Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +374 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_12.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_14.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_15.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_9.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_10.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_13.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_1.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_10.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_4.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_8.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_0.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_12.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_10.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_12.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_14.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_15.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_4.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_5.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_10.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_13.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_14.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_2.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_4.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_1.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_10.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_12.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_3.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_4.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_7.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/train/rank0.pt +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/train/rank1.pt +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/train/rank2.pt +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/train/rank3.pt +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/train/rank4.pt +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/train/rank5.pt +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/train/rank6.pt +3 -0
- pretrain/olmo2-600M-10xC-k1/step110000/train/rank7.pt +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_0.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_1.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_10.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_13.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_14.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_15.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_2.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_6.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_7.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_1.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_11.distcp +3 -0
- pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_12.distcp +3 -0
.gitattributes
CHANGED
|
@@ -2597,3 +2597,377 @@ pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_7.distcp filter=lfs d
|
|
| 2597 |
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2598 |
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2599 |
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2597 |
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2598 |
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2599 |
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2600 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2601 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2602 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2603 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2604 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2605 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2606 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2607 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2608 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2609 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2610 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2611 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2612 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2613 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2614 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2615 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2616 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2617 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2618 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2619 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2620 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2621 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2622 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2623 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2624 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2625 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2626 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2627 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2628 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2629 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2630 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2631 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2632 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2633 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2634 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2635 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2636 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2637 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2638 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2639 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2640 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2641 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2642 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2643 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2644 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2645 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2646 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2647 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2648 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2649 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2650 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2651 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2652 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2653 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2654 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2655 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2656 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2657 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2658 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2659 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2660 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2661 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2662 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2663 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2664 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2665 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2666 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2667 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2668 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2669 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2670 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2671 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2672 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2673 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2674 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2675 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2676 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2677 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2678 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2679 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2680 |
+
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2681 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2682 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2683 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2684 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2685 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2686 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2687 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2688 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2689 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2690 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2691 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2692 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2693 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2694 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2695 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2696 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2697 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2698 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2699 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2700 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2701 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2702 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2703 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2704 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2705 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2706 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2707 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2708 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2709 |
+
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2710 |
+
pretrain/olmo2-600M-10xC-k16/step105000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2711 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2712 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2713 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2714 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2715 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2716 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2717 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2718 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2719 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2720 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2721 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2722 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2723 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2724 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2725 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2726 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2727 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2728 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2729 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2730 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2731 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2732 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2733 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2734 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2735 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2736 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2737 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2738 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2739 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2740 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2741 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2742 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2743 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2744 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2745 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2746 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2747 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2748 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2749 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2750 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2751 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2752 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2753 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2754 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2755 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2756 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2757 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2758 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2759 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2760 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2761 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2762 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2763 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2764 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2765 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2766 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2767 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2768 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2769 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2770 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2771 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2772 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2773 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2774 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2775 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2776 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2777 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2778 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2779 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2780 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2781 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2782 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2783 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2784 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2785 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2786 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2787 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2788 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2789 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2790 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2791 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2792 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2793 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2794 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2795 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2796 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2797 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2798 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2799 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2800 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2801 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2802 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2803 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2804 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2805 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2806 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2807 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2808 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2809 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2810 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2811 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2812 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2813 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2814 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 2815 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2816 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2817 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2818 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2819 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2820 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2821 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2822 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2823 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2824 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2825 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2826 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2827 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2828 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2829 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2830 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2831 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2832 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 2833 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2834 |
+
pretrain/olmo2-600M-10xC-k16/step110000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2835 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2836 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2837 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2838 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2839 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2840 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2841 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2842 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2843 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2844 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2845 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2846 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2847 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2848 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2849 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2850 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2851 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2852 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2853 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2854 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2855 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2856 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2857 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2858 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2859 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2860 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2861 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2862 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2863 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2864 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2865 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2866 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2867 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2868 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2869 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2870 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2871 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2872 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2873 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2874 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2875 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2876 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2877 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2878 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2879 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2880 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2881 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2882 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2883 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2884 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2885 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2886 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2887 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2888 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2889 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2890 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2891 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2892 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2893 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2894 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2895 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2896 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2897 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2898 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2899 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2900 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2901 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2902 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2903 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2904 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2905 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2906 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2907 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2908 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2909 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2910 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2911 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2912 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2913 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2914 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_8.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2915 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2916 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2917 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2918 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2919 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2920 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2921 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2922 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2923 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2924 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2925 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2926 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2927 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2928 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2929 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2930 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2931 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2932 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2933 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2934 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_11.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2935 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__5_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2936 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2937 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2938 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2939 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2940 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__2_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2941 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2942 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2943 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2944 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2945 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2946 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2947 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_2.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2948 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2949 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2950 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2951 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_5.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2952 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__0_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2953 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2954 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__4_3.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2955 |
+
pretrain/olmo2-600M-10xC-k16/step100000/model_and_optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2956 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2957 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_10.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2958 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_14.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2959 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2960 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2961 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__4_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2962 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2963 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__2_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2964 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_6.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2965 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_7.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2966 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__0_12.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2967 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__6_15.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2968 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 2969 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__7_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2970 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_9.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2971 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_4.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2972 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__3_13.distcp filter=lfs diff=lfs merge=lfs -text
|
| 2973 |
+
pretrain/olmo2-600M-10xC-k4/step100000/model_and_optim/__5_5.distcp filter=lfs diff=lfs merge=lfs -text
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_12.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfb151945d02c91c5a7a1ef4d25a3383710591d4f6e962d7fd213f5e3a04be45
|
| 3 |
+
size 68863360
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_14.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a0227e1b6668dfa4e70906e16a230b6212de8934e8b442319e1c16f11ab79ed
|
| 3 |
+
size 68863360
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_15.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35c8ca77ad418e1e1f4b609433dd2a67808b05ab38224e3c5b96623a0a8c28c8
|
| 3 |
+
size 68863360
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__0_9.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32a98b05c2f68632112c0d6dc22f259ad115506ad641ec56ad68d18d1d711790
|
| 3 |
+
size 68858629
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_10.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b372245a2bfdc956d2068100e1644cc8fc3852cce097f41898f321b9ecbab260
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__1_13.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2509200eef45cb62565812844fd8d3d733b345ea21bd1deb9d2a1887b1996142
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88d0ae429f0859de96f1ba83ab7c5fcd9afd289ed897dcdc81f919c505d6732d
|
| 3 |
+
size 69247611
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_10.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a7440f503239dc6a30bbed4c462a9c1db439fba58c08f15586ef4a43d15617d
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_4.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8100e390f3d781466e9c71800741bd692e738c3a0e5e36561950921d3886a15b
|
| 3 |
+
size 68451499
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__2_8.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00d487d286b3c2c7ed4968844bc8e7d68d73a84811eb8a8b6bb786cf6f0ba78c
|
| 3 |
+
size 68689655
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbc67741213c7fce24cff49dd2c5844378da48ba3a16b384c0bbd44fd0d4920d
|
| 3 |
+
size 69247611
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__3_12.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ede8d8203b115ca256aa7fa1fa9666185854112b8af64e5d1aad9adf31d4a6cd
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_10.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:785d5d4cfc1e31250c3fbf5c0ce68bd989084d2b3dafddb0348c8101e52861bf
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__4_12.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51c37e5b8379ff220df01958eb9e41e5dffeaa3173998c84157694f191b0f8df
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_14.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:204c4eb55226d579b306d23bb7cd645e092776e76f894050dd67540c5cd6eef6
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_15.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b22dd1129541e25eda702b5cb8b24957c1399282b343c726354c4e6544dfccc9
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_4.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d67fab2de8f4dba2380714b921780aec85916aceff6e770b77013d11f56edeff
|
| 3 |
+
size 68451499
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__5_5.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:638a797ab5018ce16f961e14ba911144517c99d88c8293ec079f13e7d97dd74d
|
| 3 |
+
size 68449282
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_10.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9d8f8c41e30f83c26b277743df7c01720c40c579ba70d50503a538765b8ea5d
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_13.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdc8bfec346d57bf5b22b83c903b8ecf43babf924697acc7bd52db7ba004c0aa
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_14.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ad30b5958d9e7035723e5b38b23f1cfbaa1e989ed8552354982dfb9e9886d6e
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_2.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a72e6909e57a7023a95f978de857aa21ea9dd84cff797c45a64b3de81d70141
|
| 3 |
+
size 68451499
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__6_4.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e9a3a3c12b0dede86157a13f3cbe054f946f2fd73e172c6fb406efa7920636c
|
| 3 |
+
size 68451499
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8da41caead7267580c4d04d227dfa3d569f21a68c65c41a535349c0149ce6d6b
|
| 3 |
+
size 69247611
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_10.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50e3bbb6b437c6f8a4623eb38df2b6f740504aefeec207ef5e0c94e6e3c0f399
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_12.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b11c76e9ebb3edf73e8de110c58d2575a5a3d351c2666a17eaf111565dd3ab88
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_3.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4abed4ced6871ac32fd634a9202df8eb15883ace2d0a870c4ce542ca03ec4c25
|
| 3 |
+
size 68451499
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_4.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:627229f161d2853b997e502b2996928d53bacea2c49105a6ab96f6756b32aff7
|
| 3 |
+
size 68451499
|
pretrain/olmo2-600M-10xC-k1/step110000/model_and_optim/__7_7.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2133236c078c26b91f565bf3129a61acc20b3f0290e36a6f2a5f5048ddd1e87
|
| 3 |
+
size 68689655
|
pretrain/olmo2-600M-10xC-k1/step110000/train/rank0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88b74db2073e474a8f7fc5c0d14b6bc9379ec2d16a7b63d52f2aaeaed28fd03b
|
| 3 |
+
size 15317
|
pretrain/olmo2-600M-10xC-k1/step110000/train/rank1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b8edffcb2e2c534843ad6adf801f6f52dcf9cebbb92c80008695b7c7f76c79d
|
| 3 |
+
size 15317
|
pretrain/olmo2-600M-10xC-k1/step110000/train/rank2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b834f94795a1d5e54887c9210be9c1ca2716b2ac10f08ab56fff1a244d34b22
|
| 3 |
+
size 15317
|
pretrain/olmo2-600M-10xC-k1/step110000/train/rank3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:628d1302765c5924d02532a599a925470eb7844f8e2ac226a198258380cf28e4
|
| 3 |
+
size 15317
|
pretrain/olmo2-600M-10xC-k1/step110000/train/rank4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcc8c3effb091664053e0cb4248e86a4cfe7751e9597d5fabfb7ef82e9186c07
|
| 3 |
+
size 15317
|
pretrain/olmo2-600M-10xC-k1/step110000/train/rank5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0716c0e1aa992269a784d5be1649c4ae61ccf8c75c0fe59f45bfd5b8f90d0c15
|
| 3 |
+
size 15317
|
pretrain/olmo2-600M-10xC-k1/step110000/train/rank6.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bf9b85dca59cd9b9b233110e98d106bd78ac2fee351ffc7b0925b479e93a0e0
|
| 3 |
+
size 15317
|
pretrain/olmo2-600M-10xC-k1/step110000/train/rank7.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbffe68ae5ebe19ae21c46bae28531be1890de7550b4474a7b92238d425728aa
|
| 3 |
+
size 15317
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8da8fc1207f1d6010add5b455acb284388c9734809c9dbdb46ea8883fd936d06
|
| 3 |
+
size 69417846
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d2f2e89222101764eaadc6218c036ec69a53a857ad440229844aa1fd783ebbc
|
| 3 |
+
size 69417846
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_10.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbe1be632890ba30c07a007b5b502a20e61a488b2fcda02c1df1b0fe8b546576
|
| 3 |
+
size 68863360
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_13.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d064a8c4454f14ea0290fd351518cb534f6231c0c7b7371595c00afe353020da
|
| 3 |
+
size 68863360
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_14.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3c342bb0cbd69387a6245e0077a73692732ff9eab854053810fb3428765b3a8
|
| 3 |
+
size 68863360
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_15.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23a86e722fdbb11b6e7571f3ca9110b752a399bae147ab9455d84e9dd2869df0
|
| 3 |
+
size 68863360
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_2.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e04218808c28887102016515abf3c1f5e9a6fda747f903ce82fbd6263b622dc
|
| 3 |
+
size 68621734
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_6.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fe02d2c2c8fbaedf2e2897a4f56fe966a855426a51ca2e7f330d6ef0d963620
|
| 3 |
+
size 68858629
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__0_7.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17eb9cfab7c00ec504fbf6e2a5a559af02bcec785cc6b1f226031e70cca36241
|
| 3 |
+
size 68858629
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47fd955052fd1788ae8a84ea55647b9d8fd730a9f952ec1572e7e951ebdf9a9e
|
| 3 |
+
size 69247611
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_11.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b97c9c0909dae71832c1cb9839b66d7c83c23705a3d3ffe6aebac4feba305f4d
|
| 3 |
+
size 68694386
|
pretrain/olmo2-600M-10xC-k1/step113942/model_and_optim/__1_12.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfa5b314f5cb98f3fa61ae4d270a635787150d65fa564c0a175e72ea757b5a4b
|
| 3 |
+
size 68694386
|