| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9986194201564658, |
| "eval_steps": 500, |
| "global_step": 1629, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01840773124712379, |
| "grad_norm": 11.495686687617598, |
| "learning_rate": 5e-06, |
| "loss": 1.0655, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03681546249424758, |
| "grad_norm": 5.414035603637067, |
| "learning_rate": 5e-06, |
| "loss": 0.9662, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.05522319374137138, |
| "grad_norm": 1.7180886181350892, |
| "learning_rate": 5e-06, |
| "loss": 0.9362, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.07363092498849516, |
| "grad_norm": 1.795533021117465, |
| "learning_rate": 5e-06, |
| "loss": 0.922, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.09203865623561897, |
| "grad_norm": 1.1665142084019502, |
| "learning_rate": 5e-06, |
| "loss": 0.9051, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.11044638748274276, |
| "grad_norm": 0.7289439832404309, |
| "learning_rate": 5e-06, |
| "loss": 0.8929, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.12885411872986655, |
| "grad_norm": 0.9030368777254644, |
| "learning_rate": 5e-06, |
| "loss": 0.8821, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.14726184997699032, |
| "grad_norm": 0.9425682568991275, |
| "learning_rate": 5e-06, |
| "loss": 0.8734, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.16566958122411413, |
| "grad_norm": 0.7354391468644993, |
| "learning_rate": 5e-06, |
| "loss": 0.8738, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.18407731247123793, |
| "grad_norm": 0.6651957250464282, |
| "learning_rate": 5e-06, |
| "loss": 0.8724, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.2024850437183617, |
| "grad_norm": 0.7545639567673004, |
| "learning_rate": 5e-06, |
| "loss": 0.8644, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.2208927749654855, |
| "grad_norm": 0.6185140044329701, |
| "learning_rate": 5e-06, |
| "loss": 0.8613, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.2393005062126093, |
| "grad_norm": 0.6591986758093533, |
| "learning_rate": 5e-06, |
| "loss": 0.8556, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.2577082374597331, |
| "grad_norm": 0.8491087509246042, |
| "learning_rate": 5e-06, |
| "loss": 0.8539, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.2761159687068569, |
| "grad_norm": 0.6531629448196006, |
| "learning_rate": 5e-06, |
| "loss": 0.8562, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.29452369995398064, |
| "grad_norm": 0.8438280033874832, |
| "learning_rate": 5e-06, |
| "loss": 0.852, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.31293143120110445, |
| "grad_norm": 0.559902696500108, |
| "learning_rate": 5e-06, |
| "loss": 0.8443, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.33133916244822825, |
| "grad_norm": 0.5581328727424005, |
| "learning_rate": 5e-06, |
| "loss": 0.8469, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.34974689369535206, |
| "grad_norm": 0.6723674628868884, |
| "learning_rate": 5e-06, |
| "loss": 0.8423, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.36815462494247586, |
| "grad_norm": 0.5911235299913716, |
| "learning_rate": 5e-06, |
| "loss": 0.8422, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.3865623561895996, |
| "grad_norm": 0.6326816480779326, |
| "learning_rate": 5e-06, |
| "loss": 0.8451, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.4049700874367234, |
| "grad_norm": 0.545823585506014, |
| "learning_rate": 5e-06, |
| "loss": 0.8405, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.4233778186838472, |
| "grad_norm": 0.8306189189623202, |
| "learning_rate": 5e-06, |
| "loss": 0.8359, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.441785549930971, |
| "grad_norm": 0.7302046699439101, |
| "learning_rate": 5e-06, |
| "loss": 0.843, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.4601932811780948, |
| "grad_norm": 0.6097696283103196, |
| "learning_rate": 5e-06, |
| "loss": 0.8442, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.4786010124252186, |
| "grad_norm": 0.5520157322910384, |
| "learning_rate": 5e-06, |
| "loss": 0.8345, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.4970087436723424, |
| "grad_norm": 0.8387750998122173, |
| "learning_rate": 5e-06, |
| "loss": 0.8402, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.5154164749194662, |
| "grad_norm": 0.5831898004809442, |
| "learning_rate": 5e-06, |
| "loss": 0.8393, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.53382420616659, |
| "grad_norm": 0.5522040188439342, |
| "learning_rate": 5e-06, |
| "loss": 0.8326, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.5522319374137138, |
| "grad_norm": 0.5689291080618771, |
| "learning_rate": 5e-06, |
| "loss": 0.8343, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5706396686608376, |
| "grad_norm": 0.5585963481358173, |
| "learning_rate": 5e-06, |
| "loss": 0.8285, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.5890473999079613, |
| "grad_norm": 0.6246406440833802, |
| "learning_rate": 5e-06, |
| "loss": 0.8303, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.6074551311550851, |
| "grad_norm": 0.5256671010894053, |
| "learning_rate": 5e-06, |
| "loss": 0.8325, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.6258628624022089, |
| "grad_norm": 0.633273666711919, |
| "learning_rate": 5e-06, |
| "loss": 0.8302, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.6442705936493327, |
| "grad_norm": 0.8071524979584527, |
| "learning_rate": 5e-06, |
| "loss": 0.8268, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.6626783248964565, |
| "grad_norm": 0.6298754293534956, |
| "learning_rate": 5e-06, |
| "loss": 0.8274, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.6810860561435803, |
| "grad_norm": 0.580085422648526, |
| "learning_rate": 5e-06, |
| "loss": 0.8249, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.6994937873907041, |
| "grad_norm": 0.5237120595233268, |
| "learning_rate": 5e-06, |
| "loss": 0.8267, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.7179015186378279, |
| "grad_norm": 0.5205621404905915, |
| "learning_rate": 5e-06, |
| "loss": 0.8281, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.7363092498849517, |
| "grad_norm": 0.5609961443767165, |
| "learning_rate": 5e-06, |
| "loss": 0.8294, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.7547169811320755, |
| "grad_norm": 0.8113242076381498, |
| "learning_rate": 5e-06, |
| "loss": 0.8294, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.7731247123791992, |
| "grad_norm": 0.6263734997124686, |
| "learning_rate": 5e-06, |
| "loss": 0.8222, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.791532443626323, |
| "grad_norm": 0.5533838940453765, |
| "learning_rate": 5e-06, |
| "loss": 0.8256, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.8099401748734468, |
| "grad_norm": 0.5686721562918683, |
| "learning_rate": 5e-06, |
| "loss": 0.8173, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.8283479061205706, |
| "grad_norm": 0.48436281066991915, |
| "learning_rate": 5e-06, |
| "loss": 0.8269, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.8467556373676944, |
| "grad_norm": 0.5577482524512647, |
| "learning_rate": 5e-06, |
| "loss": 0.8249, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.8651633686148182, |
| "grad_norm": 0.5643149386241082, |
| "learning_rate": 5e-06, |
| "loss": 0.8191, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.883571099861942, |
| "grad_norm": 0.6614121315928284, |
| "learning_rate": 5e-06, |
| "loss": 0.8176, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.9019788311090658, |
| "grad_norm": 0.4888549298926769, |
| "learning_rate": 5e-06, |
| "loss": 0.8183, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.9203865623561897, |
| "grad_norm": 0.5740805075207074, |
| "learning_rate": 5e-06, |
| "loss": 0.8206, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9387942936033133, |
| "grad_norm": 0.49345078862695535, |
| "learning_rate": 5e-06, |
| "loss": 0.8216, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.9572020248504371, |
| "grad_norm": 0.4895624955783029, |
| "learning_rate": 5e-06, |
| "loss": 0.815, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "grad_norm": 0.5078514624048458, |
| "learning_rate": 5e-06, |
| "loss": 0.8224, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.9940174873446848, |
| "grad_norm": 0.49323310639247003, |
| "learning_rate": 5e-06, |
| "loss": 0.8223, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.9995398067188219, |
| "eval_loss": 0.8175484538078308, |
| "eval_runtime": 577.4655, |
| "eval_samples_per_second": 25.35, |
| "eval_steps_per_second": 0.397, |
| "step": 543 |
| }, |
| { |
| "epoch": 1.0124252185918086, |
| "grad_norm": 0.6931115032757318, |
| "learning_rate": 5e-06, |
| "loss": 0.8486, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.0308329498389324, |
| "grad_norm": 0.6510623966802886, |
| "learning_rate": 5e-06, |
| "loss": 0.7745, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.0492406810860562, |
| "grad_norm": 0.6616327762994352, |
| "learning_rate": 5e-06, |
| "loss": 0.7798, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.06764841233318, |
| "grad_norm": 0.5775037016510299, |
| "learning_rate": 5e-06, |
| "loss": 0.7753, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.0860561435803038, |
| "grad_norm": 0.5707136558272301, |
| "learning_rate": 5e-06, |
| "loss": 0.7769, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.1044638748274276, |
| "grad_norm": 0.7284560313205218, |
| "learning_rate": 5e-06, |
| "loss": 0.7765, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.1228716060745514, |
| "grad_norm": 0.6310103758378874, |
| "learning_rate": 5e-06, |
| "loss": 0.777, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.1412793373216752, |
| "grad_norm": 0.515513316541971, |
| "learning_rate": 5e-06, |
| "loss": 0.7736, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.159687068568799, |
| "grad_norm": 0.5492113148126704, |
| "learning_rate": 5e-06, |
| "loss": 0.7756, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.1780947998159226, |
| "grad_norm": 0.5228104705222637, |
| "learning_rate": 5e-06, |
| "loss": 0.7764, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.1965025310630466, |
| "grad_norm": 0.5035050506284052, |
| "learning_rate": 5e-06, |
| "loss": 0.7734, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.2149102623101702, |
| "grad_norm": 0.8068687083136943, |
| "learning_rate": 5e-06, |
| "loss": 0.7757, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.233317993557294, |
| "grad_norm": 0.5653783132955, |
| "learning_rate": 5e-06, |
| "loss": 0.7746, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.2517257248044178, |
| "grad_norm": 0.6662032923342155, |
| "learning_rate": 5e-06, |
| "loss": 0.7744, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.2701334560515416, |
| "grad_norm": 0.5501136952057387, |
| "learning_rate": 5e-06, |
| "loss": 0.7727, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.2885411872986654, |
| "grad_norm": 0.608620492574905, |
| "learning_rate": 5e-06, |
| "loss": 0.7757, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.3069489185457892, |
| "grad_norm": 0.6052951493689271, |
| "learning_rate": 5e-06, |
| "loss": 0.7738, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.325356649792913, |
| "grad_norm": 0.6410940625081331, |
| "learning_rate": 5e-06, |
| "loss": 0.7757, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.3437643810400368, |
| "grad_norm": 0.5699137555795393, |
| "learning_rate": 5e-06, |
| "loss": 0.7805, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.3621721122871606, |
| "grad_norm": 0.5068184484173434, |
| "learning_rate": 5e-06, |
| "loss": 0.7775, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.3805798435342844, |
| "grad_norm": 0.4931418205462196, |
| "learning_rate": 5e-06, |
| "loss": 0.7737, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.3989875747814082, |
| "grad_norm": 0.5408228174235898, |
| "learning_rate": 5e-06, |
| "loss": 0.7734, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.417395306028532, |
| "grad_norm": 0.5380361882479816, |
| "learning_rate": 5e-06, |
| "loss": 0.7753, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.4358030372756558, |
| "grad_norm": 0.5840217555045797, |
| "learning_rate": 5e-06, |
| "loss": 0.7747, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.4542107685227796, |
| "grad_norm": 0.5362828182722048, |
| "learning_rate": 5e-06, |
| "loss": 0.776, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.4726184997699034, |
| "grad_norm": 0.552799353811648, |
| "learning_rate": 5e-06, |
| "loss": 0.7758, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.491026231017027, |
| "grad_norm": 0.47793200905569844, |
| "learning_rate": 5e-06, |
| "loss": 0.7751, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.509433962264151, |
| "grad_norm": 0.5685715941391194, |
| "learning_rate": 5e-06, |
| "loss": 0.7764, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.5278416935112746, |
| "grad_norm": 0.5141942789784186, |
| "learning_rate": 5e-06, |
| "loss": 0.7718, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.5462494247583987, |
| "grad_norm": 0.5951320223055838, |
| "learning_rate": 5e-06, |
| "loss": 0.7756, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.5646571560055222, |
| "grad_norm": 0.5881625341228633, |
| "learning_rate": 5e-06, |
| "loss": 0.7752, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.5830648872526463, |
| "grad_norm": 0.5384295675334821, |
| "learning_rate": 5e-06, |
| "loss": 0.7739, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.6014726184997699, |
| "grad_norm": 0.6339064986712926, |
| "learning_rate": 5e-06, |
| "loss": 0.7767, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.6198803497468937, |
| "grad_norm": 0.5756524997905831, |
| "learning_rate": 5e-06, |
| "loss": 0.7732, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.6382880809940175, |
| "grad_norm": 0.49759423895450694, |
| "learning_rate": 5e-06, |
| "loss": 0.7713, |
| "step": 890 |
| }, |
| { |
| "epoch": 1.6566958122411413, |
| "grad_norm": 0.5426358109496824, |
| "learning_rate": 5e-06, |
| "loss": 0.7713, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.675103543488265, |
| "grad_norm": 0.5703740061473311, |
| "learning_rate": 5e-06, |
| "loss": 0.7715, |
| "step": 910 |
| }, |
| { |
| "epoch": 1.6935112747353889, |
| "grad_norm": 0.6756102849236832, |
| "learning_rate": 5e-06, |
| "loss": 0.7761, |
| "step": 920 |
| }, |
| { |
| "epoch": 1.7119190059825127, |
| "grad_norm": 0.6603200364822771, |
| "learning_rate": 5e-06, |
| "loss": 0.7732, |
| "step": 930 |
| }, |
| { |
| "epoch": 1.7303267372296365, |
| "grad_norm": 0.6519535812695805, |
| "learning_rate": 5e-06, |
| "loss": 0.7699, |
| "step": 940 |
| }, |
| { |
| "epoch": 1.7487344684767603, |
| "grad_norm": 0.5892484328148301, |
| "learning_rate": 5e-06, |
| "loss": 0.7731, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.7671421997238839, |
| "grad_norm": 0.6054216291145197, |
| "learning_rate": 5e-06, |
| "loss": 0.7765, |
| "step": 960 |
| }, |
| { |
| "epoch": 1.785549930971008, |
| "grad_norm": 0.5359072557829287, |
| "learning_rate": 5e-06, |
| "loss": 0.7694, |
| "step": 970 |
| }, |
| { |
| "epoch": 1.8039576622181315, |
| "grad_norm": 0.48947344008413946, |
| "learning_rate": 5e-06, |
| "loss": 0.7716, |
| "step": 980 |
| }, |
| { |
| "epoch": 1.8223653934652555, |
| "grad_norm": 0.5552327718140667, |
| "learning_rate": 5e-06, |
| "loss": 0.7715, |
| "step": 990 |
| }, |
| { |
| "epoch": 1.840773124712379, |
| "grad_norm": 0.49129147603369394, |
| "learning_rate": 5e-06, |
| "loss": 0.7696, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.859180855959503, |
| "grad_norm": 0.6177309925844156, |
| "learning_rate": 5e-06, |
| "loss": 0.7753, |
| "step": 1010 |
| }, |
| { |
| "epoch": 1.8775885872066267, |
| "grad_norm": 0.556337075656538, |
| "learning_rate": 5e-06, |
| "loss": 0.7724, |
| "step": 1020 |
| }, |
| { |
| "epoch": 1.8959963184537507, |
| "grad_norm": 0.6337348248265403, |
| "learning_rate": 5e-06, |
| "loss": 0.7724, |
| "step": 1030 |
| }, |
| { |
| "epoch": 1.9144040497008743, |
| "grad_norm": 0.5237811675039271, |
| "learning_rate": 5e-06, |
| "loss": 0.7744, |
| "step": 1040 |
| }, |
| { |
| "epoch": 1.932811780947998, |
| "grad_norm": 0.493087641177435, |
| "learning_rate": 5e-06, |
| "loss": 0.7732, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.951219512195122, |
| "grad_norm": 0.5743317560990825, |
| "learning_rate": 5e-06, |
| "loss": 0.7738, |
| "step": 1060 |
| }, |
| { |
| "epoch": 1.9696272434422457, |
| "grad_norm": 0.6056942269519802, |
| "learning_rate": 5e-06, |
| "loss": 0.7731, |
| "step": 1070 |
| }, |
| { |
| "epoch": 1.9880349746893695, |
| "grad_norm": 0.5324789923627218, |
| "learning_rate": 5e-06, |
| "loss": 0.7689, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.9990796134376438, |
| "eval_loss": 0.8038221001625061, |
| "eval_runtime": 578.6774, |
| "eval_samples_per_second": 25.297, |
| "eval_steps_per_second": 0.396, |
| "step": 1086 |
| }, |
| { |
| "epoch": 2.0064427059364935, |
| "grad_norm": 0.7880104184820911, |
| "learning_rate": 5e-06, |
| "loss": 0.8114, |
| "step": 1090 |
| }, |
| { |
| "epoch": 2.024850437183617, |
| "grad_norm": 0.6486016931410004, |
| "learning_rate": 5e-06, |
| "loss": 0.7261, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.0432581684307407, |
| "grad_norm": 0.6854700908189261, |
| "learning_rate": 5e-06, |
| "loss": 0.7268, |
| "step": 1110 |
| }, |
| { |
| "epoch": 2.0616658996778647, |
| "grad_norm": 0.6011201615337006, |
| "learning_rate": 5e-06, |
| "loss": 0.7268, |
| "step": 1120 |
| }, |
| { |
| "epoch": 2.0800736309249883, |
| "grad_norm": 0.5369071090939471, |
| "learning_rate": 5e-06, |
| "loss": 0.7284, |
| "step": 1130 |
| }, |
| { |
| "epoch": 2.0984813621721123, |
| "grad_norm": 0.5656204024525643, |
| "learning_rate": 5e-06, |
| "loss": 0.725, |
| "step": 1140 |
| }, |
| { |
| "epoch": 2.116889093419236, |
| "grad_norm": 0.6303299238534352, |
| "learning_rate": 5e-06, |
| "loss": 0.7303, |
| "step": 1150 |
| }, |
| { |
| "epoch": 2.13529682466636, |
| "grad_norm": 0.5123557643767893, |
| "learning_rate": 5e-06, |
| "loss": 0.7289, |
| "step": 1160 |
| }, |
| { |
| "epoch": 2.1537045559134835, |
| "grad_norm": 0.5538382553645407, |
| "learning_rate": 5e-06, |
| "loss": 0.7279, |
| "step": 1170 |
| }, |
| { |
| "epoch": 2.1721122871606076, |
| "grad_norm": 0.5168659565290504, |
| "learning_rate": 5e-06, |
| "loss": 0.726, |
| "step": 1180 |
| }, |
| { |
| "epoch": 2.190520018407731, |
| "grad_norm": 0.5149057222016729, |
| "learning_rate": 5e-06, |
| "loss": 0.7298, |
| "step": 1190 |
| }, |
| { |
| "epoch": 2.208927749654855, |
| "grad_norm": 0.5554533749205715, |
| "learning_rate": 5e-06, |
| "loss": 0.7287, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.2273354809019787, |
| "grad_norm": 0.5330943850283596, |
| "learning_rate": 5e-06, |
| "loss": 0.7344, |
| "step": 1210 |
| }, |
| { |
| "epoch": 2.2457432121491028, |
| "grad_norm": 0.8391731239503334, |
| "learning_rate": 5e-06, |
| "loss": 0.7267, |
| "step": 1220 |
| }, |
| { |
| "epoch": 2.2641509433962264, |
| "grad_norm": 0.7660636226540483, |
| "learning_rate": 5e-06, |
| "loss": 0.7263, |
| "step": 1230 |
| }, |
| { |
| "epoch": 2.2825586746433504, |
| "grad_norm": 0.7685620801521849, |
| "learning_rate": 5e-06, |
| "loss": 0.7313, |
| "step": 1240 |
| }, |
| { |
| "epoch": 2.300966405890474, |
| "grad_norm": 0.5495938135890535, |
| "learning_rate": 5e-06, |
| "loss": 0.7304, |
| "step": 1250 |
| }, |
| { |
| "epoch": 2.319374137137598, |
| "grad_norm": 0.5378287623942755, |
| "learning_rate": 5e-06, |
| "loss": 0.7272, |
| "step": 1260 |
| }, |
| { |
| "epoch": 2.3377818683847216, |
| "grad_norm": 0.4910879337814261, |
| "learning_rate": 5e-06, |
| "loss": 0.7282, |
| "step": 1270 |
| }, |
| { |
| "epoch": 2.356189599631845, |
| "grad_norm": 0.5133127271923346, |
| "learning_rate": 5e-06, |
| "loss": 0.7269, |
| "step": 1280 |
| }, |
| { |
| "epoch": 2.374597330878969, |
| "grad_norm": 0.47595606060751855, |
| "learning_rate": 5e-06, |
| "loss": 0.7339, |
| "step": 1290 |
| }, |
| { |
| "epoch": 2.393005062126093, |
| "grad_norm": 0.6100252730125039, |
| "learning_rate": 5e-06, |
| "loss": 0.7345, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.411412793373217, |
| "grad_norm": 0.7026268817947412, |
| "learning_rate": 5e-06, |
| "loss": 0.7337, |
| "step": 1310 |
| }, |
| { |
| "epoch": 2.4298205246203404, |
| "grad_norm": 0.5079596124965767, |
| "learning_rate": 5e-06, |
| "loss": 0.7302, |
| "step": 1320 |
| }, |
| { |
| "epoch": 2.4482282558674644, |
| "grad_norm": 0.6696005064461804, |
| "learning_rate": 5e-06, |
| "loss": 0.7326, |
| "step": 1330 |
| }, |
| { |
| "epoch": 2.466635987114588, |
| "grad_norm": 0.5305091535929889, |
| "learning_rate": 5e-06, |
| "loss": 0.7341, |
| "step": 1340 |
| }, |
| { |
| "epoch": 2.485043718361712, |
| "grad_norm": 0.5614144854915857, |
| "learning_rate": 5e-06, |
| "loss": 0.7307, |
| "step": 1350 |
| }, |
| { |
| "epoch": 2.5034514496088356, |
| "grad_norm": 0.5298924392144096, |
| "learning_rate": 5e-06, |
| "loss": 0.7267, |
| "step": 1360 |
| }, |
| { |
| "epoch": 2.5218591808559596, |
| "grad_norm": 0.5471748009635868, |
| "learning_rate": 5e-06, |
| "loss": 0.7313, |
| "step": 1370 |
| }, |
| { |
| "epoch": 2.540266912103083, |
| "grad_norm": 0.5294197001366643, |
| "learning_rate": 5e-06, |
| "loss": 0.7306, |
| "step": 1380 |
| }, |
| { |
| "epoch": 2.5586746433502072, |
| "grad_norm": 0.5154792682728118, |
| "learning_rate": 5e-06, |
| "loss": 0.7307, |
| "step": 1390 |
| }, |
| { |
| "epoch": 2.577082374597331, |
| "grad_norm": 0.5789014770833831, |
| "learning_rate": 5e-06, |
| "loss": 0.7301, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.595490105844455, |
| "grad_norm": 0.5711167242239414, |
| "learning_rate": 5e-06, |
| "loss": 0.7303, |
| "step": 1410 |
| }, |
| { |
| "epoch": 2.6138978370915784, |
| "grad_norm": 0.5106168370499636, |
| "learning_rate": 5e-06, |
| "loss": 0.7334, |
| "step": 1420 |
| }, |
| { |
| "epoch": 2.632305568338702, |
| "grad_norm": 0.5255898569302698, |
| "learning_rate": 5e-06, |
| "loss": 0.7304, |
| "step": 1430 |
| }, |
| { |
| "epoch": 2.650713299585826, |
| "grad_norm": 0.6031837728823062, |
| "learning_rate": 5e-06, |
| "loss": 0.7312, |
| "step": 1440 |
| }, |
| { |
| "epoch": 2.66912103083295, |
| "grad_norm": 0.5493271504786518, |
| "learning_rate": 5e-06, |
| "loss": 0.7286, |
| "step": 1450 |
| }, |
| { |
| "epoch": 2.6875287620800736, |
| "grad_norm": 0.5359957110816633, |
| "learning_rate": 5e-06, |
| "loss": 0.7333, |
| "step": 1460 |
| }, |
| { |
| "epoch": 2.705936493327197, |
| "grad_norm": 0.5315084537350974, |
| "learning_rate": 5e-06, |
| "loss": 0.7346, |
| "step": 1470 |
| }, |
| { |
| "epoch": 2.7243442245743212, |
| "grad_norm": 0.5584346211293773, |
| "learning_rate": 5e-06, |
| "loss": 0.7323, |
| "step": 1480 |
| }, |
| { |
| "epoch": 2.7427519558214453, |
| "grad_norm": 0.5792409356580582, |
| "learning_rate": 5e-06, |
| "loss": 0.7379, |
| "step": 1490 |
| }, |
| { |
| "epoch": 2.761159687068569, |
| "grad_norm": 0.5984704825439037, |
| "learning_rate": 5e-06, |
| "loss": 0.7304, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.7795674183156924, |
| "grad_norm": 0.6745195268654445, |
| "learning_rate": 5e-06, |
| "loss": 0.7279, |
| "step": 1510 |
| }, |
| { |
| "epoch": 2.7979751495628165, |
| "grad_norm": 0.5840202368947607, |
| "learning_rate": 5e-06, |
| "loss": 0.7285, |
| "step": 1520 |
| }, |
| { |
| "epoch": 2.81638288080994, |
| "grad_norm": 0.5808419078842372, |
| "learning_rate": 5e-06, |
| "loss": 0.7327, |
| "step": 1530 |
| }, |
| { |
| "epoch": 2.834790612057064, |
| "grad_norm": 0.5702913394525961, |
| "learning_rate": 5e-06, |
| "loss": 0.7359, |
| "step": 1540 |
| }, |
| { |
| "epoch": 2.8531983433041876, |
| "grad_norm": 0.5655041029108082, |
| "learning_rate": 5e-06, |
| "loss": 0.7314, |
| "step": 1550 |
| }, |
| { |
| "epoch": 2.8716060745513117, |
| "grad_norm": 0.5207693095861798, |
| "learning_rate": 5e-06, |
| "loss": 0.7305, |
| "step": 1560 |
| }, |
| { |
| "epoch": 2.8900138057984353, |
| "grad_norm": 0.5547333755102506, |
| "learning_rate": 5e-06, |
| "loss": 0.7316, |
| "step": 1570 |
| }, |
| { |
| "epoch": 2.9084215370455593, |
| "grad_norm": 0.5475003571941236, |
| "learning_rate": 5e-06, |
| "loss": 0.7288, |
| "step": 1580 |
| }, |
| { |
| "epoch": 2.926829268292683, |
| "grad_norm": 0.6206903635935059, |
| "learning_rate": 5e-06, |
| "loss": 0.7371, |
| "step": 1590 |
| }, |
| { |
| "epoch": 2.945236999539807, |
| "grad_norm": 0.5473171408927406, |
| "learning_rate": 5e-06, |
| "loss": 0.7342, |
| "step": 1600 |
| }, |
| { |
| "epoch": 2.9636447307869305, |
| "grad_norm": 0.5167351817484509, |
| "learning_rate": 5e-06, |
| "loss": 0.7313, |
| "step": 1610 |
| }, |
| { |
| "epoch": 2.982052462034054, |
| "grad_norm": 0.549878401014801, |
| "learning_rate": 5e-06, |
| "loss": 0.7326, |
| "step": 1620 |
| }, |
| { |
| "epoch": 2.9986194201564658, |
| "eval_loss": 0.8022779822349548, |
| "eval_runtime": 574.4981, |
| "eval_samples_per_second": 25.481, |
| "eval_steps_per_second": 0.399, |
| "step": 1629 |
| }, |
| { |
| "epoch": 2.9986194201564658, |
| "step": 1629, |
| "total_flos": 2728426293166080.0, |
| "train_loss": 0.7854923086710837, |
| "train_runtime": 95950.7779, |
| "train_samples_per_second": 8.696, |
| "train_steps_per_second": 0.017 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1629, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2728426293166080.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
