Upload folder using huggingface_hub
Browse files- checkpoints/fst_resume/_checkpoint_log.tsv +224 -0
- checkpoints/fst_resume/epoch_004_step_000010000_tokens_57.1b_val=0.2374.pt +3 -0
- checkpoints/fst_resume/epoch_004_step_000011000_tokens_58b_val=0.2374.pt +3 -0
- checkpoints/fst_resume/epoch_004_step_000012000_tokens_58.8b_val=0.2373.pt +3 -0
- checkpoints/fst_resume/epoch_004_step_000013000_tokens_59.7b_val=0.2373.pt +3 -0
- checkpoints/fst_resume/epoch_004_step_000014000_tokens_60.6b_val=0.2373.pt +3 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000010000_tokens_57.1b_val=0.2374.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000011000_tokens_58b_val=0.2374.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2373.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000013000_tokens_59.7b_val=0.2373.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank0.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank1.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank2.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank3.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank4.txt +0 -0
- checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank5.txt +0 -0
- checkpoints/fst_resume/metrics_summary_epoch4_top5.csv +1 -0
- checkpoints/fst_resume/verification_epoch_004_step_000010000_tokens_57.1b_val=0.2374.txt +8 -0
- checkpoints/fst_resume/verification_epoch_004_step_000011000_tokens_58b_val=0.2374.txt +8 -0
- checkpoints/fst_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2373.txt +8 -0
- checkpoints/fst_resume/verification_epoch_004_step_000013000_tokens_59.7b_val=0.2373.txt +8 -0
- checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373.txt +8 -0
- checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank0.txt +5 -0
- checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank1.txt +5 -0
- checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank2.txt +5 -0
- checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank3.txt +5 -0
- checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank4.txt +5 -0
- checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank5.txt +5 -0
checkpoints/fst_resume/_checkpoint_log.tsv
ADDED
|
@@ -0,0 +1,224 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Time Checkpoint_Type Epoch Step Train_Loss Val_Loss Tokens_Trained
|
| 2 |
+
2025-12-11 12:04:15 recent 000 000001000 0.3439227119088173 0.3244720697402954 860160000
|
| 3 |
+
2025-12-11 12:04:16 step 000 000001000 0.3439227119088173 0.3244720697402954 860160000
|
| 4 |
+
2025-12-11 12:04:18 best 000 000001000 0.3439227119088173 0.3244720697402954 860160000
|
| 5 |
+
2025-12-11 12:18:46 recent 000 000002000 0.30961067974567413 0.3051096796989441 1720320000
|
| 6 |
+
2025-12-11 12:18:48 step 000 000002000 0.30961067974567413 0.3051096796989441 1720320000
|
| 7 |
+
2025-12-11 12:18:49 best 000 000002000 0.30961067974567413 0.3051096796989441 1720320000
|
| 8 |
+
2025-12-11 12:33:26 recent 000 000003000 0.3056980222463608 0.29670092463493347 2580480000
|
| 9 |
+
2025-12-11 12:33:28 step 000 000003000 0.3056980222463608 0.29670092463493347 2580480000
|
| 10 |
+
2025-12-11 12:33:30 best 000 000003000 0.3056980222463608 0.29670092463493347 2580480000
|
| 11 |
+
2025-12-11 12:48:06 recent 000 000004000 0.3108784258365631 0.29011571407318115 3440640000
|
| 12 |
+
2025-12-11 12:48:07 step 000 000004000 0.3108784258365631 0.29011571407318115 3440640000
|
| 13 |
+
2025-12-11 12:48:09 best 000 000004000 0.3108784258365631 0.29011571407318115 3440640000
|
| 14 |
+
2025-12-11 13:02:43 recent 000 000005000 0.2862788438796997 0.2865026295185089 4300800000
|
| 15 |
+
2025-12-11 13:02:45 step 000 000005000 0.2862788438796997 0.2865026295185089 4300800000
|
| 16 |
+
2025-12-11 13:02:47 best 000 000005000 0.2862788438796997 0.2865026295185089 4300800000
|
| 17 |
+
2025-12-11 13:17:18 recent 000 000006000 0.2902119755744934 0.2830173671245575 5160960000
|
| 18 |
+
2025-12-11 13:17:19 step 000 000006000 0.2902119755744934 0.2830173671245575 5160960000
|
| 19 |
+
2025-12-11 13:17:21 best 000 000006000 0.2902119755744934 0.2830173671245575 5160960000
|
| 20 |
+
2025-12-11 13:31:52 recent 000 000007000 0.2733738273382187 0.2810177505016327 6021120000
|
| 21 |
+
2025-12-11 13:31:54 step 000 000007000 0.2733738273382187 0.2810177505016327 6021120000
|
| 22 |
+
2025-12-11 13:31:55 best 000 000007000 0.2733738273382187 0.2810177505016327 6021120000
|
| 23 |
+
2025-12-11 13:46:31 recent 000 000008000 0.2640279680490494 0.2785384953022003 6881280000
|
| 24 |
+
2025-12-11 13:46:33 step 000 000008000 0.2640279680490494 0.2785384953022003 6881280000
|
| 25 |
+
2025-12-11 13:46:35 best 000 000008000 0.2640279680490494 0.2785384953022003 6881280000
|
| 26 |
+
2025-12-11 14:01:10 recent 000 000009000 0.29455964267253876 0.27658748626708984 7741440000
|
| 27 |
+
2025-12-11 14:01:12 step 000 000009000 0.29455964267253876 0.27658748626708984 7741440000
|
| 28 |
+
2025-12-11 14:01:13 best 000 000009000 0.29455964267253876 0.27658748626708984 7741440000
|
| 29 |
+
2025-12-11 14:15:49 recent 000 000010000 0.2957393601536751 0.2751111090183258 8601600000
|
| 30 |
+
2025-12-11 14:15:51 step 000 000010000 0.2957393601536751 0.2751111090183258 8601600000
|
| 31 |
+
2025-12-11 14:15:52 best 000 000010000 0.2957393601536751 0.2751111090183258 8601600000
|
| 32 |
+
2025-12-11 14:30:22 recent 000 000011000 0.2893889471888542 0.27389711141586304 9461760000
|
| 33 |
+
2025-12-11 14:30:23 step 000 000011000 0.2893889471888542 0.27389711141586304 9461760000
|
| 34 |
+
2025-12-11 14:30:25 best 000 000011000 0.2893889471888542 0.27389711141586304 9461760000
|
| 35 |
+
2025-12-11 14:45:00 recent 000 000012000 0.31310197710990906 0.2722736597061157 10321920000
|
| 36 |
+
2025-12-11 14:45:02 step 000 000012000 0.31310197710990906 0.2722736597061157 10321920000
|
| 37 |
+
2025-12-11 14:45:03 best 000 000012000 0.31310197710990906 0.2722736597061157 10321920000
|
| 38 |
+
2025-12-11 14:59:39 recent 000 000013000 0.27358604967594147 0.2708395719528198 11182080000
|
| 39 |
+
2025-12-11 14:59:41 step 000 000013000 0.27358604967594147 0.2708395719528198 11182080000
|
| 40 |
+
2025-12-11 14:59:42 best 000 000013000 0.27358604967594147 0.2708395719528198 11182080000
|
| 41 |
+
2025-12-11 15:14:17 recent 000 000014000 0.2762528583407402 0.2696157395839691 12042240000
|
| 42 |
+
2025-12-11 15:14:19 step 000 000014000 0.2762528583407402 0.2696157395839691 12042240000
|
| 43 |
+
2025-12-11 15:14:21 best 000 000014000 0.2762528583407402 0.2696157395839691 12042240000
|
| 44 |
+
2025-12-11 15:16:39 recent 001 000000000 0.2907368093729019 0.2694391906261444 12129976320
|
| 45 |
+
2025-12-11 15:16:41 epoch 001 000000000 0.2907368093729019 0.2694391906261444 12129976320
|
| 46 |
+
2025-12-11 15:16:42 best 001 000000000 0.2907368093729019 0.2694391906261444 12129976320
|
| 47 |
+
2025-12-11 15:31:19 recent 001 000001000 0.276254840195179 0.2685832977294922 12990136320
|
| 48 |
+
2025-12-11 15:31:20 step 001 000001000 0.276254840195179 0.2685832977294922 12990136320
|
| 49 |
+
2025-12-11 15:31:22 best 001 000001000 0.276254840195179 0.2685832977294922 12990136320
|
| 50 |
+
2025-12-11 15:45:51 recent 001 000002000 0.27662599086761475 0.2673291862010956 13850296320
|
| 51 |
+
2025-12-11 15:45:52 step 001 000002000 0.27662599086761475 0.2673291862010956 13850296320
|
| 52 |
+
2025-12-11 15:45:54 best 001 000002000 0.27662599086761475 0.2673291862010956 13850296320
|
| 53 |
+
2025-12-11 16:00:28 recent 001 000003000 0.26816731691360474 0.2670857310295105 14710456320
|
| 54 |
+
2025-12-11 16:00:29 step 001 000003000 0.26816731691360474 0.2670857310295105 14710456320
|
| 55 |
+
2025-12-11 16:00:31 best 001 000003000 0.26816731691360474 0.2670857310295105 14710456320
|
| 56 |
+
2025-12-11 16:15:06 recent 001 000004000 0.2897113338112831 0.2655026614665985 15570616320
|
| 57 |
+
2025-12-11 16:15:08 step 001 000004000 0.2897113338112831 0.2655026614665985 15570616320
|
| 58 |
+
2025-12-11 16:15:09 best 001 000004000 0.2897113338112831 0.2655026614665985 15570616320
|
| 59 |
+
2025-12-11 16:29:45 recent 001 000005000 0.27645236253738403 0.2644156217575073 16430776320
|
| 60 |
+
2025-12-11 16:29:47 step 001 000005000 0.27645236253738403 0.2644156217575073 16430776320
|
| 61 |
+
2025-12-11 16:29:48 best 001 000005000 0.27645236253738403 0.2644156217575073 16430776320
|
| 62 |
+
2025-12-11 16:44:19 recent 001 000006000 0.25979746878147125 0.26352187991142273 17290936320
|
| 63 |
+
2025-12-11 16:44:21 step 001 000006000 0.25979746878147125 0.26352187991142273 17290936320
|
| 64 |
+
2025-12-11 16:44:22 best 001 000006000 0.25979746878147125 0.26352187991142273 17290936320
|
| 65 |
+
2025-12-11 16:58:55 recent 001 000007000 0.2774749845266342 0.2626994550228119 18151096320
|
| 66 |
+
2025-12-11 16:58:57 step 001 000007000 0.2774749845266342 0.2626994550228119 18151096320
|
| 67 |
+
2025-12-11 16:58:59 best 001 000007000 0.2774749845266342 0.2626994550228119 18151096320
|
| 68 |
+
2025-12-11 17:13:33 recent 001 000008000 0.2860962301492691 0.2617444396018982 19011256320
|
| 69 |
+
2025-12-11 17:13:35 step 001 000008000 0.2860962301492691 0.2617444396018982 19011256320
|
| 70 |
+
2025-12-11 17:13:36 best 001 000008000 0.2860962301492691 0.2617444396018982 19011256320
|
| 71 |
+
2025-12-11 17:28:13 recent 001 000009000 0.25598638504743576 0.26100030541419983 19871416320
|
| 72 |
+
2025-12-11 17:28:14 step 001 000009000 0.25598638504743576 0.26100030541419983 19871416320
|
| 73 |
+
2025-12-11 17:28:16 best 001 000009000 0.25598638504743576 0.26100030541419983 19871416320
|
| 74 |
+
2025-12-11 17:42:52 recent 001 000010000 0.28342578560113907 0.26024317741394043 20731576320
|
| 75 |
+
2025-12-11 17:42:53 step 001 000010000 0.28342578560113907 0.26024317741394043 20731576320
|
| 76 |
+
2025-12-11 17:42:55 best 001 000010000 0.28342578560113907 0.26024317741394043 20731576320
|
| 77 |
+
2025-12-11 17:57:24 recent 001 000011000 0.2861173525452614 0.259305864572525 21591736320
|
| 78 |
+
2025-12-11 17:57:26 step 001 000011000 0.2861173525452614 0.259305864572525 21591736320
|
| 79 |
+
2025-12-11 17:57:28 best 001 000011000 0.2861173525452614 0.259305864572525 21591736320
|
| 80 |
+
2025-12-11 18:12:03 recent 001 000012000 0.2670879513025284 0.25852206349372864 22451896320
|
| 81 |
+
2025-12-11 18:12:05 step 001 000012000 0.2670879513025284 0.25852206349372864 22451896320
|
| 82 |
+
2025-12-11 18:12:06 best 001 000012000 0.2670879513025284 0.25852206349372864 22451896320
|
| 83 |
+
2025-12-11 18:26:42 recent 001 000013000 0.2744786664843559 0.2578280568122864 23312056320
|
| 84 |
+
2025-12-11 18:26:43 step 001 000013000 0.2744786664843559 0.2578280568122864 23312056320
|
| 85 |
+
2025-12-11 18:26:45 best 001 000013000 0.2744786664843559 0.2578280568122864 23312056320
|
| 86 |
+
2025-12-11 18:41:21 recent 001 000014000 0.2746414467692375 0.2572340965270996 24172216320
|
| 87 |
+
2025-12-11 18:41:23 step 001 000014000 0.2746414467692375 0.2572340965270996 24172216320
|
| 88 |
+
2025-12-11 18:41:24 best 001 000014000 0.2746414467692375 0.2572340965270996 24172216320
|
| 89 |
+
2025-12-11 18:43:34 recent 002 000000000 0.27967356890439987 0.25697261095046997 24259952640
|
| 90 |
+
2025-12-11 18:43:35 epoch 002 000000000 0.27967356890439987 0.25697261095046997 24259952640
|
| 91 |
+
2025-12-11 18:43:37 best 002 000000000 0.27967356890439987 0.25697261095046997 24259952640
|
| 92 |
+
2025-12-11 18:58:13 recent 002 000001000 0.24822090566158295 0.25578463077545166 25120112640
|
| 93 |
+
2025-12-11 18:58:15 step 002 000001000 0.24822090566158295 0.25578463077545166 25120112640
|
| 94 |
+
2025-12-11 18:58:16 best 002 000001000 0.24822090566158295 0.25578463077545166 25120112640
|
| 95 |
+
2025-12-11 19:12:46 recent 002 000002000 0.2794698253273964 0.25524935126304626 25980272640
|
| 96 |
+
2025-12-11 19:12:47 step 002 000002000 0.2794698253273964 0.25524935126304626 25980272640
|
| 97 |
+
2025-12-11 19:12:49 best 002 000002000 0.2794698253273964 0.25524935126304626 25980272640
|
| 98 |
+
2025-12-11 19:27:24 recent 002 000003000 0.25624027103185654 0.2544611990451813 26840432640
|
| 99 |
+
2025-12-11 19:27:25 step 002 000003000 0.25624027103185654 0.2544611990451813 26840432640
|
| 100 |
+
2025-12-11 19:27:27 best 002 000003000 0.25624027103185654 0.2544611990451813 26840432640
|
| 101 |
+
2025-12-11 19:42:03 recent 002 000004000 0.25411998480558395 0.25379055738449097 27700592640
|
| 102 |
+
2025-12-11 19:42:04 step 002 000004000 0.25411998480558395 0.25379055738449097 27700592640
|
| 103 |
+
2025-12-11 19:42:06 best 002 000004000 0.25411998480558395 0.25379055738449097 27700592640
|
| 104 |
+
2025-12-11 19:56:41 recent 002 000005000 0.27206335216760635 0.25304773449897766 28560752640
|
| 105 |
+
2025-12-11 19:56:43 step 002 000005000 0.27206335216760635 0.25304773449897766 28560752640
|
| 106 |
+
2025-12-11 19:56:45 best 002 000005000 0.27206335216760635 0.25304773449897766 28560752640
|
| 107 |
+
2025-12-11 20:11:14 recent 002 000006000 0.259377621114254 0.25215402245521545 29420912640
|
| 108 |
+
2025-12-11 20:11:16 step 002 000006000 0.259377621114254 0.25215402245521545 29420912640
|
| 109 |
+
2025-12-11 20:11:18 best 002 000006000 0.259377621114254 0.25215402245521545 29420912640
|
| 110 |
+
2025-12-11 20:25:54 recent 002 000007000 0.259706512093544 0.251708060503006 30281072640
|
| 111 |
+
2025-12-11 20:25:56 step 002 000007000 0.259706512093544 0.251708060503006 30281072640
|
| 112 |
+
2025-12-11 20:25:57 best 002 000007000 0.259706512093544 0.251708060503006 30281072640
|
| 113 |
+
2025-12-11 20:40:32 recent 002 000008000 0.2519996836781502 0.251171350479126 31141232640
|
| 114 |
+
2025-12-11 20:40:34 step 002 000008000 0.2519996836781502 0.251171350479126 31141232640
|
| 115 |
+
2025-12-11 20:40:36 best 002 000008000 0.2519996836781502 0.251171350479126 31141232640
|
| 116 |
+
2025-12-11 20:55:11 recent 002 000009000 0.2465052455663681 0.2502414286136627 32001392640
|
| 117 |
+
2025-12-11 20:55:12 step 002 000009000 0.2465052455663681 0.2502414286136627 32001392640
|
| 118 |
+
2025-12-11 20:55:14 best 002 000009000 0.2465052455663681 0.2502414286136627 32001392640
|
| 119 |
+
2025-12-11 21:09:51 recent 002 000010000 0.2524038702249527 0.24950461089611053 32861552640
|
| 120 |
+
2025-12-11 21:09:52 step 002 000010000 0.2524038702249527 0.24950461089611053 32861552640
|
| 121 |
+
2025-12-11 21:09:54 best 002 000010000 0.2524038702249527 0.24950461089611053 32861552640
|
| 122 |
+
2025-12-11 21:24:23 recent 002 000011000 0.2638489082455635 0.2491004317998886 33721712640
|
| 123 |
+
2025-12-11 21:24:24 step 002 000011000 0.2638489082455635 0.2491004317998886 33721712640
|
| 124 |
+
2025-12-11 21:24:26 best 002 000011000 0.2638489082455635 0.2491004317998886 33721712640
|
| 125 |
+
2025-12-11 21:39:01 recent 002 000012000 0.2622009664773941 0.24844156205654144 34581872640
|
| 126 |
+
2025-12-11 21:39:03 step 002 000012000 0.2622009664773941 0.24844156205654144 34581872640
|
| 127 |
+
2025-12-11 21:39:05 best 002 000012000 0.2622009664773941 0.24844156205654144 34581872640
|
| 128 |
+
2025-12-11 21:53:40 recent 002 000013000 0.25010908395051956 0.2477104663848877 35442032640
|
| 129 |
+
2025-12-11 21:53:41 step 002 000013000 0.25010908395051956 0.2477104663848877 35442032640
|
| 130 |
+
2025-12-11 21:53:43 best 002 000013000 0.25010908395051956 0.2477104663848877 35442032640
|
| 131 |
+
2025-12-11 22:08:17 recent 002 000014000 0.26374630630016327 0.2470189332962036 36302192640
|
| 132 |
+
2025-12-11 22:08:18 step 002 000014000 0.26374630630016327 0.2470189332962036 36302192640
|
| 133 |
+
2025-12-11 22:08:20 best 002 000014000 0.26374630630016327 0.2470189332962036 36302192640
|
| 134 |
+
2025-12-11 22:10:30 recent 003 000000000 0.24965786933898926 0.24705520272254944 36389928960
|
| 135 |
+
2025-12-11 22:10:31 epoch 003 000000000 0.24965786933898926 0.24705520272254944 36389928960
|
| 136 |
+
2025-12-11 22:25:04 recent 003 000001000 0.25500255823135376 0.2462674379348755 37250088960
|
| 137 |
+
2025-12-11 22:25:06 step 003 000001000 0.25500255823135376 0.2462674379348755 37250088960
|
| 138 |
+
2025-12-11 22:25:07 best 003 000001000 0.25500255823135376 0.2462674379348755 37250088960
|
| 139 |
+
2025-12-11 22:39:39 recent 003 000002000 0.25009287148714066 0.24551482498645782 38110248960
|
| 140 |
+
2025-12-11 22:39:41 step 003 000002000 0.25009287148714066 0.24551482498645782 38110248960
|
| 141 |
+
2025-12-11 22:39:43 best 003 000002000 0.25009287148714066 0.24551482498645782 38110248960
|
| 142 |
+
2025-12-11 22:54:18 recent 003 000003000 0.2639870420098305 0.2450481802225113 38970408960
|
| 143 |
+
2025-12-11 22:54:20 step 003 000003000 0.2639870420098305 0.2450481802225113 38970408960
|
| 144 |
+
2025-12-11 22:54:22 best 003 000003000 0.2639870420098305 0.2450481802225113 38970408960
|
| 145 |
+
2025-12-11 23:08:56 recent 003 000004000 0.2620629668235779 0.24448950588703156 39830568960
|
| 146 |
+
2025-12-11 23:08:58 step 003 000004000 0.2620629668235779 0.24448950588703156 39830568960
|
| 147 |
+
2025-12-11 23:09:00 best 003 000004000 0.2620629668235779 0.24448950588703156 39830568960
|
| 148 |
+
2025-12-11 23:23:35 recent 003 000005000 0.24179238826036453 0.24389499425888062 40690728960
|
| 149 |
+
2025-12-11 23:23:37 step 003 000005000 0.24179238826036453 0.24389499425888062 40690728960
|
| 150 |
+
2025-12-11 23:23:38 best 003 000005000 0.24179238826036453 0.24389499425888062 40690728960
|
| 151 |
+
2025-12-11 23:38:07 recent 003 000006000 0.25250081717967987 0.2433004230260849 41550888960
|
| 152 |
+
2025-12-11 23:38:09 step 003 000006000 0.25250081717967987 0.2433004230260849 41550888960
|
| 153 |
+
2025-12-11 23:38:10 best 003 000006000 0.25250081717967987 0.2433004230260849 41550888960
|
| 154 |
+
2025-12-11 23:52:46 recent 003 000007000 0.25653084367513657 0.2427988201379776 42411048960
|
| 155 |
+
2025-12-11 23:52:47 step 003 000007000 0.25653084367513657 0.2427988201379776 42411048960
|
| 156 |
+
2025-12-11 23:52:49 best 003 000007000 0.25653084367513657 0.2427988201379776 42411048960
|
| 157 |
+
2025-12-12 00:07:25 recent 003 000008000 0.26132817566394806 0.24230463802814484 43271208960
|
| 158 |
+
2025-12-12 00:07:27 step 003 000008000 0.26132817566394806 0.24230463802814484 43271208960
|
| 159 |
+
2025-12-12 00:07:28 best 003 000008000 0.26132817566394806 0.24230463802814484 43271208960
|
| 160 |
+
2025-12-12 00:22:03 recent 003 000009000 0.2560388073325157 0.24174869060516357 44131368960
|
| 161 |
+
2025-12-12 00:22:05 step 003 000009000 0.2560388073325157 0.24174869060516357 44131368960
|
| 162 |
+
2025-12-12 00:22:07 best 003 000009000 0.2560388073325157 0.24174869060516357 44131368960
|
| 163 |
+
2025-12-12 00:36:41 recent 003 000010000 0.24657387286424637 0.24143913388252258 44991528960
|
| 164 |
+
2025-12-12 00:36:43 step 003 000010000 0.24657387286424637 0.24143913388252258 44991528960
|
| 165 |
+
2025-12-12 00:36:44 best 003 000010000 0.24657387286424637 0.24143913388252258 44991528960
|
| 166 |
+
2025-12-12 00:51:16 recent 003 000011000 0.26763254404067993 0.24073179066181183 45851688960
|
| 167 |
+
2025-12-12 00:51:17 step 003 000011000 0.26763254404067993 0.24073179066181183 45851688960
|
| 168 |
+
2025-12-12 00:51:19 best 003 000011000 0.26763254404067993 0.24073179066181183 45851688960
|
| 169 |
+
2025-12-12 01:05:54 recent 003 000012000 0.2579295039176941 0.24037586152553558 46711848960
|
| 170 |
+
2025-12-12 01:05:56 step 003 000012000 0.2579295039176941 0.24037586152553558 46711848960
|
| 171 |
+
2025-12-12 01:05:58 best 003 000012000 0.2579295039176941 0.24037586152553558 46711848960
|
| 172 |
+
2025-12-12 01:20:33 recent 003 000013000 0.24819885194301605 0.23997525870800018 47572008960
|
| 173 |
+
2025-12-12 01:20:35 step 003 000013000 0.24819885194301605 0.23997525870800018 47572008960
|
| 174 |
+
2025-12-12 01:20:37 best 003 000013000 0.24819885194301605 0.23997525870800018 47572008960
|
| 175 |
+
2025-12-12 01:35:10 recent 003 000014000 0.2604087218642235 0.23958879709243774 48432168960
|
| 176 |
+
2025-12-12 01:35:12 step 003 000014000 0.2604087218642235 0.23958879709243774 48432168960
|
| 177 |
+
2025-12-12 01:35:14 best 003 000014000 0.2604087218642235 0.23958879709243774 48432168960
|
| 178 |
+
2025-12-12 01:37:23 recent 004 000000000 0.2494329959154129 0.23956745862960815 48519905280
|
| 179 |
+
2025-12-12 01:37:25 epoch 004 000000000 0.2494329959154129 0.23956745862960815 48519905280
|
| 180 |
+
2025-12-12 01:37:27 best 004 000000000 0.2494329959154129 0.23956745862960815 48519905280
|
| 181 |
+
2025-12-12 01:52:01 recent 004 000001000 0.23722759634256363 0.2391868233680725 49380065280
|
| 182 |
+
2025-12-12 01:52:02 step 004 000001000 0.23722759634256363 0.2391868233680725 49380065280
|
| 183 |
+
2025-12-12 01:52:04 best 004 000001000 0.23722759634256363 0.2391868233680725 49380065280
|
| 184 |
+
2025-12-12 02:06:35 recent 004 000002000 0.2478501945734024 0.23878975212574005 50240225280
|
| 185 |
+
2025-12-12 02:06:37 step 004 000002000 0.2478501945734024 0.23878975212574005 50240225280
|
| 186 |
+
2025-12-12 02:06:39 best 004 000002000 0.2478501945734024 0.23878975212574005 50240225280
|
| 187 |
+
2025-12-12 02:21:13 recent 004 000003000 0.25706008821725845 0.23859435319900513 51100385280
|
| 188 |
+
2025-12-12 02:21:14 step 004 000003000 0.25706008821725845 0.23859435319900513 51100385280
|
| 189 |
+
2025-12-12 02:21:16 best 004 000003000 0.25706008821725845 0.23859435319900513 51100385280
|
| 190 |
+
2025-12-12 02:35:50 recent 004 000004000 0.2420676127076149 0.2383161336183548 51960545280
|
| 191 |
+
2025-12-12 02:35:52 step 004 000004000 0.2420676127076149 0.2383161336183548 51960545280
|
| 192 |
+
2025-12-12 02:35:53 best 004 000004000 0.2420676127076149 0.2383161336183548 51960545280
|
| 193 |
+
2025-12-12 02:50:28 recent 004 000005000 0.257579542696476 0.23810502886772156 52820705280
|
| 194 |
+
2025-12-12 02:50:29 step 004 000005000 0.257579542696476 0.23810502886772156 52820705280
|
| 195 |
+
2025-12-12 02:50:31 best 004 000005000 0.257579542696476 0.23810502886772156 52820705280
|
| 196 |
+
2025-12-12 03:05:00 recent 004 000006000 0.23875396698713303 0.2378847599029541 53680865280
|
| 197 |
+
2025-12-12 03:05:02 step 004 000006000 0.23875396698713303 0.2378847599029541 53680865280
|
| 198 |
+
2025-12-12 03:05:03 best 004 000006000 0.23875396698713303 0.2378847599029541 53680865280
|
| 199 |
+
2025-12-12 03:19:40 recent 004 000007000 0.2411988377571106 0.237748384475708 54541025280
|
| 200 |
+
2025-12-12 03:19:41 step 004 000007000 0.2411988377571106 0.237748384475708 54541025280
|
| 201 |
+
2025-12-12 03:19:43 best 004 000007000 0.2411988377571106 0.237748384475708 54541025280
|
| 202 |
+
2025-12-12 03:34:18 recent 004 000008000 0.25034378468990326 0.2375868260860443 55401185280
|
| 203 |
+
2025-12-12 03:34:19 step 004 000008000 0.25034378468990326 0.2375868260860443 55401185280
|
| 204 |
+
2025-12-12 03:34:21 best 004 000008000 0.25034378468990326 0.2375868260860443 55401185280
|
| 205 |
+
2025-12-12 03:48:57 recent 004 000009000 0.25600236654281616 0.23750117421150208 56261345280
|
| 206 |
+
2025-12-12 03:48:59 step 004 000009000 0.25600236654281616 0.23750117421150208 56261345280
|
| 207 |
+
2025-12-12 03:49:01 best 004 000009000 0.25600236654281616 0.23750117421150208 56261345280
|
| 208 |
+
2025-12-12 04:03:32 recent 004 000010000 0.2378641739487648 0.23743970692157745 57121505280
|
| 209 |
+
2025-12-12 04:03:34 step 004 000010000 0.2378641739487648 0.23743970692157745 57121505280
|
| 210 |
+
2025-12-12 04:03:36 best 004 000010000 0.2378641739487648 0.23743970692157745 57121505280
|
| 211 |
+
2025-12-12 04:18:07 recent 004 000011000 0.24954141676425934 0.2373601794242859 57981665280
|
| 212 |
+
2025-12-12 04:18:09 step 004 000011000 0.24954141676425934 0.2373601794242859 57981665280
|
| 213 |
+
2025-12-12 04:18:10 best 004 000011000 0.24954141676425934 0.2373601794242859 57981665280
|
| 214 |
+
2025-12-12 04:32:46 recent 004 000012000 0.24604463577270508 0.23732398450374603 58841825280
|
| 215 |
+
2025-12-12 04:32:48 step 004 000012000 0.24604463577270508 0.23732398450374603 58841825280
|
| 216 |
+
2025-12-12 04:32:49 best 004 000012000 0.24604463577270508 0.23732398450374603 58841825280
|
| 217 |
+
2025-12-12 04:47:25 recent 004 000013000 0.24328067898750305 0.23732741177082062 59701985280
|
| 218 |
+
2025-12-12 04:47:27 step 004 000013000 0.24328067898750305 0.23732741177082062 59701985280
|
| 219 |
+
2025-12-12 05:02:01 recent 004 000014000 0.23832398653030396 0.23732227087020874 60562145280
|
| 220 |
+
2025-12-12 05:02:02 step 004 000014000 0.23832398653030396 0.23732227087020874 60562145280
|
| 221 |
+
2025-12-12 05:02:04 best 004 000014000 0.23832398653030396 0.23732227087020874 60562145280
|
| 222 |
+
2025-12-12 05:04:15 recent 005 000000000 0.2475239485502243 0.2373163253068924 60649881600
|
| 223 |
+
2025-12-12 05:04:16 epoch 005 000000000 0.2475239485502243 0.2373163253068924 60649881600
|
| 224 |
+
2025-12-12 05:04:18 best 005 000000000 0.2475239485502243 0.2373163253068924 60649881600
|
checkpoints/fst_resume/epoch_004_step_000010000_tokens_57.1b_val=0.2374.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3021953e97b00f17de4667cc971563eb6d8c5aea28fa023c40a9d664c850bf0f
|
| 3 |
+
size 1415197993
|
checkpoints/fst_resume/epoch_004_step_000011000_tokens_58b_val=0.2374.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8ef4577a9e2cdd949894e4ceb3dab5c044c1a421c91344246bc5f8540da0acd
|
| 3 |
+
size 1415197253
|
checkpoints/fst_resume/epoch_004_step_000012000_tokens_58.8b_val=0.2373.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cde46e5ad52a8afbe22c611ed11fb91432784c8411a847859d513a0ba2e8fb2
|
| 3 |
+
size 1415197993
|
checkpoints/fst_resume/epoch_004_step_000013000_tokens_59.7b_val=0.2373.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec9b92b687ef8fd87b43275a22bfb7584c4e4c12381d8222d32e25e53ec008d7
|
| 3 |
+
size 1415197993
|
checkpoints/fst_resume/epoch_004_step_000014000_tokens_60.6b_val=0.2373.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12fbba4e4ac578bff93a6ad1327320f724025d849a3d96e851a06aa6c16d8611
|
| 3 |
+
size 1415197993
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000010000_tokens_57.1b_val=0.2374.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000011000_tokens_58b_val=0.2374.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2373.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000013000_tokens_59.7b_val=0.2373.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank0.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank1.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank2.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank3.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank4.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank5.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/fst_resume/metrics_summary_epoch4_top5.csv
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint,accuracy,correct,total
|
checkpoints/fst_resume/verification_epoch_004_step_000010000_tokens_57.1b_val=0.2374.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
============================================================
|
| 2 |
+
FINAL MERGED RESULTS
|
| 3 |
+
============================================================
|
| 4 |
+
Total: 824
|
| 5 |
+
Correct: 488
|
| 6 |
+
No Answer: 52
|
| 7 |
+
Accuracy: 59.22%
|
| 8 |
+
============================================================
|
checkpoints/fst_resume/verification_epoch_004_step_000011000_tokens_58b_val=0.2374.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
============================================================
|
| 2 |
+
FINAL MERGED RESULTS
|
| 3 |
+
============================================================
|
| 4 |
+
Total: 824
|
| 5 |
+
Correct: 483
|
| 6 |
+
No Answer: 55
|
| 7 |
+
Accuracy: 58.62%
|
| 8 |
+
============================================================
|
checkpoints/fst_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2373.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
============================================================
|
| 2 |
+
FINAL MERGED RESULTS
|
| 3 |
+
============================================================
|
| 4 |
+
Total: 659
|
| 5 |
+
Correct: 394
|
| 6 |
+
No Answer: 37
|
| 7 |
+
Accuracy: 59.79%
|
| 8 |
+
============================================================
|
checkpoints/fst_resume/verification_epoch_004_step_000013000_tokens_59.7b_val=0.2373.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
============================================================
|
| 2 |
+
FINAL MERGED RESULTS
|
| 3 |
+
============================================================
|
| 4 |
+
Total: 329
|
| 5 |
+
Correct: 201
|
| 6 |
+
No Answer: 23
|
| 7 |
+
Accuracy: 61.09%
|
| 8 |
+
============================================================
|
checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
============================================================
|
| 2 |
+
FINAL MERGED RESULTS
|
| 3 |
+
============================================================
|
| 4 |
+
Total: 165
|
| 5 |
+
Correct: 102
|
| 6 |
+
No Answer: 11
|
| 7 |
+
Accuracy: 61.82%
|
| 8 |
+
============================================================
|
checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank0.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 100
|
| 3 |
+
Incorrect: 53
|
| 4 |
+
No Answer: 12
|
| 5 |
+
Accuracy: 60.61%
|
checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank1.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 109
|
| 3 |
+
Incorrect: 43
|
| 4 |
+
No Answer: 13
|
| 5 |
+
Accuracy: 66.06%
|
checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank2.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 115
|
| 3 |
+
Incorrect: 42
|
| 4 |
+
No Answer: 8
|
| 5 |
+
Accuracy: 69.70%
|
checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank3.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 104
|
| 3 |
+
Incorrect: 51
|
| 4 |
+
No Answer: 10
|
| 5 |
+
Accuracy: 63.03%
|
checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank4.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 103
|
| 3 |
+
Incorrect: 53
|
| 4 |
+
No Answer: 9
|
| 5 |
+
Accuracy: 62.42%
|
checkpoints/fst_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2373_rank5.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 95
|
| 3 |
+
Incorrect: 63
|
| 4 |
+
No Answer: 7
|
| 5 |
+
Accuracy: 57.58%
|