| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9636552440290758, | |
| "eval_steps": 500, | |
| "global_step": 180, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016614745586708203, | |
| "grad_norm": 0.061364494264125824, | |
| "learning_rate": 4.999991432639962e-05, | |
| "loss": 0.5857, | |
| "num_input_tokens_seen": 70408, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.033229491173416406, | |
| "grad_norm": 0.0613991804420948, | |
| "learning_rate": 4.999965730618567e-05, | |
| "loss": 0.5331, | |
| "num_input_tokens_seen": 139640, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04984423676012461, | |
| "grad_norm": 0.06351307034492493, | |
| "learning_rate": 4.9999228941119745e-05, | |
| "loss": 0.5852, | |
| "num_input_tokens_seen": 223656, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06645898234683281, | |
| "grad_norm": 0.05762802064418793, | |
| "learning_rate": 4.999862923413781e-05, | |
| "loss": 0.5384, | |
| "num_input_tokens_seen": 300688, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08307372793354102, | |
| "grad_norm": 0.0632179006934166, | |
| "learning_rate": 4.999785818935018e-05, | |
| "loss": 0.5273, | |
| "num_input_tokens_seen": 366368, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09968847352024922, | |
| "grad_norm": 0.056689903140068054, | |
| "learning_rate": 4.999691581204152e-05, | |
| "loss": 0.5145, | |
| "num_input_tokens_seen": 445808, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11630321910695743, | |
| "grad_norm": 0.06574171781539917, | |
| "learning_rate": 4.9995802108670775e-05, | |
| "loss": 0.5301, | |
| "num_input_tokens_seen": 522800, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13291796469366562, | |
| "grad_norm": 0.06367070972919464, | |
| "learning_rate": 4.999451708687114e-05, | |
| "loss": 0.5552, | |
| "num_input_tokens_seen": 599608, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 0.0585966520011425, | |
| "learning_rate": 4.9993060755450015e-05, | |
| "loss": 0.5999, | |
| "num_input_tokens_seen": 681424, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16614745586708204, | |
| "grad_norm": 0.05650574713945389, | |
| "learning_rate": 4.999143312438893e-05, | |
| "loss": 0.4535, | |
| "num_input_tokens_seen": 756744, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18276220145379024, | |
| "grad_norm": 0.05954223498702049, | |
| "learning_rate": 4.998963420484349e-05, | |
| "loss": 0.4674, | |
| "num_input_tokens_seen": 842576, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19937694704049844, | |
| "grad_norm": 0.0663776770234108, | |
| "learning_rate": 4.998766400914329e-05, | |
| "loss": 0.4703, | |
| "num_input_tokens_seen": 917232, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21599169262720663, | |
| "grad_norm": 0.056374579668045044, | |
| "learning_rate": 4.9985522550791825e-05, | |
| "loss": 0.3725, | |
| "num_input_tokens_seen": 1006800, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23260643821391486, | |
| "grad_norm": 0.06437493115663528, | |
| "learning_rate": 4.998320984446641e-05, | |
| "loss": 0.4653, | |
| "num_input_tokens_seen": 1085824, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24922118380062305, | |
| "grad_norm": 0.06560757756233215, | |
| "learning_rate": 4.9980725906018074e-05, | |
| "loss": 0.5026, | |
| "num_input_tokens_seen": 1164160, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26583592938733125, | |
| "grad_norm": 0.06942517310380936, | |
| "learning_rate": 4.997807075247146e-05, | |
| "loss": 0.5401, | |
| "num_input_tokens_seen": 1242264, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2824506749740395, | |
| "grad_norm": 0.06349828094244003, | |
| "learning_rate": 4.997524440202469e-05, | |
| "loss": 0.4713, | |
| "num_input_tokens_seen": 1325904, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 0.08846385776996613, | |
| "learning_rate": 4.9972246874049254e-05, | |
| "loss": 0.5834, | |
| "num_input_tokens_seen": 1385632, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.31568016614745587, | |
| "grad_norm": 0.062130190432071686, | |
| "learning_rate": 4.996907818908987e-05, | |
| "loss": 0.4045, | |
| "num_input_tokens_seen": 1470632, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3322949117341641, | |
| "grad_norm": 0.07743565738201141, | |
| "learning_rate": 4.996573836886435e-05, | |
| "loss": 0.5283, | |
| "num_input_tokens_seen": 1547536, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34890965732087226, | |
| "grad_norm": 0.06756695359945297, | |
| "learning_rate": 4.9962227436263453e-05, | |
| "loss": 0.4199, | |
| "num_input_tokens_seen": 1615528, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3655244029075805, | |
| "grad_norm": 0.08662309497594833, | |
| "learning_rate": 4.995854541535071e-05, | |
| "loss": 0.4775, | |
| "num_input_tokens_seen": 1694352, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3821391484942887, | |
| "grad_norm": 0.08380820602178574, | |
| "learning_rate": 4.9954692331362294e-05, | |
| "loss": 0.4871, | |
| "num_input_tokens_seen": 1753776, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3987538940809969, | |
| "grad_norm": 0.09967435896396637, | |
| "learning_rate": 4.995066821070679e-05, | |
| "loss": 0.4871, | |
| "num_input_tokens_seen": 1809048, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4153686396677051, | |
| "grad_norm": 0.0871267095208168, | |
| "learning_rate": 4.994647308096509e-05, | |
| "loss": 0.5461, | |
| "num_input_tokens_seen": 1884264, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.43198338525441327, | |
| "grad_norm": 0.065020851790905, | |
| "learning_rate": 4.994210697089014e-05, | |
| "loss": 0.405, | |
| "num_input_tokens_seen": 1981704, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 0.09853450953960419, | |
| "learning_rate": 4.9937569910406756e-05, | |
| "loss": 0.4487, | |
| "num_input_tokens_seen": 2044144, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4652128764278297, | |
| "grad_norm": 0.08763110637664795, | |
| "learning_rate": 4.9932861930611454e-05, | |
| "loss": 0.3946, | |
| "num_input_tokens_seen": 2107584, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4818276220145379, | |
| "grad_norm": 0.08950547873973846, | |
| "learning_rate": 4.9927983063772196e-05, | |
| "loss": 0.4257, | |
| "num_input_tokens_seen": 2169248, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4984423676012461, | |
| "grad_norm": 0.09980211406946182, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.3911, | |
| "num_input_tokens_seen": 2230344, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5150571131879543, | |
| "grad_norm": 0.092055544257164, | |
| "learning_rate": 4.9917712803889674e-05, | |
| "loss": 0.3749, | |
| "num_input_tokens_seen": 2302368, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5316718587746625, | |
| "grad_norm": 0.10067818313837051, | |
| "learning_rate": 4.991232148123761e-05, | |
| "loss": 0.4761, | |
| "num_input_tokens_seen": 2369984, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5482866043613707, | |
| "grad_norm": 0.0717971920967102, | |
| "learning_rate": 4.990675941232353e-05, | |
| "loss": 0.4328, | |
| "num_input_tokens_seen": 2453032, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.564901349948079, | |
| "grad_norm": 0.07436250895261765, | |
| "learning_rate": 4.990102663526924e-05, | |
| "loss": 0.417, | |
| "num_input_tokens_seen": 2527464, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5815160955347871, | |
| "grad_norm": 0.09256689995527267, | |
| "learning_rate": 4.989512318936655e-05, | |
| "loss": 0.4097, | |
| "num_input_tokens_seen": 2597032, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 0.09964177012443542, | |
| "learning_rate": 4.9889049115077005e-05, | |
| "loss": 0.4065, | |
| "num_input_tokens_seen": 2671704, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6147455867082036, | |
| "grad_norm": 0.06627887487411499, | |
| "learning_rate": 4.988280445403164e-05, | |
| "loss": 0.4136, | |
| "num_input_tokens_seen": 2767640, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6313603322949117, | |
| "grad_norm": 0.0746045857667923, | |
| "learning_rate": 4.987638924903067e-05, | |
| "loss": 0.4125, | |
| "num_input_tokens_seen": 2843720, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6479750778816199, | |
| "grad_norm": 0.0795741006731987, | |
| "learning_rate": 4.9869803544043166e-05, | |
| "loss": 0.3135, | |
| "num_input_tokens_seen": 2921472, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6645898234683282, | |
| "grad_norm": 0.08914181590080261, | |
| "learning_rate": 4.9863047384206835e-05, | |
| "loss": 0.4549, | |
| "num_input_tokens_seen": 2998400, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6812045690550363, | |
| "grad_norm": 0.11220043897628784, | |
| "learning_rate": 4.985612081582764e-05, | |
| "loss": 0.4135, | |
| "num_input_tokens_seen": 3059648, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6978193146417445, | |
| "grad_norm": 0.08390027284622192, | |
| "learning_rate": 4.98490238863795e-05, | |
| "loss": 0.3538, | |
| "num_input_tokens_seen": 3140184, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7144340602284528, | |
| "grad_norm": 0.08858532458543777, | |
| "learning_rate": 4.984175664450397e-05, | |
| "loss": 0.3644, | |
| "num_input_tokens_seen": 3207184, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.731048805815161, | |
| "grad_norm": 0.07439564168453217, | |
| "learning_rate": 4.983431914000991e-05, | |
| "loss": 0.4019, | |
| "num_input_tokens_seen": 3292344, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 0.08694300055503845, | |
| "learning_rate": 4.982671142387316e-05, | |
| "loss": 0.4238, | |
| "num_input_tokens_seen": 3365384, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7642782969885774, | |
| "grad_norm": 0.0867784395813942, | |
| "learning_rate": 4.981893354823614e-05, | |
| "loss": 0.3702, | |
| "num_input_tokens_seen": 3440720, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7808930425752856, | |
| "grad_norm": 0.06278439611196518, | |
| "learning_rate": 4.9810985566407544e-05, | |
| "loss": 0.3354, | |
| "num_input_tokens_seen": 3533576, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7975077881619937, | |
| "grad_norm": 0.08999717980623245, | |
| "learning_rate": 4.980286753286195e-05, | |
| "loss": 0.4981, | |
| "num_input_tokens_seen": 3599744, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.814122533748702, | |
| "grad_norm": 0.07938859611749649, | |
| "learning_rate": 4.979457950323945e-05, | |
| "loss": 0.4016, | |
| "num_input_tokens_seen": 3689520, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8307372793354102, | |
| "grad_norm": 0.1045590192079544, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.388, | |
| "num_input_tokens_seen": 3751808, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8473520249221184, | |
| "grad_norm": 0.07890618592500687, | |
| "learning_rate": 4.9777493684149375e-05, | |
| "loss": 0.3674, | |
| "num_input_tokens_seen": 3839096, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8639667705088265, | |
| "grad_norm": 0.07802557945251465, | |
| "learning_rate": 4.976869601178609e-05, | |
| "loss": 0.4147, | |
| "num_input_tokens_seen": 3919824, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8805815160955348, | |
| "grad_norm": 0.0913538783788681, | |
| "learning_rate": 4.975972857755369e-05, | |
| "loss": 0.2978, | |
| "num_input_tokens_seen": 3989312, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 0.08525951951742172, | |
| "learning_rate": 4.975059144291394e-05, | |
| "loss": 0.3923, | |
| "num_input_tokens_seen": 4060528, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9138110072689511, | |
| "grad_norm": 0.08649709820747375, | |
| "learning_rate": 4.974128467049176e-05, | |
| "loss": 0.3282, | |
| "num_input_tokens_seen": 4129368, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9304257528556594, | |
| "grad_norm": 0.11635593324899673, | |
| "learning_rate": 4.9731808324074717e-05, | |
| "loss": 0.3403, | |
| "num_input_tokens_seen": 4175208, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9470404984423676, | |
| "grad_norm": 0.1115177720785141, | |
| "learning_rate": 4.972216246861262e-05, | |
| "loss": 0.3191, | |
| "num_input_tokens_seen": 4218096, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9636552440290758, | |
| "grad_norm": 0.0986371859908104, | |
| "learning_rate": 4.971234717021709e-05, | |
| "loss": 0.3745, | |
| "num_input_tokens_seen": 4275968, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.980269989615784, | |
| "grad_norm": 0.07860780507326126, | |
| "learning_rate": 4.9702362496161085e-05, | |
| "loss": 0.3129, | |
| "num_input_tokens_seen": 4346616, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.9968847352024922, | |
| "grad_norm": 0.08581527322530746, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.3324, | |
| "num_input_tokens_seen": 4425064, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.16779834032058716, | |
| "learning_rate": 4.968188529596342e-05, | |
| "loss": 0.2814, | |
| "num_input_tokens_seen": 4435328, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.0166147455867083, | |
| "grad_norm": 0.08948636800050735, | |
| "learning_rate": 4.9671392910170185e-05, | |
| "loss": 0.3467, | |
| "num_input_tokens_seen": 4500104, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0332294911734163, | |
| "grad_norm": 0.07826830446720123, | |
| "learning_rate": 4.966073142941239e-05, | |
| "loss": 0.3892, | |
| "num_input_tokens_seen": 4581976, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0498442367601246, | |
| "grad_norm": 0.08562575280666351, | |
| "learning_rate": 4.964990092676263e-05, | |
| "loss": 0.3354, | |
| "num_input_tokens_seen": 4652160, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.066458982346833, | |
| "grad_norm": 0.1057090312242508, | |
| "learning_rate": 4.9638901476451946e-05, | |
| "loss": 0.3457, | |
| "num_input_tokens_seen": 4709368, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.083073727933541, | |
| "grad_norm": 0.08131146430969238, | |
| "learning_rate": 4.962773315386935e-05, | |
| "loss": 0.3672, | |
| "num_input_tokens_seen": 4798256, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0996884735202492, | |
| "grad_norm": 0.09464936703443527, | |
| "learning_rate": 4.961639603556127e-05, | |
| "loss": 0.3157, | |
| "num_input_tokens_seen": 4859200, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.1163032191069575, | |
| "grad_norm": 0.0999661460518837, | |
| "learning_rate": 4.960489019923105e-05, | |
| "loss": 0.3968, | |
| "num_input_tokens_seen": 4925992, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.1329179646936656, | |
| "grad_norm": 0.09851639717817307, | |
| "learning_rate": 4.9593215723738404e-05, | |
| "loss": 0.329, | |
| "num_input_tokens_seen": 4998808, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.1495327102803738, | |
| "grad_norm": 0.08382592350244522, | |
| "learning_rate": 4.958137268909887e-05, | |
| "loss": 0.2856, | |
| "num_input_tokens_seen": 5089672, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1661474558670821, | |
| "grad_norm": 0.09073847532272339, | |
| "learning_rate": 4.9569361176483286e-05, | |
| "loss": 0.3512, | |
| "num_input_tokens_seen": 5166744, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.1827622014537902, | |
| "grad_norm": 0.10290185362100601, | |
| "learning_rate": 4.9557181268217227e-05, | |
| "loss": 0.4263, | |
| "num_input_tokens_seen": 5228264, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.1993769470404985, | |
| "grad_norm": 0.07421435415744781, | |
| "learning_rate": 4.9544833047780394e-05, | |
| "loss": 0.3126, | |
| "num_input_tokens_seen": 5338224, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.2159916926272065, | |
| "grad_norm": 0.10284842550754547, | |
| "learning_rate": 4.9532316599806124e-05, | |
| "loss": 0.3473, | |
| "num_input_tokens_seen": 5399848, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.2326064382139148, | |
| "grad_norm": 0.10817047953605652, | |
| "learning_rate": 4.951963201008076e-05, | |
| "loss": 0.3275, | |
| "num_input_tokens_seen": 5468624, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.249221183800623, | |
| "grad_norm": 0.09662210941314697, | |
| "learning_rate": 4.9506779365543046e-05, | |
| "loss": 0.3296, | |
| "num_input_tokens_seen": 5536776, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.2658359293873311, | |
| "grad_norm": 0.11193853616714478, | |
| "learning_rate": 4.949375875428357e-05, | |
| "loss": 0.3605, | |
| "num_input_tokens_seen": 5609296, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.2824506749740394, | |
| "grad_norm": 0.11866679787635803, | |
| "learning_rate": 4.9480570265544144e-05, | |
| "loss": 0.3133, | |
| "num_input_tokens_seen": 5663824, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.2990654205607477, | |
| "grad_norm": 0.09865846484899521, | |
| "learning_rate": 4.94672139897172e-05, | |
| "loss": 0.3464, | |
| "num_input_tokens_seen": 5742032, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.3156801661474558, | |
| "grad_norm": 0.09930054098367691, | |
| "learning_rate": 4.9453690018345144e-05, | |
| "loss": 0.3346, | |
| "num_input_tokens_seen": 5816864, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.332294911734164, | |
| "grad_norm": 0.1085321381688118, | |
| "learning_rate": 4.943999844411977e-05, | |
| "loss": 0.3102, | |
| "num_input_tokens_seen": 5881624, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.3489096573208723, | |
| "grad_norm": 0.08012478053569794, | |
| "learning_rate": 4.94261393608816e-05, | |
| "loss": 0.2853, | |
| "num_input_tokens_seen": 5970272, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.3655244029075804, | |
| "grad_norm": 0.10291877388954163, | |
| "learning_rate": 4.941211286361922e-05, | |
| "loss": 0.3038, | |
| "num_input_tokens_seen": 6058752, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.3821391484942886, | |
| "grad_norm": 0.11999356001615524, | |
| "learning_rate": 4.939791904846869e-05, | |
| "loss": 0.3283, | |
| "num_input_tokens_seen": 6120064, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.398753894080997, | |
| "grad_norm": 0.10502559691667557, | |
| "learning_rate": 4.938355801271282e-05, | |
| "loss": 0.321, | |
| "num_input_tokens_seen": 6182072, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.415368639667705, | |
| "grad_norm": 0.12620873749256134, | |
| "learning_rate": 4.936902985478055e-05, | |
| "loss": 0.3296, | |
| "num_input_tokens_seen": 6269680, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.4319833852544133, | |
| "grad_norm": 0.13212910294532776, | |
| "learning_rate": 4.935433467424624e-05, | |
| "loss": 0.3225, | |
| "num_input_tokens_seen": 6347424, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.4485981308411215, | |
| "grad_norm": 0.11600925773382187, | |
| "learning_rate": 4.933947257182901e-05, | |
| "loss": 0.3479, | |
| "num_input_tokens_seen": 6412584, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.4652128764278296, | |
| "grad_norm": 0.11683235317468643, | |
| "learning_rate": 4.932444364939205e-05, | |
| "loss": 0.3322, | |
| "num_input_tokens_seen": 6482728, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.4818276220145379, | |
| "grad_norm": 0.11446017026901245, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.3802, | |
| "num_input_tokens_seen": 6562104, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4984423676012462, | |
| "grad_norm": 0.10500892251729965, | |
| "learning_rate": 4.929388575762782e-05, | |
| "loss": 0.3371, | |
| "num_input_tokens_seen": 6656552, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.5150571131879542, | |
| "grad_norm": 0.13279151916503906, | |
| "learning_rate": 4.9278356997740904e-05, | |
| "loss": 0.293, | |
| "num_input_tokens_seen": 6714184, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.5316718587746625, | |
| "grad_norm": 0.107506163418293, | |
| "learning_rate": 4.9262661836713564e-05, | |
| "loss": 0.3127, | |
| "num_input_tokens_seen": 6793552, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.5482866043613708, | |
| "grad_norm": 0.124021977186203, | |
| "learning_rate": 4.924680038211867e-05, | |
| "loss": 0.3263, | |
| "num_input_tokens_seen": 6865256, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.5649013499480788, | |
| "grad_norm": 0.14172782003879547, | |
| "learning_rate": 4.9230772742668866e-05, | |
| "loss": 0.3204, | |
| "num_input_tokens_seen": 6931152, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.5815160955347871, | |
| "grad_norm": 0.12229758501052856, | |
| "learning_rate": 4.9214579028215776e-05, | |
| "loss": 0.326, | |
| "num_input_tokens_seen": 6998408, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.5981308411214954, | |
| "grad_norm": 0.1242135688662529, | |
| "learning_rate": 4.919821934974933e-05, | |
| "loss": 0.2814, | |
| "num_input_tokens_seen": 7053008, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.6147455867082035, | |
| "grad_norm": 0.12830108404159546, | |
| "learning_rate": 4.918169381939692e-05, | |
| "loss": 0.3254, | |
| "num_input_tokens_seen": 7106440, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.6313603322949117, | |
| "grad_norm": 0.12180659174919128, | |
| "learning_rate": 4.916500255042268e-05, | |
| "loss": 0.3228, | |
| "num_input_tokens_seen": 7167032, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.64797507788162, | |
| "grad_norm": 0.10792312026023865, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.2729, | |
| "num_input_tokens_seen": 7245720, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.664589823468328, | |
| "grad_norm": 0.18523500859737396, | |
| "learning_rate": 4.913112325534426e-05, | |
| "loss": 0.3462, | |
| "num_input_tokens_seen": 7326320, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.6812045690550363, | |
| "grad_norm": 0.09529964625835419, | |
| "learning_rate": 4.9113935461444955e-05, | |
| "loss": 0.3096, | |
| "num_input_tokens_seen": 7442232, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.6978193146417446, | |
| "grad_norm": 0.14481183886528015, | |
| "learning_rate": 4.9096582393332025e-05, | |
| "loss": 0.3014, | |
| "num_input_tokens_seen": 7502496, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.7144340602284527, | |
| "grad_norm": 0.14645016193389893, | |
| "learning_rate": 4.907906416994146e-05, | |
| "loss": 0.3336, | |
| "num_input_tokens_seen": 7566496, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.731048805815161, | |
| "grad_norm": 0.1306885927915573, | |
| "learning_rate": 4.906138091134118e-05, | |
| "loss": 0.3911, | |
| "num_input_tokens_seen": 7629056, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7476635514018692, | |
| "grad_norm": 0.10863160341978073, | |
| "learning_rate": 4.9043532738730284e-05, | |
| "loss": 0.3201, | |
| "num_input_tokens_seen": 7706096, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.7642782969885773, | |
| "grad_norm": 0.11725673079490662, | |
| "learning_rate": 4.9025519774438136e-05, | |
| "loss": 0.2783, | |
| "num_input_tokens_seen": 7780072, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.7808930425752856, | |
| "grad_norm": 0.1243867501616478, | |
| "learning_rate": 4.900734214192358e-05, | |
| "loss": 0.3044, | |
| "num_input_tokens_seen": 7857712, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.7975077881619939, | |
| "grad_norm": 0.13539955019950867, | |
| "learning_rate": 4.898899996577407e-05, | |
| "loss": 0.3009, | |
| "num_input_tokens_seen": 7916832, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.814122533748702, | |
| "grad_norm": 0.11198178678750992, | |
| "learning_rate": 4.8970493371704826e-05, | |
| "loss": 0.3229, | |
| "num_input_tokens_seen": 7993056, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8307372793354102, | |
| "grad_norm": 0.11881165206432343, | |
| "learning_rate": 4.8951822486557986e-05, | |
| "loss": 0.3414, | |
| "num_input_tokens_seen": 8090056, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.8473520249221185, | |
| "grad_norm": 0.12841404974460602, | |
| "learning_rate": 4.893298743830168e-05, | |
| "loss": 0.2907, | |
| "num_input_tokens_seen": 8164808, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.8639667705088265, | |
| "grad_norm": 0.14767521619796753, | |
| "learning_rate": 4.891398835602925e-05, | |
| "loss": 0.2901, | |
| "num_input_tokens_seen": 8223568, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.8805815160955348, | |
| "grad_norm": 0.15326914191246033, | |
| "learning_rate": 4.8894825369958255e-05, | |
| "loss": 0.2918, | |
| "num_input_tokens_seen": 8276160, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.897196261682243, | |
| "grad_norm": 0.1210051029920578, | |
| "learning_rate": 4.8875498611429674e-05, | |
| "loss": 0.3074, | |
| "num_input_tokens_seen": 8354904, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.9138110072689511, | |
| "grad_norm": 0.13544373214244843, | |
| "learning_rate": 4.8856008212906925e-05, | |
| "loss": 0.3461, | |
| "num_input_tokens_seen": 8442584, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.9304257528556594, | |
| "grad_norm": 0.13535892963409424, | |
| "learning_rate": 4.8836354307975026e-05, | |
| "loss": 0.3078, | |
| "num_input_tokens_seen": 8506688, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.9470404984423677, | |
| "grad_norm": 0.10383590310811996, | |
| "learning_rate": 4.881653703133966e-05, | |
| "loss": 0.2432, | |
| "num_input_tokens_seen": 8610712, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.9636552440290758, | |
| "grad_norm": 0.12125886976718903, | |
| "learning_rate": 4.87965565188262e-05, | |
| "loss": 0.2915, | |
| "num_input_tokens_seen": 8692624, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.980269989615784, | |
| "grad_norm": 0.1351424902677536, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.3006, | |
| "num_input_tokens_seen": 8772208, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9968847352024923, | |
| "grad_norm": 0.11472523212432861, | |
| "learning_rate": 4.8756106335059646e-05, | |
| "loss": 0.2774, | |
| "num_input_tokens_seen": 8854904, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.3606414794921875, | |
| "learning_rate": 4.87356369410476e-05, | |
| "loss": 0.2786, | |
| "num_input_tokens_seen": 8872656, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.016614745586708, | |
| "grad_norm": 0.13124766945838928, | |
| "learning_rate": 4.8715004865637614e-05, | |
| "loss": 0.294, | |
| "num_input_tokens_seen": 8946480, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.0332294911734166, | |
| "grad_norm": 0.12415049225091934, | |
| "learning_rate": 4.869421025023965e-05, | |
| "loss": 0.2931, | |
| "num_input_tokens_seen": 9023328, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.0498442367601246, | |
| "grad_norm": 0.16626115143299103, | |
| "learning_rate": 4.867325323737765e-05, | |
| "loss": 0.2887, | |
| "num_input_tokens_seen": 9074320, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0664589823468327, | |
| "grad_norm": 0.153628870844841, | |
| "learning_rate": 4.8652133970688636e-05, | |
| "loss": 0.2776, | |
| "num_input_tokens_seen": 9148784, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.083073727933541, | |
| "grad_norm": 0.12231138348579407, | |
| "learning_rate": 4.8630852594921706e-05, | |
| "loss": 0.3091, | |
| "num_input_tokens_seen": 9246624, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.0996884735202492, | |
| "grad_norm": 0.15192057192325592, | |
| "learning_rate": 4.860940925593703e-05, | |
| "loss": 0.3354, | |
| "num_input_tokens_seen": 9328176, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.1163032191069573, | |
| "grad_norm": 0.13820070028305054, | |
| "learning_rate": 4.8587804100704845e-05, | |
| "loss": 0.282, | |
| "num_input_tokens_seen": 9388936, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.132917964693666, | |
| "grad_norm": 0.14466816186904907, | |
| "learning_rate": 4.856603727730447e-05, | |
| "loss": 0.2801, | |
| "num_input_tokens_seen": 9461664, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.149532710280374, | |
| "grad_norm": 0.14671838283538818, | |
| "learning_rate": 4.854410893492326e-05, | |
| "loss": 0.2927, | |
| "num_input_tokens_seen": 9535000, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.166147455867082, | |
| "grad_norm": 0.1757712960243225, | |
| "learning_rate": 4.852201922385564e-05, | |
| "loss": 0.2807, | |
| "num_input_tokens_seen": 9600296, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.1827622014537904, | |
| "grad_norm": 0.17755423486232758, | |
| "learning_rate": 4.8499768295502004e-05, | |
| "loss": 0.2765, | |
| "num_input_tokens_seen": 9686784, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.1993769470404985, | |
| "grad_norm": 0.13321827352046967, | |
| "learning_rate": 4.847735630236773e-05, | |
| "loss": 0.3068, | |
| "num_input_tokens_seen": 9781112, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.2159916926272065, | |
| "grad_norm": 0.15012745559215546, | |
| "learning_rate": 4.8454783398062106e-05, | |
| "loss": 0.2737, | |
| "num_input_tokens_seen": 9849528, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.232606438213915, | |
| "grad_norm": 0.14000360667705536, | |
| "learning_rate": 4.843204973729729e-05, | |
| "loss": 0.2831, | |
| "num_input_tokens_seen": 9931080, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.249221183800623, | |
| "grad_norm": 0.14742712676525116, | |
| "learning_rate": 4.840915547588725e-05, | |
| "loss": 0.3047, | |
| "num_input_tokens_seen": 10011176, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.265835929387331, | |
| "grad_norm": 0.16192346811294556, | |
| "learning_rate": 4.838610077074669e-05, | |
| "loss": 0.2759, | |
| "num_input_tokens_seen": 10084128, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.2824506749740396, | |
| "grad_norm": 0.1502583771944046, | |
| "learning_rate": 4.836288577988996e-05, | |
| "loss": 0.298, | |
| "num_input_tokens_seen": 10155536, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.2990654205607477, | |
| "grad_norm": 0.12661044299602509, | |
| "learning_rate": 4.8339510662430046e-05, | |
| "loss": 0.255, | |
| "num_input_tokens_seen": 10251160, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.3156801661474558, | |
| "grad_norm": 0.14002998173236847, | |
| "learning_rate": 4.8315975578577355e-05, | |
| "loss": 0.2566, | |
| "num_input_tokens_seen": 10345864, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.3322949117341643, | |
| "grad_norm": 0.17870523035526276, | |
| "learning_rate": 4.8292280689638725e-05, | |
| "loss": 0.4367, | |
| "num_input_tokens_seen": 10417616, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.3489096573208723, | |
| "grad_norm": 0.17209866642951965, | |
| "learning_rate": 4.826842615801628e-05, | |
| "loss": 0.2954, | |
| "num_input_tokens_seen": 10481816, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.3655244029075804, | |
| "grad_norm": 0.1665940284729004, | |
| "learning_rate": 4.8244412147206284e-05, | |
| "loss": 0.341, | |
| "num_input_tokens_seen": 10562056, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.382139148494289, | |
| "grad_norm": 0.18919898569583893, | |
| "learning_rate": 4.822023882179811e-05, | |
| "loss": 0.2716, | |
| "num_input_tokens_seen": 10612808, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.398753894080997, | |
| "grad_norm": 0.1681865006685257, | |
| "learning_rate": 4.8195906347473e-05, | |
| "loss": 0.2716, | |
| "num_input_tokens_seen": 10682328, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.415368639667705, | |
| "grad_norm": 0.13141104578971863, | |
| "learning_rate": 4.817141489100302e-05, | |
| "loss": 0.2829, | |
| "num_input_tokens_seen": 10771912, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.431983385254413, | |
| "grad_norm": 0.16544249653816223, | |
| "learning_rate": 4.814676462024988e-05, | |
| "loss": 0.3038, | |
| "num_input_tokens_seen": 10842232, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.4485981308411215, | |
| "grad_norm": 0.17946277558803558, | |
| "learning_rate": 4.8121955704163745e-05, | |
| "loss": 0.2792, | |
| "num_input_tokens_seen": 10902264, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 2.4652128764278296, | |
| "grad_norm": 0.14012685418128967, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.2403, | |
| "num_input_tokens_seen": 10992744, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4818276220145377, | |
| "grad_norm": 0.103813536465168, | |
| "learning_rate": 4.8071862617228855e-05, | |
| "loss": 0.1605, | |
| "num_input_tokens_seen": 11090064, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 2.498442367601246, | |
| "grad_norm": 0.1596001833677292, | |
| "learning_rate": 4.8046578789712515e-05, | |
| "loss": 0.2547, | |
| "num_input_tokens_seen": 11162864, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.515057113187954, | |
| "grad_norm": 0.17366129159927368, | |
| "learning_rate": 4.8021137003525664e-05, | |
| "loss": 0.2676, | |
| "num_input_tokens_seen": 11224368, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.5316718587746623, | |
| "grad_norm": 0.1615227609872818, | |
| "learning_rate": 4.7995537433043446e-05, | |
| "loss": 0.2898, | |
| "num_input_tokens_seen": 11291056, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.5482866043613708, | |
| "grad_norm": 0.1951528787612915, | |
| "learning_rate": 4.796978025372246e-05, | |
| "loss": 0.2546, | |
| "num_input_tokens_seen": 11345464, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.564901349948079, | |
| "grad_norm": 0.15065862238407135, | |
| "learning_rate": 4.794386564209953e-05, | |
| "loss": 0.3134, | |
| "num_input_tokens_seen": 11418912, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.581516095534787, | |
| "grad_norm": 0.17094938457012177, | |
| "learning_rate": 4.79177937757905e-05, | |
| "loss": 0.2689, | |
| "num_input_tokens_seen": 11491216, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.5981308411214954, | |
| "grad_norm": 0.16850312054157257, | |
| "learning_rate": 4.7891564833489035e-05, | |
| "loss": 0.2359, | |
| "num_input_tokens_seen": 11558016, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.6147455867082035, | |
| "grad_norm": 0.16789822280406952, | |
| "learning_rate": 4.7865178994965344e-05, | |
| "loss": 0.2735, | |
| "num_input_tokens_seen": 11630432, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.6313603322949115, | |
| "grad_norm": 0.19538354873657227, | |
| "learning_rate": 4.783863644106502e-05, | |
| "loss": 0.254, | |
| "num_input_tokens_seen": 11684624, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.64797507788162, | |
| "grad_norm": 0.1609475016593933, | |
| "learning_rate": 4.781193735370777e-05, | |
| "loss": 0.2763, | |
| "num_input_tokens_seen": 11770232, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 2.664589823468328, | |
| "grad_norm": 0.1964447796344757, | |
| "learning_rate": 4.7785081915886134e-05, | |
| "loss": 0.2663, | |
| "num_input_tokens_seen": 11828360, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.681204569055036, | |
| "grad_norm": 0.18869946897029877, | |
| "learning_rate": 4.775807031166428e-05, | |
| "loss": 0.2625, | |
| "num_input_tokens_seen": 11915944, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 2.6978193146417446, | |
| "grad_norm": 0.20539921522140503, | |
| "learning_rate": 4.773090272617672e-05, | |
| "loss": 0.2615, | |
| "num_input_tokens_seen": 11981792, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.7144340602284527, | |
| "grad_norm": 0.1616145521402359, | |
| "learning_rate": 4.7703579345627035e-05, | |
| "loss": 0.3453, | |
| "num_input_tokens_seen": 12044024, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.7310488058151607, | |
| "grad_norm": 0.22601978480815887, | |
| "learning_rate": 4.7676100357286624e-05, | |
| "loss": 0.3036, | |
| "num_input_tokens_seen": 12093424, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.7476635514018692, | |
| "grad_norm": 0.15262462198734283, | |
| "learning_rate": 4.76484659494934e-05, | |
| "loss": 0.2523, | |
| "num_input_tokens_seen": 12167792, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 2.7642782969885773, | |
| "grad_norm": 0.17928001284599304, | |
| "learning_rate": 4.762067631165049e-05, | |
| "loss": 0.2791, | |
| "num_input_tokens_seen": 12233712, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.7808930425752854, | |
| "grad_norm": 0.15228766202926636, | |
| "learning_rate": 4.7592731634224966e-05, | |
| "loss": 0.2291, | |
| "num_input_tokens_seen": 12310544, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 2.797507788161994, | |
| "grad_norm": 0.18862110376358032, | |
| "learning_rate": 4.756463210874652e-05, | |
| "loss": 0.2628, | |
| "num_input_tokens_seen": 12400160, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.814122533748702, | |
| "grad_norm": 0.16640189290046692, | |
| "learning_rate": 4.753637792780614e-05, | |
| "loss": 0.2824, | |
| "num_input_tokens_seen": 12480432, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.83073727933541, | |
| "grad_norm": 0.151117205619812, | |
| "learning_rate": 4.7507969285054845e-05, | |
| "loss": 0.2663, | |
| "num_input_tokens_seen": 12568064, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.8473520249221185, | |
| "grad_norm": 0.26551589369773865, | |
| "learning_rate": 4.7479406375202264e-05, | |
| "loss": 0.28, | |
| "num_input_tokens_seen": 12647400, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 2.8639667705088265, | |
| "grad_norm": 0.22416891157627106, | |
| "learning_rate": 4.745068939401539e-05, | |
| "loss": 0.2424, | |
| "num_input_tokens_seen": 12698208, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.8805815160955346, | |
| "grad_norm": 0.2024654597043991, | |
| "learning_rate": 4.742181853831721e-05, | |
| "loss": 0.2518, | |
| "num_input_tokens_seen": 12758528, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.897196261682243, | |
| "grad_norm": 0.18288369476795197, | |
| "learning_rate": 4.7392794005985326e-05, | |
| "loss": 0.259, | |
| "num_input_tokens_seen": 12837264, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.913811007268951, | |
| "grad_norm": 0.18088208138942719, | |
| "learning_rate": 4.7363615995950626e-05, | |
| "loss": 0.247, | |
| "num_input_tokens_seen": 12902368, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.930425752855659, | |
| "grad_norm": 0.16595424711704254, | |
| "learning_rate": 4.733428470819594e-05, | |
| "loss": 0.2438, | |
| "num_input_tokens_seen": 12974296, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.9470404984423677, | |
| "grad_norm": 0.17989091575145721, | |
| "learning_rate": 4.730480034375462e-05, | |
| "loss": 0.2708, | |
| "num_input_tokens_seen": 13057280, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 2.9636552440290758, | |
| "grad_norm": 0.16136637330055237, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.3171, | |
| "num_input_tokens_seen": 13158232, | |
| "step": 180 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 1200, | |
| "num_input_tokens_seen": 13158232, | |
| "num_train_epochs": 20, | |
| "save_steps": 60, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.614082820239524e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |