homebrewnlp

2022-09-20 18:56:29

[ 133/262144] Loss: 2.027 - Accuracy: 0.445 | LearningRate: 0.01298 | StepTime: 69.225306s - Rate: 30,106.5 Tokens/s

2022-09-20 18:57:39

[ 137/262144] Loss: 1.995 - Accuracy: 0.457 | LearningRate: 0.01337 | StepTime: 69.232675s - Rate: 30,111.7 Tokens/s

2022-09-20 18:58:47

[ 141/262144] Loss: 1.994 - Accuracy: 0.455 | LearningRate: 0.01376 | StepTime: 69.216654s - Rate: 30,116.8 Tokens/s

2022-09-20 18:59:57

[ 145/262144] Loss: 1.955 - Accuracy: 0.463 | LearningRate: 0.01415 | StepTime: 69.245504s - Rate: 30,121.3 Tokens/s

2022-09-20 19:01:05

[ 149/262144] Loss: 1.927 - Accuracy: 0.469 | LearningRate: 0.01454 | StepTime: 69.236968s - Rate: 30,125.6 Tokens/s

2022-09-20 19:02:16

[ 153/262144] Loss: 1.905 - Accuracy: 0.477 | LearningRate: 0.01493 | StepTime: 69.227934s - Rate: 30,129.6 Tokens/s

2022-09-20 19:03:26

[ 157/262144] Loss: 1.893 - Accuracy: 0.480 | LearningRate: 0.01532 | StepTime: 69.234735s - Rate: 30,133.4 Tokens/s

2022-09-20 19:04:34

[ 161/262144] Loss: 1.913 - Accuracy: 0.474 | LearningRate: 0.01572 | StepTime: 69.231730s - Rate: 30,137.1 Tokens/s

2022-09-20 19:05:44

[ 165/262144] Loss: 1.891 - Accuracy: 0.478 | LearningRate: 0.01611 | StepTime: 69.243391s - Rate: 30,140.6 Tokens/s

2022-09-20 19:06:52

[ 169/262144] Loss: 1.969 - Accuracy: 0.458 | LearningRate: 0.01650 | StepTime: 69.256716s - Rate: 30,143.8 Tokens/s

2022-09-20 19:06:52

[ 169/262144] Loss: 1.969 - Accuracy: 0.458 | LearningRate: 0.01650 | StepTime: 69.244239s - Rate: 30,069.6 Tokens/s

2022-09-20 19:08:02

[ 173/262144] Loss: 1.904 - Accuracy: 0.474 | LearningRate: 0.01689 | StepTime: 69.251665s - Rate: 30,074.3 Tokens/s

Clashluke's group workspace