| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6397952655150352, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006397952655150352, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9893367455747496e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012795905310300703, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.978673491149499e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019193857965451054, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.968010236724249e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025591810620601407, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9573469822989975e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03198976327575176, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.946683727873747e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03838771593090211, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.936020473448497e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.044785668586052464, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.925357219023246e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05118362124120281, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9146939645979955e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05758157389635317, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.904030710172745e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06397952655150352, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.893367455747495e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07037747920665387, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.882704201322244e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07677543186180422, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.872040946896993e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08317338451695458, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.861377692471742e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08957133717210493, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.850714438046492e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09596928982725528, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8400511836212415e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10236724248240563, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.829387929195991e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.10876519513755598, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.81872467477074e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11516314779270634, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.80806142034549e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12156110044785669, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.797398165920239e-05, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12795905310300704, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.786734911494988e-05, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1343570057581574, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7760716570697375e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14075495841330773, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7654084026444875e-05, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.1471529110684581, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.754745148219237e-05, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.15355086372360843, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.744081893793986e-05, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1599488163787588, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7334186393687355e-05, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16634676903390916, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7227553849434855e-05, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.1727447216890595, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.712092130518234e-05, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.17914267434420986, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7014288760929834e-05, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.1855406269993602, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6907656216677334e-05, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.19193857965451055, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.680102367242483e-05, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19833653230966092, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.669439112817232e-05, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.20473448496481125, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6587758583919814e-05, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.21113243761996162, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6481126039667314e-05, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.21753039027511195, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.63744934954148e-05, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.22392834293026231, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6267860951162294e-05, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.23032629558541268, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.616122840690979e-05, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.236724248240563, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.605459586265729e-05, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.24312220089571338, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.594796331840478e-05, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.2495201535508637, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5841330774152274e-05, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.2559181062060141, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.573469822989977e-05, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26231605886116444, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.562806568564727e-05, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.2687140115163148, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5521433141394754e-05, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.2751119641714651, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.541480059714225e-05, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.28150991682661547, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.530816805288974e-05, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.28790786948176583, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.520153550863724e-05, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.2943058221369162, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5094902964384734e-05, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.30070377479206656, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.498827042013223e-05, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.30710172744721687, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.488163787587972e-05, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.31349968010236723, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.477500533162721e-05, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3198976327575176, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.466837278737471e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32629558541266795, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.45617402431222e-05, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.3326935380678183, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.44551076988697e-05, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.3390914907229686, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.434847515461719e-05, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.345489443378119, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4241842610364687e-05, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.35188739603326935, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.413521006611218e-05, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3582853486884197, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.402857752185967e-05, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.3646833013435701, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3921944977607166e-05, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.3710812539987204, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.381531243335466e-05, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.37747920665387075, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.370867988910215e-05, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.3838771593090211, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.360204734484965e-05, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3902751119641715, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3495414800597146e-05, | |
| "loss": 0.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.39667306461932184, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.338878225634464e-05, | |
| "loss": 0.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.40307101727447214, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.328214971209213e-05, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.4094689699296225, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3175517167839626e-05, | |
| "loss": 0.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.41586692258477287, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.306888462358712e-05, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.42226487523992323, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.296225207933461e-05, | |
| "loss": 0.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.4286628278950736, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2855619535082106e-05, | |
| "loss": 0.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.4350607805502239, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2748986990829606e-05, | |
| "loss": 0.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.44145873320537427, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.26423544465771e-05, | |
| "loss": 0.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.44785668586052463, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.253572190232459e-05, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.454254638515675, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2429089358072086e-05, | |
| "loss": 0.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.46065259117082535, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.232245681381958e-05, | |
| "loss": 0.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.46705054382597566, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.221582426956707e-05, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.473448496481126, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2109191725314565e-05, | |
| "loss": 0.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.4798464491362764, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2002559181062066e-05, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.48624440179142675, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.189592663680956e-05, | |
| "loss": 0.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.4926423544465771, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.178929409255705e-05, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.4990403071017274, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1682661548304545e-05, | |
| "loss": 0.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.5054382597568778, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.157602900405204e-05, | |
| "loss": 0.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.5118362124120281, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.146939645979953e-05, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5182341650671785, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1362763915547025e-05, | |
| "loss": 0.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.5246321177223289, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.125613137129452e-05, | |
| "loss": 0.0, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.5310300703774792, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.114949882704202e-05, | |
| "loss": 0.0, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.5374280230326296, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.104286628278951e-05, | |
| "loss": 0.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.5438259756877799, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0936233738537005e-05, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.5502239283429302, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.08296011942845e-05, | |
| "loss": 0.0, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.5566218809980806, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.072296865003199e-05, | |
| "loss": 0.0, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.5630198336532309, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0616336105779485e-05, | |
| "loss": 0.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.5694177863083814, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.050970356152698e-05, | |
| "loss": 0.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.5758157389635317, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.040307101727447e-05, | |
| "loss": 0.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.582213691618682, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.029643847302197e-05, | |
| "loss": 0.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.5886116442738324, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0189805928769465e-05, | |
| "loss": 0.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.5950095969289827, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.008317338451696e-05, | |
| "loss": 0.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.6014075495841331, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.997654084026445e-05, | |
| "loss": 0.0, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.6078055022392834, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9869908296011945e-05, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.6142034548944337, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.976327575175944e-05, | |
| "loss": 0.0, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.6206014075495841, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.965664320750693e-05, | |
| "loss": 0.0, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.6269993602047345, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9550010663254424e-05, | |
| "loss": 0.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.6333973128598849, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9443378119001924e-05, | |
| "loss": 0.0, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.6397952655150352, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.933674557474942e-05, | |
| "loss": 0.0, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4689, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |