| { | |
| "best_metric": 0.004802440293133259, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.7330482590103848, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004886988393402566, | |
| "grad_norm": 3.496391773223877, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 4.5908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004886988393402566, | |
| "eval_loss": 4.457808017730713, | |
| "eval_runtime": 3.1608, | |
| "eval_samples_per_second": 15.819, | |
| "eval_steps_per_second": 4.113, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009773976786805132, | |
| "grad_norm": 3.437105417251587, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.5269, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014660965180207697, | |
| "grad_norm": 3.467268705368042, | |
| "learning_rate": 5e-05, | |
| "loss": 4.551, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019547953573610263, | |
| "grad_norm": 3.4430549144744873, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 4.4104, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02443494196701283, | |
| "grad_norm": 3.4603631496429443, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 4.0045, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.029321930360415395, | |
| "grad_norm": 3.4329891204833984, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3489, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03420891875381796, | |
| "grad_norm": 3.1279687881469727, | |
| "learning_rate": 9.998929121859592e-05, | |
| "loss": 2.5521, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03909590714722053, | |
| "grad_norm": 2.870373249053955, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 1.8669, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04398289554062309, | |
| "grad_norm": 2.74849271774292, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.3343, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04886988393402566, | |
| "grad_norm": 2.134420156478882, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 0.9228, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05375687232742822, | |
| "grad_norm": 1.9005703926086426, | |
| "learning_rate": 9.973253522000438e-05, | |
| "loss": 0.6209, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05864386072083079, | |
| "grad_norm": 1.5681957006454468, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.4086, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06353084911423336, | |
| "grad_norm": 1.2829203605651855, | |
| "learning_rate": 9.947626797104925e-05, | |
| "loss": 0.3602, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06841783750763591, | |
| "grad_norm": 2.018519878387451, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 0.3689, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07330482590103848, | |
| "grad_norm": 1.200795292854309, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.2407, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07819181429444105, | |
| "grad_norm": 0.7333146333694458, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 0.1828, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08307880268784362, | |
| "grad_norm": 0.8203049302101135, | |
| "learning_rate": 9.871039314159677e-05, | |
| "loss": 0.1775, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08796579108124618, | |
| "grad_norm": 0.40979278087615967, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.1498, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09285277947464875, | |
| "grad_norm": 0.6932844519615173, | |
| "learning_rate": 9.82022434473668e-05, | |
| "loss": 0.1343, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09773976786805132, | |
| "grad_norm": 0.3889353275299072, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.1287, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10262675626145389, | |
| "grad_norm": 0.5370850563049316, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.121, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10751374465485644, | |
| "grad_norm": 0.43492749333381653, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.1071, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11240073304825901, | |
| "grad_norm": 0.2682703733444214, | |
| "learning_rate": 9.694035411772594e-05, | |
| "loss": 0.0857, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11728772144166158, | |
| "grad_norm": 0.4315255582332611, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0563, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12217470983506414, | |
| "grad_norm": 0.5034452080726624, | |
| "learning_rate": 9.618901656037514e-05, | |
| "loss": 0.0362, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12217470983506414, | |
| "eval_loss": 0.09082719683647156, | |
| "eval_runtime": 3.232, | |
| "eval_samples_per_second": 15.47, | |
| "eval_steps_per_second": 4.022, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12706169822846672, | |
| "grad_norm": 0.7888331413269043, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.1436, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13194868662186926, | |
| "grad_norm": 0.6206626296043396, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.1505, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13683567501527183, | |
| "grad_norm": 0.5963620543479919, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.1375, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1417226634086744, | |
| "grad_norm": 0.642953634262085, | |
| "learning_rate": 9.445270400683786e-05, | |
| "loss": 0.1211, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14660965180207697, | |
| "grad_norm": 0.3498934507369995, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.1147, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15149664019547954, | |
| "grad_norm": 0.7011544704437256, | |
| "learning_rate": 9.34710341802826e-05, | |
| "loss": 0.0905, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1563836285888821, | |
| "grad_norm": 0.299635112285614, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.0823, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16127061698228468, | |
| "grad_norm": 0.36785322427749634, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.0777, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.16615760537568725, | |
| "grad_norm": 0.34238114953041077, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.0748, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1710445937690898, | |
| "grad_norm": 0.1910071223974228, | |
| "learning_rate": 9.129000719203672e-05, | |
| "loss": 0.0674, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.17593158216249236, | |
| "grad_norm": 0.15098601579666138, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.0457, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18081857055589493, | |
| "grad_norm": 0.30129632353782654, | |
| "learning_rate": 9.009480173917968e-05, | |
| "loss": 0.0323, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1857055589492975, | |
| "grad_norm": 0.19990572333335876, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.0659, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.19059254734270006, | |
| "grad_norm": 0.31118127703666687, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.1034, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.19547953573610263, | |
| "grad_norm": 0.2536146640777588, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.0837, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2003665241295052, | |
| "grad_norm": 0.2500099539756775, | |
| "learning_rate": 8.7506378292689e-05, | |
| "loss": 0.0794, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.20525351252290777, | |
| "grad_norm": 0.24145787954330444, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0797, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2101405009163103, | |
| "grad_norm": 0.2965352237224579, | |
| "learning_rate": 8.611808751020213e-05, | |
| "loss": 0.0714, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.21502748930971288, | |
| "grad_norm": 0.3214447498321533, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.065, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.21991447770311545, | |
| "grad_norm": 0.15810289978981018, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.056, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22480146609651802, | |
| "grad_norm": 0.48764532804489136, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.0531, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2296884544899206, | |
| "grad_norm": 0.27347925305366516, | |
| "learning_rate": 8.316655624828267e-05, | |
| "loss": 0.038, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.23457544288332316, | |
| "grad_norm": 0.11946756392717361, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0319, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.23946243127672573, | |
| "grad_norm": 0.31073084473609924, | |
| "learning_rate": 8.160893417636122e-05, | |
| "loss": 0.0362, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.24434941967012827, | |
| "grad_norm": 0.2531058192253113, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.0174, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24434941967012827, | |
| "eval_loss": 0.033168304711580276, | |
| "eval_runtime": 3.2218, | |
| "eval_samples_per_second": 15.519, | |
| "eval_steps_per_second": 4.035, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24923640806353084, | |
| "grad_norm": 0.4061261713504791, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0797, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.25412339645693344, | |
| "grad_norm": 0.21066705882549286, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 0.0657, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.259010384850336, | |
| "grad_norm": 0.30424046516418457, | |
| "learning_rate": 7.834479661722347e-05, | |
| "loss": 0.0624, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.2638973732437385, | |
| "grad_norm": 0.32400649785995483, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0554, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2687843616371411, | |
| "grad_norm": 0.3764171004295349, | |
| "learning_rate": 7.664449460137245e-05, | |
| "loss": 0.0549, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.27367135003054366, | |
| "grad_norm": 0.2119298130273819, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 0.0487, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.27855833842394623, | |
| "grad_norm": 0.24470122158527374, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0454, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2834453268173488, | |
| "grad_norm": 0.2825168967247009, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 0.0414, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.28833231521075137, | |
| "grad_norm": 0.13654862344264984, | |
| "learning_rate": 7.312360104364318e-05, | |
| "loss": 0.0376, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.29321930360415394, | |
| "grad_norm": 0.18448443710803986, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0339, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2981062919975565, | |
| "grad_norm": 0.0950138047337532, | |
| "learning_rate": 7.130971172276657e-05, | |
| "loss": 0.02, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3029932803909591, | |
| "grad_norm": 0.18261590600013733, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.0153, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.30788026878436164, | |
| "grad_norm": 0.1410977840423584, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0378, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3127672571777642, | |
| "grad_norm": 0.21909953653812408, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 0.0525, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.3176542455711668, | |
| "grad_norm": 0.2571473717689514, | |
| "learning_rate": 6.759230563139466e-05, | |
| "loss": 0.064, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.32254123396456935, | |
| "grad_norm": 0.17875425517559052, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0489, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3274282223579719, | |
| "grad_norm": 0.1534833163022995, | |
| "learning_rate": 6.56958651546778e-05, | |
| "loss": 0.0453, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.3323152107513745, | |
| "grad_norm": 0.1610105186700821, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 0.0397, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.337202199144777, | |
| "grad_norm": 0.16883207857608795, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.035, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3420891875381796, | |
| "grad_norm": 0.16259914636611938, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.0289, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.34697617593158214, | |
| "grad_norm": 0.18017540872097015, | |
| "learning_rate": 6.184555237854625e-05, | |
| "loss": 0.0307, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3518631643249847, | |
| "grad_norm": 0.15212522447109222, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0278, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3567501527183873, | |
| "grad_norm": 0.1106053963303566, | |
| "learning_rate": 5.989900936833841e-05, | |
| "loss": 0.019, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.36163714111178985, | |
| "grad_norm": 0.11007523536682129, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.0181, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3665241295051924, | |
| "grad_norm": 0.04825620353221893, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0037, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3665241295051924, | |
| "eval_loss": 0.017774144187569618, | |
| "eval_runtime": 3.2279, | |
| "eval_samples_per_second": 15.49, | |
| "eval_steps_per_second": 4.027, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.371411117898595, | |
| "grad_norm": 0.3393837809562683, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 0.0564, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.37629810629199756, | |
| "grad_norm": 0.19871211051940918, | |
| "learning_rate": 5.598166982655526e-05, | |
| "loss": 0.0472, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3811850946854001, | |
| "grad_norm": 0.20391109585762024, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0435, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3860720830788027, | |
| "grad_norm": 0.18788817524909973, | |
| "learning_rate": 5.4018330173444754e-05, | |
| "loss": 0.0379, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.39095907147220527, | |
| "grad_norm": 0.14316879212856293, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 0.0283, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.39584605986560784, | |
| "grad_norm": 0.17786382138729095, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.027, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.4007330482590104, | |
| "grad_norm": 0.21436955034732819, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 0.0309, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.405620036652413, | |
| "grad_norm": 0.16341635584831238, | |
| "learning_rate": 5.0100990631661606e-05, | |
| "loss": 0.0287, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.41050702504581554, | |
| "grad_norm": 0.19714505970478058, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0267, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.41539401343921806, | |
| "grad_norm": 0.1616361290216446, | |
| "learning_rate": 4.8154447621453744e-05, | |
| "loss": 0.0217, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4202810018326206, | |
| "grad_norm": 0.11600978672504425, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.0178, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.4251679902260232, | |
| "grad_norm": 0.10082818567752838, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0108, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.43005497861942577, | |
| "grad_norm": 0.21947574615478516, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 0.0339, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.43494196701282833, | |
| "grad_norm": 0.231426402926445, | |
| "learning_rate": 4.430413484532222e-05, | |
| "loss": 0.0479, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.4398289554062309, | |
| "grad_norm": 0.23115426301956177, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0427, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4447159437996335, | |
| "grad_norm": 0.19273918867111206, | |
| "learning_rate": 4.240769436860537e-05, | |
| "loss": 0.0372, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.44960293219303604, | |
| "grad_norm": 0.17096419632434845, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 0.0293, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4544899205864386, | |
| "grad_norm": 0.15599671006202698, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0252, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4593769089798412, | |
| "grad_norm": 0.14636379480361938, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0289, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.46426389737324375, | |
| "grad_norm": 0.1349724531173706, | |
| "learning_rate": 3.8690288277233435e-05, | |
| "loss": 0.021, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4691508857666463, | |
| "grad_norm": 0.18591056764125824, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0206, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.4740378741600489, | |
| "grad_norm": 0.1168551817536354, | |
| "learning_rate": 3.687639895635684e-05, | |
| "loss": 0.017, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.47892486255345146, | |
| "grad_norm": 0.15066345036029816, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.0151, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.483811850946854, | |
| "grad_norm": 0.10822492092847824, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0098, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.48869883934025654, | |
| "grad_norm": 0.09653550386428833, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 0.0064, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.48869883934025654, | |
| "eval_loss": 0.012017174623906612, | |
| "eval_runtime": 3.2213, | |
| "eval_samples_per_second": 15.522, | |
| "eval_steps_per_second": 4.036, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4935858277336591, | |
| "grad_norm": 0.24904842674732208, | |
| "learning_rate": 3.3355505398627566e-05, | |
| "loss": 0.0339, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.4984728161270617, | |
| "grad_norm": 0.2502872347831726, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0348, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.5033598045204642, | |
| "grad_norm": 0.27058976888656616, | |
| "learning_rate": 3.165520338277653e-05, | |
| "loss": 0.0306, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.5082467929138669, | |
| "grad_norm": 0.16723230481147766, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 0.0215, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.5131337813072694, | |
| "grad_norm": 0.2476491630077362, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0243, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.518020769700672, | |
| "grad_norm": 0.16993577778339386, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 0.022, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.5229077580940745, | |
| "grad_norm": 0.20630362629890442, | |
| "learning_rate": 2.8391065823638806e-05, | |
| "loss": 0.0214, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.527794746487477, | |
| "grad_norm": 0.18468116223812103, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0224, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.5326817348808797, | |
| "grad_norm": 0.12725146114826202, | |
| "learning_rate": 2.6833443751717347e-05, | |
| "loss": 0.0101, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.5375687232742822, | |
| "grad_norm": 0.14481593668460846, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 0.0165, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5424557116676848, | |
| "grad_norm": 0.14558053016662598, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0191, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.5473427000610873, | |
| "grad_norm": 0.09826002269983292, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 0.005, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.5522296884544899, | |
| "grad_norm": 0.2601858973503113, | |
| "learning_rate": 2.3881912489797885e-05, | |
| "loss": 0.0232, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.5571166768478925, | |
| "grad_norm": 0.2997516393661499, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0294, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.5620036652412951, | |
| "grad_norm": 0.2502405345439911, | |
| "learning_rate": 2.2493621707311002e-05, | |
| "loss": 0.0341, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5668906536346976, | |
| "grad_norm": 0.21258173882961273, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 0.0251, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5717776420281002, | |
| "grad_norm": 0.2167203426361084, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0233, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.5766646304215027, | |
| "grad_norm": 0.20736785233020782, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 0.0238, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5815516188149054, | |
| "grad_norm": 0.18189823627471924, | |
| "learning_rate": 1.9905198260820328e-05, | |
| "loss": 0.0239, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.5864386072083079, | |
| "grad_norm": 0.17831675708293915, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0139, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5913255956017105, | |
| "grad_norm": 0.17311929166316986, | |
| "learning_rate": 1.8709992807963285e-05, | |
| "loss": 0.0155, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.596212583995113, | |
| "grad_norm": 0.21193860471248627, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 0.0138, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.6010995723885155, | |
| "grad_norm": 0.12439697980880737, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0081, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.6059865607819181, | |
| "grad_norm": 0.1485549807548523, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 0.0061, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.6108735491753207, | |
| "grad_norm": 0.0644276961684227, | |
| "learning_rate": 1.6528965819717413e-05, | |
| "loss": 0.002, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.6108735491753207, | |
| "eval_loss": 0.006207775324583054, | |
| "eval_runtime": 3.2392, | |
| "eval_samples_per_second": 15.436, | |
| "eval_steps_per_second": 4.013, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.6157605375687233, | |
| "grad_norm": 0.2093576341867447, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0323, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.6206475259621258, | |
| "grad_norm": 0.24124690890312195, | |
| "learning_rate": 1.5547295993162156e-05, | |
| "loss": 0.0263, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.6255345143555284, | |
| "grad_norm": 0.22997763752937317, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 0.0246, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.6304215027489309, | |
| "grad_norm": 0.17232383787631989, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.024, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.6353084911423336, | |
| "grad_norm": 0.20387302339076996, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 0.021, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6401954795357361, | |
| "grad_norm": 0.19521893560886383, | |
| "learning_rate": 1.3810983439624881e-05, | |
| "loss": 0.0224, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.6450824679291387, | |
| "grad_norm": 0.16281966865062714, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0145, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.6499694563225412, | |
| "grad_norm": 0.13637928664684296, | |
| "learning_rate": 1.305964588227407e-05, | |
| "loss": 0.0133, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.6548564447159438, | |
| "grad_norm": 0.194955512881279, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 0.0181, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.6597434331093464, | |
| "grad_norm": 0.12221532315015793, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.009, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.664630421502749, | |
| "grad_norm": 0.14309658110141754, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 0.01, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.6695174098961515, | |
| "grad_norm": 0.1093713566660881, | |
| "learning_rate": 1.1797756552633215e-05, | |
| "loss": 0.0051, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.674404398289554, | |
| "grad_norm": 0.2528100609779358, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0218, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6792913866829566, | |
| "grad_norm": 0.27401408553123474, | |
| "learning_rate": 1.1289606858403237e-05, | |
| "loss": 0.0312, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.6841783750763591, | |
| "grad_norm": 0.20631706714630127, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 0.0255, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6890653634697618, | |
| "grad_norm": 0.2128758430480957, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0194, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.6939523518631643, | |
| "grad_norm": 0.24871855974197388, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 0.0204, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.6988393402565669, | |
| "grad_norm": 0.2161489576101303, | |
| "learning_rate": 1.0523732028950771e-05, | |
| "loss": 0.0172, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.7037263286499694, | |
| "grad_norm": 0.1810789704322815, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0137, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.708613317043372, | |
| "grad_norm": 0.1576724499464035, | |
| "learning_rate": 1.0267464779995617e-05, | |
| "loss": 0.014, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.7135003054367746, | |
| "grad_norm": 0.17585541307926178, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 0.0117, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.7183872938301772, | |
| "grad_norm": 0.13925491273403168, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0111, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.7232742822235797, | |
| "grad_norm": 0.11349561810493469, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 0.0082, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.7281612706169823, | |
| "grad_norm": 0.11688259989023209, | |
| "learning_rate": 1.001070878140409e-05, | |
| "loss": 0.0054, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.7330482590103848, | |
| "grad_norm": 0.05643425136804581, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0018, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7330482590103848, | |
| "eval_loss": 0.004802440293133259, | |
| "eval_runtime": 3.2337, | |
| "eval_samples_per_second": 15.462, | |
| "eval_steps_per_second": 4.02, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6872173431947264e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |