diff --git a/README.md b/README.md deleted file mode 100644 index 669a55bb4f3c9bd550a7436756d8c935acba0c5e..0000000000000000000000000000000000000000 --- a/README.md +++ /dev/null @@ -1,56 +0,0 @@ -`f` = 1e18 FLOPs. - -| run | step | params | wandb | -|---|---|---|---| -| arm/113M-100f | 104137 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/05e8f627) | -| arm/113M-10f | 10413 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/6267ec3a) | -| arm/113M-30f | 31241 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/2815a9c5) | -| arm/113M-60f | 62482 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/19004b12) | -| arm/113M-6f | 6248 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/7e3c6d2b) | -| arm/1233M-100f | 12083 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/4e99db0b) | -| arm/1233M-10f | 1208 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/b2a7f2e4) | -| arm/1233M-30f | 3624 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/317e3d54) | -| arm/1233M-60f | 7249 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/a576010e) | -| arm/1233M-6f | 724 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/81b529e3) | -| arm/170M-100f | 73072 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/96a4f141) | -| arm/170M-10f | 7307 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/a681c70c) | -| arm/170M-30f | 21921 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/733111c7) | -| arm/170M-60f | 43843 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/546e1184) | -| arm/170M-6f | 4384 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/2eaee3cb) | -| arm/336M-100f | 40144 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/19b8f681) | -| arm/336M-10f | 4014 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/72b6e66a) | -| arm/336M-30f | 12043 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/4bbbee37) | -| arm/336M-60f | 24086 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/b825f0c3) | -| arm/336M-6f | 2408 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/af6cc85a) | -| arm/472M-100f | 29462 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/4bd0b799) | -| arm/472M-10f | 2946 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/e444698b) | -| arm/472M-30f | 8838 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/988cad3a) | -| arm/472M-60f | 17677 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/6ea8aa24) | -| arm/472M-6f | 1767 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/e8adf0f3) | -| arm/629M-100f | 22588 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/812425e3) | -| arm/629M-10f | 2258 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/61027ca4) | -| arm/629M-30f | 6776 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/93963428) | -| arm/629M-60f | 13553 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/178adad8) | -| arm/629M-6f | 1355 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/7a5b5d2d) | -| arm/66M-10f | 16241 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/0fd0e998) | -| arm/66M-30f | 48724 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/080db9bb) | -| arm/66M-60f | 97449 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/f0c93293) | -| arm/66M-6f | 9744 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/79ab5ffb) | -| arm/944M-100f | 15467 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/8a660db5) | -| arm/944M-10f | 1546 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/59ad9a8e) | -| arm/944M-30f | 4640 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/c2b04352) | -| arm/944M-60f | 9280 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/db7d6e67) | -| arm/944M-6f | 928 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/abd2629e) | -| e2d2-w32/113M-100f | 93162 | 171,371,520 | [link](https://wandb.ai/marksmans/dlm/runs/11815232) | -| e2d2-w32/170M-100f | 65485 | 233,316,096 | [link](https://wandb.ai/marksmans/dlm/runs/01826f73) | -| e2d2-w32/336M-100f | 35628 | 427,485,184 | [link](https://wandb.ai/marksmans/dlm/runs/ffae6288) | -| e2d2-w32/472M-100f | 26099 | 593,332,480 | [link](https://wandb.ai/marksmans/dlm/runs/e91a392d) | -| e2d2-w32/66M-60f | 88391 | 112,332,160 | [link](https://wandb.ai/marksmans/dlm/runs/054ceaa1) | -| e2d2-w4/113M-100f | 95282 | 169,601,280 | [link](https://wandb.ai/marksmans/dlm/runs/cfad7e10) | -| e2d2-w4/170M-100f | 66561 | 229,775,616 | [link](https://wandb.ai/marksmans/dlm/runs/c88f2d5a) | -| e2d2-w4/336M-100f | 36185 | 421,191,680 | [link](https://wandb.ai/marksmans/dlm/runs/01fe245f) | -| e2d2-w4/472M-100f | 26556 | 583,499,520 | [link](https://wandb.ai/marksmans/dlm/runs/2dcdde1e) | -| e2d2-w4/66M-60f | 90605 | 109,873,280 | [link](https://wandb.ai/marksmans/dlm/runs/0aabab12) | -| maskarm/113M-100f | 104137 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/dcbba724) | -| maskarm/170M-100f | 73072 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/03692e1c) | -| maskarm/66M-60f | 97449 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/f73b8bfe) | diff --git a/arm/113M-100f/model.safetensors b/arm/113M-100f/model.safetensors deleted file mode 100644 index cd733eb9c622a9e5a5d2d7ebacda1034418b647f..0000000000000000000000000000000000000000 --- a/arm/113M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:73337fbffe39b215afdb26bba77e52425464cb3fdd5138f036ad5beee2163ed9 -size 310884952 diff --git a/arm/113M-100f/run.json b/arm/113M-100f/run.json deleted file mode 100644 index b694d379e063c6536879a590e11df0de3bcf611d..0000000000000000000000000000000000000000 --- a/arm/113M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/113M-100f", - "run_dir": "arm-113M-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 104137, - "params": 155437824, - "wandb": "https://wandb.ai/marksmans/dlm/runs/05e8f627" -} \ No newline at end of file diff --git a/arm/113M-10f/model.safetensors b/arm/113M-10f/model.safetensors deleted file mode 100644 index f19bb3840356f2f6b8cee695b570d4bad6dfafe5..0000000000000000000000000000000000000000 --- a/arm/113M-10f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:78d9d005a29302e352427d73ad55b0003908f41984c8bf2e47eb51a1fe64fe62 -size 310884952 diff --git a/arm/113M-10f/run.json b/arm/113M-10f/run.json deleted file mode 100644 index 67003dc57e31646f361aebe64537d47e35bd9f6b..0000000000000000000000000000000000000000 --- a/arm/113M-10f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/113M-10f", - "run_dir": "arm-113M-10.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 10413, - "params": 155437824, - "wandb": "https://wandb.ai/marksmans/dlm/runs/6267ec3a" -} \ No newline at end of file diff --git a/arm/113M-30f/model.safetensors b/arm/113M-30f/model.safetensors deleted file mode 100644 index 0f135facf674c662b73cb3b19c12d0a9c59a6945..0000000000000000000000000000000000000000 --- a/arm/113M-30f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:19187c564ac0b927f14167fe49094559cf9b34969242fab4acfd11f2520fe061 -size 310884952 diff --git a/arm/113M-30f/run.json b/arm/113M-30f/run.json deleted file mode 100644 index 250fc95d066ec1c9b294d3a1f07b01df1af0bd19..0000000000000000000000000000000000000000 --- a/arm/113M-30f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/113M-30f", - "run_dir": "arm-113M-30.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 31241, - "params": 155437824, - "wandb": "https://wandb.ai/marksmans/dlm/runs/2815a9c5" -} \ No newline at end of file diff --git a/arm/113M-60f/model.safetensors b/arm/113M-60f/model.safetensors deleted file mode 100644 index 65af54a17804256d1d4ae1cce014344142dc0b41..0000000000000000000000000000000000000000 --- a/arm/113M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8f29ae614b33723e3734add525662452155a70b04ed5fb16a55b69de69fa27e1 -size 310884952 diff --git a/arm/113M-60f/run.json b/arm/113M-60f/run.json deleted file mode 100644 index c065e970b0352546d04c59da029f63c04daf5340..0000000000000000000000000000000000000000 --- a/arm/113M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/113M-60f", - "run_dir": "arm-113M-60.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 62482, - "params": 155437824, - "wandb": "https://wandb.ai/marksmans/dlm/runs/19004b12" -} \ No newline at end of file diff --git a/arm/113M-6f/model.safetensors b/arm/113M-6f/model.safetensors deleted file mode 100644 index f311c4267799fd73ae368dd2361408cc7ec8365f..0000000000000000000000000000000000000000 --- a/arm/113M-6f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2eefa2828d54afa5183452bd24035903771ae4a3bf843fc2dcb482f239bfb326 -size 310884952 diff --git a/arm/113M-6f/run.json b/arm/113M-6f/run.json deleted file mode 100644 index 2b70ea1ffe4cec2c07766f1e13315059b03fa30a..0000000000000000000000000000000000000000 --- a/arm/113M-6f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/113M-6f", - "run_dir": "arm-113M-6.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 6248, - "params": 155437824, - "wandb": "https://wandb.ai/marksmans/dlm/runs/7e3c6d2b" -} \ No newline at end of file diff --git a/arm/1233M-100f/model.safetensors b/arm/1233M-100f/model.safetensors deleted file mode 100644 index 1161694074e429aec2225865b83a267054a6d8c1..0000000000000000000000000000000000000000 --- a/arm/1233M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:577dde70afa34c317489f1e2f41936bef13c3d2d10e19405cfed00d76a2da312 -size 2542139296 diff --git a/arm/1233M-100f/run.json b/arm/1233M-100f/run.json deleted file mode 100644 index cdd19df5e7266cc7d9a8055a94fba2794d6ad924..0000000000000000000000000000000000000000 --- a/arm/1233M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/1233M-100f", - "run_dir": "arm-1233M-100.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask", - "step": 12083, - "params": 1271060224, - "wandb": "https://wandb.ai/marksmans/dlm/runs/4e99db0b" -} \ No newline at end of file diff --git a/arm/1233M-10f/model.safetensors b/arm/1233M-10f/model.safetensors deleted file mode 100644 index 5c30b2f4f0b5a03b5d95338ac64177c11bc3d479..0000000000000000000000000000000000000000 --- a/arm/1233M-10f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:486d061a4360c87e02992b0baecf57ab10e59d13a055190b9b81e88a0a23533c -size 2542139296 diff --git a/arm/1233M-10f/run.json b/arm/1233M-10f/run.json deleted file mode 100644 index f0c88b89c19a1646803050f7c7580d91d142b684..0000000000000000000000000000000000000000 --- a/arm/1233M-10f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/1233M-10f", - "run_dir": "arm-1233M-10.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask", - "step": 1208, - "params": 1271060224, - "wandb": "https://wandb.ai/marksmans/dlm/runs/b2a7f2e4" -} \ No newline at end of file diff --git a/arm/1233M-30f/model.safetensors b/arm/1233M-30f/model.safetensors deleted file mode 100644 index 13d8edbb31f36d49eb4f7f6696086d3be653f175..0000000000000000000000000000000000000000 --- a/arm/1233M-30f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1a8c2532cfb5bfc5e5e4fa1b20ae883afd62b333529294cd4d3e53692485fb0e -size 2542139296 diff --git a/arm/1233M-30f/run.json b/arm/1233M-30f/run.json deleted file mode 100644 index 45270235e28eb1b65e24a1acb0323b6fc79912c7..0000000000000000000000000000000000000000 --- a/arm/1233M-30f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/1233M-30f", - "run_dir": "arm-1233M-30.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask", - "step": 3624, - "params": 1271060224, - "wandb": "https://wandb.ai/marksmans/dlm/runs/317e3d54" -} \ No newline at end of file diff --git a/arm/1233M-60f/model.safetensors b/arm/1233M-60f/model.safetensors deleted file mode 100644 index e2ffdb28785849e166f599eca2ff317aeb1d24f7..0000000000000000000000000000000000000000 --- a/arm/1233M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b6717b12ad2d076e8d5233fdee82aa367774ca05ce090d96be5fd718d68787e5 -size 2542139296 diff --git a/arm/1233M-60f/run.json b/arm/1233M-60f/run.json deleted file mode 100644 index 833e67ec9ad6dfa95fa36671b7c89e0c2afc68b2..0000000000000000000000000000000000000000 --- a/arm/1233M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/1233M-60f", - "run_dir": "arm-1233M-60.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask", - "step": 7249, - "params": 1271060224, - "wandb": "https://wandb.ai/marksmans/dlm/runs/a576010e" -} \ No newline at end of file diff --git a/arm/1233M-6f/model.safetensors b/arm/1233M-6f/model.safetensors deleted file mode 100644 index 0b8f9c65fdf4e28f1f5f9fc0efcf490387f2aece..0000000000000000000000000000000000000000 --- a/arm/1233M-6f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6dccbb397510169af60c515fe82981a17b4258d375a97a3b213e4ceabbe4e9af -size 2542139296 diff --git a/arm/1233M-6f/run.json b/arm/1233M-6f/run.json deleted file mode 100644 index 4bcdb3477e3342a96556b1a82c102e9c312f9721..0000000000000000000000000000000000000000 --- a/arm/1233M-6f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/1233M-6f", - "run_dir": "arm-1233M-6.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask", - "step": 724, - "params": 1271060224, - "wandb": "https://wandb.ai/marksmans/dlm/runs/81b529e3" -} \ No newline at end of file diff --git a/arm/170M-100f/model.safetensors b/arm/170M-100f/model.safetensors deleted file mode 100644 index 2cdd9fb97b18a8bf97948cb4f0ddcfd5bbb346cc..0000000000000000000000000000000000000000 --- a/arm/170M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3bd001281be0281d91b6ea20336466c94e26b2428a92f90b263837cc2eeb9957 -size 417076256 diff --git a/arm/170M-100f/run.json b/arm/170M-100f/run.json deleted file mode 100644 index 846172a54e249c2ad9b3776b0570993afc65f6e3..0000000000000000000000000000000000000000 --- a/arm/170M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/170M-100f", - "run_dir": "arm-170M-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 73072, - "params": 208531200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/96a4f141" -} \ No newline at end of file diff --git a/arm/170M-10f/model.safetensors b/arm/170M-10f/model.safetensors deleted file mode 100644 index f318744777ccbbc412a9d5dae1cccf26f1fc7370..0000000000000000000000000000000000000000 --- a/arm/170M-10f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:25518d443375c92a58a3512dc2f6285bda70ca0dd87a446d171ed7f3d655b2d7 -size 417076256 diff --git a/arm/170M-10f/run.json b/arm/170M-10f/run.json deleted file mode 100644 index c082917b2b18146841526dd4e014d71491b9e32f..0000000000000000000000000000000000000000 --- a/arm/170M-10f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/170M-10f", - "run_dir": "arm-170M-10.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 7307, - "params": 208531200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/a681c70c" -} \ No newline at end of file diff --git a/arm/170M-30f/model.safetensors b/arm/170M-30f/model.safetensors deleted file mode 100644 index e8f52cda31c5bcbdb0e79866f60932eeeae83180..0000000000000000000000000000000000000000 --- a/arm/170M-30f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b5a49915a2cc24442a0ff54bd26c028d38ae750d7949b8c2cf4cc5b058e78bf4 -size 417076256 diff --git a/arm/170M-30f/run.json b/arm/170M-30f/run.json deleted file mode 100644 index 06fb8915d04003222a3c2ac88844f5ee86da75af..0000000000000000000000000000000000000000 --- a/arm/170M-30f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/170M-30f", - "run_dir": "arm-170M-30.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 21921, - "params": 208531200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/733111c7" -} \ No newline at end of file diff --git a/arm/170M-60f/model.safetensors b/arm/170M-60f/model.safetensors deleted file mode 100644 index be5b9520c57b9cb155a752ad00d4e7ef962275df..0000000000000000000000000000000000000000 --- a/arm/170M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:89ccda08cba92cc7bdaa7907439a2d54d9754dfeb9833b6fee4773db409f0a6f -size 417076256 diff --git a/arm/170M-60f/run.json b/arm/170M-60f/run.json deleted file mode 100644 index 0ea0cb614b7060c23a64f84c2a4061abbbafef69..0000000000000000000000000000000000000000 --- a/arm/170M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/170M-60f", - "run_dir": "arm-170M-60.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 43843, - "params": 208531200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/546e1184" -} \ No newline at end of file diff --git a/arm/170M-6f/model.safetensors b/arm/170M-6f/model.safetensors deleted file mode 100644 index 51be525f6d15e5dc7314a3ff3e0a27cba9792db8..0000000000000000000000000000000000000000 --- a/arm/170M-6f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:901dd06d5c190465f67827efa2f74aff272b0273b1606b1802f66d9635b94ccb -size 417076256 diff --git a/arm/170M-6f/run.json b/arm/170M-6f/run.json deleted file mode 100644 index 86a4926a01093ad6712b7aee1ad35a9c227f5415..0000000000000000000000000000000000000000 --- a/arm/170M-6f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/170M-6f", - "run_dir": "arm-170M-6.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 4384, - "params": 208531200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/2eaee3cb" -} \ No newline at end of file diff --git a/arm/336M-100f/model.safetensors b/arm/336M-100f/model.safetensors deleted file mode 100644 index d67dd39fa2fae377f52bcd61e8a5b2f02d3dd061..0000000000000000000000000000000000000000 --- a/arm/336M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9ec7bee77ecf759a2c4e03e8547f50c28cedcf1fa51762efd18e08a16e4e8331 -size 760579272 diff --git a/arm/336M-100f/run.json b/arm/336M-100f/run.json deleted file mode 100644 index ebb027a4a07b24725beb1a33b79f558560d55402..0000000000000000000000000000000000000000 --- a/arm/336M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/336M-100f", - "run_dir": "arm-336M-100.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask", - "step": 40144, - "params": 380281856, - "wandb": "https://wandb.ai/marksmans/dlm/runs/19b8f681" -} \ No newline at end of file diff --git a/arm/336M-10f/model.safetensors b/arm/336M-10f/model.safetensors deleted file mode 100644 index e270ab1eb7298ca00f6bb773578b70429dc977a9..0000000000000000000000000000000000000000 --- a/arm/336M-10f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:432cb69a3bee1f09733a2e62337c2c6adacc113d796d392ac1821c51b8b5c47c -size 760579272 diff --git a/arm/336M-10f/run.json b/arm/336M-10f/run.json deleted file mode 100644 index f9bed933a7472be3b2b3b36608e44905dba01771..0000000000000000000000000000000000000000 --- a/arm/336M-10f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/336M-10f", - "run_dir": "arm-336M-10.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask", - "step": 4014, - "params": 380281856, - "wandb": "https://wandb.ai/marksmans/dlm/runs/72b6e66a" -} \ No newline at end of file diff --git a/arm/336M-30f/model.safetensors b/arm/336M-30f/model.safetensors deleted file mode 100644 index 0436878226d7459dbbfcd038c0a4dfe67e69358d..0000000000000000000000000000000000000000 --- a/arm/336M-30f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cf87d29d60735dc3de165be66eb24a9e14e233ac37edaa061a89b342f559a0a6 -size 760579272 diff --git a/arm/336M-30f/run.json b/arm/336M-30f/run.json deleted file mode 100644 index 83f293f59460c30a40c5f266a0ad4325cfa44a73..0000000000000000000000000000000000000000 --- a/arm/336M-30f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/336M-30f", - "run_dir": "arm-336M-30.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask", - "step": 12043, - "params": 380281856, - "wandb": "https://wandb.ai/marksmans/dlm/runs/4bbbee37" -} \ No newline at end of file diff --git a/arm/336M-60f/model.safetensors b/arm/336M-60f/model.safetensors deleted file mode 100644 index c7a97f6c216a46d7cee1c158b9d7792db0feca52..0000000000000000000000000000000000000000 --- a/arm/336M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0931e813a7722ce340aa9ccc0998dfac23cbf26c555e597e1adfb368b8b10da5 -size 760579272 diff --git a/arm/336M-60f/run.json b/arm/336M-60f/run.json deleted file mode 100644 index 2dbfc4e2769aebde2c37a7fbb8685c9baa7c9e5f..0000000000000000000000000000000000000000 --- a/arm/336M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/336M-60f", - "run_dir": "arm-336M-60.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask", - "step": 24086, - "params": 380281856, - "wandb": "https://wandb.ai/marksmans/dlm/runs/b825f0c3" -} \ No newline at end of file diff --git a/arm/336M-6f/model.safetensors b/arm/336M-6f/model.safetensors deleted file mode 100644 index 41053854a72d8656737c3cdffa962e76c3b54258..0000000000000000000000000000000000000000 --- a/arm/336M-6f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:153d55f2c545f32f5e35a6b07b17baf70e9cd557e0022364f5fb0ad2b91184d3 -size 760579272 diff --git a/arm/336M-6f/run.json b/arm/336M-6f/run.json deleted file mode 100644 index 1ae5e0dca5e6a272ac9fa53a3608957ec47a1bc4..0000000000000000000000000000000000000000 --- a/arm/336M-6f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/336M-6f", - "run_dir": "arm-336M-6.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask", - "step": 2408, - "params": 380281856, - "wandb": "https://wandb.ai/marksmans/dlm/runs/af6cc85a" -} \ No newline at end of file diff --git a/arm/472M-100f/model.safetensors b/arm/472M-100f/model.safetensors deleted file mode 100644 index f7eca57f19348506bfb58c2f12826c5b4ce8ef2f..0000000000000000000000000000000000000000 --- a/arm/472M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:92cc19851c04351f84bc5a13d1032551a18b5f4cd19d5e49245e76e07e81410c -size 1049012432 diff --git a/arm/472M-100f/run.json b/arm/472M-100f/run.json deleted file mode 100644 index f71f537e9bab078d4a784eb5bb89b3e054d98a01..0000000000000000000000000000000000000000 --- a/arm/472M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/472M-100f", - "run_dir": "arm-472M-100.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 29462, - "params": 524499200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/4bd0b799" -} \ No newline at end of file diff --git a/arm/472M-10f/model.safetensors b/arm/472M-10f/model.safetensors deleted file mode 100644 index 6efc773e14a03cef8b0895cb949d4d70f6342530..0000000000000000000000000000000000000000 --- a/arm/472M-10f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:13cc602b5126e417efeeaaa6ad6fbbc76b6d1ecacba2d35675127d3e0f0b7cd6 -size 1049012432 diff --git a/arm/472M-10f/run.json b/arm/472M-10f/run.json deleted file mode 100644 index 24f0608eedc5f4f9094b74c7bcd31637097f14bf..0000000000000000000000000000000000000000 --- a/arm/472M-10f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/472M-10f", - "run_dir": "arm-472M-10.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 2946, - "params": 524499200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/e444698b" -} \ No newline at end of file diff --git a/arm/472M-30f/model.safetensors b/arm/472M-30f/model.safetensors deleted file mode 100644 index e913777b9bbbdb2cb923e0fdd3a26eab491a8ca5..0000000000000000000000000000000000000000 --- a/arm/472M-30f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:40bd8b709952c9fa27ee896c4e5606b5a8c24c64e273996ef8e5ddcd8c045699 -size 1049012432 diff --git a/arm/472M-30f/run.json b/arm/472M-30f/run.json deleted file mode 100644 index abec53bfb42b6291b7b28905b04601b3b675b454..0000000000000000000000000000000000000000 --- a/arm/472M-30f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/472M-30f", - "run_dir": "arm-472M-30.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 8838, - "params": 524499200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/988cad3a" -} \ No newline at end of file diff --git a/arm/472M-60f/model.safetensors b/arm/472M-60f/model.safetensors deleted file mode 100644 index 29cb21b13d43cb3cbc82429b4584e5d50848f191..0000000000000000000000000000000000000000 --- a/arm/472M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:997398450f6a69c2e4eab78e6b93c9efc3068e15278614bb895ab08e64f696f8 -size 1049012432 diff --git a/arm/472M-60f/run.json b/arm/472M-60f/run.json deleted file mode 100644 index 180550728b975f0851057386424c0a366d3ce2bb..0000000000000000000000000000000000000000 --- a/arm/472M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/472M-60f", - "run_dir": "arm-472M-60.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 17677, - "params": 524499200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/6ea8aa24" -} \ No newline at end of file diff --git a/arm/472M-6f/model.safetensors b/arm/472M-6f/model.safetensors deleted file mode 100644 index 1e15b5fd6f7b730355a3e4abdfbf53e554ee447a..0000000000000000000000000000000000000000 --- a/arm/472M-6f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c6646a7b33c524d2f5a9aaaeae95cade8b296f79419211fe4b6355ccc018e24b -size 1049012432 diff --git a/arm/472M-6f/run.json b/arm/472M-6f/run.json deleted file mode 100644 index 78e62d34eb1416673bc645a142a0fcba83e0e614..0000000000000000000000000000000000000000 --- a/arm/472M-6f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/472M-6f", - "run_dir": "arm-472M-6.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 1767, - "params": 524499200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/e8adf0f3" -} \ No newline at end of file diff --git a/arm/629M-100f/model.safetensors b/arm/629M-100f/model.safetensors deleted file mode 100644 index 0b26f09018abe3439ed6c2bd21089608a5efdb6e..0000000000000000000000000000000000000000 --- a/arm/629M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2135d47c87f9c8625b36e907c3cb095dd31ddaebf3bd01c490c0122e5c26cd4a -size 1343959832 diff --git a/arm/629M-100f/run.json b/arm/629M-100f/run.json deleted file mode 100644 index 839ab926f56ddf25f983a4fc8a7f2afdb9628666..0000000000000000000000000000000000000000 --- a/arm/629M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/629M-100f", - "run_dir": "arm-629M-100.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 22588, - "params": 671970560, - "wandb": "https://wandb.ai/marksmans/dlm/runs/812425e3" -} \ No newline at end of file diff --git a/arm/629M-10f/model.safetensors b/arm/629M-10f/model.safetensors deleted file mode 100644 index 1741987b39cf81446c61e2b7aed03f46e3f1ec0e..0000000000000000000000000000000000000000 --- a/arm/629M-10f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8a297940b9f1827c2967cdd0b7eb3898b84c549cfe23b75d46d4af7230e08b82 -size 1343959832 diff --git a/arm/629M-10f/run.json b/arm/629M-10f/run.json deleted file mode 100644 index 591ca9497240c88fcb17bc50149b078aa41348f1..0000000000000000000000000000000000000000 --- a/arm/629M-10f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/629M-10f", - "run_dir": "arm-629M-10.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 2258, - "params": 671970560, - "wandb": "https://wandb.ai/marksmans/dlm/runs/61027ca4" -} \ No newline at end of file diff --git a/arm/629M-30f/model.safetensors b/arm/629M-30f/model.safetensors deleted file mode 100644 index f58e0d26607d401d62655cc6740b7cad8e6c0594..0000000000000000000000000000000000000000 --- a/arm/629M-30f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6f4c2366fa536e92f1b28059d40ee3c71d8cae97acada112188897aaada1bfb3 -size 1343959832 diff --git a/arm/629M-30f/run.json b/arm/629M-30f/run.json deleted file mode 100644 index e33185e3f267a91c559748b35e45e4b18fb4b18e..0000000000000000000000000000000000000000 --- a/arm/629M-30f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/629M-30f", - "run_dir": "arm-629M-30.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 6776, - "params": 671970560, - "wandb": "https://wandb.ai/marksmans/dlm/runs/93963428" -} \ No newline at end of file diff --git a/arm/629M-60f/model.safetensors b/arm/629M-60f/model.safetensors deleted file mode 100644 index d761bae76c9bc25a5bae4d391826089b4d803cba..0000000000000000000000000000000000000000 --- a/arm/629M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:17f45203dad7bd71064e6f663a081afc88ccf570bfc26a76e18c2c582c20af17 -size 1343959832 diff --git a/arm/629M-60f/run.json b/arm/629M-60f/run.json deleted file mode 100644 index aa0a88313813b0c4d8226591a51b262268ca3d7d..0000000000000000000000000000000000000000 --- a/arm/629M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/629M-60f", - "run_dir": "arm-629M-60.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 13553, - "params": 671970560, - "wandb": "https://wandb.ai/marksmans/dlm/runs/178adad8" -} \ No newline at end of file diff --git a/arm/629M-6f/model.safetensors b/arm/629M-6f/model.safetensors deleted file mode 100644 index bc2d5298584b2326b76888360d39c3fdec8e429b..0000000000000000000000000000000000000000 --- a/arm/629M-6f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8494c508624ca87fdae9b712ee72f2f60dc8b845a917369b8258dd5f27e8b979 -size 1343959832 diff --git a/arm/629M-6f/run.json b/arm/629M-6f/run.json deleted file mode 100644 index dfdd3d64b3bb6b5e7827d96fc456854000a6542d..0000000000000000000000000000000000000000 --- a/arm/629M-6f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/629M-6f", - "run_dir": "arm-629M-6.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 1355, - "params": 671970560, - "wandb": "https://wandb.ai/marksmans/dlm/runs/7a5b5d2d" -} \ No newline at end of file diff --git a/arm/66M-10f/model.safetensors b/arm/66M-10f/model.safetensors deleted file mode 100644 index 696b5f09689d2f329aed90ac44053c47470e1441..0000000000000000000000000000000000000000 --- a/arm/66M-10f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1ae7b3e9e7fae5c548e8d9c6fb904467f3a873f56c7e72a364a768e335a4eeef -size 204998480 diff --git a/arm/66M-10f/run.json b/arm/66M-10f/run.json deleted file mode 100644 index ed1057a103691a5d2d52b4f0f482346a280a83b1..0000000000000000000000000000000000000000 --- a/arm/66M-10f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/66M-10f", - "run_dir": "arm-66M-10.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 16241, - "params": 102495360, - "wandb": "https://wandb.ai/marksmans/dlm/runs/0fd0e998" -} \ No newline at end of file diff --git a/arm/66M-30f/model.safetensors b/arm/66M-30f/model.safetensors deleted file mode 100644 index 876bfd4e8fe846ef7f7fbe74591849c5a30e8135..0000000000000000000000000000000000000000 --- a/arm/66M-30f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cec49366040f1a501f6e9d731df75c9cfcd16a345933f15535db135a984a3ef6 -size 204998480 diff --git a/arm/66M-30f/run.json b/arm/66M-30f/run.json deleted file mode 100644 index ec9ede96ab9e0f5fb689fbdd3c190f8c3b390a5e..0000000000000000000000000000000000000000 --- a/arm/66M-30f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/66M-30f", - "run_dir": "arm-66M-30.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 48724, - "params": 102495360, - "wandb": "https://wandb.ai/marksmans/dlm/runs/080db9bb" -} \ No newline at end of file diff --git a/arm/66M-60f/model.safetensors b/arm/66M-60f/model.safetensors deleted file mode 100644 index ca5f85b2049b979c7f0770aba4c78f16be0db082..0000000000000000000000000000000000000000 --- a/arm/66M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9aa57395b20848434f925b9935b52d2e85fd8aa24b12fe74b0ae67dcad85ba79 -size 204998480 diff --git a/arm/66M-60f/run.json b/arm/66M-60f/run.json deleted file mode 100644 index e525044e8e4f682a922f487c48bd8f70d0763f02..0000000000000000000000000000000000000000 --- a/arm/66M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/66M-60f", - "run_dir": "arm-66M-60.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 97449, - "params": 102495360, - "wandb": "https://wandb.ai/marksmans/dlm/runs/f0c93293" -} \ No newline at end of file diff --git a/arm/66M-6f/model.safetensors b/arm/66M-6f/model.safetensors deleted file mode 100644 index 0a5730cb16e105d17cc86ead811c0ed038b6c233..0000000000000000000000000000000000000000 --- a/arm/66M-6f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e7bd17b78f4e7649b32b4a1c6e1b01358907e83f6f908ccb32ae7c8442403e9f -size 204998480 diff --git a/arm/66M-6f/run.json b/arm/66M-6f/run.json deleted file mode 100644 index 2afcbfd1cf1b49699aed5029f9cb589e0b00d26b..0000000000000000000000000000000000000000 --- a/arm/66M-6f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/66M-6f", - "run_dir": "arm-66M-6.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 9744, - "params": 102495360, - "wandb": "https://wandb.ai/marksmans/dlm/runs/79ab5ffb" -} \ No newline at end of file diff --git a/arm/944M-100f/model.safetensors b/arm/944M-100f/model.safetensors deleted file mode 100644 index 9a4f86ff9399256bc8278514c157890f37a079e9..0000000000000000000000000000000000000000 --- a/arm/944M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cb9ed1f714f9844ff6bf1ce71bc071edd21d9e49fb5d66c37675fd6229226eda -size 1966649464 diff --git a/arm/944M-100f/run.json b/arm/944M-100f/run.json deleted file mode 100644 index e73d6575f3ab7f03ae1f35ccdf1fe0c59e0694bf..0000000000000000000000000000000000000000 --- a/arm/944M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/944M-100f", - "run_dir": "arm-944M-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 15467, - "params": 983314944, - "wandb": "https://wandb.ai/marksmans/dlm/runs/8a660db5" -} \ No newline at end of file diff --git a/arm/944M-10f/model.safetensors b/arm/944M-10f/model.safetensors deleted file mode 100644 index 5302dbee69a8d605ef571e57f9d95e54fefc1a48..0000000000000000000000000000000000000000 --- a/arm/944M-10f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0b5bb3661c6f373c36e2f181127af451728dca764a507d327646f73d16d05df5 -size 1966649464 diff --git a/arm/944M-10f/run.json b/arm/944M-10f/run.json deleted file mode 100644 index 3601a2630c4a6697edea90993d400a22de54a36c..0000000000000000000000000000000000000000 --- a/arm/944M-10f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/944M-10f", - "run_dir": "arm-944M-10.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 1546, - "params": 983314944, - "wandb": "https://wandb.ai/marksmans/dlm/runs/59ad9a8e" -} \ No newline at end of file diff --git a/arm/944M-30f/model.safetensors b/arm/944M-30f/model.safetensors deleted file mode 100644 index c0fa8eda887632b238be1bff56154e95e95e61b3..0000000000000000000000000000000000000000 --- a/arm/944M-30f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0a56900750a064619217607ff69a2c6c8e0de94583e60e10d50afa3db11ac4ac -size 1966649464 diff --git a/arm/944M-30f/run.json b/arm/944M-30f/run.json deleted file mode 100644 index d690701ba483603345b93250faabb3166ce71270..0000000000000000000000000000000000000000 --- a/arm/944M-30f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/944M-30f", - "run_dir": "arm-944M-30.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 4640, - "params": 983314944, - "wandb": "https://wandb.ai/marksmans/dlm/runs/c2b04352" -} \ No newline at end of file diff --git a/arm/944M-60f/model.safetensors b/arm/944M-60f/model.safetensors deleted file mode 100644 index 1ce13621bcfa222185657663c2235ac7069f959a..0000000000000000000000000000000000000000 --- a/arm/944M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0bd1c91e21ab137fec3847c8f2728e71a9cb82f47b6b08719fe9f4ca37216824 -size 1966649464 diff --git a/arm/944M-60f/run.json b/arm/944M-60f/run.json deleted file mode 100644 index 8fdf9d6e5717493ad764372f7188bdd528a3a7e4..0000000000000000000000000000000000000000 --- a/arm/944M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/944M-60f", - "run_dir": "arm-944M-60.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 9280, - "params": 983314944, - "wandb": "https://wandb.ai/marksmans/dlm/runs/db7d6e67" -} \ No newline at end of file diff --git a/arm/944M-6f/model.safetensors b/arm/944M-6f/model.safetensors deleted file mode 100644 index ee82d326ffc557fd7a933be063b8e922dfdfa84b..0000000000000000000000000000000000000000 --- a/arm/944M-6f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ab1836f2005cbe2c509a3f6b1f3dd1a0560b3eabe384e43a66e66a9bc37dccee -size 1966649464 diff --git a/arm/944M-6f/run.json b/arm/944M-6f/run.json deleted file mode 100644 index 2b97bd3d6793010553dd078ab1d44381a8a7c8e2..0000000000000000000000000000000000000000 --- a/arm/944M-6f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "arm/944M-6f", - "run_dir": "arm-944M-6.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 928, - "params": 983314944, - "wandb": "https://wandb.ai/marksmans/dlm/runs/abd2629e" -} \ No newline at end of file diff --git a/e2d2-w32/113M-100f/model.safetensors b/e2d2-w32/113M-100f/model.safetensors deleted file mode 100644 index 87be90b948d7d216c4fa6a7a96135b61eb471d4d..0000000000000000000000000000000000000000 --- a/e2d2-w32/113M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:19969cb08a353c99fb9ad344f4295a6b355ccfd92660a10ab920ba8fb30b7317 -size 342756240 diff --git a/e2d2-w32/113M-100f/run.json b/e2d2-w32/113M-100f/run.json deleted file mode 100644 index f6ad6dd371d6bc3ef26c439f2e7ba8a826bb97c6..0000000000000000000000000000000000000000 --- a/e2d2-w32/113M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w32/113M-100f", - "run_dir": "e2d2-113M-9dec-w32-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask-lowvar", - "step": 93162, - "params": 171371520, - "wandb": "https://wandb.ai/marksmans/dlm/runs/11815232" -} \ No newline at end of file diff --git a/e2d2-w32/170M-100f/model.safetensors b/e2d2-w32/170M-100f/model.safetensors deleted file mode 100644 index a1ecc5fa340ee5b995888a6396fe604a4c48b5e0..0000000000000000000000000000000000000000 --- a/e2d2-w32/170M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:acd2092b2ddfd1cdf6f3f8644cfdb50da006022ba39be5522e21cd46c9eb2dad -size 466652104 diff --git a/e2d2-w32/170M-100f/run.json b/e2d2-w32/170M-100f/run.json deleted file mode 100644 index 22f82ec9427c87594d3ac990dea108cee3c6be3b..0000000000000000000000000000000000000000 --- a/e2d2-w32/170M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w32/170M-100f", - "run_dir": "e2d2-170M-14dec-w32-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask-lowvar", - "step": 65485, - "params": 233316096, - "wandb": "https://wandb.ai/marksmans/dlm/runs/01826f73" -} \ No newline at end of file diff --git a/e2d2-w32/336M-100f/model.safetensors b/e2d2-w32/336M-100f/model.safetensors deleted file mode 100644 index 03c9179177c3122f1d7dd9d0f848138b48391554..0000000000000000000000000000000000000000 --- a/e2d2-w32/336M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:185cc47edb3051c21ba2e7e53c0a9443e671abf515cf55bbb1f9cce8433e3f25 -size 854992544 diff --git a/e2d2-w32/336M-100f/run.json b/e2d2-w32/336M-100f/run.json deleted file mode 100644 index 0b1369c722148af619c3f06167507a265612fc98..0000000000000000000000000000000000000000 --- a/e2d2-w32/336M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w32/336M-100f", - "run_dir": "e2d2-336M-15dec-w32-100.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask-lowvar", - "step": 35628, - "params": 427485184, - "wandb": "https://wandb.ai/marksmans/dlm/runs/ffae6288" -} \ No newline at end of file diff --git a/e2d2-w32/472M-100f/model.safetensors b/e2d2-w32/472M-100f/model.safetensors deleted file mode 100644 index 3cf9bb2c7e056f835434ef308eae927920b7f222..0000000000000000000000000000000000000000 --- a/e2d2-w32/472M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9e3f4d6e9ac5d6078c089a4d89dd4c68531223e2ce5ef4c11ece8a4e648c6c0c -size 1186685200 diff --git a/e2d2-w32/472M-100f/run.json b/e2d2-w32/472M-100f/run.json deleted file mode 100644 index a70adceb69e048b92114b1c07c3dac9c1cea8138..0000000000000000000000000000000000000000 --- a/e2d2-w32/472M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w32/472M-100f", - "run_dir": "e2d2-472M-14dec-w32-100.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask-lowvar", - "step": 26099, - "params": 593332480, - "wandb": "https://wandb.ai/marksmans/dlm/runs/e91a392d" -} \ No newline at end of file diff --git a/e2d2-w32/66M-60f/model.safetensors b/e2d2-w32/66M-60f/model.safetensors deleted file mode 100644 index e3c7e0d27012acafb84f40a4102f9cd26fcab3da..0000000000000000000000000000000000000000 --- a/e2d2-w32/66M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7ab054c1dba1d5ba61c350c85181296f5b840705268d05543fd92a2225d20949 -size 224675528 diff --git a/e2d2-w32/66M-60f/run.json b/e2d2-w32/66M-60f/run.json deleted file mode 100644 index 1f8c05fe7373987bc7237b12d889ab716f78d058..0000000000000000000000000000000000000000 --- a/e2d2-w32/66M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w32/66M-60f", - "run_dir": "e2d2-66M-8dec-w32-60.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask-lowvar", - "step": 88391, - "params": 112332160, - "wandb": "https://wandb.ai/marksmans/dlm/runs/054ceaa1" -} \ No newline at end of file diff --git a/e2d2-w4/113M-100f/model.safetensors b/e2d2-w4/113M-100f/model.safetensors deleted file mode 100644 index ad42c6836c16241f6058244f8a0e23e6e837a38f..0000000000000000000000000000000000000000 --- a/e2d2-w4/113M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7ae192d05ca48f4e79cc9cc469efbff7d6d56fc6ae868b54e1a7f0fb9e6ad1af -size 339215336 diff --git a/e2d2-w4/113M-100f/run.json b/e2d2-w4/113M-100f/run.json deleted file mode 100644 index 96760a96267dea9b3cacad9ceb9cb571ea49402e..0000000000000000000000000000000000000000 --- a/e2d2-w4/113M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w4/113M-100f", - "run_dir": "e2d2-113M-8dec-w4-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask-lowvar", - "step": 95282, - "params": 169601280, - "wandb": "https://wandb.ai/marksmans/dlm/runs/cfad7e10" -} \ No newline at end of file diff --git a/e2d2-w4/170M-100f/model.safetensors b/e2d2-w4/170M-100f/model.safetensors deleted file mode 100644 index 739d8c8a0bdb883e3f6b0a6b4b028dd4b2c5e50f..0000000000000000000000000000000000000000 --- a/e2d2-w4/170M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e05d30d29d36c25cea1863d3485ae61e29ed651cf6565f49bf60d0bfa6c9087e -size 459570272 diff --git a/e2d2-w4/170M-100f/run.json b/e2d2-w4/170M-100f/run.json deleted file mode 100644 index ee36fe46e524edb3a98e874d1708fd65b7728ae2..0000000000000000000000000000000000000000 --- a/e2d2-w4/170M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w4/170M-100f", - "run_dir": "e2d2-170M-12dec-w4-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask-lowvar", - "step": 66561, - "params": 229775616, - "wandb": "https://wandb.ai/marksmans/dlm/runs/c88f2d5a" -} \ No newline at end of file diff --git a/e2d2-w4/336M-100f/model.safetensors b/e2d2-w4/336M-100f/model.safetensors deleted file mode 100644 index 190460224ec761014013a516b4f355b13bad5f59..0000000000000000000000000000000000000000 --- a/e2d2-w4/336M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ab112dc406abe4f84804c552e6238102b0d3e8053c7b6618a38803d8642caa27 -size 842404656 diff --git a/e2d2-w4/336M-100f/run.json b/e2d2-w4/336M-100f/run.json deleted file mode 100644 index cca28fcbbce8fa94775aa5fd0b814f09ea09bf91..0000000000000000000000000000000000000000 --- a/e2d2-w4/336M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w4/336M-100f", - "run_dir": "e2d2-336M-13dec-w4-100.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask-lowvar", - "step": 36185, - "params": 421191680, - "wandb": "https://wandb.ai/marksmans/dlm/runs/01fe245f" -} \ No newline at end of file diff --git a/e2d2-w4/472M-100f/model.safetensors b/e2d2-w4/472M-100f/model.safetensors deleted file mode 100644 index 8eb31792ed5cdca36c7d83a2de6ac5ac31807f20..0000000000000000000000000000000000000000 --- a/e2d2-w4/472M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c7bd2433417c76ebb647e8f1e752d10c7b966c8ec18197ec774e693118302615 -size 1167018392 diff --git a/e2d2-w4/472M-100f/run.json b/e2d2-w4/472M-100f/run.json deleted file mode 100644 index f2e4142de00d6913d6ac8cdf6770b4a23ca97a2c..0000000000000000000000000000000000000000 --- a/e2d2-w4/472M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w4/472M-100f", - "run_dir": "e2d2-472M-12dec-w4-100.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask-lowvar", - "step": 26556, - "params": 583499520, - "wandb": "https://wandb.ai/marksmans/dlm/runs/2dcdde1e" -} \ No newline at end of file diff --git a/e2d2-w4/66M-60f/model.safetensors b/e2d2-w4/66M-60f/model.safetensors deleted file mode 100644 index f1fd283ae818a6f9c1cd4cd99126736943ee8a73..0000000000000000000000000000000000000000 --- a/e2d2-w4/66M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2f9bcc85345ee30a9b6399adf30c9122d46ab3f590985ff185492ac9d9a3da71 -size 219756920 diff --git a/e2d2-w4/66M-60f/run.json b/e2d2-w4/66M-60f/run.json deleted file mode 100644 index 1c53b84a21d88a1c184e4090d85e0190c99359a4..0000000000000000000000000000000000000000 --- a/e2d2-w4/66M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "e2d2-w4/66M-60f", - "run_dir": "e2d2-66M-6dec-w4-60.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask-lowvar", - "step": 90605, - "params": 109873280, - "wandb": "https://wandb.ai/marksmans/dlm/runs/0aabab12" -} \ No newline at end of file diff --git a/maskarm/113M-100f/model.safetensors b/maskarm/113M-100f/model.safetensors deleted file mode 100644 index 53cf65f10cdd7b8408b90d76b6a974785528cb14..0000000000000000000000000000000000000000 --- a/maskarm/113M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:935b831ed985e4569f713a200ac05c384ca074edf7894c661b118ef8350ffa05 -size 310884952 diff --git a/maskarm/113M-100f/run.json b/maskarm/113M-100f/run.json deleted file mode 100644 index 6387a8246f9ab51a8413cc619bf4dc1629757144..0000000000000000000000000000000000000000 --- a/maskarm/113M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "maskarm/113M-100f", - "run_dir": "maskarm-113M-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 104137, - "params": 155437824, - "wandb": "https://wandb.ai/marksmans/dlm/runs/dcbba724" -} \ No newline at end of file diff --git a/maskarm/170M-100f/model.safetensors b/maskarm/170M-100f/model.safetensors deleted file mode 100644 index f9c6422392af5d06102faa010db2dc53df55c5a6..0000000000000000000000000000000000000000 --- a/maskarm/170M-100f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:095d3d767795b0838e87c8ea969093b71a6ff7ab752df436735d32d2942cf47d -size 417076256 diff --git a/maskarm/170M-100f/run.json b/maskarm/170M-100f/run.json deleted file mode 100644 index ab4100fb075e70bb3df0e21c3b6aceddf2a248be..0000000000000000000000000000000000000000 --- a/maskarm/170M-100f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "maskarm/170M-100f", - "run_dir": "maskarm-170M-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask", - "step": 73072, - "params": 208531200, - "wandb": "https://wandb.ai/marksmans/dlm/runs/03692e1c" -} \ No newline at end of file diff --git a/maskarm/66M-60f/model.safetensors b/maskarm/66M-60f/model.safetensors deleted file mode 100644 index ab02677449f088428caf745f52f01b16006ac28c..0000000000000000000000000000000000000000 --- a/maskarm/66M-60f/model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:147c6efc56280fdf2cb59cff5393de629aecd3ae5072ca94851578664422aade -size 204998480 diff --git a/maskarm/66M-60f/run.json b/maskarm/66M-60f/run.json deleted file mode 100644 index cdbf88580693481168f6396a3c5593bb08000468..0000000000000000000000000000000000000000 --- a/maskarm/66M-60f/run.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "path": "maskarm/66M-60f", - "run_dir": "maskarm-66M-60.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask", - "step": 97449, - "params": 102495360, - "wandb": "https://wandb.ai/marksmans/dlm/runs/f73b8bfe" -} \ No newline at end of file