| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.99695843190267, | |
| "eval_steps": 500, | |
| "global_step": 1107, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.027036160865157147, | |
| "grad_norm": 3.7416573454919604, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8414, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.054072321730314295, | |
| "grad_norm": 2.420213587424198, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6857, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08110848259547145, | |
| "grad_norm": 2.026364466482845, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6481, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10814464346062859, | |
| "grad_norm": 1.7544085093823143, | |
| "learning_rate": 5e-06, | |
| "loss": 0.636, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13518080432578575, | |
| "grad_norm": 2.5689946075394876, | |
| "learning_rate": 5e-06, | |
| "loss": 0.621, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1622169651909429, | |
| "grad_norm": 2.90035063993728, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6159, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18925312605610004, | |
| "grad_norm": 1.9704021628275166, | |
| "learning_rate": 5e-06, | |
| "loss": 0.613, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21628928692125718, | |
| "grad_norm": 2.0006565102546277, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6038, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24332544778641432, | |
| "grad_norm": 1.8244581409196392, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6014, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2703616086515715, | |
| "grad_norm": 3.5170158663707562, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6058, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.29739776951672864, | |
| "grad_norm": 1.9160505890443071, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6012, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3244339303818858, | |
| "grad_norm": 1.5411483704174398, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5956, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3514700912470429, | |
| "grad_norm": 2.649167678139615, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5974, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.37850625211220007, | |
| "grad_norm": 1.4247865709072371, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5965, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4055424129773572, | |
| "grad_norm": 1.4405880085697187, | |
| "learning_rate": 5e-06, | |
| "loss": 0.589, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.43257857384251436, | |
| "grad_norm": 1.6781578168272708, | |
| "learning_rate": 5e-06, | |
| "loss": 0.592, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4596147347076715, | |
| "grad_norm": 1.9394919639875512, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5928, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.48665089557282865, | |
| "grad_norm": 1.7808260489612084, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5922, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5136870564379858, | |
| "grad_norm": 1.6418704591917206, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5887, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.540723217303143, | |
| "grad_norm": 1.463644316677313, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5863, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5677593781683001, | |
| "grad_norm": 1.7587180647301535, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5887, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5947955390334573, | |
| "grad_norm": 1.6536202559796944, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5843, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6218316998986144, | |
| "grad_norm": 1.4196511331884876, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5857, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6488678607637716, | |
| "grad_norm": 1.36566737151604, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5824, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6759040216289287, | |
| "grad_norm": 2.9952670177096987, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5761, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7029401824940859, | |
| "grad_norm": 1.4939335531208207, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5792, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.729976343359243, | |
| "grad_norm": 1.3045505143888763, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5809, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7570125042244001, | |
| "grad_norm": 1.2454141875159743, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5761, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7840486650895573, | |
| "grad_norm": 1.6672422177821689, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5762, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8110848259547144, | |
| "grad_norm": 1.3806810495733297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5761, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8381209868198716, | |
| "grad_norm": 1.4982083898695995, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5734, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8651571476850287, | |
| "grad_norm": 1.6985418707956137, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5721, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8921933085501859, | |
| "grad_norm": 2.04658180538426, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5735, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.919229469415343, | |
| "grad_norm": 2.2541915966390924, | |
| "learning_rate": 5e-06, | |
| "loss": 0.581, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9462656302805001, | |
| "grad_norm": 1.9396838879359772, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5715, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9733017911456573, | |
| "grad_norm": 1.981100443956288, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5691, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.9976343359242987, | |
| "eval_loss": 0.07115323096513748, | |
| "eval_runtime": 246.0901, | |
| "eval_samples_per_second": 40.493, | |
| "eval_steps_per_second": 0.634, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.0023656640757013, | |
| "grad_norm": 3.6621685211123927, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5653, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.0294018249408583, | |
| "grad_norm": 2.4178358681298926, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4812, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.0564379858060156, | |
| "grad_norm": 1.573769542810224, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4752, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0834741466711728, | |
| "grad_norm": 1.6174732701515342, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4784, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.1105103075363298, | |
| "grad_norm": 1.3203029544672327, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4767, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.1375464684014869, | |
| "grad_norm": 1.659088202560807, | |
| "learning_rate": 5e-06, | |
| "loss": 0.48, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.1645826292666441, | |
| "grad_norm": 1.5293709624512395, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4886, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.1916187901318014, | |
| "grad_norm": 1.7162950969288626, | |
| "learning_rate": 5e-06, | |
| "loss": 0.48, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.2186549509969584, | |
| "grad_norm": 1.789642107765462, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4846, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.2456911118621157, | |
| "grad_norm": 2.3719269899175464, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4868, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 2.0649999632624234, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4867, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.29976343359243, | |
| "grad_norm": 1.7868192883503795, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4808, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.326799594457587, | |
| "grad_norm": 1.580468512053965, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4802, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.3538357553227442, | |
| "grad_norm": 1.4368050523026477, | |
| "learning_rate": 5e-06, | |
| "loss": 0.484, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3808719161879013, | |
| "grad_norm": 1.8494974343766688, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4852, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.4079080770530585, | |
| "grad_norm": 1.4845281910598, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4873, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.4349442379182156, | |
| "grad_norm": 1.7382803616315246, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4805, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.4619803987833728, | |
| "grad_norm": 1.9374881637819812, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4852, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.4890165596485299, | |
| "grad_norm": 2.0166526872457995, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4837, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.5160527205136871, | |
| "grad_norm": 1.9298737331649736, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4854, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.5430888813788441, | |
| "grad_norm": 1.656041584162736, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4805, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.5701250422440014, | |
| "grad_norm": 1.322425683347454, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4824, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.5971612031091587, | |
| "grad_norm": 1.5996884459070573, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4865, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.6241973639743157, | |
| "grad_norm": 1.7912731135269302, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4855, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6512335248394727, | |
| "grad_norm": 1.6299247983634995, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4839, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.67826968570463, | |
| "grad_norm": 1.6195975059981367, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4879, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.7053058465697872, | |
| "grad_norm": 1.5581289945884544, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4934, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.7323420074349443, | |
| "grad_norm": 1.7245628020214243, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4921, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.7593781683001013, | |
| "grad_norm": 1.4558529164875116, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4899, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.7864143291652586, | |
| "grad_norm": 1.3838084244152689, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4867, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.8134504900304158, | |
| "grad_norm": 1.2978952486050377, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4898, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.8404866508955728, | |
| "grad_norm": 1.3510779632006422, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4933, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.8675228117607299, | |
| "grad_norm": 1.2650328544272216, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4922, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.8945589726258871, | |
| "grad_norm": 1.2364699638447674, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4949, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.9215951334910444, | |
| "grad_norm": 1.2724457587924303, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4995, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.9486312943562014, | |
| "grad_norm": 1.3500253788955112, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4927, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.9756674552213584, | |
| "grad_norm": 1.211531877719849, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4889, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.9972963839134843, | |
| "eval_loss": 0.07184100151062012, | |
| "eval_runtime": 245.9279, | |
| "eval_samples_per_second": 40.52, | |
| "eval_steps_per_second": 0.634, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 2.0047313281514025, | |
| "grad_norm": 3.245553628462997, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4769, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.0317674890165596, | |
| "grad_norm": 1.8685703471097137, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3856, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.0588036498817166, | |
| "grad_norm": 1.9250688037531085, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3858, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.085839810746874, | |
| "grad_norm": 1.7824110630026255, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3817, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.112875971612031, | |
| "grad_norm": 1.6606355551312104, | |
| "learning_rate": 5e-06, | |
| "loss": 0.382, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.139912132477188, | |
| "grad_norm": 1.638700904915986, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3811, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.1669482933423456, | |
| "grad_norm": 1.615315899395297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3877, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.1939844542075027, | |
| "grad_norm": 1.708187020441321, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3869, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.2210206150726597, | |
| "grad_norm": 1.7454063972273366, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3874, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.2480567759378167, | |
| "grad_norm": 1.8331936510642228, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3899, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.2750929368029738, | |
| "grad_norm": 1.7020028217377983, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3922, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.3021290976681312, | |
| "grad_norm": 1.6721649170340955, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3866, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.3291652585332883, | |
| "grad_norm": 1.6841976597663628, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3902, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.3562014193984453, | |
| "grad_norm": 1.5088788343187851, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3953, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.3832375802636028, | |
| "grad_norm": 1.7096850640735373, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3938, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.41027374112876, | |
| "grad_norm": 1.5945133369441267, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3936, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.437309901993917, | |
| "grad_norm": 1.7236799110962686, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3944, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.464346062859074, | |
| "grad_norm": 1.6116484052046463, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3925, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.4913822237242313, | |
| "grad_norm": 1.575428566577217, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3939, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.5184183845893884, | |
| "grad_norm": 1.5852588401636647, | |
| "learning_rate": 5e-06, | |
| "loss": 0.393, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 1.5725956084643744, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4006, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.5724907063197024, | |
| "grad_norm": 1.5697632754260353, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3958, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.59952686718486, | |
| "grad_norm": 1.6015038862083164, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4015, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.626563028050017, | |
| "grad_norm": 1.5339909095907225, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3997, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.653599188915174, | |
| "grad_norm": 1.5352960562989082, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4039, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.6806353497803315, | |
| "grad_norm": 1.5748878900674392, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4019, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.7076715106454885, | |
| "grad_norm": 1.8108417713608, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3956, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.7347076715106455, | |
| "grad_norm": 1.9888167435166277, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4028, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.7617438323758026, | |
| "grad_norm": 1.6982996347109014, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4052, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.7887799932409596, | |
| "grad_norm": 1.4591697770426337, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4029, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.815816154106117, | |
| "grad_norm": 1.4793538277944271, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4024, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.842852314971274, | |
| "grad_norm": 1.5146429069615557, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4037, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.869888475836431, | |
| "grad_norm": 1.4264075457576446, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3995, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.8969246367015886, | |
| "grad_norm": 1.6106041516243625, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4078, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.9239607975667457, | |
| "grad_norm": 1.4810218451874833, | |
| "learning_rate": 5e-06, | |
| "loss": 0.403, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.9509969584319027, | |
| "grad_norm": 1.4927021349271592, | |
| "learning_rate": 5e-06, | |
| "loss": 0.406, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.9780331192970597, | |
| "grad_norm": 1.4791467599867494, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4055, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.99695843190267, | |
| "eval_loss": 0.07671036571264267, | |
| "eval_runtime": 251.6292, | |
| "eval_samples_per_second": 39.602, | |
| "eval_steps_per_second": 0.62, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 2.99695843190267, | |
| "step": 1107, | |
| "total_flos": 1854056851046400.0, | |
| "train_loss": 0.49416024618140186, | |
| "train_runtime": 35644.3817, | |
| "train_samples_per_second": 15.935, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1107, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1854056851046400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |