffle=True, dataset_split=train, dataset_subset=None, dataset_uri=distily_c4_multilingual_1M, lr_scheduler_kwargs=None, lr_scheduler_type=constant
- dataset_shuffle=True, dataset_split=train, dataset_subset=None, dataset_uri=distily_synth_gpt2_t1_seq_1M, lr_scheduler_kwargs=None, lr_scheduler_type=constant
- dataset_split=train, dataset_subset=None, dataset_uri=distily_c4_multilingual_1M, lr_scheduler_kwargs=None, lr_scheduler_type=constant
- dataset_split=train, dataset_subset=None, dataset_uri=distily_c4_multilingual_1M
- dataset_split=train, dataset_subset=None, dataset_uri=distily_filtered_redpajama_en
- dataset_split=train, dataset_subset=None, dataset_uri=distily_filtered_redpajama_multilingual
- dataset_split=train, dataset_subset=None, dataset_uri=distily_synth_gpt2_t1_seq_1M, lr_scheduler_kwargs=None, lr_scheduler_type=constant
- dataset_split=train, dataset_subset=None, dataset_uri=distily_synth_gpt2_t1_seq_1M
-
0 Bytes
-
1.49 MB
LFS
-
529 Bytes
LFS