18 days ago
-
upload: checkpoints/part2/sweep_sophia_lr/sophia_lr_5e-4_dynamics_history.json
-
upload: checkpoints/part2/sweep_sophia_lr/sophia_lr_5e-4_model_best.pt
-
upload: checkpoints/part2/sweep_muon_lr/muon_lr_0.01_dynamics_history.json
-
upload: checkpoints/part2/sweep_muon_lr/muon_lr_0.01_model_best.pt
-
upload: checkpoints/part2/sweep_lion_lr/lion_lr_3e-4_dynamics_history.json
-
upload: checkpoints/part2/sweep_lion_lr/lion_lr_3e-4_model_best.pt
-
upload: checkpoints/part2/sweep_cautious_lr/cautious_lr_1e-3_dynamics_history.json
-
upload: checkpoints/part2/sweep_cautious_lr/cautious_lr_1e-3_model_best.pt
-
upload: checkpoints/part2/sweep_adamw_lr/adamw_lr_1e-3_dynamics_history.json
-
upload: checkpoints/part2/sweep_adamw_lr/adamw_lr_1e-3_model_best.pt
-
upload: checkpoints/part1/variant5/training_history.json
-
upload: checkpoints/part1/variant5/model_variant5_best.pt
-
upload: checkpoints/part1/variant4/training_history.json
-
upload: checkpoints/part1/variant4/model_variant4_best.pt
-
upload: checkpoints/part1/variant3/training_history.json
-
upload: checkpoints/part1/variant3/model_variant3_best.pt
-
upload: checkpoints/part1/variant2/training_history.json
-
upload: checkpoints/part1/variant2/model_variant2_best.pt
-
upload: checkpoints/part1/variant1/training_history.json
-
upload: checkpoints/part1/variant1/model_variant1_best.pt