English
n-gram
olmo-core
language-modeling
IanMagnusson commited on
Commit
fb9c7f9
·
verified ·
1 Parent(s): 78c16b9

Add release files (part 2)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +97 -0
  2. model-ladders/count-1b/1B/step16268/model_and_optim/__1_0.distcp +3 -0
  3. model-ladders/count-1b/1B/step16268/model_and_optim/__2_0.distcp +3 -0
  4. model-ladders/count-1b/1B/step16268/model_and_optim/__3_0.distcp +3 -0
  5. model-ladders/count-1b/1B/step16268/model_and_optim/__4_0.distcp +3 -0
  6. model-ladders/count-1b/1B/step16268/model_and_optim/__5_0.distcp +3 -0
  7. model-ladders/count-1b/1B/step16268/model_and_optim/__6_0.distcp +3 -0
  8. model-ladders/count-1b/1B/step16268/model_and_optim/__7_0.distcp +3 -0
  9. model-ladders/count-1b/1B/step16268/model_and_optim/__8_0.distcp +3 -0
  10. model-ladders/count-1b/1B/step16268/model_and_optim/__9_0.distcp +3 -0
  11. model-ladders/count-1b/1B/step16268/release_args.json +13 -0
  12. model-ladders/count-1b/1B/step16268/train/rank0.pt +3 -0
  13. model-ladders/count-1b/1B/step16268/train/rank1.pt +3 -0
  14. model-ladders/count-1b/1B/step16268/train/rank10.pt +3 -0
  15. model-ladders/count-1b/1B/step16268/train/rank11.pt +3 -0
  16. model-ladders/count-1b/1B/step16268/train/rank12.pt +3 -0
  17. model-ladders/count-1b/1B/step16268/train/rank13.pt +3 -0
  18. model-ladders/count-1b/1B/step16268/train/rank14.pt +3 -0
  19. model-ladders/count-1b/1B/step16268/train/rank15.pt +3 -0
  20. model-ladders/count-1b/1B/step16268/train/rank2.pt +3 -0
  21. model-ladders/count-1b/1B/step16268/train/rank3.pt +3 -0
  22. model-ladders/count-1b/1B/step16268/train/rank4.pt +3 -0
  23. model-ladders/count-1b/1B/step16268/train/rank5.pt +3 -0
  24. model-ladders/count-1b/1B/step16268/train/rank6.pt +3 -0
  25. model-ladders/count-1b/1B/step16268/train/rank7.pt +3 -0
  26. model-ladders/count-1b/1B/step16268/train/rank8.pt +3 -0
  27. model-ladders/count-1b/1B/step16268/train/rank9.pt +3 -0
  28. model-ladders/count-1b/1B/step32537/.metadata.json +1 -0
  29. model-ladders/count-1b/1B/step32537/config.json +162 -0
  30. model-ladders/count-1b/1B/step32537/model_and_optim/.metadata +3 -0
  31. model-ladders/count-1b/1B/step32537/model_and_optim/__0_0.distcp +3 -0
  32. model-ladders/count-1b/1B/step32537/model_and_optim/__10_0.distcp +3 -0
  33. model-ladders/count-1b/1B/step32537/model_and_optim/__11_0.distcp +3 -0
  34. model-ladders/count-1b/1B/step32537/model_and_optim/__12_0.distcp +3 -0
  35. model-ladders/count-1b/1B/step32537/model_and_optim/__13_0.distcp +3 -0
  36. model-ladders/count-1b/1B/step32537/model_and_optim/__14_0.distcp +3 -0
  37. model-ladders/count-1b/1B/step32537/model_and_optim/__15_0.distcp +3 -0
  38. model-ladders/count-1b/1B/step32537/model_and_optim/__1_0.distcp +3 -0
  39. model-ladders/count-1b/1B/step32537/model_and_optim/__2_0.distcp +3 -0
  40. model-ladders/count-1b/1B/step32537/model_and_optim/__3_0.distcp +3 -0
  41. model-ladders/count-1b/1B/step32537/model_and_optim/__4_0.distcp +3 -0
  42. model-ladders/count-1b/1B/step32537/model_and_optim/__5_0.distcp +3 -0
  43. model-ladders/count-1b/1B/step32537/model_and_optim/__6_0.distcp +3 -0
  44. model-ladders/count-1b/1B/step32537/model_and_optim/__7_0.distcp +3 -0
  45. model-ladders/count-1b/1B/step32537/model_and_optim/__8_0.distcp +3 -0
  46. model-ladders/count-1b/1B/step32537/model_and_optim/__9_0.distcp +3 -0
  47. model-ladders/count-1b/1B/step32537/release_args.json +13 -0
  48. model-ladders/count-1b/1B/step32537/train/rank0.pt +3 -0
  49. model-ladders/count-1b/1B/step32537/train/rank1.pt +3 -0
  50. model-ladders/count-1b/1B/step32537/train/rank10.pt +3 -0
.gitattributes CHANGED
@@ -245,3 +245,100 @@ model-ladders/count-1b/1B/step16268/model_and_optim/__12_0.distcp filter=lfs dif
245
  model-ladders/count-1b/1B/step16268/model_and_optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
246
  model-ladders/count-1b/1B/step16268/model_and_optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
247
  model-ladders/count-1b/1B/step16268/model_and_optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
245
  model-ladders/count-1b/1B/step16268/model_and_optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
246
  model-ladders/count-1b/1B/step16268/model_and_optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
247
  model-ladders/count-1b/1B/step16268/model_and_optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
248
+ model-ladders/count-1b/1B/step16268/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
249
+ model-ladders/count-1b/1B/step16268/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
250
+ model-ladders/count-1b/1B/step16268/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
251
+ model-ladders/count-1b/1B/step16268/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
252
+ model-ladders/count-1b/1B/step16268/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
253
+ model-ladders/count-1b/1B/step16268/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
254
+ model-ladders/count-1b/1B/step16268/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
255
+ model-ladders/count-1b/1B/step16268/model_and_optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
256
+ model-ladders/count-1b/1B/step16268/model_and_optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
257
+ model-ladders/count-1b/1B/step32537/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
258
+ model-ladders/count-1b/1B/step32537/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
259
+ model-ladders/count-1b/1B/step32537/model_and_optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text
260
+ model-ladders/count-1b/1B/step32537/model_and_optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
261
+ model-ladders/count-1b/1B/step32537/model_and_optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
262
+ model-ladders/count-1b/1B/step32537/model_and_optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
263
+ model-ladders/count-1b/1B/step32537/model_and_optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
264
+ model-ladders/count-1b/1B/step32537/model_and_optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
265
+ model-ladders/count-1b/1B/step32537/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
266
+ model-ladders/count-1b/1B/step32537/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
267
+ model-ladders/count-1b/1B/step32537/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
268
+ model-ladders/count-1b/1B/step32537/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
269
+ model-ladders/count-1b/1B/step32537/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
270
+ model-ladders/count-1b/1B/step32537/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
271
+ model-ladders/count-1b/1B/step32537/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
272
+ model-ladders/count-1b/1B/step32537/model_and_optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
273
+ model-ladders/count-1b/1B/step32537/model_and_optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
274
+ model-ladders/count-1b/1B/step8134/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
275
+ model-ladders/count-1b/1B/step8134/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
276
+ model-ladders/count-1b/1B/step8134/model_and_optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text
277
+ model-ladders/count-1b/1B/step8134/model_and_optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text
278
+ model-ladders/count-1b/1B/step8134/model_and_optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text
279
+ model-ladders/count-1b/1B/step8134/model_and_optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text
280
+ model-ladders/count-1b/1B/step8134/model_and_optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text
281
+ model-ladders/count-1b/1B/step8134/model_and_optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text
282
+ model-ladders/count-1b/1B/step8134/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
283
+ model-ladders/count-1b/1B/step8134/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
284
+ model-ladders/count-1b/1B/step8134/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
285
+ model-ladders/count-1b/1B/step8134/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
286
+ model-ladders/count-1b/1B/step8134/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
287
+ model-ladders/count-1b/1B/step8134/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
288
+ model-ladders/count-1b/1B/step8134/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
289
+ model-ladders/count-1b/1B/step8134/model_and_optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text
290
+ model-ladders/count-1b/1B/step8134/model_and_optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text
291
+ model-ladders/count-370m/370M/step18883/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
292
+ model-ladders/count-370m/370M/step18883/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
293
+ model-ladders/count-370m/370M/step18883/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
294
+ model-ladders/count-370m/370M/step18883/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
295
+ model-ladders/count-370m/370M/step18883/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
296
+ model-ladders/count-370m/370M/step4721/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
297
+ model-ladders/count-370m/370M/step4721/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
298
+ model-ladders/count-370m/370M/step4721/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
299
+ model-ladders/count-370m/370M/step4721/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
300
+ model-ladders/count-370m/370M/step4721/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
301
+ model-ladders/count-370m/370M/step9442/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
302
+ model-ladders/count-370m/370M/step9442/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
303
+ model-ladders/count-370m/370M/step9442/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
304
+ model-ladders/count-370m/370M/step9442/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
305
+ model-ladders/count-370m/370M/step9442/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
306
+ model-ladders/count-600m/600M/step11148/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
307
+ model-ladders/count-600m/600M/step11148/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
308
+ model-ladders/count-600m/600M/step11148/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
309
+ model-ladders/count-600m/600M/step11148/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
310
+ model-ladders/count-600m/600M/step11148/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
311
+ model-ladders/count-600m/600M/step22297/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
312
+ model-ladders/count-600m/600M/step22297/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
313
+ model-ladders/count-600m/600M/step22297/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
314
+ model-ladders/count-600m/600M/step22297/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
315
+ model-ladders/count-600m/600M/step22297/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
316
+ model-ladders/count-600m/600M/step5574/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
317
+ model-ladders/count-600m/600M/step5574/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
318
+ model-ladders/count-600m/600M/step5574/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
319
+ model-ladders/count-600m/600M/step5574/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
320
+ model-ladders/count-600m/600M/step5574/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
321
+ model-ladders/count-60m/60M/step2190/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
322
+ model-ladders/count-60m/60M/step2190/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
323
+ model-ladders/count-60m/60M/step2190/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
324
+ model-ladders/count-60m/60M/step4381/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
325
+ model-ladders/count-60m/60M/step4381/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
326
+ model-ladders/count-60m/60M/step4381/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
327
+ model-ladders/count-60m/60M/step8762/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
328
+ model-ladders/count-60m/60M/step8762/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
329
+ model-ladders/count-60m/60M/step8762/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
330
+ model-ladders/count-760m/760M/step11570/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
331
+ model-ladders/count-760m/760M/step11570/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
332
+ model-ladders/count-760m/760M/step11570/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
333
+ model-ladders/count-760m/760M/step11570/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
334
+ model-ladders/count-760m/760M/step11570/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
335
+ model-ladders/count-760m/760M/step23139/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
336
+ model-ladders/count-760m/760M/step23139/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
337
+ model-ladders/count-760m/760M/step23139/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
338
+ model-ladders/count-760m/760M/step23139/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
339
+ model-ladders/count-760m/760M/step23139/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
340
+ model-ladders/count-760m/760M/step5785/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
341
+ model-ladders/count-760m/760M/step5785/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
342
+ model-ladders/count-760m/760M/step5785/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
343
+ model-ladders/count-760m/760M/step5785/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
344
+ model-ladders/count-760m/760M/step5785/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
model-ladders/count-1b/1B/step16268/model_and_optim/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:522cf8767c0aa3baa5ec37e04da91f0ed2a3edc9f6db1ab65b455946518019f2
3
+ size 1114546935
model-ladders/count-1b/1B/step16268/model_and_optim/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50f99929c7c7a86dcde28ede47c785379a04121505336b75eb00d7aec5c8add
3
+ size 1114546935
model-ladders/count-1b/1B/step16268/model_and_optim/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888716e1f60048e7652ede411ebd8ae789c4717aa80d1905e53a60f4fd29289d
3
+ size 1114546935
model-ladders/count-1b/1B/step16268/model_and_optim/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:367988326492117313a5a9e4da0a35766a432071a92565b0a3f6fe8e286c0008
3
+ size 1114546935
model-ladders/count-1b/1B/step16268/model_and_optim/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33317f9a0d659cf234c1fe2a9beea1bda0f2b3e2eaea22db4f201fe30bf5d71f
3
+ size 1114546935
model-ladders/count-1b/1B/step16268/model_and_optim/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56257ea3568f7bea6678b686f8e48677d377de6f127d6344cd1140f6b9d5936d
3
+ size 1114546935
model-ladders/count-1b/1B/step16268/model_and_optim/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f6cba72f7b9a7d16c8f1c76720ab5e4e074bbb4d74543449428583521810be
3
+ size 1114546935
model-ladders/count-1b/1B/step16268/model_and_optim/__8_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed623bfea53d87c5d3a1809393d1aed06548327b3d9668e9166aba61f82e204
3
+ size 1114546935
model-ladders/count-1b/1B/step16268/model_and_optim/__9_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f493b2d1e85ffa5da3c1830fcee5bcd428c4105622a3c4036da3976265757f
3
+ size 1114546935
model-ladders/count-1b/1B/step16268/release_args.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": "1B",
3
+ "seed": 1042,
4
+ "fixed_global_batch_size": 1572864,
5
+ "sequence_length": 8192,
6
+ "trained_world_size": 16,
7
+ "d_over_n": 20,
8
+ "step": 16268,
9
+ "count_k": 8,
10
+ "count_max_order": 6,
11
+ "count_num_orders": 6,
12
+ "count_table": "general-797gb"
13
+ }
model-ladders/count-1b/1B/step16268/train/rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42832ead1d165df3d0fd45ba8aa74673d8b545a42b1e444b2c0204897d023401
3
+ size 15637
model-ladders/count-1b/1B/step16268/train/rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25fb2dfcfa2dfcf535cbb12f9eb208ad3888133ce40ec950f67ce21faa8975d3
3
+ size 15637
model-ladders/count-1b/1B/step16268/train/rank10.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d468dc101764996bdf790bd2096e1a34ec8cae5267529d7bd73704890d512b3
3
+ size 15645
model-ladders/count-1b/1B/step16268/train/rank11.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb37bfd48e806516e631a374d86876d0639f670ca084c70927181defab5bbda
3
+ size 15645
model-ladders/count-1b/1B/step16268/train/rank12.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3643c4a730e899ae64a8482cfa24a0cf00f5b380b6e11796b3c4a75ca1f0c8
3
+ size 15645
model-ladders/count-1b/1B/step16268/train/rank13.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d464aea1c622744d3cf5ef0ae34c21ab132376170b22e3a3e8e48860fa82bd7
3
+ size 15645
model-ladders/count-1b/1B/step16268/train/rank14.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7beb24b619c8d7ae39d1917a3471d63d8772311072d66899373ba769abd30fd
3
+ size 15645
model-ladders/count-1b/1B/step16268/train/rank15.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c04126af9e3a19b9e24f2dacabfbffe87d7a87658be1b0d2d530514ee0f1e935
3
+ size 15645
model-ladders/count-1b/1B/step16268/train/rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:814b504058f9c4dc6c156ab594a388e5a42ad97a7573c0d3bf609ab55c1ec1ed
3
+ size 15637
model-ladders/count-1b/1B/step16268/train/rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cd9d2da2d5759f95edfb90f01f261a1705405e9de9dae2a12a7ab95020a0e2
3
+ size 15637
model-ladders/count-1b/1B/step16268/train/rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34386ae7d6e4f6e6f6e6f0d7f4064a50c2339e3b41803016f468acec281f9f12
3
+ size 15637
model-ladders/count-1b/1B/step16268/train/rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a79cd991a0be6adca4368aba6cbba7196615a8963731d587f06d7226972aec9
3
+ size 15637
model-ladders/count-1b/1B/step16268/train/rank6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0ff9137f8b9226498de696f2b49c64bf3d26dd6252a42759f80e113b833b2d
3
+ size 15637
model-ladders/count-1b/1B/step16268/train/rank7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04153f529b4fe903379d7edcbfc5c701f358b100e99dae415c674fea1ed5a5d1
3
+ size 15637
model-ladders/count-1b/1B/step16268/train/rank8.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59240366d78a170e0224bd97190cea341bd68fd190cc6c351ab27962f9650a1
3
+ size 15637
model-ladders/count-1b/1B/step16268/train/rank9.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82c57cc6c715b6916d6af784e2694cd5ce33b97f1c69ec405f72d12782d55d7c
3
+ size 15637
model-ladders/count-1b/1B/step32537/.metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"ephemeral": false, "version": "2.5.0"}
model-ladders/count-1b/1B/step32537/config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "seed": 1042,
3
+ "size": "1B",
4
+ "model": {
5
+ "d_model": 2048,
6
+ "vocab_size": 100352,
7
+ "n_layers": 16,
8
+ "block": {
9
+ "sequence_mixer": {
10
+ "name": "default",
11
+ "n_heads": 16,
12
+ "bias": false,
13
+ "rope": {
14
+ "name": "default",
15
+ "theta": 500000,
16
+ "full_precision": true,
17
+ "no_global_rope": false,
18
+ "_CLASS_": "olmo_core.nn.rope.RoPEConfig"
19
+ },
20
+ "qk_norm": {
21
+ "name": "rms",
22
+ "eps": 1e-06,
23
+ "bias": false,
24
+ "dtype": "float32",
25
+ "_CLASS_": "olmo_core.nn.layer_norm.LayerNormConfig"
26
+ },
27
+ "backend": "flash_3",
28
+ "dtype": "float32",
29
+ "use_head_qk_norm": false,
30
+ "_CLASS_": "olmo_core.nn.attention.AttentionConfig",
31
+ "type": "attention"
32
+ },
33
+ "layer_norm": {
34
+ "name": "rms",
35
+ "eps": 1e-06,
36
+ "bias": false,
37
+ "dtype": "float32",
38
+ "_CLASS_": "olmo_core.nn.layer_norm.LayerNormConfig"
39
+ },
40
+ "feed_forward": {
41
+ "hidden_size": 8192,
42
+ "name": "default",
43
+ "bias": false,
44
+ "dtype": "float32",
45
+ "activation": "silu",
46
+ "_CLASS_": "olmo_core.nn.feed_forward.FeedForwardConfig"
47
+ },
48
+ "name": "reordered_norm",
49
+ "_CLASS_": "olmo_core.nn.transformer.config.TransformerBlockConfig"
50
+ },
51
+ "lm_head": {
52
+ "name": "default",
53
+ "layer_norm": {
54
+ "name": "rms",
55
+ "eps": 1e-06,
56
+ "bias": false,
57
+ "dtype": "float32",
58
+ "_CLASS_": "olmo_core.nn.layer_norm.LayerNormConfig"
59
+ },
60
+ "bias": false,
61
+ "dtype": "float32",
62
+ "loss_implementation": "default",
63
+ "_CLASS_": "olmo_core.nn.lm_head.LMHeadConfig"
64
+ },
65
+ "name": "default",
66
+ "dtype": "float32",
67
+ "init_method": "normal",
68
+ "init_seed": 0,
69
+ "init_std": 0.02,
70
+ "_CLASS_": "olmo_core.nn.transformer.config.TransformerConfig"
71
+ },
72
+ "optim": {
73
+ "group_overrides": [
74
+ {
75
+ "params": [
76
+ "embeddings.weight"
77
+ ],
78
+ "opts": {
79
+ "weight_decay": 0.0
80
+ },
81
+ "_CLASS_": "olmo_core.optim.config.OptimGroupOverride"
82
+ }
83
+ ],
84
+ "compile": false,
85
+ "fixed_fields": [
86
+ "initial_lr"
87
+ ],
88
+ "lr": 0.0010308784697907792,
89
+ "betas": [
90
+ 0.9,
91
+ 0.95
92
+ ],
93
+ "eps": 1e-08,
94
+ "weight_decay": 0.1,
95
+ "foreach": true,
96
+ "step_increment_bugfix": true,
97
+ "rolling_interval_length": 128,
98
+ "sigma_factor": 6,
99
+ "_CLASS_": "olmo_core.optim.adamw.SkipStepAdamWConfig",
100
+ "type": "skip_step_adamw"
101
+ },
102
+ "scheduler": {
103
+ "lr_field": "lr",
104
+ "initial_lr_field": "initial_lr",
105
+ "units": "tokens",
106
+ "period_lengths": [
107
+ 12793675776,
108
+ 12793675776,
109
+ 25588924416
110
+ ],
111
+ "warmup": 1279395840,
112
+ "decay_fraction": 0.1,
113
+ "warmup_min_lr": 0.0,
114
+ "decay_min_lr": 0.0,
115
+ "_CLASS_": "olmo_core.optim.scheduler.WSDS",
116
+ "type": "wsds"
117
+ },
118
+ "data_loader": {
119
+ "seed": 0,
120
+ "shuffle": true,
121
+ "sources_per_epoch": -1,
122
+ "num_workers": 16,
123
+ "generate_doc_lengths": false,
124
+ "instance_filter_config": {
125
+ "repetition_max_period": 13,
126
+ "repetition_min_period": 1,
127
+ "repetition_max_count": 32,
128
+ "_CLASS_": "olmo_core.data.composable.data_loader.InstanceFilterConfig"
129
+ },
130
+ "display_source_visualization": true,
131
+ "_CLASS_": "olmo_core.data.composable.data_loader.ComposableDataLoaderConfig",
132
+ "type": "composable"
133
+ },
134
+ "instance_sources": [
135
+ {
136
+ "sources": [
137
+ {
138
+ "tokenizer": {
139
+ "vocab_size": 100278,
140
+ "eos_token_id": 100257,
141
+ "pad_token_id": 100277,
142
+ "identifier": "allenai/dolma2-tokenizer",
143
+ "_CLASS_": "olmo_core.data.tokenizer.TokenizerConfig"
144
+ },
145
+ "source_group_size": 1,
146
+ "long_doc_strategy": "truncate",
147
+ "source_paths": [
148
+ "<data-root>/all-dressed-snazzy2-fixed/**/*.npy",
149
+ "<data-root>/arxiv/**/*.npy",
150
+ "<data-root>/finemath-3plus/**/*.npy",
151
+ "<data-root>/s2pdf/**/*.npy",
152
+ "<data-root>/stack-edu/**/*.npy",
153
+ "<data-root>/wikipedia/**/*.npy"
154
+ ],
155
+ "_CLASS_": "olmo_core.data.composable.numpy_document_source.NumpyDocumentSourceConfig"
156
+ }
157
+ ],
158
+ "sequence_length": 8192,
159
+ "_CLASS_": "olmo_core.data.composable.concat_and_chunk_instance_source.ConcatAndChunkInstanceSourceConfig"
160
+ }
161
+ ]
162
+ }
model-ladders/count-1b/1B/step32537/model_and_optim/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b67b1cbabf26b35c27923de71d56218a35aa0d00d3683762d8aada37daa157
3
+ size 1961340
model-ladders/count-1b/1B/step32537/model_and_optim/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5307e60b32df3e543c53021c8da6b82d61070ea472d67c4378e872c453d3d704
3
+ size 1115973577
model-ladders/count-1b/1B/step32537/model_and_optim/__10_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dbc2556684bf874d7f2639da168380a10d7a8a0d229281828bf13a361e63165
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__11_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef597e1313145251f2da9486cf7b452a76c39e054ef039a335a563f20a0acbb
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__12_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef34efd885ebc1bc86f539dfe43ae8a8549d7172b88008963195a226c59d311c
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__13_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c11c65225f9f11fb382c58f6a166706992adb62f635590ed33e0cd7b8d50de0
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__14_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4120b424e9542ea8d3a95919aa5b04eafe3eb046c50619591838e119891d26e6
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__15_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5ebd8eff07c3a5d5da6bfd16e269dfdd3260c74ed18a031df059bf1b5fa1f00
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1647e0f97ba5f7f799de011b72f6c4b1dcffa66d1b04fa1c565f81b7346bca7f
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb691764c2bf41c80cae2c183896ca2ff83b2ce95593ff08041eaf1546ff53d4
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca6f555ad37b141203625f4814337fd3d60578bbeae8cd58c1f1f3b920b0f72
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55eff1ce44b386f8ca3b44b5bb95d23dfb1cee5cb97da3de209a7eafed9a2c42
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d010deeecff2da2d81dee790698d2ce43de8f7b030b740c273720d39c0c122
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45cb07440221a467be85ac6da81cdaeb0d4feef4087670201a0d08a97b8159a0
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00596d7b52e21b9265c431ca877e98ec7df35b5462c08ead87a63c03e3b99e21
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__8_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e63ac5717f4af5fc458133b5fc8ae629954127be9ee15652226ef535a40c98a
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/model_and_optim/__9_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6940926d976a2716271174fd983ece3b2d50ac1fb477d357aad46b5f4857acf8
3
+ size 1114546935
model-ladders/count-1b/1B/step32537/release_args.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": "1B",
3
+ "seed": 1042,
4
+ "fixed_global_batch_size": 1572864,
5
+ "sequence_length": 8192,
6
+ "trained_world_size": 16,
7
+ "d_over_n": 40,
8
+ "step": 32537,
9
+ "count_k": 8,
10
+ "count_max_order": 6,
11
+ "count_num_orders": 6,
12
+ "count_table": "general-797gb"
13
+ }
model-ladders/count-1b/1B/step32537/train/rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62288d59054b3bb379a7e45eccf4dc9d1a70813c2e9bb8e8b4cb30d601b48bab
3
+ size 15637
model-ladders/count-1b/1B/step32537/train/rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca166a4797f2918aef37ac26e0b70dcce4fcf5f6b3cc79ebf0ff5d2a58efd3e3
3
+ size 15637
model-ladders/count-1b/1B/step32537/train/rank10.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:686605674979701602b6117e2608018be9d7e250d7a981dd1060b860bc430c92
3
+ size 15645