th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.001-weightdecay0.0001-seed42
1B
•
Updated
•
5
pt-ffw
models pretrained on ffw, varying amount of math in pretraining dataset
-
-
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.001-weightdecay0.001-seed42
1B • Updated • 4 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.001-weightdecay0.01-seed42
1B • Updated • 8 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.001-weightdecay0.1-seed42
1B • Updated • 8 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.001-weightdecay1.0-seed42
1B • Updated • 3 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.005-weightdecay0.0001-seed42
1B • Updated • 6 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.005-weightdecay0.001-seed42
1B • Updated • 7 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.005-weightdecay0.01-seed42
1B • Updated • 5 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.005-weightdecay0.1-seed42
1B • Updated • 7 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.005-weightdecay1.0-seed42
1B • Updated • 6 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.01-weightdecay0.0001-seed42
1B • Updated • 9 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.01-weightdecay0.001-seed42
1B • Updated • 5 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.01-weightdecay0.01-seed42
1B • Updated • 7 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.01-weightdecay0.1-seed42
1B • Updated • 6 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.01-weightdecay1.0-seed42
1B • Updated • 6 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.05-weightdecay0.0001-seed42
1B • Updated • 5 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.05-weightdecay0.001-seed42
1B • Updated • 4 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.05-weightdecay0.01-seed42
1B • Updated • 8 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.05-weightdecay0.1-seed42
1B • Updated • 9 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.05-weightdecay1.0-seed42
1B • Updated • 9 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.1-weightdecay0.0001-seed42
1B • Updated • 9 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.1-weightdecay0.001-seed42
1B • Updated • 9 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.1-weightdecay0.01-seed42
1B • Updated • 8 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.1-weightdecay0.1-seed42
1B • Updated • 6 -
th135/llama-1B-20BT-ffwmysubset20BT-mathematics0.1-weightdecay1.0-seed42
1B • Updated • 7