| { | |
| "best_metric": 0.39342138171195984, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-250", | |
| "epoch": 0.5941014215998303, | |
| "eval_steps": 50, | |
| "global_step": 350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001697432633142372, | |
| "grad_norm": 0.22029195725917816, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.2479, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001697432633142372, | |
| "eval_loss": 0.6322442293167114, | |
| "eval_runtime": 65.6226, | |
| "eval_samples_per_second": 2.941, | |
| "eval_steps_per_second": 2.941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003394865266284744, | |
| "grad_norm": 0.24590638279914856, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.2438, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005092297899427116, | |
| "grad_norm": 0.23055589199066162, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.0916, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006789730532569488, | |
| "grad_norm": 0.21309782564640045, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.0918, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008487163165711862, | |
| "grad_norm": 0.21661481261253357, | |
| "learning_rate": 0.00015, | |
| "loss": 0.8365, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010184595798854232, | |
| "grad_norm": 0.2395806461572647, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.0087, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011882028431996604, | |
| "grad_norm": 0.25481849908828735, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.9591, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013579461065138977, | |
| "grad_norm": 0.22890186309814453, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.6067, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015276893698281349, | |
| "grad_norm": 0.2807515263557434, | |
| "learning_rate": 0.00027, | |
| "loss": 0.6593, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016974326331423723, | |
| "grad_norm": 0.3522188067436218, | |
| "learning_rate": 0.0003, | |
| "loss": 0.847, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018671758964566094, | |
| "grad_norm": 0.31385794281959534, | |
| "learning_rate": 0.0002999992447508326, | |
| "loss": 0.7329, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020369191597708464, | |
| "grad_norm": 0.5269914269447327, | |
| "learning_rate": 0.0002999969790109359, | |
| "loss": 0.8751, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02206662423085084, | |
| "grad_norm": 0.2571907341480255, | |
| "learning_rate": 0.0002999932028031259, | |
| "loss": 0.6175, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02376405686399321, | |
| "grad_norm": 0.2777341306209564, | |
| "learning_rate": 0.0002999879161654289, | |
| "loss": 0.7442, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025461489497135583, | |
| "grad_norm": 0.19830763339996338, | |
| "learning_rate": 0.00029998111915108125, | |
| "loss": 0.4802, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027158922130277954, | |
| "grad_norm": 0.21772292256355286, | |
| "learning_rate": 0.00029997281182852885, | |
| "loss": 0.527, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.028856354763420328, | |
| "grad_norm": 0.18149510025978088, | |
| "learning_rate": 0.00029996299428142637, | |
| "loss": 0.4808, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030553787396562698, | |
| "grad_norm": 0.22295671701431274, | |
| "learning_rate": 0.00029995166660863636, | |
| "loss": 0.5326, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03225122002970507, | |
| "grad_norm": 0.24240700900554657, | |
| "learning_rate": 0.0002999388289242284, | |
| "loss": 0.5986, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.033948652662847446, | |
| "grad_norm": 0.21365882456302643, | |
| "learning_rate": 0.00029992448135747777, | |
| "loss": 0.4533, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03564608529598982, | |
| "grad_norm": 0.13466337323188782, | |
| "learning_rate": 0.00029990862405286433, | |
| "loss": 0.2177, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03734351792913219, | |
| "grad_norm": 0.2027832567691803, | |
| "learning_rate": 0.00029989125717007104, | |
| "loss": 0.4166, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03904095056227456, | |
| "grad_norm": 0.14215879142284393, | |
| "learning_rate": 0.0002998723808839821, | |
| "loss": 0.2648, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04073838319541693, | |
| "grad_norm": 0.10996250063180923, | |
| "learning_rate": 0.00029985199538468154, | |
| "loss": 0.1554, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042435815828559306, | |
| "grad_norm": 0.10510318726301193, | |
| "learning_rate": 0.0002998301008774512, | |
| "loss": 0.0231, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04413324846170168, | |
| "grad_norm": 0.10925798863172531, | |
| "learning_rate": 0.00029980669758276836, | |
| "loss": 0.1159, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04583068109484405, | |
| "grad_norm": 0.06849532574415207, | |
| "learning_rate": 0.0002997817857363041, | |
| "loss": 0.039, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04752811372798642, | |
| "grad_norm": 0.0729198008775711, | |
| "learning_rate": 0.0002997553655889203, | |
| "loss": 0.0084, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.049225546361128796, | |
| "grad_norm": 0.10013315826654434, | |
| "learning_rate": 0.00029972743740666765, | |
| "loss": 0.0985, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.050922978994271166, | |
| "grad_norm": 0.047209128737449646, | |
| "learning_rate": 0.00029969800147078263, | |
| "loss": 0.0234, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05262041162741354, | |
| "grad_norm": 0.015719635412096977, | |
| "learning_rate": 0.00029966705807768474, | |
| "loss": 0.0014, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05431784426055591, | |
| "grad_norm": 0.032827939838171005, | |
| "learning_rate": 0.0002996346075389736, | |
| "loss": 0.005, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.056015276893698285, | |
| "grad_norm": 0.021124735474586487, | |
| "learning_rate": 0.0002996006501814258, | |
| "loss": 0.0012, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.057712709526840655, | |
| "grad_norm": 0.014757171273231506, | |
| "learning_rate": 0.0002995651863469916, | |
| "loss": 0.0019, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.059410142159983026, | |
| "grad_norm": 0.013099136762320995, | |
| "learning_rate": 0.00029952821639279135, | |
| "loss": 0.0012, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061107574793125397, | |
| "grad_norm": 0.02350614406168461, | |
| "learning_rate": 0.0002994897406911121, | |
| "loss": 0.0032, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06280500742626777, | |
| "grad_norm": 0.01101439818739891, | |
| "learning_rate": 0.0002994497596294037, | |
| "loss": 0.0006, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06450244005941014, | |
| "grad_norm": 0.08192350715398788, | |
| "learning_rate": 0.00029940827361027504, | |
| "loss": 0.0046, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06619987269255251, | |
| "grad_norm": 0.03598169609904289, | |
| "learning_rate": 0.0002993652830514899, | |
| "loss": 0.0027, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06789730532569489, | |
| "grad_norm": 0.045441944152116776, | |
| "learning_rate": 0.0002993207883859627, | |
| "loss": 0.0076, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06959473795883726, | |
| "grad_norm": 0.048115745186805725, | |
| "learning_rate": 0.00029927479006175417, | |
| "loss": 0.0028, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07129217059197963, | |
| "grad_norm": 0.027597462758421898, | |
| "learning_rate": 0.00029922728854206703, | |
| "loss": 0.002, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.072989603225122, | |
| "grad_norm": 0.0355045348405838, | |
| "learning_rate": 0.00029917828430524096, | |
| "loss": 0.0013, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07468703585826438, | |
| "grad_norm": 0.0412307046353817, | |
| "learning_rate": 0.00029912777784474814, | |
| "loss": 0.003, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07638446849140675, | |
| "grad_norm": 0.051867593079805374, | |
| "learning_rate": 0.0002990757696691881, | |
| "loss": 0.0039, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07808190112454912, | |
| "grad_norm": 0.06054271385073662, | |
| "learning_rate": 0.00029902226030228247, | |
| "loss": 0.0019, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07977933375769149, | |
| "grad_norm": 0.05313190817832947, | |
| "learning_rate": 0.00029896725028287014, | |
| "loss": 0.0041, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08147676639083386, | |
| "grad_norm": 0.18755203485488892, | |
| "learning_rate": 0.00029891074016490126, | |
| "loss": 0.0036, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08317419902397624, | |
| "grad_norm": 0.05305561423301697, | |
| "learning_rate": 0.00029885273051743214, | |
| "loss": 0.0051, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08487163165711861, | |
| "grad_norm": 0.08674199134111404, | |
| "learning_rate": 0.00029879322192461925, | |
| "loss": 0.012, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08487163165711861, | |
| "eval_loss": 0.4556533694267273, | |
| "eval_runtime": 65.6522, | |
| "eval_samples_per_second": 2.94, | |
| "eval_steps_per_second": 2.94, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08656906429026098, | |
| "grad_norm": 0.5487300753593445, | |
| "learning_rate": 0.00029873221498571354, | |
| "loss": 1.0487, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08826649692340335, | |
| "grad_norm": 0.27697888016700745, | |
| "learning_rate": 0.00029866971031505417, | |
| "loss": 0.7504, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.08996392955654572, | |
| "grad_norm": 0.2856276035308838, | |
| "learning_rate": 0.00029860570854206244, | |
| "loss": 1.0179, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0916613621896881, | |
| "grad_norm": 0.43166583776474, | |
| "learning_rate": 0.0002985402103112355, | |
| "loss": 0.7947, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09335879482283047, | |
| "grad_norm": 0.26107504963874817, | |
| "learning_rate": 0.0002984732162821399, | |
| "loss": 0.9617, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09505622745597284, | |
| "grad_norm": 0.20953023433685303, | |
| "learning_rate": 0.00029840472712940465, | |
| "loss": 0.7355, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0967536600891152, | |
| "grad_norm": 0.22740969061851501, | |
| "learning_rate": 0.0002983347435427148, | |
| "loss": 0.839, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09845109272225759, | |
| "grad_norm": 0.24932198226451874, | |
| "learning_rate": 0.00029826326622680433, | |
| "loss": 0.775, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.10014852535539996, | |
| "grad_norm": 0.260080486536026, | |
| "learning_rate": 0.000298190295901449, | |
| "loss": 0.9275, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.10184595798854233, | |
| "grad_norm": 0.22443322837352753, | |
| "learning_rate": 0.00029811583330145914, | |
| "loss": 0.796, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1035433906216847, | |
| "grad_norm": 0.2286413460969925, | |
| "learning_rate": 0.0002980398791766723, | |
| "loss": 0.6944, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.10524082325482707, | |
| "grad_norm": 0.18511152267456055, | |
| "learning_rate": 0.00029796243429194575, | |
| "loss": 0.4977, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.10693825588796944, | |
| "grad_norm": 0.745172917842865, | |
| "learning_rate": 0.00029788349942714854, | |
| "loss": 0.4391, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.10863568852111181, | |
| "grad_norm": 0.27929672598838806, | |
| "learning_rate": 0.0002978030753771539, | |
| "loss": 0.8052, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.11033312115425419, | |
| "grad_norm": 0.3147849440574646, | |
| "learning_rate": 0.0002977211629518312, | |
| "loss": 1.0817, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.11203055378739657, | |
| "grad_norm": 0.22278442978858948, | |
| "learning_rate": 0.00029763776297603756, | |
| "loss": 0.5924, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.11372798642053894, | |
| "grad_norm": 0.1911861002445221, | |
| "learning_rate": 0.0002975528762896098, | |
| "loss": 0.3729, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.11542541905368131, | |
| "grad_norm": 0.21224386990070343, | |
| "learning_rate": 0.000297466503747356, | |
| "loss": 0.569, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.11712285168682368, | |
| "grad_norm": 0.25374075770378113, | |
| "learning_rate": 0.0002973786462190466, | |
| "loss": 0.8077, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.11882028431996605, | |
| "grad_norm": 0.16218560934066772, | |
| "learning_rate": 0.00029728930458940595, | |
| "loss": 0.3303, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12051771695310842, | |
| "grad_norm": 0.18142607808113098, | |
| "learning_rate": 0.0002971984797581034, | |
| "loss": 0.4428, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.12221514958625079, | |
| "grad_norm": 0.22838933765888214, | |
| "learning_rate": 0.0002971061726397438, | |
| "loss": 0.6141, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.12391258221939316, | |
| "grad_norm": 0.16390271484851837, | |
| "learning_rate": 0.00029701238416385896, | |
| "loss": 0.3882, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.12561001485253553, | |
| "grad_norm": 0.07758953422307968, | |
| "learning_rate": 0.00029691711527489776, | |
| "loss": 0.0949, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1273074474856779, | |
| "grad_norm": 0.10925949364900589, | |
| "learning_rate": 0.0002968203669322168, | |
| "loss": 0.1791, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.12900488011882028, | |
| "grad_norm": 0.021430950611829758, | |
| "learning_rate": 0.0002967221401100708, | |
| "loss": 0.003, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.13070231275196265, | |
| "grad_norm": 0.02433953993022442, | |
| "learning_rate": 0.0002966224357976029, | |
| "loss": 0.0021, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.13239974538510502, | |
| "grad_norm": 0.11294607818126678, | |
| "learning_rate": 0.0002965212549988342, | |
| "loss": 0.0765, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1340971780182474, | |
| "grad_norm": 0.026264643296599388, | |
| "learning_rate": 0.0002964185987326545, | |
| "loss": 0.0026, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.13579461065138979, | |
| "grad_norm": 0.0762176588177681, | |
| "learning_rate": 0.00029631446803281107, | |
| "loss": 0.0394, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13749204328453216, | |
| "grad_norm": 0.03476507589221001, | |
| "learning_rate": 0.00029620886394789885, | |
| "loss": 0.005, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.13918947591767453, | |
| "grad_norm": 0.03176519274711609, | |
| "learning_rate": 0.00029610178754135, | |
| "loss": 0.0038, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.1408869085508169, | |
| "grad_norm": 0.006855768151581287, | |
| "learning_rate": 0.00029599323989142263, | |
| "loss": 0.0004, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.14258434118395927, | |
| "grad_norm": 0.013548546470701694, | |
| "learning_rate": 0.00029588322209119037, | |
| "loss": 0.0007, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.14428177381710164, | |
| "grad_norm": 0.032073307782411575, | |
| "learning_rate": 0.00029577173524853123, | |
| "loss": 0.0023, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.145979206450244, | |
| "grad_norm": 0.06568052619695663, | |
| "learning_rate": 0.0002956587804861165, | |
| "loss": 0.003, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.14767663908338638, | |
| "grad_norm": 0.017053432762622833, | |
| "learning_rate": 0.0002955443589413994, | |
| "loss": 0.0011, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.14937407171652875, | |
| "grad_norm": 0.027703823521733284, | |
| "learning_rate": 0.0002954284717666036, | |
| "loss": 0.0011, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.15107150434967112, | |
| "grad_norm": 0.028447195887565613, | |
| "learning_rate": 0.00029531112012871175, | |
| "loss": 0.002, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.1527689369828135, | |
| "grad_norm": 0.051351480185985565, | |
| "learning_rate": 0.0002951923052094534, | |
| "loss": 0.0023, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15446636961595586, | |
| "grad_norm": 0.04188869521021843, | |
| "learning_rate": 0.0002950720282052936, | |
| "loss": 0.0022, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.15616380224909823, | |
| "grad_norm": 0.03857725113630295, | |
| "learning_rate": 0.00029495029032742024, | |
| "loss": 0.0013, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.1578612348822406, | |
| "grad_norm": 0.030291402712464333, | |
| "learning_rate": 0.0002948270928017326, | |
| "loss": 0.0015, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.15955866751538297, | |
| "grad_norm": 0.05515044555068016, | |
| "learning_rate": 0.00029470243686882837, | |
| "loss": 0.0008, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.16125610014852534, | |
| "grad_norm": 0.0681704506278038, | |
| "learning_rate": 0.00029457632378399127, | |
| "loss": 0.0016, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.16295353278166771, | |
| "grad_norm": 0.17659763991832733, | |
| "learning_rate": 0.0002944487548171788, | |
| "loss": 0.0015, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.1646509654148101, | |
| "grad_norm": 0.01778286136686802, | |
| "learning_rate": 0.00029431973125300907, | |
| "loss": 0.0003, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.16634839804795248, | |
| "grad_norm": 0.052063290029764175, | |
| "learning_rate": 0.0002941892543907478, | |
| "loss": 0.0042, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.16804583068109485, | |
| "grad_norm": 0.08560975641012192, | |
| "learning_rate": 0.00029405732554429564, | |
| "loss": 0.003, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.16974326331423722, | |
| "grad_norm": 0.07182486355304718, | |
| "learning_rate": 0.0002939239460421746, | |
| "loss": 0.0091, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16974326331423722, | |
| "eval_loss": 0.4275517165660858, | |
| "eval_runtime": 65.6527, | |
| "eval_samples_per_second": 2.94, | |
| "eval_steps_per_second": 2.94, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1714406959473796, | |
| "grad_norm": 0.33816632628440857, | |
| "learning_rate": 0.0002937891172275147, | |
| "loss": 0.6861, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.17313812858052197, | |
| "grad_norm": 0.24974839389324188, | |
| "learning_rate": 0.00029365284045804077, | |
| "loss": 0.7581, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.17483556121366434, | |
| "grad_norm": 0.389892041683197, | |
| "learning_rate": 0.00029351511710605825, | |
| "loss": 0.8517, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.1765329938468067, | |
| "grad_norm": 0.21865390241146088, | |
| "learning_rate": 0.0002933759485584397, | |
| "loss": 0.7927, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.17823042647994908, | |
| "grad_norm": 0.2867435812950134, | |
| "learning_rate": 0.00029323533621661106, | |
| "loss": 0.8931, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.17992785911309145, | |
| "grad_norm": 0.19504129886627197, | |
| "learning_rate": 0.0002930932814965369, | |
| "loss": 0.5056, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.18162529174623382, | |
| "grad_norm": 0.2704707980155945, | |
| "learning_rate": 0.00029294978582870666, | |
| "loss": 0.7927, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.1833227243793762, | |
| "grad_norm": 0.20052890479564667, | |
| "learning_rate": 0.0002928048506581202, | |
| "loss": 0.6507, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.18502015701251856, | |
| "grad_norm": 0.20652854442596436, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.6928, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.18671758964566093, | |
| "grad_norm": 0.2864634096622467, | |
| "learning_rate": 0.00029251066766114176, | |
| "loss": 1.0405, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1884150222788033, | |
| "grad_norm": 0.2000068873167038, | |
| "learning_rate": 0.0002923614227971694, | |
| "loss": 0.5787, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.19011245491194567, | |
| "grad_norm": 0.16141685843467712, | |
| "learning_rate": 0.0002922107443552499, | |
| "loss": 0.4154, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.19180988754508804, | |
| "grad_norm": 0.2669724225997925, | |
| "learning_rate": 0.00029205863385271363, | |
| "loss": 0.9767, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.1935073201782304, | |
| "grad_norm": 0.7105275988578796, | |
| "learning_rate": 0.00029190509282131153, | |
| "loss": 0.6763, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.1952047528113728, | |
| "grad_norm": 0.23595799505710602, | |
| "learning_rate": 0.00029175012280720024, | |
| "loss": 0.6856, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.19690218544451518, | |
| "grad_norm": 0.23921440541744232, | |
| "learning_rate": 0.00029159372537092596, | |
| "loss": 0.7075, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.19859961807765755, | |
| "grad_norm": 0.21551960706710815, | |
| "learning_rate": 0.0002914359020874092, | |
| "loss": 0.6004, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.20029705071079992, | |
| "grad_norm": 0.20390333235263824, | |
| "learning_rate": 0.0002912766545459287, | |
| "loss": 0.57, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.2019944833439423, | |
| "grad_norm": 0.15612931549549103, | |
| "learning_rate": 0.0002911159843501053, | |
| "loss": 0.2055, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.20369191597708466, | |
| "grad_norm": 0.17460142076015472, | |
| "learning_rate": 0.0002909538931178862, | |
| "loss": 0.371, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.20538934861022703, | |
| "grad_norm": 0.18853937089443207, | |
| "learning_rate": 0.00029079038248152835, | |
| "loss": 0.4252, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.2070867812433694, | |
| "grad_norm": 0.14426594972610474, | |
| "learning_rate": 0.0002906254540875819, | |
| "loss": 0.2658, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.20878421387651178, | |
| "grad_norm": 0.16134832799434662, | |
| "learning_rate": 0.0002904591095968741, | |
| "loss": 0.297, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.21048164650965415, | |
| "grad_norm": 0.3797933757305145, | |
| "learning_rate": 0.00029029135068449195, | |
| "loss": 0.2837, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.21217907914279652, | |
| "grad_norm": 0.038109440356492996, | |
| "learning_rate": 0.000290122179039766, | |
| "loss": 0.0149, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2138765117759389, | |
| "grad_norm": 0.11762002855539322, | |
| "learning_rate": 0.00028995159636625276, | |
| "loss": 0.0684, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.21557394440908126, | |
| "grad_norm": 0.02665620669722557, | |
| "learning_rate": 0.00028977960438171784, | |
| "loss": 0.0044, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.21727137704222363, | |
| "grad_norm": 0.03071051463484764, | |
| "learning_rate": 0.0002896062048181186, | |
| "loss": 0.0018, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.218968809675366, | |
| "grad_norm": 0.009578248485922813, | |
| "learning_rate": 0.00028943139942158683, | |
| "loss": 0.0004, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.22066624230850837, | |
| "grad_norm": 0.0018459237180650234, | |
| "learning_rate": 0.0002892551899524109, | |
| "loss": 0.0001, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.22236367494165074, | |
| "grad_norm": 0.09641125798225403, | |
| "learning_rate": 0.0002890775781850181, | |
| "loss": 0.0588, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.22406110757479314, | |
| "grad_norm": 0.008955306373536587, | |
| "learning_rate": 0.000288898565907957, | |
| "loss": 0.0002, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.2257585402079355, | |
| "grad_norm": 0.4112979471683502, | |
| "learning_rate": 0.0002887181549238793, | |
| "loss": 0.0037, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.22745597284107788, | |
| "grad_norm": 0.0008860170491971076, | |
| "learning_rate": 0.00028853634704952165, | |
| "loss": 0.0001, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.22915340547422025, | |
| "grad_norm": 0.03983623534440994, | |
| "learning_rate": 0.0002883531441156872, | |
| "loss": 0.0014, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.23085083810736262, | |
| "grad_norm": 0.13147315382957458, | |
| "learning_rate": 0.00028816854796722747, | |
| "loss": 0.0039, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.232548270740505, | |
| "grad_norm": 0.027041589841246605, | |
| "learning_rate": 0.00028798256046302375, | |
| "loss": 0.003, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.23424570337364736, | |
| "grad_norm": 0.012492002919316292, | |
| "learning_rate": 0.000287795183475968, | |
| "loss": 0.0006, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.23594313600678973, | |
| "grad_norm": 0.004202733281999826, | |
| "learning_rate": 0.00028760641889294446, | |
| "loss": 0.0002, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.2376405686399321, | |
| "grad_norm": 0.004685190040618181, | |
| "learning_rate": 0.0002874162686148104, | |
| "loss": 0.0003, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23933800127307447, | |
| "grad_norm": 0.009362437762320042, | |
| "learning_rate": 0.000287224734556377, | |
| "loss": 0.0007, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.24103543390621684, | |
| "grad_norm": 0.0981183648109436, | |
| "learning_rate": 0.0002870318186463901, | |
| "loss": 0.0042, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.24273286653935922, | |
| "grad_norm": 0.015274147503077984, | |
| "learning_rate": 0.00028683752282751074, | |
| "loss": 0.0007, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.24443029917250159, | |
| "grad_norm": 0.00900458823889494, | |
| "learning_rate": 0.0002866418490562957, | |
| "loss": 0.0007, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.24612773180564396, | |
| "grad_norm": 0.01067203190177679, | |
| "learning_rate": 0.00028644479930317775, | |
| "loss": 0.0006, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.24782516443878633, | |
| "grad_norm": 0.022083261981606483, | |
| "learning_rate": 0.0002862463755524455, | |
| "loss": 0.0006, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.2495225970719287, | |
| "grad_norm": 0.003914229571819305, | |
| "learning_rate": 0.00028604657980222417, | |
| "loss": 0.0003, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.25122002970507107, | |
| "grad_norm": 0.005544353276491165, | |
| "learning_rate": 0.0002858454140644546, | |
| "loss": 0.0004, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.25291746233821344, | |
| "grad_norm": 0.006152280140668154, | |
| "learning_rate": 0.00028564288036487357, | |
| "loss": 0.0005, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.2546148949713558, | |
| "grad_norm": 0.04355669021606445, | |
| "learning_rate": 0.00028543898074299317, | |
| "loss": 0.0053, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2546148949713558, | |
| "eval_loss": 0.42699772119522095, | |
| "eval_runtime": 65.6214, | |
| "eval_samples_per_second": 2.941, | |
| "eval_steps_per_second": 2.941, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2563123276044982, | |
| "grad_norm": 0.33021700382232666, | |
| "learning_rate": 0.00028523371725208035, | |
| "loss": 0.7046, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.25800976023764055, | |
| "grad_norm": 0.29715627431869507, | |
| "learning_rate": 0.00028502709195913614, | |
| "loss": 0.8173, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.2597071928707829, | |
| "grad_norm": 0.23798537254333496, | |
| "learning_rate": 0.000284819106944875, | |
| "loss": 0.8376, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.2614046255039253, | |
| "grad_norm": 0.24740736186504364, | |
| "learning_rate": 0.0002846097643037037, | |
| "loss": 0.8829, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.26310205813706766, | |
| "grad_norm": 0.8396446704864502, | |
| "learning_rate": 0.00028439906614370034, | |
| "loss": 0.8286, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.26479949077021003, | |
| "grad_norm": 0.271604061126709, | |
| "learning_rate": 0.00028418701458659304, | |
| "loss": 0.8996, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.2664969234033524, | |
| "grad_norm": 0.2267700582742691, | |
| "learning_rate": 0.00028397361176773855, | |
| "loss": 0.6639, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.2681943560364948, | |
| "grad_norm": 0.19427096843719482, | |
| "learning_rate": 0.000283758859836101, | |
| "loss": 0.4771, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.2698917886696372, | |
| "grad_norm": 0.1682572066783905, | |
| "learning_rate": 0.0002835427609542298, | |
| "loss": 0.407, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.27158922130277957, | |
| "grad_norm": 0.22453951835632324, | |
| "learning_rate": 0.0002833253172982385, | |
| "loss": 0.6087, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.27328665393592194, | |
| "grad_norm": 0.2826938331127167, | |
| "learning_rate": 0.00028310653105778215, | |
| "loss": 0.8161, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.2749840865690643, | |
| "grad_norm": 0.26969850063323975, | |
| "learning_rate": 0.0002828864044360358, | |
| "loss": 0.9043, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.2766815192022067, | |
| "grad_norm": 0.2145734280347824, | |
| "learning_rate": 0.0002826649396496721, | |
| "loss": 0.5051, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.27837895183534905, | |
| "grad_norm": 0.22222040593624115, | |
| "learning_rate": 0.000282442138928839, | |
| "loss": 0.6356, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.2800763844684914, | |
| "grad_norm": 0.1878889799118042, | |
| "learning_rate": 0.0002822180045171373, | |
| "loss": 0.4778, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.2817738171016338, | |
| "grad_norm": 0.1969398856163025, | |
| "learning_rate": 0.00028199253867159795, | |
| "loss": 0.4855, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.28347124973477617, | |
| "grad_norm": 0.11540260910987854, | |
| "learning_rate": 0.0002817657436626596, | |
| "loss": 0.1777, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.28516868236791854, | |
| "grad_norm": 0.14375105500221252, | |
| "learning_rate": 0.0002815376217741454, | |
| "loss": 0.3379, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.2868661150010609, | |
| "grad_norm": 0.4472449719905853, | |
| "learning_rate": 0.0002813081753032403, | |
| "loss": 0.5727, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.2885635476342033, | |
| "grad_norm": 0.24242308735847473, | |
| "learning_rate": 0.0002810774065604677, | |
| "loss": 0.3351, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29026098026734565, | |
| "grad_norm": 0.13647812604904175, | |
| "learning_rate": 0.0002808453178696663, | |
| "loss": 0.2388, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.291958412900488, | |
| "grad_norm": 0.13304531574249268, | |
| "learning_rate": 0.00028061191156796656, | |
| "loss": 0.2208, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.2936558455336304, | |
| "grad_norm": 0.13337798416614532, | |
| "learning_rate": 0.0002803771900057674, | |
| "loss": 0.1881, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.29535327816677276, | |
| "grad_norm": 0.12482510507106781, | |
| "learning_rate": 0.00028014115554671236, | |
| "loss": 0.1659, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.29705071079991513, | |
| "grad_norm": 0.05092178285121918, | |
| "learning_rate": 0.0002799038105676658, | |
| "loss": 0.0022, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2987481434330575, | |
| "grad_norm": 0.03115926869213581, | |
| "learning_rate": 0.000279665157458689, | |
| "loss": 0.007, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.30044557606619987, | |
| "grad_norm": 0.048752959817647934, | |
| "learning_rate": 0.0002794251986230161, | |
| "loss": 0.0231, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.30214300869934224, | |
| "grad_norm": 0.049951329827308655, | |
| "learning_rate": 0.0002791839364770301, | |
| "loss": 0.024, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.3038404413324846, | |
| "grad_norm": 0.019635546952486038, | |
| "learning_rate": 0.00027894137345023785, | |
| "loss": 0.0009, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.305537873965627, | |
| "grad_norm": 0.008390502072870731, | |
| "learning_rate": 0.0002786975119852465, | |
| "loss": 0.0002, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.30723530659876935, | |
| "grad_norm": 0.030752401798963547, | |
| "learning_rate": 0.00027845235453773836, | |
| "loss": 0.0012, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.3089327392319117, | |
| "grad_norm": 0.004207144025713205, | |
| "learning_rate": 0.000278205903576446, | |
| "loss": 0.0001, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.3106301718650541, | |
| "grad_norm": 0.012170841917395592, | |
| "learning_rate": 0.00027795816158312803, | |
| "loss": 0.0004, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.31232760449819646, | |
| "grad_norm": 0.004860470537096262, | |
| "learning_rate": 0.0002777091310525435, | |
| "loss": 0.0002, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.31402503713133884, | |
| "grad_norm": 0.004869968164712191, | |
| "learning_rate": 0.00027745881449242713, | |
| "loss": 0.0002, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.3157224697644812, | |
| "grad_norm": 0.011595932766795158, | |
| "learning_rate": 0.00027720721442346387, | |
| "loss": 0.0003, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.3174199023976236, | |
| "grad_norm": 0.02118592895567417, | |
| "learning_rate": 0.0002769543333792636, | |
| "loss": 0.0012, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.31911733503076595, | |
| "grad_norm": 0.03935430571436882, | |
| "learning_rate": 0.00027670017390633573, | |
| "loss": 0.0003, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.3208147676639083, | |
| "grad_norm": 0.0356944277882576, | |
| "learning_rate": 0.0002764447385640632, | |
| "loss": 0.0008, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.3225122002970507, | |
| "grad_norm": 0.05277875065803528, | |
| "learning_rate": 0.0002761880299246772, | |
| "loss": 0.0007, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.32420963293019306, | |
| "grad_norm": 0.0025087774265557528, | |
| "learning_rate": 0.0002759300505732307, | |
| "loss": 0.0001, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.32590706556333543, | |
| "grad_norm": 0.002132557798177004, | |
| "learning_rate": 0.00027567080310757306, | |
| "loss": 0.0001, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.3276044981964778, | |
| "grad_norm": 0.0010882457718253136, | |
| "learning_rate": 0.0002754102901383233, | |
| "loss": 0.0001, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.3293019308296202, | |
| "grad_norm": 0.02085525542497635, | |
| "learning_rate": 0.0002751485142888443, | |
| "loss": 0.0004, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.3309993634627626, | |
| "grad_norm": 0.003921423573046923, | |
| "learning_rate": 0.0002748854781952157, | |
| "loss": 0.0001, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.33269679609590497, | |
| "grad_norm": 0.05576641112565994, | |
| "learning_rate": 0.0002746211845062082, | |
| "loss": 0.0027, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.33439422872904734, | |
| "grad_norm": 0.025059282779693604, | |
| "learning_rate": 0.0002743556358832562, | |
| "loss": 0.0009, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.3360916613621897, | |
| "grad_norm": 0.14736546576023102, | |
| "learning_rate": 0.00027408883500043156, | |
| "loss": 0.0117, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.3377890939953321, | |
| "grad_norm": 0.022192303091287613, | |
| "learning_rate": 0.00027382078454441606, | |
| "loss": 0.0005, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.33948652662847445, | |
| "grad_norm": 0.005171961151063442, | |
| "learning_rate": 0.0002735514872144749, | |
| "loss": 0.0002, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33948652662847445, | |
| "eval_loss": 0.42559075355529785, | |
| "eval_runtime": 65.6151, | |
| "eval_samples_per_second": 2.941, | |
| "eval_steps_per_second": 2.941, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3411839592616168, | |
| "grad_norm": 0.5887985825538635, | |
| "learning_rate": 0.0002732809457224292, | |
| "loss": 0.9434, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.3428813918947592, | |
| "grad_norm": 0.38302966952323914, | |
| "learning_rate": 0.00027300916279262866, | |
| "loss": 1.0988, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.34457882452790156, | |
| "grad_norm": 0.2614414095878601, | |
| "learning_rate": 0.0002727361411619245, | |
| "loss": 0.6772, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.34627625716104393, | |
| "grad_norm": 0.3063081204891205, | |
| "learning_rate": 0.0002724618835796414, | |
| "loss": 0.7314, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.3479736897941863, | |
| "grad_norm": 0.18658895790576935, | |
| "learning_rate": 0.0002721863928075503, | |
| "loss": 0.514, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.3496711224273287, | |
| "grad_norm": 0.282010018825531, | |
| "learning_rate": 0.0002719096716198402, | |
| "loss": 0.892, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.35136855506047104, | |
| "grad_norm": 0.17541489005088806, | |
| "learning_rate": 0.00027163172280309026, | |
| "loss": 0.5047, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.3530659876936134, | |
| "grad_norm": 0.21916832029819489, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.7146, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.3547634203267558, | |
| "grad_norm": 0.20561501383781433, | |
| "learning_rate": 0.0002710721534905712, | |
| "loss": 0.6104, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.35646085295989816, | |
| "grad_norm": 0.1947142332792282, | |
| "learning_rate": 0.00027079053862965875, | |
| "loss": 0.4924, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3581582855930405, | |
| "grad_norm": 0.23798146843910217, | |
| "learning_rate": 0.00027050770740936336, | |
| "loss": 0.6153, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.3598557182261829, | |
| "grad_norm": 0.21775560081005096, | |
| "learning_rate": 0.00027022366267779224, | |
| "loss": 0.4658, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.36155315085932527, | |
| "grad_norm": 0.24994409084320068, | |
| "learning_rate": 0.0002699384072952727, | |
| "loss": 0.5979, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.36325058349246764, | |
| "grad_norm": 0.28469640016555786, | |
| "learning_rate": 0.0002696519441343233, | |
| "loss": 0.8796, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.36494801612561, | |
| "grad_norm": 0.2747570276260376, | |
| "learning_rate": 0.0002693642760796248, | |
| "loss": 0.8625, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.3666454487587524, | |
| "grad_norm": 0.2469591647386551, | |
| "learning_rate": 0.00026907540602799136, | |
| "loss": 0.6991, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.36834288139189475, | |
| "grad_norm": 0.20425763726234436, | |
| "learning_rate": 0.00026878533688834123, | |
| "loss": 0.5774, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.3700403140250371, | |
| "grad_norm": 0.2737872898578644, | |
| "learning_rate": 0.0002684940715816674, | |
| "loss": 0.9062, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.3717377466581795, | |
| "grad_norm": 0.2064121514558792, | |
| "learning_rate": 0.00026820161304100823, | |
| "loss": 0.5054, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.37343517929132186, | |
| "grad_norm": 0.14863868057727814, | |
| "learning_rate": 0.00026790796421141813, | |
| "loss": 0.285, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.37513261192446423, | |
| "grad_norm": 0.12498918920755386, | |
| "learning_rate": 0.00026761312804993734, | |
| "loss": 0.1999, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.3768300445576066, | |
| "grad_norm": 0.1726280152797699, | |
| "learning_rate": 0.0002673171075255629, | |
| "loss": 0.2852, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.378527477190749, | |
| "grad_norm": 0.1533537358045578, | |
| "learning_rate": 0.0002670199056192181, | |
| "loss": 0.3106, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.38022490982389134, | |
| "grad_norm": 0.125217467546463, | |
| "learning_rate": 0.00026672152532372287, | |
| "loss": 0.1804, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.3819223424570337, | |
| "grad_norm": 0.05522383376955986, | |
| "learning_rate": 0.0002664219696437635, | |
| "loss": 0.0442, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.3836197750901761, | |
| "grad_norm": 0.04138198867440224, | |
| "learning_rate": 0.00026612124159586237, | |
| "loss": 0.023, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.38531720772331846, | |
| "grad_norm": 0.05575822666287422, | |
| "learning_rate": 0.0002658193442083475, | |
| "loss": 0.0024, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.3870146403564608, | |
| "grad_norm": 0.12629126012325287, | |
| "learning_rate": 0.0002655162805213223, | |
| "loss": 0.1524, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.38871207298960325, | |
| "grad_norm": 0.02942221239209175, | |
| "learning_rate": 0.00026521205358663477, | |
| "loss": 0.0096, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.3904095056227456, | |
| "grad_norm": 0.0953650251030922, | |
| "learning_rate": 0.00026490666646784665, | |
| "loss": 0.0043, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.392106938255888, | |
| "grad_norm": 0.005734459031373262, | |
| "learning_rate": 0.00026460012224020297, | |
| "loss": 0.0003, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.39380437088903036, | |
| "grad_norm": 0.010758363641798496, | |
| "learning_rate": 0.0002642924239906006, | |
| "loss": 0.0003, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.39550180352217273, | |
| "grad_norm": 0.01772010512650013, | |
| "learning_rate": 0.0002639835748175575, | |
| "loss": 0.0007, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.3971992361553151, | |
| "grad_norm": 0.005056055262684822, | |
| "learning_rate": 0.0002636735778311815, | |
| "loss": 0.0002, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.3988966687884575, | |
| "grad_norm": 0.24263891577720642, | |
| "learning_rate": 0.00026336243615313873, | |
| "loss": 0.0008, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.40059410142159985, | |
| "grad_norm": 0.0014849180588498712, | |
| "learning_rate": 0.0002630501529166224, | |
| "loss": 0.0001, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.4022915340547422, | |
| "grad_norm": 0.0037826071493327618, | |
| "learning_rate": 0.00026273673126632133, | |
| "loss": 0.0002, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.4039889666878846, | |
| "grad_norm": 0.08331254124641418, | |
| "learning_rate": 0.0002624221743583881, | |
| "loss": 0.0016, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.40568639932102696, | |
| "grad_norm": 0.002364553976804018, | |
| "learning_rate": 0.0002621064853604071, | |
| "loss": 0.0001, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.40738383195416933, | |
| "grad_norm": 0.014542756602168083, | |
| "learning_rate": 0.0002617896674513632, | |
| "loss": 0.0002, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4090812645873117, | |
| "grad_norm": 0.0031418628059327602, | |
| "learning_rate": 0.00026147172382160914, | |
| "loss": 0.0001, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.41077869722045407, | |
| "grad_norm": 0.11094752699136734, | |
| "learning_rate": 0.00026115265767283374, | |
| "loss": 0.0031, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.41247612985359644, | |
| "grad_norm": 0.012769564054906368, | |
| "learning_rate": 0.0002608324722180296, | |
| "loss": 0.0005, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.4141735624867388, | |
| "grad_norm": 0.055052801966667175, | |
| "learning_rate": 0.0002605111706814607, | |
| "loss": 0.0023, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.4158709951198812, | |
| "grad_norm": 0.003668338293209672, | |
| "learning_rate": 0.00026018875629862996, | |
| "loss": 0.0002, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.41756842775302355, | |
| "grad_norm": 0.009973675012588501, | |
| "learning_rate": 0.0002598652323162466, | |
| "loss": 0.0003, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.4192658603861659, | |
| "grad_norm": 0.02005830593407154, | |
| "learning_rate": 0.0002595406019921936, | |
| "loss": 0.0008, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.4209632930193083, | |
| "grad_norm": 0.02860446274280548, | |
| "learning_rate": 0.0002592148685954946, | |
| "loss": 0.0024, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.42266072565245066, | |
| "grad_norm": 0.03582284599542618, | |
| "learning_rate": 0.0002588880354062814, | |
| "loss": 0.0014, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.42435815828559303, | |
| "grad_norm": 0.03657930716872215, | |
| "learning_rate": 0.0002585601057157605, | |
| "loss": 0.0023, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.42435815828559303, | |
| "eval_loss": 0.39342138171195984, | |
| "eval_runtime": 65.6277, | |
| "eval_samples_per_second": 2.941, | |
| "eval_steps_per_second": 2.941, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4260555909187354, | |
| "grad_norm": 0.3402771055698395, | |
| "learning_rate": 0.0002582310828261803, | |
| "loss": 0.955, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.4277530235518778, | |
| "grad_norm": 0.2694092392921448, | |
| "learning_rate": 0.00025790097005079764, | |
| "loss": 0.7843, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.42945045618502015, | |
| "grad_norm": 0.22484031319618225, | |
| "learning_rate": 0.00025756977071384455, | |
| "loss": 0.6626, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.4311478888181625, | |
| "grad_norm": 0.25034627318382263, | |
| "learning_rate": 0.0002572374881504945, | |
| "loss": 0.8865, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.4328453214513049, | |
| "grad_norm": 0.25369909405708313, | |
| "learning_rate": 0.00025690412570682946, | |
| "loss": 0.7099, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.43454275408444726, | |
| "grad_norm": 0.22795934975147247, | |
| "learning_rate": 0.0002565696867398053, | |
| "loss": 0.7818, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.43624018671758963, | |
| "grad_norm": 0.2158069759607315, | |
| "learning_rate": 0.00025623417461721884, | |
| "loss": 0.6434, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.437937619350732, | |
| "grad_norm": 0.2332068681716919, | |
| "learning_rate": 0.00025589759271767344, | |
| "loss": 0.8126, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.43963505198387437, | |
| "grad_norm": 0.21993213891983032, | |
| "learning_rate": 0.00025555994443054504, | |
| "loss": 0.6689, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.44133248461701674, | |
| "grad_norm": 0.26037323474884033, | |
| "learning_rate": 0.0002552212331559482, | |
| "loss": 0.992, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4430299172501591, | |
| "grad_norm": 0.2357717603445053, | |
| "learning_rate": 0.00025488146230470156, | |
| "loss": 0.7212, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.4447273498833015, | |
| "grad_norm": 0.22752051055431366, | |
| "learning_rate": 0.00025454063529829405, | |
| "loss": 0.7759, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.44642478251644385, | |
| "grad_norm": 0.20641978085041046, | |
| "learning_rate": 0.0002541987555688496, | |
| "loss": 0.6029, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.4481222151495863, | |
| "grad_norm": 1.728589415550232, | |
| "learning_rate": 0.0002538558265590934, | |
| "loss": 0.8527, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.44981964778272865, | |
| "grad_norm": 0.3176920711994171, | |
| "learning_rate": 0.0002535118517223168, | |
| "loss": 1.0045, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.451517080415871, | |
| "grad_norm": 0.22813205420970917, | |
| "learning_rate": 0.00025316683452234254, | |
| "loss": 0.5755, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.4532145130490134, | |
| "grad_norm": 0.27417638897895813, | |
| "learning_rate": 0.00025282077843349, | |
| "loss": 0.6442, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.45491194568215576, | |
| "grad_norm": 0.23180553317070007, | |
| "learning_rate": 0.00025247368694054017, | |
| "loss": 0.3961, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.45660937831529813, | |
| "grad_norm": 0.21716707944869995, | |
| "learning_rate": 0.0002521255635387005, | |
| "loss": 0.5498, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.4583068109484405, | |
| "grad_norm": 0.1608789563179016, | |
| "learning_rate": 0.0002517764117335698, | |
| "loss": 0.3229, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.4600042435815829, | |
| "grad_norm": 0.06968680769205093, | |
| "learning_rate": 0.00025142623504110286, | |
| "loss": 0.0545, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.46170167621472524, | |
| "grad_norm": 0.17753787338733673, | |
| "learning_rate": 0.0002510750369875752, | |
| "loss": 0.3944, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.4633991088478676, | |
| "grad_norm": 0.1846492886543274, | |
| "learning_rate": 0.0002507228211095471, | |
| "loss": 0.4219, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.46509654148101, | |
| "grad_norm": 0.12200163304805756, | |
| "learning_rate": 0.0002503695909538287, | |
| "loss": 0.1832, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.46679397411415235, | |
| "grad_norm": 0.08617426455020905, | |
| "learning_rate": 0.00025001535007744373, | |
| "loss": 0.0833, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.4684914067472947, | |
| "grad_norm": 0.10826346278190613, | |
| "learning_rate": 0.0002496601020475938, | |
| "loss": 0.1379, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.4701888393804371, | |
| "grad_norm": 0.09130895137786865, | |
| "learning_rate": 0.00024930385044162276, | |
| "loss": 0.0909, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.47188627201357947, | |
| "grad_norm": 0.01284122746437788, | |
| "learning_rate": 0.0002489465988469802, | |
| "loss": 0.0011, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.47358370464672184, | |
| "grad_norm": 0.03364328294992447, | |
| "learning_rate": 0.0002485883508611858, | |
| "loss": 0.0151, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.4752811372798642, | |
| "grad_norm": 0.005700011737644672, | |
| "learning_rate": 0.00024822911009179276, | |
| "loss": 0.0004, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4769785699130066, | |
| "grad_norm": 0.026785628870129585, | |
| "learning_rate": 0.0002478688801563516, | |
| "loss": 0.0022, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.47867600254614895, | |
| "grad_norm": 0.014533424749970436, | |
| "learning_rate": 0.00024750766468237387, | |
| "loss": 0.0009, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.4803734351792913, | |
| "grad_norm": 0.02565724588930607, | |
| "learning_rate": 0.0002471454673072953, | |
| "loss": 0.0015, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.4820708678124337, | |
| "grad_norm": 0.01476586889475584, | |
| "learning_rate": 0.0002467822916784394, | |
| "loss": 0.0007, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.48376830044557606, | |
| "grad_norm": 0.0030139784794300795, | |
| "learning_rate": 0.0002464181414529809, | |
| "loss": 0.0001, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.48546573307871843, | |
| "grad_norm": 0.013711950741708279, | |
| "learning_rate": 0.00024605302029790836, | |
| "loss": 0.0002, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.4871631657118608, | |
| "grad_norm": 0.0045742918737232685, | |
| "learning_rate": 0.00024568693188998776, | |
| "loss": 0.0002, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.48886059834500317, | |
| "grad_norm": 0.01617550477385521, | |
| "learning_rate": 0.00024531987991572543, | |
| "loss": 0.0008, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.49055803097814554, | |
| "grad_norm": 0.0015017741825431585, | |
| "learning_rate": 0.00024495186807133056, | |
| "loss": 0.0001, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.4922554636112879, | |
| "grad_norm": 0.04141293093562126, | |
| "learning_rate": 0.00024458290006267833, | |
| "loss": 0.0021, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4939528962444303, | |
| "grad_norm": 0.03005625680088997, | |
| "learning_rate": 0.0002442129796052726, | |
| "loss": 0.0015, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.49565032887757265, | |
| "grad_norm": 0.0004941977094858885, | |
| "learning_rate": 0.00024384211042420822, | |
| "loss": 0.0, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.497347761510715, | |
| "grad_norm": 0.0018400073749944568, | |
| "learning_rate": 0.00024347029625413364, | |
| "loss": 0.0001, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.4990451941438574, | |
| "grad_norm": 0.023964567109942436, | |
| "learning_rate": 0.00024309754083921354, | |
| "loss": 0.0008, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.5007426267769998, | |
| "grad_norm": 0.00808011181652546, | |
| "learning_rate": 0.00024272384793309077, | |
| "loss": 0.0003, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.5024400594101421, | |
| "grad_norm": 0.026506319642066956, | |
| "learning_rate": 0.0002423492212988487, | |
| "loss": 0.0011, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.5041374920432845, | |
| "grad_norm": 0.0033183887135237455, | |
| "learning_rate": 0.0002419736647089735, | |
| "loss": 0.0001, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.5058349246764269, | |
| "grad_norm": 0.0012288711732253432, | |
| "learning_rate": 0.00024159718194531572, | |
| "loss": 0.0001, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.5075323573095692, | |
| "grad_norm": 0.001825229381211102, | |
| "learning_rate": 0.00024121977679905266, | |
| "loss": 0.0001, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.5092297899427116, | |
| "grad_norm": 0.0013848728267475963, | |
| "learning_rate": 0.00024084145307064997, | |
| "loss": 0.0001, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5092297899427116, | |
| "eval_loss": 0.408105731010437, | |
| "eval_runtime": 65.5854, | |
| "eval_samples_per_second": 2.943, | |
| "eval_steps_per_second": 2.943, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.510927222575854, | |
| "grad_norm": 0.6500065922737122, | |
| "learning_rate": 0.0002404622145698234, | |
| "loss": 1.2109, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.5126246552089964, | |
| "grad_norm": 0.2953287661075592, | |
| "learning_rate": 0.00024008206511550044, | |
| "loss": 0.8961, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.5143220878421387, | |
| "grad_norm": 0.2599642276763916, | |
| "learning_rate": 0.00023970100853578185, | |
| "loss": 0.822, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.5160195204752811, | |
| "grad_norm": 0.22075462341308594, | |
| "learning_rate": 0.00023931904866790317, | |
| "loss": 0.7042, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.5177169531084235, | |
| "grad_norm": 0.1947249174118042, | |
| "learning_rate": 0.00023893618935819607, | |
| "loss": 0.6038, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.5194143857415658, | |
| "grad_norm": 0.1981605589389801, | |
| "learning_rate": 0.00023855243446204946, | |
| "loss": 0.5842, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.5211118183747082, | |
| "grad_norm": 0.25752243399620056, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.7636, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.5228092510078506, | |
| "grad_norm": 0.20701764523983002, | |
| "learning_rate": 0.00023778225337704772, | |
| "loss": 0.5711, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.524506683640993, | |
| "grad_norm": 0.1890690177679062, | |
| "learning_rate": 0.00023739583494390752, | |
| "loss": 0.5323, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.5262041162741353, | |
| "grad_norm": 0.2634682059288025, | |
| "learning_rate": 0.0002370085364356797, | |
| "loss": 0.8929, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5279015489072777, | |
| "grad_norm": 0.21140585839748383, | |
| "learning_rate": 0.00023662036175245595, | |
| "loss": 0.6722, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.5295989815404201, | |
| "grad_norm": 0.1461462825536728, | |
| "learning_rate": 0.00023623131480315107, | |
| "loss": 0.3355, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.5312964141735624, | |
| "grad_norm": 0.25913017988204956, | |
| "learning_rate": 0.00023584139950546344, | |
| "loss": 0.809, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.5329938468067048, | |
| "grad_norm": 0.20216749608516693, | |
| "learning_rate": 0.0002354506197858358, | |
| "loss": 0.522, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.5346912794398472, | |
| "grad_norm": 0.19447529315948486, | |
| "learning_rate": 0.00023505897957941556, | |
| "loss": 0.4756, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.5363887120729895, | |
| "grad_norm": 0.20887967944145203, | |
| "learning_rate": 0.00023466648283001538, | |
| "loss": 0.5348, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.538086144706132, | |
| "grad_norm": 0.2380082756280899, | |
| "learning_rate": 0.000234273133490073, | |
| "loss": 0.6786, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.5397835773392744, | |
| "grad_norm": 0.13057811558246613, | |
| "learning_rate": 0.00023387893552061199, | |
| "loss": 0.2262, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.5414810099724168, | |
| "grad_norm": 0.19371569156646729, | |
| "learning_rate": 0.00023348389289120158, | |
| "loss": 0.4282, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.5431784426055591, | |
| "grad_norm": 0.20126739144325256, | |
| "learning_rate": 0.00023308800957991653, | |
| "loss": 0.4524, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5448758752387015, | |
| "grad_norm": 0.1577330082654953, | |
| "learning_rate": 0.00023269128957329748, | |
| "loss": 0.2979, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.5465733078718439, | |
| "grad_norm": 0.1581580936908722, | |
| "learning_rate": 0.0002322937368663105, | |
| "loss": 0.2393, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.5482707405049863, | |
| "grad_norm": 0.0836775079369545, | |
| "learning_rate": 0.00023189535546230683, | |
| "loss": 0.0756, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.5499681731381286, | |
| "grad_norm": 0.13577239215373993, | |
| "learning_rate": 0.00023149614937298296, | |
| "loss": 0.204, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.551665605771271, | |
| "grad_norm": 0.003654525149613619, | |
| "learning_rate": 0.00023109612261833963, | |
| "loss": 0.0001, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.5533630384044134, | |
| "grad_norm": 0.0016976917395368218, | |
| "learning_rate": 0.00023069527922664186, | |
| "loss": 0.0001, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.5550604710375557, | |
| "grad_norm": 0.006387701723724604, | |
| "learning_rate": 0.00023029362323437818, | |
| "loss": 0.0002, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.5567579036706981, | |
| "grad_norm": 0.0010255499510094523, | |
| "learning_rate": 0.00022989115868621995, | |
| "loss": 0.0001, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.5584553363038405, | |
| "grad_norm": 0.002511462429538369, | |
| "learning_rate": 0.0002294878896349807, | |
| "loss": 0.0001, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.5601527689369828, | |
| "grad_norm": 0.002243687631562352, | |
| "learning_rate": 0.00022908382014157533, | |
| "loss": 0.0001, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5618502015701252, | |
| "grad_norm": 0.0010394121054559946, | |
| "learning_rate": 0.00022867895427497914, | |
| "loss": 0.0, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.5635476342032676, | |
| "grad_norm": 0.004921845626085997, | |
| "learning_rate": 0.00022827329611218688, | |
| "loss": 0.0002, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.56524506683641, | |
| "grad_norm": 0.006571977864950895, | |
| "learning_rate": 0.0002278668497381718, | |
| "loss": 0.0003, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.5669424994695523, | |
| "grad_norm": 0.06410548835992813, | |
| "learning_rate": 0.00022745961924584428, | |
| "loss": 0.0393, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.5686399321026947, | |
| "grad_norm": 0.0016587848076596856, | |
| "learning_rate": 0.00022705160873601096, | |
| "loss": 0.0001, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.5703373647358371, | |
| "grad_norm": 0.002642609179019928, | |
| "learning_rate": 0.00022664282231733309, | |
| "loss": 0.0001, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.5720347973689794, | |
| "grad_norm": 0.09959813952445984, | |
| "learning_rate": 0.00022623326410628534, | |
| "loss": 0.0009, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.5737322300021218, | |
| "grad_norm": 0.0017017674399539828, | |
| "learning_rate": 0.00022582293822711444, | |
| "loss": 0.0001, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.5754296626352642, | |
| "grad_norm": 0.0015052666421979666, | |
| "learning_rate": 0.00022541184881179737, | |
| "loss": 0.0001, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.5771270952684066, | |
| "grad_norm": 0.0034250568132847548, | |
| "learning_rate": 0.000225, | |
| "loss": 0.0001, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5788245279015489, | |
| "grad_norm": 0.004533613566309214, | |
| "learning_rate": 0.0002245873959390353, | |
| "loss": 0.0001, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.5805219605346913, | |
| "grad_norm": 0.0014232480898499489, | |
| "learning_rate": 0.00022417404078382152, | |
| "loss": 0.0001, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.5822193931678337, | |
| "grad_norm": 0.0018840961856767535, | |
| "learning_rate": 0.00022375993869684058, | |
| "loss": 0.0, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.583916825800976, | |
| "grad_norm": 0.0005610976368188858, | |
| "learning_rate": 0.00022334509384809584, | |
| "loss": 0.0, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.5856142584341184, | |
| "grad_norm": 0.011308716610074043, | |
| "learning_rate": 0.00022292951041507028, | |
| "loss": 0.0003, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.5873116910672608, | |
| "grad_norm": 0.008396640419960022, | |
| "learning_rate": 0.00022251319258268453, | |
| "loss": 0.0001, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.5890091237004031, | |
| "grad_norm": 0.016598394140601158, | |
| "learning_rate": 0.00022209614454325459, | |
| "loss": 0.0002, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.5907065563335455, | |
| "grad_norm": 0.0011634851107373834, | |
| "learning_rate": 0.00022167837049644947, | |
| "loss": 0.0, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.5924039889666879, | |
| "grad_norm": 0.05063653737306595, | |
| "learning_rate": 0.00022125987464924926, | |
| "loss": 0.0006, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.5941014215998303, | |
| "grad_norm": 0.030548613518476486, | |
| "learning_rate": 0.0002208406612159024, | |
| "loss": 0.0005, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5941014215998303, | |
| "eval_loss": 0.403373122215271, | |
| "eval_runtime": 65.5747, | |
| "eval_samples_per_second": 2.943, | |
| "eval_steps_per_second": 2.943, | |
| "step": 350 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2671983590244352e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |