| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.19990004997501248, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 3.3340563149001086, | |
| "learning_rate": 0.0, | |
| "loss": 11.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.398812329952019, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 10.125, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.394322446895115, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 10.1172, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.9958816684399585, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 9.875, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.8270465897882062, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 9.6641, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.7854046471397795, | |
| "learning_rate": 0.0003, | |
| "loss": 9.4844, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.719416749115252, | |
| "learning_rate": 0.00035999999999999997, | |
| "loss": 9.3281, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.4637825746112274, | |
| "learning_rate": 0.00041999999999999996, | |
| "loss": 9.2109, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.4393631015406718, | |
| "learning_rate": 0.00047999999999999996, | |
| "loss": 8.9453, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.2936734586915988, | |
| "learning_rate": 0.00054, | |
| "loss": 8.7109, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.0756922378227356, | |
| "learning_rate": 0.0005999986405514987, | |
| "loss": 8.4609, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.9277829127413892, | |
| "learning_rate": 0.0005999945622196846, | |
| "loss": 8.2344, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.8084581786682467, | |
| "learning_rate": 0.0005999877650456265, | |
| "loss": 8.125, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.7635084596900947, | |
| "learning_rate": 0.000599978249097772, | |
| "loss": 7.9766, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.9186699644247788, | |
| "learning_rate": 0.0005999660144719463, | |
| "loss": 7.8555, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6609504256551479, | |
| "learning_rate": 0.0005999510612913519, | |
| "loss": 7.7734, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.7086232844782971, | |
| "learning_rate": 0.0005999333897065673, | |
| "loss": 7.7148, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 16.38048851691348, | |
| "learning_rate": 0.0005999129998955453, | |
| "loss": 8.4844, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.3057527590449889, | |
| "learning_rate": 0.0005998898920636111, | |
| "loss": 7.7539, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6966048242948986, | |
| "learning_rate": 0.00059986406644346, | |
| "loss": 7.75, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6348089115348993, | |
| "learning_rate": 0.0005998355232951559, | |
| "loss": 7.7031, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.7829163518610293, | |
| "learning_rate": 0.0005998042629061279, | |
| "loss": 7.6992, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.5900591778980369, | |
| "learning_rate": 0.0005997702855911678, | |
| "loss": 7.6016, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.4655170213064256, | |
| "learning_rate": 0.0005997335916924268, | |
| "loss": 7.5977, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.6287348258915756, | |
| "learning_rate": 0.0005996941815794121, | |
| "loss": 7.5586, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.6137321903884564, | |
| "learning_rate": 0.0005996520556489831, | |
| "loss": 7.5898, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.44962562710631065, | |
| "learning_rate": 0.0005996072143253473, | |
| "loss": 7.4336, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.46130046454703316, | |
| "learning_rate": 0.0005995596580600566, | |
| "loss": 7.4023, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.4686712675731326, | |
| "learning_rate": 0.0005995093873320018, | |
| "loss": 7.3789, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.4672147564288997, | |
| "learning_rate": 0.0005994564026474087, | |
| "loss": 7.3711, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.40408354581233474, | |
| "learning_rate": 0.0005994007045398324, | |
| "loss": 7.3672, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.46032146732584733, | |
| "learning_rate": 0.0005993422935701524, | |
| "loss": 7.3477, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.4765534634593268, | |
| "learning_rate": 0.0005992811703265664, | |
| "loss": 7.3555, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.46208489386235113, | |
| "learning_rate": 0.0005992173354245849, | |
| "loss": 7.3047, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.2956144524964961, | |
| "learning_rate": 0.0005991507895070244, | |
| "loss": 7.3125, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.4834645389868856, | |
| "learning_rate": 0.0005990815332440017, | |
| "loss": 7.207, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.4411831350968505, | |
| "learning_rate": 0.0005990095673329266, | |
| "loss": 7.1758, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.24809297748968667, | |
| "learning_rate": 0.0005989348924984951, | |
| "loss": 7.2188, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.39402988416840584, | |
| "learning_rate": 0.0005988575094926817, | |
| "loss": 7.1953, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3868345222189167, | |
| "learning_rate": 0.0005987774190947328, | |
| "loss": 7.1641, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3777261230135448, | |
| "learning_rate": 0.0005986946221111575, | |
| "loss": 7.1328, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.4687511444077827, | |
| "learning_rate": 0.0005986091193757206, | |
| "loss": 7.0898, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.34935796211612463, | |
| "learning_rate": 0.0005985209117494337, | |
| "loss": 7.1367, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.38764476686849886, | |
| "learning_rate": 0.0005984300001205466, | |
| "loss": 7.125, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3956487898882936, | |
| "learning_rate": 0.0005983363854045386, | |
| "loss": 7.1094, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.31140257544677513, | |
| "learning_rate": 0.0005982400685441084, | |
| "loss": 7.0898, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3664476570531787, | |
| "learning_rate": 0.0005981410505091662, | |
| "loss": 7.0664, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.31891741142945207, | |
| "learning_rate": 0.0005980393322968223, | |
| "loss": 7.0273, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.4533529037337155, | |
| "learning_rate": 0.0005979349149313778, | |
| "loss": 7.0586, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.30532331638835586, | |
| "learning_rate": 0.0005978277994643147, | |
| "loss": 7.0195, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.6501991746260075, | |
| "learning_rate": 0.0005977179869742844, | |
| "loss": 6.9648, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.43904455901717926, | |
| "learning_rate": 0.0005976054785670975, | |
| "loss": 6.9805, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.4826001598483571, | |
| "learning_rate": 0.0005974902753757124, | |
| "loss": 6.9297, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.2924998027034648, | |
| "learning_rate": 0.000597372378560224, | |
| "loss": 6.8984, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.4439033666380787, | |
| "learning_rate": 0.0005972517893078517, | |
| "loss": 6.8945, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.6135914255073411, | |
| "learning_rate": 0.0005971285088329284, | |
| "loss": 6.9727, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.5575686565598483, | |
| "learning_rate": 0.0005970025383768866, | |
| "loss": 6.9219, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.4820951675994578, | |
| "learning_rate": 0.0005968738792082478, | |
| "loss": 6.8516, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.40164190019465584, | |
| "learning_rate": 0.0005967425326226082, | |
| "loss": 6.7734, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.46129863945181293, | |
| "learning_rate": 0.0005966084999426265, | |
| "loss": 6.8125, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.33322355827118677, | |
| "learning_rate": 0.0005964717825180101, | |
| "loss": 6.7891, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3847525153855558, | |
| "learning_rate": 0.0005963323817255024, | |
| "loss": 6.8242, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3384433591375982, | |
| "learning_rate": 0.0005961902989688674, | |
| "loss": 6.707, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.3937003195165685, | |
| "learning_rate": 0.000596045535678877, | |
| "loss": 6.8203, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.35423488053528107, | |
| "learning_rate": 0.0005958980933132962, | |
| "loss": 6.7383, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.36005939745315396, | |
| "learning_rate": 0.0005957479733568675, | |
| "loss": 6.7109, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3499278317706933, | |
| "learning_rate": 0.0005955951773212976, | |
| "loss": 6.7266, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3708385192137018, | |
| "learning_rate": 0.0005954397067452407, | |
| "loss": 6.7617, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3775657656205869, | |
| "learning_rate": 0.0005952815631942839, | |
| "loss": 6.7148, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3040083750375816, | |
| "learning_rate": 0.0005951207482609307, | |
| "loss": 6.5938, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3443020808841468, | |
| "learning_rate": 0.0005949572635645861, | |
| "loss": 6.6523, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3520066316939, | |
| "learning_rate": 0.0005947911107515389, | |
| "loss": 6.6211, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3739040572679613, | |
| "learning_rate": 0.0005946222914949462, | |
| "loss": 6.5547, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.34890731989025553, | |
| "learning_rate": 0.000594450807494816, | |
| "loss": 6.5859, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.40910932350136514, | |
| "learning_rate": 0.0005942766604779903, | |
| "loss": 6.5547, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.5698342865852906, | |
| "learning_rate": 0.0005940998521981274, | |
| "loss": 6.457, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.5179452709555474, | |
| "learning_rate": 0.0005939203844356852, | |
| "loss": 6.5547, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.5222512938673792, | |
| "learning_rate": 0.0005937382589979016, | |
| "loss": 6.5039, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.5682332793686307, | |
| "learning_rate": 0.0005935534777187781, | |
| "loss": 6.5547, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3869287710460676, | |
| "learning_rate": 0.0005933660424590598, | |
| "loss": 6.5156, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3078211032807607, | |
| "learning_rate": 0.000593175955106218, | |
| "loss": 6.4258, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3611357511872241, | |
| "learning_rate": 0.00059298321757443, | |
| "loss": 6.4727, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.29633467844266953, | |
| "learning_rate": 0.0005927878318045608, | |
| "loss": 6.3281, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3257574200776832, | |
| "learning_rate": 0.0005925897997641426, | |
| "loss": 6.3203, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.2824054533852328, | |
| "learning_rate": 0.0005923891234473562, | |
| "loss": 6.4062, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3056199770204573, | |
| "learning_rate": 0.0005921858048750097, | |
| "loss": 6.3984, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.2966438824341908, | |
| "learning_rate": 0.000591979846094519, | |
| "loss": 6.3555, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.32782438676663733, | |
| "learning_rate": 0.0005917712491798866, | |
| "loss": 6.4023, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3538316399620157, | |
| "learning_rate": 0.0005915600162316811, | |
| "loss": 6.2812, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.375858298192913, | |
| "learning_rate": 0.0005913461493770162, | |
| "loss": 6.3086, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.5189251339815161, | |
| "learning_rate": 0.0005911296507695284, | |
| "loss": 6.2812, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.6304909542669104, | |
| "learning_rate": 0.0005909105225893564, | |
| "loss": 6.2969, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.4655662819622591, | |
| "learning_rate": 0.0005906887670431187, | |
| "loss": 6.1953, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.39035390983920965, | |
| "learning_rate": 0.000590464386363891, | |
| "loss": 6.2617, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.4918417851770978, | |
| "learning_rate": 0.0005902373828111843, | |
| "loss": 6.2148, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.35670770889552555, | |
| "learning_rate": 0.0005900077586709219, | |
| "loss": 6.2461, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.4177985869939347, | |
| "learning_rate": 0.0005897755162554163, | |
| "loss": 6.1797, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.3742471130708234, | |
| "learning_rate": 0.000589540657903346, | |
| "loss": 6.1406, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.28627666723978284, | |
| "learning_rate": 0.0005893031859797322, | |
| "loss": 6.2031, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.32238563846046103, | |
| "learning_rate": 0.0005890631028759143, | |
| "loss": 6.0625, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.2556625657587849, | |
| "learning_rate": 0.0005888204110095265, | |
| "loss": 6.1797, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.35463629701710253, | |
| "learning_rate": 0.0005885751128244734, | |
| "loss": 6.125, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.31975770214936095, | |
| "learning_rate": 0.0005883272107909048, | |
| "loss": 6.1836, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.3464621815245048, | |
| "learning_rate": 0.0005880767074051915, | |
| "loss": 6.125, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.3663428920796654, | |
| "learning_rate": 0.0005878236051898998, | |
| "loss": 6.0781, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.31594460565215293, | |
| "learning_rate": 0.0005875679066937664, | |
| "loss": 6.082, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.3552617109396582, | |
| "learning_rate": 0.000587309614491672, | |
| "loss": 6.1016, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.307016409692456, | |
| "learning_rate": 0.0005870487311846164, | |
| "loss": 6.1406, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.32188902148474213, | |
| "learning_rate": 0.0005867852593996914, | |
| "loss": 6.0039, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.25501199715105083, | |
| "learning_rate": 0.0005865192017900551, | |
| "loss": 6.0938, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.3416203070024056, | |
| "learning_rate": 0.0005862505610349049, | |
| "loss": 6.0234, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.3562508875852537, | |
| "learning_rate": 0.0005859793398394498, | |
| "loss": 6.0469, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.4443953757302568, | |
| "learning_rate": 0.0005857055409348845, | |
| "loss": 5.9766, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.42023839332714596, | |
| "learning_rate": 0.0005854291670783607, | |
| "loss": 6.0781, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.4618323255809241, | |
| "learning_rate": 0.0005851502210529604, | |
| "loss": 5.9727, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.379195014798667, | |
| "learning_rate": 0.0005848687056676668, | |
| "loss": 5.9922, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.3931552573296799, | |
| "learning_rate": 0.0005845846237573366, | |
| "loss": 5.9492, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.2567080044949908, | |
| "learning_rate": 0.0005842979781826717, | |
| "loss": 6.0273, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.4190305965377807, | |
| "learning_rate": 0.0005840087718301895, | |
| "loss": 6.0391, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.3996803869430228, | |
| "learning_rate": 0.0005837170076121951, | |
| "loss": 5.9531, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.478219248015785, | |
| "learning_rate": 0.000583422688466751, | |
| "loss": 6.0586, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.40869844309811526, | |
| "learning_rate": 0.0005831258173576474, | |
| "loss": 6.0117, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.3728598080697978, | |
| "learning_rate": 0.0005828263972743733, | |
| "loss": 5.9375, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.3560055462882015, | |
| "learning_rate": 0.0005825244312320856, | |
| "loss": 5.9531, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.40446932887864323, | |
| "learning_rate": 0.0005822199222715787, | |
| "loss": 5.9609, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.38514065739946723, | |
| "learning_rate": 0.000581912873459255, | |
| "loss": 5.8594, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.35367576386319416, | |
| "learning_rate": 0.0005816032878870921, | |
| "loss": 5.9023, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.3341681995122829, | |
| "learning_rate": 0.0005812911686726135, | |
| "loss": 5.9062, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.3387022688975784, | |
| "learning_rate": 0.0005809765189588563, | |
| "loss": 5.8945, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.31638659898934757, | |
| "learning_rate": 0.0005806593419143395, | |
| "loss": 5.8242, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.3229678508227436, | |
| "learning_rate": 0.0005803396407330325, | |
| "loss": 5.8516, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.35499490868584455, | |
| "learning_rate": 0.0005800174186343226, | |
| "loss": 5.9258, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.40753171542848754, | |
| "learning_rate": 0.0005796926788629828, | |
| "loss": 5.8242, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.3625374018348824, | |
| "learning_rate": 0.0005793654246891389, | |
| "loss": 5.832, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.3583489573569317, | |
| "learning_rate": 0.000579035659408237, | |
| "loss": 5.8398, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.39657706318861896, | |
| "learning_rate": 0.0005787033863410095, | |
| "loss": 5.8633, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3965837889564036, | |
| "learning_rate": 0.0005783686088334428, | |
| "loss": 5.8633, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.29496474301865566, | |
| "learning_rate": 0.0005780313302567424, | |
| "loss": 5.8203, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.44637192639243695, | |
| "learning_rate": 0.0005776915540073001, | |
| "loss": 5.8477, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.39605473508683114, | |
| "learning_rate": 0.0005773492835066587, | |
| "loss": 5.7383, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3008962634266945, | |
| "learning_rate": 0.0005770045222014786, | |
| "loss": 5.7617, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.36915495506607826, | |
| "learning_rate": 0.0005766572735635022, | |
| "loss": 5.7695, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3282300349560706, | |
| "learning_rate": 0.0005763075410895193, | |
| "loss": 5.8281, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.2747449814083844, | |
| "learning_rate": 0.0005759553283013323, | |
| "loss": 5.7812, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.28905882704179764, | |
| "learning_rate": 0.00057560063874572, | |
| "loss": 5.7344, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.280625988867192, | |
| "learning_rate": 0.000575243475994402, | |
| "loss": 5.7773, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.41061863948012467, | |
| "learning_rate": 0.0005748838436440035, | |
| "loss": 5.7578, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.4920152483870267, | |
| "learning_rate": 0.0005745217453160183, | |
| "loss": 5.7305, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.5463207978955044, | |
| "learning_rate": 0.0005741571846567725, | |
| "loss": 5.7383, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.3986359831157306, | |
| "learning_rate": 0.0005737901653373878, | |
| "loss": 5.668, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.37908758170100293, | |
| "learning_rate": 0.0005734206910537447, | |
| "loss": 5.6875, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.35929793070492694, | |
| "learning_rate": 0.0005730487655264451, | |
| "loss": 5.7188, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.4217799574145456, | |
| "learning_rate": 0.0005726743925007751, | |
| "loss": 5.7305, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.4024411981587195, | |
| "learning_rate": 0.0005722975757466667, | |
| "loss": 5.6289, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.3472391905877033, | |
| "learning_rate": 0.0005719183190586606, | |
| "loss": 5.6523, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.31752956812138816, | |
| "learning_rate": 0.0005715366262558675, | |
| "loss": 5.6172, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.3170152384332457, | |
| "learning_rate": 0.0005711525011819294, | |
| "loss": 5.6172, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.40520629326601837, | |
| "learning_rate": 0.0005707659477049818, | |
| "loss": 5.625, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.3965976910198806, | |
| "learning_rate": 0.0005703769697176137, | |
| "loss": 5.6562, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.40422960541801994, | |
| "learning_rate": 0.0005699855711368293, | |
| "loss": 5.6836, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.3780813184050647, | |
| "learning_rate": 0.0005695917559040079, | |
| "loss": 5.5938, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.36917638857736573, | |
| "learning_rate": 0.0005691955279848645, | |
| "loss": 5.668, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.37769176081037814, | |
| "learning_rate": 0.0005687968913694098, | |
| "loss": 5.4961, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.3255116524991148, | |
| "learning_rate": 0.0005683958500719103, | |
| "loss": 5.5117, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.31897629016848805, | |
| "learning_rate": 0.0005679924081308471, | |
| "loss": 5.5664, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.2869064236553046, | |
| "learning_rate": 0.0005675865696088764, | |
| "loss": 5.5391, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.29226729022634845, | |
| "learning_rate": 0.0005671783385927873, | |
| "loss": 5.5586, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.2534117210955766, | |
| "learning_rate": 0.0005667677191934618, | |
| "loss": 5.5312, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.289828484125484, | |
| "learning_rate": 0.0005663547155458326, | |
| "loss": 5.6484, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.2717242930342115, | |
| "learning_rate": 0.0005659393318088419, | |
| "loss": 5.5352, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.3595538109137759, | |
| "learning_rate": 0.0005655215721653993, | |
| "loss": 5.5742, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.4255054350471108, | |
| "learning_rate": 0.0005651014408223398, | |
| "loss": 5.5469, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.3670561941219979, | |
| "learning_rate": 0.0005646789420103814, | |
| "loss": 5.5078, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.40280130904983164, | |
| "learning_rate": 0.0005642540799840822, | |
| "loss": 5.5, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.41159472035983025, | |
| "learning_rate": 0.0005638268590217984, | |
| "loss": 5.5039, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.4316778037513652, | |
| "learning_rate": 0.0005633972834256401, | |
| "loss": 5.5352, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.5674781128363939, | |
| "learning_rate": 0.000562965357521429, | |
| "loss": 5.4336, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.41654662151365446, | |
| "learning_rate": 0.0005625310856586541, | |
| "loss": 5.6211, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.5159976364107484, | |
| "learning_rate": 0.0005620944722104282, | |
| "loss": 5.4844, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.34364678177014185, | |
| "learning_rate": 0.0005616555215734438, | |
| "loss": 5.4922, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3708077784459011, | |
| "learning_rate": 0.0005612142381679289, | |
| "loss": 5.5234, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3620051253453866, | |
| "learning_rate": 0.0005607706264376028, | |
| "loss": 5.4961, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.34735585210929654, | |
| "learning_rate": 0.0005603246908496305, | |
| "loss": 5.4453, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.37719874705792217, | |
| "learning_rate": 0.0005598764358945783, | |
| "loss": 5.4844, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3749130664831207, | |
| "learning_rate": 0.0005594258660863689, | |
| "loss": 5.4648, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.40951353306235827, | |
| "learning_rate": 0.0005589729859622351, | |
| "loss": 5.5039, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.40146882563949804, | |
| "learning_rate": 0.0005585178000826745, | |
| "loss": 5.3672, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.4062987628428303, | |
| "learning_rate": 0.0005580603130314043, | |
| "loss": 5.3984, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.35626322654799136, | |
| "learning_rate": 0.0005576005294153138, | |
| "loss": 5.3984, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.3140647930801716, | |
| "learning_rate": 0.0005571384538644188, | |
| "loss": 5.3906, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.2990060538353662, | |
| "learning_rate": 0.0005566740910318153, | |
| "loss": 5.3711, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.3337525907515936, | |
| "learning_rate": 0.0005562074455936315, | |
| "loss": 5.4023, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.3381587051014816, | |
| "learning_rate": 0.000555738522248982, | |
| "loss": 5.4414, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.2954008999469894, | |
| "learning_rate": 0.0005552673257199197, | |
| "loss": 5.418, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.3242310900810155, | |
| "learning_rate": 0.0005547938607513882, | |
| "loss": 5.418, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.3149021804393678, | |
| "learning_rate": 0.0005543181321111747, | |
| "loss": 5.4375, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.32859412218218814, | |
| "learning_rate": 0.0005538401445898612, | |
| "loss": 5.4492, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.2960282598050701, | |
| "learning_rate": 0.0005533599030007768, | |
| "loss": 5.3867, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.2866762878199755, | |
| "learning_rate": 0.0005528774121799489, | |
| "loss": 5.3789, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.34865216327038784, | |
| "learning_rate": 0.0005523926769860549, | |
| "loss": 5.3711, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |