Hugging Face's logo

hoangp111
/
dlm

Safetensors
Model card Files
xet
 Community
1

Delete arm/60.0flop/arm-1233M-60.0flop/iter-032000-ckpt.pth with huggingface_hub

#1
by ngqtrung - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+0
-1720
This view is limited to 50 files because it contains too many changes. See the raw diff here.
Files changed (50) hide show
  1. README.md +0 -160
  2. arm/113M-100f/model.safetensors +0 -3
  3. arm/113M-100f/run.json +0 -7
  4. arm/113M-10f/model.safetensors +0 -3
  5. arm/113M-10f/run.json +0 -7
  6. arm/113M-30f/model.safetensors +0 -3
  7. arm/113M-30f/run.json +0 -7
  8. arm/113M-60f/model.safetensors +0 -3
  9. arm/113M-60f/run.json +0 -7
  10. arm/113M-6f/model.safetensors +0 -3
  11. arm/113M-6f/run.json +0 -7
  12. arm/1233M-100f/model.safetensors +0 -3
  13. arm/1233M-100f/run.json +0 -7
  14. arm/1233M-10f/model.safetensors +0 -3
  15. arm/1233M-10f/run.json +0 -7
  16. arm/1233M-30f/model.safetensors +0 -3
  17. arm/1233M-30f/run.json +0 -7
  18. arm/1233M-60f/model.safetensors +0 -3
  19. arm/1233M-60f/run.json +0 -7
  20. arm/1233M-6f/model.safetensors +0 -3
  21. arm/1233M-6f/run.json +0 -7
  22. arm/170M-100f/model.safetensors +0 -3
  23. arm/170M-100f/run.json +0 -7
  24. arm/170M-10f/model.safetensors +0 -3
  25. arm/170M-10f/run.json +0 -7
  26. arm/170M-30f/model.safetensors +0 -3
  27. arm/170M-30f/run.json +0 -7
  28. arm/170M-60f/model.safetensors +0 -3
  29. arm/170M-60f/run.json +0 -7
  30. arm/170M-6f/model.safetensors +0 -3
  31. arm/170M-6f/run.json +0 -7
  32. arm/336M-100f/model.safetensors +0 -3
  33. arm/336M-100f/run.json +0 -7
  34. arm/336M-10f/model.safetensors +0 -3
  35. arm/336M-10f/run.json +0 -7
  36. arm/336M-30f/model.safetensors +0 -3
  37. arm/336M-30f/run.json +0 -7
  38. arm/336M-60f/model.safetensors +0 -3
  39. arm/336M-60f/run.json +0 -7
  40. arm/336M-6f/model.safetensors +0 -3
  41. arm/336M-6f/run.json +0 -7
  42. arm/472M-100f/model.safetensors +0 -3
  43. arm/472M-100f/run.json +0 -7
  44. arm/472M-10f/model.safetensors +0 -3
  45. arm/472M-10f/run.json +0 -7
  46. arm/472M-30f/model.safetensors +0 -3
  47. arm/472M-30f/run.json +0 -7
  48. arm/472M-60f/model.safetensors +0 -3
  49. arm/472M-60f/run.json +0 -7
  50. arm/472M-6f/model.safetensors +0 -3
README.md DELETED
@@ -1,160 +0,0 @@
1
- `f` = 1e18 FLOPs.
2
-
3
- | run | step | params | wandb |
4
- |---|---|---|---|
5
- | arm/113M-100f | 104137 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/05e8f627) |
6
- | arm/113M-10f | 10413 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/6267ec3a) |
7
- | arm/113M-30f | 31241 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/2815a9c5) |
8
- | arm/113M-60f | 62482 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/19004b12) |
9
- | arm/113M-6f | 6248 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/7e3c6d2b) |
10
- | arm/1233M-100f | 12083 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/4e99db0b) |
11
- | arm/1233M-10f | 1208 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/b2a7f2e4) |
12
- | arm/1233M-30f | 3624 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/317e3d54) |
13
- | arm/1233M-60f | 7249 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/a576010e) |
14
- | arm/1233M-6f | 724 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/81b529e3) |
15
- | arm/170M-100f | 73072 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/96a4f141) |
16
- | arm/170M-10f | 7307 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/a681c70c) |
17
- | arm/170M-30f | 21921 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/733111c7) |
18
- | arm/170M-60f | 43843 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/546e1184) |
19
- | arm/170M-6f | 4384 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/2eaee3cb) |
20
- | arm/336M-100f | 40144 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/19b8f681) |
21
- | arm/336M-10f | 4014 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/72b6e66a) |
22
- | arm/336M-30f | 12043 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/4bbbee37) |
23
- | arm/336M-60f | 24086 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/b825f0c3) |
24
- | arm/336M-6f | 2408 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/af6cc85a) |
25
- | arm/472M-100f | 29462 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/4bd0b799) |
26
- | arm/472M-10f | 2946 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/e444698b) |
27
- | arm/472M-30f | 8838 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/988cad3a) |
28
- | arm/472M-60f | 17677 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/6ea8aa24) |
29
- | arm/472M-6f | 1767 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/e8adf0f3) |
30
- | arm/629M-100f | 22588 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/812425e3) |
31
- | arm/629M-10f | 2258 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/61027ca4) |
32
- | arm/629M-30f | 6776 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/93963428) |
33
- | arm/629M-60f | 13553 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/178adad8) |
34
- | arm/629M-6f | 1355 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/7a5b5d2d) |
35
- | arm/66M-10f | 16241 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/0fd0e998) |
36
- | arm/66M-30f | 48724 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/080db9bb) |
37
- | arm/66M-60f | 97449 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/f0c93293) |
38
- | arm/66M-6f | 9744 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/79ab5ffb) |
39
- | arm/944M-100f | 15467 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/8a660db5) |
40
- | arm/944M-10f | 1546 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/59ad9a8e) |
41
- | arm/944M-30f | 4640 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/c2b04352) |
42
- | arm/944M-60f | 9280 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/db7d6e67) |
43
- | arm/944M-6f | 928 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/abd2629e) |
44
- | e2d2-w32/113M-100f | 93162 | 171,371,520 | [link](https://wandb.ai/marksmans/dlm/runs/11815232) |
45
- | e2d2-w32/113M-10f | 9316 | 171,371,520 | [link](https://wandb.ai/marksmans/dlm/runs/82e0b025) |
46
- | e2d2-w32/113M-30f | 27948 | 171,371,520 | [link](https://wandb.ai/marksmans/dlm/runs/cc9416e1) |
47
- | e2d2-w32/113M-60f | 55897 | 171,371,520 | [link](https://wandb.ai/marksmans/dlm/runs/50ae295a) |
48
- | e2d2-w32/113M-6f | 5589 | 171,371,520 | [link](https://wandb.ai/marksmans/dlm/runs/08e38255) |
49
- | e2d2-w32/1233M-100f | 10568 | 1,454,139,904 | [link](https://wandb.ai/marksmans/dlm/runs/c5f45d1c) |
50
- | e2d2-w32/1233M-10f | 1056 | 1,454,139,904 | [link](https://wandb.ai/marksmans/dlm/runs/4efb0469) |
51
- | e2d2-w32/1233M-30f | 3170 | 1,454,139,904 | [link](https://wandb.ai/marksmans/dlm/runs/00a9bd59) |
52
- | e2d2-w32/1233M-60f | 6341 | 1,454,139,904 | [link](https://wandb.ai/marksmans/dlm/runs/be3db3fc) |
53
- | e2d2-w32/1233M-6f | 634 | 1,454,139,904 | [link](https://wandb.ai/marksmans/dlm/runs/b575898c) |
54
- | e2d2-w32/170M-100f | 65485 | 233,316,096 | [link](https://wandb.ai/marksmans/dlm/runs/01826f73) |
55
- | e2d2-w32/170M-10f | 6548 | 233,316,096 | [link](https://wandb.ai/marksmans/dlm/runs/28fd45dc) |
56
- | e2d2-w32/170M-30f | 19645 | 233,316,096 | [link](https://wandb.ai/marksmans/dlm/runs/40a92d11) |
57
- | e2d2-w32/170M-60f | 39291 | 233,316,096 | [link](https://wandb.ai/marksmans/dlm/runs/f74f7cee) |
58
- | e2d2-w32/170M-6f | 3929 | 233,316,096 | [link](https://wandb.ai/marksmans/dlm/runs/a184ee0e) |
59
- | e2d2-w32/336M-100f | 35628 | 427,485,184 | [link](https://wandb.ai/marksmans/dlm/runs/ffae6288) |
60
- | e2d2-w32/336M-10f | 3562 | 427,485,184 | [link](https://wandb.ai/marksmans/dlm/runs/d33eb9bc) |
61
- | e2d2-w32/336M-30f | 10688 | 427,485,184 | [link](https://wandb.ai/marksmans/dlm/runs/0f87ad27) |
62
- | e2d2-w32/336M-60f | 21377 | 427,485,184 | [link](https://wandb.ai/marksmans/dlm/runs/b3974e90) |
63
- | e2d2-w32/336M-6f | 2137 | 427,485,184 | [link](https://wandb.ai/marksmans/dlm/runs/5b007327) |
64
- | e2d2-w32/472M-100f | 26099 | 593,332,480 | [link](https://wandb.ai/marksmans/dlm/runs/e91a392d) |
65
- | e2d2-w32/472M-10f | 2609 | 593,332,480 | [link](https://wandb.ai/marksmans/dlm/runs/da69085d) |
66
- | e2d2-w32/472M-30f | 7829 | 593,332,480 | [link](https://wandb.ai/marksmans/dlm/runs/9f693d22) |
67
- | e2d2-w32/472M-60f | 15659 | 593,332,480 | [link](https://wandb.ai/marksmans/dlm/runs/e4a3dbce) |
68
- | e2d2-w32/472M-6f | 1565 | 593,332,480 | [link](https://wandb.ai/marksmans/dlm/runs/0a0cd474) |
69
- | e2d2-w32/629M-100f | 19844 | 765,386,240 | [link](https://wandb.ai/marksmans/dlm/runs/80c2d366) |
70
- | e2d2-w32/629M-10f | 1984 | 765,386,240 | [link](https://wandb.ai/marksmans/dlm/runs/44bc4b32) |
71
- | e2d2-w32/629M-30f | 5953 | 765,386,240 | [link](https://wandb.ai/marksmans/dlm/runs/63c6beaf) |
72
- | e2d2-w32/629M-60f | 11906 | 765,386,240 | [link](https://wandb.ai/marksmans/dlm/runs/2e6e3a99) |
73
- | e2d2-w32/629M-6f | 1190 | 765,386,240 | [link](https://wandb.ai/marksmans/dlm/runs/73e4645d) |
74
- | e2d2-w32/66M-10f | 14731 | 112,332,160 | [link](https://wandb.ai/marksmans/dlm/runs/a6db8e59) |
75
- | e2d2-w32/66M-30f | 44195 | 112,332,160 | [link](https://wandb.ai/marksmans/dlm/runs/73f36145) |
76
- | e2d2-w32/66M-60f | 88391 | 112,332,160 | [link](https://wandb.ai/marksmans/dlm/runs/054ceaa1) |
77
- | e2d2-w32/66M-6f | 8839 | 112,332,160 | [link](https://wandb.ai/marksmans/dlm/runs/026ef903) |
78
- | e2d2-w32/944M-100f | 13663 | 1,117,827,072 | [link](https://wandb.ai/marksmans/dlm/runs/f6acf2c2) |
79
- | e2d2-w32/944M-10f | 1366 | 1,117,827,072 | [link](https://wandb.ai/marksmans/dlm/runs/78871b0b) |
80
- | e2d2-w32/944M-30f | 4099 | 1,117,827,072 | [link](https://wandb.ai/marksmans/dlm/runs/d6ee574a) |
81
- | e2d2-w32/944M-60f | 8198 | 1,117,827,072 | [link](https://wandb.ai/marksmans/dlm/runs/d320542f) |
82
- | e2d2-w32/944M-6f | 819 | 1,117,827,072 | [link](https://wandb.ai/marksmans/dlm/runs/ef92ff23) |
83
- | e2d2-w4/113M-100f | 95282 | 169,601,280 | [link](https://wandb.ai/marksmans/dlm/runs/cfad7e10) |
84
- | e2d2-w4/113M-10f | 9528 | 169,601,280 | [link](https://wandb.ai/marksmans/dlm/runs/b175d13e) |
85
- | e2d2-w4/113M-30f | 28584 | 169,601,280 | [link](https://wandb.ai/marksmans/dlm/runs/38c38fa0) |
86
- | e2d2-w4/113M-60f | 57169 | 169,601,280 | [link](https://wandb.ai/marksmans/dlm/runs/7b440a0d) |
87
- | e2d2-w4/113M-6f | 5716 | 169,601,280 | [link](https://wandb.ai/marksmans/dlm/runs/b6d49dc6) |
88
- | e2d2-w4/1233M-100f | 10855 | 1,415,597,568 | [link](https://wandb.ai/marksmans/dlm/runs/92cac08a) |
89
- | e2d2-w4/1233M-10f | 1085 | 1,415,597,568 | [link](https://wandb.ai/marksmans/dlm/runs/c7b1cb57) |
90
- | e2d2-w4/1233M-30f | 3256 | 1,415,597,568 | [link](https://wandb.ai/marksmans/dlm/runs/1572ae1c) |
91
- | e2d2-w4/1233M-60f | 6513 | 1,415,597,568 | [link](https://wandb.ai/marksmans/dlm/runs/def9a88a) |
92
- | e2d2-w4/1233M-6f | 651 | 1,415,597,568 | [link](https://wandb.ai/marksmans/dlm/runs/04af57ba) |
93
- | e2d2-w4/170M-100f | 66561 | 229,775,616 | [link](https://wandb.ai/marksmans/dlm/runs/c88f2d5a) |
94
- | e2d2-w4/170M-10f | 6656 | 229,775,616 | [link](https://wandb.ai/marksmans/dlm/runs/a25be5c8) |
95
- | e2d2-w4/170M-30f | 19968 | 229,775,616 | [link](https://wandb.ai/marksmans/dlm/runs/691471a3) |
96
- | e2d2-w4/170M-60f | 39937 | 229,775,616 | [link](https://wandb.ai/marksmans/dlm/runs/44fb1856) |
97
- | e2d2-w4/170M-6f | 3993 | 229,775,616 | [link](https://wandb.ai/marksmans/dlm/runs/79cf6f07) |
98
- | e2d2-w4/336M-100f | 36185 | 421,191,680 | [link](https://wandb.ai/marksmans/dlm/runs/01fe245f) |
99
- | e2d2-w4/336M-10f | 3618 | 421,191,680 | [link](https://wandb.ai/marksmans/dlm/runs/2e211bc7) |
100
- | e2d2-w4/336M-30f | 10855 | 421,191,680 | [link](https://wandb.ai/marksmans/dlm/runs/9724fc66) |
101
- | e2d2-w4/336M-60f | 21711 | 421,191,680 | [link](https://wandb.ai/marksmans/dlm/runs/e8f1ce3b) |
102
- | e2d2-w4/336M-6f | 2171 | 421,191,680 | [link](https://wandb.ai/marksmans/dlm/runs/82c18687) |
103
- | e2d2-w4/472M-100f | 26556 | 583,499,520 | [link](https://wandb.ai/marksmans/dlm/runs/2dcdde1e) |
104
- | e2d2-w4/472M-10f | 2655 | 583,499,520 | [link](https://wandb.ai/marksmans/dlm/runs/bbad7a6c) |
105
- | e2d2-w4/472M-30f | 7966 | 583,499,520 | [link](https://wandb.ai/marksmans/dlm/runs/6fb95b8e) |
106
- | e2d2-w4/472M-60f | 15933 | 583,499,520 | [link](https://wandb.ai/marksmans/dlm/runs/e0eea608) |
107
- | e2d2-w4/472M-6f | 1593 | 583,499,520 | [link](https://wandb.ai/marksmans/dlm/runs/97eab534) |
108
- | e2d2-w4/629M-100f | 20366 | 745,720,320 | [link](https://wandb.ai/marksmans/dlm/runs/bb3818dc) |
109
- | e2d2-w4/629M-10f | 2036 | 745,720,320 | [link](https://wandb.ai/marksmans/dlm/runs/90a96dc0) |
110
- | e2d2-w4/629M-30f | 6109 | 745,720,320 | [link](https://wandb.ai/marksmans/dlm/runs/b47c5e70) |
111
- | e2d2-w4/629M-60f | 12219 | 745,720,320 | [link](https://wandb.ai/marksmans/dlm/runs/b948e3c9) |
112
- | e2d2-w4/629M-6f | 1221 | 745,720,320 | [link](https://wandb.ai/marksmans/dlm/runs/77adc886) |
113
- | e2d2-w4/66M-10f | 15100 | 109,873,280 | [link](https://wandb.ai/marksmans/dlm/runs/2b7d661a) |
114
- | e2d2-w4/66M-30f | 45302 | 109,873,280 | [link](https://wandb.ai/marksmans/dlm/runs/3c7e5536) |
115
- | e2d2-w4/66M-60f | 90605 | 109,873,280 | [link](https://wandb.ai/marksmans/dlm/runs/0aabab12) |
116
- | e2d2-w4/66M-6f | 9060 | 109,873,280 | [link](https://wandb.ai/marksmans/dlm/runs/31e595df) |
117
- | e2d2-w4/944M-100f | 13930 | 1,096,588,800 | [link](https://wandb.ai/marksmans/dlm/runs/6bcba193) |
118
- | e2d2-w4/944M-10f | 1393 | 1,096,588,800 | [link](https://wandb.ai/marksmans/dlm/runs/f6e3fad2) |
119
- | e2d2-w4/944M-30f | 4179 | 1,096,588,800 | [link](https://wandb.ai/marksmans/dlm/runs/b35236a1) |
120
- | e2d2-w4/944M-60f | 8358 | 1,096,588,800 | [link](https://wandb.ai/marksmans/dlm/runs/9bee5c12) |
121
- | e2d2-w4/944M-6f | 835 | 1,096,588,800 | [link](https://wandb.ai/marksmans/dlm/runs/90486546) |
122
- | maskarm/113M-100f | 104137 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/dcbba724) |
123
- | maskarm/113M-10f | 10413 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/fed5724d) |
124
- | maskarm/113M-30f | 31241 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/ccfd0b74) |
125
- | maskarm/113M-60f | 62482 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/f53a9e0c) |
126
- | maskarm/113M-6f | 6248 | 155,437,824 | [link](https://wandb.ai/marksmans/dlm/runs/706c0614) |
127
- | maskarm/1233M-100f | 12083 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/25c96e77) |
128
- | maskarm/1233M-10f | 1208 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/5fd0e102) |
129
- | maskarm/1233M-30f | 3624 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/d46f44f6) |
130
- | maskarm/1233M-60f | 7249 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/61a5a9c8) |
131
- | maskarm/1233M-6f | 724 | 1,271,060,224 | [link](https://wandb.ai/marksmans/dlm/runs/e2aad288) |
132
- | maskarm/170M-100f | 73072 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/03692e1c) |
133
- | maskarm/170M-10f | 7307 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/d6fa6544) |
134
- | maskarm/170M-30f | 21921 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/b5f6f351) |
135
- | maskarm/170M-60f | 43843 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/2facff2f) |
136
- | maskarm/170M-6f | 4384 | 208,531,200 | [link](https://wandb.ai/marksmans/dlm/runs/9ed41f79) |
137
- | maskarm/336M-100f | 40144 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/b0b8b338) |
138
- | maskarm/336M-10f | 4014 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/2fd46801) |
139
- | maskarm/336M-30f | 12043 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/0c08d46e) |
140
- | maskarm/336M-60f | 24086 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/0c974c6c) |
141
- | maskarm/336M-6f | 2408 | 380,281,856 | [link](https://wandb.ai/marksmans/dlm/runs/0bfe33b1) |
142
- | maskarm/472M-100f | 29462 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/bae81779) |
143
- | maskarm/472M-10f | 2946 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/1ab970e1) |
144
- | maskarm/472M-30f | 8838 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/175abc06) |
145
- | maskarm/472M-60f | 17677 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/8b5db358) |
146
- | maskarm/472M-6f | 1767 | 524,499,200 | [link](https://wandb.ai/marksmans/dlm/runs/48230244) |
147
- | maskarm/629M-100f | 22588 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/a1fed9ff) |
148
- | maskarm/629M-10f | 2258 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/5114f700) |
149
- | maskarm/629M-30f | 6776 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/3c2a812f) |
150
- | maskarm/629M-60f | 13553 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/fe50c118) |
151
- | maskarm/629M-6f | 1355 | 671,970,560 | [link](https://wandb.ai/marksmans/dlm/runs/cbe5e716) |
152
- | maskarm/66M-10f | 16241 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/e9951cdc) |
153
- | maskarm/66M-30f | 48724 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/2ca77f8a) |
154
- | maskarm/66M-60f | 97449 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/f73b8bfe) |
155
- | maskarm/66M-6f | 9744 | 102,495,360 | [link](https://wandb.ai/marksmans/dlm/runs/3d72daf7) |
156
- | maskarm/944M-100f | 15467 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/cc51834f) |
157
- | maskarm/944M-10f | 1546 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/208dab87) |
158
- | maskarm/944M-30f | 4640 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/23e134ba) |
159
- | maskarm/944M-60f | 9280 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/01863cb5) |
160
- | maskarm/944M-6f | 928 | 983,314,944 | [link](https://wandb.ai/marksmans/dlm/runs/e84b2d5a) |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
arm/113M-100f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:73337fbffe39b215afdb26bba77e52425464cb3fdd5138f036ad5beee2163ed9
3
- size 310884952
 
 
 
 
arm/113M-100f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/113M-100f",
3
- "run_dir": "arm-113M-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 104137,
5
- "params": 155437824,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/05e8f627"
7
- }
 
 
 
 
 
 
 
 
arm/113M-10f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:78d9d005a29302e352427d73ad55b0003908f41984c8bf2e47eb51a1fe64fe62
3
- size 310884952
 
 
 
 
arm/113M-10f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/113M-10f",
3
- "run_dir": "arm-113M-10.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 10413,
5
- "params": 155437824,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/6267ec3a"
7
- }
 
 
 
 
 
 
 
 
arm/113M-30f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:19187c564ac0b927f14167fe49094559cf9b34969242fab4acfd11f2520fe061
3
- size 310884952
 
 
 
 
arm/113M-30f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/113M-30f",
3
- "run_dir": "arm-113M-30.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 31241,
5
- "params": 155437824,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/2815a9c5"
7
- }
 
 
 
 
 
 
 
 
arm/113M-60f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f29ae614b33723e3734add525662452155a70b04ed5fb16a55b69de69fa27e1
3
- size 310884952
 
 
 
 
arm/113M-60f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/113M-60f",
3
- "run_dir": "arm-113M-60.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 62482,
5
- "params": 155437824,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/19004b12"
7
- }
 
 
 
 
 
 
 
 
arm/113M-6f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eefa2828d54afa5183452bd24035903771ae4a3bf843fc2dcb482f239bfb326
3
- size 310884952
 
 
 
 
arm/113M-6f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/113M-6f",
3
- "run_dir": "arm-113M-6.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 6248,
5
- "params": 155437824,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/7e3c6d2b"
7
- }
 
 
 
 
 
 
 
 
arm/1233M-100f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:577dde70afa34c317489f1e2f41936bef13c3d2d10e19405cfed00d76a2da312
3
- size 2542139296
 
 
 
 
arm/1233M-100f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/1233M-100f",
3
- "run_dir": "arm-1233M-100.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask",
4
- "step": 12083,
5
- "params": 1271060224,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/4e99db0b"
7
- }
 
 
 
 
 
 
 
 
arm/1233M-10f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:486d061a4360c87e02992b0baecf57ab10e59d13a055190b9b81e88a0a23533c
3
- size 2542139296
 
 
 
 
arm/1233M-10f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/1233M-10f",
3
- "run_dir": "arm-1233M-10.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask",
4
- "step": 1208,
5
- "params": 1271060224,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/b2a7f2e4"
7
- }
 
 
 
 
 
 
 
 
arm/1233M-30f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a8c2532cfb5bfc5e5e4fa1b20ae883afd62b333529294cd4d3e53692485fb0e
3
- size 2542139296
 
 
 
 
arm/1233M-30f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/1233M-30f",
3
- "run_dir": "arm-1233M-30.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask",
4
- "step": 3624,
5
- "params": 1271060224,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/317e3d54"
7
- }
 
 
 
 
 
 
 
 
arm/1233M-60f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6717b12ad2d076e8d5233fdee82aa367774ca05ce090d96be5fd718d68787e5
3
- size 2542139296
 
 
 
 
arm/1233M-60f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/1233M-60f",
3
- "run_dir": "arm-1233M-60.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask",
4
- "step": 7249,
5
- "params": 1271060224,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/a576010e"
7
- }
 
 
 
 
 
 
 
 
arm/1233M-6f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dccbb397510169af60c515fe82981a17b4258d375a97a3b213e4ceabbe4e9af
3
- size 2542139296
 
 
 
 
arm/1233M-6f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/1233M-6f",
3
- "run_dir": "arm-1233M-6.0flop-SSSL-qknorm-noaffine-gqa7-n4096-docmask",
4
- "step": 724,
5
- "params": 1271060224,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/81b529e3"
7
- }
 
 
 
 
 
 
 
 
arm/170M-100f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bd001281be0281d91b6ea20336466c94e26b2428a92f90b263837cc2eeb9957
3
- size 417076256
 
 
 
 
arm/170M-100f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/170M-100f",
3
- "run_dir": "arm-170M-100.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 73072,
5
- "params": 208531200,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/96a4f141"
7
- }
 
 
 
 
 
 
 
 
arm/170M-10f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:25518d443375c92a58a3512dc2f6285bda70ca0dd87a446d171ed7f3d655b2d7
3
- size 417076256
 
 
 
 
arm/170M-10f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/170M-10f",
3
- "run_dir": "arm-170M-10.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 7307,
5
- "params": 208531200,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/a681c70c"
7
- }
 
 
 
 
 
 
 
 
arm/170M-30f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5a49915a2cc24442a0ff54bd26c028d38ae750d7949b8c2cf4cc5b058e78bf4
3
- size 417076256
 
 
 
 
arm/170M-30f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/170M-30f",
3
- "run_dir": "arm-170M-30.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 21921,
5
- "params": 208531200,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/733111c7"
7
- }
 
 
 
 
 
 
 
 
arm/170M-60f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:89ccda08cba92cc7bdaa7907439a2d54d9754dfeb9833b6fee4773db409f0a6f
3
- size 417076256
 
 
 
 
arm/170M-60f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/170M-60f",
3
- "run_dir": "arm-170M-60.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 43843,
5
- "params": 208531200,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/546e1184"
7
- }
 
 
 
 
 
 
 
 
arm/170M-6f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:901dd06d5c190465f67827efa2f74aff272b0273b1606b1802f66d9635b94ccb
3
- size 417076256
 
 
 
 
arm/170M-6f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/170M-6f",
3
- "run_dir": "arm-170M-6.0flop-SSSL-qknorm-noaffine-gqa6-n4096-docmask",
4
- "step": 4384,
5
- "params": 208531200,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/2eaee3cb"
7
- }
 
 
 
 
 
 
 
 
arm/336M-100f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ec7bee77ecf759a2c4e03e8547f50c28cedcf1fa51762efd18e08a16e4e8331
3
- size 760579272
 
 
 
 
arm/336M-100f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/336M-100f",
3
- "run_dir": "arm-336M-100.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask",
4
- "step": 40144,
5
- "params": 380281856,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/19b8f681"
7
- }
 
 
 
 
 
 
 
 
arm/336M-10f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:432cb69a3bee1f09733a2e62337c2c6adacc113d796d392ac1821c51b8b5c47c
3
- size 760579272
 
 
 
 
arm/336M-10f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/336M-10f",
3
- "run_dir": "arm-336M-10.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask",
4
- "step": 4014,
5
- "params": 380281856,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/72b6e66a"
7
- }
 
 
 
 
 
 
 
 
arm/336M-30f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf87d29d60735dc3de165be66eb24a9e14e233ac37edaa061a89b342f559a0a6
3
- size 760579272
 
 
 
 
arm/336M-30f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/336M-30f",
3
- "run_dir": "arm-336M-30.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask",
4
- "step": 12043,
5
- "params": 380281856,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/4bbbee37"
7
- }
 
 
 
 
 
 
 
 
arm/336M-60f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0931e813a7722ce340aa9ccc0998dfac23cbf26c555e597e1adfb368b8b10da5
3
- size 760579272
 
 
 
 
arm/336M-60f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/336M-60f",
3
- "run_dir": "arm-336M-60.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask",
4
- "step": 24086,
5
- "params": 380281856,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/b825f0c3"
7
- }
 
 
 
 
 
 
 
 
arm/336M-6f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:153d55f2c545f32f5e35a6b07b17baf70e9cd557e0022364f5fb0ad2b91184d3
3
- size 760579272
 
 
 
 
arm/336M-6f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/336M-6f",
3
- "run_dir": "arm-336M-6.0flop-SSSL-qknorm-noaffine-gqa8-n4096-docmask",
4
- "step": 2408,
5
- "params": 380281856,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/af6cc85a"
7
- }
 
 
 
 
 
 
 
 
arm/472M-100f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:92cc19851c04351f84bc5a13d1032551a18b5f4cd19d5e49245e76e07e81410c
3
- size 1049012432
 
 
 
 
arm/472M-100f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/472M-100f",
3
- "run_dir": "arm-472M-100.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask",
4
- "step": 29462,
5
- "params": 524499200,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/4bd0b799"
7
- }
 
 
 
 
 
 
 
 
arm/472M-10f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:13cc602b5126e417efeeaaa6ad6fbbc76b6d1ecacba2d35675127d3e0f0b7cd6
3
- size 1049012432
 
 
 
 
arm/472M-10f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/472M-10f",
3
- "run_dir": "arm-472M-10.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask",
4
- "step": 2946,
5
- "params": 524499200,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/e444698b"
7
- }
 
 
 
 
 
 
 
 
arm/472M-30f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:40bd8b709952c9fa27ee896c4e5606b5a8c24c64e273996ef8e5ddcd8c045699
3
- size 1049012432
 
 
 
 
arm/472M-30f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/472M-30f",
3
- "run_dir": "arm-472M-30.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask",
4
- "step": 8838,
5
- "params": 524499200,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/988cad3a"
7
- }
 
 
 
 
 
 
 
 
arm/472M-60f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:997398450f6a69c2e4eab78e6b93c9efc3068e15278614bb895ab08e64f696f8
3
- size 1049012432
 
 
 
 
arm/472M-60f/run.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "path": "arm/472M-60f",
3
- "run_dir": "arm-472M-60.0flop-SSSL-qknorm-noaffine-gqa5-n4096-docmask",
4
- "step": 17677,
5
- "params": 524499200,
6
- "wandb": "https://wandb.ai/marksmans/dlm/runs/6ea8aa24"
7
- }
 
 
 
 
 
 
 
 
arm/472M-6f/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6646a7b33c524d2f5a9aaaeae95cade8b296f79419211fe4b6355ccc018e24b
3
- size 1049012432