| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9999832990964811, | |
| "eval_steps": 500, | |
| "global_step": 29938, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001670090351888037, | |
| "grad_norm": 7.16015625, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 0.6304, | |
| "mean_token_accuracy": 0.811416609287262, | |
| "num_tokens": 150666.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003340180703776074, | |
| "grad_norm": 5.58984375, | |
| "learning_rate": 1.999986736222114e-05, | |
| "loss": 0.4501, | |
| "mean_token_accuracy": 0.8562266689538955, | |
| "num_tokens": 307563.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0050102710556641115, | |
| "grad_norm": 5.0859375, | |
| "learning_rate": 1.9999458569756985e-05, | |
| "loss": 0.5118, | |
| "mean_token_accuracy": 0.838346039056778, | |
| "num_tokens": 454754.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006680361407552148, | |
| "grad_norm": 4.37890625, | |
| "learning_rate": 1.9998773578656093e-05, | |
| "loss": 0.5075, | |
| "mean_token_accuracy": 0.8403138118982315, | |
| "num_tokens": 604733.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.008350451759440186, | |
| "grad_norm": 4.40234375, | |
| "learning_rate": 1.999781240783885e-05, | |
| "loss": 0.5057, | |
| "mean_token_accuracy": 0.8395608925819397, | |
| "num_tokens": 751094.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.010020542111328223, | |
| "grad_norm": 4.26953125, | |
| "learning_rate": 1.9996575083854096e-05, | |
| "loss": 0.5063, | |
| "mean_token_accuracy": 0.8390217781066894, | |
| "num_tokens": 906188.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01169063246321626, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.9995061640878407e-05, | |
| "loss": 0.5076, | |
| "mean_token_accuracy": 0.8388406819105149, | |
| "num_tokens": 1058839.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.013360722815104297, | |
| "grad_norm": 4.41015625, | |
| "learning_rate": 1.9993272120715135e-05, | |
| "loss": 0.5248, | |
| "mean_token_accuracy": 0.83592469394207, | |
| "num_tokens": 1210117.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.015030813166992334, | |
| "grad_norm": 4.4921875, | |
| "learning_rate": 1.9991206572793253e-05, | |
| "loss": 0.5103, | |
| "mean_token_accuracy": 0.8381919747591019, | |
| "num_tokens": 1365295.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.016700903518880372, | |
| "grad_norm": 4.69921875, | |
| "learning_rate": 1.998886505416601e-05, | |
| "loss": 0.5177, | |
| "mean_token_accuracy": 0.838459021449089, | |
| "num_tokens": 1519295.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.018370993870768407, | |
| "grad_norm": 4.6484375, | |
| "learning_rate": 1.9986247629509327e-05, | |
| "loss": 0.5784, | |
| "mean_token_accuracy": 0.8219448757171631, | |
| "num_tokens": 1670026.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.020041084222656446, | |
| "grad_norm": 4.25, | |
| "learning_rate": 1.9983354371120035e-05, | |
| "loss": 0.7304, | |
| "mean_token_accuracy": 0.7821861469745636, | |
| "num_tokens": 1830249.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02171117457454448, | |
| "grad_norm": 3.994140625, | |
| "learning_rate": 1.998018535891386e-05, | |
| "loss": 0.7442, | |
| "mean_token_accuracy": 0.7787324601411819, | |
| "num_tokens": 1981040.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.02338126492643252, | |
| "grad_norm": 3.548828125, | |
| "learning_rate": 1.9976740680423227e-05, | |
| "loss": 0.7469, | |
| "mean_token_accuracy": 0.7790761750936508, | |
| "num_tokens": 2133645.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02505135527832056, | |
| "grad_norm": 3.595703125, | |
| "learning_rate": 1.997302043079484e-05, | |
| "loss": 0.7073, | |
| "mean_token_accuracy": 0.7876522129774094, | |
| "num_tokens": 2286147.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.026721445630208594, | |
| "grad_norm": 3.787109375, | |
| "learning_rate": 1.9969024712787045e-05, | |
| "loss": 0.7117, | |
| "mean_token_accuracy": 0.7861441165208817, | |
| "num_tokens": 2435302.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.028391535982096632, | |
| "grad_norm": 4.07421875, | |
| "learning_rate": 1.996475363676701e-05, | |
| "loss": 0.7301, | |
| "mean_token_accuracy": 0.7839706349372864, | |
| "num_tokens": 2586271.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.030061626333984667, | |
| "grad_norm": 4.15234375, | |
| "learning_rate": 1.9960207320707655e-05, | |
| "loss": 0.7237, | |
| "mean_token_accuracy": 0.7836953294277191, | |
| "num_tokens": 2736739.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.031731716685872706, | |
| "grad_norm": 4.83984375, | |
| "learning_rate": 1.9955385890184415e-05, | |
| "loss": 0.7354, | |
| "mean_token_accuracy": 0.7828176522254944, | |
| "num_tokens": 2882560.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.033401807037760745, | |
| "grad_norm": 3.923828125, | |
| "learning_rate": 1.995028947837175e-05, | |
| "loss": 0.7236, | |
| "mean_token_accuracy": 0.7848378765583038, | |
| "num_tokens": 3043075.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03507189738964878, | |
| "grad_norm": 3.59375, | |
| "learning_rate": 1.994491822603948e-05, | |
| "loss": 0.7182, | |
| "mean_token_accuracy": 0.7871662402153015, | |
| "num_tokens": 3198694.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.036741987741536815, | |
| "grad_norm": 4.04296875, | |
| "learning_rate": 1.9939272281548897e-05, | |
| "loss": 0.7076, | |
| "mean_token_accuracy": 0.7869892084598541, | |
| "num_tokens": 3351166.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03841207809342485, | |
| "grad_norm": 4.29296875, | |
| "learning_rate": 1.9933351800848663e-05, | |
| "loss": 0.7079, | |
| "mean_token_accuracy": 0.7874267196655274, | |
| "num_tokens": 3497030.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.04008216844531289, | |
| "grad_norm": 3.650390625, | |
| "learning_rate": 1.99271569474705e-05, | |
| "loss": 0.6844, | |
| "mean_token_accuracy": 0.7945140707492828, | |
| "num_tokens": 3650753.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.04175225879720093, | |
| "grad_norm": 4.3515625, | |
| "learning_rate": 1.9920687892524676e-05, | |
| "loss": 0.714, | |
| "mean_token_accuracy": 0.7859313750267028, | |
| "num_tokens": 3803593.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.04342234914908896, | |
| "grad_norm": 3.603515625, | |
| "learning_rate": 1.9913944814695285e-05, | |
| "loss": 0.6818, | |
| "mean_token_accuracy": 0.7935056626796723, | |
| "num_tokens": 3954344.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.045092439500977, | |
| "grad_norm": 3.8828125, | |
| "learning_rate": 1.99069279002353e-05, | |
| "loss": 0.6986, | |
| "mean_token_accuracy": 0.7902963298559189, | |
| "num_tokens": 4109865.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.04676252985286504, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.9899637342961434e-05, | |
| "loss": 0.6922, | |
| "mean_token_accuracy": 0.7937425565719605, | |
| "num_tokens": 4258123.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.04843262020475308, | |
| "grad_norm": 4.23046875, | |
| "learning_rate": 1.9892073344248794e-05, | |
| "loss": 0.6954, | |
| "mean_token_accuracy": 0.7912928277254104, | |
| "num_tokens": 4404817.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.05010271055664112, | |
| "grad_norm": 3.623046875, | |
| "learning_rate": 1.98842361130253e-05, | |
| "loss": 0.6794, | |
| "mean_token_accuracy": 0.7929424160718918, | |
| "num_tokens": 4552500.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.05177280090852915, | |
| "grad_norm": 4.046875, | |
| "learning_rate": 1.987612586576593e-05, | |
| "loss": 0.7069, | |
| "mean_token_accuracy": 0.7885507994890213, | |
| "num_tokens": 4700529.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.05344289126041719, | |
| "grad_norm": 3.5078125, | |
| "learning_rate": 1.986774282648674e-05, | |
| "loss": 0.6928, | |
| "mean_token_accuracy": 0.7903753596544266, | |
| "num_tokens": 4854159.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.055112981612305226, | |
| "grad_norm": 3.23828125, | |
| "learning_rate": 1.9859087226738667e-05, | |
| "loss": 0.6862, | |
| "mean_token_accuracy": 0.7946210086345673, | |
| "num_tokens": 5004881.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.056783071964193264, | |
| "grad_norm": 3.8828125, | |
| "learning_rate": 1.9850159305601142e-05, | |
| "loss": 0.681, | |
| "mean_token_accuracy": 0.7951335823535919, | |
| "num_tokens": 5155074.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.0584531623160813, | |
| "grad_norm": 3.435546875, | |
| "learning_rate": 1.984095930967548e-05, | |
| "loss": 0.6775, | |
| "mean_token_accuracy": 0.7948978447914123, | |
| "num_tokens": 5305327.0, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.060123252667969335, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 1.983148749307807e-05, | |
| "loss": 0.6815, | |
| "mean_token_accuracy": 0.7944793283939362, | |
| "num_tokens": 5453165.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.06179334301985737, | |
| "grad_norm": 3.498046875, | |
| "learning_rate": 1.9821744117433367e-05, | |
| "loss": 0.6737, | |
| "mean_token_accuracy": 0.7980403685569764, | |
| "num_tokens": 5605423.0, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.06346343337174541, | |
| "grad_norm": 4.46484375, | |
| "learning_rate": 1.9811729451866647e-05, | |
| "loss": 0.6914, | |
| "mean_token_accuracy": 0.7934044080972672, | |
| "num_tokens": 5751905.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.06513352372363344, | |
| "grad_norm": 3.724609375, | |
| "learning_rate": 1.980144377299658e-05, | |
| "loss": 0.6879, | |
| "mean_token_accuracy": 0.7944984430074692, | |
| "num_tokens": 5900554.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.06680361407552149, | |
| "grad_norm": 3.11328125, | |
| "learning_rate": 1.9790887364927603e-05, | |
| "loss": 0.6887, | |
| "mean_token_accuracy": 0.7929914563894271, | |
| "num_tokens": 6057264.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.06847370442740952, | |
| "grad_norm": 3.974609375, | |
| "learning_rate": 1.9780060519242047e-05, | |
| "loss": 0.6795, | |
| "mean_token_accuracy": 0.7947278439998626, | |
| "num_tokens": 6207563.0, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.07014379477929757, | |
| "grad_norm": 3.337890625, | |
| "learning_rate": 1.9768963534992114e-05, | |
| "loss": 0.695, | |
| "mean_token_accuracy": 0.7921637284755707, | |
| "num_tokens": 6362024.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.0718138851311856, | |
| "grad_norm": 4.35546875, | |
| "learning_rate": 1.975759671869159e-05, | |
| "loss": 0.6813, | |
| "mean_token_accuracy": 0.7945687365531922, | |
| "num_tokens": 6511612.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.07348397548307363, | |
| "grad_norm": 3.443359375, | |
| "learning_rate": 1.9745960384307384e-05, | |
| "loss": 0.6664, | |
| "mean_token_accuracy": 0.7972371423244476, | |
| "num_tokens": 6664163.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.07515406583496168, | |
| "grad_norm": 3.927734375, | |
| "learning_rate": 1.9734054853250876e-05, | |
| "loss": 0.6745, | |
| "mean_token_accuracy": 0.7965255242586136, | |
| "num_tokens": 6818983.0, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.0768241561868497, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 1.9721880454369012e-05, | |
| "loss": 0.6775, | |
| "mean_token_accuracy": 0.7949534428119659, | |
| "num_tokens": 6969178.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.07849424653873775, | |
| "grad_norm": 3.94140625, | |
| "learning_rate": 1.9709437523935234e-05, | |
| "loss": 0.6933, | |
| "mean_token_accuracy": 0.7906970298290252, | |
| "num_tokens": 7120862.0, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.08016433689062578, | |
| "grad_norm": 4.1484375, | |
| "learning_rate": 1.9696726405640194e-05, | |
| "loss": 0.6678, | |
| "mean_token_accuracy": 0.7977210181951523, | |
| "num_tokens": 7273755.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.08183442724251382, | |
| "grad_norm": 3.671875, | |
| "learning_rate": 1.9683747450582257e-05, | |
| "loss": 0.7022, | |
| "mean_token_accuracy": 0.7893240767717361, | |
| "num_tokens": 7423742.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.08350451759440186, | |
| "grad_norm": 3.5078125, | |
| "learning_rate": 1.9670501017257805e-05, | |
| "loss": 0.6847, | |
| "mean_token_accuracy": 0.7929366368055344, | |
| "num_tokens": 7574222.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.0851746079462899, | |
| "grad_norm": 3.384765625, | |
| "learning_rate": 1.965698747155133e-05, | |
| "loss": 0.6571, | |
| "mean_token_accuracy": 0.7997360718250275, | |
| "num_tokens": 7730085.0, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.08684469829817792, | |
| "grad_norm": 3.466796875, | |
| "learning_rate": 1.9643207186725324e-05, | |
| "loss": 0.6672, | |
| "mean_token_accuracy": 0.7982296937704086, | |
| "num_tokens": 7881768.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.08851478865006597, | |
| "grad_norm": 3.521484375, | |
| "learning_rate": 1.962916054340999e-05, | |
| "loss": 0.685, | |
| "mean_token_accuracy": 0.7952978044748307, | |
| "num_tokens": 8027897.0, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.090184879001954, | |
| "grad_norm": 3.79296875, | |
| "learning_rate": 1.961484792959271e-05, | |
| "loss": 0.6778, | |
| "mean_token_accuracy": 0.7966848593950272, | |
| "num_tokens": 8175954.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.09185496935384205, | |
| "grad_norm": 3.40234375, | |
| "learning_rate": 1.9600269740607328e-05, | |
| "loss": 0.6488, | |
| "mean_token_accuracy": 0.8027435272932053, | |
| "num_tokens": 8332915.0, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.09352505970573008, | |
| "grad_norm": 3.408203125, | |
| "learning_rate": 1.958542637912324e-05, | |
| "loss": 0.673, | |
| "mean_token_accuracy": 0.7967682188749313, | |
| "num_tokens": 8485109.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.09519515005761811, | |
| "grad_norm": 3.244140625, | |
| "learning_rate": 1.9570318255134263e-05, | |
| "loss": 0.6544, | |
| "mean_token_accuracy": 0.7994941908121109, | |
| "num_tokens": 8638846.0, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.09686524040950616, | |
| "grad_norm": 3.62109375, | |
| "learning_rate": 1.9554945785947314e-05, | |
| "loss": 0.67, | |
| "mean_token_accuracy": 0.7985292530059814, | |
| "num_tokens": 8788759.0, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.09853533076139419, | |
| "grad_norm": 3.466796875, | |
| "learning_rate": 1.953930939617089e-05, | |
| "loss": 0.6722, | |
| "mean_token_accuracy": 0.7943358135223388, | |
| "num_tokens": 8941895.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.10020542111328223, | |
| "grad_norm": 3.6796875, | |
| "learning_rate": 1.952340951770333e-05, | |
| "loss": 0.6488, | |
| "mean_token_accuracy": 0.8029305410385131, | |
| "num_tokens": 9093399.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.10187551146517027, | |
| "grad_norm": 3.673828125, | |
| "learning_rate": 1.9507246589720887e-05, | |
| "loss": 0.6591, | |
| "mean_token_accuracy": 0.7998628175258636, | |
| "num_tokens": 9246318.0, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.1035456018170583, | |
| "grad_norm": 3.796875, | |
| "learning_rate": 1.9490821058665597e-05, | |
| "loss": 0.6842, | |
| "mean_token_accuracy": 0.7952588319778442, | |
| "num_tokens": 9393063.0, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.10521569216894634, | |
| "grad_norm": 3.64453125, | |
| "learning_rate": 1.9474133378232955e-05, | |
| "loss": 0.6627, | |
| "mean_token_accuracy": 0.7986302423477173, | |
| "num_tokens": 9546557.0, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.10688578252083437, | |
| "grad_norm": 3.662109375, | |
| "learning_rate": 1.945718400935938e-05, | |
| "loss": 0.6564, | |
| "mean_token_accuracy": 0.8012412291765213, | |
| "num_tokens": 9698417.0, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.10855587287272242, | |
| "grad_norm": 3.21484375, | |
| "learning_rate": 1.9439973420209467e-05, | |
| "loss": 0.67, | |
| "mean_token_accuracy": 0.7971057319641113, | |
| "num_tokens": 9846015.0, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.11022596322461045, | |
| "grad_norm": 3.294921875, | |
| "learning_rate": 1.9422502086163093e-05, | |
| "loss": 0.6672, | |
| "mean_token_accuracy": 0.797788228392601, | |
| "num_tokens": 10001053.0, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.11189605357649848, | |
| "grad_norm": 3.607421875, | |
| "learning_rate": 1.9404770489802242e-05, | |
| "loss": 0.6529, | |
| "mean_token_accuracy": 0.7996513998508453, | |
| "num_tokens": 10151845.0, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.11356614392838653, | |
| "grad_norm": 3.240234375, | |
| "learning_rate": 1.9386779120897712e-05, | |
| "loss": 0.6268, | |
| "mean_token_accuracy": 0.8078747218847275, | |
| "num_tokens": 10303872.0, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.11523623428027456, | |
| "grad_norm": 3.38671875, | |
| "learning_rate": 1.936852847639556e-05, | |
| "loss": 0.6608, | |
| "mean_token_accuracy": 0.8000670689344406, | |
| "num_tokens": 10456152.0, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.1169063246321626, | |
| "grad_norm": 3.337890625, | |
| "learning_rate": 1.9350019060403398e-05, | |
| "loss": 0.6469, | |
| "mean_token_accuracy": 0.8042119026184082, | |
| "num_tokens": 10605108.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.11857641498405064, | |
| "grad_norm": 3.521484375, | |
| "learning_rate": 1.933125138417645e-05, | |
| "loss": 0.6506, | |
| "mean_token_accuracy": 0.8032512718439102, | |
| "num_tokens": 10749490.0, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.12024650533593867, | |
| "grad_norm": 3.251953125, | |
| "learning_rate": 1.9312225966103445e-05, | |
| "loss": 0.6753, | |
| "mean_token_accuracy": 0.7979339599609375, | |
| "num_tokens": 10899284.0, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.12191659568782671, | |
| "grad_norm": 3.548828125, | |
| "learning_rate": 1.9292943331692285e-05, | |
| "loss": 0.6663, | |
| "mean_token_accuracy": 0.7995783388614655, | |
| "num_tokens": 11046487.0, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.12358668603971475, | |
| "grad_norm": 3.27734375, | |
| "learning_rate": 1.9273404013555544e-05, | |
| "loss": 0.6481, | |
| "mean_token_accuracy": 0.8006290888786316, | |
| "num_tokens": 11197224.0, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.1252567763916028, | |
| "grad_norm": 3.7109375, | |
| "learning_rate": 1.9253608551395745e-05, | |
| "loss": 0.6645, | |
| "mean_token_accuracy": 0.7999362868070602, | |
| "num_tokens": 11349738.0, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.12692686674349082, | |
| "grad_norm": 4.05078125, | |
| "learning_rate": 1.923355749199046e-05, | |
| "loss": 0.644, | |
| "mean_token_accuracy": 0.8039193218946457, | |
| "num_tokens": 11501057.0, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.12859695709537886, | |
| "grad_norm": 3.26171875, | |
| "learning_rate": 1.92132513891772e-05, | |
| "loss": 0.6398, | |
| "mean_token_accuracy": 0.8046829622983932, | |
| "num_tokens": 11656329.0, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.1302670474472669, | |
| "grad_norm": 3.41796875, | |
| "learning_rate": 1.919269080383813e-05, | |
| "loss": 0.6595, | |
| "mean_token_accuracy": 0.7993488019704819, | |
| "num_tokens": 11800257.0, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.13193713779915495, | |
| "grad_norm": 3.822265625, | |
| "learning_rate": 1.9171876303884555e-05, | |
| "loss": 0.6533, | |
| "mean_token_accuracy": 0.8011213219165803, | |
| "num_tokens": 11952176.0, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.13360722815104298, | |
| "grad_norm": 3.0859375, | |
| "learning_rate": 1.9150808464241257e-05, | |
| "loss": 0.6443, | |
| "mean_token_accuracy": 0.8050255984067917, | |
| "num_tokens": 12103443.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.135277318502931, | |
| "grad_norm": 3.5078125, | |
| "learning_rate": 1.9129487866830602e-05, | |
| "loss": 0.6533, | |
| "mean_token_accuracy": 0.8013356167078018, | |
| "num_tokens": 12254997.0, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.13694740885481904, | |
| "grad_norm": 3.30078125, | |
| "learning_rate": 1.9107915100556473e-05, | |
| "loss": 0.6532, | |
| "mean_token_accuracy": 0.8014611840248108, | |
| "num_tokens": 12408985.0, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.13861749920670707, | |
| "grad_norm": 3.14453125, | |
| "learning_rate": 1.908609076128799e-05, | |
| "loss": 0.6575, | |
| "mean_token_accuracy": 0.8021772617101669, | |
| "num_tokens": 12559124.0, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.14028758955859513, | |
| "grad_norm": 3.515625, | |
| "learning_rate": 1.906401545184307e-05, | |
| "loss": 0.6475, | |
| "mean_token_accuracy": 0.8028253322839737, | |
| "num_tokens": 12707796.0, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.14195767991048316, | |
| "grad_norm": 3.646484375, | |
| "learning_rate": 1.9041689781971765e-05, | |
| "loss": 0.6506, | |
| "mean_token_accuracy": 0.8031806921958924, | |
| "num_tokens": 12858676.0, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.1436277702623712, | |
| "grad_norm": 4.37109375, | |
| "learning_rate": 1.901911436833942e-05, | |
| "loss": 0.6558, | |
| "mean_token_accuracy": 0.8009441828727722, | |
| "num_tokens": 13007021.0, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.14529786061425923, | |
| "grad_norm": 3.494140625, | |
| "learning_rate": 1.899628983450964e-05, | |
| "loss": 0.629, | |
| "mean_token_accuracy": 0.8062937146425248, | |
| "num_tokens": 13155780.0, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.14696795096614726, | |
| "grad_norm": 2.982421875, | |
| "learning_rate": 1.8973216810927077e-05, | |
| "loss": 0.6461, | |
| "mean_token_accuracy": 0.8051383906602859, | |
| "num_tokens": 13302653.0, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.14863804131803532, | |
| "grad_norm": 3.529296875, | |
| "learning_rate": 1.89498959349e-05, | |
| "loss": 0.6367, | |
| "mean_token_accuracy": 0.805459765791893, | |
| "num_tokens": 13455088.0, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.15030813166992335, | |
| "grad_norm": 3.228515625, | |
| "learning_rate": 1.8926327850582706e-05, | |
| "loss": 0.6288, | |
| "mean_token_accuracy": 0.8068876641988755, | |
| "num_tokens": 13609983.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.15197822202181138, | |
| "grad_norm": 3.72265625, | |
| "learning_rate": 1.8902513208957712e-05, | |
| "loss": 0.6521, | |
| "mean_token_accuracy": 0.8004961597919464, | |
| "num_tokens": 13759536.0, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.1536483123736994, | |
| "grad_norm": 3.83203125, | |
| "learning_rate": 1.8878452667817785e-05, | |
| "loss": 0.6314, | |
| "mean_token_accuracy": 0.8060730373859406, | |
| "num_tokens": 13914544.0, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.15531840272558745, | |
| "grad_norm": 3.88671875, | |
| "learning_rate": 1.8854146891747788e-05, | |
| "loss": 0.6397, | |
| "mean_token_accuracy": 0.805094587802887, | |
| "num_tokens": 14064759.0, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.1569884930774755, | |
| "grad_norm": 3.373046875, | |
| "learning_rate": 1.8829596552106276e-05, | |
| "loss": 0.6477, | |
| "mean_token_accuracy": 0.8041272169351578, | |
| "num_tokens": 14213937.0, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.15865858342936354, | |
| "grad_norm": 3.1484375, | |
| "learning_rate": 1.8804802327007005e-05, | |
| "loss": 0.63, | |
| "mean_token_accuracy": 0.8083387905359268, | |
| "num_tokens": 14363168.0, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.16032867378125157, | |
| "grad_norm": 3.6328125, | |
| "learning_rate": 1.8779764901300174e-05, | |
| "loss": 0.633, | |
| "mean_token_accuracy": 0.8068809920549392, | |
| "num_tokens": 14511952.0, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.1619987641331396, | |
| "grad_norm": 3.693359375, | |
| "learning_rate": 1.875448496655351e-05, | |
| "loss": 0.6529, | |
| "mean_token_accuracy": 0.8010576856136322, | |
| "num_tokens": 14659521.0, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.16366885448502763, | |
| "grad_norm": 3.970703125, | |
| "learning_rate": 1.8728963221033168e-05, | |
| "loss": 0.6299, | |
| "mean_token_accuracy": 0.8058782732486724, | |
| "num_tokens": 14812856.0, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.16533894483691566, | |
| "grad_norm": 3.056640625, | |
| "learning_rate": 1.870320036968445e-05, | |
| "loss": 0.6102, | |
| "mean_token_accuracy": 0.8117638313770295, | |
| "num_tokens": 14968517.0, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.16700903518880372, | |
| "grad_norm": 3.572265625, | |
| "learning_rate": 1.867719712411233e-05, | |
| "loss": 0.6454, | |
| "mean_token_accuracy": 0.8036060810089112, | |
| "num_tokens": 15120586.0, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.16867912554069175, | |
| "grad_norm": 3.0390625, | |
| "learning_rate": 1.8650954202561786e-05, | |
| "loss": 0.6341, | |
| "mean_token_accuracy": 0.8054838758707047, | |
| "num_tokens": 15272994.0, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.1703492158925798, | |
| "grad_norm": 2.947265625, | |
| "learning_rate": 1.8624472329897985e-05, | |
| "loss": 0.6328, | |
| "mean_token_accuracy": 0.8070685297250748, | |
| "num_tokens": 15423469.0, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.17201930624446782, | |
| "grad_norm": 3.240234375, | |
| "learning_rate": 1.8597752237586242e-05, | |
| "loss": 0.6228, | |
| "mean_token_accuracy": 0.809105772972107, | |
| "num_tokens": 15568404.0, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.17368939659635585, | |
| "grad_norm": 3.26171875, | |
| "learning_rate": 1.8570794663671824e-05, | |
| "loss": 0.6128, | |
| "mean_token_accuracy": 0.811137170791626, | |
| "num_tokens": 15721906.0, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.1753594869482439, | |
| "grad_norm": 3.345703125, | |
| "learning_rate": 1.8543600352759563e-05, | |
| "loss": 0.6207, | |
| "mean_token_accuracy": 0.8088931626081467, | |
| "num_tokens": 15867611.0, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.17702957730013194, | |
| "grad_norm": 3.76171875, | |
| "learning_rate": 1.851617005599329e-05, | |
| "loss": 0.6198, | |
| "mean_token_accuracy": 0.810358560681343, | |
| "num_tokens": 16017301.0, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.17869966765201997, | |
| "grad_norm": 3.484375, | |
| "learning_rate": 1.8488504531035084e-05, | |
| "loss": 0.6354, | |
| "mean_token_accuracy": 0.806412605047226, | |
| "num_tokens": 16174153.0, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.180369758003908, | |
| "grad_norm": 3.6015625, | |
| "learning_rate": 1.8460604542044344e-05, | |
| "loss": 0.6206, | |
| "mean_token_accuracy": 0.809535750746727, | |
| "num_tokens": 16326166.0, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.18203984835579604, | |
| "grad_norm": 4.4765625, | |
| "learning_rate": 1.8432470859656687e-05, | |
| "loss": 0.6399, | |
| "mean_token_accuracy": 0.8042701333761215, | |
| "num_tokens": 16476025.0, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.1837099387076841, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 1.8404104260962662e-05, | |
| "loss": 0.6148, | |
| "mean_token_accuracy": 0.811469207406044, | |
| "num_tokens": 16622887.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.18538002905957213, | |
| "grad_norm": 3.763671875, | |
| "learning_rate": 1.8375505529486283e-05, | |
| "loss": 0.6266, | |
| "mean_token_accuracy": 0.8079740327596664, | |
| "num_tokens": 16772669.0, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.18705011941146016, | |
| "grad_norm": 3.28515625, | |
| "learning_rate": 1.8346675455163376e-05, | |
| "loss": 0.6151, | |
| "mean_token_accuracy": 0.8107228165864945, | |
| "num_tokens": 16920269.0, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.1887202097633482, | |
| "grad_norm": 4.6015625, | |
| "learning_rate": 1.8317614834319783e-05, | |
| "loss": 0.6321, | |
| "mean_token_accuracy": 0.8072718501091003, | |
| "num_tokens": 17067401.0, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.19039030011523622, | |
| "grad_norm": 4.953125, | |
| "learning_rate": 1.828832446964935e-05, | |
| "loss": 0.635, | |
| "mean_token_accuracy": 0.8083576399087906, | |
| "num_tokens": 17210399.0, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.19206039046712428, | |
| "grad_norm": 3.9453125, | |
| "learning_rate": 1.825880517019176e-05, | |
| "loss": 0.6101, | |
| "mean_token_accuracy": 0.8119984632730484, | |
| "num_tokens": 17355215.0, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.1937304808190123, | |
| "grad_norm": 3.5390625, | |
| "learning_rate": 1.8229057751310188e-05, | |
| "loss": 0.6179, | |
| "mean_token_accuracy": 0.8104551881551743, | |
| "num_tokens": 17501111.0, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.19540057117090034, | |
| "grad_norm": 3.25, | |
| "learning_rate": 1.8199083034668774e-05, | |
| "loss": 0.6245, | |
| "mean_token_accuracy": 0.8110457295179367, | |
| "num_tokens": 17655096.0, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.19707066152278838, | |
| "grad_norm": 3.59375, | |
| "learning_rate": 1.816888184820993e-05, | |
| "loss": 0.6302, | |
| "mean_token_accuracy": 0.8070375627279281, | |
| "num_tokens": 17809403.0, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.1987407518746764, | |
| "grad_norm": 3.259765625, | |
| "learning_rate": 1.8138455026131477e-05, | |
| "loss": 0.6078, | |
| "mean_token_accuracy": 0.8126195806264878, | |
| "num_tokens": 17959815.0, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.20041084222656447, | |
| "grad_norm": 3.291015625, | |
| "learning_rate": 1.81078034088636e-05, | |
| "loss": 0.6, | |
| "mean_token_accuracy": 0.8153526914119721, | |
| "num_tokens": 18112482.0, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.2020809325784525, | |
| "grad_norm": 3.619140625, | |
| "learning_rate": 1.807692784304562e-05, | |
| "loss": 0.6088, | |
| "mean_token_accuracy": 0.8110599368810654, | |
| "num_tokens": 18269537.0, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.20375102293034053, | |
| "grad_norm": 3.349609375, | |
| "learning_rate": 1.8045829181502642e-05, | |
| "loss": 0.62, | |
| "mean_token_accuracy": 0.8105544656515121, | |
| "num_tokens": 18418714.0, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.20542111328222856, | |
| "grad_norm": 3.341796875, | |
| "learning_rate": 1.8014508283221953e-05, | |
| "loss": 0.6249, | |
| "mean_token_accuracy": 0.807090380191803, | |
| "num_tokens": 18577084.0, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.2070912036341166, | |
| "grad_norm": 3.5546875, | |
| "learning_rate": 1.798296601332935e-05, | |
| "loss": 0.6166, | |
| "mean_token_accuracy": 0.8106195080280304, | |
| "num_tokens": 18723440.0, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.20876129398600465, | |
| "grad_norm": 3.4921875, | |
| "learning_rate": 1.7951203243065184e-05, | |
| "loss": 0.6169, | |
| "mean_token_accuracy": 0.8116037601232529, | |
| "num_tokens": 18870030.0, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.21043138433789269, | |
| "grad_norm": 3.80859375, | |
| "learning_rate": 1.7919220849760347e-05, | |
| "loss": 0.6093, | |
| "mean_token_accuracy": 0.8129760199785232, | |
| "num_tokens": 19020540.0, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.21210147468978072, | |
| "grad_norm": 3.212890625, | |
| "learning_rate": 1.7887019716812015e-05, | |
| "loss": 0.6202, | |
| "mean_token_accuracy": 0.8104865264892578, | |
| "num_tokens": 19171916.0, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 0.21377156504166875, | |
| "grad_norm": 3.998046875, | |
| "learning_rate": 1.785460073365924e-05, | |
| "loss": 0.6243, | |
| "mean_token_accuracy": 0.810001392364502, | |
| "num_tokens": 19317653.0, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.21544165539355678, | |
| "grad_norm": 3.6015625, | |
| "learning_rate": 1.782196479575841e-05, | |
| "loss": 0.5972, | |
| "mean_token_accuracy": 0.815451757311821, | |
| "num_tokens": 19469488.0, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.21711174574544484, | |
| "grad_norm": 3.171875, | |
| "learning_rate": 1.778911280455848e-05, | |
| "loss": 0.6094, | |
| "mean_token_accuracy": 0.8127148807048797, | |
| "num_tokens": 19617524.0, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.21878183609733287, | |
| "grad_norm": 3.478515625, | |
| "learning_rate": 1.7756045667476095e-05, | |
| "loss": 0.6365, | |
| "mean_token_accuracy": 0.8052962213754654, | |
| "num_tokens": 19766937.0, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 0.2204519264492209, | |
| "grad_norm": 3.943359375, | |
| "learning_rate": 1.7722764297870534e-05, | |
| "loss": 0.6008, | |
| "mean_token_accuracy": 0.8136671632528305, | |
| "num_tokens": 19918307.0, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.22212201680110893, | |
| "grad_norm": 3.169921875, | |
| "learning_rate": 1.768926961501846e-05, | |
| "loss": 0.6066, | |
| "mean_token_accuracy": 0.8141713869571686, | |
| "num_tokens": 20066541.0, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 0.22379210715299697, | |
| "grad_norm": 3.19921875, | |
| "learning_rate": 1.7655562544088534e-05, | |
| "loss": 0.6034, | |
| "mean_token_accuracy": 0.8118478727340698, | |
| "num_tokens": 20221668.0, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.22546219750488503, | |
| "grad_norm": 3.275390625, | |
| "learning_rate": 1.762164401611587e-05, | |
| "loss": 0.6189, | |
| "mean_token_accuracy": 0.8125155258178711, | |
| "num_tokens": 20368732.0, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.22713228785677306, | |
| "grad_norm": 3.462890625, | |
| "learning_rate": 1.7587514967976315e-05, | |
| "loss": 0.6095, | |
| "mean_token_accuracy": 0.8130715191364288, | |
| "num_tokens": 20519573.0, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.2288023782086611, | |
| "grad_norm": 3.05859375, | |
| "learning_rate": 1.7553176342360564e-05, | |
| "loss": 0.6381, | |
| "mean_token_accuracy": 0.8038551956415176, | |
| "num_tokens": 20668027.0, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 0.23047246856054912, | |
| "grad_norm": 3.392578125, | |
| "learning_rate": 1.7518629087748125e-05, | |
| "loss": 0.6147, | |
| "mean_token_accuracy": 0.8109205877780914, | |
| "num_tokens": 20815967.0, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.23214255891243715, | |
| "grad_norm": 3.642578125, | |
| "learning_rate": 1.7483874158381137e-05, | |
| "loss": 0.6093, | |
| "mean_token_accuracy": 0.812092969417572, | |
| "num_tokens": 20966880.0, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 0.2338126492643252, | |
| "grad_norm": 3.2578125, | |
| "learning_rate": 1.7448912514237976e-05, | |
| "loss": 0.5986, | |
| "mean_token_accuracy": 0.8138788425922394, | |
| "num_tokens": 21117408.0, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.23548273961621324, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 1.7413745121006777e-05, | |
| "loss": 0.6143, | |
| "mean_token_accuracy": 0.8106629079580308, | |
| "num_tokens": 21258290.0, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 0.23715282996810128, | |
| "grad_norm": 3.671875, | |
| "learning_rate": 1.737837295005874e-05, | |
| "loss": 0.6026, | |
| "mean_token_accuracy": 0.8134672123193741, | |
| "num_tokens": 21413317.0, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.2388229203199893, | |
| "grad_norm": 3.42578125, | |
| "learning_rate": 1.73427969784213e-05, | |
| "loss": 0.5989, | |
| "mean_token_accuracy": 0.81451107442379, | |
| "num_tokens": 21559517.0, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 0.24049301067187734, | |
| "grad_norm": 3.2890625, | |
| "learning_rate": 1.7307018188751153e-05, | |
| "loss": 0.6134, | |
| "mean_token_accuracy": 0.8111221677064896, | |
| "num_tokens": 21711355.0, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.2421631010237654, | |
| "grad_norm": 3.314453125, | |
| "learning_rate": 1.72710375693071e-05, | |
| "loss": 0.5866, | |
| "mean_token_accuracy": 0.8179266756772995, | |
| "num_tokens": 21863362.0, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 0.24383319137565343, | |
| "grad_norm": 3.07421875, | |
| "learning_rate": 1.723485611392275e-05, | |
| "loss": 0.5775, | |
| "mean_token_accuracy": 0.8185840421915054, | |
| "num_tokens": 22015880.0, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.24550328172754146, | |
| "grad_norm": 3.33203125, | |
| "learning_rate": 1.7198474821979075e-05, | |
| "loss": 0.6035, | |
| "mean_token_accuracy": 0.814561493396759, | |
| "num_tokens": 22164719.0, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 0.2471733720794295, | |
| "grad_norm": 3.439453125, | |
| "learning_rate": 1.7161894698376814e-05, | |
| "loss": 0.5944, | |
| "mean_token_accuracy": 0.8162802219390869, | |
| "num_tokens": 22316748.0, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.24884346243131752, | |
| "grad_norm": 3.787109375, | |
| "learning_rate": 1.7125116753508696e-05, | |
| "loss": 0.5999, | |
| "mean_token_accuracy": 0.8156676411628723, | |
| "num_tokens": 22466344.0, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 0.2505135527832056, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 1.708814200323155e-05, | |
| "loss": 0.5842, | |
| "mean_token_accuracy": 0.8202319222688675, | |
| "num_tokens": 22619286.0, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.2521836431350936, | |
| "grad_norm": 3.37890625, | |
| "learning_rate": 1.705097146883823e-05, | |
| "loss": 0.6108, | |
| "mean_token_accuracy": 0.8124721819162368, | |
| "num_tokens": 22769773.0, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 0.25385373348698165, | |
| "grad_norm": 3.431640625, | |
| "learning_rate": 1.7013606177029417e-05, | |
| "loss": 0.6097, | |
| "mean_token_accuracy": 0.812991201877594, | |
| "num_tokens": 22923130.0, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.2555238238388697, | |
| "grad_norm": 3.142578125, | |
| "learning_rate": 1.6976047159885258e-05, | |
| "loss": 0.5725, | |
| "mean_token_accuracy": 0.8219118654727936, | |
| "num_tokens": 23072994.0, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 0.2571939141907577, | |
| "grad_norm": 2.869140625, | |
| "learning_rate": 1.6938295454836855e-05, | |
| "loss": 0.5903, | |
| "mean_token_accuracy": 0.8173499464988708, | |
| "num_tokens": 23220605.0, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.25886400454264574, | |
| "grad_norm": 4.078125, | |
| "learning_rate": 1.6900352104637616e-05, | |
| "loss": 0.6188, | |
| "mean_token_accuracy": 0.8102790033817291, | |
| "num_tokens": 23370496.0, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 0.2605340948945338, | |
| "grad_norm": 3.7421875, | |
| "learning_rate": 1.686221815733444e-05, | |
| "loss": 0.6076, | |
| "mean_token_accuracy": 0.8124845671653748, | |
| "num_tokens": 23524575.0, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.2622041852464218, | |
| "grad_norm": 4.11328125, | |
| "learning_rate": 1.682389466623879e-05, | |
| "loss": 0.5937, | |
| "mean_token_accuracy": 0.8181423616409301, | |
| "num_tokens": 23673370.0, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 0.2638742755983099, | |
| "grad_norm": 3.591796875, | |
| "learning_rate": 1.678538268989757e-05, | |
| "loss": 0.5962, | |
| "mean_token_accuracy": 0.8151667928695678, | |
| "num_tokens": 23824567.0, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.2655443659501979, | |
| "grad_norm": 3.638671875, | |
| "learning_rate": 1.6746683292063913e-05, | |
| "loss": 0.595, | |
| "mean_token_accuracy": 0.816837123632431, | |
| "num_tokens": 23979656.0, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 0.26721445630208596, | |
| "grad_norm": 3.806640625, | |
| "learning_rate": 1.670779754166779e-05, | |
| "loss": 0.571, | |
| "mean_token_accuracy": 0.8221717000007629, | |
| "num_tokens": 24124997.0, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.268884546653974, | |
| "grad_norm": 4.38671875, | |
| "learning_rate": 1.666872651278648e-05, | |
| "loss": 0.5823, | |
| "mean_token_accuracy": 0.8184084331989289, | |
| "num_tokens": 24274928.0, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 0.270554637005862, | |
| "grad_norm": 3.314453125, | |
| "learning_rate": 1.66294712846149e-05, | |
| "loss": 0.5908, | |
| "mean_token_accuracy": 0.8170400822162628, | |
| "num_tokens": 24425253.0, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.27222472735775005, | |
| "grad_norm": 3.328125, | |
| "learning_rate": 1.6590032941435812e-05, | |
| "loss": 0.587, | |
| "mean_token_accuracy": 0.8180436098575592, | |
| "num_tokens": 24570789.0, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 0.2738948177096381, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 1.6550412572589857e-05, | |
| "loss": 0.5961, | |
| "mean_token_accuracy": 0.8165696883201599, | |
| "num_tokens": 24728204.0, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.2755649080615261, | |
| "grad_norm": 3.09375, | |
| "learning_rate": 1.6510611272445472e-05, | |
| "loss": 0.5883, | |
| "mean_token_accuracy": 0.8188752412796021, | |
| "num_tokens": 24884334.0, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 0.27723499841341415, | |
| "grad_norm": 3.611328125, | |
| "learning_rate": 1.6470630140368663e-05, | |
| "loss": 0.591, | |
| "mean_token_accuracy": 0.8173883992433548, | |
| "num_tokens": 25029094.0, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.2789050887653022, | |
| "grad_norm": 3.271484375, | |
| "learning_rate": 1.6430470280692644e-05, | |
| "loss": 0.5848, | |
| "mean_token_accuracy": 0.820589507818222, | |
| "num_tokens": 25177586.0, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 0.28057517911719027, | |
| "grad_norm": 3.2109375, | |
| "learning_rate": 1.639013280268732e-05, | |
| "loss": 0.5581, | |
| "mean_token_accuracy": 0.8250171238183975, | |
| "num_tokens": 25332667.0, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.2822452694690783, | |
| "grad_norm": 3.505859375, | |
| "learning_rate": 1.6349618820528662e-05, | |
| "loss": 0.5978, | |
| "mean_token_accuracy": 0.8156885832548142, | |
| "num_tokens": 25482520.0, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 0.28391535982096633, | |
| "grad_norm": 3.703125, | |
| "learning_rate": 1.6308929453267918e-05, | |
| "loss": 0.5633, | |
| "mean_token_accuracy": 0.8238223212957382, | |
| "num_tokens": 25639672.0, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.28558545017285436, | |
| "grad_norm": 3.390625, | |
| "learning_rate": 1.6268065824800723e-05, | |
| "loss": 0.5888, | |
| "mean_token_accuracy": 0.8175674903392792, | |
| "num_tokens": 25793282.0, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 0.2872555405247424, | |
| "grad_norm": 3.59375, | |
| "learning_rate": 1.622702906383603e-05, | |
| "loss": 0.579, | |
| "mean_token_accuracy": 0.8193080085515976, | |
| "num_tokens": 25946540.0, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.2889256308766304, | |
| "grad_norm": 3.0390625, | |
| "learning_rate": 1.6185820303864957e-05, | |
| "loss": 0.5738, | |
| "mean_token_accuracy": 0.8222082054615021, | |
| "num_tokens": 26105903.0, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 0.29059572122851846, | |
| "grad_norm": 3.185546875, | |
| "learning_rate": 1.614444068312946e-05, | |
| "loss": 0.595, | |
| "mean_token_accuracy": 0.8175247597694397, | |
| "num_tokens": 26254429.0, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.2922658115804065, | |
| "grad_norm": 2.779296875, | |
| "learning_rate": 1.610289134459091e-05, | |
| "loss": 0.5878, | |
| "mean_token_accuracy": 0.818896831870079, | |
| "num_tokens": 26410820.0, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 0.2939359019322945, | |
| "grad_norm": 3.423828125, | |
| "learning_rate": 1.606117343589851e-05, | |
| "loss": 0.5953, | |
| "mean_token_accuracy": 0.8172416472434998, | |
| "num_tokens": 26561505.0, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.29560599228418255, | |
| "grad_norm": 3.47265625, | |
| "learning_rate": 1.60192881093576e-05, | |
| "loss": 0.5691, | |
| "mean_token_accuracy": 0.8218266826868057, | |
| "num_tokens": 26714736.0, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 0.29727608263607064, | |
| "grad_norm": 3.501953125, | |
| "learning_rate": 1.5977236521897824e-05, | |
| "loss": 0.5887, | |
| "mean_token_accuracy": 0.8170481222867966, | |
| "num_tokens": 26864415.0, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.29894617298795867, | |
| "grad_norm": 3.005859375, | |
| "learning_rate": 1.593501983504119e-05, | |
| "loss": 0.556, | |
| "mean_token_accuracy": 0.8250821077823639, | |
| "num_tokens": 27012496.0, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 0.3006162633398467, | |
| "grad_norm": 3.279296875, | |
| "learning_rate": 1.589263921486997e-05, | |
| "loss": 0.596, | |
| "mean_token_accuracy": 0.8154706001281739, | |
| "num_tokens": 27165174.0, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.30228635369173473, | |
| "grad_norm": 4.0078125, | |
| "learning_rate": 1.5850095831994486e-05, | |
| "loss": 0.5945, | |
| "mean_token_accuracy": 0.8172478175163269, | |
| "num_tokens": 27322736.0, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 0.30395644404362276, | |
| "grad_norm": 3.69921875, | |
| "learning_rate": 1.5807390861520805e-05, | |
| "loss": 0.5964, | |
| "mean_token_accuracy": 0.8172479033470154, | |
| "num_tokens": 27470431.0, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.3056265343955108, | |
| "grad_norm": 3.1796875, | |
| "learning_rate": 1.5764525483018254e-05, | |
| "loss": 0.5978, | |
| "mean_token_accuracy": 0.8172558772563935, | |
| "num_tokens": 27616926.0, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 0.3072966247473988, | |
| "grad_norm": 3.384765625, | |
| "learning_rate": 1.5721500880486847e-05, | |
| "loss": 0.5727, | |
| "mean_token_accuracy": 0.8231468296051025, | |
| "num_tokens": 27766315.0, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.30896671509928686, | |
| "grad_norm": 3.265625, | |
| "learning_rate": 1.5678318242324587e-05, | |
| "loss": 0.6048, | |
| "mean_token_accuracy": 0.8166863393783569, | |
| "num_tokens": 27912309.0, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 0.3106368054511749, | |
| "grad_norm": 3.587890625, | |
| "learning_rate": 1.5634978761294627e-05, | |
| "loss": 0.5783, | |
| "mean_token_accuracy": 0.8223829501867295, | |
| "num_tokens": 28068124.0, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.3123068958030629, | |
| "grad_norm": 3.619140625, | |
| "learning_rate": 1.559148363449235e-05, | |
| "loss": 0.5815, | |
| "mean_token_accuracy": 0.8205723863840103, | |
| "num_tokens": 28212240.0, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 0.313976986154951, | |
| "grad_norm": 3.5078125, | |
| "learning_rate": 1.554783406331226e-05, | |
| "loss": 0.5708, | |
| "mean_token_accuracy": 0.8217070680856705, | |
| "num_tokens": 28361807.0, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.31564707650683904, | |
| "grad_norm": 3.46875, | |
| "learning_rate": 1.5504031253414854e-05, | |
| "loss": 0.5704, | |
| "mean_token_accuracy": 0.8224059015512466, | |
| "num_tokens": 28520675.0, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 0.3173171668587271, | |
| "grad_norm": 3.56640625, | |
| "learning_rate": 1.5460076414693276e-05, | |
| "loss": 0.5947, | |
| "mean_token_accuracy": 0.8166932672262192, | |
| "num_tokens": 28671012.0, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.3189872572106151, | |
| "grad_norm": 3.40625, | |
| "learning_rate": 1.5415970761239908e-05, | |
| "loss": 0.5703, | |
| "mean_token_accuracy": 0.823592340350151, | |
| "num_tokens": 28826413.0, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 0.32065734756250314, | |
| "grad_norm": 3.021484375, | |
| "learning_rate": 1.5371715511312846e-05, | |
| "loss": 0.5524, | |
| "mean_token_accuracy": 0.8269542592763901, | |
| "num_tokens": 28973595.0, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.32232743791439117, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.5327311887302247e-05, | |
| "loss": 0.587, | |
| "mean_token_accuracy": 0.8197296333312988, | |
| "num_tokens": 29118143.0, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 0.3239975282662792, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 1.528276111569656e-05, | |
| "loss": 0.573, | |
| "mean_token_accuracy": 0.8212918490171432, | |
| "num_tokens": 29271964.0, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.32566761861816723, | |
| "grad_norm": 3.27734375, | |
| "learning_rate": 1.5238064427048644e-05, | |
| "loss": 0.5636, | |
| "mean_token_accuracy": 0.8254357093572616, | |
| "num_tokens": 29423354.0, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 0.32733770897005526, | |
| "grad_norm": 3.314453125, | |
| "learning_rate": 1.5193223055941793e-05, | |
| "loss": 0.5585, | |
| "mean_token_accuracy": 0.8258392840623856, | |
| "num_tokens": 29573920.0, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.3290077993219433, | |
| "grad_norm": 3.05078125, | |
| "learning_rate": 1.5148238240955628e-05, | |
| "loss": 0.5751, | |
| "mean_token_accuracy": 0.8223698770999909, | |
| "num_tokens": 29723005.0, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 0.3306778896738313, | |
| "grad_norm": 3.27734375, | |
| "learning_rate": 1.5103111224631875e-05, | |
| "loss": 0.5801, | |
| "mean_token_accuracy": 0.8200888675451279, | |
| "num_tokens": 29869002.0, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.3323479800257194, | |
| "grad_norm": 3.923828125, | |
| "learning_rate": 1.5057843253440063e-05, | |
| "loss": 0.5861, | |
| "mean_token_accuracy": 0.8186714911460876, | |
| "num_tokens": 30015782.0, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 0.33401807037760745, | |
| "grad_norm": 3.38671875, | |
| "learning_rate": 1.5012435577743085e-05, | |
| "loss": 0.5844, | |
| "mean_token_accuracy": 0.821356486082077, | |
| "num_tokens": 30161096.0, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.3356881607294955, | |
| "grad_norm": 4.05078125, | |
| "learning_rate": 1.4966889451762658e-05, | |
| "loss": 0.5633, | |
| "mean_token_accuracy": 0.8244505578279495, | |
| "num_tokens": 30310339.0, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 0.3373582510813835, | |
| "grad_norm": 3.69921875, | |
| "learning_rate": 1.492120613354469e-05, | |
| "loss": 0.5602, | |
| "mean_token_accuracy": 0.8251171362400055, | |
| "num_tokens": 30462338.0, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.33902834143327154, | |
| "grad_norm": 3.177734375, | |
| "learning_rate": 1.487538688492452e-05, | |
| "loss": 0.5581, | |
| "mean_token_accuracy": 0.825383592247963, | |
| "num_tokens": 30614667.0, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 0.3406984317851596, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 1.482943297149207e-05, | |
| "loss": 0.5503, | |
| "mean_token_accuracy": 0.8295097362995147, | |
| "num_tokens": 30763133.0, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.3423685221370476, | |
| "grad_norm": 3.802734375, | |
| "learning_rate": 1.4783345662556894e-05, | |
| "loss": 0.573, | |
| "mean_token_accuracy": 0.823209963440895, | |
| "num_tokens": 30917281.0, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 0.34403861248893564, | |
| "grad_norm": 3.8828125, | |
| "learning_rate": 1.47371262311131e-05, | |
| "loss": 0.5714, | |
| "mean_token_accuracy": 0.8230595916509629, | |
| "num_tokens": 31063586.0, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.34570870284082367, | |
| "grad_norm": 3.333984375, | |
| "learning_rate": 1.4690775953804206e-05, | |
| "loss": 0.5487, | |
| "mean_token_accuracy": 0.8284380221366883, | |
| "num_tokens": 31219950.0, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 0.3473787931927117, | |
| "grad_norm": 3.666015625, | |
| "learning_rate": 1.4644296110887869e-05, | |
| "loss": 0.5672, | |
| "mean_token_accuracy": 0.8228234505653381, | |
| "num_tokens": 31370295.0, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.3490488835445998, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 1.4597687986200529e-05, | |
| "loss": 0.5744, | |
| "mean_token_accuracy": 0.8230278396606445, | |
| "num_tokens": 31517590.0, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 0.3507189738964878, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 1.4550952867121933e-05, | |
| "loss": 0.5654, | |
| "mean_token_accuracy": 0.824184655547142, | |
| "num_tokens": 31668597.0, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.35238906424837585, | |
| "grad_norm": 3.6953125, | |
| "learning_rate": 1.4504092044539597e-05, | |
| "loss": 0.5592, | |
| "mean_token_accuracy": 0.8253324276208878, | |
| "num_tokens": 31817864.0, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 0.3540591546002639, | |
| "grad_norm": 3.45703125, | |
| "learning_rate": 1.4457106812813127e-05, | |
| "loss": 0.5505, | |
| "mean_token_accuracy": 0.827171710729599, | |
| "num_tokens": 31973663.0, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.3557292449521519, | |
| "grad_norm": 3.0234375, | |
| "learning_rate": 1.4409998469738486e-05, | |
| "loss": 0.5603, | |
| "mean_token_accuracy": 0.8264797705411911, | |
| "num_tokens": 32122867.0, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 0.35739933530403994, | |
| "grad_norm": 3.646484375, | |
| "learning_rate": 1.4362768316512143e-05, | |
| "loss": 0.5526, | |
| "mean_token_accuracy": 0.8274721032381058, | |
| "num_tokens": 32271390.0, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.359069425655928, | |
| "grad_norm": 3.0390625, | |
| "learning_rate": 1.431541765769512e-05, | |
| "loss": 0.5704, | |
| "mean_token_accuracy": 0.8233271539211273, | |
| "num_tokens": 32422937.0, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 0.360739516007816, | |
| "grad_norm": 3.361328125, | |
| "learning_rate": 1.4267947801176972e-05, | |
| "loss": 0.5592, | |
| "mean_token_accuracy": 0.8274497729539871, | |
| "num_tokens": 32575242.0, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.36240960635970404, | |
| "grad_norm": 3.708984375, | |
| "learning_rate": 1.4220360058139658e-05, | |
| "loss": 0.563, | |
| "mean_token_accuracy": 0.8254307335615159, | |
| "num_tokens": 32729992.0, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 0.36407969671159207, | |
| "grad_norm": 4.1640625, | |
| "learning_rate": 1.4172655743021317e-05, | |
| "loss": 0.5382, | |
| "mean_token_accuracy": 0.8311225980520248, | |
| "num_tokens": 32875452.0, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.36574978706348016, | |
| "grad_norm": 3.388671875, | |
| "learning_rate": 1.4124836173479972e-05, | |
| "loss": 0.5514, | |
| "mean_token_accuracy": 0.8262929075956345, | |
| "num_tokens": 33030316.0, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 0.3674198774153682, | |
| "grad_norm": 3.482421875, | |
| "learning_rate": 1.4076902670357132e-05, | |
| "loss": 0.5602, | |
| "mean_token_accuracy": 0.8263766020536423, | |
| "num_tokens": 33183725.0, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.3690899677672562, | |
| "grad_norm": 4.14453125, | |
| "learning_rate": 1.4028856557641307e-05, | |
| "loss": 0.56, | |
| "mean_token_accuracy": 0.8278713476657867, | |
| "num_tokens": 33338154.0, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 0.37076005811914425, | |
| "grad_norm": 3.494140625, | |
| "learning_rate": 1.3980699162431421e-05, | |
| "loss": 0.5614, | |
| "mean_token_accuracy": 0.8253583014011383, | |
| "num_tokens": 33490131.0, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.3724301484710323, | |
| "grad_norm": 3.3828125, | |
| "learning_rate": 1.3932431814900195e-05, | |
| "loss": 0.5431, | |
| "mean_token_accuracy": 0.8307267421483994, | |
| "num_tokens": 33644521.0, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 0.3741002388229203, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 1.3884055848257369e-05, | |
| "loss": 0.5521, | |
| "mean_token_accuracy": 0.8285236042737961, | |
| "num_tokens": 33800815.0, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.37577032917480835, | |
| "grad_norm": 3.08203125, | |
| "learning_rate": 1.383557259871289e-05, | |
| "loss": 0.5586, | |
| "mean_token_accuracy": 0.8272363543510437, | |
| "num_tokens": 33946173.0, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 0.3774404195266964, | |
| "grad_norm": 4.18359375, | |
| "learning_rate": 1.3786983405440013e-05, | |
| "loss": 0.552, | |
| "mean_token_accuracy": 0.8265141195058823, | |
| "num_tokens": 34095920.0, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.3791105098785844, | |
| "grad_norm": 3.103515625, | |
| "learning_rate": 1.373828961053829e-05, | |
| "loss": 0.5837, | |
| "mean_token_accuracy": 0.8216396170854569, | |
| "num_tokens": 34248446.0, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 0.38078060023047244, | |
| "grad_norm": 3.419921875, | |
| "learning_rate": 1.3689492558996529e-05, | |
| "loss": 0.5463, | |
| "mean_token_accuracy": 0.8293001532554627, | |
| "num_tokens": 34400906.0, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.38245069058236053, | |
| "grad_norm": 3.173828125, | |
| "learning_rate": 1.3640593598655611e-05, | |
| "loss": 0.5463, | |
| "mean_token_accuracy": 0.8295714586973191, | |
| "num_tokens": 34553639.0, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 0.38412078093424856, | |
| "grad_norm": 3.44140625, | |
| "learning_rate": 1.3591594080171286e-05, | |
| "loss": 0.5626, | |
| "mean_token_accuracy": 0.8255741602182388, | |
| "num_tokens": 34705512.0, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.3857908712861366, | |
| "grad_norm": 2.962890625, | |
| "learning_rate": 1.3542495356976851e-05, | |
| "loss": 0.5529, | |
| "mean_token_accuracy": 0.8291010856628418, | |
| "num_tokens": 34851485.0, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 0.3874609616380246, | |
| "grad_norm": 3.091796875, | |
| "learning_rate": 1.3493298785245778e-05, | |
| "loss": 0.5588, | |
| "mean_token_accuracy": 0.826916481256485, | |
| "num_tokens": 35008468.0, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.38913105198991266, | |
| "grad_norm": 3.2109375, | |
| "learning_rate": 1.344400572385424e-05, | |
| "loss": 0.5458, | |
| "mean_token_accuracy": 0.8301201510429382, | |
| "num_tokens": 35157833.0, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 0.3908011423418007, | |
| "grad_norm": 4.0859375, | |
| "learning_rate": 1.3394617534343596e-05, | |
| "loss": 0.5461, | |
| "mean_token_accuracy": 0.8286441028118133, | |
| "num_tokens": 35310802.0, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.3924712326936887, | |
| "grad_norm": 3.578125, | |
| "learning_rate": 1.3345135580882764e-05, | |
| "loss": 0.553, | |
| "mean_token_accuracy": 0.8291445529460907, | |
| "num_tokens": 35456677.0, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 0.39414132304557675, | |
| "grad_norm": 4.30078125, | |
| "learning_rate": 1.3295561230230555e-05, | |
| "loss": 0.557, | |
| "mean_token_accuracy": 0.827009784579277, | |
| "num_tokens": 35604720.0, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.3958114133974648, | |
| "grad_norm": 3.46875, | |
| "learning_rate": 1.3245895851697914e-05, | |
| "loss": 0.5387, | |
| "mean_token_accuracy": 0.832523928284645, | |
| "num_tokens": 35758780.0, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 0.3974815037493528, | |
| "grad_norm": 3.318359375, | |
| "learning_rate": 1.3196140817110104e-05, | |
| "loss": 0.5501, | |
| "mean_token_accuracy": 0.8280089855194092, | |
| "num_tokens": 35908459.0, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.3991515941012409, | |
| "grad_norm": 3.591796875, | |
| "learning_rate": 1.3146297500768799e-05, | |
| "loss": 0.5518, | |
| "mean_token_accuracy": 0.8280233424901963, | |
| "num_tokens": 36054122.0, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 0.40082168445312893, | |
| "grad_norm": 3.591796875, | |
| "learning_rate": 1.3096367279414142e-05, | |
| "loss": 0.557, | |
| "mean_token_accuracy": 0.8281977719068527, | |
| "num_tokens": 36206481.0, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.40249177480501697, | |
| "grad_norm": 3.64453125, | |
| "learning_rate": 1.3046351532186718e-05, | |
| "loss": 0.5341, | |
| "mean_token_accuracy": 0.8324338626861573, | |
| "num_tokens": 36357066.0, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 0.404161865156905, | |
| "grad_norm": 4.046875, | |
| "learning_rate": 1.2996251640589443e-05, | |
| "loss": 0.5597, | |
| "mean_token_accuracy": 0.8256447410583496, | |
| "num_tokens": 36509298.0, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.40583195550879303, | |
| "grad_norm": 3.501953125, | |
| "learning_rate": 1.2946068988449416e-05, | |
| "loss": 0.5461, | |
| "mean_token_accuracy": 0.8304660183191299, | |
| "num_tokens": 36664284.0, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 0.40750204586068106, | |
| "grad_norm": 3.775390625, | |
| "learning_rate": 1.2895804961879697e-05, | |
| "loss": 0.5452, | |
| "mean_token_accuracy": 0.8312527567148209, | |
| "num_tokens": 36815575.0, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.4091721362125691, | |
| "grad_norm": 2.853515625, | |
| "learning_rate": 1.2845460949241018e-05, | |
| "loss": 0.5481, | |
| "mean_token_accuracy": 0.8277529460191727, | |
| "num_tokens": 36974534.0, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 0.4108422265644571, | |
| "grad_norm": 3.171875, | |
| "learning_rate": 1.2795038341103432e-05, | |
| "loss": 0.5543, | |
| "mean_token_accuracy": 0.8282213443517685, | |
| "num_tokens": 37125168.0, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.41251231691634516, | |
| "grad_norm": 3.2734375, | |
| "learning_rate": 1.2744538530207916e-05, | |
| "loss": 0.547, | |
| "mean_token_accuracy": 0.8285178303718567, | |
| "num_tokens": 37278364.0, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 0.4141824072682332, | |
| "grad_norm": 2.806640625, | |
| "learning_rate": 1.2693962911427877e-05, | |
| "loss": 0.568, | |
| "mean_token_accuracy": 0.8246202218532562, | |
| "num_tokens": 37431928.0, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.4158524976201213, | |
| "grad_norm": 2.970703125, | |
| "learning_rate": 1.264331288173065e-05, | |
| "loss": 0.5553, | |
| "mean_token_accuracy": 0.8278548353910447, | |
| "num_tokens": 37584284.0, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 0.4175225879720093, | |
| "grad_norm": 3.25390625, | |
| "learning_rate": 1.2592589840138897e-05, | |
| "loss": 0.5417, | |
| "mean_token_accuracy": 0.8309043395519257, | |
| "num_tokens": 37729858.0, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.41919267832389734, | |
| "grad_norm": 3.705078125, | |
| "learning_rate": 1.2541795187691971e-05, | |
| "loss": 0.5514, | |
| "mean_token_accuracy": 0.8308093577623368, | |
| "num_tokens": 37876100.0, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 0.42086276867578537, | |
| "grad_norm": 3.5, | |
| "learning_rate": 1.2490930327407209e-05, | |
| "loss": 0.5575, | |
| "mean_token_accuracy": 0.8272964191436768, | |
| "num_tokens": 38025185.0, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.4225328590276734, | |
| "grad_norm": 3.21484375, | |
| "learning_rate": 1.243999666424119e-05, | |
| "loss": 0.5485, | |
| "mean_token_accuracy": 0.8294407540559768, | |
| "num_tokens": 38181591.0, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 0.42420294937956143, | |
| "grad_norm": 2.900390625, | |
| "learning_rate": 1.2388995605050914e-05, | |
| "loss": 0.5449, | |
| "mean_token_accuracy": 0.8301975548267364, | |
| "num_tokens": 38327561.0, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.42587303973144947, | |
| "grad_norm": 3.689453125, | |
| "learning_rate": 1.2337928558554956e-05, | |
| "loss": 0.5332, | |
| "mean_token_accuracy": 0.8314021265506745, | |
| "num_tokens": 38473244.0, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 0.4275431300833375, | |
| "grad_norm": 3.4921875, | |
| "learning_rate": 1.2286796935294551e-05, | |
| "loss": 0.5471, | |
| "mean_token_accuracy": 0.8304495525360107, | |
| "num_tokens": 38624223.0, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.42921322043522553, | |
| "grad_norm": 3.779296875, | |
| "learning_rate": 1.2235602147594631e-05, | |
| "loss": 0.5479, | |
| "mean_token_accuracy": 0.8294032102823258, | |
| "num_tokens": 38773521.0, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 0.43088331078711356, | |
| "grad_norm": 3.548828125, | |
| "learning_rate": 1.2184345609524813e-05, | |
| "loss": 0.5482, | |
| "mean_token_accuracy": 0.8288749468326568, | |
| "num_tokens": 38926115.0, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.43255340113900165, | |
| "grad_norm": 2.939453125, | |
| "learning_rate": 1.2133028736860348e-05, | |
| "loss": 0.5353, | |
| "mean_token_accuracy": 0.8340490102767945, | |
| "num_tokens": 39077937.0, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 0.4342234914908897, | |
| "grad_norm": 3.244140625, | |
| "learning_rate": 1.2081652947043003e-05, | |
| "loss": 0.5501, | |
| "mean_token_accuracy": 0.8298387557268143, | |
| "num_tokens": 39229394.0, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.4358935818427777, | |
| "grad_norm": 2.775390625, | |
| "learning_rate": 1.2030219659141928e-05, | |
| "loss": 0.5353, | |
| "mean_token_accuracy": 0.8325220793485641, | |
| "num_tokens": 39378856.0, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 0.43756367219466574, | |
| "grad_norm": 3.701171875, | |
| "learning_rate": 1.1978730293814438e-05, | |
| "loss": 0.5334, | |
| "mean_token_accuracy": 0.8330723947286606, | |
| "num_tokens": 39531138.0, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.4392337625465538, | |
| "grad_norm": 3.646484375, | |
| "learning_rate": 1.1927186273266784e-05, | |
| "loss": 0.5345, | |
| "mean_token_accuracy": 0.8333028835058213, | |
| "num_tokens": 39677471.0, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 0.4409038528984418, | |
| "grad_norm": 3.234375, | |
| "learning_rate": 1.1875589021214877e-05, | |
| "loss": 0.5436, | |
| "mean_token_accuracy": 0.8311423152685166, | |
| "num_tokens": 39825562.0, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.44257394325032984, | |
| "grad_norm": 3.224609375, | |
| "learning_rate": 1.1823939962844944e-05, | |
| "loss": 0.5326, | |
| "mean_token_accuracy": 0.8338733261823654, | |
| "num_tokens": 39979460.0, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 0.44424403360221787, | |
| "grad_norm": 3.4765625, | |
| "learning_rate": 1.1772240524774179e-05, | |
| "loss": 0.5395, | |
| "mean_token_accuracy": 0.8336213880777359, | |
| "num_tokens": 40121774.0, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.4459141239541059, | |
| "grad_norm": 3.6875, | |
| "learning_rate": 1.172049213501133e-05, | |
| "loss": 0.5434, | |
| "mean_token_accuracy": 0.8318886595964432, | |
| "num_tokens": 40272793.0, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 0.44758421430599393, | |
| "grad_norm": 3.65234375, | |
| "learning_rate": 1.166869622291726e-05, | |
| "loss": 0.5425, | |
| "mean_token_accuracy": 0.8311206418275833, | |
| "num_tokens": 40425954.0, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.44925430465788196, | |
| "grad_norm": 3.109375, | |
| "learning_rate": 1.1616854219165452e-05, | |
| "loss": 0.5352, | |
| "mean_token_accuracy": 0.8340102022886277, | |
| "num_tokens": 40578555.0, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 0.45092439500977005, | |
| "grad_norm": 3.138671875, | |
| "learning_rate": 1.1564967555702526e-05, | |
| "loss": 0.5593, | |
| "mean_token_accuracy": 0.8278708016872406, | |
| "num_tokens": 40725781.0, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.4525944853616581, | |
| "grad_norm": 3.943359375, | |
| "learning_rate": 1.1513037665708639e-05, | |
| "loss": 0.5105, | |
| "mean_token_accuracy": 0.8397551566362381, | |
| "num_tokens": 40874427.0, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 0.4542645757135461, | |
| "grad_norm": 3.845703125, | |
| "learning_rate": 1.146106598355794e-05, | |
| "loss": 0.5195, | |
| "mean_token_accuracy": 0.8360963726043701, | |
| "num_tokens": 41027698.0, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.45593466606543415, | |
| "grad_norm": 4.0546875, | |
| "learning_rate": 1.1409053944778925e-05, | |
| "loss": 0.5367, | |
| "mean_token_accuracy": 0.8321689450740815, | |
| "num_tokens": 41177523.0, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 0.4576047564173222, | |
| "grad_norm": 3.27734375, | |
| "learning_rate": 1.1357002986014803e-05, | |
| "loss": 0.5253, | |
| "mean_token_accuracy": 0.8352927279472351, | |
| "num_tokens": 41329674.0, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.4592748467692102, | |
| "grad_norm": 3.017578125, | |
| "learning_rate": 1.1304914544983794e-05, | |
| "loss": 0.5232, | |
| "mean_token_accuracy": 0.835522665977478, | |
| "num_tokens": 41476485.0, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 0.46094493712109824, | |
| "grad_norm": 3.44921875, | |
| "learning_rate": 1.125279006043945e-05, | |
| "loss": 0.5674, | |
| "mean_token_accuracy": 0.824871341586113, | |
| "num_tokens": 41628555.0, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.4626150274729863, | |
| "grad_norm": 3.52734375, | |
| "learning_rate": 1.1200630972130867e-05, | |
| "loss": 0.5282, | |
| "mean_token_accuracy": 0.8343129450082779, | |
| "num_tokens": 41775801.0, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 0.4642851178248743, | |
| "grad_norm": 2.576171875, | |
| "learning_rate": 1.1148438720762961e-05, | |
| "loss": 0.5106, | |
| "mean_token_accuracy": 0.8398624455928803, | |
| "num_tokens": 41925501.0, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.46595520817676234, | |
| "grad_norm": 4.1015625, | |
| "learning_rate": 1.109621474795666e-05, | |
| "loss": 0.5338, | |
| "mean_token_accuracy": 0.8335544627904892, | |
| "num_tokens": 42079129.0, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 0.4676252985286504, | |
| "grad_norm": 3.314453125, | |
| "learning_rate": 1.104396049620907e-05, | |
| "loss": 0.5235, | |
| "mean_token_accuracy": 0.8374920153617859, | |
| "num_tokens": 42225486.0, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.46929538888053846, | |
| "grad_norm": 3.83203125, | |
| "learning_rate": 1.0991677408853643e-05, | |
| "loss": 0.5387, | |
| "mean_token_accuracy": 0.8317029625177383, | |
| "num_tokens": 42379482.0, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 0.4709654792324265, | |
| "grad_norm": 4.4296875, | |
| "learning_rate": 1.093936693002032e-05, | |
| "loss": 0.5135, | |
| "mean_token_accuracy": 0.8377016627788544, | |
| "num_tokens": 42531797.0, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.4726355695843145, | |
| "grad_norm": 2.8984375, | |
| "learning_rate": 1.0887030504595624e-05, | |
| "loss": 0.5392, | |
| "mean_token_accuracy": 0.8313734871149063, | |
| "num_tokens": 42686643.0, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 0.47430565993620255, | |
| "grad_norm": 3.212890625, | |
| "learning_rate": 1.0834669578182757e-05, | |
| "loss": 0.5475, | |
| "mean_token_accuracy": 0.8304911911487579, | |
| "num_tokens": 42836786.0, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.4759757502880906, | |
| "grad_norm": 3.361328125, | |
| "learning_rate": 1.0782285597061679e-05, | |
| "loss": 0.5259, | |
| "mean_token_accuracy": 0.8347867679595947, | |
| "num_tokens": 42982714.0, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 0.4776458406399786, | |
| "grad_norm": 4.04296875, | |
| "learning_rate": 1.0729880008149142e-05, | |
| "loss": 0.5485, | |
| "mean_token_accuracy": 0.829542515873909, | |
| "num_tokens": 43142510.0, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.47931593099186665, | |
| "grad_norm": 3.369140625, | |
| "learning_rate": 1.0677454258958746e-05, | |
| "loss": 0.5244, | |
| "mean_token_accuracy": 0.8368889981508255, | |
| "num_tokens": 43288399.0, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 0.4809860213437547, | |
| "grad_norm": 3.76171875, | |
| "learning_rate": 1.0625009797560936e-05, | |
| "loss": 0.5142, | |
| "mean_token_accuracy": 0.8388600462675094, | |
| "num_tokens": 43444562.0, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.4826561116956427, | |
| "grad_norm": 2.94140625, | |
| "learning_rate": 1.0572548072543021e-05, | |
| "loss": 0.5284, | |
| "mean_token_accuracy": 0.8348941618204117, | |
| "num_tokens": 43591116.0, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 0.4843262020475308, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 1.0520070532969142e-05, | |
| "loss": 0.5208, | |
| "mean_token_accuracy": 0.8390517139434814, | |
| "num_tokens": 43740326.0, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.4859962923994188, | |
| "grad_norm": 3.853515625, | |
| "learning_rate": 1.0467578628340278e-05, | |
| "loss": 0.5075, | |
| "mean_token_accuracy": 0.8397658413648605, | |
| "num_tokens": 43891895.0, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 0.48766638275130686, | |
| "grad_norm": 3.06640625, | |
| "learning_rate": 1.0415073808554178e-05, | |
| "loss": 0.5151, | |
| "mean_token_accuracy": 0.8379220014810562, | |
| "num_tokens": 44046860.0, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.4893364731031949, | |
| "grad_norm": 3.13671875, | |
| "learning_rate": 1.0362557523865323e-05, | |
| "loss": 0.5281, | |
| "mean_token_accuracy": 0.8356298345327378, | |
| "num_tokens": 44203029.0, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 0.4910065634550829, | |
| "grad_norm": 3.08984375, | |
| "learning_rate": 1.0310031224844878e-05, | |
| "loss": 0.5365, | |
| "mean_token_accuracy": 0.8323665148019791, | |
| "num_tokens": 44355830.0, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.49267665380697095, | |
| "grad_norm": 3.234375, | |
| "learning_rate": 1.0257496362340622e-05, | |
| "loss": 0.5168, | |
| "mean_token_accuracy": 0.8371515053510666, | |
| "num_tokens": 44506850.0, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 0.494346744158859, | |
| "grad_norm": 3.34765625, | |
| "learning_rate": 1.0204954387436847e-05, | |
| "loss": 0.5228, | |
| "mean_token_accuracy": 0.8363370823860169, | |
| "num_tokens": 44658966.0, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.496016834510747, | |
| "grad_norm": 3.560546875, | |
| "learning_rate": 1.0152406751414328e-05, | |
| "loss": 0.5151, | |
| "mean_token_accuracy": 0.8392669379711151, | |
| "num_tokens": 44805368.0, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 0.49768692486263505, | |
| "grad_norm": 3.609375, | |
| "learning_rate": 1.0099854905710183e-05, | |
| "loss": 0.5285, | |
| "mean_token_accuracy": 0.8332407021522522, | |
| "num_tokens": 44951969.0, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.4993570152145231, | |
| "grad_norm": 3.0078125, | |
| "learning_rate": 1.0047300301877822e-05, | |
| "loss": 0.5289, | |
| "mean_token_accuracy": 0.8356048625707626, | |
| "num_tokens": 45108518.0, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 0.5010271055664112, | |
| "grad_norm": 3.59765625, | |
| "learning_rate": 9.994744391546838e-06, | |
| "loss": 0.5206, | |
| "mean_token_accuracy": 0.8376101624965667, | |
| "num_tokens": 45263447.0, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.5026971959182992, | |
| "grad_norm": 3.474609375, | |
| "learning_rate": 9.942188626382897e-06, | |
| "loss": 0.5434, | |
| "mean_token_accuracy": 0.8310336023569107, | |
| "num_tokens": 45414902.0, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 0.5043672862701872, | |
| "grad_norm": 4.12109375, | |
| "learning_rate": 9.889634458047673e-06, | |
| "loss": 0.5142, | |
| "mean_token_accuracy": 0.8397058790922165, | |
| "num_tokens": 45571812.0, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.5060373766220753, | |
| "grad_norm": 3.69140625, | |
| "learning_rate": 9.837083338158727e-06, | |
| "loss": 0.5248, | |
| "mean_token_accuracy": 0.8354938596487045, | |
| "num_tokens": 45727612.0, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 0.5077074669739633, | |
| "grad_norm": 3.9609375, | |
| "learning_rate": 9.784536718249412e-06, | |
| "loss": 0.5266, | |
| "mean_token_accuracy": 0.8367443948984146, | |
| "num_tokens": 45873117.0, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.5093775573258513, | |
| "grad_norm": 3.62890625, | |
| "learning_rate": 9.731996049728788e-06, | |
| "loss": 0.5182, | |
| "mean_token_accuracy": 0.8391673922538757, | |
| "num_tokens": 46023817.0, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 0.5110476476777394, | |
| "grad_norm": 3.126953125, | |
| "learning_rate": 9.67946278384154e-06, | |
| "loss": 0.5094, | |
| "mean_token_accuracy": 0.8392078793048858, | |
| "num_tokens": 46174815.0, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.5127177380296274, | |
| "grad_norm": 3.53515625, | |
| "learning_rate": 9.626938371627867e-06, | |
| "loss": 0.5123, | |
| "mean_token_accuracy": 0.8391502851247787, | |
| "num_tokens": 46324335.0, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 0.5143878283815154, | |
| "grad_norm": 4.2734375, | |
| "learning_rate": 9.574424263883426e-06, | |
| "loss": 0.5078, | |
| "mean_token_accuracy": 0.8403759181499482, | |
| "num_tokens": 46477188.0, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.5160579187334035, | |
| "grad_norm": 3.53125, | |
| "learning_rate": 9.521921911119254e-06, | |
| "loss": 0.5035, | |
| "mean_token_accuracy": 0.8410092943906784, | |
| "num_tokens": 46631384.0, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 0.5177280090852915, | |
| "grad_norm": 3.3515625, | |
| "learning_rate": 9.469432763521689e-06, | |
| "loss": 0.5054, | |
| "mean_token_accuracy": 0.8401052719354629, | |
| "num_tokens": 46785556.0, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.5193980994371795, | |
| "grad_norm": 2.900390625, | |
| "learning_rate": 9.41695827091233e-06, | |
| "loss": 0.522, | |
| "mean_token_accuracy": 0.8375687634944916, | |
| "num_tokens": 46933148.0, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 0.5210681897890675, | |
| "grad_norm": 3.34375, | |
| "learning_rate": 9.36449988270798e-06, | |
| "loss": 0.5132, | |
| "mean_token_accuracy": 0.839164929986, | |
| "num_tokens": 47088638.0, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.5227382801409556, | |
| "grad_norm": 3.193359375, | |
| "learning_rate": 9.312059047880634e-06, | |
| "loss": 0.5137, | |
| "mean_token_accuracy": 0.8407429993152619, | |
| "num_tokens": 47241852.0, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 0.5244083704928436, | |
| "grad_norm": 3.4765625, | |
| "learning_rate": 9.259637214917417e-06, | |
| "loss": 0.5054, | |
| "mean_token_accuracy": 0.8394024974107742, | |
| "num_tokens": 47391908.0, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.5260784608447318, | |
| "grad_norm": 3.01953125, | |
| "learning_rate": 9.20723583178061e-06, | |
| "loss": 0.513, | |
| "mean_token_accuracy": 0.8386244624853134, | |
| "num_tokens": 47546987.0, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 0.5277485511966198, | |
| "grad_norm": 3.49609375, | |
| "learning_rate": 9.154856345867633e-06, | |
| "loss": 0.4975, | |
| "mean_token_accuracy": 0.843689147233963, | |
| "num_tokens": 47697148.0, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.5294186415485078, | |
| "grad_norm": 4.02734375, | |
| "learning_rate": 9.102500203971085e-06, | |
| "loss": 0.5149, | |
| "mean_token_accuracy": 0.8367012405395508, | |
| "num_tokens": 47848694.0, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 0.5310887319003958, | |
| "grad_norm": 3.2578125, | |
| "learning_rate": 9.050168852238767e-06, | |
| "loss": 0.5081, | |
| "mean_token_accuracy": 0.8401696521043778, | |
| "num_tokens": 47999043.0, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.5327588222522839, | |
| "grad_norm": 3.025390625, | |
| "learning_rate": 8.997863736133738e-06, | |
| "loss": 0.5122, | |
| "mean_token_accuracy": 0.8394769513607026, | |
| "num_tokens": 48149462.0, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 0.5344289126041719, | |
| "grad_norm": 3.150390625, | |
| "learning_rate": 8.945586300394395e-06, | |
| "loss": 0.5214, | |
| "mean_token_accuracy": 0.8370646077394486, | |
| "num_tokens": 48305787.0, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.53609900295606, | |
| "grad_norm": 2.970703125, | |
| "learning_rate": 8.893337988994576e-06, | |
| "loss": 0.5145, | |
| "mean_token_accuracy": 0.8388128334283829, | |
| "num_tokens": 48461962.0, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 0.537769093307948, | |
| "grad_norm": 3.6640625, | |
| "learning_rate": 8.841120245103648e-06, | |
| "loss": 0.5013, | |
| "mean_token_accuracy": 0.8403582525253296, | |
| "num_tokens": 48616886.0, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.539439183659836, | |
| "grad_norm": 3.603515625, | |
| "learning_rate": 8.788934511046678e-06, | |
| "loss": 0.4856, | |
| "mean_token_accuracy": 0.8478838753700256, | |
| "num_tokens": 48773096.0, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 0.541109274011724, | |
| "grad_norm": 3.224609375, | |
| "learning_rate": 8.736782228264559e-06, | |
| "loss": 0.5333, | |
| "mean_token_accuracy": 0.8341756075620651, | |
| "num_tokens": 48925256.0, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.5427793643636121, | |
| "grad_norm": 3.666015625, | |
| "learning_rate": 8.684664837274238e-06, | |
| "loss": 0.5326, | |
| "mean_token_accuracy": 0.8348221153020858, | |
| "num_tokens": 49074214.0, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 0.5444494547155001, | |
| "grad_norm": 4.4296875, | |
| "learning_rate": 8.632583777628883e-06, | |
| "loss": 0.5009, | |
| "mean_token_accuracy": 0.8419860059022903, | |
| "num_tokens": 49231663.0, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.5461195450673881, | |
| "grad_norm": 3.11328125, | |
| "learning_rate": 8.580540487878155e-06, | |
| "loss": 0.513, | |
| "mean_token_accuracy": 0.8394070512056351, | |
| "num_tokens": 49379114.0, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 0.5477896354192762, | |
| "grad_norm": 3.583984375, | |
| "learning_rate": 8.528536405528443e-06, | |
| "loss": 0.5076, | |
| "mean_token_accuracy": 0.8402014470100403, | |
| "num_tokens": 49533012.0, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 0.5494597257711642, | |
| "grad_norm": 3.56640625, | |
| "learning_rate": 8.476572967003193e-06, | |
| "loss": 0.5088, | |
| "mean_token_accuracy": 0.8388606005907059, | |
| "num_tokens": 49684505.0, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 0.5511298161230522, | |
| "grad_norm": 3.34375, | |
| "learning_rate": 8.424651607603206e-06, | |
| "loss": 0.4997, | |
| "mean_token_accuracy": 0.8425060153007508, | |
| "num_tokens": 49835171.0, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.5527999064749403, | |
| "grad_norm": 2.751953125, | |
| "learning_rate": 8.372773761466992e-06, | |
| "loss": 0.4993, | |
| "mean_token_accuracy": 0.844070131778717, | |
| "num_tokens": 49985980.0, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 0.5544699968268283, | |
| "grad_norm": 3.142578125, | |
| "learning_rate": 8.320940861531174e-06, | |
| "loss": 0.4999, | |
| "mean_token_accuracy": 0.8419631046056747, | |
| "num_tokens": 50133884.0, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 0.5561400871787163, | |
| "grad_norm": 3.814453125, | |
| "learning_rate": 8.269154339490906e-06, | |
| "loss": 0.5141, | |
| "mean_token_accuracy": 0.840504658818245, | |
| "num_tokens": 50282413.0, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 0.5578101775306044, | |
| "grad_norm": 3.3359375, | |
| "learning_rate": 8.217415625760304e-06, | |
| "loss": 0.5141, | |
| "mean_token_accuracy": 0.8382816570997238, | |
| "num_tokens": 50425249.0, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 0.5594802678824924, | |
| "grad_norm": 4.0234375, | |
| "learning_rate": 8.165726149432965e-06, | |
| "loss": 0.5097, | |
| "mean_token_accuracy": 0.8394738847017288, | |
| "num_tokens": 50572898.0, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 0.5611503582343805, | |
| "grad_norm": 3.732421875, | |
| "learning_rate": 8.114087338242487e-06, | |
| "loss": 0.502, | |
| "mean_token_accuracy": 0.8411443334817886, | |
| "num_tokens": 50720479.0, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 0.5628204485862686, | |
| "grad_norm": 3.01171875, | |
| "learning_rate": 8.062500618523016e-06, | |
| "loss": 0.5037, | |
| "mean_token_accuracy": 0.8405672430992126, | |
| "num_tokens": 50871329.0, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 0.5644905389381566, | |
| "grad_norm": 3.318359375, | |
| "learning_rate": 8.010967415169868e-06, | |
| "loss": 0.5157, | |
| "mean_token_accuracy": 0.8394720613956451, | |
| "num_tokens": 51021016.0, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 0.5661606292900446, | |
| "grad_norm": 2.96484375, | |
| "learning_rate": 7.959489151600157e-06, | |
| "loss": 0.5098, | |
| "mean_token_accuracy": 0.8396425741910934, | |
| "num_tokens": 51178696.0, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 0.5678307196419327, | |
| "grad_norm": 4.0234375, | |
| "learning_rate": 7.9080672497135e-06, | |
| "loss": 0.5117, | |
| "mean_token_accuracy": 0.8394624823331833, | |
| "num_tokens": 51329342.0, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.5695008099938207, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 7.856703129852713e-06, | |
| "loss": 0.5265, | |
| "mean_token_accuracy": 0.8355883210897446, | |
| "num_tokens": 51477147.0, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 0.5711709003457087, | |
| "grad_norm": 3.197265625, | |
| "learning_rate": 7.805398210764602e-06, | |
| "loss": 0.5028, | |
| "mean_token_accuracy": 0.8421104747056961, | |
| "num_tokens": 51626587.0, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 0.5728409906975968, | |
| "grad_norm": 2.873046875, | |
| "learning_rate": 7.75415390956076e-06, | |
| "loss": 0.5163, | |
| "mean_token_accuracy": 0.8387602722644806, | |
| "num_tokens": 51778610.0, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 0.5745110810494848, | |
| "grad_norm": 2.939453125, | |
| "learning_rate": 7.70297164167844e-06, | |
| "loss": 0.5052, | |
| "mean_token_accuracy": 0.8407110857963562, | |
| "num_tokens": 51931187.0, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 0.5761811714013728, | |
| "grad_norm": 3.853515625, | |
| "learning_rate": 7.65185282084145e-06, | |
| "loss": 0.5018, | |
| "mean_token_accuracy": 0.84199602663517, | |
| "num_tokens": 52083924.0, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 0.5778512617532608, | |
| "grad_norm": 3.15234375, | |
| "learning_rate": 7.600798859021093e-06, | |
| "loss": 0.4807, | |
| "mean_token_accuracy": 0.8484761095046998, | |
| "num_tokens": 52235027.0, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 0.5795213521051489, | |
| "grad_norm": 3.228515625, | |
| "learning_rate": 7.549811166397189e-06, | |
| "loss": 0.4914, | |
| "mean_token_accuracy": 0.8452172386646271, | |
| "num_tokens": 52381199.0, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 0.5811914424570369, | |
| "grad_norm": 3.25, | |
| "learning_rate": 7.498891151319116e-06, | |
| "loss": 0.4994, | |
| "mean_token_accuracy": 0.8403958940505981, | |
| "num_tokens": 52533270.0, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.5828615328089249, | |
| "grad_norm": 3.501953125, | |
| "learning_rate": 7.448040220266894e-06, | |
| "loss": 0.5025, | |
| "mean_token_accuracy": 0.8417500221729278, | |
| "num_tokens": 52689068.0, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 0.584531623160813, | |
| "grad_norm": 3.96875, | |
| "learning_rate": 7.397259777812356e-06, | |
| "loss": 0.4894, | |
| "mean_token_accuracy": 0.8449425888061524, | |
| "num_tokens": 52840463.0, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.586201713512701, | |
| "grad_norm": 2.83984375, | |
| "learning_rate": 7.346551226580335e-06, | |
| "loss": 0.5054, | |
| "mean_token_accuracy": 0.8414785838127137, | |
| "num_tokens": 52985660.0, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 0.587871803864589, | |
| "grad_norm": 2.927734375, | |
| "learning_rate": 7.295915967209948e-06, | |
| "loss": 0.504, | |
| "mean_token_accuracy": 0.8404000741243363, | |
| "num_tokens": 53137289.0, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 0.5895418942164771, | |
| "grad_norm": 3.544921875, | |
| "learning_rate": 7.245355398315878e-06, | |
| "loss": 0.4917, | |
| "mean_token_accuracy": 0.8452743798494339, | |
| "num_tokens": 53288007.0, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 0.5912119845683651, | |
| "grad_norm": 3.560546875, | |
| "learning_rate": 7.1948709164497545e-06, | |
| "loss": 0.5038, | |
| "mean_token_accuracy": 0.8420122969150543, | |
| "num_tokens": 53444532.0, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 0.5928820749202531, | |
| "grad_norm": 3.5234375, | |
| "learning_rate": 7.14446391606159e-06, | |
| "loss": 0.518, | |
| "mean_token_accuracy": 0.8379052346944809, | |
| "num_tokens": 53593721.0, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 0.5945521652721413, | |
| "grad_norm": 3.349609375, | |
| "learning_rate": 7.094135789461245e-06, | |
| "loss": 0.5139, | |
| "mean_token_accuracy": 0.8400999325513839, | |
| "num_tokens": 53746625.0, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 0.5962222556240293, | |
| "grad_norm": 3.166015625, | |
| "learning_rate": 7.043887926779981e-06, | |
| "loss": 0.5095, | |
| "mean_token_accuracy": 0.839566165804863, | |
| "num_tokens": 53900215.0, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 0.5978923459759173, | |
| "grad_norm": 3.544921875, | |
| "learning_rate": 6.993721715932056e-06, | |
| "loss": 0.4974, | |
| "mean_token_accuracy": 0.8424713629484176, | |
| "num_tokens": 54056974.0, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 0.5995624363278054, | |
| "grad_norm": 3.33984375, | |
| "learning_rate": 6.943638542576406e-06, | |
| "loss": 0.5077, | |
| "mean_token_accuracy": 0.839752956032753, | |
| "num_tokens": 54208833.0, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 0.6012325266796934, | |
| "grad_norm": 3.3203125, | |
| "learning_rate": 6.893639790078351e-06, | |
| "loss": 0.5134, | |
| "mean_token_accuracy": 0.8396169519424439, | |
| "num_tokens": 54356723.0, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.6029026170315814, | |
| "grad_norm": 3.099609375, | |
| "learning_rate": 6.843726839471386e-06, | |
| "loss": 0.4965, | |
| "mean_token_accuracy": 0.8424419635534286, | |
| "num_tokens": 54507048.0, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 0.6045727073834695, | |
| "grad_norm": 3.041015625, | |
| "learning_rate": 6.793901069419049e-06, | |
| "loss": 0.5257, | |
| "mean_token_accuracy": 0.8359838783740997, | |
| "num_tokens": 54653595.0, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 0.6062427977353575, | |
| "grad_norm": 3.521484375, | |
| "learning_rate": 6.744163856176837e-06, | |
| "loss": 0.5005, | |
| "mean_token_accuracy": 0.8421499592065811, | |
| "num_tokens": 54803842.0, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 0.6079128880872455, | |
| "grad_norm": 3.51171875, | |
| "learning_rate": 6.694516573554174e-06, | |
| "loss": 0.5215, | |
| "mean_token_accuracy": 0.8361709529161453, | |
| "num_tokens": 54955969.0, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 0.6095829784391336, | |
| "grad_norm": 3.07421875, | |
| "learning_rate": 6.64496059287649e-06, | |
| "loss": 0.4836, | |
| "mean_token_accuracy": 0.846044403910637, | |
| "num_tokens": 55109017.0, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 0.6112530687910216, | |
| "grad_norm": 4.25390625, | |
| "learning_rate": 6.595497282947323e-06, | |
| "loss": 0.5152, | |
| "mean_token_accuracy": 0.8393888825178146, | |
| "num_tokens": 55255297.0, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 0.6129231591429096, | |
| "grad_norm": 3.484375, | |
| "learning_rate": 6.5461280100105266e-06, | |
| "loss": 0.4904, | |
| "mean_token_accuracy": 0.8448991054296493, | |
| "num_tokens": 55403332.0, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 0.6145932494947977, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 6.49685413771252e-06, | |
| "loss": 0.4825, | |
| "mean_token_accuracy": 0.8474397557973862, | |
| "num_tokens": 55546985.0, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 0.6162633398466857, | |
| "grad_norm": 4.0390625, | |
| "learning_rate": 6.447677027064627e-06, | |
| "loss": 0.5273, | |
| "mean_token_accuracy": 0.8365333503484726, | |
| "num_tokens": 55691026.0, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 0.6179334301985737, | |
| "grad_norm": 3.052734375, | |
| "learning_rate": 6.398598036405479e-06, | |
| "loss": 0.4843, | |
| "mean_token_accuracy": 0.8466820430755615, | |
| "num_tokens": 55843632.0, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.6196035205504618, | |
| "grad_norm": 3.517578125, | |
| "learning_rate": 6.349618521363517e-06, | |
| "loss": 0.5121, | |
| "mean_token_accuracy": 0.8395395117998123, | |
| "num_tokens": 55997557.0, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 0.6212736109023498, | |
| "grad_norm": 4.0703125, | |
| "learning_rate": 6.300739834819511e-06, | |
| "loss": 0.4891, | |
| "mean_token_accuracy": 0.8449855887889862, | |
| "num_tokens": 56152352.0, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 0.6229437012542378, | |
| "grad_norm": 3.16015625, | |
| "learning_rate": 6.251963326869217e-06, | |
| "loss": 0.4976, | |
| "mean_token_accuracy": 0.8433358126878738, | |
| "num_tokens": 56307858.0, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 0.6246137916061258, | |
| "grad_norm": 3.46484375, | |
| "learning_rate": 6.2032903447860805e-06, | |
| "loss": 0.5087, | |
| "mean_token_accuracy": 0.8407702177762986, | |
| "num_tokens": 56462929.0, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 0.6262838819580139, | |
| "grad_norm": 3.904296875, | |
| "learning_rate": 6.154722232984027e-06, | |
| "loss": 0.4914, | |
| "mean_token_accuracy": 0.8438418072462082, | |
| "num_tokens": 56612262.0, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 0.627953972309902, | |
| "grad_norm": 3.3671875, | |
| "learning_rate": 6.1062603329803136e-06, | |
| "loss": 0.5065, | |
| "mean_token_accuracy": 0.8423253172636032, | |
| "num_tokens": 56759791.0, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 0.62962406266179, | |
| "grad_norm": 3.3125, | |
| "learning_rate": 6.057905983358483e-06, | |
| "loss": 0.512, | |
| "mean_token_accuracy": 0.8387475430965423, | |
| "num_tokens": 56916536.0, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 0.6312941530136781, | |
| "grad_norm": 3.439453125, | |
| "learning_rate": 6.009660519731404e-06, | |
| "loss": 0.5227, | |
| "mean_token_accuracy": 0.8364591300487518, | |
| "num_tokens": 57064092.0, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 0.6329642433655661, | |
| "grad_norm": 3.529296875, | |
| "learning_rate": 5.9615252747043464e-06, | |
| "loss": 0.4801, | |
| "mean_token_accuracy": 0.8485021156072616, | |
| "num_tokens": 57217258.0, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 0.6346343337174541, | |
| "grad_norm": 3.330078125, | |
| "learning_rate": 5.913501577838209e-06, | |
| "loss": 0.4792, | |
| "mean_token_accuracy": 0.8483067131042481, | |
| "num_tokens": 57365074.0, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.6363044240693422, | |
| "grad_norm": 3.900390625, | |
| "learning_rate": 5.865590755612765e-06, | |
| "loss": 0.4919, | |
| "mean_token_accuracy": 0.8429829436540603, | |
| "num_tokens": 57518605.0, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 0.6379745144212302, | |
| "grad_norm": 2.84375, | |
| "learning_rate": 5.817794131390048e-06, | |
| "loss": 0.5133, | |
| "mean_token_accuracy": 0.8389324611425399, | |
| "num_tokens": 57673009.0, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 0.6396446047731182, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 5.7701130253777845e-06, | |
| "loss": 0.495, | |
| "mean_token_accuracy": 0.8427667218446732, | |
| "num_tokens": 57814817.0, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 0.6413146951250063, | |
| "grad_norm": 3.125, | |
| "learning_rate": 5.722548754592929e-06, | |
| "loss": 0.4862, | |
| "mean_token_accuracy": 0.8466757655143737, | |
| "num_tokens": 57968336.0, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 0.6429847854768943, | |
| "grad_norm": 3.6484375, | |
| "learning_rate": 5.675102632825282e-06, | |
| "loss": 0.4677, | |
| "mean_token_accuracy": 0.8494550919532776, | |
| "num_tokens": 58122804.0, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 0.6446548758287823, | |
| "grad_norm": 3.56640625, | |
| "learning_rate": 5.627775970601226e-06, | |
| "loss": 0.4954, | |
| "mean_token_accuracy": 0.8431641709804535, | |
| "num_tokens": 58272832.0, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 0.6463249661806704, | |
| "grad_norm": 3.50390625, | |
| "learning_rate": 5.580570075147487e-06, | |
| "loss": 0.4897, | |
| "mean_token_accuracy": 0.8479071563482284, | |
| "num_tokens": 58432958.0, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 0.6479950565325584, | |
| "grad_norm": 3.328125, | |
| "learning_rate": 5.533486250355065e-06, | |
| "loss": 0.4864, | |
| "mean_token_accuracy": 0.8480485719442368, | |
| "num_tokens": 58589348.0, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 0.6496651468844464, | |
| "grad_norm": 3.3203125, | |
| "learning_rate": 5.486525796743191e-06, | |
| "loss": 0.5059, | |
| "mean_token_accuracy": 0.8420396673679352, | |
| "num_tokens": 58739224.0, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 0.6513352372363345, | |
| "grad_norm": 5.3359375, | |
| "learning_rate": 5.439690011423427e-06, | |
| "loss": 0.4825, | |
| "mean_token_accuracy": 0.8476492571830749, | |
| "num_tokens": 58885946.0, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.6530053275882225, | |
| "grad_norm": 3.228515625, | |
| "learning_rate": 5.392980188063818e-06, | |
| "loss": 0.4941, | |
| "mean_token_accuracy": 0.8443203908205033, | |
| "num_tokens": 59035587.0, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 0.6546754179401105, | |
| "grad_norm": 3.287109375, | |
| "learning_rate": 5.346397616853171e-06, | |
| "loss": 0.4949, | |
| "mean_token_accuracy": 0.8428336310386658, | |
| "num_tokens": 59185407.0, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 0.6563455082919986, | |
| "grad_norm": 3.248046875, | |
| "learning_rate": 5.299943584465418e-06, | |
| "loss": 0.503, | |
| "mean_token_accuracy": 0.8430741858482361, | |
| "num_tokens": 59338306.0, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 0.6580155986438866, | |
| "grad_norm": 3.876953125, | |
| "learning_rate": 5.253619374024077e-06, | |
| "loss": 0.5053, | |
| "mean_token_accuracy": 0.8425169682502747, | |
| "num_tokens": 59486735.0, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 0.6596856889957746, | |
| "grad_norm": 3.39453125, | |
| "learning_rate": 5.2074262650668e-06, | |
| "loss": 0.5052, | |
| "mean_token_accuracy": 0.8416625607013702, | |
| "num_tokens": 59644149.0, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 0.6613557793476627, | |
| "grad_norm": 3.849609375, | |
| "learning_rate": 5.161365533510036e-06, | |
| "loss": 0.4987, | |
| "mean_token_accuracy": 0.8422721582651138, | |
| "num_tokens": 59802799.0, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 0.6630258696995508, | |
| "grad_norm": 3.169921875, | |
| "learning_rate": 5.115438451613806e-06, | |
| "loss": 0.4898, | |
| "mean_token_accuracy": 0.8450227230787277, | |
| "num_tokens": 59952454.0, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 0.6646959600514388, | |
| "grad_norm": 3.05078125, | |
| "learning_rate": 5.0696462879465225e-06, | |
| "loss": 0.4923, | |
| "mean_token_accuracy": 0.8432435488700867, | |
| "num_tokens": 60100348.0, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 0.6663660504033269, | |
| "grad_norm": 2.826171875, | |
| "learning_rate": 5.023990307349998e-06, | |
| "loss": 0.4962, | |
| "mean_token_accuracy": 0.8441808766126633, | |
| "num_tokens": 60254096.0, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 0.6680361407552149, | |
| "grad_norm": 3.048828125, | |
| "learning_rate": 4.978471770904461e-06, | |
| "loss": 0.5138, | |
| "mean_token_accuracy": 0.8379841154813766, | |
| "num_tokens": 60405878.0, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.6697062311071029, | |
| "grad_norm": 3.482421875, | |
| "learning_rate": 4.933091935893763e-06, | |
| "loss": 0.5085, | |
| "mean_token_accuracy": 0.8400601810216903, | |
| "num_tokens": 60559754.0, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 0.671376321458991, | |
| "grad_norm": 3.673828125, | |
| "learning_rate": 4.887852055770625e-06, | |
| "loss": 0.5084, | |
| "mean_token_accuracy": 0.8403496730327606, | |
| "num_tokens": 60706233.0, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 0.673046411810879, | |
| "grad_norm": 3.439453125, | |
| "learning_rate": 4.842753380122024e-06, | |
| "loss": 0.4708, | |
| "mean_token_accuracy": 0.8510260754823684, | |
| "num_tokens": 60853416.0, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 0.674716502162767, | |
| "grad_norm": 3.912109375, | |
| "learning_rate": 4.797797154634674e-06, | |
| "loss": 0.4812, | |
| "mean_token_accuracy": 0.8473618775606155, | |
| "num_tokens": 61001132.0, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 0.676386592514655, | |
| "grad_norm": 3.30078125, | |
| "learning_rate": 4.75298462106063e-06, | |
| "loss": 0.4864, | |
| "mean_token_accuracy": 0.8453113460540771, | |
| "num_tokens": 61150647.0, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 0.6780566828665431, | |
| "grad_norm": 3.3984375, | |
| "learning_rate": 4.7083170171829825e-06, | |
| "loss": 0.4691, | |
| "mean_token_accuracy": 0.8507994741201401, | |
| "num_tokens": 61299229.0, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 0.6797267732184311, | |
| "grad_norm": 3.578125, | |
| "learning_rate": 4.663795576781657e-06, | |
| "loss": 0.4971, | |
| "mean_token_accuracy": 0.8436929321289063, | |
| "num_tokens": 61454266.0, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 0.6813968635703191, | |
| "grad_norm": 3.240234375, | |
| "learning_rate": 4.619421529599347e-06, | |
| "loss": 0.4897, | |
| "mean_token_accuracy": 0.8451752752065659, | |
| "num_tokens": 61609305.0, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 0.6830669539222072, | |
| "grad_norm": 3.427734375, | |
| "learning_rate": 4.575196101307554e-06, | |
| "loss": 0.4905, | |
| "mean_token_accuracy": 0.8451364821195603, | |
| "num_tokens": 61761298.0, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 0.6847370442740952, | |
| "grad_norm": 3.119140625, | |
| "learning_rate": 4.531120513472712e-06, | |
| "loss": 0.4882, | |
| "mean_token_accuracy": 0.8447253012657165, | |
| "num_tokens": 61921258.0, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.6864071346259832, | |
| "grad_norm": 2.9921875, | |
| "learning_rate": 4.48719598352247e-06, | |
| "loss": 0.4634, | |
| "mean_token_accuracy": 0.8520550775527954, | |
| "num_tokens": 62073444.0, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 0.6880772249778713, | |
| "grad_norm": 2.982421875, | |
| "learning_rate": 4.443423724712039e-06, | |
| "loss": 0.4704, | |
| "mean_token_accuracy": 0.8503249382972717, | |
| "num_tokens": 62229096.0, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 0.6897473153297593, | |
| "grad_norm": 3.7421875, | |
| "learning_rate": 4.39980494609071e-06, | |
| "loss": 0.4939, | |
| "mean_token_accuracy": 0.8424547004699707, | |
| "num_tokens": 62378734.0, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 0.6914174056816473, | |
| "grad_norm": 4.4453125, | |
| "learning_rate": 4.356340852468429e-06, | |
| "loss": 0.4862, | |
| "mean_token_accuracy": 0.8453142333030701, | |
| "num_tokens": 62529417.0, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 0.6930874960335354, | |
| "grad_norm": 3.478515625, | |
| "learning_rate": 4.313032644382534e-06, | |
| "loss": 0.4894, | |
| "mean_token_accuracy": 0.8457726097106933, | |
| "num_tokens": 62677430.0, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 0.6947575863854234, | |
| "grad_norm": 3.05078125, | |
| "learning_rate": 4.2698815180646e-06, | |
| "loss": 0.4887, | |
| "mean_token_accuracy": 0.8468521314859391, | |
| "num_tokens": 62826175.0, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 0.6964276767373115, | |
| "grad_norm": 2.701171875, | |
| "learning_rate": 4.226888665407391e-06, | |
| "loss": 0.4816, | |
| "mean_token_accuracy": 0.849350945353508, | |
| "num_tokens": 62975966.0, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 0.6980977670891996, | |
| "grad_norm": 3.328125, | |
| "learning_rate": 4.184055273931925e-06, | |
| "loss": 0.5043, | |
| "mean_token_accuracy": 0.8405849385261536, | |
| "num_tokens": 63124686.0, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 0.6997678574410876, | |
| "grad_norm": 3.630859375, | |
| "learning_rate": 4.141382526754691e-06, | |
| "loss": 0.4919, | |
| "mean_token_accuracy": 0.8457988566160202, | |
| "num_tokens": 63278909.0, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 0.7014379477929756, | |
| "grad_norm": 3.173828125, | |
| "learning_rate": 4.098871602554974e-06, | |
| "loss": 0.4964, | |
| "mean_token_accuracy": 0.8428309279680252, | |
| "num_tokens": 63431791.0, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.7031080381448637, | |
| "grad_norm": 3.3203125, | |
| "learning_rate": 4.056523675542277e-06, | |
| "loss": 0.4813, | |
| "mean_token_accuracy": 0.8467002534866332, | |
| "num_tokens": 63582219.0, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 0.7047781284967517, | |
| "grad_norm": 4.9140625, | |
| "learning_rate": 4.0143399154238975e-06, | |
| "loss": 0.4949, | |
| "mean_token_accuracy": 0.843778178691864, | |
| "num_tokens": 63735135.0, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 0.7064482188486397, | |
| "grad_norm": 3.5078125, | |
| "learning_rate": 3.972321487372628e-06, | |
| "loss": 0.4903, | |
| "mean_token_accuracy": 0.8455115538835526, | |
| "num_tokens": 63885628.0, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 0.7081183092005278, | |
| "grad_norm": 3.701171875, | |
| "learning_rate": 3.930469551994567e-06, | |
| "loss": 0.4873, | |
| "mean_token_accuracy": 0.8451563888788223, | |
| "num_tokens": 64037663.0, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 0.7097883995524158, | |
| "grad_norm": 3.3671875, | |
| "learning_rate": 3.88878526529705e-06, | |
| "loss": 0.4804, | |
| "mean_token_accuracy": 0.8490526312589646, | |
| "num_tokens": 64189564.0, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 0.7114584899043038, | |
| "grad_norm": 4.0859375, | |
| "learning_rate": 3.847269778656732e-06, | |
| "loss": 0.504, | |
| "mean_token_accuracy": 0.8420998674631118, | |
| "num_tokens": 64344059.0, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 0.7131285802561919, | |
| "grad_norm": 3.37109375, | |
| "learning_rate": 3.805924238787777e-06, | |
| "loss": 0.4815, | |
| "mean_token_accuracy": 0.8460740214586258, | |
| "num_tokens": 64491912.0, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 0.7147986706080799, | |
| "grad_norm": 6.3671875, | |
| "learning_rate": 3.7647497877101956e-06, | |
| "loss": 0.4915, | |
| "mean_token_accuracy": 0.8465023702383041, | |
| "num_tokens": 64643358.0, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 0.7164687609599679, | |
| "grad_norm": 3.578125, | |
| "learning_rate": 3.723747562718293e-06, | |
| "loss": 0.4834, | |
| "mean_token_accuracy": 0.8463284826278686, | |
| "num_tokens": 64800624.0, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 0.718138851311856, | |
| "grad_norm": 3.1484375, | |
| "learning_rate": 3.6829186963492503e-06, | |
| "loss": 0.4912, | |
| "mean_token_accuracy": 0.8451859301328659, | |
| "num_tokens": 64955760.0, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.719808941663744, | |
| "grad_norm": 3.443359375, | |
| "learning_rate": 3.642264316351847e-06, | |
| "loss": 0.4831, | |
| "mean_token_accuracy": 0.8466964775323867, | |
| "num_tokens": 65107173.0, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 0.721479032015632, | |
| "grad_norm": 2.876953125, | |
| "learning_rate": 3.601785545655321e-06, | |
| "loss": 0.4831, | |
| "mean_token_accuracy": 0.8477119094133377, | |
| "num_tokens": 65255564.0, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 0.72314912236752, | |
| "grad_norm": 3.0703125, | |
| "learning_rate": 3.561483502338333e-06, | |
| "loss": 0.4879, | |
| "mean_token_accuracy": 0.8454282933473587, | |
| "num_tokens": 65404541.0, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 0.7248192127194081, | |
| "grad_norm": 3.33984375, | |
| "learning_rate": 3.521359299598096e-06, | |
| "loss": 0.4812, | |
| "mean_token_accuracy": 0.8468845194578171, | |
| "num_tokens": 65557174.0, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 0.7264893030712961, | |
| "grad_norm": 3.111328125, | |
| "learning_rate": 3.4814140457196268e-06, | |
| "loss": 0.4701, | |
| "mean_token_accuracy": 0.8508721369504929, | |
| "num_tokens": 65708106.0, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 0.7281593934231841, | |
| "grad_norm": 4.52734375, | |
| "learning_rate": 3.4416488440451333e-06, | |
| "loss": 0.5035, | |
| "mean_token_accuracy": 0.8433184975385666, | |
| "num_tokens": 65861136.0, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 0.7298294837750723, | |
| "grad_norm": 4.35546875, | |
| "learning_rate": 3.4020647929435326e-06, | |
| "loss": 0.4679, | |
| "mean_token_accuracy": 0.8526981258392334, | |
| "num_tokens": 66009000.0, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 0.7314995741269603, | |
| "grad_norm": 3.396484375, | |
| "learning_rate": 3.3626629857801164e-06, | |
| "loss": 0.4888, | |
| "mean_token_accuracy": 0.8452479732036591, | |
| "num_tokens": 66159610.0, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 0.7331696644788483, | |
| "grad_norm": 2.798828125, | |
| "learning_rate": 3.323444510886349e-06, | |
| "loss": 0.5022, | |
| "mean_token_accuracy": 0.8416718345880508, | |
| "num_tokens": 66315128.0, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 0.7348397548307364, | |
| "grad_norm": 3.212890625, | |
| "learning_rate": 3.284410451529816e-06, | |
| "loss": 0.481, | |
| "mean_token_accuracy": 0.8480905383825302, | |
| "num_tokens": 66468814.0, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.7365098451826244, | |
| "grad_norm": 3.55859375, | |
| "learning_rate": 3.245561885884293e-06, | |
| "loss": 0.4854, | |
| "mean_token_accuracy": 0.8432433831691742, | |
| "num_tokens": 66613155.0, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 0.7381799355345124, | |
| "grad_norm": 3.111328125, | |
| "learning_rate": 3.2068998869999613e-06, | |
| "loss": 0.4742, | |
| "mean_token_accuracy": 0.8501115536689758, | |
| "num_tokens": 66766673.0, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 0.7398500258864005, | |
| "grad_norm": 3.564453125, | |
| "learning_rate": 3.1684255227737824e-06, | |
| "loss": 0.4964, | |
| "mean_token_accuracy": 0.8437844455242157, | |
| "num_tokens": 66917613.0, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 0.7415201162382885, | |
| "grad_norm": 5.51171875, | |
| "learning_rate": 3.130139855919988e-06, | |
| "loss": 0.4788, | |
| "mean_token_accuracy": 0.8494738894701004, | |
| "num_tokens": 67064166.0, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 0.7431902065901765, | |
| "grad_norm": 2.904296875, | |
| "learning_rate": 3.0920439439407292e-06, | |
| "loss": 0.4813, | |
| "mean_token_accuracy": 0.8486757451295852, | |
| "num_tokens": 67215706.0, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 0.7448602969420646, | |
| "grad_norm": 2.751953125, | |
| "learning_rate": 3.0541388390968786e-06, | |
| "loss": 0.4941, | |
| "mean_token_accuracy": 0.8425833195447922, | |
| "num_tokens": 67363559.0, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 0.7465303872939526, | |
| "grad_norm": 3.943359375, | |
| "learning_rate": 3.0164255883789538e-06, | |
| "loss": 0.495, | |
| "mean_token_accuracy": 0.8441985923051835, | |
| "num_tokens": 67513806.0, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 0.7482004776458406, | |
| "grad_norm": 2.908203125, | |
| "learning_rate": 2.9789052334781965e-06, | |
| "loss": 0.4795, | |
| "mean_token_accuracy": 0.8471468478441239, | |
| "num_tokens": 67660583.0, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 0.7498705679977287, | |
| "grad_norm": 3.40234375, | |
| "learning_rate": 2.9415788107578047e-06, | |
| "loss": 0.4875, | |
| "mean_token_accuracy": 0.8455528634786605, | |
| "num_tokens": 67812517.0, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 0.7515406583496167, | |
| "grad_norm": 3.779296875, | |
| "learning_rate": 2.9044473512243054e-06, | |
| "loss": 0.4977, | |
| "mean_token_accuracy": 0.8441984283924103, | |
| "num_tokens": 67963181.0, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.7532107487015047, | |
| "grad_norm": 3.232421875, | |
| "learning_rate": 2.867511880499084e-06, | |
| "loss": 0.4908, | |
| "mean_token_accuracy": 0.8454032260179519, | |
| "num_tokens": 68109761.0, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 0.7548808390533928, | |
| "grad_norm": 3.146484375, | |
| "learning_rate": 2.830773418790038e-06, | |
| "loss": 0.4873, | |
| "mean_token_accuracy": 0.8482973438501358, | |
| "num_tokens": 68247832.0, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 0.7565509294052808, | |
| "grad_norm": 3.091796875, | |
| "learning_rate": 2.7942329808634206e-06, | |
| "loss": 0.5103, | |
| "mean_token_accuracy": 0.8390360820293427, | |
| "num_tokens": 68399556.0, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 0.7582210197571688, | |
| "grad_norm": 3.48046875, | |
| "learning_rate": 2.7578915760157864e-06, | |
| "loss": 0.474, | |
| "mean_token_accuracy": 0.8499324053525925, | |
| "num_tokens": 68550332.0, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 0.7598911101090569, | |
| "grad_norm": 3.513671875, | |
| "learning_rate": 2.7217502080461368e-06, | |
| "loss": 0.4824, | |
| "mean_token_accuracy": 0.8491689574718475, | |
| "num_tokens": 68705059.0, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 0.7615612004609449, | |
| "grad_norm": 3.12890625, | |
| "learning_rate": 2.685809875228176e-06, | |
| "loss": 0.5044, | |
| "mean_token_accuracy": 0.8416903901100159, | |
| "num_tokens": 68860328.0, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 0.763231290812833, | |
| "grad_norm": 4.3046875, | |
| "learning_rate": 2.6500715702827407e-06, | |
| "loss": 0.4909, | |
| "mean_token_accuracy": 0.8453281289339065, | |
| "num_tokens": 69018858.0, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 0.7649013811647211, | |
| "grad_norm": 3.15625, | |
| "learning_rate": 2.6145362803503926e-06, | |
| "loss": 0.4942, | |
| "mean_token_accuracy": 0.8447019332647323, | |
| "num_tokens": 69165665.0, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 0.7665714715166091, | |
| "grad_norm": 4.1171875, | |
| "learning_rate": 2.579204986964141e-06, | |
| "loss": 0.4812, | |
| "mean_token_accuracy": 0.8473155897855759, | |
| "num_tokens": 69311704.0, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 0.7682415618684971, | |
| "grad_norm": 4.05859375, | |
| "learning_rate": 2.544078666022328e-06, | |
| "loss": 0.4956, | |
| "mean_token_accuracy": 0.844502074122429, | |
| "num_tokens": 69463894.0, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.7699116522203852, | |
| "grad_norm": 3.2734375, | |
| "learning_rate": 2.5091582877616804e-06, | |
| "loss": 0.498, | |
| "mean_token_accuracy": 0.8427008324861527, | |
| "num_tokens": 69613564.0, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 0.7715817425722732, | |
| "grad_norm": 3.283203125, | |
| "learning_rate": 2.474444816730507e-06, | |
| "loss": 0.4792, | |
| "mean_token_accuracy": 0.847426295876503, | |
| "num_tokens": 69761845.0, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 0.7732518329241612, | |
| "grad_norm": 3.4140625, | |
| "learning_rate": 2.4399392117620613e-06, | |
| "loss": 0.4963, | |
| "mean_token_accuracy": 0.8438633060455323, | |
| "num_tokens": 69908752.0, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 0.7749219232760493, | |
| "grad_norm": 3.693359375, | |
| "learning_rate": 2.4056424259480547e-06, | |
| "loss": 0.4925, | |
| "mean_token_accuracy": 0.8448504638671875, | |
| "num_tokens": 70062257.0, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 0.7765920136279373, | |
| "grad_norm": 3.115234375, | |
| "learning_rate": 2.3715554066123215e-06, | |
| "loss": 0.4822, | |
| "mean_token_accuracy": 0.8483648711442947, | |
| "num_tokens": 70211575.0, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 0.7782621039798253, | |
| "grad_norm": 3.44140625, | |
| "learning_rate": 2.3376790952846706e-06, | |
| "loss": 0.4771, | |
| "mean_token_accuracy": 0.8487663650512696, | |
| "num_tokens": 70363136.0, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 0.7799321943317133, | |
| "grad_norm": 2.814453125, | |
| "learning_rate": 2.3040144276748644e-06, | |
| "loss": 0.4913, | |
| "mean_token_accuracy": 0.8446182125806808, | |
| "num_tokens": 70516885.0, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 0.7816022846836014, | |
| "grad_norm": 3.951171875, | |
| "learning_rate": 2.2705623336467765e-06, | |
| "loss": 0.4962, | |
| "mean_token_accuracy": 0.842961351275444, | |
| "num_tokens": 70669970.0, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 0.7832723750354894, | |
| "grad_norm": 3.759765625, | |
| "learning_rate": 2.237323737192709e-06, | |
| "loss": 0.489, | |
| "mean_token_accuracy": 0.8459052920341492, | |
| "num_tokens": 70821194.0, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 0.7849424653873774, | |
| "grad_norm": 3.359375, | |
| "learning_rate": 2.2042995564078763e-06, | |
| "loss": 0.4764, | |
| "mean_token_accuracy": 0.8495719933509827, | |
| "num_tokens": 70972600.0, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.7866125557392655, | |
| "grad_norm": 3.599609375, | |
| "learning_rate": 2.171490703465039e-06, | |
| "loss": 0.4775, | |
| "mean_token_accuracy": 0.8484279763698578, | |
| "num_tokens": 71125360.0, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 0.7882826460911535, | |
| "grad_norm": 3.01171875, | |
| "learning_rate": 2.138898084589307e-06, | |
| "loss": 0.4638, | |
| "mean_token_accuracy": 0.8524714910984039, | |
| "num_tokens": 71277634.0, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 0.7899527364430415, | |
| "grad_norm": 3.251953125, | |
| "learning_rate": 2.1065226000331096e-06, | |
| "loss": 0.4707, | |
| "mean_token_accuracy": 0.8515409278869629, | |
| "num_tokens": 71429025.0, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 0.7916228267949296, | |
| "grad_norm": 3.69140625, | |
| "learning_rate": 2.07436514405134e-06, | |
| "loss": 0.4864, | |
| "mean_token_accuracy": 0.8450417071580887, | |
| "num_tokens": 71580872.0, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 0.7932929171468176, | |
| "grad_norm": 3.24609375, | |
| "learning_rate": 2.042426604876634e-06, | |
| "loss": 0.4727, | |
| "mean_token_accuracy": 0.8491108435392379, | |
| "num_tokens": 71730410.0, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 0.7949630074987056, | |
| "grad_norm": 2.900390625, | |
| "learning_rate": 2.0107078646948595e-06, | |
| "loss": 0.4952, | |
| "mean_token_accuracy": 0.8437976878881455, | |
| "num_tokens": 71881773.0, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 0.7966330978505937, | |
| "grad_norm": 3.27734375, | |
| "learning_rate": 1.979209799620727e-06, | |
| "loss": 0.4937, | |
| "mean_token_accuracy": 0.8433756965398789, | |
| "num_tokens": 72043896.0, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 0.7983031882024818, | |
| "grad_norm": 3.583984375, | |
| "learning_rate": 1.9479332796736094e-06, | |
| "loss": 0.502, | |
| "mean_token_accuracy": 0.8438859677314758, | |
| "num_tokens": 72191942.0, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 0.7999732785543698, | |
| "grad_norm": 3.583984375, | |
| "learning_rate": 1.9168791687534973e-06, | |
| "loss": 0.4779, | |
| "mean_token_accuracy": 0.8502110910415649, | |
| "num_tokens": 72343315.0, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 0.8016433689062579, | |
| "grad_norm": 3.693359375, | |
| "learning_rate": 1.886048324617139e-06, | |
| "loss": 0.4964, | |
| "mean_token_accuracy": 0.8427167356014251, | |
| "num_tokens": 72499358.0, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.8033134592581459, | |
| "grad_norm": 3.484375, | |
| "learning_rate": 1.855441598854355e-06, | |
| "loss": 0.4879, | |
| "mean_token_accuracy": 0.8462699401378632, | |
| "num_tokens": 72650001.0, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 0.8049835496100339, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 1.8250598368645122e-06, | |
| "loss": 0.4976, | |
| "mean_token_accuracy": 0.8434474515914917, | |
| "num_tokens": 72796837.0, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 0.806653639961922, | |
| "grad_norm": 3.333984375, | |
| "learning_rate": 1.7949038778331729e-06, | |
| "loss": 0.4983, | |
| "mean_token_accuracy": 0.8429196667671204, | |
| "num_tokens": 72948156.0, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 0.80832373031381, | |
| "grad_norm": 3.0859375, | |
| "learning_rate": 1.7649745547089103e-06, | |
| "loss": 0.4884, | |
| "mean_token_accuracy": 0.8464457362890243, | |
| "num_tokens": 73098490.0, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 0.809993820665698, | |
| "grad_norm": 3.3046875, | |
| "learning_rate": 1.7352726941803066e-06, | |
| "loss": 0.4893, | |
| "mean_token_accuracy": 0.8473053193092346, | |
| "num_tokens": 73252835.0, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 0.8116639110175861, | |
| "grad_norm": 3.74609375, | |
| "learning_rate": 1.705799116653124e-06, | |
| "loss": 0.4966, | |
| "mean_token_accuracy": 0.8456600403785706, | |
| "num_tokens": 73402697.0, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 0.8133340013694741, | |
| "grad_norm": 3.46875, | |
| "learning_rate": 1.6765546362276297e-06, | |
| "loss": 0.4928, | |
| "mean_token_accuracy": 0.8445676666498184, | |
| "num_tokens": 73557739.0, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 0.8150040917213621, | |
| "grad_norm": 3.154296875, | |
| "learning_rate": 1.6475400606761239e-06, | |
| "loss": 0.484, | |
| "mean_token_accuracy": 0.8451971143484116, | |
| "num_tokens": 73708132.0, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 0.8166741820732502, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 1.6187561914206208e-06, | |
| "loss": 0.4754, | |
| "mean_token_accuracy": 0.8489796489477157, | |
| "num_tokens": 73859714.0, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 0.8183442724251382, | |
| "grad_norm": 3.380859375, | |
| "learning_rate": 1.5902038235107086e-06, | |
| "loss": 0.4812, | |
| "mean_token_accuracy": 0.8480531734228134, | |
| "num_tokens": 74016829.0, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.8200143627770262, | |
| "grad_norm": 2.998046875, | |
| "learning_rate": 1.5618837456015978e-06, | |
| "loss": 0.4962, | |
| "mean_token_accuracy": 0.8424737280607224, | |
| "num_tokens": 74168520.0, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 0.8216844531289142, | |
| "grad_norm": 3.99609375, | |
| "learning_rate": 1.5337967399323306e-06, | |
| "loss": 0.4987, | |
| "mean_token_accuracy": 0.8446889609098435, | |
| "num_tokens": 74319133.0, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 0.8233545434808023, | |
| "grad_norm": 3.466796875, | |
| "learning_rate": 1.50594358230418e-06, | |
| "loss": 0.4991, | |
| "mean_token_accuracy": 0.8431148356199265, | |
| "num_tokens": 74465171.0, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 0.8250246338326903, | |
| "grad_norm": 3.326171875, | |
| "learning_rate": 1.47832504205922e-06, | |
| "loss": 0.4697, | |
| "mean_token_accuracy": 0.8510027927160263, | |
| "num_tokens": 74617993.0, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 0.8266947241845783, | |
| "grad_norm": 3.359375, | |
| "learning_rate": 1.450941882059068e-06, | |
| "loss": 0.4874, | |
| "mean_token_accuracy": 0.8466904902458191, | |
| "num_tokens": 74761326.0, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 0.8283648145364664, | |
| "grad_norm": 2.76171875, | |
| "learning_rate": 1.4237948586638195e-06, | |
| "loss": 0.4881, | |
| "mean_token_accuracy": 0.8453599536418914, | |
| "num_tokens": 74912565.0, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 0.8300349048883544, | |
| "grad_norm": 2.697265625, | |
| "learning_rate": 1.3968847217111626e-06, | |
| "loss": 0.4784, | |
| "mean_token_accuracy": 0.8479279518127442, | |
| "num_tokens": 75068424.0, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 0.8317049952402426, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 1.3702122144956543e-06, | |
| "loss": 0.4947, | |
| "mean_token_accuracy": 0.8452018421888351, | |
| "num_tokens": 75214301.0, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 0.8333750855921306, | |
| "grad_norm": 2.861328125, | |
| "learning_rate": 1.3437780737481932e-06, | |
| "loss": 0.4871, | |
| "mean_token_accuracy": 0.8459746861457824, | |
| "num_tokens": 75364779.0, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 0.8350451759440186, | |
| "grad_norm": 2.9296875, | |
| "learning_rate": 1.3175830296156789e-06, | |
| "loss": 0.491, | |
| "mean_token_accuracy": 0.8458395266532898, | |
| "num_tokens": 75515083.0, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.8367152662959066, | |
| "grad_norm": 4.07421875, | |
| "learning_rate": 1.2916278056408349e-06, | |
| "loss": 0.4812, | |
| "mean_token_accuracy": 0.8470104867219925, | |
| "num_tokens": 75666975.0, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 0.8383853566477947, | |
| "grad_norm": 3.619140625, | |
| "learning_rate": 1.2659131187422236e-06, | |
| "loss": 0.4944, | |
| "mean_token_accuracy": 0.8450325924158096, | |
| "num_tokens": 75820014.0, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 0.8400554469996827, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 1.2404396791944473e-06, | |
| "loss": 0.4977, | |
| "mean_token_accuracy": 0.8447578704357147, | |
| "num_tokens": 75963775.0, | |
| "step": 25150 | |
| }, | |
| { | |
| "epoch": 0.8417255373515707, | |
| "grad_norm": 2.6953125, | |
| "learning_rate": 1.2152081906085289e-06, | |
| "loss": 0.4857, | |
| "mean_token_accuracy": 0.8468400800228119, | |
| "num_tokens": 76117956.0, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 0.8433956277034588, | |
| "grad_norm": 3.158203125, | |
| "learning_rate": 1.190219349912477e-06, | |
| "loss": 0.4916, | |
| "mean_token_accuracy": 0.8440502685308456, | |
| "num_tokens": 76258129.0, | |
| "step": 25250 | |
| }, | |
| { | |
| "epoch": 0.8450657180553468, | |
| "grad_norm": 3.5078125, | |
| "learning_rate": 1.1654738473320403e-06, | |
| "loss": 0.4769, | |
| "mean_token_accuracy": 0.8501708889007569, | |
| "num_tokens": 76405459.0, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 0.8467358084072348, | |
| "grad_norm": 3.970703125, | |
| "learning_rate": 1.1409723663716278e-06, | |
| "loss": 0.4855, | |
| "mean_token_accuracy": 0.8484237200021744, | |
| "num_tokens": 76548091.0, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 0.8484058987591229, | |
| "grad_norm": 3.904296875, | |
| "learning_rate": 1.1167155837954503e-06, | |
| "loss": 0.4833, | |
| "mean_token_accuracy": 0.8471252977848053, | |
| "num_tokens": 76699837.0, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 0.8500759891110109, | |
| "grad_norm": 2.97265625, | |
| "learning_rate": 1.0927041696088104e-06, | |
| "loss": 0.4728, | |
| "mean_token_accuracy": 0.8495503830909729, | |
| "num_tokens": 76857343.0, | |
| "step": 25450 | |
| }, | |
| { | |
| "epoch": 0.8517460794628989, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 1.0689387870396018e-06, | |
| "loss": 0.4808, | |
| "mean_token_accuracy": 0.8465770441293716, | |
| "num_tokens": 77009589.0, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.853416169814787, | |
| "grad_norm": 3.865234375, | |
| "learning_rate": 1.0454200925199897e-06, | |
| "loss": 0.5122, | |
| "mean_token_accuracy": 0.8390571755170823, | |
| "num_tokens": 77155606.0, | |
| "step": 25550 | |
| }, | |
| { | |
| "epoch": 0.855086260166675, | |
| "grad_norm": 3.19140625, | |
| "learning_rate": 1.0221487356682901e-06, | |
| "loss": 0.4905, | |
| "mean_token_accuracy": 0.8453446280956268, | |
| "num_tokens": 77299713.0, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 0.856756350518563, | |
| "grad_norm": 3.412109375, | |
| "learning_rate": 9.99125359271007e-07, | |
| "loss": 0.4729, | |
| "mean_token_accuracy": 0.8484119319915772, | |
| "num_tokens": 77452443.0, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 0.8584264408704511, | |
| "grad_norm": 3.193359375, | |
| "learning_rate": 9.76350599265088e-07, | |
| "loss": 0.467, | |
| "mean_token_accuracy": 0.8510044306516648, | |
| "num_tokens": 77605507.0, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 0.8600965312223391, | |
| "grad_norm": 3.7890625, | |
| "learning_rate": 9.538250847203566e-07, | |
| "loss": 0.4884, | |
| "mean_token_accuracy": 0.8455595719814301, | |
| "num_tokens": 77755545.0, | |
| "step": 25750 | |
| }, | |
| { | |
| "epoch": 0.8617666215742271, | |
| "grad_norm": 3.52734375, | |
| "learning_rate": 9.315494378221457e-07, | |
| "loss": 0.4841, | |
| "mean_token_accuracy": 0.8470376193523407, | |
| "num_tokens": 77916521.0, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 0.8634367119261152, | |
| "grad_norm": 4.20703125, | |
| "learning_rate": 9.095242738540955e-07, | |
| "loss": 0.481, | |
| "mean_token_accuracy": 0.8469012695550918, | |
| "num_tokens": 78061502.0, | |
| "step": 25850 | |
| }, | |
| { | |
| "epoch": 0.8651068022780033, | |
| "grad_norm": 3.123046875, | |
| "learning_rate": 8.877502011811745e-07, | |
| "loss": 0.4866, | |
| "mean_token_accuracy": 0.8478066647052764, | |
| "num_tokens": 78205509.0, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 0.8667768926298913, | |
| "grad_norm": 3.39453125, | |
| "learning_rate": 8.662278212328612e-07, | |
| "loss": 0.4885, | |
| "mean_token_accuracy": 0.8462014383077622, | |
| "num_tokens": 78362012.0, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 0.8684469829817794, | |
| "grad_norm": 3.3359375, | |
| "learning_rate": 8.449577284865451e-07, | |
| "loss": 0.4794, | |
| "mean_token_accuracy": 0.8476994061470031, | |
| "num_tokens": 78513220.0, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.8701170733336674, | |
| "grad_norm": 2.5703125, | |
| "learning_rate": 8.239405104510967e-07, | |
| "loss": 0.4787, | |
| "mean_token_accuracy": 0.8499228221178055, | |
| "num_tokens": 78664236.0, | |
| "step": 26050 | |
| }, | |
| { | |
| "epoch": 0.8717871636855554, | |
| "grad_norm": 2.982421875, | |
| "learning_rate": 8.031767476506436e-07, | |
| "loss": 0.467, | |
| "mean_token_accuracy": 0.8520147293806076, | |
| "num_tokens": 78817095.0, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 0.8734572540374435, | |
| "grad_norm": 3.146484375, | |
| "learning_rate": 7.826670136085357e-07, | |
| "loss": 0.488, | |
| "mean_token_accuracy": 0.8445002466440201, | |
| "num_tokens": 78971669.0, | |
| "step": 26150 | |
| }, | |
| { | |
| "epoch": 0.8751273443893315, | |
| "grad_norm": 3.076171875, | |
| "learning_rate": 7.624118748315056e-07, | |
| "loss": 0.4796, | |
| "mean_token_accuracy": 0.8476287919282913, | |
| "num_tokens": 79120543.0, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 0.8767974347412195, | |
| "grad_norm": 3.880859375, | |
| "learning_rate": 7.42411890794017e-07, | |
| "loss": 0.4741, | |
| "mean_token_accuracy": 0.8487919306755066, | |
| "num_tokens": 79272175.0, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 0.8784675250931075, | |
| "grad_norm": 3.84765625, | |
| "learning_rate": 7.226676139228095e-07, | |
| "loss": 0.4845, | |
| "mean_token_accuracy": 0.8499467664957047, | |
| "num_tokens": 79427977.0, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 0.8801376154449956, | |
| "grad_norm": 3.013671875, | |
| "learning_rate": 7.031795895816473e-07, | |
| "loss": 0.4813, | |
| "mean_token_accuracy": 0.8485451680421829, | |
| "num_tokens": 79577717.0, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 0.8818077057968836, | |
| "grad_norm": 3.87109375, | |
| "learning_rate": 6.839483560562521e-07, | |
| "loss": 0.4928, | |
| "mean_token_accuracy": 0.8454676699638367, | |
| "num_tokens": 79731571.0, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 0.8834777961487716, | |
| "grad_norm": 3.90625, | |
| "learning_rate": 6.649744445394302e-07, | |
| "loss": 0.4829, | |
| "mean_token_accuracy": 0.8480045157670975, | |
| "num_tokens": 79886342.0, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 0.8851478865006597, | |
| "grad_norm": 4.01171875, | |
| "learning_rate": 6.462583791164079e-07, | |
| "loss": 0.5005, | |
| "mean_token_accuracy": 0.8420239347219467, | |
| "num_tokens": 80035051.0, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.8868179768525477, | |
| "grad_norm": 3.642578125, | |
| "learning_rate": 6.278006767503519e-07, | |
| "loss": 0.4893, | |
| "mean_token_accuracy": 0.8441035449504852, | |
| "num_tokens": 80187728.0, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 0.8884880672044357, | |
| "grad_norm": 3.365234375, | |
| "learning_rate": 6.096018472680876e-07, | |
| "loss": 0.4894, | |
| "mean_token_accuracy": 0.8452079063653946, | |
| "num_tokens": 80342892.0, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 0.8901581575563238, | |
| "grad_norm": 3.57421875, | |
| "learning_rate": 5.916623933460208e-07, | |
| "loss": 0.4758, | |
| "mean_token_accuracy": 0.848841341137886, | |
| "num_tokens": 80493726.0, | |
| "step": 26650 | |
| }, | |
| { | |
| "epoch": 0.8918282479082118, | |
| "grad_norm": 3.609375, | |
| "learning_rate": 5.739828104962497e-07, | |
| "loss": 0.4776, | |
| "mean_token_accuracy": 0.8501479059457779, | |
| "num_tokens": 80643884.0, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 0.8934983382600998, | |
| "grad_norm": 3.244140625, | |
| "learning_rate": 5.56563587052884e-07, | |
| "loss": 0.4685, | |
| "mean_token_accuracy": 0.849325276017189, | |
| "num_tokens": 80796586.0, | |
| "step": 26750 | |
| }, | |
| { | |
| "epoch": 0.8951684286119879, | |
| "grad_norm": 3.87890625, | |
| "learning_rate": 5.394052041585529e-07, | |
| "loss": 0.4826, | |
| "mean_token_accuracy": 0.8456845390796661, | |
| "num_tokens": 80946479.0, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 0.8968385189638759, | |
| "grad_norm": 3.68359375, | |
| "learning_rate": 5.225081357511119e-07, | |
| "loss": 0.4665, | |
| "mean_token_accuracy": 0.8520998895168305, | |
| "num_tokens": 81102046.0, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 0.8985086093157639, | |
| "grad_norm": 4.3828125, | |
| "learning_rate": 5.058728485505537e-07, | |
| "loss": 0.4866, | |
| "mean_token_accuracy": 0.8477198016643525, | |
| "num_tokens": 81248967.0, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 0.9001786996676521, | |
| "grad_norm": 2.90625, | |
| "learning_rate": 4.894998020461261e-07, | |
| "loss": 0.4824, | |
| "mean_token_accuracy": 0.8479921519756317, | |
| "num_tokens": 81391750.0, | |
| "step": 26950 | |
| }, | |
| { | |
| "epoch": 0.9018487900195401, | |
| "grad_norm": 4.54296875, | |
| "learning_rate": 4.7338944848362324e-07, | |
| "loss": 0.4943, | |
| "mean_token_accuracy": 0.8454796385765075, | |
| "num_tokens": 81540717.0, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.9035188803714281, | |
| "grad_norm": 3.091796875, | |
| "learning_rate": 4.5754223285291e-07, | |
| "loss": 0.4597, | |
| "mean_token_accuracy": 0.8557877415418624, | |
| "num_tokens": 81694918.0, | |
| "step": 27050 | |
| }, | |
| { | |
| "epoch": 0.9051889707233162, | |
| "grad_norm": 3.55078125, | |
| "learning_rate": 4.419585928756187e-07, | |
| "loss": 0.493, | |
| "mean_token_accuracy": 0.843122188448906, | |
| "num_tokens": 81849310.0, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 0.9068590610752042, | |
| "grad_norm": 3.1796875, | |
| "learning_rate": 4.2663895899306973e-07, | |
| "loss": 0.5071, | |
| "mean_token_accuracy": 0.8416213816404343, | |
| "num_tokens": 82000775.0, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 0.9085291514270922, | |
| "grad_norm": 3.84375, | |
| "learning_rate": 4.1158375435437105e-07, | |
| "loss": 0.476, | |
| "mean_token_accuracy": 0.8484762197732926, | |
| "num_tokens": 82152188.0, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 0.9101992417789803, | |
| "grad_norm": 3.029296875, | |
| "learning_rate": 3.9679339480473866e-07, | |
| "loss": 0.4961, | |
| "mean_token_accuracy": 0.8445427894592286, | |
| "num_tokens": 82304977.0, | |
| "step": 27250 | |
| }, | |
| { | |
| "epoch": 0.9118693321308683, | |
| "grad_norm": 4.1484375, | |
| "learning_rate": 3.8226828887400256e-07, | |
| "loss": 0.4891, | |
| "mean_token_accuracy": 0.8454877972602844, | |
| "num_tokens": 82462339.0, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 0.9135394224827563, | |
| "grad_norm": 3.19921875, | |
| "learning_rate": 3.680088377653346e-07, | |
| "loss": 0.4967, | |
| "mean_token_accuracy": 0.8424636000394821, | |
| "num_tokens": 82616547.0, | |
| "step": 27350 | |
| }, | |
| { | |
| "epoch": 0.9152095128346444, | |
| "grad_norm": 3.64453125, | |
| "learning_rate": 3.5401543534415383e-07, | |
| "loss": 0.4948, | |
| "mean_token_accuracy": 0.8457672435045243, | |
| "num_tokens": 82775538.0, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 0.9168796031865324, | |
| "grad_norm": 3.130859375, | |
| "learning_rate": 3.402884681272567e-07, | |
| "loss": 0.4899, | |
| "mean_token_accuracy": 0.847527865767479, | |
| "num_tokens": 82916957.0, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 0.9185496935384204, | |
| "grad_norm": 3.498046875, | |
| "learning_rate": 3.268283152721319e-07, | |
| "loss": 0.4994, | |
| "mean_token_accuracy": 0.8429735559225082, | |
| "num_tokens": 83065642.0, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.9202197838903085, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 3.136353485664978e-07, | |
| "loss": 0.4706, | |
| "mean_token_accuracy": 0.853091567158699, | |
| "num_tokens": 83220450.0, | |
| "step": 27550 | |
| }, | |
| { | |
| "epoch": 0.9218898742421965, | |
| "grad_norm": 2.953125, | |
| "learning_rate": 3.007099324180263e-07, | |
| "loss": 0.4815, | |
| "mean_token_accuracy": 0.848934428691864, | |
| "num_tokens": 83378859.0, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 0.9235599645940845, | |
| "grad_norm": 3.310546875, | |
| "learning_rate": 2.8805242384427833e-07, | |
| "loss": 0.4808, | |
| "mean_token_accuracy": 0.8472306907176972, | |
| "num_tokens": 83530380.0, | |
| "step": 27650 | |
| }, | |
| { | |
| "epoch": 0.9252300549459725, | |
| "grad_norm": 2.82421875, | |
| "learning_rate": 2.756631724628478e-07, | |
| "loss": 0.4703, | |
| "mean_token_accuracy": 0.8495277607440949, | |
| "num_tokens": 83688186.0, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 0.9269001452978606, | |
| "grad_norm": 3.080078125, | |
| "learning_rate": 2.6354252048169326e-07, | |
| "loss": 0.483, | |
| "mean_token_accuracy": 0.8481793910264969, | |
| "num_tokens": 83837220.0, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 0.9285702356497486, | |
| "grad_norm": 3.2265625, | |
| "learning_rate": 2.5169080268969917e-07, | |
| "loss": 0.4691, | |
| "mean_token_accuracy": 0.849290372133255, | |
| "num_tokens": 83986025.0, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 0.9302403260016366, | |
| "grad_norm": 5.03515625, | |
| "learning_rate": 2.4010834644741633e-07, | |
| "loss": 0.4776, | |
| "mean_token_accuracy": 0.8499486774206162, | |
| "num_tokens": 84138357.0, | |
| "step": 27850 | |
| }, | |
| { | |
| "epoch": 0.9319104163535247, | |
| "grad_norm": 3.751953125, | |
| "learning_rate": 2.2879547167803274e-07, | |
| "loss": 0.4903, | |
| "mean_token_accuracy": 0.8482499140501022, | |
| "num_tokens": 84288102.0, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 0.9335805067054128, | |
| "grad_norm": 3.48046875, | |
| "learning_rate": 2.1775249085852158e-07, | |
| "loss": 0.4893, | |
| "mean_token_accuracy": 0.844903923869133, | |
| "num_tokens": 84436433.0, | |
| "step": 27950 | |
| }, | |
| { | |
| "epoch": 0.9352505970573008, | |
| "grad_norm": 3.40234375, | |
| "learning_rate": 2.0697970901102704e-07, | |
| "loss": 0.4918, | |
| "mean_token_accuracy": 0.8453414106369018, | |
| "num_tokens": 84583301.0, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.9369206874091889, | |
| "grad_norm": 3.251953125, | |
| "learning_rate": 1.9647742369442113e-07, | |
| "loss": 0.4805, | |
| "mean_token_accuracy": 0.8479578644037247, | |
| "num_tokens": 84731691.0, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 0.9385907777610769, | |
| "grad_norm": 3.154296875, | |
| "learning_rate": 1.8624592499610238e-07, | |
| "loss": 0.4593, | |
| "mean_token_accuracy": 0.8539443391561509, | |
| "num_tokens": 84883861.0, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 0.9402608681129649, | |
| "grad_norm": 3.56640625, | |
| "learning_rate": 1.7628549552397123e-07, | |
| "loss": 0.4904, | |
| "mean_token_accuracy": 0.8445527547597885, | |
| "num_tokens": 85040550.0, | |
| "step": 28150 | |
| }, | |
| { | |
| "epoch": 0.941930958464853, | |
| "grad_norm": 2.673828125, | |
| "learning_rate": 1.6659641039862395e-07, | |
| "loss": 0.4696, | |
| "mean_token_accuracy": 0.8498814082145691, | |
| "num_tokens": 85191672.0, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 0.943601048816741, | |
| "grad_norm": 3.681640625, | |
| "learning_rate": 1.5717893724576438e-07, | |
| "loss": 0.4926, | |
| "mean_token_accuracy": 0.8447581386566162, | |
| "num_tokens": 85338334.0, | |
| "step": 28250 | |
| }, | |
| { | |
| "epoch": 0.945271139168629, | |
| "grad_norm": 3.01171875, | |
| "learning_rate": 1.4803333618880088e-07, | |
| "loss": 0.4705, | |
| "mean_token_accuracy": 0.8505678433179855, | |
| "num_tokens": 85494849.0, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 0.9469412295205171, | |
| "grad_norm": 3.6953125, | |
| "learning_rate": 1.3915985984166435e-07, | |
| "loss": 0.4732, | |
| "mean_token_accuracy": 0.850211044549942, | |
| "num_tokens": 85649140.0, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 0.9486113198724051, | |
| "grad_norm": 2.94921875, | |
| "learning_rate": 1.3055875330183154e-07, | |
| "loss": 0.4807, | |
| "mean_token_accuracy": 0.8487061250209809, | |
| "num_tokens": 85793629.0, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 0.9502814102242931, | |
| "grad_norm": 3.693359375, | |
| "learning_rate": 1.2223025414355604e-07, | |
| "loss": 0.486, | |
| "mean_token_accuracy": 0.8450452494621277, | |
| "num_tokens": 85948765.0, | |
| "step": 28450 | |
| }, | |
| { | |
| "epoch": 0.9519515005761812, | |
| "grad_norm": 3.6328125, | |
| "learning_rate": 1.1417459241130357e-07, | |
| "loss": 0.4895, | |
| "mean_token_accuracy": 0.8471877181529999, | |
| "num_tokens": 86103889.0, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.9536215909280692, | |
| "grad_norm": 3.53125, | |
| "learning_rate": 1.0639199061340255e-07, | |
| "loss": 0.4799, | |
| "mean_token_accuracy": 0.8471868449449539, | |
| "num_tokens": 86260094.0, | |
| "step": 28550 | |
| }, | |
| { | |
| "epoch": 0.9552916812799572, | |
| "grad_norm": 3.6328125, | |
| "learning_rate": 9.888266371589128e-08, | |
| "loss": 0.5024, | |
| "mean_token_accuracy": 0.8427884036302566, | |
| "num_tokens": 86412941.0, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 0.9569617716318453, | |
| "grad_norm": 2.900390625, | |
| "learning_rate": 9.16468191365849e-08, | |
| "loss": 0.4976, | |
| "mean_token_accuracy": 0.8445427298545838, | |
| "num_tokens": 86561925.0, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 0.9586318619837333, | |
| "grad_norm": 3.013671875, | |
| "learning_rate": 8.468465673934556e-08, | |
| "loss": 0.4731, | |
| "mean_token_accuracy": 0.848741769194603, | |
| "num_tokens": 86716374.0, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 0.9603019523356213, | |
| "grad_norm": 3.640625, | |
| "learning_rate": 7.799636882856231e-08, | |
| "loss": 0.5023, | |
| "mean_token_accuracy": 0.8427910894155503, | |
| "num_tokens": 86869461.0, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 0.9619720426875094, | |
| "grad_norm": 3.26953125, | |
| "learning_rate": 7.158214014383546e-08, | |
| "loss": 0.4742, | |
| "mean_token_accuracy": 0.8496136933565139, | |
| "num_tokens": 87016441.0, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 0.9636421330393974, | |
| "grad_norm": 3.28515625, | |
| "learning_rate": 6.544214785488279e-08, | |
| "loss": 0.4901, | |
| "mean_token_accuracy": 0.8451434719562531, | |
| "num_tokens": 87174835.0, | |
| "step": 28850 | |
| }, | |
| { | |
| "epoch": 0.9653122233912854, | |
| "grad_norm": 3.232421875, | |
| "learning_rate": 5.957656155663349e-08, | |
| "loss": 0.4864, | |
| "mean_token_accuracy": 0.8473431074619293, | |
| "num_tokens": 87327651.0, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 0.9669823137431736, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 5.398554326455641e-08, | |
| "loss": 0.4808, | |
| "mean_token_accuracy": 0.8496101415157318, | |
| "num_tokens": 87466157.0, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 0.9686524040950616, | |
| "grad_norm": 3.328125, | |
| "learning_rate": 4.8669247410173534e-08, | |
| "loss": 0.493, | |
| "mean_token_accuracy": 0.8440994262695313, | |
| "num_tokens": 87614797.0, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.9703224944469496, | |
| "grad_norm": 2.853515625, | |
| "learning_rate": 4.36278208368035e-08, | |
| "loss": 0.4553, | |
| "mean_token_accuracy": 0.853015764951706, | |
| "num_tokens": 87776226.0, | |
| "step": 29050 | |
| }, | |
| { | |
| "epoch": 0.9719925847988377, | |
| "grad_norm": 3.4921875, | |
| "learning_rate": 3.8861402795499213e-08, | |
| "loss": 0.4872, | |
| "mean_token_accuracy": 0.8455040341615677, | |
| "num_tokens": 87929297.0, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 0.9736626751507257, | |
| "grad_norm": 3.033203125, | |
| "learning_rate": 3.4370124941207615e-08, | |
| "loss": 0.4735, | |
| "mean_token_accuracy": 0.8511977607011795, | |
| "num_tokens": 88084638.0, | |
| "step": 29150 | |
| }, | |
| { | |
| "epoch": 0.9753327655026137, | |
| "grad_norm": 3.689453125, | |
| "learning_rate": 3.015411132912482e-08, | |
| "loss": 0.4671, | |
| "mean_token_accuracy": 0.8513818371295929, | |
| "num_tokens": 88244094.0, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 0.9770028558545018, | |
| "grad_norm": 3.63671875, | |
| "learning_rate": 2.6213478411278857e-08, | |
| "loss": 0.501, | |
| "mean_token_accuracy": 0.8424295943975448, | |
| "num_tokens": 88393611.0, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 0.9786729462063898, | |
| "grad_norm": 3.818359375, | |
| "learning_rate": 2.2548335033306668e-08, | |
| "loss": 0.4771, | |
| "mean_token_accuracy": 0.8486606007814408, | |
| "num_tokens": 88541497.0, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 0.9803430365582778, | |
| "grad_norm": 3.662109375, | |
| "learning_rate": 1.9158782431449863e-08, | |
| "loss": 0.4754, | |
| "mean_token_accuracy": 0.8510383212566376, | |
| "num_tokens": 88687947.0, | |
| "step": 29350 | |
| }, | |
| { | |
| "epoch": 0.9820131269101658, | |
| "grad_norm": 3.791015625, | |
| "learning_rate": 1.604491422975807e-08, | |
| "loss": 0.4939, | |
| "mean_token_accuracy": 0.8457209450006485, | |
| "num_tokens": 88837931.0, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 0.9836832172620539, | |
| "grad_norm": 3.44140625, | |
| "learning_rate": 1.320681643750321e-08, | |
| "loss": 0.482, | |
| "mean_token_accuracy": 0.8474183118343354, | |
| "num_tokens": 88987901.0, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 0.9853533076139419, | |
| "grad_norm": 3.73828125, | |
| "learning_rate": 1.0644567446804754e-08, | |
| "loss": 0.4823, | |
| "mean_token_accuracy": 0.8454068493843079, | |
| "num_tokens": 89138818.0, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.9870233979658299, | |
| "grad_norm": 2.734375, | |
| "learning_rate": 8.35823803046032e-09, | |
| "loss": 0.4738, | |
| "mean_token_accuracy": 0.849404364824295, | |
| "num_tokens": 89288450.0, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 0.988693488317718, | |
| "grad_norm": 2.919921875, | |
| "learning_rate": 6.3478913399983575e-09, | |
| "loss": 0.48, | |
| "mean_token_accuracy": 0.8481200301647186, | |
| "num_tokens": 89434839.0, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 0.990363578669606, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 4.613582903925107e-09, | |
| "loss": 0.4944, | |
| "mean_token_accuracy": 0.8446270251274108, | |
| "num_tokens": 89584190.0, | |
| "step": 29650 | |
| }, | |
| { | |
| "epoch": 0.992033669021494, | |
| "grad_norm": 3.12890625, | |
| "learning_rate": 3.1553606261969237e-09, | |
| "loss": 0.4842, | |
| "mean_token_accuracy": 0.8476704114675522, | |
| "num_tokens": 89731535.0, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 0.9937037593733821, | |
| "grad_norm": 3.26171875, | |
| "learning_rate": 1.9732647848969e-09, | |
| "loss": 0.4669, | |
| "mean_token_accuracy": 0.8503151494264602, | |
| "num_tokens": 89881402.0, | |
| "step": 29750 | |
| }, | |
| { | |
| "epoch": 0.9953738497252701, | |
| "grad_norm": 3.6015625, | |
| "learning_rate": 1.0673280311168655e-09, | |
| "loss": 0.47, | |
| "mean_token_accuracy": 0.8526832580566406, | |
| "num_tokens": 90034281.0, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 0.9970439400771581, | |
| "grad_norm": 2.82421875, | |
| "learning_rate": 4.375753880614397e-10, | |
| "loss": 0.4738, | |
| "mean_token_accuracy": 0.8500426000356675, | |
| "num_tokens": 90187320.0, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 0.9987140304290462, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 8.402425035636264e-11, | |
| "loss": 0.4606, | |
| "mean_token_accuracy": 0.8513167107105255, | |
| "num_tokens": 90339712.0, | |
| "step": 29900 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 29938, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.210475070517412e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |