homebrewnlp

Clashluke's group workspace

Group: adam-square-no-decay-mixer

981

893

1-2

of 2

Timestamps visible

2022-12-11 21:33:35

[ 7269/262144] Loss: 0.876 - Accuracy: 0.733 | LearningRate: 0.00951 | StepTime: 50.857918s - Rate: 247,061.1 Tokens/s

2022-12-11 21:34:25

[ 7273/262144] Loss: 0.873 - Accuracy: 0.735 | LearningRate: 0.00951 | StepTime: 50.812110s - Rate: 246,790.4 Tokens/s

2022-12-11 21:35:17

[ 7277/262144] Loss: 0.879 - Accuracy: 0.732 | LearningRate: 0.00951 | StepTime: 50.820459s - Rate: 246,518.5 Tokens/s

2022-12-11 21:28:30

[ 7245/262144] Loss: 0.885 - Accuracy: 0.731 | LearningRate: 0.00951 | StepTime: 50.843128s - Rate: 248,655.5 Tokens/s

2022-12-11 21:29:20

[ 7249/262144] Loss: 0.873 - Accuracy: 0.734 | LearningRate: 0.00951 | StepTime: 50.841567s - Rate: 248,379.3 Tokens/s

2022-12-11 21:30:12

[ 7253/262144] Loss: 0.892 - Accuracy: 0.729 | LearningRate: 0.00951 | StepTime: 50.845515s - Rate: 248,104.0 Tokens/s

2022-12-11 21:31:02

[ 7257/262144] Loss: 0.881 - Accuracy: 0.732 | LearningRate: 0.00951 | StepTime: 50.818590s - Rate: 247,829.9 Tokens/s

2022-12-11 21:31:52

[ 7261/262144] Loss: 0.885 - Accuracy: 0.731 | LearningRate: 0.00951 | StepTime: 50.843609s - Rate: 247,556.4 Tokens/s

2022-12-11 21:32:44

[ 7265/262144] Loss: 0.878 - Accuracy: 0.732 | LearningRate: 0.00951 | StepTime: 50.836486s - Rate: 247,283.9 Tokens/s

2022-12-11 21:33:34

[ 7269/262144] Loss: 0.876 - Accuracy: 0.733 | LearningRate: 0.00951 | StepTime: 50.820204s - Rate: 247,012.5 Tokens/s

2022-12-11 21:34:26

[ 7273/262144] Loss: 0.873 - Accuracy: 0.735 | LearningRate: 0.00951 | StepTime: 50.847511s - Rate: 246,741.7 Tokens/s

2022-12-11 21:35:16

[ 7277/262144] Loss: 0.879 - Accuracy: 0.732 | LearningRate: 0.00951 | StepTime: 50.818593s - Rate: 246,472.0 Tokens/s