loris3/stratified_equitoken_10m_curriculum_roberta_roberta_influence_decr_bins_lognorm Fill-Mask • 0.1B • Updated Apr 14, 2025 • 8
loris3/stratified_equitoken_10m_curriculum_roberta_roberta_influence_incr_bins_lognorm Fill-Mask • 0.1B • Updated Apr 14, 2025 • 4
loris3/stratified_equitoken_10m_curriculum_roberta_roberta_influence_decr_bins_dirac Fill-Mask • 0.1B • Updated Apr 14, 2025 • 6
loris3/stratified_equitoken_10m_curriculum_roberta_roberta_influence_incr_bins_dirac Fill-Mask • 0.1B • Updated Apr 14, 2025 • 11
loris3/stratified_equitoken_10m_curriculum_roberta_roberta_influence_epoch_repetition Fill-Mask • 0.1B • Updated Apr 14, 2025 • 8
loris3/stratified_equitoken_10m_curriculum_llama_llama_influence_decr_bins_lognorm Text Generation • 97.2M • Updated Apr 14, 2025 • 9
loris3/babylm_2024_10m_curriculum_roberta_roberta_influence_decr_bins_lognorm Fill-Mask • 0.1B • Updated Apr 14, 2025 • 7
loris3/babylm_2024_10m_curriculum_roberta_mattr_increasing Fill-Mask • 0.1B • Updated Apr 14, 2025 • 14
loris3/babylm_2024_10m_curriculum_roberta_source_difficulty Fill-Mask • 0.1B • Updated Apr 14, 2025 • 12
loris3/babylm_2024_10m_curriculum_roberta_roberta_influence_tracin_sandwich Fill-Mask • 0.1B • Updated Apr 9, 2025 • 16
loris3/babylm_2024_10m_curriculum_roberta_roberta_influence_top_50_cp_shuffled Fill-Mask • 0.1B • Updated Apr 9, 2025 • 7
loris3/babylm_2024_10m_curriculum_roberta_roberta_influence_decr_cp_dirac Fill-Mask • 0.1B • Updated Apr 9, 2025 • 7
loris3/babylm_2024_10m_curriculum_roberta_roberta_influence_incr_cp_dirac Fill-Mask • 0.1B • Updated Apr 8, 2025 • 6
loris3/babylm_2024_10m_curriculum_roberta_roberta_influence_incr_bins_lognorm Fill-Mask • 0.1B • Updated Apr 8, 2025 • 9
loris3/babylm_2024_10m_curriculum_roberta_roberta_influence_decr_bins_dirac Fill-Mask • 0.1B • Updated Apr 8, 2025 • 16
loris3/babylm_2024_10m_curriculum_roberta_roberta_influence_incr_bins_dirac Fill-Mask • 0.1B • Updated Apr 8, 2025 • 6
loris3/babylm_2024_10m_curriculum_roberta_roberta_influence_epoch_repetition Fill-Mask • 0.1B • Updated Apr 8, 2025 • 11
loris3/stratified_equitoken_10m_curriculum_roberta_random Fill-Mask • 0.1B • Updated Apr 7, 2025 • 16
loris3/stratified_10m_curriculum_llama_perplexity_increasing Text Generation • 97.2M • Updated Apr 5, 2025 • 7
loris3/stratified_10m_curriculum_llama_mattr_increasing Text Generation • 97.2M • Updated Apr 5, 2025 • 10
loris3/stratified_10m_curriculum_llama_source_difficulty Text Generation • 97.2M • Updated Apr 5, 2025 • 7
loris3/stratified_10m_curriculum_llama_llama_influence_tracin_sandwich Text Generation • 97.2M • Updated Apr 5, 2025 • 10
loris3/stratified_10m_curriculum_llama_llama_influence_top_50_cp_shuffled Text Generation • 97.2M • Updated Apr 5, 2025 • 9
loris3/stratified_10m_curriculum_llama_llama_influence_decr_cp_dirac Text Generation • 97.2M • Updated Apr 4, 2025 • 11
loris3/stratified_10m_curriculum_llama_llama_influence_incr_cp_dirac Text Generation • 97.2M • Updated Apr 4, 2025 • 8
loris3/stratified_10m_curriculum_llama_llama_influence_incr_bins_lognorm Text Generation • 97.2M • Updated Apr 4, 2025 • 8
loris3/stratified_10m_curriculum_llama_llama_influence_decr_bins_dirac Text Generation • 97.2M • Updated Apr 4, 2025 • 10
loris3/stratified_10m_curriculum_llama_llama_influence_incr_bins_dirac Text Generation • 97.2M • Updated Apr 4, 2025 • 7