mlfoundations-dev/hp_ablations_qwen_adambeta2_0.999_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_adambeta2_0.995_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_adambeta2_0.9995_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 38
mlfoundations-dev/hp_ablations_qwen_adambeta2_0.99_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_scheduler_constant_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.05_minlr1e-6_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 3
mlfoundations-dev/hp_ablations_qwen_scheduler_inverse_sqrt_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.05_minlr5e-7_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 3
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.05_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 40
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.15_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.05_minlr1e-7_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.10_minlr1e-6_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.10_minlr1e-7_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.10_minlr5e-7_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_scheduler_cosine_warmup0.10_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39
mlfoundations-dev/hp_ablations_qwen_scheduler_linear_warmup0.10_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 3
mlfoundations-dev/hp_ablations_qwen_scheduler_linear_warmup0.05_dcftv1.2 Text Generation • Updated Dec 5, 2024 • 39