nick11roberts/SL-discrep-chinchilla-rw-params455M_maxstep8920-flop_6_40e18_step_4469
Text Generation • 0.5B • Updated • 1
Nicholas Roberts PRO
nick11roberts
AI & ML interests
Data-Centric AutoML–i.e., making machine learning more accessible and practically applicable to new domains while reducing human involvement.
Recent Activity
upvoted a paper 11 days ago
Test-Time Scaling Makes Overtraining Compute-Optimal submitted a paper 11 days ago
Test-Time Scaling Makes Overtraining Compute-Optimal upvoted a paper 21 days ago
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative TasksOrganizations
nick11roberts/SL-discrep-chinchilla-rw-params455M_maxstep8920-flop_1_28e19_step_8936
Text Generation • 0.5B • Updated • 4
nick11roberts/SL-discrep-chinchilla-rw-params7M_maxstep120-flop_3_12e15_step_132
Text Generation • 14M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params28M_maxstep1100-flop_1_00e17_step_1108
Text Generation • 44.8M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params28M_maxstep1100-flop_5_01e16_step_555
Text Generation • 44.8M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params57M_maxstep1100-flop_2_00e17_step_1107
Text Generation • 81.6M • Updated • 2
nick11roberts/SL-discrep-chinchilla-rw-params57M_maxstep1100-flop_1_00e17_step_554
Text Generation • 81.6M • Updated • 106
nick11roberts/SL-discrep-chinchilla-rw-params37M_maxstep840-flop_5_00e16_step_429
Text Generation • 56.5M • Updated • 104
nick11roberts/SL-discrep-chinchilla-rw-params37M_maxstep840-flop_1_00e17_step_857
Text Generation • 56.5M • Updated • 4
nick11roberts/SL-discrep-chinchilla-rw-params15M_maxstep500-flop_2_50e16_step_509
Text Generation • 26.9M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params15M_maxstep500-flop_1_25e16_step_255
Text Generation • 26.9M • Updated • 101
nick11roberts/SL-discrep-chinchilla-rw-params611M_maxstep13280-flop_2_56e19_step_13298
Text Generation • 0.7B • Updated • 152
nick11roberts/SL-discrep-chinchilla-rw-params611M_maxstep13280-flop_1_28e19_step_6650
Text Generation • 0.7B • Updated • 7
nick11roberts/SL-discrep-chinchilla-rw-params7M_maxstep520-flop_6_26e15_step_265
Text Generation • 14M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params7M_maxstep520-flop_1_25e16_step_529
Text Generation • 14M • Updated • 2
nick11roberts/SL-discrep-chinchilla-rw-params5M_maxstep380-flop_3_14e15_step_193
Text Generation • 10M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params5M_maxstep380-flop_6_25e15_step_383
Text Generation • 10M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params84M_maxstep180-flop_5_00e16_step_187
Text Generation • 0.1B • Updated • 101
nick11roberts/SL-discrep-chinchilla-rw-params84M_maxstep180-flop_2_51e16_step_94
Text Generation • 0.1B • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params28M_maxstep2200-flop_2_00e17_step_2217
Text Generation • 44.8M • Updated
nick11roberts/SL-discrep-chinchilla-rw-params28M_maxstep2200-flop_1_00e17_step_1109
Text Generation • 44.8M • Updated • 107
nick11roberts/SL-discrep-chinchilla-rw-params347M_maxstep14640-flop_1_28e19_step_14654
Text Generation • 0.4B • Updated • 107
nick11roberts/SL-discrep-chinchilla-rw-params347M_maxstep14640-flop_1_28e19_step_11724
Text Generation • 0.4B • Updated • 2
nick11roberts/SL-discrep-chinchilla-rw-params57M_maxstep540-flop_5_00e16_step_277
Text Generation • 81.6M • Updated • 107
nick11roberts/SL-discrep-chinchilla-rw-params57M_maxstep540-flop_1_00e17_step_553
Text Generation • 81.6M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params15M_maxstep60-flop_3_12e15_step_63
Text Generation • 26.9M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params611M_maxstep3320-flop_3_20e18_step_1663
Text Generation • 0.7B • Updated • 96
nick11roberts/SL-discrep-chinchilla-rw-params611M_maxstep3320-flop_6_40e18_step_3324
Text Generation • 0.7B • Updated • 115
nick11roberts/resolving_test
10M • Updated • 1
nick11roberts/gpt-neo-125M_pretrain-code-50000
Text Generation • Updated • 3