Weyaxi's picture
Upload folder using huggingface_hub
03ad7a7
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.19906687402799378,
"eval_steps": 500,
"global_step": 160,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.000000000000001e-07,
"logits/chosen": -2.0463106632232666,
"logits/rejected": -1.8486888408660889,
"logps/chosen": -311.57489013671875,
"logps/rejected": -415.468505859375,
"loss": 0.671,
"rewards/accuracies": 0.75,
"rewards/chosen": -0.021808436140418053,
"rewards/margins": 0.04626159369945526,
"rewards/rejected": -0.06807002425193787,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.0000000000000002e-06,
"logits/chosen": -2.060105562210083,
"logits/rejected": -2.106396198272705,
"logps/chosen": -220.380615234375,
"logps/rejected": -404.501220703125,
"loss": 0.6745,
"rewards/accuracies": 0.6875,
"rewards/chosen": -0.02021012455224991,
"rewards/margins": 0.03883519023656845,
"rewards/rejected": -0.05904531478881836,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.5e-06,
"logits/chosen": -2.239086151123047,
"logits/rejected": -2.0575525760650635,
"logps/chosen": -163.8677978515625,
"logps/rejected": -446.79180908203125,
"loss": 0.67,
"rewards/accuracies": 0.6875,
"rewards/chosen": -0.024322081357240677,
"rewards/margins": 0.04956565052270889,
"rewards/rejected": -0.07388772815465927,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2.0000000000000003e-06,
"logits/chosen": -2.1058502197265625,
"logits/rejected": -2.344322681427002,
"logps/chosen": -318.9349670410156,
"logps/rejected": -378.9231262207031,
"loss": 0.6576,
"rewards/accuracies": 0.9375,
"rewards/chosen": -0.027724243700504303,
"rewards/margins": 0.07309143990278244,
"rewards/rejected": -0.10081568360328674,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 2.5e-06,
"logits/chosen": -2.287339687347412,
"logits/rejected": -2.3221607208251953,
"logps/chosen": -221.33163452148438,
"logps/rejected": -388.6357421875,
"loss": 0.6498,
"rewards/accuracies": 0.8125,
"rewards/chosen": -0.03215093910694122,
"rewards/margins": 0.09096165001392365,
"rewards/rejected": -0.12311258912086487,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 3e-06,
"logits/chosen": -1.98830246925354,
"logits/rejected": -1.9178718328475952,
"logps/chosen": -244.0532684326172,
"logps/rejected": -373.9111328125,
"loss": 0.6395,
"rewards/accuracies": 0.8125,
"rewards/chosen": -0.0789945125579834,
"rewards/margins": 0.11430712044239044,
"rewards/rejected": -0.19330161809921265,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 3.5000000000000004e-06,
"logits/chosen": -2.0385985374450684,
"logits/rejected": -1.9476547241210938,
"logps/chosen": -347.14227294921875,
"logps/rejected": -426.24603271484375,
"loss": 0.6148,
"rewards/accuracies": 0.9375,
"rewards/chosen": -0.0816906988620758,
"rewards/margins": 0.1658005714416504,
"rewards/rejected": -0.2474912703037262,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 4.000000000000001e-06,
"logits/chosen": -1.695872187614441,
"logits/rejected": -1.7980302572250366,
"logps/chosen": -287.9168395996094,
"logps/rejected": -355.14129638671875,
"loss": 0.5785,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.07900090515613556,
"rewards/margins": 0.25094836950302124,
"rewards/rejected": -0.329949289560318,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 4.5e-06,
"logits/chosen": -1.9222339391708374,
"logits/rejected": -1.8972643613815308,
"logps/chosen": -211.97979736328125,
"logps/rejected": -405.848388671875,
"loss": 0.5229,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.09827227890491486,
"rewards/margins": 0.3891267478466034,
"rewards/rejected": -0.48739901185035706,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 5e-06,
"logits/chosen": -1.9703621864318848,
"logits/rejected": -1.7560880184173584,
"logps/chosen": -277.2589416503906,
"logps/rejected": -445.6544494628906,
"loss": 0.4853,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.1426083892583847,
"rewards/margins": 0.4861423373222351,
"rewards/rejected": -0.628750741481781,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 5.500000000000001e-06,
"logits/chosen": -2.0542986392974854,
"logits/rejected": -2.110658884048462,
"logps/chosen": -283.9775390625,
"logps/rejected": -394.361572265625,
"loss": 0.4476,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.14311671257019043,
"rewards/margins": 0.6046640872955322,
"rewards/rejected": -0.7477807998657227,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 6e-06,
"logits/chosen": -2.0650949478149414,
"logits/rejected": -2.0736098289489746,
"logps/chosen": -235.07675170898438,
"logps/rejected": -448.17919921875,
"loss": 0.3701,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.23901399970054626,
"rewards/margins": 0.9068580269813538,
"rewards/rejected": -1.1458721160888672,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 6.5000000000000004e-06,
"logits/chosen": -2.011099100112915,
"logits/rejected": -2.106595754623413,
"logps/chosen": -289.19970703125,
"logps/rejected": -417.64208984375,
"loss": 0.3675,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.26357388496398926,
"rewards/margins": 0.8955046534538269,
"rewards/rejected": -1.159078598022461,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 7.000000000000001e-06,
"logits/chosen": -2.1066994667053223,
"logits/rejected": -1.7827305793762207,
"logps/chosen": -169.27044677734375,
"logps/rejected": -446.7305908203125,
"loss": 0.254,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.2715146541595459,
"rewards/margins": 1.3259609937667847,
"rewards/rejected": -1.5974756479263306,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 7.5e-06,
"logits/chosen": -1.9394950866699219,
"logits/rejected": -1.9831421375274658,
"logps/chosen": -194.98016357421875,
"logps/rejected": -470.9692687988281,
"loss": 0.2298,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.4095136225223541,
"rewards/margins": 1.628616452217102,
"rewards/rejected": -2.038130044937134,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 8.000000000000001e-06,
"logits/chosen": -1.7606948614120483,
"logits/rejected": -2.0152878761291504,
"logps/chosen": -253.0347900390625,
"logps/rejected": -428.3993835449219,
"loss": 0.2528,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.581798255443573,
"rewards/margins": 1.3869069814682007,
"rewards/rejected": -1.968705177307129,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 8.500000000000002e-06,
"logits/chosen": -2.0609982013702393,
"logits/rejected": -1.9835376739501953,
"logps/chosen": -265.3518371582031,
"logps/rejected": -501.8542785644531,
"loss": 0.1997,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.681609570980072,
"rewards/margins": 2.0102298259735107,
"rewards/rejected": -2.6918392181396484,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 9e-06,
"logits/chosen": -2.117746114730835,
"logits/rejected": -2.218081474304199,
"logps/chosen": -202.6907501220703,
"logps/rejected": -413.13604736328125,
"loss": 0.1582,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.6984068751335144,
"rewards/margins": 1.8970444202423096,
"rewards/rejected": -2.5954513549804688,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 9.5e-06,
"logits/chosen": -2.385519504547119,
"logits/rejected": -1.8222811222076416,
"logps/chosen": -175.93809509277344,
"logps/rejected": -469.17657470703125,
"loss": 0.0951,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.7677481174468994,
"rewards/margins": 2.7113454341888428,
"rewards/rejected": -3.479093551635742,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"logits/chosen": -2.187441349029541,
"logits/rejected": -2.1218032836914062,
"logps/chosen": -301.7166442871094,
"logps/rejected": -490.854736328125,
"loss": 0.0944,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.2999629974365234,
"rewards/margins": 3.2447361946105957,
"rewards/rejected": -4.544699192047119,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 1.05e-05,
"logits/chosen": -1.967098355293274,
"logits/rejected": -1.9263262748718262,
"logps/chosen": -176.0479278564453,
"logps/rejected": -472.8221435546875,
"loss": 0.0459,
"rewards/accuracies": 1.0,
"rewards/chosen": -0.8402897119522095,
"rewards/margins": 4.1183624267578125,
"rewards/rejected": -4.958651542663574,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 1.1000000000000001e-05,
"logits/chosen": -2.188459873199463,
"logits/rejected": -2.156071424484253,
"logps/chosen": -243.41683959960938,
"logps/rejected": -465.08685302734375,
"loss": 0.1389,
"rewards/accuracies": 0.9375,
"rewards/chosen": -1.5002142190933228,
"rewards/margins": 4.108778953552246,
"rewards/rejected": -5.608993053436279,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 1.1500000000000002e-05,
"logits/chosen": -1.7361280918121338,
"logits/rejected": -1.8734406232833862,
"logps/chosen": -274.4007568359375,
"logps/rejected": -465.7174987792969,
"loss": 0.074,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.6840157508850098,
"rewards/margins": 4.5255866050720215,
"rewards/rejected": -6.209602355957031,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 1.2e-05,
"logits/chosen": -1.8966342210769653,
"logits/rejected": -1.772972583770752,
"logps/chosen": -275.3910217285156,
"logps/rejected": -462.07720947265625,
"loss": 0.0381,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.017077922821045,
"rewards/margins": 4.740576267242432,
"rewards/rejected": -6.757654666900635,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 1.25e-05,
"logits/chosen": -2.2573952674865723,
"logits/rejected": -1.9883058071136475,
"logps/chosen": -172.16043090820312,
"logps/rejected": -391.4390563964844,
"loss": 0.0666,
"rewards/accuracies": 1.0,
"rewards/chosen": -1.9856681823730469,
"rewards/margins": 4.858271598815918,
"rewards/rejected": -6.843939781188965,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 1.3000000000000001e-05,
"logits/chosen": -2.0475640296936035,
"logits/rejected": -1.8690011501312256,
"logps/chosen": -184.4323272705078,
"logps/rejected": -468.86175537109375,
"loss": 0.0805,
"rewards/accuracies": 0.9375,
"rewards/chosen": -2.08463716506958,
"rewards/margins": 6.207521438598633,
"rewards/rejected": -8.292158126831055,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 1.3500000000000001e-05,
"logits/chosen": -1.9634509086608887,
"logits/rejected": -2.260413646697998,
"logps/chosen": -398.9476013183594,
"logps/rejected": -540.3334350585938,
"loss": 0.029,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.3595480918884277,
"rewards/margins": 6.726611614227295,
"rewards/rejected": -10.086159706115723,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 1.4000000000000001e-05,
"logits/chosen": -1.9712620973587036,
"logits/rejected": -1.827807068824768,
"logps/chosen": -221.26559448242188,
"logps/rejected": -483.7889709472656,
"loss": 0.0063,
"rewards/accuracies": 1.0,
"rewards/chosen": -2.3635034561157227,
"rewards/margins": 7.733745098114014,
"rewards/rejected": -10.097248077392578,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 1.45e-05,
"logits/chosen": -1.542866587638855,
"logits/rejected": -1.7318823337554932,
"logps/chosen": -267.33880615234375,
"logps/rejected": -558.8424072265625,
"loss": 0.0746,
"rewards/accuracies": 0.9375,
"rewards/chosen": -3.391514301300049,
"rewards/margins": 9.136863708496094,
"rewards/rejected": -12.528377532958984,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 1.5e-05,
"logits/chosen": -2.037372589111328,
"logits/rejected": -1.8312575817108154,
"logps/chosen": -288.1588134765625,
"logps/rejected": -670.7269287109375,
"loss": 0.0007,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.795253276824951,
"rewards/margins": 11.858222961425781,
"rewards/rejected": -15.653478622436523,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 1.55e-05,
"logits/chosen": -1.5374680757522583,
"logits/rejected": -1.8392678499221802,
"logps/chosen": -281.0010070800781,
"logps/rejected": -553.43017578125,
"loss": 0.0149,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.836461067199707,
"rewards/margins": 9.380411148071289,
"rewards/rejected": -13.216873168945312,
"step": 31
},
{
"epoch": 0.04,
"learning_rate": 1.6000000000000003e-05,
"logits/chosen": -2.033914566040039,
"logits/rejected": -1.9804089069366455,
"logps/chosen": -261.31103515625,
"logps/rejected": -545.380126953125,
"loss": 0.0123,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.321026802062988,
"rewards/margins": 9.96163272857666,
"rewards/rejected": -14.282659530639648,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 1.65e-05,
"logits/chosen": -1.652747631072998,
"logits/rejected": -1.6527116298675537,
"logps/chosen": -250.82638549804688,
"logps/rejected": -536.0584106445312,
"loss": 0.0017,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.393105506896973,
"rewards/margins": 11.006621360778809,
"rewards/rejected": -15.399725914001465,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 1.7000000000000003e-05,
"logits/chosen": -1.5870184898376465,
"logits/rejected": -1.9295532703399658,
"logps/chosen": -276.73248291015625,
"logps/rejected": -588.6087646484375,
"loss": 0.2671,
"rewards/accuracies": 0.875,
"rewards/chosen": -5.017908573150635,
"rewards/margins": 12.34096908569336,
"rewards/rejected": -17.35887908935547,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 1.75e-05,
"logits/chosen": -1.9227735996246338,
"logits/rejected": -1.954828143119812,
"logps/chosen": -266.1369323730469,
"logps/rejected": -550.742919921875,
"loss": 0.0035,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.8841400146484375,
"rewards/margins": 13.669473648071289,
"rewards/rejected": -18.553613662719727,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 1.8e-05,
"logits/chosen": -1.6637210845947266,
"logits/rejected": -1.3936012983322144,
"logps/chosen": -256.7511901855469,
"logps/rejected": -591.1787109375,
"loss": 0.0022,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.027996063232422,
"rewards/margins": 13.286176681518555,
"rewards/rejected": -19.314172744750977,
"step": 36
},
{
"epoch": 0.05,
"learning_rate": 1.85e-05,
"logits/chosen": -1.6170068979263306,
"logits/rejected": -1.6388572454452515,
"logps/chosen": -257.0255126953125,
"logps/rejected": -605.7335205078125,
"loss": 0.0008,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.929409027099609,
"rewards/margins": 14.035564422607422,
"rewards/rejected": -19.9649715423584,
"step": 37
},
{
"epoch": 0.05,
"learning_rate": 1.9e-05,
"logits/chosen": -1.967097520828247,
"logits/rejected": -1.778485894203186,
"logps/chosen": -239.90533447265625,
"logps/rejected": -570.31787109375,
"loss": 0.0839,
"rewards/accuracies": 0.9375,
"rewards/chosen": -6.8724775314331055,
"rewards/margins": 13.892675399780273,
"rewards/rejected": -20.765153884887695,
"step": 38
},
{
"epoch": 0.05,
"learning_rate": 1.9500000000000003e-05,
"logits/chosen": -1.6693722009658813,
"logits/rejected": -1.573314905166626,
"logps/chosen": -349.86480712890625,
"logps/rejected": -702.0185546875,
"loss": 0.0008,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.373364448547363,
"rewards/margins": 15.567668914794922,
"rewards/rejected": -22.941036224365234,
"step": 39
},
{
"epoch": 0.05,
"learning_rate": 2e-05,
"logits/chosen": -1.556606650352478,
"logits/rejected": -1.394392967224121,
"logps/chosen": -213.81959533691406,
"logps/rejected": -637.4287109375,
"loss": 0.041,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.418168067932129,
"rewards/margins": 17.626686096191406,
"rewards/rejected": -22.04485321044922,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 2.05e-05,
"logits/chosen": -1.6436810493469238,
"logits/rejected": -1.7172099351882935,
"logps/chosen": -304.43438720703125,
"logps/rejected": -704.897216796875,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.733709812164307,
"rewards/margins": 19.767263412475586,
"rewards/rejected": -26.500972747802734,
"step": 41
},
{
"epoch": 0.05,
"learning_rate": 2.1e-05,
"logits/chosen": -1.5168399810791016,
"logits/rejected": -1.508206844329834,
"logps/chosen": -262.28515625,
"logps/rejected": -556.9771118164062,
"loss": 0.062,
"rewards/accuracies": 0.9375,
"rewards/chosen": -5.817533493041992,
"rewards/margins": 13.013591766357422,
"rewards/rejected": -18.831125259399414,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 2.15e-05,
"logits/chosen": -1.3590738773345947,
"logits/rejected": -1.1529805660247803,
"logps/chosen": -205.32371520996094,
"logps/rejected": -576.4129638671875,
"loss": 0.002,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.326513290405273,
"rewards/margins": 15.988494873046875,
"rewards/rejected": -21.315006256103516,
"step": 43
},
{
"epoch": 0.05,
"learning_rate": 2.2000000000000003e-05,
"logits/chosen": -1.5084015130996704,
"logits/rejected": -1.5834801197052002,
"logps/chosen": -332.94580078125,
"logps/rejected": -685.3295288085938,
"loss": 0.0038,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.390817642211914,
"rewards/margins": 18.214908599853516,
"rewards/rejected": -25.60572624206543,
"step": 44
},
{
"epoch": 0.06,
"learning_rate": 2.25e-05,
"logits/chosen": -1.4891091585159302,
"logits/rejected": -1.5173286199569702,
"logps/chosen": -250.24951171875,
"logps/rejected": -675.5242309570312,
"loss": 0.0026,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.26884126663208,
"rewards/margins": 19.75680160522461,
"rewards/rejected": -26.025644302368164,
"step": 45
},
{
"epoch": 0.06,
"learning_rate": 2.3000000000000003e-05,
"logits/chosen": -1.433956265449524,
"logits/rejected": -1.5273690223693848,
"logps/chosen": -366.8013000488281,
"logps/rejected": -703.315185546875,
"loss": 0.0103,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.857599258422852,
"rewards/margins": 19.714298248291016,
"rewards/rejected": -26.571901321411133,
"step": 46
},
{
"epoch": 0.06,
"learning_rate": 2.35e-05,
"logits/chosen": -1.351868987083435,
"logits/rejected": -1.2347944974899292,
"logps/chosen": -292.37091064453125,
"logps/rejected": -687.9886474609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.611140251159668,
"rewards/margins": 19.30370330810547,
"rewards/rejected": -26.91484260559082,
"step": 47
},
{
"epoch": 0.06,
"learning_rate": 2.4e-05,
"logits/chosen": -1.3243939876556396,
"logits/rejected": -1.0474777221679688,
"logps/chosen": -292.1935729980469,
"logps/rejected": -626.897705078125,
"loss": 0.0025,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.425950527191162,
"rewards/margins": 17.86639404296875,
"rewards/rejected": -24.292346954345703,
"step": 48
},
{
"epoch": 0.06,
"learning_rate": 2.45e-05,
"logits/chosen": -0.9694186449050903,
"logits/rejected": -1.2784701585769653,
"logps/chosen": -260.8387756347656,
"logps/rejected": -618.62451171875,
"loss": 0.1257,
"rewards/accuracies": 0.9375,
"rewards/chosen": -6.1030497550964355,
"rewards/margins": 18.54592514038086,
"rewards/rejected": -24.648975372314453,
"step": 49
},
{
"epoch": 0.06,
"learning_rate": 2.5e-05,
"logits/chosen": -0.9199879765510559,
"logits/rejected": -1.2466750144958496,
"logps/chosen": -430.0943603515625,
"logps/rejected": -720.2520141601562,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.701850891113281,
"rewards/margins": 16.992839813232422,
"rewards/rejected": -25.694692611694336,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 2.5500000000000003e-05,
"logits/chosen": -0.9574620127677917,
"logits/rejected": -1.1837575435638428,
"logps/chosen": -301.4226379394531,
"logps/rejected": -568.0577392578125,
"loss": 0.0033,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.406881332397461,
"rewards/margins": 13.906658172607422,
"rewards/rejected": -20.313539505004883,
"step": 51
},
{
"epoch": 0.06,
"learning_rate": 2.6000000000000002e-05,
"logits/chosen": -1.3775969743728638,
"logits/rejected": -1.1746721267700195,
"logps/chosen": -292.12841796875,
"logps/rejected": -541.6993408203125,
"loss": 0.0143,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.582497596740723,
"rewards/margins": 13.31058120727539,
"rewards/rejected": -19.893077850341797,
"step": 52
},
{
"epoch": 0.07,
"learning_rate": 2.6500000000000004e-05,
"logits/chosen": -1.5340209007263184,
"logits/rejected": -1.5800985097885132,
"logps/chosen": -274.92852783203125,
"logps/rejected": -618.4048461914062,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.103458404541016,
"rewards/margins": 16.42413330078125,
"rewards/rejected": -22.527591705322266,
"step": 53
},
{
"epoch": 0.07,
"learning_rate": 2.7000000000000002e-05,
"logits/chosen": -1.1566357612609863,
"logits/rejected": -1.3419249057769775,
"logps/chosen": -266.595458984375,
"logps/rejected": -609.8141479492188,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.4973931312561035,
"rewards/margins": 17.105182647705078,
"rewards/rejected": -22.602575302124023,
"step": 54
},
{
"epoch": 0.07,
"learning_rate": 2.7500000000000004e-05,
"logits/chosen": -1.1755287647247314,
"logits/rejected": -1.436917781829834,
"logps/chosen": -293.0464172363281,
"logps/rejected": -614.6860961914062,
"loss": 0.038,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.360505104064941,
"rewards/margins": 17.14010238647461,
"rewards/rejected": -23.5006103515625,
"step": 55
},
{
"epoch": 0.07,
"learning_rate": 2.8000000000000003e-05,
"logits/chosen": -0.9510018825531006,
"logits/rejected": -1.4989765882492065,
"logps/chosen": -246.72573852539062,
"logps/rejected": -593.3004760742188,
"loss": 0.0019,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.071164131164551,
"rewards/margins": 16.324851989746094,
"rewards/rejected": -21.396015167236328,
"step": 56
},
{
"epoch": 0.07,
"learning_rate": 2.8499999999999998e-05,
"logits/chosen": -0.8883547782897949,
"logits/rejected": -0.8475340604782104,
"logps/chosen": -284.69122314453125,
"logps/rejected": -582.0223999023438,
"loss": 0.092,
"rewards/accuracies": 0.9375,
"rewards/chosen": -5.555781364440918,
"rewards/margins": 15.147626876831055,
"rewards/rejected": -20.703407287597656,
"step": 57
},
{
"epoch": 0.07,
"learning_rate": 2.9e-05,
"logits/chosen": -1.420696496963501,
"logits/rejected": -1.3382985591888428,
"logps/chosen": -223.16297912597656,
"logps/rejected": -681.352294921875,
"loss": 0.0027,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.9901018142700195,
"rewards/margins": 20.429107666015625,
"rewards/rejected": -25.419208526611328,
"step": 58
},
{
"epoch": 0.07,
"learning_rate": 2.95e-05,
"logits/chosen": -1.037627100944519,
"logits/rejected": -1.745126485824585,
"logps/chosen": -249.64974975585938,
"logps/rejected": -605.685546875,
"loss": 0.097,
"rewards/accuracies": 0.9375,
"rewards/chosen": -5.2863945960998535,
"rewards/margins": 16.568225860595703,
"rewards/rejected": -21.8546199798584,
"step": 59
},
{
"epoch": 0.07,
"learning_rate": 3e-05,
"logits/chosen": -1.1528346538543701,
"logits/rejected": -1.5133743286132812,
"logps/chosen": -319.42352294921875,
"logps/rejected": -627.826171875,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.5534515380859375,
"rewards/margins": 16.326492309570312,
"rewards/rejected": -21.87994384765625,
"step": 60
},
{
"epoch": 0.08,
"learning_rate": 3.05e-05,
"logits/chosen": -1.4599294662475586,
"logits/rejected": -1.4529486894607544,
"logps/chosen": -292.13299560546875,
"logps/rejected": -663.6395263671875,
"loss": 0.0036,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.249754905700684,
"rewards/margins": 16.525672912597656,
"rewards/rejected": -21.775428771972656,
"step": 61
},
{
"epoch": 0.08,
"learning_rate": 3.1e-05,
"logits/chosen": -1.3739594221115112,
"logits/rejected": -1.441535472869873,
"logps/chosen": -361.3265380859375,
"logps/rejected": -623.9736938476562,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.781492233276367,
"rewards/margins": 16.213455200195312,
"rewards/rejected": -20.99494743347168,
"step": 62
},
{
"epoch": 0.08,
"learning_rate": 3.15e-05,
"logits/chosen": -1.0977773666381836,
"logits/rejected": -1.2894166707992554,
"logps/chosen": -272.4936828613281,
"logps/rejected": -633.6181640625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.058845520019531,
"rewards/margins": 18.464832305908203,
"rewards/rejected": -23.523677825927734,
"step": 63
},
{
"epoch": 0.08,
"learning_rate": 3.2000000000000005e-05,
"logits/chosen": -1.8300187587738037,
"logits/rejected": -1.3356730937957764,
"logps/chosen": -311.8466796875,
"logps/rejected": -677.257568359375,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.877348899841309,
"rewards/margins": 16.247228622436523,
"rewards/rejected": -22.124576568603516,
"step": 64
},
{
"epoch": 0.08,
"learning_rate": 3.2500000000000004e-05,
"logits/chosen": -1.6267454624176025,
"logits/rejected": -1.1310009956359863,
"logps/chosen": -358.5579833984375,
"logps/rejected": -641.7317504882812,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.5671796798706055,
"rewards/margins": 15.705550193786621,
"rewards/rejected": -21.27273178100586,
"step": 65
},
{
"epoch": 0.08,
"learning_rate": 3.3e-05,
"logits/chosen": -1.8895033597946167,
"logits/rejected": -1.6860744953155518,
"logps/chosen": -486.3850402832031,
"logps/rejected": -664.045166015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.0797834396362305,
"rewards/margins": 13.979126930236816,
"rewards/rejected": -19.058910369873047,
"step": 66
},
{
"epoch": 0.08,
"learning_rate": 3.35e-05,
"logits/chosen": -1.836645483970642,
"logits/rejected": -1.4774869680404663,
"logps/chosen": -261.5281982421875,
"logps/rejected": -621.8162841796875,
"loss": 0.0011,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.790907382965088,
"rewards/margins": 14.66439437866211,
"rewards/rejected": -19.45530128479004,
"step": 67
},
{
"epoch": 0.08,
"learning_rate": 3.4000000000000007e-05,
"logits/chosen": -1.4897315502166748,
"logits/rejected": -1.2426286935806274,
"logps/chosen": -225.94337463378906,
"logps/rejected": -547.6304321289062,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.037389755249023,
"rewards/margins": 13.804460525512695,
"rewards/rejected": -17.84185028076172,
"step": 68
},
{
"epoch": 0.09,
"learning_rate": 3.45e-05,
"logits/chosen": -1.3410481214523315,
"logits/rejected": -1.2696239948272705,
"logps/chosen": -220.23153686523438,
"logps/rejected": -545.1270751953125,
"loss": 0.0035,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.0619893074035645,
"rewards/margins": 14.104720115661621,
"rewards/rejected": -18.166709899902344,
"step": 69
},
{
"epoch": 0.09,
"learning_rate": 3.5e-05,
"logits/chosen": -1.1692075729370117,
"logits/rejected": -1.4098597764968872,
"logps/chosen": -291.9318542480469,
"logps/rejected": -606.8259887695312,
"loss": 0.037,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.749131679534912,
"rewards/margins": 13.3434476852417,
"rewards/rejected": -18.09257698059082,
"step": 70
},
{
"epoch": 0.09,
"learning_rate": 3.55e-05,
"logits/chosen": -1.291015386581421,
"logits/rejected": -1.0744752883911133,
"logps/chosen": -235.30746459960938,
"logps/rejected": -571.0240478515625,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -3.615610122680664,
"rewards/margins": 14.394880294799805,
"rewards/rejected": -18.01049041748047,
"step": 71
},
{
"epoch": 0.09,
"learning_rate": 3.6e-05,
"logits/chosen": -1.3118032217025757,
"logits/rejected": -1.3245186805725098,
"logps/chosen": -278.8104248046875,
"logps/rejected": -621.2532958984375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.277045249938965,
"rewards/margins": 17.554424285888672,
"rewards/rejected": -21.831466674804688,
"step": 72
},
{
"epoch": 0.09,
"learning_rate": 3.65e-05,
"logits/chosen": -1.5896751880645752,
"logits/rejected": -1.3609411716461182,
"logps/chosen": -243.6151123046875,
"logps/rejected": -572.5302124023438,
"loss": 0.0006,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.514758110046387,
"rewards/margins": 12.668429374694824,
"rewards/rejected": -17.183185577392578,
"step": 73
},
{
"epoch": 0.09,
"learning_rate": 3.7e-05,
"logits/chosen": -1.431384801864624,
"logits/rejected": -1.5531063079833984,
"logps/chosen": -306.5356750488281,
"logps/rejected": -600.71484375,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.694637298583984,
"rewards/margins": 18.718229293823242,
"rewards/rejected": -23.412864685058594,
"step": 74
},
{
"epoch": 0.09,
"learning_rate": 3.7500000000000003e-05,
"logits/chosen": -1.557645559310913,
"logits/rejected": -1.5208816528320312,
"logps/chosen": -258.01324462890625,
"logps/rejected": -619.49462890625,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.0902862548828125,
"rewards/margins": 15.939676284790039,
"rewards/rejected": -21.029964447021484,
"step": 75
},
{
"epoch": 0.09,
"learning_rate": 3.8e-05,
"logits/chosen": -1.0553147792816162,
"logits/rejected": -1.5524070262908936,
"logps/chosen": -309.97412109375,
"logps/rejected": -524.318603515625,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.439201354980469,
"rewards/margins": 13.217429161071777,
"rewards/rejected": -17.656631469726562,
"step": 76
},
{
"epoch": 0.1,
"learning_rate": 3.85e-05,
"logits/chosen": -1.3808860778808594,
"logits/rejected": -1.490052342414856,
"logps/chosen": -249.54974365234375,
"logps/rejected": -647.080078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.671748161315918,
"rewards/margins": 17.54851531982422,
"rewards/rejected": -23.220260620117188,
"step": 77
},
{
"epoch": 0.1,
"learning_rate": 3.9000000000000006e-05,
"logits/chosen": -1.6017792224884033,
"logits/rejected": -1.437800407409668,
"logps/chosen": -270.47894287109375,
"logps/rejected": -523.1994018554688,
"loss": 0.0107,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.677766799926758,
"rewards/margins": 13.664579391479492,
"rewards/rejected": -19.34234619140625,
"step": 78
},
{
"epoch": 0.1,
"learning_rate": 3.9500000000000005e-05,
"logits/chosen": -1.7644150257110596,
"logits/rejected": -1.1649854183197021,
"logps/chosen": -352.513671875,
"logps/rejected": -660.660888671875,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.161036968231201,
"rewards/margins": 15.742412567138672,
"rewards/rejected": -21.90345001220703,
"step": 79
},
{
"epoch": 0.1,
"learning_rate": 4e-05,
"logits/chosen": -1.7110097408294678,
"logits/rejected": -1.4986464977264404,
"logps/chosen": -285.781005859375,
"logps/rejected": -601.8524780273438,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.4479594230651855,
"rewards/margins": 17.196250915527344,
"rewards/rejected": -23.644210815429688,
"step": 80
},
{
"epoch": 0.1,
"learning_rate": 4.05e-05,
"logits/chosen": -1.5364179611206055,
"logits/rejected": -1.5603926181793213,
"logps/chosen": -205.1665802001953,
"logps/rejected": -514.8365478515625,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.383946418762207,
"rewards/margins": 13.479593276977539,
"rewards/rejected": -18.863540649414062,
"step": 81
},
{
"epoch": 0.1,
"learning_rate": 4.1e-05,
"logits/chosen": -1.2903649806976318,
"logits/rejected": -1.077599287033081,
"logps/chosen": -240.99749755859375,
"logps/rejected": -672.7728271484375,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.660610675811768,
"rewards/margins": 18.02043914794922,
"rewards/rejected": -23.681049346923828,
"step": 82
},
{
"epoch": 0.1,
"learning_rate": 4.15e-05,
"logits/chosen": -1.2030022144317627,
"logits/rejected": -1.4182593822479248,
"logps/chosen": -302.1430358886719,
"logps/rejected": -677.5120849609375,
"loss": 0.0056,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.275785446166992,
"rewards/margins": 16.768428802490234,
"rewards/rejected": -23.044212341308594,
"step": 83
},
{
"epoch": 0.1,
"learning_rate": 4.2e-05,
"logits/chosen": -1.459336519241333,
"logits/rejected": -1.0312726497650146,
"logps/chosen": -303.3758544921875,
"logps/rejected": -617.7279052734375,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.219513416290283,
"rewards/margins": 14.163326263427734,
"rewards/rejected": -21.38283920288086,
"step": 84
},
{
"epoch": 0.11,
"learning_rate": 4.25e-05,
"logits/chosen": -1.6425917148590088,
"logits/rejected": -1.1666898727416992,
"logps/chosen": -349.3736267089844,
"logps/rejected": -678.3955078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.792992115020752,
"rewards/margins": 19.550434112548828,
"rewards/rejected": -27.343425750732422,
"step": 85
},
{
"epoch": 0.11,
"learning_rate": 4.3e-05,
"logits/chosen": -1.159060001373291,
"logits/rejected": -1.2317029237747192,
"logps/chosen": -377.60040283203125,
"logps/rejected": -658.4701538085938,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.494105339050293,
"rewards/margins": 16.188596725463867,
"rewards/rejected": -24.682701110839844,
"step": 86
},
{
"epoch": 0.11,
"learning_rate": 4.35e-05,
"logits/chosen": -1.5545859336853027,
"logits/rejected": -1.2424968481063843,
"logps/chosen": -332.1812744140625,
"logps/rejected": -686.550537109375,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.362907409667969,
"rewards/margins": 18.219987869262695,
"rewards/rejected": -25.58289337158203,
"step": 87
},
{
"epoch": 0.11,
"learning_rate": 4.4000000000000006e-05,
"logits/chosen": -1.329568862915039,
"logits/rejected": -1.5836312770843506,
"logps/chosen": -344.522705078125,
"logps/rejected": -663.6416015625,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.556987762451172,
"rewards/margins": 16.531614303588867,
"rewards/rejected": -25.08860206604004,
"step": 88
},
{
"epoch": 0.11,
"learning_rate": 4.4500000000000004e-05,
"logits/chosen": -0.9687823057174683,
"logits/rejected": -1.0615956783294678,
"logps/chosen": -248.99139404296875,
"logps/rejected": -666.9677734375,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.284422874450684,
"rewards/margins": 18.494182586669922,
"rewards/rejected": -25.778606414794922,
"step": 89
},
{
"epoch": 0.11,
"learning_rate": 4.5e-05,
"logits/chosen": -1.5608181953430176,
"logits/rejected": -1.603400707244873,
"logps/chosen": -406.6678161621094,
"logps/rejected": -738.91015625,
"loss": 0.0006,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.280235290527344,
"rewards/margins": 20.654300689697266,
"rewards/rejected": -28.93453598022461,
"step": 90
},
{
"epoch": 0.11,
"learning_rate": 4.55e-05,
"logits/chosen": -1.1856168508529663,
"logits/rejected": -1.2493767738342285,
"logps/chosen": -248.82559204101562,
"logps/rejected": -637.666259765625,
"loss": 0.0007,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.917981147766113,
"rewards/margins": 18.320941925048828,
"rewards/rejected": -25.238922119140625,
"step": 91
},
{
"epoch": 0.11,
"learning_rate": 4.600000000000001e-05,
"logits/chosen": -1.4266817569732666,
"logits/rejected": -1.3622314929962158,
"logps/chosen": -236.7372283935547,
"logps/rejected": -677.9640502929688,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.995168685913086,
"rewards/margins": 21.01068687438965,
"rewards/rejected": -29.005855560302734,
"step": 92
},
{
"epoch": 0.12,
"learning_rate": 4.6500000000000005e-05,
"logits/chosen": -1.1082837581634521,
"logits/rejected": -1.383658528327942,
"logps/chosen": -314.92681884765625,
"logps/rejected": -658.524169921875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.042872428894043,
"rewards/margins": 17.163429260253906,
"rewards/rejected": -26.206302642822266,
"step": 93
},
{
"epoch": 0.12,
"learning_rate": 4.7e-05,
"logits/chosen": -1.5014522075653076,
"logits/rejected": -1.7101225852966309,
"logps/chosen": -260.1839904785156,
"logps/rejected": -683.700927734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.463061332702637,
"rewards/margins": 17.54586410522461,
"rewards/rejected": -27.008926391601562,
"step": 94
},
{
"epoch": 0.12,
"learning_rate": 4.75e-05,
"logits/chosen": -1.5970165729522705,
"logits/rejected": -1.3586769104003906,
"logps/chosen": -318.0454406738281,
"logps/rejected": -684.9884033203125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.960655212402344,
"rewards/margins": 20.025028228759766,
"rewards/rejected": -29.985679626464844,
"step": 95
},
{
"epoch": 0.12,
"learning_rate": 4.8e-05,
"logits/chosen": -1.1033860445022583,
"logits/rejected": -0.8102812767028809,
"logps/chosen": -301.2135925292969,
"logps/rejected": -720.0145263671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.136268615722656,
"rewards/margins": 20.93104362487793,
"rewards/rejected": -29.067312240600586,
"step": 96
},
{
"epoch": 0.12,
"learning_rate": 4.85e-05,
"logits/chosen": -1.1413370370864868,
"logits/rejected": -0.9585047960281372,
"logps/chosen": -329.30133056640625,
"logps/rejected": -630.4498291015625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.226066589355469,
"rewards/margins": 16.47555923461914,
"rewards/rejected": -25.70162582397461,
"step": 97
},
{
"epoch": 0.12,
"learning_rate": 4.9e-05,
"logits/chosen": -1.5005364418029785,
"logits/rejected": -1.1674431562423706,
"logps/chosen": -264.9545593261719,
"logps/rejected": -639.041259765625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.097036361694336,
"rewards/margins": 17.606611251831055,
"rewards/rejected": -25.70364761352539,
"step": 98
},
{
"epoch": 0.12,
"learning_rate": 4.9500000000000004e-05,
"logits/chosen": -1.181979775428772,
"logits/rejected": -1.1194593906402588,
"logps/chosen": -295.6553955078125,
"logps/rejected": -625.8030395507812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.671294212341309,
"rewards/margins": 18.466283798217773,
"rewards/rejected": -26.1375789642334,
"step": 99
},
{
"epoch": 0.12,
"learning_rate": 5e-05,
"logits/chosen": -1.6407731771469116,
"logits/rejected": -1.7556546926498413,
"logps/chosen": -251.4920654296875,
"logps/rejected": -707.2771606445312,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.03681468963623,
"rewards/margins": 19.950708389282227,
"rewards/rejected": -28.98752212524414,
"step": 100
},
{
"epoch": 0.13,
"learning_rate": 4.998766400914329e-05,
"logits/chosen": -1.49093496799469,
"logits/rejected": -1.454042673110962,
"logps/chosen": -401.38555908203125,
"logps/rejected": -656.6805419921875,
"loss": 0.0004,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.029119491577148,
"rewards/margins": 17.11648941040039,
"rewards/rejected": -26.14560890197754,
"step": 101
},
{
"epoch": 0.13,
"learning_rate": 4.995066821070679e-05,
"logits/chosen": -1.1679431200027466,
"logits/rejected": -1.1486090421676636,
"logps/chosen": -378.21893310546875,
"logps/rejected": -720.4594116210938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.716445922851562,
"rewards/margins": 19.0845947265625,
"rewards/rejected": -28.801040649414062,
"step": 102
},
{
"epoch": 0.13,
"learning_rate": 4.9889049115077005e-05,
"logits/chosen": -1.0046123266220093,
"logits/rejected": -1.2339215278625488,
"logps/chosen": -258.95635986328125,
"logps/rejected": -639.7680053710938,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.76823902130127,
"rewards/margins": 18.9598388671875,
"rewards/rejected": -27.728076934814453,
"step": 103
},
{
"epoch": 0.13,
"learning_rate": 4.980286753286195e-05,
"logits/chosen": -0.9866207242012024,
"logits/rejected": -1.2342731952667236,
"logps/chosen": -353.4874267578125,
"logps/rejected": -652.6710205078125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.72028923034668,
"rewards/margins": 18.17083740234375,
"rewards/rejected": -26.891128540039062,
"step": 104
},
{
"epoch": 0.13,
"learning_rate": 4.9692208514878444e-05,
"logits/chosen": -1.644493818283081,
"logits/rejected": -1.3671150207519531,
"logps/chosen": -407.6358337402344,
"logps/rejected": -680.9503784179688,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.58061408996582,
"rewards/margins": 16.537212371826172,
"rewards/rejected": -26.117826461791992,
"step": 105
},
{
"epoch": 0.13,
"learning_rate": 4.9557181268217227e-05,
"logits/chosen": -1.3883347511291504,
"logits/rejected": -1.1226028203964233,
"logps/chosen": -298.3403625488281,
"logps/rejected": -661.0068969726562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.479090690612793,
"rewards/margins": 19.53042984008789,
"rewards/rejected": -28.009523391723633,
"step": 106
},
{
"epoch": 0.13,
"learning_rate": 4.939791904846869e-05,
"logits/chosen": -1.2119803428649902,
"logits/rejected": -1.5936832427978516,
"logps/chosen": -269.82684326171875,
"logps/rejected": -645.09619140625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.107880592346191,
"rewards/margins": 20.64764976501465,
"rewards/rejected": -28.755531311035156,
"step": 107
},
{
"epoch": 0.13,
"learning_rate": 4.9214579028215776e-05,
"logits/chosen": -1.2132232189178467,
"logits/rejected": -1.3179054260253906,
"logps/chosen": -438.98321533203125,
"logps/rejected": -713.7950439453125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.158727645874023,
"rewards/margins": 17.90839958190918,
"rewards/rejected": -28.06713104248047,
"step": 108
},
{
"epoch": 0.14,
"learning_rate": 4.900734214192358e-05,
"logits/chosen": -1.0279672145843506,
"logits/rejected": -0.8536261320114136,
"logps/chosen": -382.6248779296875,
"logps/rejected": -738.4147338867188,
"loss": 0.0034,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.301639556884766,
"rewards/margins": 20.556997299194336,
"rewards/rejected": -28.858638763427734,
"step": 109
},
{
"epoch": 0.14,
"learning_rate": 4.877641290737884e-05,
"logits/chosen": -1.1681768894195557,
"logits/rejected": -0.6321386694908142,
"logps/chosen": -295.9759521484375,
"logps/rejected": -673.0234375,
"loss": 0.0168,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.42588996887207,
"rewards/margins": 17.69922637939453,
"rewards/rejected": -28.12511444091797,
"step": 110
},
{
"epoch": 0.14,
"learning_rate": 4.852201922385564e-05,
"logits/chosen": -0.6276636123657227,
"logits/rejected": -0.6425186991691589,
"logps/chosen": -268.58050537109375,
"logps/rejected": -601.134033203125,
"loss": 0.0005,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.623042583465576,
"rewards/margins": 20.134323120117188,
"rewards/rejected": -26.75736427307129,
"step": 111
},
{
"epoch": 0.14,
"learning_rate": 4.8244412147206284e-05,
"logits/chosen": -1.298043966293335,
"logits/rejected": -1.8934366703033447,
"logps/chosen": -363.50616455078125,
"logps/rejected": -793.5181274414062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.013703346252441,
"rewards/margins": 21.266841888427734,
"rewards/rejected": -30.28054428100586,
"step": 112
},
{
"epoch": 0.14,
"learning_rate": 4.794386564209953e-05,
"logits/chosen": -1.3218209743499756,
"logits/rejected": -0.8168056011199951,
"logps/chosen": -306.5829772949219,
"logps/rejected": -696.270263671875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.502519607543945,
"rewards/margins": 23.955406188964844,
"rewards/rejected": -31.457927703857422,
"step": 113
},
{
"epoch": 0.14,
"learning_rate": 4.762067631165049e-05,
"logits/chosen": -1.1450629234313965,
"logits/rejected": -1.393950343132019,
"logps/chosen": -376.8450622558594,
"logps/rejected": -673.3822631835938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.097296714782715,
"rewards/margins": 18.731908798217773,
"rewards/rejected": -27.829204559326172,
"step": 114
},
{
"epoch": 0.14,
"learning_rate": 4.72751631047092e-05,
"logits/chosen": -1.3087085485458374,
"logits/rejected": -1.6303530931472778,
"logps/chosen": -272.7848205566406,
"logps/rejected": -697.6502685546875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.2123308181762695,
"rewards/margins": 22.104957580566406,
"rewards/rejected": -29.31728744506836,
"step": 115
},
{
"epoch": 0.14,
"learning_rate": 4.690766700109659e-05,
"logits/chosen": -1.3388525247573853,
"logits/rejected": -1.523690938949585,
"logps/chosen": -281.05694580078125,
"logps/rejected": -593.7879028320312,
"loss": 0.0035,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.953818321228027,
"rewards/margins": 17.667112350463867,
"rewards/rejected": -23.620929718017578,
"step": 116
},
{
"epoch": 0.15,
"learning_rate": 4.65185506750986e-05,
"logits/chosen": -1.3922251462936401,
"logits/rejected": -1.2891855239868164,
"logps/chosen": -322.259765625,
"logps/rejected": -654.0626220703125,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.73513126373291,
"rewards/margins": 19.120628356933594,
"rewards/rejected": -25.855758666992188,
"step": 117
},
{
"epoch": 0.15,
"learning_rate": 4.610819813755038e-05,
"logits/chosen": -1.0762147903442383,
"logits/rejected": -1.2459900379180908,
"logps/chosen": -339.0086364746094,
"logps/rejected": -729.5966796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.075998306274414,
"rewards/margins": 22.65298843383789,
"rewards/rejected": -29.728988647460938,
"step": 118
},
{
"epoch": 0.15,
"learning_rate": 4.567701435686404e-05,
"logits/chosen": -1.4852521419525146,
"logits/rejected": -1.3211164474487305,
"logps/chosen": -221.89089965820312,
"logps/rejected": -554.428466796875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.827755928039551,
"rewards/margins": 15.966878890991211,
"rewards/rejected": -22.794635772705078,
"step": 119
},
{
"epoch": 0.15,
"learning_rate": 4.522542485937369e-05,
"logits/chosen": -1.4120067358016968,
"logits/rejected": -1.1943210363388062,
"logps/chosen": -251.79034423828125,
"logps/rejected": -700.6851196289062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.087055206298828,
"rewards/margins": 20.131147384643555,
"rewards/rejected": -26.218202590942383,
"step": 120
},
{
"epoch": 0.15,
"learning_rate": 4.4753875309392266e-05,
"logits/chosen": -1.564077377319336,
"logits/rejected": -1.4048410654067993,
"logps/chosen": -260.0417175292969,
"logps/rejected": -702.1083984375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.242954730987549,
"rewards/margins": 23.306888580322266,
"rewards/rejected": -30.549842834472656,
"step": 121
},
{
"epoch": 0.15,
"learning_rate": 4.426283106939474e-05,
"logits/chosen": -1.6456904411315918,
"logits/rejected": -1.3609850406646729,
"logps/chosen": -267.5194396972656,
"logps/rejected": -620.3526611328125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.6236772537231445,
"rewards/margins": 17.591167449951172,
"rewards/rejected": -24.21484375,
"step": 122
},
{
"epoch": 0.15,
"learning_rate": 4.375277674076149e-05,
"logits/chosen": -0.8970831632614136,
"logits/rejected": -1.2291415929794312,
"logps/chosen": -263.4637451171875,
"logps/rejected": -561.6110229492188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.951724052429199,
"rewards/margins": 17.361831665039062,
"rewards/rejected": -23.313554763793945,
"step": 123
},
{
"epoch": 0.15,
"learning_rate": 4.3224215685535294e-05,
"logits/chosen": -1.5338877439498901,
"logits/rejected": -1.3900439739227295,
"logps/chosen": -266.0079345703125,
"logps/rejected": -646.4955444335938,
"loss": 0.0002,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.709009170532227,
"rewards/margins": 20.428083419799805,
"rewards/rejected": -27.1370906829834,
"step": 124
},
{
"epoch": 0.16,
"learning_rate": 4.267766952966369e-05,
"logits/chosen": -1.0960302352905273,
"logits/rejected": -1.468554139137268,
"logps/chosen": -285.5207214355469,
"logps/rejected": -672.1173095703125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -4.691971302032471,
"rewards/margins": 24.13559913635254,
"rewards/rejected": -28.82756996154785,
"step": 125
},
{
"epoch": 0.16,
"learning_rate": 4.211367764821722e-05,
"logits/chosen": -2.010265588760376,
"logits/rejected": -1.6019049882888794,
"logps/chosen": -354.89190673828125,
"logps/rejected": -666.0311279296875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.3796706199646,
"rewards/margins": 19.254438400268555,
"rewards/rejected": -25.634109497070312,
"step": 126
},
{
"epoch": 0.16,
"learning_rate": 4.1532796633091296e-05,
"logits/chosen": -1.8576483726501465,
"logits/rejected": -1.5691324472427368,
"logps/chosen": -286.91375732421875,
"logps/rejected": -716.0498046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.725906848907471,
"rewards/margins": 24.17666244506836,
"rewards/rejected": -30.902565002441406,
"step": 127
},
{
"epoch": 0.16,
"learning_rate": 4.093559974371725e-05,
"logits/chosen": -1.9219647645950317,
"logits/rejected": -1.7591352462768555,
"logps/chosen": -364.5614318847656,
"logps/rejected": -736.0914306640625,
"loss": 0.0015,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.333095550537109,
"rewards/margins": 23.11652946472168,
"rewards/rejected": -30.44962501525879,
"step": 128
},
{
"epoch": 0.16,
"learning_rate": 4.0322676341324415e-05,
"logits/chosen": -1.2601250410079956,
"logits/rejected": -1.2032322883605957,
"logps/chosen": -316.52935791015625,
"logps/rejected": -660.7392578125,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.681999206542969,
"rewards/margins": 18.961524963378906,
"rewards/rejected": -25.643526077270508,
"step": 129
},
{
"epoch": 0.16,
"learning_rate": 3.969463130731183e-05,
"logits/chosen": -1.1819369792938232,
"logits/rejected": -1.330411672592163,
"logps/chosen": -334.45440673828125,
"logps/rejected": -668.8825073242188,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.4721527099609375,
"rewards/margins": 20.78248405456543,
"rewards/rejected": -27.254636764526367,
"step": 130
},
{
"epoch": 0.16,
"learning_rate": 3.905208444630327e-05,
"logits/chosen": -1.359390377998352,
"logits/rejected": -1.4633076190948486,
"logps/chosen": -449.515869140625,
"logps/rejected": -722.9254760742188,
"loss": 0.0009,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.208673477172852,
"rewards/margins": 17.24679946899414,
"rewards/rejected": -25.45547103881836,
"step": 131
},
{
"epoch": 0.16,
"learning_rate": 3.8395669874474915e-05,
"logits/chosen": -1.5751495361328125,
"logits/rejected": -1.4079082012176514,
"logps/chosen": -316.51824951171875,
"logps/rejected": -690.4049072265625,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.716471195220947,
"rewards/margins": 21.65338134765625,
"rewards/rejected": -28.369853973388672,
"step": 132
},
{
"epoch": 0.17,
"learning_rate": 3.7726035393759285e-05,
"logits/chosen": -1.5979351997375488,
"logits/rejected": -1.5114738941192627,
"logps/chosen": -395.20916748046875,
"logps/rejected": -718.419677734375,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.750358581542969,
"rewards/margins": 18.212371826171875,
"rewards/rejected": -25.96272850036621,
"step": 133
},
{
"epoch": 0.17,
"learning_rate": 3.704384185254288e-05,
"logits/chosen": -1.5029571056365967,
"logits/rejected": -1.4255585670471191,
"logps/chosen": -254.38461303710938,
"logps/rejected": -803.1172485351562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.148038387298584,
"rewards/margins": 28.40212059020996,
"rewards/rejected": -34.5501594543457,
"step": 134
},
{
"epoch": 0.17,
"learning_rate": 3.634976249348867e-05,
"logits/chosen": -1.0641860961914062,
"logits/rejected": -1.3426963090896606,
"logps/chosen": -322.1287536621094,
"logps/rejected": -627.5282592773438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.379766464233398,
"rewards/margins": 17.175968170166016,
"rewards/rejected": -24.555734634399414,
"step": 135
},
{
"epoch": 0.17,
"learning_rate": 3.564448228912682e-05,
"logits/chosen": -1.4602770805358887,
"logits/rejected": -1.4505391120910645,
"logps/chosen": -343.05450439453125,
"logps/rejected": -651.352783203125,
"loss": 0.0052,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.195021629333496,
"rewards/margins": 18.67833709716797,
"rewards/rejected": -26.87335777282715,
"step": 136
},
{
"epoch": 0.17,
"learning_rate": 3.4928697265869515e-05,
"logits/chosen": -1.2342597246170044,
"logits/rejected": -0.98235023021698,
"logps/chosen": -267.2305603027344,
"logps/rejected": -662.8800048828125,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -5.990522384643555,
"rewards/margins": 20.408323287963867,
"rewards/rejected": -26.39884376525879,
"step": 137
},
{
"epoch": 0.17,
"learning_rate": 3.4203113817116957e-05,
"logits/chosen": -1.5317420959472656,
"logits/rejected": -1.4648504257202148,
"logps/chosen": -291.79547119140625,
"logps/rejected": -663.3065795898438,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.487759590148926,
"rewards/margins": 20.33439064025879,
"rewards/rejected": -27.8221492767334,
"step": 138
},
{
"epoch": 0.17,
"learning_rate": 3.346844800613229e-05,
"logits/chosen": -1.0398391485214233,
"logits/rejected": -1.127720832824707,
"logps/chosen": -310.21142578125,
"logps/rejected": -683.2669677734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.429044723510742,
"rewards/margins": 19.585290908813477,
"rewards/rejected": -26.01433753967285,
"step": 139
},
{
"epoch": 0.17,
"learning_rate": 3.272542485937369e-05,
"logits/chosen": -1.1515860557556152,
"logits/rejected": -1.2663438320159912,
"logps/chosen": -311.65545654296875,
"logps/rejected": -805.0521850585938,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.75864315032959,
"rewards/margins": 26.559768676757812,
"rewards/rejected": -35.31841278076172,
"step": 140
},
{
"epoch": 0.18,
"learning_rate": 3.1974777650980735e-05,
"logits/chosen": -1.6724903583526611,
"logits/rejected": -1.2102152109146118,
"logps/chosen": -216.79110717773438,
"logps/rejected": -664.1553344726562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.002614498138428,
"rewards/margins": 23.148998260498047,
"rewards/rejected": -29.151615142822266,
"step": 141
},
{
"epoch": 0.18,
"learning_rate": 3.121724717912138e-05,
"logits/chosen": -1.2503281831741333,
"logits/rejected": -1.4109008312225342,
"logps/chosen": -257.79205322265625,
"logps/rejected": -626.7386474609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.028193473815918,
"rewards/margins": 20.606430053710938,
"rewards/rejected": -28.63462257385254,
"step": 142
},
{
"epoch": 0.18,
"learning_rate": 3.045358103491357e-05,
"logits/chosen": -1.6434905529022217,
"logits/rejected": -1.5915906429290771,
"logps/chosen": -333.8968811035156,
"logps/rejected": -733.0169677734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.511116027832031,
"rewards/margins": 27.476917266845703,
"rewards/rejected": -35.988033294677734,
"step": 143
},
{
"epoch": 0.18,
"learning_rate": 2.9684532864643122e-05,
"logits/chosen": -1.4675549268722534,
"logits/rejected": -1.9043865203857422,
"logps/chosen": -309.0293273925781,
"logps/rejected": -591.2290649414062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.682902336120605,
"rewards/margins": 18.137462615966797,
"rewards/rejected": -26.820363998413086,
"step": 144
},
{
"epoch": 0.18,
"learning_rate": 2.8910861626005776e-05,
"logits/chosen": -1.7422269582748413,
"logits/rejected": -1.2487080097198486,
"logps/chosen": -260.97528076171875,
"logps/rejected": -634.4310302734375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.767115592956543,
"rewards/margins": 18.91771697998047,
"rewards/rejected": -26.684831619262695,
"step": 145
},
{
"epoch": 0.18,
"learning_rate": 2.8133330839107608e-05,
"logits/chosen": -1.277583122253418,
"logits/rejected": -1.6845176219940186,
"logps/chosen": -352.37738037109375,
"logps/rejected": -807.046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.428441047668457,
"rewards/margins": 24.504329681396484,
"rewards/rejected": -34.932769775390625,
"step": 146
},
{
"epoch": 0.18,
"learning_rate": 2.7352707832962865e-05,
"logits/chosen": -1.4795787334442139,
"logits/rejected": -1.813377857208252,
"logps/chosen": -331.2845153808594,
"logps/rejected": -801.8402099609375,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.046164512634277,
"rewards/margins": 27.718435287475586,
"rewards/rejected": -37.76459884643555,
"step": 147
},
{
"epoch": 0.18,
"learning_rate": 2.656976298823284e-05,
"logits/chosen": -1.283496379852295,
"logits/rejected": -1.0843333005905151,
"logps/chosen": -287.734619140625,
"logps/rejected": -661.9713745117188,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.094979286193848,
"rewards/margins": 21.19150161743164,
"rewards/rejected": -29.286481857299805,
"step": 148
},
{
"epoch": 0.19,
"learning_rate": 2.578526897695321e-05,
"logits/chosen": -1.5580577850341797,
"logits/rejected": -1.6201229095458984,
"logps/chosen": -301.7952880859375,
"logps/rejected": -713.572998046875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.939479827880859,
"rewards/margins": 23.91385269165039,
"rewards/rejected": -31.85333251953125,
"step": 149
},
{
"epoch": 0.19,
"learning_rate": 2.5e-05,
"logits/chosen": -1.5227057933807373,
"logits/rejected": -1.5960218906402588,
"logps/chosen": -350.0317077636719,
"logps/rejected": -813.5361938476562,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.528999328613281,
"rewards/margins": 25.71453094482422,
"rewards/rejected": -35.2435302734375,
"step": 150
},
{
"epoch": 0.19,
"learning_rate": 2.4214731023046793e-05,
"logits/chosen": -1.5164449214935303,
"logits/rejected": -1.3943390846252441,
"logps/chosen": -262.6053466796875,
"logps/rejected": -667.7622680664062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.690636157989502,
"rewards/margins": 21.432931900024414,
"rewards/rejected": -28.123567581176758,
"step": 151
},
{
"epoch": 0.19,
"learning_rate": 2.3430237011767167e-05,
"logits/chosen": -1.4828455448150635,
"logits/rejected": -1.2360996007919312,
"logps/chosen": -435.7225036621094,
"logps/rejected": -812.917724609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.94736385345459,
"rewards/margins": 23.513948440551758,
"rewards/rejected": -34.46131134033203,
"step": 152
},
{
"epoch": 0.19,
"learning_rate": 2.2647292167037144e-05,
"logits/chosen": -1.7452964782714844,
"logits/rejected": -1.3689957857131958,
"logps/chosen": -338.7836608886719,
"logps/rejected": -629.8165283203125,
"loss": 0.0089,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.47596549987793,
"rewards/margins": 18.36334228515625,
"rewards/rejected": -27.839309692382812,
"step": 153
},
{
"epoch": 0.19,
"learning_rate": 2.186666916089239e-05,
"logits/chosen": -1.1591405868530273,
"logits/rejected": -1.1171772480010986,
"logps/chosen": -251.10696411132812,
"logps/rejected": -677.5640258789062,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.3279805183410645,
"rewards/margins": 23.134410858154297,
"rewards/rejected": -30.462392807006836,
"step": 154
},
{
"epoch": 0.19,
"learning_rate": 2.1089138373994223e-05,
"logits/chosen": -1.800222635269165,
"logits/rejected": -1.1949923038482666,
"logps/chosen": -363.82037353515625,
"logps/rejected": -834.6056518554688,
"loss": 0.0001,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.19363784790039,
"rewards/margins": 27.392547607421875,
"rewards/rejected": -37.586185455322266,
"step": 155
},
{
"epoch": 0.19,
"learning_rate": 2.031546713535688e-05,
"logits/chosen": -1.80062735080719,
"logits/rejected": -1.8262879848480225,
"logps/chosen": -405.14239501953125,
"logps/rejected": -789.0555419921875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -10.376029968261719,
"rewards/margins": 25.058115005493164,
"rewards/rejected": -35.43414306640625,
"step": 156
},
{
"epoch": 0.2,
"learning_rate": 1.9546418965086442e-05,
"logits/chosen": -1.6067843437194824,
"logits/rejected": -1.5892972946166992,
"logps/chosen": -300.63055419921875,
"logps/rejected": -763.7952880859375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -8.260177612304688,
"rewards/margins": 28.313352584838867,
"rewards/rejected": -36.57353210449219,
"step": 157
},
{
"epoch": 0.2,
"learning_rate": 1.8782752820878634e-05,
"logits/chosen": -1.0016999244689941,
"logits/rejected": -1.4391802549362183,
"logps/chosen": -352.371826171875,
"logps/rejected": -763.2830810546875,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -9.006278991699219,
"rewards/margins": 22.58731460571289,
"rewards/rejected": -31.593591690063477,
"step": 158
},
{
"epoch": 0.2,
"learning_rate": 1.802522234901927e-05,
"logits/chosen": -1.1005672216415405,
"logits/rejected": -1.2123079299926758,
"logps/chosen": -329.65667724609375,
"logps/rejected": -706.2532348632812,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -7.16185998916626,
"rewards/margins": 22.066129684448242,
"rewards/rejected": -29.22798728942871,
"step": 159
},
{
"epoch": 0.2,
"learning_rate": 1.7274575140626318e-05,
"logits/chosen": -1.442047119140625,
"logits/rejected": -1.6045359373092651,
"logps/chosen": -415.3704833984375,
"logps/rejected": -721.92724609375,
"loss": 0.0,
"rewards/accuracies": 1.0,
"rewards/chosen": -6.923215389251709,
"rewards/margins": 19.695026397705078,
"rewards/rejected": -26.618240356445312,
"step": 160
}
],
"logging_steps": 1,
"max_steps": 200,
"num_train_epochs": 1,
"save_steps": 40,
"total_flos": 0.0,
"trial_name": null,
"trial_params": null
}