{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":818119281,"defaultBranch":"main","name":"bert","ownerLogin":"cwallenwein","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2024-06-21T06:26:40.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/40916592?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1721159353.0","currentOid":""},"activityList":{"items":[{"before":"24497e6f36bf68acf381c4b520546c9276393ba1","after":"096b4f15c3c15593b24a541a40b38180a03c1ee5","ref":"refs/heads/main","pushedAt":"2024-08-20T10:17:16.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"allow changing the dropout probability for finetuning","shortMessageHtmlLink":"allow changing the dropout probability for finetuning"}},{"before":"2b12e7be7d1f43de29e67eb66b6aaa30ec91c56f","after":"24497e6f36bf68acf381c4b520546c9276393ba1","ref":"refs/heads/main","pushedAt":"2024-08-20T09:50:45.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"switch LayerNorm and Dropout in embedding","shortMessageHtmlLink":"switch LayerNorm and Dropout in embedding"}},{"before":"c90535b97919bf1c13628861ae61993149475ae1","after":"2b12e7be7d1f43de29e67eb66b6aaa30ec91c56f","ref":"refs/heads/main","pushedAt":"2024-08-20T08:57:10.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"switch to CosineAnnealingLR","shortMessageHtmlLink":"switch to CosineAnnealingLR"}},{"before":"fb4232d36a03fa2039df7ce83161679ce6ab7503","after":"c90535b97919bf1c13628861ae61993149475ae1","ref":"refs/heads/main","pushedAt":"2024-08-20T08:16:18.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"set default learning rate","shortMessageHtmlLink":"set default learning rate"}},{"before":"af9e0ac321dcd91d63bedef50852890a41f0c8fe","after":"fb4232d36a03fa2039df7ce83161679ce6ab7503","ref":"refs/heads/main","pushedAt":"2024-08-20T08:06:54.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"allow using lr schedulers with and without dynamic decaying (-> decay that is not predefined before training but is dynamically started during training)","shortMessageHtmlLink":"allow using lr schedulers with and without dynamic decaying (-> decay…"}},{"before":"39bdb9d37ac2c3129e7ae98e15d3004841ee85c3","after":"af9e0ac321dcd91d63bedef50852890a41f0c8fe","ref":"refs/heads/main","pushedAt":"2024-08-20T07:42:44.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"switch finetuning to 1cycle","shortMessageHtmlLink":"switch finetuning to 1cycle"}},{"before":"61ff3ee64824371fa2d42730d6dbec8e758d6ce2","after":"39bdb9d37ac2c3129e7ae98e15d3004841ee85c3","ref":"refs/heads/main","pushedAt":"2024-08-20T07:40:25.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"move logging metrics outside of the model again","shortMessageHtmlLink":"move logging metrics outside of the model again"}},{"before":"307afef9e8ff922551dfcdc297eb6fc3ee2501b8","after":"61ff3ee64824371fa2d42730d6dbec8e758d6ce2","ref":"refs/heads/main","pushedAt":"2024-08-16T09:20:01.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"update imports for data preprocessing","shortMessageHtmlLink":"update imports for data preprocessing"}},{"before":"4c76f8ea6d894fe901ad0b62ad457db45d1296f6","after":"307afef9e8ff922551dfcdc297eb6fc3ee2501b8","ref":"refs/heads/main","pushedAt":"2024-08-16T09:19:11.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"include lightning in requirements","shortMessageHtmlLink":"include lightning in requirements"}},{"before":"9eefae5fbacc71d4493bf116d6b65a046c8f7758","after":"4c76f8ea6d894fe901ad0b62ad457db45d1296f6","ref":"refs/heads/main","pushedAt":"2024-08-16T08:49:15.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"add tokenize util","shortMessageHtmlLink":"add tokenize util"}},{"before":"cf3de5447a3d4b1367887dd5a81d4afaf5d127cb","after":"9eefae5fbacc71d4493bf116d6b65a046c8f7758","ref":"refs/heads/main","pushedAt":"2024-08-15T07:31:26.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"log step duration per sample","shortMessageHtmlLink":"log step duration per sample"}},{"before":"6c1274bcff40a5fe55379b477348b836d660aed7","after":"cf3de5447a3d4b1367887dd5a81d4afaf5d127cb","ref":"refs/heads/main","pushedAt":"2024-08-15T07:24:58.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"log step duration","shortMessageHtmlLink":"log step duration"}},{"before":"8fc4a4d42a8936a94f0f07e497cc6f10c8f35159","after":"6c1274bcff40a5fe55379b477348b836d660aed7","ref":"refs/heads/main","pushedAt":"2024-08-15T06:26:18.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"allow setting torch dtype during finetuning","shortMessageHtmlLink":"allow setting torch dtype during finetuning"}},{"before":"4f506090f8533b07db18de46e110780b7a545b74","after":"8fc4a4d42a8936a94f0f07e497cc6f10c8f35159","ref":"refs/heads/main","pushedAt":"2024-08-15T06:22:48.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"allow setting torch dtype during training","shortMessageHtmlLink":"allow setting torch dtype during training"}},{"before":"46e820662a981d6d22618c7323c90b8942f20fca","after":"4f506090f8533b07db18de46e110780b7a545b74","ref":"refs/heads/main","pushedAt":"2024-08-14T19:47:49.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"turn BertModelForSequenceClassification into Lightning Module","shortMessageHtmlLink":"turn BertModelForSequenceClassification into Lightning Module"}},{"before":"ef47632a9216f91eb5a5e56c53a98fef9265ffd7","after":"46e820662a981d6d22618c7323c90b8942f20fca","ref":"refs/heads/main","pushedAt":"2024-08-14T19:28:01.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"fix stopping after time is over","shortMessageHtmlLink":"fix stopping after time is over"}},{"before":"1e29a651125d95ed908fb9d016df750f62b7d9ea","after":"ef47632a9216f91eb5a5e56c53a98fef9265ffd7","ref":"refs/heads/main","pushedAt":"2024-08-14T18:53:20.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"fix wandb when using torch.compile","shortMessageHtmlLink":"fix wandb when using torch.compile"}},{"before":"b35bee367df0ba8d1923fc4d24f76981a4966ab8","after":"1e29a651125d95ed908fb9d016df750f62b7d9ea","ref":"refs/heads/main","pushedAt":"2024-08-14T15:56:07.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"implement sparse token prediction","shortMessageHtmlLink":"implement sparse token prediction"}},{"before":"76cce597325cd5bbf8851470456e546cf2cd93be","after":"b35bee367df0ba8d1923fc4d24f76981a4966ab8","ref":"refs/heads/main","pushedAt":"2024-08-14T15:44:01.000Z","pushType":"push","commitsCount":4,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"move accuracy calculation to model","shortMessageHtmlLink":"move accuracy calculation to model"}},{"before":"a3ae5287e66631d84feabc4d63bea34f5dbb2d3b","after":"76cce597325cd5bbf8851470456e546cf2cd93be","ref":"refs/heads/main","pushedAt":"2024-08-14T12:17:20.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"test 1Cycle learning rate scheduler","shortMessageHtmlLink":"test 1Cycle learning rate scheduler"}},{"before":"5c5dd6e8f2ceee9a4c412c07e91b27fc559e3028","after":"a3ae5287e66631d84feabc4d63bea34f5dbb2d3b","ref":"refs/heads/main","pushedAt":"2024-08-14T12:16:52.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"use PyTorch lightning modules","shortMessageHtmlLink":"use PyTorch lightning modules"}},{"before":"b588dac5aff11aeb447ddda41be864cfa762018e","after":"5c5dd6e8f2ceee9a4c412c07e91b27fc559e3028","ref":"refs/heads/main","pushedAt":"2024-08-14T07:53:18.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"fix multi-epoch finetuning","shortMessageHtmlLink":"fix multi-epoch finetuning"}},{"before":"60b8b18314d50d10796445d23c3a70f05dc89bf0","after":"b588dac5aff11aeb447ddda41be864cfa762018e","ref":"refs/heads/main","pushedAt":"2024-08-12T15:36:36.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"add trainer for finetuning","shortMessageHtmlLink":"add trainer for finetuning"}},{"before":"32ad881e5e57a1e2fbb68040f6efedaee929af5b","after":"60b8b18314d50d10796445d23c3a70f05dc89bf0","ref":"refs/heads/main","pushedAt":"2024-08-12T14:38:01.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"update .gitignore","shortMessageHtmlLink":"update .gitignore"}},{"before":"e8cae173144731bee58a09b9901b44ab5a9e5e12","after":"32ad881e5e57a1e2fbb68040f6efedaee929af5b","ref":"refs/heads/main","pushedAt":"2024-08-12T13:33:45.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"refactor bert code + add flash attention support","shortMessageHtmlLink":"refactor bert code + add flash attention support"}},{"before":"8e403e635bc570c8e5e5ea8829492ce8b7390759","after":"e8cae173144731bee58a09b9901b44ab5a9e5e12","ref":"refs/heads/main","pushedAt":"2024-08-12T09:38:10.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"allow disabling nsp head","shortMessageHtmlLink":"allow disabling nsp head"}},{"before":"7d8b4167075791a78d0d72b22f62e87c47ebb886","after":"8e403e635bc570c8e5e5ea8829492ce8b7390759","ref":"refs/heads/main","pushedAt":"2024-08-10T21:11:31.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"save data in optimal dtype","shortMessageHtmlLink":"save data in optimal dtype"}},{"before":"ccbd4afe05a6885cbda2f0c30098a347a9aff725","after":"7d8b4167075791a78d0d72b22f62e87c47ebb886","ref":"refs/heads/main","pushedAt":"2024-08-07T19:13:20.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"turn scaled dot product attention into a function","shortMessageHtmlLink":"turn scaled dot product attention into a function"}},{"before":"c3efe9b80e3fdcd22157268982c0d1f2edc00c7f","after":"ccbd4afe05a6885cbda2f0c30098a347a9aff725","ref":"refs/heads/main","pushedAt":"2024-08-06T19:44:12.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"typecast to more accurate dtypes","shortMessageHtmlLink":"typecast to more accurate dtypes"}},{"before":"da3ae5216957af20386f5484d0fec8671675c28e","after":"c3efe9b80e3fdcd22157268982c0d1f2edc00c7f","ref":"refs/heads/main","pushedAt":"2024-08-05T20:47:17.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cwallenwein","name":"Christian Wallenwein","path":"/cwallenwein","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40916592?s=80&v=4"},"commit":{"message":"merge optimized multihead-attention and unoptimized multihead-attention","shortMessageHtmlLink":"merge optimized multihead-attention and unoptimized multihead-attention"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEnvMotwA","startCursor":null,"endCursor":null}},"title":"Activity · cwallenwein/bert"}