Upload folder using huggingface_hub
Browse files- checkpoints/transformer_resume/_checkpoint_log.tsv +223 -0
- checkpoints/transformer_resume/best_epoch_004_step_000013000_tokens_59.7b_val=0.2368.pt +3 -0
- checkpoints/transformer_resume/epoch_004_step_000010000_tokens_57.1b_val=0.2369.pt +3 -0
- checkpoints/transformer_resume/epoch_004_step_000011000_tokens_58b_val=0.2368.pt +3 -0
- checkpoints/transformer_resume/epoch_004_step_000012000_tokens_58.8b_val=0.2368.pt +3 -0
- checkpoints/transformer_resume/epoch_004_step_000013000_tokens_59.7b_val=0.2368.pt +3 -0
- checkpoints/transformer_resume/epoch_004_step_000014000_tokens_60.6b_val=0.2368.pt +3 -0
- checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank0.txt +0 -0
- checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank2.txt +0 -0
- checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank3.txt +0 -0
- checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank4.txt +0 -0
- checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank5.txt +0 -0
- checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank6.txt +0 -0
- checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank7.txt +0 -0
- checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000013000_tokens_59.7b_val=0.2368.txt +0 -0
- checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2368.txt +0 -0
- checkpoints/transformer_resume/metrics_summary_epoch4_top5.csv +2 -0
- checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank0.txt +5 -0
- checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank2.txt +5 -0
- checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank3.txt +5 -0
- checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank4.txt +5 -0
- checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank5.txt +5 -0
- checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank6.txt +5 -0
- checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank7.txt +5 -0
- checkpoints/transformer_resume/verification_epoch_004_step_000013000_tokens_59.7b_val=0.2368.txt +8 -0
- checkpoints/transformer_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2368.txt +8 -0
checkpoints/transformer_resume/_checkpoint_log.tsv
ADDED
|
@@ -0,0 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Time Checkpoint_Type Epoch Step Train_Loss Val_Loss Tokens_Trained
|
| 2 |
+
2025-12-11 09:27:23 recent 000 000001000 0.36613672971725464 0.3444387912750244 860160000
|
| 3 |
+
2025-12-11 09:27:25 step 000 000001000 0.36613672971725464 0.3444387912750244 860160000
|
| 4 |
+
2025-12-11 09:27:28 best 000 000001000 0.36613672971725464 0.3444387912750244 860160000
|
| 5 |
+
2025-12-11 09:44:09 recent 000 000002000 0.3280094116926193 0.3190518319606781 1720320000
|
| 6 |
+
2025-12-11 09:44:11 step 000 000002000 0.3280094116926193 0.3190518319606781 1720320000
|
| 7 |
+
2025-12-11 09:44:13 best 000 000002000 0.3280094116926193 0.3190518319606781 1720320000
|
| 8 |
+
2025-12-11 10:00:52 recent 000 000003000 0.31777187436819077 0.307509183883667 2580480000
|
| 9 |
+
2025-12-11 10:00:55 step 000 000003000 0.31777187436819077 0.307509183883667 2580480000
|
| 10 |
+
2025-12-11 10:00:58 best 000 000003000 0.31777187436819077 0.307509183883667 2580480000
|
| 11 |
+
2025-12-11 10:17:39 recent 000 000004000 0.3202485591173172 0.3003028929233551 3440640000
|
| 12 |
+
2025-12-11 10:17:42 step 000 000004000 0.3202485591173172 0.3003028929233551 3440640000
|
| 13 |
+
2025-12-11 10:17:44 best 000 000004000 0.3202485591173172 0.3003028929233551 3440640000
|
| 14 |
+
2025-12-11 10:34:25 recent 000 000005000 0.29960839450359344 0.2945575416088104 4300800000
|
| 15 |
+
2025-12-11 10:34:27 step 000 000005000 0.29960839450359344 0.2945575416088104 4300800000
|
| 16 |
+
2025-12-11 10:34:30 best 000 000005000 0.29960839450359344 0.2945575416088104 4300800000
|
| 17 |
+
2025-12-11 10:51:09 recent 000 000006000 0.2941434159874916 0.2903696596622467 5160960000
|
| 18 |
+
2025-12-11 10:51:11 step 000 000006000 0.2941434159874916 0.2903696596622467 5160960000
|
| 19 |
+
2025-12-11 10:51:14 best 000 000006000 0.2941434159874916 0.2903696596622467 5160960000
|
| 20 |
+
2025-12-11 11:07:54 recent 000 000007000 0.2800699919462204 0.28666606545448303 6021120000
|
| 21 |
+
2025-12-11 11:07:57 step 000 000007000 0.2800699919462204 0.28666606545448303 6021120000
|
| 22 |
+
2025-12-11 11:08:00 best 000 000007000 0.2800699919462204 0.28666606545448303 6021120000
|
| 23 |
+
2025-12-11 11:24:41 recent 000 000008000 0.26715802401304245 0.28432497382164 6881280000
|
| 24 |
+
2025-12-11 11:24:43 step 000 000008000 0.26715802401304245 0.28432497382164 6881280000
|
| 25 |
+
2025-12-11 11:24:46 best 000 000008000 0.26715802401304245 0.28432497382164 6881280000
|
| 26 |
+
2025-12-11 11:41:27 recent 000 000009000 0.2975319102406502 0.28179633617401123 7741440000
|
| 27 |
+
2025-12-11 11:41:29 step 000 000009000 0.2975319102406502 0.28179633617401123 7741440000
|
| 28 |
+
2025-12-11 11:41:31 best 000 000009000 0.2975319102406502 0.28179633617401123 7741440000
|
| 29 |
+
2025-12-11 11:58:10 recent 000 000010000 0.3000650256872177 0.27950870990753174 8601600000
|
| 30 |
+
2025-12-11 11:58:13 step 000 000010000 0.3000650256872177 0.27950870990753174 8601600000
|
| 31 |
+
2025-12-11 11:58:15 best 000 000010000 0.3000650256872177 0.27950870990753174 8601600000
|
| 32 |
+
2025-12-11 12:14:59 recent 000 000011000 0.2962534725666046 0.2778068482875824 9461760000
|
| 33 |
+
2025-12-11 12:15:01 step 000 000011000 0.2962534725666046 0.2778068482875824 9461760000
|
| 34 |
+
2025-12-11 12:15:04 best 000 000011000 0.2962534725666046 0.2778068482875824 9461760000
|
| 35 |
+
2025-12-11 12:31:47 recent 000 000012000 0.3176053464412689 0.27590566873550415 10321920000
|
| 36 |
+
2025-12-11 12:31:50 step 000 000012000 0.3176053464412689 0.27590566873550415 10321920000
|
| 37 |
+
2025-12-11 12:31:52 best 000 000012000 0.3176053464412689 0.27590566873550415 10321920000
|
| 38 |
+
2025-12-11 12:48:30 recent 000 000013000 0.2762407213449478 0.2742904722690582 11182080000
|
| 39 |
+
2025-12-11 12:48:32 step 000 000013000 0.2762407213449478 0.2742904722690582 11182080000
|
| 40 |
+
2025-12-11 12:48:34 best 000 000013000 0.2762407213449478 0.2742904722690582 11182080000
|
| 41 |
+
2025-12-11 13:05:16 recent 000 000014000 0.27883637696504593 0.2727672755718231 12042240000
|
| 42 |
+
2025-12-11 13:05:18 step 000 000014000 0.27883637696504593 0.2727672755718231 12042240000
|
| 43 |
+
2025-12-11 13:05:20 best 000 000014000 0.27883637696504593 0.2727672755718231 12042240000
|
| 44 |
+
2025-12-11 13:07:57 recent 001 000000000 0.29382694512605667 0.27266374230384827 12129976320
|
| 45 |
+
2025-12-11 13:07:59 epoch 001 000000000 0.29382694512605667 0.27266374230384827 12129976320
|
| 46 |
+
2025-12-11 13:08:01 best 001 000000000 0.29382694512605667 0.27266374230384827 12129976320
|
| 47 |
+
2025-12-11 13:24:45 recent 001 000001000 0.27998270094394684 0.271516352891922 12990136320
|
| 48 |
+
2025-12-11 13:24:48 step 001 000001000 0.27998270094394684 0.271516352891922 12990136320
|
| 49 |
+
2025-12-11 13:24:51 best 001 000001000 0.27998270094394684 0.271516352891922 12990136320
|
| 50 |
+
2025-12-11 13:41:29 recent 001 000002000 0.27671778202056885 0.27047619223594666 13850296320
|
| 51 |
+
2025-12-11 13:41:32 step 001 000002000 0.27671778202056885 0.27047619223594666 13850296320
|
| 52 |
+
2025-12-11 13:41:35 best 001 000002000 0.27671778202056885 0.27047619223594666 13850296320
|
| 53 |
+
2025-12-11 13:58:18 recent 001 000003000 0.26892121136188507 0.26948779821395874 14710456320
|
| 54 |
+
2025-12-11 13:58:20 step 001 000003000 0.26892121136188507 0.26948779821395874 14710456320
|
| 55 |
+
2025-12-11 13:58:23 best 001 000003000 0.26892121136188507 0.26948779821395874 14710456320
|
| 56 |
+
2025-12-11 14:15:07 recent 001 000004000 0.29253649711608887 0.2683350443840027 15570616320
|
| 57 |
+
2025-12-11 14:15:09 step 001 000004000 0.29253649711608887 0.2683350443840027 15570616320
|
| 58 |
+
2025-12-11 14:15:12 best 001 000004000 0.29253649711608887 0.2683350443840027 15570616320
|
| 59 |
+
2025-12-11 14:31:51 recent 001 000005000 0.27853891998529434 0.26717275381088257 16430776320
|
| 60 |
+
2025-12-11 14:31:54 step 001 000005000 0.27853891998529434 0.26717275381088257 16430776320
|
| 61 |
+
2025-12-11 14:31:56 best 001 000005000 0.27853891998529434 0.26717275381088257 16430776320
|
| 62 |
+
2025-12-11 14:48:39 recent 001 000006000 0.263127438724041 0.2661120593547821 17290936320
|
| 63 |
+
2025-12-11 14:48:41 step 001 000006000 0.263127438724041 0.2661120593547821 17290936320
|
| 64 |
+
2025-12-11 14:48:44 best 001 000006000 0.263127438724041 0.2661120593547821 17290936320
|
| 65 |
+
2025-12-11 15:05:27 recent 001 000007000 0.27765025943517685 0.26518088579177856 18151096320
|
| 66 |
+
2025-12-11 15:05:30 step 001 000007000 0.27765025943517685 0.26518088579177856 18151096320
|
| 67 |
+
2025-12-11 15:05:32 best 001 000007000 0.27765025943517685 0.26518088579177856 18151096320
|
| 68 |
+
2025-12-11 15:22:13 recent 001 000008000 0.2887879014015198 0.2640847861766815 19011256320
|
| 69 |
+
2025-12-11 15:22:15 step 001 000008000 0.2887879014015198 0.2640847861766815 19011256320
|
| 70 |
+
2025-12-11 15:22:18 best 001 000008000 0.2887879014015198 0.2640847861766815 19011256320
|
| 71 |
+
2025-12-11 15:38:58 recent 001 000009000 0.2546284720301628 0.26351097226142883 19871416320
|
| 72 |
+
2025-12-11 15:39:00 step 001 000009000 0.2546284720301628 0.26351097226142883 19871416320
|
| 73 |
+
2025-12-11 15:39:02 best 001 000009000 0.2546284720301628 0.26351097226142883 19871416320
|
| 74 |
+
2025-12-11 15:55:44 recent 001 000010000 0.2887316718697548 0.2621825039386749 20731576320
|
| 75 |
+
2025-12-11 15:55:46 step 001 000010000 0.2887316718697548 0.2621825039386749 20731576320
|
| 76 |
+
2025-12-11 15:55:49 best 001 000010000 0.2887316718697548 0.2621825039386749 20731576320
|
| 77 |
+
2025-12-11 16:12:28 recent 001 000011000 0.2872507646679878 0.2613237500190735 21591736320
|
| 78 |
+
2025-12-11 16:12:30 step 001 000011000 0.2872507646679878 0.2613237500190735 21591736320
|
| 79 |
+
2025-12-11 16:12:33 best 001 000011000 0.2872507646679878 0.2613237500190735 21591736320
|
| 80 |
+
2025-12-11 16:29:13 recent 001 000012000 0.2715538963675499 0.260507196187973 22451896320
|
| 81 |
+
2025-12-11 16:29:15 step 001 000012000 0.2715538963675499 0.260507196187973 22451896320
|
| 82 |
+
2025-12-11 16:29:17 best 001 000012000 0.2715538963675499 0.260507196187973 22451896320
|
| 83 |
+
2025-12-11 16:46:00 recent 001 000013000 0.27833670377731323 0.2597297728061676 23312056320
|
| 84 |
+
2025-12-11 16:46:02 step 001 000013000 0.27833670377731323 0.2597297728061676 23312056320
|
| 85 |
+
2025-12-11 16:46:04 best 001 000013000 0.27833670377731323 0.2597297728061676 23312056320
|
| 86 |
+
2025-12-11 17:02:43 recent 001 000014000 0.2754926159977913 0.2586735188961029 24172216320
|
| 87 |
+
2025-12-11 17:02:45 step 001 000014000 0.2754926159977913 0.2586735188961029 24172216320
|
| 88 |
+
2025-12-11 17:02:48 best 001 000014000 0.2754926159977913 0.2586735188961029 24172216320
|
| 89 |
+
2025-12-11 17:05:28 recent 002 000000000 0.286208875477314 0.25874537229537964 24259952640
|
| 90 |
+
2025-12-11 17:05:30 epoch 002 000000000 0.286208875477314 0.25874537229537964 24259952640
|
| 91 |
+
2025-12-11 17:22:10 recent 002 000001000 0.2496793493628502 0.2573777735233307 25120112640
|
| 92 |
+
2025-12-11 17:22:13 step 002 000001000 0.2496793493628502 0.2573777735233307 25120112640
|
| 93 |
+
2025-12-11 17:22:16 best 002 000001000 0.2496793493628502 0.2573777735233307 25120112640
|
| 94 |
+
2025-12-11 17:38:59 recent 002 000002000 0.2780672535300255 0.25689762830734253 25980272640
|
| 95 |
+
2025-12-11 17:39:01 step 002 000002000 0.2780672535300255 0.25689762830734253 25980272640
|
| 96 |
+
2025-12-11 17:39:04 best 002 000002000 0.2780672535300255 0.25689762830734253 25980272640
|
| 97 |
+
2025-12-11 17:55:46 recent 002 000003000 0.254419706761837 0.2560234069824219 26840432640
|
| 98 |
+
2025-12-11 17:55:49 step 002 000003000 0.254419706761837 0.2560234069824219 26840432640
|
| 99 |
+
2025-12-11 17:55:51 best 002 000003000 0.254419706761837 0.2560234069824219 26840432640
|
| 100 |
+
2025-12-11 18:12:29 recent 002 000004000 0.2529037743806839 0.25541624426841736 27700592640
|
| 101 |
+
2025-12-11 18:12:31 step 002 000004000 0.2529037743806839 0.25541624426841736 27700592640
|
| 102 |
+
2025-12-11 18:12:34 best 002 000004000 0.2529037743806839 0.25541624426841736 27700592640
|
| 103 |
+
2025-12-11 18:29:16 recent 002 000005000 0.27012404799461365 0.25456273555755615 28560752640
|
| 104 |
+
2025-12-11 18:29:18 step 002 000005000 0.27012404799461365 0.25456273555755615 28560752640
|
| 105 |
+
2025-12-11 18:29:20 best 002 000005000 0.27012404799461365 0.25456273555755615 28560752640
|
| 106 |
+
2025-12-11 18:46:02 recent 002 000006000 0.2641011252999306 0.25369343161582947 29420912640
|
| 107 |
+
2025-12-11 18:46:04 step 002 000006000 0.2641011252999306 0.25369343161582947 29420912640
|
| 108 |
+
2025-12-11 18:46:07 best 002 000006000 0.2641011252999306 0.25369343161582947 29420912640
|
| 109 |
+
2025-12-11 19:02:45 recent 002 000007000 0.26155364513397217 0.2527071535587311 30281072640
|
| 110 |
+
2025-12-11 19:02:47 step 002 000007000 0.26155364513397217 0.2527071535587311 30281072640
|
| 111 |
+
2025-12-11 19:02:50 best 002 000007000 0.26155364513397217 0.2527071535587311 30281072640
|
| 112 |
+
2025-12-11 19:19:31 recent 002 000008000 0.2528020441532135 0.25216734409332275 31141232640
|
| 113 |
+
2025-12-11 19:19:34 step 002 000008000 0.2528020441532135 0.25216734409332275 31141232640
|
| 114 |
+
2025-12-11 19:19:37 best 002 000008000 0.2528020441532135 0.25216734409332275 31141232640
|
| 115 |
+
2025-12-11 19:36:20 recent 002 000009000 0.244673453271389 0.2513868510723114 32001392640
|
| 116 |
+
2025-12-11 19:36:22 step 002 000009000 0.244673453271389 0.2513868510723114 32001392640
|
| 117 |
+
2025-12-11 19:36:25 best 002 000009000 0.244673453271389 0.2513868510723114 32001392640
|
| 118 |
+
2025-12-11 19:53:04 recent 002 000010000 0.25688424706459045 0.25060907006263733 32861552640
|
| 119 |
+
2025-12-11 19:53:07 step 002 000010000 0.25688424706459045 0.25060907006263733 32861552640
|
| 120 |
+
2025-12-11 19:53:09 best 002 000010000 0.25688424706459045 0.25060907006263733 32861552640
|
| 121 |
+
2025-12-11 20:09:52 recent 002 000011000 0.26670128107070923 0.2501091957092285 33721712640
|
| 122 |
+
2025-12-11 20:09:55 step 002 000011000 0.26670128107070923 0.2501091957092285 33721712640
|
| 123 |
+
2025-12-11 20:09:58 best 002 000011000 0.26670128107070923 0.2501091957092285 33721712640
|
| 124 |
+
2025-12-11 20:26:40 recent 002 000012000 0.26035507768392563 0.24926462769508362 34581872640
|
| 125 |
+
2025-12-11 20:26:43 step 002 000012000 0.26035507768392563 0.24926462769508362 34581872640
|
| 126 |
+
2025-12-11 20:26:45 best 002 000012000 0.26035507768392563 0.24926462769508362 34581872640
|
| 127 |
+
2025-12-11 20:43:25 recent 002 000013000 0.25230734795331955 0.24867957830429077 35442032640
|
| 128 |
+
2025-12-11 20:43:27 step 002 000013000 0.25230734795331955 0.24867957830429077 35442032640
|
| 129 |
+
2025-12-11 20:43:30 best 002 000013000 0.25230734795331955 0.24867957830429077 35442032640
|
| 130 |
+
2025-12-11 21:00:12 recent 002 000014000 0.26635780185461044 0.24779155850410461 36302192640
|
| 131 |
+
2025-12-11 21:00:15 step 002 000014000 0.26635780185461044 0.24779155850410461 36302192640
|
| 132 |
+
2025-12-11 21:00:17 best 002 000014000 0.26635780185461044 0.24779155850410461 36302192640
|
| 133 |
+
2025-12-11 21:02:54 recent 003 000000000 0.24850519001483917 0.2477075457572937 36389928960
|
| 134 |
+
2025-12-11 21:02:56 epoch 003 000000000 0.24850519001483917 0.2477075457572937 36389928960
|
| 135 |
+
2025-12-11 21:02:58 best 003 000000000 0.24850519001483917 0.2477075457572937 36389928960
|
| 136 |
+
2025-12-11 21:19:42 recent 003 000001000 0.2549551874399185 0.24675163626670837 37250088960
|
| 137 |
+
2025-12-11 21:19:44 step 003 000001000 0.2549551874399185 0.24675163626670837 37250088960
|
| 138 |
+
2025-12-11 21:19:46 best 003 000001000 0.2549551874399185 0.24675163626670837 37250088960
|
| 139 |
+
2025-12-11 21:36:27 recent 003 000002000 0.2487943097949028 0.24610209465026855 38110248960
|
| 140 |
+
2025-12-11 21:36:30 step 003 000002000 0.2487943097949028 0.24610209465026855 38110248960
|
| 141 |
+
2025-12-11 21:36:33 best 003 000002000 0.2487943097949028 0.24610209465026855 38110248960
|
| 142 |
+
2025-12-11 21:53:13 recent 003 000003000 0.25783489644527435 0.24556264281272888 38970408960
|
| 143 |
+
2025-12-11 21:53:15 step 003 000003000 0.25783489644527435 0.24556264281272888 38970408960
|
| 144 |
+
2025-12-11 21:53:18 best 003 000003000 0.25783489644527435 0.24556264281272888 38970408960
|
| 145 |
+
2025-12-11 22:09:59 recent 003 000004000 0.26186297833919525 0.2449091225862503 39830568960
|
| 146 |
+
2025-12-11 22:10:02 step 003 000004000 0.26186297833919525 0.2449091225862503 39830568960
|
| 147 |
+
2025-12-11 22:10:04 best 003 000004000 0.26186297833919525 0.2449091225862503 39830568960
|
| 148 |
+
2025-12-11 22:26:48 recent 003 000005000 0.24109402298927307 0.24432429671287537 40690728960
|
| 149 |
+
2025-12-11 22:26:50 step 003 000005000 0.24109402298927307 0.24432429671287537 40690728960
|
| 150 |
+
2025-12-11 22:26:53 best 003 000005000 0.24109402298927307 0.24432429671287537 40690728960
|
| 151 |
+
2025-12-11 22:43:32 recent 003 000006000 0.25387822836637497 0.24357324838638306 41550888960
|
| 152 |
+
2025-12-11 22:43:35 step 003 000006000 0.25387822836637497 0.24357324838638306 41550888960
|
| 153 |
+
2025-12-11 22:43:37 best 003 000006000 0.25387822836637497 0.24357324838638306 41550888960
|
| 154 |
+
2025-12-11 23:00:21 recent 003 000007000 0.2561892941594124 0.24296054244041443 42411048960
|
| 155 |
+
2025-12-11 23:00:24 step 003 000007000 0.2561892941594124 0.24296054244041443 42411048960
|
| 156 |
+
2025-12-11 23:00:26 best 003 000007000 0.2561892941594124 0.24296054244041443 42411048960
|
| 157 |
+
2025-12-11 23:17:11 recent 003 000008000 0.26385103166103363 0.24235203862190247 43271208960
|
| 158 |
+
2025-12-11 23:17:13 step 003 000008000 0.26385103166103363 0.24235203862190247 43271208960
|
| 159 |
+
2025-12-11 23:17:16 best 003 000008000 0.26385103166103363 0.24235203862190247 43271208960
|
| 160 |
+
2025-12-11 23:33:55 recent 003 000009000 0.2555175647139549 0.24181638658046722 44131368960
|
| 161 |
+
2025-12-11 23:33:58 step 003 000009000 0.2555175647139549 0.24181638658046722 44131368960
|
| 162 |
+
2025-12-11 23:34:01 best 003 000009000 0.2555175647139549 0.24181638658046722 44131368960
|
| 163 |
+
2025-12-11 23:50:44 recent 003 000010000 0.24845317006111145 0.24128860235214233 44991528960
|
| 164 |
+
2025-12-11 23:50:46 step 003 000010000 0.24845317006111145 0.24128860235214233 44991528960
|
| 165 |
+
2025-12-11 23:50:48 best 003 000010000 0.24845317006111145 0.24128860235214233 44991528960
|
| 166 |
+
2025-12-12 00:07:30 recent 003 000011000 0.26487279683351517 0.24068216979503632 45851688960
|
| 167 |
+
2025-12-12 00:07:32 step 003 000011000 0.26487279683351517 0.24068216979503632 45851688960
|
| 168 |
+
2025-12-12 00:07:34 best 003 000011000 0.26487279683351517 0.24068216979503632 45851688960
|
| 169 |
+
2025-12-12 00:24:14 recent 003 000012000 0.2596351355314255 0.2402358204126358 46711848960
|
| 170 |
+
2025-12-12 00:24:16 step 003 000012000 0.2596351355314255 0.2402358204126358 46711848960
|
| 171 |
+
2025-12-12 00:24:19 best 003 000012000 0.2596351355314255 0.2402358204126358 46711848960
|
| 172 |
+
2025-12-12 00:41:03 recent 003 000013000 0.24632927030324936 0.23980067670345306 47572008960
|
| 173 |
+
2025-12-12 00:41:06 step 003 000013000 0.24632927030324936 0.23980067670345306 47572008960
|
| 174 |
+
2025-12-12 00:41:08 best 003 000013000 0.24632927030324936 0.23980067670345306 47572008960
|
| 175 |
+
2025-12-12 00:57:50 recent 003 000014000 0.2587994262576103 0.23938465118408203 48432168960
|
| 176 |
+
2025-12-12 00:57:52 step 003 000014000 0.2587994262576103 0.23938465118408203 48432168960
|
| 177 |
+
2025-12-12 00:57:55 best 003 000014000 0.2587994262576103 0.23938465118408203 48432168960
|
| 178 |
+
2025-12-12 01:00:32 recent 004 000000000 0.2514341250061989 0.23926229774951935 48519905280
|
| 179 |
+
2025-12-12 01:00:34 epoch 004 000000000 0.2514341250061989 0.23926229774951935 48519905280
|
| 180 |
+
2025-12-12 01:00:36 best 004 000000000 0.2514341250061989 0.23926229774951935 48519905280
|
| 181 |
+
2025-12-12 01:17:18 recent 004 000001000 0.2341514453291893 0.23888924717903137 49380065280
|
| 182 |
+
2025-12-12 01:17:21 step 004 000001000 0.2341514453291893 0.23888924717903137 49380065280
|
| 183 |
+
2025-12-12 01:17:23 best 004 000001000 0.2341514453291893 0.23888924717903137 49380065280
|
| 184 |
+
2025-12-12 01:34:06 recent 004 000002000 0.24926341325044632 0.2385013997554779 50240225280
|
| 185 |
+
2025-12-12 01:34:09 step 004 000002000 0.24926341325044632 0.2385013997554779 50240225280
|
| 186 |
+
2025-12-12 01:34:11 best 004 000002000 0.24926341325044632 0.2385013997554779 50240225280
|
| 187 |
+
2025-12-12 01:50:54 recent 004 000003000 0.2557940036058426 0.2382514625787735 51100385280
|
| 188 |
+
2025-12-12 01:50:57 step 004 000003000 0.2557940036058426 0.2382514625787735 51100385280
|
| 189 |
+
2025-12-12 01:51:00 best 004 000003000 0.2557940036058426 0.2382514625787735 51100385280
|
| 190 |
+
2025-12-12 02:07:41 recent 004 000004000 0.24072552472352982 0.2379457652568817 51960545280
|
| 191 |
+
2025-12-12 02:07:43 step 004 000004000 0.24072552472352982 0.2379457652568817 51960545280
|
| 192 |
+
2025-12-12 02:07:46 best 004 000004000 0.24072552472352982 0.2379457652568817 51960545280
|
| 193 |
+
2025-12-12 02:24:27 recent 004 000005000 0.2581201121211052 0.2376399040222168 52820705280
|
| 194 |
+
2025-12-12 02:24:29 step 004 000005000 0.2581201121211052 0.2376399040222168 52820705280
|
| 195 |
+
2025-12-12 02:24:32 best 004 000005000 0.2581201121211052 0.2376399040222168 52820705280
|
| 196 |
+
2025-12-12 02:41:16 recent 004 000006000 0.2410748153924942 0.2373885065317154 53680865280
|
| 197 |
+
2025-12-12 02:41:18 step 004 000006000 0.2410748153924942 0.2373885065317154 53680865280
|
| 198 |
+
2025-12-12 02:41:21 best 004 000006000 0.2410748153924942 0.2373885065317154 53680865280
|
| 199 |
+
2025-12-12 02:58:01 recent 004 000007000 0.2373994141817093 0.23723778128623962 54541025280
|
| 200 |
+
2025-12-12 02:58:03 step 004 000007000 0.2373994141817093 0.23723778128623962 54541025280
|
| 201 |
+
2025-12-12 02:58:05 best 004 000007000 0.2373994141817093 0.23723778128623962 54541025280
|
| 202 |
+
2025-12-12 03:14:47 recent 004 000008000 0.25438663363456726 0.23709622025489807 55401185280
|
| 203 |
+
2025-12-12 03:14:49 step 004 000008000 0.25438663363456726 0.23709622025489807 55401185280
|
| 204 |
+
2025-12-12 03:14:51 best 004 000008000 0.25438663363456726 0.23709622025489807 55401185280
|
| 205 |
+
2025-12-12 03:31:34 recent 004 000009000 0.2561103329062462 0.23696348071098328 56261345280
|
| 206 |
+
2025-12-12 03:31:36 step 004 000009000 0.2561103329062462 0.23696348071098328 56261345280
|
| 207 |
+
2025-12-12 03:31:39 best 004 000009000 0.2561103329062462 0.23696348071098328 56261345280
|
| 208 |
+
2025-12-12 03:48:22 recent 004 000010000 0.23769138008356094 0.2368747889995575 57121505280
|
| 209 |
+
2025-12-12 03:48:24 step 004 000010000 0.23769138008356094 0.2368747889995575 57121505280
|
| 210 |
+
2025-12-12 03:48:26 best 004 000010000 0.23769138008356094 0.2368747889995575 57121505280
|
| 211 |
+
2025-12-12 04:05:05 recent 004 000011000 0.24944376200437546 0.2368248552083969 57981665280
|
| 212 |
+
2025-12-12 04:05:07 step 004 000011000 0.24944376200437546 0.2368248552083969 57981665280
|
| 213 |
+
2025-12-12 04:05:09 best 004 000011000 0.24944376200437546 0.2368248552083969 57981665280
|
| 214 |
+
2025-12-12 04:21:53 recent 004 000012000 0.2450619339942932 0.23676633834838867 58841825280
|
| 215 |
+
2025-12-12 04:21:56 step 004 000012000 0.2450619339942932 0.23676633834838867 58841825280
|
| 216 |
+
2025-12-12 04:21:59 best 004 000012000 0.2450619339942932 0.23676633834838867 58841825280
|
| 217 |
+
2025-12-12 04:38:41 recent 004 000013000 0.2392006367444992 0.23675858974456787 59701985280
|
| 218 |
+
2025-12-12 04:38:43 step 004 000013000 0.2392006367444992 0.23675858974456787 59701985280
|
| 219 |
+
2025-12-12 04:38:46 best 004 000013000 0.2392006367444992 0.23675858974456787 59701985280
|
| 220 |
+
2025-12-12 04:55:24 recent 004 000014000 0.2381642907857895 0.23676025867462158 60562145280
|
| 221 |
+
2025-12-12 04:55:26 step 004 000014000 0.2381642907857895 0.23676025867462158 60562145280
|
| 222 |
+
2025-12-12 04:58:03 recent 005 000000000 0.246761292219162 0.23676618933677673 60649881600
|
| 223 |
+
2025-12-12 04:58:05 epoch 005 000000000 0.246761292219162 0.23676618933677673 60649881600
|
checkpoints/transformer_resume/best_epoch_004_step_000013000_tokens_59.7b_val=0.2368.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9673ca2c7d4830dec90fa65c8c48aed9ac568cfd3099e44bb0898a10d9d1d71
|
| 3 |
+
size 1415094487
|
checkpoints/transformer_resume/epoch_004_step_000010000_tokens_57.1b_val=0.2369.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d085027bd0ff95b27221714d606b01581370b346b57751e98f26b44ef2fdcb3d
|
| 3 |
+
size 1415092762
|
checkpoints/transformer_resume/epoch_004_step_000011000_tokens_58b_val=0.2368.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e0f7214ea82c8659bbc5083268947e004cc9e0dd1f1809c443f8c9c88a54fdd
|
| 3 |
+
size 1415092072
|
checkpoints/transformer_resume/epoch_004_step_000012000_tokens_58.8b_val=0.2368.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db4c179a14b6239ef321ba56b70d0c57239705a7fc749fca714e6041f53743c6
|
| 3 |
+
size 1415092762
|
checkpoints/transformer_resume/epoch_004_step_000013000_tokens_59.7b_val=0.2368.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65b87c6bd3ee21344fcb10e2ee0ce1f1b88146202bb1cc509a10caf56a5401a5
|
| 3 |
+
size 1415092762
|
checkpoints/transformer_resume/epoch_004_step_000014000_tokens_60.6b_val=0.2368.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0a60c433e6a167c79a479751164b3aae1cf11ec6c57dda5ba03c15ace780d59
|
| 3 |
+
size 1415092762
|
checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank0.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank2.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank3.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank4.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank5.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank6.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank7.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000013000_tokens_59.7b_val=0.2368.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/transformer_resume/gsm8k_results_epoch_004_step_000014000_tokens_60.6b_val=0.2368.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/transformer_resume/metrics_summary_epoch4_top5.csv
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
checkpoint,accuracy,correct,total
|
| 2 |
+
epoch_004_step_000013000_tokens_59.7b_val=0.2368.pt,0.6338,836,1319
|
checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank0.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 106
|
| 3 |
+
Incorrect: 49
|
| 4 |
+
No Answer: 10
|
| 5 |
+
Accuracy: 64.24%
|
checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank2.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 109
|
| 3 |
+
Incorrect: 53
|
| 4 |
+
No Answer: 3
|
| 5 |
+
Accuracy: 66.06%
|
checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank3.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 110
|
| 3 |
+
Incorrect: 53
|
| 4 |
+
No Answer: 2
|
| 5 |
+
Accuracy: 66.67%
|
checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank4.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 102
|
| 3 |
+
Incorrect: 55
|
| 4 |
+
No Answer: 8
|
| 5 |
+
Accuracy: 61.82%
|
checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank5.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 102
|
| 3 |
+
Incorrect: 58
|
| 4 |
+
No Answer: 5
|
| 5 |
+
Accuracy: 61.82%
|
checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank6.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 165
|
| 2 |
+
Correct: 96
|
| 3 |
+
Incorrect: 63
|
| 4 |
+
No Answer: 6
|
| 5 |
+
Accuracy: 58.18%
|
checkpoints/transformer_resume/verification_epoch_004_step_000012000_tokens_58.8b_val=0.2368_rank7.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Total: 164
|
| 2 |
+
Correct: 111
|
| 3 |
+
Incorrect: 50
|
| 4 |
+
No Answer: 3
|
| 5 |
+
Accuracy: 67.68%
|
checkpoints/transformer_resume/verification_epoch_004_step_000013000_tokens_59.7b_val=0.2368.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
============================================================
|
| 2 |
+
FINAL MERGED RESULTS
|
| 3 |
+
============================================================
|
| 4 |
+
Total: 1319
|
| 5 |
+
Correct: 836
|
| 6 |
+
No Answer: 35
|
| 7 |
+
Accuracy: 63.38%
|
| 8 |
+
============================================================
|
checkpoints/transformer_resume/verification_epoch_004_step_000014000_tokens_60.6b_val=0.2368.txt
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
============================================================
|
| 2 |
+
FINAL MERGED RESULTS
|
| 3 |
+
============================================================
|
| 4 |
+
Total: 1319
|
| 5 |
+
Correct: 847
|
| 6 |
+
No Answer: 38
|
| 7 |
+
Accuracy: 64.22%
|
| 8 |
+
============================================================
|