{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":819496912,"defaultBranch":"main","name":"gpt-2","ownerLogin":"vhmth","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2024-06-24T16:09:34.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/603426?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1719246734.0","currentOid":""},"activityList":{"items":[{"before":"2ffbab779f8edeb943bd1b3590b51527fba5f606","after":"d2f77a7ecd44562caa649f19bd62b4247356f927","ref":"refs/heads/main","pushedAt":"2024-07-06T13:20:56.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"checkpoint 31k","shortMessageHtmlLink":"checkpoint 31k"}},{"before":"19f34bf5135fa7cb9b92b5b3712822022ce8fb7d","after":"2ffbab779f8edeb943bd1b3590b51527fba5f606","ref":"refs/heads/main","pushedAt":"2024-07-04T14:55:12.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"credit where it's due","shortMessageHtmlLink":"credit where it's due"}},{"before":"4ef91896cade390cde2185702af8b43dc1b2c404","after":"19f34bf5135fa7cb9b92b5b3712822022ce8fb7d","ref":"refs/heads/main","pushedAt":"2024-07-04T14:52:06.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"allow prompt and max tokens to be passed into sample script","shortMessageHtmlLink":"allow prompt and max tokens to be passed into sample script"}},{"before":"46edf071e4dd31bd904b2c6b14116684c468c550","after":"4ef91896cade390cde2185702af8b43dc1b2c404","ref":"refs/heads/main","pushedAt":"2024-07-04T13:13:01.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"remove undefined ref in checkpoint util","shortMessageHtmlLink":"remove undefined ref in checkpoint util"}},{"before":"2799ffe8dddefe8f038216e13ab375cbfc09352b","after":"46edf071e4dd31bd904b2c6b14116684c468c550","ref":"refs/heads/main","pushedAt":"2024-07-04T13:10:08.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"training log 15k with new model","shortMessageHtmlLink":"training log 15k with new model"}},{"before":"d87d62fee77dade2eadeb88f5cf87449f40efb0e","after":"2799ffe8dddefe8f038216e13ab375cbfc09352b","ref":"refs/heads/main","pushedAt":"2024-07-04T13:05:51.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"swap in new checkpoint with optimizations from course","shortMessageHtmlLink":"swap in new checkpoint with optimizations from course"}},{"before":"ead26806147a9b6fe0fc51b61022c37dde1e7d62","after":"d87d62fee77dade2eadeb88f5cf87449f40efb0e","ref":"refs/heads/main","pushedAt":"2024-07-04T00:48:14.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"get sampling to work again","shortMessageHtmlLink":"get sampling to work again"}},{"before":"b59c18a13d2e2f519426511679fe63778ce40483","after":"ead26806147a9b6fe0fc51b61022c37dde1e7d62","ref":"refs/heads/main","pushedAt":"2024-07-04T00:25:01.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"torch.autocast for estimating loss","shortMessageHtmlLink":"torch.autocast for estimating loss"}},{"before":"6a410cf86fd5e11211c97300678ce3b01c6cdbc2","after":"b59c18a13d2e2f519426511679fe63778ce40483","ref":"refs/heads/main","pushedAt":"2024-07-04T00:09:36.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"re-enable checkpoints","shortMessageHtmlLink":"re-enable checkpoints"}},{"before":"769313e0edc461d7bcc90beaa4ad3dd1d3c5f306","after":"6a410cf86fd5e11211c97300678ce3b01c6cdbc2","ref":"refs/heads/main","pushedAt":"2024-07-04T00:00:31.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"ddp pt 2","shortMessageHtmlLink":"ddp pt 2"}},{"before":"eddc84978bb93bde34e1c682f32ef1c0d6657943","after":"769313e0edc461d7bcc90beaa4ad3dd1d3c5f306","ref":"refs/heads/main","pushedAt":"2024-07-03T23:13:09.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"WIP: ddp","shortMessageHtmlLink":"WIP: ddp"}},{"before":"7aa02f366d0ce8f04779170594155c546189716f","after":"eddc84978bb93bde34e1c682f32ef1c0d6657943","ref":"refs/heads/main","pushedAt":"2024-07-03T22:47:01.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"gradient accumulation","shortMessageHtmlLink":"gradient accumulation"}},{"before":"b56bab0ae43a1e2bcc1b1ad26468d67c6fb5c533","after":"7aa02f366d0ce8f04779170594155c546189716f","ref":"refs/heads/main","pushedAt":"2024-07-03T22:21:09.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"adamw with weight decay","shortMessageHtmlLink":"adamw with weight decay"}},{"before":"b4aeaeb8b46d4c0f4571122a766ddf9b2145cc84","after":"b56bab0ae43a1e2bcc1b1ad26468d67c6fb5c533","ref":"refs/heads/main","pushedAt":"2024-07-03T22:19:45.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"adamw with weight decay","shortMessageHtmlLink":"adamw with weight decay"}},{"before":"7ddf7d412abac6e1b3513e4a6e4450125983a862","after":"b4aeaeb8b46d4c0f4571122a766ddf9b2145cc84","ref":"refs/heads/main","pushedAt":"2024-07-03T22:16:32.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"adamw with weight decay","shortMessageHtmlLink":"adamw with weight decay"}},{"before":"ce5549159a48803415eb4a653b7d164683a0ea25","after":"7ddf7d412abac6e1b3513e4a6e4450125983a862","ref":"refs/heads/main","pushedAt":"2024-07-03T22:04:19.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"bump batch size to 20","shortMessageHtmlLink":"bump batch size to 20"}},{"before":"cf044202213dfc214a2f720a09382300314ce5e8","after":"ce5549159a48803415eb4a653b7d164683a0ea25","ref":"refs/heads/main","pushedAt":"2024-07-03T21:26:36.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"gradient clipping and prettier printing","shortMessageHtmlLink":"gradient clipping and prettier printing"}},{"before":"2227a535a4c075adc51c08b9d9095d6158d93646","after":"cf044202213dfc214a2f720a09382300314ce5e8","ref":"refs/heads/main","pushedAt":"2024-07-03T21:16:13.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"optimizer parameters from GPT-3 training details","shortMessageHtmlLink":"optimizer parameters from GPT-3 training details"}},{"before":"649d81ebaa22f60ec43a33c428ec383da9ad0f8e","after":"2227a535a4c075adc51c08b9d9095d6158d93646","ref":"refs/heads/main","pushedAt":"2024-07-03T21:12:59.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"change vocab_size to 50304 to get more GPU utilization","shortMessageHtmlLink":"change vocab_size to 50304 to get more GPU utilization"}},{"before":"6d781d87b7f2fe5a8369cec3be94d4753981566a","after":"649d81ebaa22f60ec43a33c428ec383da9ad0f8e","ref":"refs/heads/main","pushedAt":"2024-07-03T20:52:08.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"implement weight sharing with compilation via F.linear","shortMessageHtmlLink":"implement weight sharing with compilation via F.linear"}},{"before":"dc079f0dbefcbbdce2dd7151a1a47e3fc59ee715","after":"6d781d87b7f2fe5a8369cec3be94d4753981566a","ref":"refs/heads/main","pushedAt":"2024-07-03T20:43:00.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"should estimate loss by default","shortMessageHtmlLink":"should estimate loss by default"}},{"before":"330cfbe16a66844fa2854c328aa7961a8b6fd525","after":"dc079f0dbefcbbdce2dd7151a1a47e3fc59ee715","ref":"refs/heads/main","pushedAt":"2024-07-03T20:38:28.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"no bias in lm_head","shortMessageHtmlLink":"no bias in lm_head"}},{"before":"2cc9aa8916ee8716813dfff7ef441cf4ea0b3c4d","after":"330cfbe16a66844fa2854c328aa7961a8b6fd525","ref":"refs/heads/main","pushedAt":"2024-07-03T20:37:29.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"remove bias from lm_head","shortMessageHtmlLink":"remove bias from lm_head"}},{"before":"13c1bf5584b152e4b44cb76637406503a05f8ba9","after":"2cc9aa8916ee8716813dfff7ef441cf4ea0b3c4d","ref":"refs/heads/main","pushedAt":"2024-07-03T20:32:27.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"estimate_loss flag","shortMessageHtmlLink":"estimate_loss flag"}},{"before":"1e27777bb5a5d82739dca7dd1d7693fbde895d68","after":"13c1bf5584b152e4b44cb76637406503a05f8ba9","ref":"refs/heads/main","pushedAt":"2024-07-03T20:31:23.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"estimate_loss flag","shortMessageHtmlLink":"estimate_loss flag"}},{"before":"0639dd38f457231ad6657aa1f7aad18fbad01af1","after":"1e27777bb5a5d82739dca7dd1d7693fbde895d68","ref":"refs/heads/main","pushedAt":"2024-07-03T20:31:00.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"estimate_loss flag","shortMessageHtmlLink":"estimate_loss flag"}},{"before":"9bf301931e2c64cf30bc82b43403bddbe6e56c03","after":"0639dd38f457231ad6657aa1f7aad18fbad01af1","ref":"refs/heads/main","pushedAt":"2024-07-03T20:10:06.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"torch.autocast with new training print statement with token throughput","shortMessageHtmlLink":"torch.autocast with new training print statement with token throughput"}},{"before":"33ba308ba7353655976bb18da885e7f19cb4d051","after":"9bf301931e2c64cf30bc82b43403bddbe6e56c03","ref":"refs/heads/main","pushedAt":"2024-07-03T20:09:20.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"torch.autocast with new training print statement with token throughput","shortMessageHtmlLink":"torch.autocast with new training print statement with token throughput"}},{"before":"f170af065ec243d9f7602c2f9e82f54309dfc82d","after":"33ba308ba7353655976bb18da885e7f19cb4d051","ref":"refs/heads/main","pushedAt":"2024-07-03T20:08:14.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"get rid of tqdm on main training loop","shortMessageHtmlLink":"get rid of tqdm on main training loop"}},{"before":"ca417e5448d55a2d9c8b90e5d33b2656a4ec2a7f","after":"f170af065ec243d9f7602c2f9e82f54309dfc82d","ref":"refs/heads/main","pushedAt":"2024-07-03T20:07:49.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vhmth","name":"Vinay","path":"/vhmth","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/603426?s=80&v=4"},"commit":{"message":"allow tf32 precision","shortMessageHtmlLink":"allow tf32 precision"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEeG4TtgA","startCursor":null,"endCursor":null}},"title":"Activity · vhmth/gpt-2"}