nick11roberts/SL-discrep-chinchilla-rw-params108M_maxstep2340-flop_4_00e17_step_1173
Text Generation • 0.1B • Updated • 25
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 about 1 month ago
Test-Time Scaling Makes Overtraining Compute-Optimal submitted a paper about 1 month ago
Test-Time Scaling Makes Overtraining Compute-Optimal upvoted a paper about 2 months ago
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative TasksOrganizations
nick11roberts/SL-discrep-chinchilla-rw-params149M_maxstep13640-flop_6_40e18_step_13650
Text Generation • 0.2B • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params149M_maxstep13640-flop_3_20e18_step_6826
Text Generation • 0.2B • Updated • 25
nick11roberts/SL-discrep-chinchilla-rw-params28M_maxstep260-flop_1_25e16_step_139
Text Generation • 44.8M • Updated • 29
nick11roberts/SL-discrep-chinchilla-rw-params28M_maxstep260-flop_2_50e16_step_277
Text Generation • 44.8M • Updated • 25
nick11roberts/SL-discrep-chinchilla-rw-params108M_maxstep9360-flop_1_60e18_step_4690
Text Generation • 0.1B • Updated • 29
nick11roberts/SL-discrep-chinchilla-rw-params108M_maxstep9360-flop_3_20e18_step_9378
Text Generation • 0.1B • Updated • 27
nick11roberts/SL-discrep-chinchilla-rw-params9M_maxstep40-flop_3_12e15_step_50
Text Generation • 17.9M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params901M_maxstep2240-flop_6_40e18_step_2256
Text Generation • 1.0B • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params901M_maxstep2240-flop_3_20e18_step_1129
Text Generation • 1.0B • Updated • 27
nick11roberts/SL-discrep-chinchilla-rw-params37M_maxstep1700-flop_2_00e17_step_1715
Text Generation • 56.5M • Updated • 2
nick11roberts/SL-discrep-chinchilla-rw-params37M_maxstep1700-flop_1_00e17_step_858
Text Generation • 56.5M • Updated • 28
nick11roberts/SL-discrep-chinchilla-rw-params149M_maxstep3400-flop_1_60e18_step_3412
Text Generation • 0.2B • Updated • 2
nick11roberts/SL-discrep-chinchilla-rw-params149M_maxstep3400-flop_8_00e17_step_1707
Text Generation • 0.2B • Updated • 27
nick11roberts/SL-discrep-chinchilla-rw-params5M_maxstep760-flop_1_25e16_step_767
Text Generation • 10M • Updated • 27
nick11roberts/SL-discrep-chinchilla-rw-params5M_maxstep760-flop_6_27e15_step_385
Text Generation • 10M • Updated • 2
nick11roberts/SL-discrep-chinchilla-rw-params7M_maxstep1040-flop_2_50e16_step_1059
Text Generation • 14M • Updated • 26
nick11roberts/SL-discrep-chinchilla-rw-params7M_maxstep1040-flop_1_25e16_step_530
Text Generation • 14M • Updated • 25
nick11roberts/SL-discrep-chinchilla-rw-params455M_maxstep4460-flop_3_20e18_step_2235
Text Generation • 0.5B • Updated • 25
nick11roberts/SL-discrep-chinchilla-rw-params455M_maxstep4460-flop_6_40e18_step_4468
Text Generation • 0.5B • Updated • 26
nick11roberts/SL-discrep-chinchilla-rw-params220M_maxstep560-flop_2_00e17_step_288
Text Generation • 0.3B • Updated • 27
nick11roberts/SL-discrep-chinchilla-rw-params220M_maxstep560-flop_4_00e17_step_575
Text Generation • 0.3B • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params347M_maxstep5860-flop_3_20e18_step_2931
Text Generation • 0.4B • Updated • 2
nick11roberts/SL-discrep-chinchilla-rw-params347M_maxstep5860-flop_6_40e18_step_5861
Text Generation • 0.4B • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params22M_maxstep340-flop_2_50e16_step_353
Text Generation • 37M • Updated • 2
nick11roberts/SL-discrep-chinchilla-rw-params22M_maxstep340-flop_1_25e16_step_177
Text Generation • 37M • Updated • 27
nick11roberts/SL-discrep-chinchilla-rw-params220M_maxstep18420-flop_1_28e19_step_18422
Text Generation • 0.3B • Updated • 28
nick11roberts/SL-discrep-chinchilla-rw-params220M_maxstep18420-flop_6_40e18_step_9212
Text Generation • 0.3B • Updated • 2
nick11roberts/SL-discrep-chinchilla-rw-params9M_maxstep100-flop_3_12e15_step_101
Text Generation • 17.9M • Updated • 1
nick11roberts/SL-discrep-chinchilla-rw-params22M_maxstep700-flop_5_00e16_step_706
Text Generation • 37M • Updated • 2