| [ |
| { |
| "loss": 3.5175, |
| "grad_norm": 5.565041542053223, |
| "learning_rate": 1.4084507042253523e-06, |
| "epoch": 0.035211267605633804, |
| "step": 10 |
| }, |
| { |
| "loss": 3.442, |
| "grad_norm": 5.5761823654174805, |
| "learning_rate": 2.8169014084507046e-06, |
| "epoch": 0.07042253521126761, |
| "step": 20 |
| }, |
| { |
| "loss": 3.4738, |
| "grad_norm": 4.932906627655029, |
| "learning_rate": 4.225352112676057e-06, |
| "epoch": 0.1056338028169014, |
| "step": 30 |
| }, |
| { |
| "loss": 3.4348, |
| "grad_norm": 4.843143463134766, |
| "learning_rate": 5.633802816901409e-06, |
| "epoch": 0.14084507042253522, |
| "step": 40 |
| }, |
| { |
| "loss": 3.4126, |
| "grad_norm": 4.041543006896973, |
| "learning_rate": 7.042253521126761e-06, |
| "epoch": 0.176056338028169, |
| "step": 50 |
| }, |
| { |
| "loss": 3.4001, |
| "grad_norm": 4.474198818206787, |
| "learning_rate": 8.450704225352114e-06, |
| "epoch": 0.2112676056338028, |
| "step": 60 |
| }, |
| { |
| "loss": 3.4608, |
| "grad_norm": 4.319010257720947, |
| "learning_rate": 9.859154929577466e-06, |
| "epoch": 0.24647887323943662, |
| "step": 70 |
| }, |
| { |
| "loss": 3.3525, |
| "grad_norm": 5.172270774841309, |
| "learning_rate": 1.1267605633802819e-05, |
| "epoch": 0.28169014084507044, |
| "step": 80 |
| }, |
| { |
| "loss": 3.3754, |
| "grad_norm": 5.9189839363098145, |
| "learning_rate": 1.2676056338028171e-05, |
| "epoch": 0.31690140845070425, |
| "step": 90 |
| }, |
| { |
| "loss": 3.2967, |
| "grad_norm": 5.190176010131836, |
| "learning_rate": 1.4084507042253522e-05, |
| "epoch": 0.352112676056338, |
| "step": 100 |
| }, |
| { |
| "loss": 3.2748, |
| "grad_norm": 5.891371726989746, |
| "learning_rate": 1.5492957746478872e-05, |
| "epoch": 0.3873239436619718, |
| "step": 110 |
| }, |
| { |
| "loss": 3.3054, |
| "grad_norm": 5.310686111450195, |
| "learning_rate": 1.6901408450704228e-05, |
| "epoch": 0.4225352112676056, |
| "step": 120 |
| }, |
| { |
| "loss": 3.2041, |
| "grad_norm": 8.007060050964355, |
| "learning_rate": 1.830985915492958e-05, |
| "epoch": 0.45774647887323944, |
| "step": 130 |
| }, |
| { |
| "loss": 3.1923, |
| "grad_norm": 6.142883777618408, |
| "learning_rate": 1.9718309859154933e-05, |
| "epoch": 0.49295774647887325, |
| "step": 140 |
| }, |
| { |
| "loss": 3.1226, |
| "grad_norm": 7.110233783721924, |
| "learning_rate": 1.9874804381846636e-05, |
| "epoch": 0.528169014084507, |
| "step": 150 |
| }, |
| { |
| "loss": 2.9466, |
| "grad_norm": 6.629207611083984, |
| "learning_rate": 1.9718309859154933e-05, |
| "epoch": 0.5633802816901409, |
| "step": 160 |
| }, |
| { |
| "loss": 2.9508, |
| "grad_norm": 7.121689796447754, |
| "learning_rate": 1.9561815336463226e-05, |
| "epoch": 0.5985915492957746, |
| "step": 170 |
| }, |
| { |
| "loss": 2.8045, |
| "grad_norm": 7.066350936889648, |
| "learning_rate": 1.940532081377152e-05, |
| "epoch": 0.6338028169014085, |
| "step": 180 |
| }, |
| { |
| "loss": 2.5482, |
| "grad_norm": 6.999160289764404, |
| "learning_rate": 1.9248826291079815e-05, |
| "epoch": 0.6690140845070423, |
| "step": 190 |
| }, |
| { |
| "loss": 2.5868, |
| "grad_norm": 8.449387550354004, |
| "learning_rate": 1.9092331768388108e-05, |
| "epoch": 0.704225352112676, |
| "step": 200 |
| }, |
| { |
| "loss": 2.3915, |
| "grad_norm": 7.70518684387207, |
| "learning_rate": 1.89358372456964e-05, |
| "epoch": 0.7394366197183099, |
| "step": 210 |
| }, |
| { |
| "loss": 2.4275, |
| "grad_norm": 8.197113037109375, |
| "learning_rate": 1.8779342723004698e-05, |
| "epoch": 0.7746478873239436, |
| "step": 220 |
| }, |
| { |
| "loss": 2.1541, |
| "grad_norm": 7.156861305236816, |
| "learning_rate": 1.862284820031299e-05, |
| "epoch": 0.8098591549295775, |
| "step": 230 |
| }, |
| { |
| "loss": 2.1481, |
| "grad_norm": 8.494321823120117, |
| "learning_rate": 1.8466353677621284e-05, |
| "epoch": 0.8450704225352113, |
| "step": 240 |
| }, |
| { |
| "loss": 2.1078, |
| "grad_norm": 5.825531482696533, |
| "learning_rate": 1.830985915492958e-05, |
| "epoch": 0.8802816901408451, |
| "step": 250 |
| }, |
| { |
| "loss": 1.9146, |
| "grad_norm": 6.99673318862915, |
| "learning_rate": 1.8153364632237873e-05, |
| "epoch": 0.9154929577464789, |
| "step": 260 |
| }, |
| { |
| "loss": 1.8766, |
| "grad_norm": 8.612900733947754, |
| "learning_rate": 1.7996870109546166e-05, |
| "epoch": 0.9507042253521126, |
| "step": 270 |
| }, |
| { |
| "loss": 1.7913, |
| "grad_norm": 7.821394443511963, |
| "learning_rate": 1.7840375586854463e-05, |
| "epoch": 0.9859154929577465, |
| "step": 280 |
| }, |
| { |
| "eval_loss": 1.6347781419754028, |
| "eval_accuracy": 0.7083700440528634, |
| "eval_f1": 0.6049143027945829, |
| "eval_runtime": 6.5467, |
| "eval_samples_per_second": 173.369, |
| "eval_steps_per_second": 10.845, |
| "epoch": 1.0, |
| "step": 284 |
| }, |
| { |
| "loss": 1.5623, |
| "grad_norm": 8.131426811218262, |
| "learning_rate": 1.7683881064162756e-05, |
| "epoch": 1.0211267605633803, |
| "step": 290 |
| }, |
| { |
| "loss": 1.5953, |
| "grad_norm": 8.78809642791748, |
| "learning_rate": 1.752738654147105e-05, |
| "epoch": 1.056338028169014, |
| "step": 300 |
| }, |
| { |
| "loss": 1.6067, |
| "grad_norm": 5.926104545593262, |
| "learning_rate": 1.7370892018779345e-05, |
| "epoch": 1.091549295774648, |
| "step": 310 |
| }, |
| { |
| "loss": 1.5927, |
| "grad_norm": 7.396566867828369, |
| "learning_rate": 1.721439749608764e-05, |
| "epoch": 1.1267605633802817, |
| "step": 320 |
| }, |
| { |
| "loss": 1.4279, |
| "grad_norm": 8.511696815490723, |
| "learning_rate": 1.705790297339593e-05, |
| "epoch": 1.1619718309859155, |
| "step": 330 |
| }, |
| { |
| "loss": 1.4992, |
| "grad_norm": 6.154587745666504, |
| "learning_rate": 1.6901408450704228e-05, |
| "epoch": 1.1971830985915493, |
| "step": 340 |
| }, |
| { |
| "loss": 1.4041, |
| "grad_norm": 13.939669609069824, |
| "learning_rate": 1.674491392801252e-05, |
| "epoch": 1.232394366197183, |
| "step": 350 |
| }, |
| { |
| "loss": 1.4161, |
| "grad_norm": 7.556514263153076, |
| "learning_rate": 1.6588419405320814e-05, |
| "epoch": 1.267605633802817, |
| "step": 360 |
| }, |
| { |
| "loss": 1.2424, |
| "grad_norm": 7.370925426483154, |
| "learning_rate": 1.643192488262911e-05, |
| "epoch": 1.3028169014084507, |
| "step": 370 |
| }, |
| { |
| "loss": 1.248, |
| "grad_norm": 6.655207633972168, |
| "learning_rate": 1.6275430359937403e-05, |
| "epoch": 1.3380281690140845, |
| "step": 380 |
| }, |
| { |
| "loss": 1.1601, |
| "grad_norm": 9.040409088134766, |
| "learning_rate": 1.6118935837245697e-05, |
| "epoch": 1.3732394366197183, |
| "step": 390 |
| }, |
| { |
| "loss": 1.1461, |
| "grad_norm": 8.453059196472168, |
| "learning_rate": 1.5962441314553993e-05, |
| "epoch": 1.408450704225352, |
| "step": 400 |
| }, |
| { |
| "loss": 1.2187, |
| "grad_norm": 7.965033054351807, |
| "learning_rate": 1.5805946791862286e-05, |
| "epoch": 1.443661971830986, |
| "step": 410 |
| }, |
| { |
| "loss": 1.1057, |
| "grad_norm": 7.8456645011901855, |
| "learning_rate": 1.564945226917058e-05, |
| "epoch": 1.4788732394366197, |
| "step": 420 |
| }, |
| { |
| "loss": 1.1947, |
| "grad_norm": 6.965514659881592, |
| "learning_rate": 1.5492957746478872e-05, |
| "epoch": 1.5140845070422535, |
| "step": 430 |
| }, |
| { |
| "loss": 1.1401, |
| "grad_norm": 5.833000659942627, |
| "learning_rate": 1.533646322378717e-05, |
| "epoch": 1.5492957746478875, |
| "step": 440 |
| }, |
| { |
| "loss": 1.137, |
| "grad_norm": 6.739829063415527, |
| "learning_rate": 1.5179968701095462e-05, |
| "epoch": 1.584507042253521, |
| "step": 450 |
| }, |
| { |
| "loss": 1.0756, |
| "grad_norm": 7.934983253479004, |
| "learning_rate": 1.5023474178403756e-05, |
| "epoch": 1.619718309859155, |
| "step": 460 |
| }, |
| { |
| "loss": 0.9483, |
| "grad_norm": 7.326385021209717, |
| "learning_rate": 1.4866979655712051e-05, |
| "epoch": 1.6549295774647887, |
| "step": 470 |
| }, |
| { |
| "loss": 1.016, |
| "grad_norm": 4.909506797790527, |
| "learning_rate": 1.4710485133020344e-05, |
| "epoch": 1.6901408450704225, |
| "step": 480 |
| }, |
| { |
| "loss": 1.0134, |
| "grad_norm": 7.309936046600342, |
| "learning_rate": 1.4553990610328639e-05, |
| "epoch": 1.7253521126760565, |
| "step": 490 |
| }, |
| { |
| "loss": 1.0056, |
| "grad_norm": 9.106132507324219, |
| "learning_rate": 1.4397496087636934e-05, |
| "epoch": 1.76056338028169, |
| "step": 500 |
| }, |
| { |
| "loss": 1.1269, |
| "grad_norm": 7.531581401824951, |
| "learning_rate": 1.4241001564945227e-05, |
| "epoch": 1.795774647887324, |
| "step": 510 |
| }, |
| { |
| "loss": 1.0258, |
| "grad_norm": 6.902132511138916, |
| "learning_rate": 1.4084507042253522e-05, |
| "epoch": 1.8309859154929577, |
| "step": 520 |
| }, |
| { |
| "loss": 1.0024, |
| "grad_norm": 10.563477516174316, |
| "learning_rate": 1.3928012519561815e-05, |
| "epoch": 1.8661971830985915, |
| "step": 530 |
| }, |
| { |
| "loss": 0.8689, |
| "grad_norm": 5.611667633056641, |
| "learning_rate": 1.377151799687011e-05, |
| "epoch": 1.9014084507042255, |
| "step": 540 |
| }, |
| { |
| "loss": 0.8298, |
| "grad_norm": 6.363973617553711, |
| "learning_rate": 1.3615023474178406e-05, |
| "epoch": 1.936619718309859, |
| "step": 550 |
| }, |
| { |
| "loss": 0.7272, |
| "grad_norm": 8.456687927246094, |
| "learning_rate": 1.34585289514867e-05, |
| "epoch": 1.971830985915493, |
| "step": 560 |
| }, |
| { |
| "eval_loss": 0.7739513516426086, |
| "eval_accuracy": 0.8704845814977974, |
| "eval_f1": 0.8655265093934765, |
| "eval_runtime": 6.2617, |
| "eval_samples_per_second": 181.26, |
| "eval_steps_per_second": 11.339, |
| "epoch": 2.0, |
| "step": 568 |
| }, |
| { |
| "loss": 0.8506, |
| "grad_norm": 7.487066745758057, |
| "learning_rate": 1.3302034428794994e-05, |
| "epoch": 2.007042253521127, |
| "step": 570 |
| }, |
| { |
| "loss": 0.7333, |
| "grad_norm": 5.738982677459717, |
| "learning_rate": 1.3145539906103288e-05, |
| "epoch": 2.0422535211267605, |
| "step": 580 |
| }, |
| { |
| "loss": 0.7168, |
| "grad_norm": 4.924327373504639, |
| "learning_rate": 1.2989045383411583e-05, |
| "epoch": 2.0774647887323945, |
| "step": 590 |
| }, |
| { |
| "loss": 0.7653, |
| "grad_norm": 3.7934069633483887, |
| "learning_rate": 1.2832550860719876e-05, |
| "epoch": 2.112676056338028, |
| "step": 600 |
| }, |
| { |
| "loss": 0.7952, |
| "grad_norm": 6.368825912475586, |
| "learning_rate": 1.2676056338028171e-05, |
| "epoch": 2.147887323943662, |
| "step": 610 |
| }, |
| { |
| "loss": 0.6612, |
| "grad_norm": 5.713892936706543, |
| "learning_rate": 1.2519561815336466e-05, |
| "epoch": 2.183098591549296, |
| "step": 620 |
| }, |
| { |
| "loss": 0.6836, |
| "grad_norm": 6.111892223358154, |
| "learning_rate": 1.2363067292644759e-05, |
| "epoch": 2.2183098591549295, |
| "step": 630 |
| }, |
| { |
| "loss": 0.7365, |
| "grad_norm": 8.857637405395508, |
| "learning_rate": 1.2206572769953053e-05, |
| "epoch": 2.2535211267605635, |
| "step": 640 |
| }, |
| { |
| "loss": 0.6132, |
| "grad_norm": 3.4862544536590576, |
| "learning_rate": 1.2050078247261348e-05, |
| "epoch": 2.288732394366197, |
| "step": 650 |
| }, |
| { |
| "loss": 0.6442, |
| "grad_norm": 6.8738861083984375, |
| "learning_rate": 1.1893583724569641e-05, |
| "epoch": 2.323943661971831, |
| "step": 660 |
| }, |
| { |
| "loss": 0.6584, |
| "grad_norm": 3.2398829460144043, |
| "learning_rate": 1.1737089201877936e-05, |
| "epoch": 2.359154929577465, |
| "step": 670 |
| }, |
| { |
| "loss": 0.5896, |
| "grad_norm": 4.472248077392578, |
| "learning_rate": 1.158059467918623e-05, |
| "epoch": 2.3943661971830985, |
| "step": 680 |
| }, |
| { |
| "loss": 0.5091, |
| "grad_norm": 5.502006530761719, |
| "learning_rate": 1.1424100156494524e-05, |
| "epoch": 2.4295774647887325, |
| "step": 690 |
| }, |
| { |
| "loss": 0.6145, |
| "grad_norm": 4.565939903259277, |
| "learning_rate": 1.1267605633802819e-05, |
| "epoch": 2.464788732394366, |
| "step": 700 |
| }, |
| { |
| "loss": 0.5311, |
| "grad_norm": 4.030102252960205, |
| "learning_rate": 1.1111111111111113e-05, |
| "epoch": 2.5, |
| "step": 710 |
| }, |
| { |
| "loss": 0.5494, |
| "grad_norm": 5.067589282989502, |
| "learning_rate": 1.0954616588419406e-05, |
| "epoch": 2.535211267605634, |
| "step": 720 |
| }, |
| { |
| "loss": 0.5832, |
| "grad_norm": 9.302046775817871, |
| "learning_rate": 1.0798122065727701e-05, |
| "epoch": 2.5704225352112675, |
| "step": 730 |
| }, |
| { |
| "loss": 0.4302, |
| "grad_norm": 2.904606819152832, |
| "learning_rate": 1.0641627543035994e-05, |
| "epoch": 2.6056338028169015, |
| "step": 740 |
| }, |
| { |
| "loss": 0.4584, |
| "grad_norm": 7.644087314605713, |
| "learning_rate": 1.0485133020344289e-05, |
| "epoch": 2.640845070422535, |
| "step": 750 |
| }, |
| { |
| "loss": 0.5171, |
| "grad_norm": 3.483180284500122, |
| "learning_rate": 1.0328638497652584e-05, |
| "epoch": 2.676056338028169, |
| "step": 760 |
| }, |
| { |
| "loss": 0.5933, |
| "grad_norm": 6.797661781311035, |
| "learning_rate": 1.0172143974960877e-05, |
| "epoch": 2.711267605633803, |
| "step": 770 |
| }, |
| { |
| "loss": 0.5288, |
| "grad_norm": 7.253881931304932, |
| "learning_rate": 1.0015649452269172e-05, |
| "epoch": 2.7464788732394365, |
| "step": 780 |
| }, |
| { |
| "loss": 0.5413, |
| "grad_norm": 3.835197687149048, |
| "learning_rate": 9.859154929577466e-06, |
| "epoch": 2.7816901408450705, |
| "step": 790 |
| }, |
| { |
| "loss": 0.4847, |
| "grad_norm": 4.124076843261719, |
| "learning_rate": 9.70266040688576e-06, |
| "epoch": 2.816901408450704, |
| "step": 800 |
| }, |
| { |
| "loss": 0.4481, |
| "grad_norm": 5.035274982452393, |
| "learning_rate": 9.546165884194054e-06, |
| "epoch": 2.852112676056338, |
| "step": 810 |
| }, |
| { |
| "loss": 0.486, |
| "grad_norm": 4.004342079162598, |
| "learning_rate": 9.389671361502349e-06, |
| "epoch": 2.887323943661972, |
| "step": 820 |
| }, |
| { |
| "loss": 0.4158, |
| "grad_norm": 8.212543487548828, |
| "learning_rate": 9.233176838810642e-06, |
| "epoch": 2.9225352112676055, |
| "step": 830 |
| }, |
| { |
| "loss": 0.3879, |
| "grad_norm": 7.012823104858398, |
| "learning_rate": 9.076682316118937e-06, |
| "epoch": 2.9577464788732395, |
| "step": 840 |
| }, |
| { |
| "loss": 0.4711, |
| "grad_norm": 3.63045072555542, |
| "learning_rate": 8.920187793427231e-06, |
| "epoch": 2.992957746478873, |
| "step": 850 |
| }, |
| { |
| "eval_loss": 0.5145121812820435, |
| "eval_accuracy": 0.8986784140969163, |
| "eval_f1": 0.907173419320349, |
| "eval_runtime": 6.3694, |
| "eval_samples_per_second": 178.195, |
| "eval_steps_per_second": 11.147, |
| "epoch": 3.0, |
| "step": 852 |
| }, |
| { |
| "loss": 0.4283, |
| "grad_norm": 7.712802886962891, |
| "learning_rate": 8.763693270735524e-06, |
| "epoch": 3.028169014084507, |
| "step": 860 |
| }, |
| { |
| "loss": 0.3899, |
| "grad_norm": 3.2548012733459473, |
| "learning_rate": 8.60719874804382e-06, |
| "epoch": 3.063380281690141, |
| "step": 870 |
| }, |
| { |
| "loss": 0.3646, |
| "grad_norm": 7.220994472503662, |
| "learning_rate": 8.450704225352114e-06, |
| "epoch": 3.0985915492957745, |
| "step": 880 |
| }, |
| { |
| "loss": 0.3313, |
| "grad_norm": 2.882326126098633, |
| "learning_rate": 8.294209702660407e-06, |
| "epoch": 3.1338028169014085, |
| "step": 890 |
| }, |
| { |
| "loss": 0.4364, |
| "grad_norm": 3.5633955001831055, |
| "learning_rate": 8.137715179968702e-06, |
| "epoch": 3.169014084507042, |
| "step": 900 |
| }, |
| { |
| "loss": 0.2967, |
| "grad_norm": 1.0878703594207764, |
| "learning_rate": 7.981220657276996e-06, |
| "epoch": 3.204225352112676, |
| "step": 910 |
| }, |
| { |
| "loss": 0.3765, |
| "grad_norm": 4.074843883514404, |
| "learning_rate": 7.82472613458529e-06, |
| "epoch": 3.23943661971831, |
| "step": 920 |
| }, |
| { |
| "loss": 0.3718, |
| "grad_norm": 3.4090213775634766, |
| "learning_rate": 7.668231611893584e-06, |
| "epoch": 3.2746478873239435, |
| "step": 930 |
| }, |
| { |
| "loss": 0.3826, |
| "grad_norm": 9.247264862060547, |
| "learning_rate": 7.511737089201878e-06, |
| "epoch": 3.3098591549295775, |
| "step": 940 |
| }, |
| { |
| "loss": 0.2875, |
| "grad_norm": 4.87561559677124, |
| "learning_rate": 7.355242566510172e-06, |
| "epoch": 3.345070422535211, |
| "step": 950 |
| }, |
| { |
| "loss": 0.322, |
| "grad_norm": 6.722829341888428, |
| "learning_rate": 7.198748043818467e-06, |
| "epoch": 3.380281690140845, |
| "step": 960 |
| }, |
| { |
| "loss": 0.4269, |
| "grad_norm": 4.985360145568848, |
| "learning_rate": 7.042253521126761e-06, |
| "epoch": 3.415492957746479, |
| "step": 970 |
| }, |
| { |
| "loss": 0.3102, |
| "grad_norm": 6.112848281860352, |
| "learning_rate": 6.885758998435055e-06, |
| "epoch": 3.4507042253521125, |
| "step": 980 |
| }, |
| { |
| "loss": 0.3138, |
| "grad_norm": 2.813039779663086, |
| "learning_rate": 6.72926447574335e-06, |
| "epoch": 3.4859154929577465, |
| "step": 990 |
| }, |
| { |
| "loss": 0.3323, |
| "grad_norm": 4.038683891296387, |
| "learning_rate": 6.572769953051644e-06, |
| "epoch": 3.52112676056338, |
| "step": 1000 |
| }, |
| { |
| "loss": 0.366, |
| "grad_norm": 2.771172046661377, |
| "learning_rate": 6.416275430359938e-06, |
| "epoch": 3.556338028169014, |
| "step": 1010 |
| }, |
| { |
| "loss": 0.3743, |
| "grad_norm": 5.438896179199219, |
| "learning_rate": 6.259780907668233e-06, |
| "epoch": 3.591549295774648, |
| "step": 1020 |
| }, |
| { |
| "loss": 0.3858, |
| "grad_norm": 5.540735721588135, |
| "learning_rate": 6.103286384976527e-06, |
| "epoch": 3.626760563380282, |
| "step": 1030 |
| }, |
| { |
| "loss": 0.2838, |
| "grad_norm": 3.3250198364257812, |
| "learning_rate": 5.946791862284821e-06, |
| "epoch": 3.6619718309859155, |
| "step": 1040 |
| }, |
| { |
| "loss": 0.2888, |
| "grad_norm": 4.223079204559326, |
| "learning_rate": 5.790297339593115e-06, |
| "epoch": 3.697183098591549, |
| "step": 1050 |
| }, |
| { |
| "loss": 0.3347, |
| "grad_norm": 6.852585792541504, |
| "learning_rate": 5.633802816901409e-06, |
| "epoch": 3.732394366197183, |
| "step": 1060 |
| }, |
| { |
| "loss": 0.2995, |
| "grad_norm": 2.4974894523620605, |
| "learning_rate": 5.477308294209703e-06, |
| "epoch": 3.767605633802817, |
| "step": 1070 |
| }, |
| { |
| "loss": 0.3614, |
| "grad_norm": 2.6977944374084473, |
| "learning_rate": 5.320813771517997e-06, |
| "epoch": 3.802816901408451, |
| "step": 1080 |
| }, |
| { |
| "loss": 0.3058, |
| "grad_norm": 3.4490833282470703, |
| "learning_rate": 5.164319248826292e-06, |
| "epoch": 3.8380281690140845, |
| "step": 1090 |
| }, |
| { |
| "loss": 0.2763, |
| "grad_norm": 2.6724023818969727, |
| "learning_rate": 5.007824726134586e-06, |
| "epoch": 3.873239436619718, |
| "step": 1100 |
| }, |
| { |
| "loss": 0.3458, |
| "grad_norm": 1.8767718076705933, |
| "learning_rate": 4.85133020344288e-06, |
| "epoch": 3.908450704225352, |
| "step": 1110 |
| }, |
| { |
| "loss": 0.3269, |
| "grad_norm": 13.369972229003906, |
| "learning_rate": 4.694835680751174e-06, |
| "epoch": 3.943661971830986, |
| "step": 1120 |
| }, |
| { |
| "loss": 0.3508, |
| "grad_norm": 9.277174949645996, |
| "learning_rate": 4.538341158059468e-06, |
| "epoch": 3.97887323943662, |
| "step": 1130 |
| }, |
| { |
| "eval_loss": 0.4453487694263458, |
| "eval_accuracy": 0.9030837004405287, |
| "eval_f1": 0.9101041734248071, |
| "eval_runtime": 6.2611, |
| "eval_samples_per_second": 181.279, |
| "eval_steps_per_second": 11.34, |
| "epoch": 4.0, |
| "step": 1136 |
| }, |
| { |
| "loss": 0.3061, |
| "grad_norm": 5.516575336456299, |
| "learning_rate": 4.381846635367762e-06, |
| "epoch": 4.014084507042254, |
| "step": 1140 |
| }, |
| { |
| "loss": 0.3649, |
| "grad_norm": 5.982604026794434, |
| "learning_rate": 4.225352112676057e-06, |
| "epoch": 4.049295774647887, |
| "step": 1150 |
| }, |
| { |
| "loss": 0.2965, |
| "grad_norm": 7.574158668518066, |
| "learning_rate": 4.068857589984351e-06, |
| "epoch": 4.084507042253521, |
| "step": 1160 |
| }, |
| { |
| "loss": 0.2558, |
| "grad_norm": 2.2732813358306885, |
| "learning_rate": 3.912363067292645e-06, |
| "epoch": 4.119718309859155, |
| "step": 1170 |
| }, |
| { |
| "loss": 0.2397, |
| "grad_norm": 4.167398929595947, |
| "learning_rate": 3.755868544600939e-06, |
| "epoch": 4.154929577464789, |
| "step": 1180 |
| }, |
| { |
| "loss": 0.2143, |
| "grad_norm": 1.0560132265090942, |
| "learning_rate": 3.5993740219092334e-06, |
| "epoch": 4.190140845070423, |
| "step": 1190 |
| }, |
| { |
| "loss": 0.3412, |
| "grad_norm": 12.945590019226074, |
| "learning_rate": 3.4428794992175273e-06, |
| "epoch": 4.225352112676056, |
| "step": 1200 |
| }, |
| { |
| "loss": 0.2683, |
| "grad_norm": 2.5129096508026123, |
| "learning_rate": 3.286384976525822e-06, |
| "epoch": 4.26056338028169, |
| "step": 1210 |
| }, |
| { |
| "loss": 0.2002, |
| "grad_norm": 2.868868827819824, |
| "learning_rate": 3.1298904538341164e-06, |
| "epoch": 4.295774647887324, |
| "step": 1220 |
| }, |
| { |
| "loss": 0.2111, |
| "grad_norm": 5.586353778839111, |
| "learning_rate": 2.9733959311424103e-06, |
| "epoch": 4.330985915492958, |
| "step": 1230 |
| }, |
| { |
| "loss": 0.1924, |
| "grad_norm": 2.2831079959869385, |
| "learning_rate": 2.8169014084507046e-06, |
| "epoch": 4.366197183098592, |
| "step": 1240 |
| }, |
| { |
| "loss": 0.1564, |
| "grad_norm": 1.5656145811080933, |
| "learning_rate": 2.6604068857589986e-06, |
| "epoch": 4.401408450704225, |
| "step": 1250 |
| }, |
| { |
| "loss": 0.2483, |
| "grad_norm": 1.9988621473312378, |
| "learning_rate": 2.503912363067293e-06, |
| "epoch": 4.436619718309859, |
| "step": 1260 |
| }, |
| { |
| "loss": 0.2739, |
| "grad_norm": 2.6662495136260986, |
| "learning_rate": 2.347417840375587e-06, |
| "epoch": 4.471830985915493, |
| "step": 1270 |
| }, |
| { |
| "loss": 0.2701, |
| "grad_norm": 7.080715656280518, |
| "learning_rate": 2.190923317683881e-06, |
| "epoch": 4.507042253521127, |
| "step": 1280 |
| }, |
| { |
| "loss": 0.2675, |
| "grad_norm": 2.611051082611084, |
| "learning_rate": 2.0344287949921754e-06, |
| "epoch": 4.542253521126761, |
| "step": 1290 |
| }, |
| { |
| "loss": 0.2305, |
| "grad_norm": 2.516238212585449, |
| "learning_rate": 1.8779342723004696e-06, |
| "epoch": 4.577464788732394, |
| "step": 1300 |
| }, |
| { |
| "loss": 0.2796, |
| "grad_norm": 2.024088144302368, |
| "learning_rate": 1.7214397496087637e-06, |
| "epoch": 4.612676056338028, |
| "step": 1310 |
| }, |
| { |
| "loss": 0.2608, |
| "grad_norm": 4.545577049255371, |
| "learning_rate": 1.5649452269170582e-06, |
| "epoch": 4.647887323943662, |
| "step": 1320 |
| }, |
| { |
| "loss": 0.1957, |
| "grad_norm": 7.018043041229248, |
| "learning_rate": 1.4084507042253523e-06, |
| "epoch": 4.683098591549296, |
| "step": 1330 |
| }, |
| { |
| "loss": 0.2977, |
| "grad_norm": 1.9592317342758179, |
| "learning_rate": 1.2519561815336464e-06, |
| "epoch": 4.71830985915493, |
| "step": 1340 |
| }, |
| { |
| "loss": 0.2935, |
| "grad_norm": 2.5041024684906006, |
| "learning_rate": 1.0954616588419406e-06, |
| "epoch": 4.753521126760563, |
| "step": 1350 |
| }, |
| { |
| "loss": 0.2294, |
| "grad_norm": 2.4718971252441406, |
| "learning_rate": 9.389671361502348e-07, |
| "epoch": 4.788732394366197, |
| "step": 1360 |
| }, |
| { |
| "loss": 0.2916, |
| "grad_norm": 1.6896077394485474, |
| "learning_rate": 7.824726134585291e-07, |
| "epoch": 4.823943661971831, |
| "step": 1370 |
| }, |
| { |
| "loss": 0.2454, |
| "grad_norm": 1.6241123676300049, |
| "learning_rate": 6.259780907668232e-07, |
| "epoch": 4.859154929577465, |
| "step": 1380 |
| }, |
| { |
| "loss": 0.2732, |
| "grad_norm": 1.5693773031234741, |
| "learning_rate": 4.694835680751174e-07, |
| "epoch": 4.894366197183099, |
| "step": 1390 |
| }, |
| { |
| "loss": 0.2474, |
| "grad_norm": 1.2409546375274658, |
| "learning_rate": 3.129890453834116e-07, |
| "epoch": 4.929577464788732, |
| "step": 1400 |
| }, |
| { |
| "loss": 0.198, |
| "grad_norm": 5.357175827026367, |
| "learning_rate": 1.564945226917058e-07, |
| "epoch": 4.964788732394366, |
| "step": 1410 |
| }, |
| { |
| "loss": 0.1852, |
| "grad_norm": 0.5980310440063477, |
| "learning_rate": 0.0, |
| "epoch": 5.0, |
| "step": 1420 |
| }, |
| { |
| "eval_loss": 0.42191559076309204, |
| "eval_accuracy": 0.9118942731277533, |
| "eval_f1": 0.9167823247394992, |
| "eval_runtime": 6.6973, |
| "eval_samples_per_second": 169.471, |
| "eval_steps_per_second": 10.601, |
| "epoch": 5.0, |
| "step": 1420 |
| }, |
| { |
| "train_runtime": 510.4172, |
| "train_samples_per_second": 44.454, |
| "train_steps_per_second": 2.782, |
| "total_flos": 1492886076971520.0, |
| "train_loss": 1.0440410888530838, |
| "epoch": 5.0, |
| "step": 1420 |
| }, |
| { |
| "eval_loss": 0.42191559076309204, |
| "eval_accuracy": 0.9118942731277533, |
| "eval_f1": 0.9167823247394992, |
| "eval_runtime": 6.542, |
| "eval_samples_per_second": 173.496, |
| "eval_steps_per_second": 10.853, |
| "epoch": 5.0, |
| "step": 1420 |
| } |
| ] |
