Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fine-tuning on GSM8K (test)
Loading...
2.4887
Test Perplexity
GaLore-AF
2.440916
2.763458
3.086
3.408542
May 6, 2026
Test Perplexity
Updated 27d ago
Evaluation Results
Method
Method
Links
Test Perplexity
GaLore-AF
Model=Llama_3.2_3B, St...
2026.05
2.4887
GaLore-AF
Model=Llama_3.2_1B, St...
2026.05
2.7346
Adam-mini
Model=Llama_3.2_1B, St...
2026.05
3.0536
BAOC0.5
Model=Llama_3.2_1B, St...
2026.05
3.403
GaLore-AW32
Model=Llama_3.2_1B, St...
2026.05
3.4293
AdamW16
Model=Llama_3.2_1B, St...
2026.05
3.4436
AdamW8
Model=Llama_3.2_1B, St...
2026.05
3.4735
GaLore-AW32
Model=Llama_3.2_3B, St...
2026.05
3.5431
AdamW16
Model=Llama_3.2_3B, St...
2026.05
3.5495
BAOC0.5
Model=Llama_3.2_3B, St...
2026.05
3.5713
AdamW8
Model=Llama_3.2_3B, St...
2026.05
3.6559
Adam-mini
Model=Llama_3.2_3B, St...
2026.05
3.6833
Feedback
Search any
task
Search any
task