| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9991537376586743, | |
| "eval_steps": 500, | |
| "global_step": 1329, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022566995768688293, | |
| "grad_norm": 3.9500676023225703, | |
| "learning_rate": 3.7593984962406015e-07, | |
| "loss": 0.8582, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045133991537376586, | |
| "grad_norm": 1.395677808116374, | |
| "learning_rate": 7.518796992481203e-07, | |
| "loss": 0.8024, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06770098730606489, | |
| "grad_norm": 0.9062193282306004, | |
| "learning_rate": 1.1278195488721805e-06, | |
| "loss": 0.7357, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09026798307475317, | |
| "grad_norm": 0.8282785482347225, | |
| "learning_rate": 1.5037593984962406e-06, | |
| "loss": 0.6898, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11283497884344147, | |
| "grad_norm": 0.701981062657255, | |
| "learning_rate": 1.8796992481203007e-06, | |
| "loss": 0.6707, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13540197461212977, | |
| "grad_norm": 0.640628105313228, | |
| "learning_rate": 2.255639097744361e-06, | |
| "loss": 0.6616, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15796897038081806, | |
| "grad_norm": 0.6794950494897954, | |
| "learning_rate": 2.631578947368421e-06, | |
| "loss": 0.6518, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18053596614950634, | |
| "grad_norm": 0.7767981323221586, | |
| "learning_rate": 3.007518796992481e-06, | |
| "loss": 0.6496, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20310296191819463, | |
| "grad_norm": 0.7882061395786479, | |
| "learning_rate": 3.3834586466165413e-06, | |
| "loss": 0.6451, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22566995768688294, | |
| "grad_norm": 0.9439189657933283, | |
| "learning_rate": 3.7593984962406014e-06, | |
| "loss": 0.6417, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24823695345557123, | |
| "grad_norm": 0.7346506648254489, | |
| "learning_rate": 4.135338345864662e-06, | |
| "loss": 0.6314, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27080394922425954, | |
| "grad_norm": 0.6595327999279074, | |
| "learning_rate": 4.511278195488722e-06, | |
| "loss": 0.6293, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2933709449929478, | |
| "grad_norm": 0.8336967878084969, | |
| "learning_rate": 4.887218045112782e-06, | |
| "loss": 0.6301, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3159379407616361, | |
| "grad_norm": 1.0189555343494847, | |
| "learning_rate": 4.9995858503307465e-06, | |
| "loss": 0.6244, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3385049365303244, | |
| "grad_norm": 0.7728001819911596, | |
| "learning_rate": 4.997557699213042e-06, | |
| "loss": 0.6247, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3610719322990127, | |
| "grad_norm": 0.9777925962610354, | |
| "learning_rate": 4.993840875896834e-06, | |
| "loss": 0.6272, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.383638928067701, | |
| "grad_norm": 0.7322084042258205, | |
| "learning_rate": 4.988437944773639e-06, | |
| "loss": 0.6206, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.40620592383638926, | |
| "grad_norm": 0.5923379291119025, | |
| "learning_rate": 4.981352633551117e-06, | |
| "loss": 0.6168, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4287729196050776, | |
| "grad_norm": 0.5930368670137429, | |
| "learning_rate": 4.972589830681161e-06, | |
| "loss": 0.611, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4513399153737659, | |
| "grad_norm": 0.6233035871272617, | |
| "learning_rate": 4.962155581987166e-06, | |
| "loss": 0.6169, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47390691114245415, | |
| "grad_norm": 0.9181448240990033, | |
| "learning_rate": 4.9500570864927485e-06, | |
| "loss": 0.6131, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.49647390691114246, | |
| "grad_norm": 0.6136110334327369, | |
| "learning_rate": 4.936302691454844e-06, | |
| "loss": 0.6046, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5190409026798307, | |
| "grad_norm": 0.6511071668467217, | |
| "learning_rate": 4.920901886604593e-06, | |
| "loss": 0.6133, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5416078984485191, | |
| "grad_norm": 0.7958047199444372, | |
| "learning_rate": 4.9038652975999665e-06, | |
| "loss": 0.6118, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5641748942172073, | |
| "grad_norm": 0.6134271249647514, | |
| "learning_rate": 4.8852046786946946e-06, | |
| "loss": 0.6057, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5867418899858956, | |
| "grad_norm": 0.7236439355039117, | |
| "learning_rate": 4.864932904628507e-06, | |
| "loss": 0.608, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.609308885754584, | |
| "grad_norm": 0.6533513563016325, | |
| "learning_rate": 4.843063961744315e-06, | |
| "loss": 0.6031, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6318758815232722, | |
| "grad_norm": 0.6682862848806669, | |
| "learning_rate": 4.819612938338455e-06, | |
| "loss": 0.6096, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6544428772919605, | |
| "grad_norm": 0.6266507108859902, | |
| "learning_rate": 4.794596014250633e-06, | |
| "loss": 0.6027, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6770098730606487, | |
| "grad_norm": 0.6518141655545894, | |
| "learning_rate": 4.768030449700788e-06, | |
| "loss": 0.6086, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6995768688293371, | |
| "grad_norm": 0.5630169599812361, | |
| "learning_rate": 4.7399345733805415e-06, | |
| "loss": 0.6015, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7221438645980254, | |
| "grad_norm": 0.5368338699635572, | |
| "learning_rate": 4.710327769807469e-06, | |
| "loss": 0.6046, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7447108603667136, | |
| "grad_norm": 0.5663633274514737, | |
| "learning_rate": 4.679230465950908e-06, | |
| "loss": 0.6, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.767277856135402, | |
| "grad_norm": 0.6293933108526993, | |
| "learning_rate": 4.646664117138547e-06, | |
| "loss": 0.5993, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7898448519040903, | |
| "grad_norm": 0.5856354618989478, | |
| "learning_rate": 4.612651192253495e-06, | |
| "loss": 0.6004, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8124118476727785, | |
| "grad_norm": 0.5921119713926103, | |
| "learning_rate": 4.577215158232064e-06, | |
| "loss": 0.5993, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8349788434414669, | |
| "grad_norm": 0.6330447864809035, | |
| "learning_rate": 4.540380463872945e-06, | |
| "loss": 0.6063, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8575458392101551, | |
| "grad_norm": 0.5905756830961565, | |
| "learning_rate": 4.502172522968966e-06, | |
| "loss": 0.6027, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8801128349788434, | |
| "grad_norm": 0.6831894646683164, | |
| "learning_rate": 4.462617696773059e-06, | |
| "loss": 0.5966, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9026798307475318, | |
| "grad_norm": 0.7462417386371082, | |
| "learning_rate": 4.4217432758105215e-06, | |
| "loss": 0.5988, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.92524682651622, | |
| "grad_norm": 0.6005218513233451, | |
| "learning_rate": 4.379577461050153e-06, | |
| "loss": 0.5967, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9478138222849083, | |
| "grad_norm": 0.6506758426507315, | |
| "learning_rate": 4.336149344447227e-06, | |
| "loss": 0.5972, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9703808180535967, | |
| "grad_norm": 0.5379000787907976, | |
| "learning_rate": 4.291488888871734e-06, | |
| "loss": 0.591, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9929478138222849, | |
| "grad_norm": 0.5676292405964318, | |
| "learning_rate": 4.245626907435755e-06, | |
| "loss": 0.5957, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9997179125528914, | |
| "eval_loss": 0.5937371253967285, | |
| "eval_runtime": 688.298, | |
| "eval_samples_per_second": 17.349, | |
| "eval_steps_per_second": 0.543, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.0155148095909732, | |
| "grad_norm": 0.6510043441238305, | |
| "learning_rate": 4.198595042234199e-06, | |
| "loss": 0.6093, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0380818053596614, | |
| "grad_norm": 0.6399485357865101, | |
| "learning_rate": 4.150425742513609e-06, | |
| "loss": 0.5388, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0606488011283497, | |
| "grad_norm": 0.6202997517009662, | |
| "learning_rate": 4.101152242284071e-06, | |
| "loss": 0.5538, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0832157968970382, | |
| "grad_norm": 0.596478907194731, | |
| "learning_rate": 4.050808537389682e-06, | |
| "loss": 0.5413, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1057827926657264, | |
| "grad_norm": 0.6688106585925544, | |
| "learning_rate": 3.999429362053397e-06, | |
| "loss": 0.5516, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1283497884344147, | |
| "grad_norm": 0.5514385320720825, | |
| "learning_rate": 3.947050164912446e-06, | |
| "loss": 0.5497, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.150916784203103, | |
| "grad_norm": 0.5764779109375965, | |
| "learning_rate": 3.893707084560831e-06, | |
| "loss": 0.5506, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1734837799717912, | |
| "grad_norm": 0.5687644731921871, | |
| "learning_rate": 3.839436924615808e-06, | |
| "loss": 0.5428, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.1960507757404795, | |
| "grad_norm": 0.6716035430024566, | |
| "learning_rate": 3.784277128325532e-06, | |
| "loss": 0.5485, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2186177715091677, | |
| "grad_norm": 0.7510569732848463, | |
| "learning_rate": 3.7282657527354014e-06, | |
| "loss": 0.5458, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2411847672778562, | |
| "grad_norm": 0.7205124677149223, | |
| "learning_rate": 3.671441442430908e-06, | |
| "loss": 0.5507, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2637517630465445, | |
| "grad_norm": 0.5847094902297382, | |
| "learning_rate": 3.6138434028751334e-06, | |
| "loss": 0.5521, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2863187588152327, | |
| "grad_norm": 0.569651078418994, | |
| "learning_rate": 3.555511373359255e-06, | |
| "loss": 0.549, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.308885754583921, | |
| "grad_norm": 0.6219046665446807, | |
| "learning_rate": 3.496485599584756e-06, | |
| "loss": 0.5489, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3314527503526092, | |
| "grad_norm": 0.5714415325332034, | |
| "learning_rate": 3.4368068058962357e-06, | |
| "loss": 0.5487, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.3540197461212977, | |
| "grad_norm": 1.1106035467973956, | |
| "learning_rate": 3.376516167183983e-06, | |
| "loss": 0.5542, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.376586741889986, | |
| "grad_norm": 0.5885941973302055, | |
| "learning_rate": 3.315655280475704e-06, | |
| "loss": 0.5459, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.3991537376586742, | |
| "grad_norm": 0.5908363560064332, | |
| "learning_rate": 3.2542661362369925e-06, | |
| "loss": 0.5502, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4217207334273625, | |
| "grad_norm": 0.5591849121824698, | |
| "learning_rate": 3.1923910894003598e-06, | |
| "loss": 0.5479, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4442877291960508, | |
| "grad_norm": 0.5602591930048809, | |
| "learning_rate": 3.1300728301427947e-06, | |
| "loss": 0.5471, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.466854724964739, | |
| "grad_norm": 0.5931164000131571, | |
| "learning_rate": 3.0673543544320354e-06, | |
| "loss": 0.5479, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.4894217207334273, | |
| "grad_norm": 0.6020148726486988, | |
| "learning_rate": 3.00427893436185e-06, | |
| "loss": 0.5515, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5119887165021155, | |
| "grad_norm": 0.5726305762841026, | |
| "learning_rate": 2.9408900882968174e-06, | |
| "loss": 0.5459, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5345557122708038, | |
| "grad_norm": 0.5629379890905293, | |
| "learning_rate": 2.8772315508471893e-06, | |
| "loss": 0.5402, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.5571227080394923, | |
| "grad_norm": 0.5704880969842114, | |
| "learning_rate": 2.8133472426945584e-06, | |
| "loss": 0.5417, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.5796897038081805, | |
| "grad_norm": 0.5710723412296994, | |
| "learning_rate": 2.749281240289151e-06, | |
| "loss": 0.546, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6022566995768688, | |
| "grad_norm": 0.5392466716099986, | |
| "learning_rate": 2.6850777454396342e-06, | |
| "loss": 0.5486, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6248236953455573, | |
| "grad_norm": 0.5812586258338217, | |
| "learning_rate": 2.620781054816457e-06, | |
| "loss": 0.5563, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6473906911142455, | |
| "grad_norm": 0.5716844996625347, | |
| "learning_rate": 2.5564355293897154e-06, | |
| "loss": 0.5393, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6699576868829338, | |
| "grad_norm": 0.753596906503236, | |
| "learning_rate": 2.49208556382268e-06, | |
| "loss": 0.5546, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.692524682651622, | |
| "grad_norm": 0.576809698814229, | |
| "learning_rate": 2.427775555842057e-06, | |
| "loss": 0.5461, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7150916784203103, | |
| "grad_norm": 0.5622230076695471, | |
| "learning_rate": 2.3635498756061458e-06, | |
| "loss": 0.5448, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7376586741889986, | |
| "grad_norm": 0.5168416840202211, | |
| "learning_rate": 2.299452835092016e-06, | |
| "loss": 0.545, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7602256699576868, | |
| "grad_norm": 0.5622613178078913, | |
| "learning_rate": 2.2355286575228257e-06, | |
| "loss": 0.5411, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.782792665726375, | |
| "grad_norm": 0.5430296403870848, | |
| "learning_rate": 2.1718214468563717e-06, | |
| "loss": 0.5441, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8053596614950633, | |
| "grad_norm": 0.5628381998512493, | |
| "learning_rate": 2.108375157355931e-06, | |
| "loss": 0.5388, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8279266572637518, | |
| "grad_norm": 0.5362604312102565, | |
| "learning_rate": 2.0452335632643795e-06, | |
| "loss": 0.5494, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.85049365303244, | |
| "grad_norm": 0.5154758412468956, | |
| "learning_rate": 1.9824402286025154e-06, | |
| "loss": 0.5363, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8730606488011283, | |
| "grad_norm": 0.5518765581430269, | |
| "learning_rate": 1.92003847711242e-06, | |
| "loss": 0.5481, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.8956276445698168, | |
| "grad_norm": 0.5312728956898368, | |
| "learning_rate": 1.8580713623666068e-06, | |
| "loss": 0.5483, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.918194640338505, | |
| "grad_norm": 0.5739522548168999, | |
| "learning_rate": 1.7965816380635584e-06, | |
| "loss": 0.5358, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9407616361071933, | |
| "grad_norm": 0.5414270420814203, | |
| "learning_rate": 1.7356117285301693e-06, | |
| "loss": 0.5409, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9633286318758816, | |
| "grad_norm": 0.5315261469742604, | |
| "learning_rate": 1.675203699451431e-06, | |
| "loss": 0.5475, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9858956276445698, | |
| "grad_norm": 0.5423045172744205, | |
| "learning_rate": 1.6153992288475608e-06, | |
| "loss": 0.5451, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.9994358251057829, | |
| "eval_loss": 0.5835120677947998, | |
| "eval_runtime": 684.5151, | |
| "eval_samples_per_second": 17.444, | |
| "eval_steps_per_second": 0.546, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 2.008462623413258, | |
| "grad_norm": 0.7539353987683947, | |
| "learning_rate": 1.556239578318598e-06, | |
| "loss": 0.5758, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0310296191819464, | |
| "grad_norm": 0.649378671530231, | |
| "learning_rate": 1.4977655645762997e-06, | |
| "loss": 0.4993, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0535966149506346, | |
| "grad_norm": 0.5877788518727063, | |
| "learning_rate": 1.4400175312829936e-06, | |
| "loss": 0.5018, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.076163610719323, | |
| "grad_norm": 0.5479736885278639, | |
| "learning_rate": 1.383035321216798e-06, | |
| "loss": 0.4941, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.098730606488011, | |
| "grad_norm": 0.560572864576164, | |
| "learning_rate": 1.3268582487824252e-06, | |
| "loss": 0.5008, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1212976022566994, | |
| "grad_norm": 0.544916918302148, | |
| "learning_rate": 1.2715250728865372e-06, | |
| "loss": 0.5045, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.143864598025388, | |
| "grad_norm": 0.5381551703507882, | |
| "learning_rate": 1.2170739701963579e-06, | |
| "loss": 0.5052, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1664315937940763, | |
| "grad_norm": 0.546851451490464, | |
| "learning_rate": 1.1635425087999944e-06, | |
| "loss": 0.5012, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.1889985895627646, | |
| "grad_norm": 0.553761979218256, | |
| "learning_rate": 1.1109676222866447e-06, | |
| "loss": 0.4979, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.211565585331453, | |
| "grad_norm": 0.5140355615402071, | |
| "learning_rate": 1.0593855842645777e-06, | |
| "loss": 0.4922, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.234132581100141, | |
| "grad_norm": 0.5469356578333175, | |
| "learning_rate": 1.0088319833344533e-06, | |
| "loss": 0.4919, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2566995768688294, | |
| "grad_norm": 0.5770077265245278, | |
| "learning_rate": 9.593416985352631e-07, | |
| "loss": 0.5012, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.2792665726375176, | |
| "grad_norm": 0.5611649964055478, | |
| "learning_rate": 9.109488752798265e-07, | |
| "loss": 0.5067, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.301833568406206, | |
| "grad_norm": 0.544952831573923, | |
| "learning_rate": 8.636869017964417e-07, | |
| "loss": 0.5007, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.324400564174894, | |
| "grad_norm": 0.5789004985292946, | |
| "learning_rate": 8.175883860929587e-07, | |
| "loss": 0.5045, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3469675599435824, | |
| "grad_norm": 0.5276179958933169, | |
| "learning_rate": 7.726851334591511e-07, | |
| "loss": 0.5017, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.3695345557122707, | |
| "grad_norm": 0.5396380700970511, | |
| "learning_rate": 7.290081245229201e-07, | |
| "loss": 0.4989, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.392101551480959, | |
| "grad_norm": 0.5079546332537075, | |
| "learning_rate": 6.865874938754659e-07, | |
| "loss": 0.498, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.414668547249647, | |
| "grad_norm": 0.5372856734992372, | |
| "learning_rate": 6.454525092801745e-07, | |
| "loss": 0.4983, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4372355430183354, | |
| "grad_norm": 0.5433991054748281, | |
| "learning_rate": 6.056315514795699e-07, | |
| "loss": 0.5016, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.459802538787024, | |
| "grad_norm": 0.5113580868200133, | |
| "learning_rate": 5.671520946142526e-07, | |
| "loss": 0.4997, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.4823695345557124, | |
| "grad_norm": 0.5287422362758118, | |
| "learning_rate": 5.300406872673434e-07, | |
| "loss": 0.5022, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5049365303244007, | |
| "grad_norm": 0.5243252088737198, | |
| "learning_rate": 4.943229341475108e-07, | |
| "loss": 0.5054, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.527503526093089, | |
| "grad_norm": 0.5214904323076445, | |
| "learning_rate": 4.600234784232087e-07, | |
| "loss": 0.495, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.550070521861777, | |
| "grad_norm": 0.5270933929763095, | |
| "learning_rate": 4.2716598472033066e-07, | |
| "loss": 0.4999, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5726375176304654, | |
| "grad_norm": 0.5345621477399009, | |
| "learning_rate": 3.957731227949975e-07, | |
| "loss": 0.4982, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.5952045133991537, | |
| "grad_norm": 0.5205630847096079, | |
| "learning_rate": 3.6586655189274235e-07, | |
| "loss": 0.4986, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.617771509167842, | |
| "grad_norm": 0.5533684987412459, | |
| "learning_rate": 3.374669058048948e-07, | |
| "loss": 0.5019, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.64033850493653, | |
| "grad_norm": 0.5750216155975586, | |
| "learning_rate": 3.1059377863246947e-07, | |
| "loss": 0.4904, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.6629055007052185, | |
| "grad_norm": 0.5225421360510641, | |
| "learning_rate": 2.8526571126737587e-07, | |
| "loss": 0.5015, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.685472496473907, | |
| "grad_norm": 0.5182002723553231, | |
| "learning_rate": 2.615001786002833e-07, | |
| "loss": 0.502, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.7080394922425954, | |
| "grad_norm": 0.5335554786344534, | |
| "learning_rate": 2.3931357746396515e-07, | |
| "loss": 0.5001, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.7306064880112837, | |
| "grad_norm": 0.5298076499586926, | |
| "learning_rate": 2.1872121532043977e-07, | |
| "loss": 0.5009, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.753173483779972, | |
| "grad_norm": 0.521497332991374, | |
| "learning_rate": 1.9973729969971315e-07, | |
| "loss": 0.4973, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.77574047954866, | |
| "grad_norm": 0.5199026307611461, | |
| "learning_rate": 1.823749283974119e-07, | |
| "loss": 0.5041, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.7983074753173485, | |
| "grad_norm": 0.5141813761312602, | |
| "learning_rate": 1.6664608043806614e-07, | |
| "loss": 0.5023, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8208744710860367, | |
| "grad_norm": 0.513473611989643, | |
| "learning_rate": 1.5256160781028118e-07, | |
| "loss": 0.5021, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.843441466854725, | |
| "grad_norm": 0.5144086219492163, | |
| "learning_rate": 1.401312279794984e-07, | |
| "loss": 0.5036, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8660084626234132, | |
| "grad_norm": 0.507879807961254, | |
| "learning_rate": 1.2936351718350923e-07, | |
| "loss": 0.5009, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.8885754583921015, | |
| "grad_norm": 0.5056596630306435, | |
| "learning_rate": 1.202659045153513e-07, | |
| "loss": 0.4983, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9111424541607898, | |
| "grad_norm": 0.5186469070972282, | |
| "learning_rate": 1.1284466679766762e-07, | |
| "loss": 0.5021, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.933709449929478, | |
| "grad_norm": 0.5191667761810439, | |
| "learning_rate": 1.0710492425206354e-07, | |
| "loss": 0.4973, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9562764456981663, | |
| "grad_norm": 0.5453516596097608, | |
| "learning_rate": 1.0305063696645283e-07, | |
| "loss": 0.5012, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.9788434414668545, | |
| "grad_norm": 0.5160351097067257, | |
| "learning_rate": 1.006846021628281e-07, | |
| "loss": 0.4967, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.9991537376586743, | |
| "eval_loss": 0.5900959968566895, | |
| "eval_runtime": 688.3543, | |
| "eval_samples_per_second": 17.347, | |
| "eval_steps_per_second": 0.543, | |
| "step": 1329 | |
| }, | |
| { | |
| "epoch": 2.9991537376586743, | |
| "step": 1329, | |
| "total_flos": 5064195066298368.0, | |
| "train_loss": 0.55943138999451, | |
| "train_runtime": 121397.9839, | |
| "train_samples_per_second": 5.606, | |
| "train_steps_per_second": 0.011 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1329, | |
| "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": 5064195066298368.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |