th135/llama-0.5B-10BT-weightdecay0.0001-seed42-hellaswag
0.5B • Updated • 6
ft-lang
models pretrained on fw + finetuned on language and general knowledge datasets
-
-
th135/llama-0.5B-10BT-weightdecay0.0001-seed42-winogrande
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.0001-seed42-piqa
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay0.0001-seed42-arc_easy
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay0.0001-seed42-arc_challenge
0.5B • Updated • 4 -
th135/llama-0.5B-10BT-weightdecay0.001-seed42-hellaswag
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.001-seed42-winogrande
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.001-seed42-piqa
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.001-seed42-arc_easy
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay0.001-seed42-arc_challenge
0.5B • Updated • 4 -
th135/llama-0.5B-10BT-weightdecay0.01-seed42-hellaswag
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.01-seed42-winogrande
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay0.01-seed42-piqa
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay0.01-seed42-arc_easy
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay0.01-seed42-arc_challenge
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.1-seed42-hellaswag
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.1-seed42-winogrande
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.1-seed42-piqa
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.1-seed42-arc_easy
0.5B • Updated • 4 -
th135/llama-0.5B-10BT-weightdecay0.1-seed42-arc_challenge
0.5B • Updated • 4 -
th135/llama-0.5B-10BT-weightdecay0.5-seed42-hellaswag
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.5-seed42-winogrande
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.5-seed42-piqa
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay0.5-seed42-arc_easy
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay0.5-seed42-arc_challenge
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay1.0-seed42-hellaswag
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay1.0-seed42-winogrande
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay1.0-seed42-piqa
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay1.0-seed42-arc_easy
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay1.0-seed42-arc_challenge
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay1.5-seed42-hellaswag
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay1.5-seed42-winogrande
0.5B • Updated • 8 -
th135/llama-0.5B-10BT-weightdecay1.5-seed42-piqa
0.5B • Updated • 4 -
th135/llama-0.5B-10BT-weightdecay1.5-seed42-arc_easy
0.5B • Updated • 8 -
th135/llama-0.5B-10BT-weightdecay1.5-seed42-arc_challenge
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay3.0-seed42-hellaswag
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay3.0-seed42-winogrande
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay3.0-seed42-piqa
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay3.0-seed42-arc_easy
0.5B • Updated • 4 -
th135/llama-0.5B-10BT-weightdecay3.0-seed42-arc_challenge
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay10.0-seed42-hellaswag
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay10.0-seed42-winogrande
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay10.0-seed42-piqa
0.5B • Updated • 6 -
th135/llama-0.5B-10BT-weightdecay10.0-seed42-arc_easy
0.5B • Updated • 8 -
th135/llama-0.5B-10BT-weightdecay10.0-seed42-arc_challenge
0.5B • Updated • 5 -
th135/llama-1B-20BT-weightdecay0.0001-seed42-hellaswag
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.0001-seed42-winogrande
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.0001-seed42-piqa
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.0001-seed42-arc_easy
1B • Updated • 5 -
th135/llama-1B-20BT-weightdecay0.0001-seed42-arc_challenge
1B • Updated • 5 -
th135/llama-1B-20BT-weightdecay0.001-seed42-hellaswag
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.001-seed42-winogrande
1B • Updated • 6 -
th135/llama-1B-20BT-weightdecay0.001-seed42-piqa
1B • Updated • 5 -
th135/llama-1B-20BT-weightdecay0.001-seed42-arc_easy
1B • Updated • 5 -
th135/llama-1B-20BT-weightdecay0.001-seed42-arc_challenge
1B • Updated • 5 -
th135/llama-1B-20BT-weightdecay0.01-seed42-hellaswag
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.01-seed42-winogrande
1B • Updated • 6 -
th135/llama-1B-20BT-weightdecay0.01-seed42-piqa
1B • Updated • 6 -
th135/llama-1B-20BT-weightdecay0.01-seed42-arc_easy
1B • Updated • 6 -
th135/llama-1B-20BT-weightdecay0.01-seed42-arc_challenge
1B • Updated • 6 -
th135/llama-1B-20BT-weightdecay0.1-seed42-hellaswag
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.1-seed42-winogrande
1B • Updated • 6 -
th135/llama-1B-20BT-weightdecay0.1-seed42-piqa
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.1-seed42-arc_easy
1B • Updated • 6 -
th135/llama-1B-20BT-weightdecay0.1-seed42-arc_challenge
1B • Updated • 6 -
th135/llama-1B-20BT-weightdecay0.5-seed42-hellaswag
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.5-seed42-winogrande
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.5-seed42-piqa
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.5-seed42-arc_easy
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.5-seed42-arc_challenge
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay1.0-seed42-hellaswag
1B • Updated • 3 -
th135/llama-1B-20BT-weightdecay1.0-seed42-winogrande
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay1.0-seed42-piqa
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay1.0-seed42-arc_easy
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay1.0-seed42-arc_challenge
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay1.5-seed42-hellaswag
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay1.5-seed42-winogrande
1B • Updated • 3 -
th135/llama-1B-20BT-weightdecay1.5-seed42-piqa
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay1.5-seed42-arc_easy
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay1.5-seed42-arc_challenge
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay3.0-seed42-hellaswag
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay3.0-seed42-winogrande
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay3.0-seed42-piqa
1B • Updated • 6 -
th135/llama-1B-20BT-weightdecay3.0-seed42-arc_easy
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay3.0-seed42-arc_challenge
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay10.0-seed42-hellaswag
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay10.0-seed42-winogrande
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay10.0-seed42-piqa
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay10.0-seed42-arc_easy
1B • Updated • 5 -
th135/llama-1B-20BT-weightdecay10.0-seed42-arc_challenge
1B • Updated • 4 -
th135/llama-4B-80BT-weightdecay0.1-seed42-hellaswag
4B • Updated • 4 -
th135/llama-4B-80BT-weightdecay0.1-seed42-winogrande
4B • Updated • 4 -
th135/llama-4B-80BT-weightdecay0.1-seed42-piqa
4B • Updated • 4 -
th135/llama-4B-80BT-weightdecay0.1-seed42-arc_easy
4B • Updated • 4 -
th135/llama-4B-80BT-weightdecay0.1-seed42-arc_challenge
4B • Updated • 6 -
th135/llama-4B-80BT-weightdecay1.0-seed42-hellaswag
4B • Updated • 4 -
th135/llama-4B-80BT-weightdecay1.0-seed42-winogrande
4B • Updated • 4 -
th135/llama-4B-80BT-weightdecay1.0-seed42-piqa
4B • Updated • 5 -
th135/llama-4B-80BT-weightdecay1.0-seed42-arc_easy
4B • Updated • 5 -
th135/llama-4B-80BT-weightdecay1.0-seed42-arc_challenge
4B • Updated • 4 -
th135/olmo-1B-30BT-weightdecay0.1-hellaswag
1B • Updated • 4 -
th135/olmo-1B-30BT-weightdecay0.1-winogrande
1B • Updated • 4 -
th135/olmo-1B-30BT-weightdecay0.1-piqa
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay0.1-arc_easy
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay0.1-arc_challenge
1B • Updated • 4 -
th135/olmo-1B-30BT-weightdecay0.3-hellaswag
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay0.3-winogrande
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay0.3-piqa
1B • Updated • 6 -
th135/olmo-1B-30BT-weightdecay0.3-arc_easy
1B • Updated • 4 -
th135/olmo-1B-30BT-weightdecay0.3-arc_challenge
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay0.6-hellaswag
1B • Updated • 6 -
th135/olmo-1B-30BT-weightdecay0.6-winogrande
1B • Updated • 6 -
th135/olmo-1B-30BT-weightdecay0.6-piqa
1B • Updated • 6 -
th135/olmo-1B-30BT-weightdecay0.6-arc_easy
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay0.6-arc_challenge
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay1.0-hellaswag
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay1.0-winogrande
1B • Updated • 6 -
th135/olmo-1B-30BT-weightdecay1.0-piqa
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay1.0-arc_easy
1B • Updated • 6 -
th135/olmo-1B-30BT-weightdecay1.0-arc_challenge
1B • Updated • 5 -
th135/olmo-1B-210BT-weightdecay0.1-hellaswag
1B • Updated • 5 -
th135/olmo-1B-210BT-weightdecay0.1-winogrande
1B • Updated • 5 -
th135/olmo-1B-210BT-weightdecay0.1-piqa
1B • Updated • 4 -
th135/olmo-1B-210BT-weightdecay0.1-arc_easy
1B • Updated • 7 -
th135/olmo-1B-210BT-weightdecay0.1-arc_challenge
1B • Updated • 5 -
th135/olmo-1B-210BT-weightdecay0.3-hellaswag
1B • Updated • 3 -
th135/olmo-1B-210BT-weightdecay0.3-winogrande
1B • Updated • 4 -
th135/olmo-1B-210BT-weightdecay0.3-piqa
1B • Updated • 4 -
th135/olmo-1B-210BT-weightdecay0.3-arc_easy
1B • Updated • 4 -
th135/olmo-1B-210BT-weightdecay0.3-arc_challenge
1B • Updated • 5 -
th135/olmo-1B-210BT-weightdecay1.0-hellaswag
1B • Updated • 4 -
th135/olmo-1B-210BT-weightdecay1.0-winogrande
1B • Updated • 4 -
th135/olmo-1B-210BT-weightdecay1.0-piqa
1B • Updated • 4 -
th135/olmo-1B-210BT-weightdecay1.0-arc_easy
1B • Updated • 4 -
th135/olmo-1B-210BT-weightdecay1.0-arc_challenge
1B • Updated • 4 -
th135/llama-0.5B-10BT-weightdecay0.0-seed42-hellaswag
0.5B • Updated • 4 -
th135/llama-0.5B-10BT-weightdecay0.0-seed42-winogrande
0.5B • Updated • 5 -
th135/llama-0.5B-10BT-weightdecay0.0-seed42-piqa
0.5B • Updated • 3 -
th135/llama-0.5B-10BT-weightdecay0.0-seed42-arc_easy
0.5B • Updated • 4 -
th135/llama-0.5B-10BT-weightdecay0.0-seed42-arc_challenge
0.5B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.0-seed42-hellaswag
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.0-seed42-winogrande
1B • Updated • 3 -
th135/llama-1B-20BT-weightdecay0.0-seed42-piqa
1B • Updated • 4 -
th135/llama-1B-20BT-weightdecay0.0-seed42-arc_easy
1B • Updated • 5 -
th135/llama-1B-20BT-weightdecay0.0-seed42-arc_challenge
1B • Updated • 4 -
th135/llama-4B-80BT-weightdecay0.0-seed42-hellaswag
4B • Updated • 4 -
th135/llama-4B-80BT-weightdecay0.0-seed42-winogrande
4B • Updated • 4 -
th135/llama-4B-80BT-weightdecay0.0-seed42-piqa
4B • Updated • 5 -
th135/llama-4B-80BT-weightdecay0.0-seed42-arc_easy
4B • Updated • 5 -
th135/llama-4B-80BT-weightdecay0.0-seed42-arc_challenge
4B • Updated • 4 -
th135/olmo-1B-30BT-weightdecay0.0-hellaswag
1B • Updated • 6 -
th135/olmo-1B-30BT-weightdecay0.0-winogrande
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay0.0-piqa
1B • Updated • 6 -
th135/olmo-1B-30BT-weightdecay0.0-arc_easy
1B • Updated • 5 -
th135/olmo-1B-30BT-weightdecay0.0-arc_challenge
1B • Updated • 7 -
th135/olmo-1B-210BT-weightdecay0.0-hellaswag
1B • Updated • 5 -
th135/olmo-1B-210BT-weightdecay0.0-winogrande
1B • Updated • 5 -
th135/olmo-1B-210BT-weightdecay0.0-piqa
1B • Updated • 4 -
th135/olmo-1B-210BT-weightdecay0.0-arc_easy
1B • Updated • 5 -
th135/olmo-1B-210BT-weightdecay0.0-arc_challenge
1B • Updated • 3