4.7 KiB
4.7 KiB
| 1 | step | train/loss | train/grad_norm | train/learning_rate | train/epoch | train/train_runtime | train/train_samples_per_second | train/train_steps_per_second | train/total_flos | train/train_loss |
|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 2 | 2.7920000553131104 | 0.035306449979543686 | 7.999999979801942e-06 | 0.010457516647875309 | |||||
| 3 | 4 | 2.8011999130249023 | 0.03491510450839996 | 1.5999999959603883e-05 | 0.020915033295750618 | |||||
| 4 | 6 | 2.7964000701904297 | 0.032717395573854446 | 2.4000000848900527e-05 | 0.0313725508749485 | |||||
| 5 | 8 | 2.763700008392334 | 0.024953875690698624 | 3.199999991920777e-05 | 0.041830066591501236 | |||||
| 6 | 10 | 3.2811999320983887 | 0.3170815408229828 | 3.9999998989515007e-05 | 0.05228758230805397 | |||||
| 7 | 12 | 2.9409000873565674 | 0.04423849284648895 | 3.995128281530924e-05 | 0.062745101749897 | |||||
| 8 | 14 | 2.851900100708008 | 0.03667925298213959 | 3.9805359847377986e-05 | 0.07320261746644974 | |||||
| 9 | 16 | 2.7869999408721924 | 0.022814607247710228 | 3.9562950405525044e-05 | 0.08366013318300247 | |||||
| 10 | 18 | 2.782599925994873 | 0.021528413519263268 | 3.922523319488391e-05 | 0.0941176488995552 | |||||
| 11 | 20 | 2.785599946975708 | 0.017014438286423683 | 3.87938525818754e-05 | 0.10457516461610794 | |||||
| 12 | 22 | 2.7571001052856445 | 0.015719758346676826 | 3.827090768027119e-05 | 0.11503268033266068 | |||||
| 13 | 24 | 2.762399911880493 | 0.016948623582720757 | 3.7658952351193875e-05 | 0.125490203499794 | |||||
| 14 | 26 | 2.7411000728607178 | 0.015535997226834297 | 3.6960962461307645e-05 | 0.13594771921634674 | |||||
| 15 | 28 | 2.7330000400543213 | 0.012748735956847668 | 3.6180339520797133e-05 | 0.14640523493289948 | |||||
| 16 | 30 | 2.723299980163574 | 0.014809778891503811 | 3.532088885549456e-05 | 0.1568627506494522 | |||||
| 17 | 32 | 2.7342000007629395 | 0.01219236571341753 | 3.4386797779006884e-05 | 0.16732026636600494 | |||||
| 18 | 34 | 2.7321999073028564 | 0.012785322032868862 | 3.338261376484297e-05 | 0.17777778208255768 | |||||
| 19 | 36 | 2.7314000129699707 | 0.012986919842660427 | 3.231322989449836e-05 | 0.1882352977991104 | |||||
| 20 | 38 | 2.7065999507904053 | 0.01096824835985899 | 3.118385939160362e-05 | 0.19869281351566315 | |||||
| 21 | 40 | 2.6958999633789062 | 0.012387535534799099 | 2.9999999242136255e-05 | 0.20915032923221588 | |||||
| 22 | 42 | 2.751499891281128 | 0.011586200445890427 | 2.8767422918463126e-05 | 0.21960784494876862 | |||||
| 23 | 44 | 2.713099956512451 | 0.011821281164884567 | 2.749213126662653e-05 | 0.23006536066532135 | |||||
| 24 | 46 | 2.7102999687194824 | 0.01147585827857256 | 2.6180339773418382e-05 | 0.24052287638187408 | |||||
| 25 | 48 | 2.7019999027252197 | 0.011368263512849808 | 2.483843854861334e-05 | 0.250980406999588 | |||||
| 26 | 50 | 2.680500030517578 | 0.009935515932738781 | 2.3472963221138343e-05 | 0.26143792271614075 | |||||
| 27 | 52 | 2.6993000507354736 | 0.0109846917912364 | 2.2090569473220967e-05 | 0.2718954384326935 | |||||
| 28 | 54 | 2.6940999031066895 | 0.010465175844728947 | 2.0697989384643734e-05 | 0.2823529541492462 | |||||
| 29 | 56 | 2.7091000080108643 | 0.01009758748114109 | 1.9302009604871273e-05 | 0.29281046986579895 | |||||
| 30 | 58 | 2.69950008392334 | 0.01249368954449892 | 1.7909431335283443e-05 | 0.3032679855823517 | |||||
| 31 | 60 | 2.7216999530792236 | 0.01051376760005951 | 1.6527035768376663e-05 | 0.3137255012989044 | |||||
| 32 | 62 | 2.7158000469207764 | 0.01054943073540926 | 1.516156225989107e-05 | 0.32418301701545715 | |||||
| 33 | 64 | 2.7214999198913574 | 0.01076149195432663 | 1.3819660125591327e-05 | 0.3346405327320099 | |||||
| 34 | 66 | 2.7116000652313232 | 0.010380392894148827 | 1.2507867722888477e-05 | 0.3450980484485626 | |||||
| 35 | 68 | 2.6923000812530518 | 0.010425001382827759 | 1.1232576980546582e-05 | 0.35555556416511536 | |||||
| 36 | 70 | 2.683199882507324 | 0.00925016961991787 | 9.999999747378752e-06 | 0.3660130798816681 | |||||
| 37 | 72 | 2.7093000411987305 | 0.01072422880679369 | 8.816142326395493e-06 | 0.3764705955982208 | |||||
| 38 | 74 | 2.6988000869750977 | 0.011063243262469769 | 7.686770914006047e-06 | 0.38692811131477356 | |||||
| 39 | 76 | 2.7125000953674316 | 0.01013101264834404 | 6.61738795315614e-06 | 0.3973856270313263 | |||||
| 40 | 78 | 2.6993000507354736 | 0.009940676391124725 | 5.613203938992228e-06 | 0.40784314274787903 | |||||
| 41 | 80 | 2.6861000061035156 | 0.01050259917974472 | 4.6791110435151495e-06 | 0.41830065846443176 | |||||
| 42 | 82 | 2.6828999519348145 | 0.009912634268403053 | 3.819659923465224e-06 | 0.4287581741809845 | |||||
| 43 | 84 | 2.699199914932251 | 0.010668900795280933 | 3.03903811982309e-06 | 0.43921568989753723 | |||||
| 44 | 86 | 2.698899984359741 | 0.009650414809584618 | 2.3410482299368596e-06 | 0.44967320561408997 | |||||
| 45 | 88 | 2.6884000301361084 | 0.01006452739238739 | 1.7290908544964623e-06 | 0.4601307213306427 | |||||
| 46 | 90 | 2.6928999423980713 | 0.010409764014184475 | 1.206147544507985e-06 | 0.47058823704719543 | |||||
| 47 | 92 | 2.714200019836426 | 0.009937116876244545 | 7.74766078848188e-07 | 0.48104575276374817 | |||||
| 48 | 94 | 2.672300100326538 | 0.009728306904435158 | 4.370479871340649e-07 | 0.4915032684803009 | |||||
| 49 | 96 | 2.7018001079559326 | 0.010098566301167011 | 1.9463863054625108e-07 | 0.501960813999176 | |||||
| 50 | 98 | 2.7123000621795654 | 0.009524320252239704 | 4.8718995060426096e-08 | 0.5124183297157288 | |||||
| 51 | 100 | 2.7028000354766846 | 0.009290286339819431 | 0.0 | 0.5228758454322815 | 788.0635986328125 | 64.96900177001953 | 0.12700000405311584 | 4.629706395531346e+17 | 2.739542245864868 |