| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9968602825745683, | |
| "eval_steps": 100, | |
| "global_step": 954, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.0416666666666667e-07, | |
| "logits/chosen": 0.29368966817855835, | |
| "logits/rejected": 0.3178113102912903, | |
| "logps/chosen": -295.21783447265625, | |
| "logps/rejected": -290.84619140625, | |
| "loss": 0.6933, | |
| "rewards/accuracies": 0.4000000059604645, | |
| "rewards/chosen": 0.00023447822604794055, | |
| "rewards/margins": 0.00020264319027774036, | |
| "rewards/rejected": 3.183506123605184e-05, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.0833333333333333e-07, | |
| "logits/chosen": 0.25306791067123413, | |
| "logits/rejected": 0.3252382278442383, | |
| "logps/chosen": -318.19073486328125, | |
| "logps/rejected": -289.6706237792969, | |
| "loss": 0.6929, | |
| "rewards/accuracies": 0.53125, | |
| "rewards/chosen": 0.00048495858209207654, | |
| "rewards/margins": 0.0009848512709140778, | |
| "rewards/rejected": -0.0004998926888220012, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.1249999999999997e-07, | |
| "logits/chosen": 0.33226653933525085, | |
| "logits/rejected": 0.3872108459472656, | |
| "logps/chosen": -296.3697204589844, | |
| "logps/rejected": -283.0611877441406, | |
| "loss": 0.692, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -0.0008094090735539794, | |
| "rewards/margins": 0.0026363185606896877, | |
| "rewards/rejected": -0.003445727750658989, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.1666666666666667e-07, | |
| "logits/chosen": 0.22801101207733154, | |
| "logits/rejected": 0.32900214195251465, | |
| "logps/chosen": -305.9015197753906, | |
| "logps/rejected": -293.1842346191406, | |
| "loss": 0.6883, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": -0.0027595984283834696, | |
| "rewards/margins": 0.006589935161173344, | |
| "rewards/rejected": -0.00934953335672617, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.208333333333334e-07, | |
| "logits/chosen": 0.27091675996780396, | |
| "logits/rejected": 0.31866759061813354, | |
| "logps/chosen": -314.2833557128906, | |
| "logps/rejected": -307.02532958984375, | |
| "loss": 0.683, | |
| "rewards/accuracies": 0.6312500238418579, | |
| "rewards/chosen": -0.0060192132368683815, | |
| "rewards/margins": 0.019419629126787186, | |
| "rewards/rejected": -0.025438839569687843, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 6.249999999999999e-07, | |
| "logits/chosen": 0.31704145669937134, | |
| "logits/rejected": 0.4334793984889984, | |
| "logps/chosen": -294.429931640625, | |
| "logps/rejected": -272.87994384765625, | |
| "loss": 0.6735, | |
| "rewards/accuracies": 0.6312500238418579, | |
| "rewards/chosen": -0.022902976721525192, | |
| "rewards/margins": 0.04408121109008789, | |
| "rewards/rejected": -0.06698418408632278, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.291666666666666e-07, | |
| "logits/chosen": 0.31964099407196045, | |
| "logits/rejected": 0.3377896547317505, | |
| "logps/chosen": -304.6803894042969, | |
| "logps/rejected": -311.32794189453125, | |
| "loss": 0.6602, | |
| "rewards/accuracies": 0.6312500238418579, | |
| "rewards/chosen": -0.05670947954058647, | |
| "rewards/margins": 0.05069820210337639, | |
| "rewards/rejected": -0.10740767419338226, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.333333333333333e-07, | |
| "logits/chosen": 0.35048729181289673, | |
| "logits/rejected": 0.4193252921104431, | |
| "logps/chosen": -306.3404541015625, | |
| "logps/rejected": -282.4783020019531, | |
| "loss": 0.6474, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": -0.10853584855794907, | |
| "rewards/margins": 0.13117292523384094, | |
| "rewards/rejected": -0.2397087812423706, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.374999999999999e-07, | |
| "logits/chosen": 0.32813602685928345, | |
| "logits/rejected": 0.4464220404624939, | |
| "logps/chosen": -341.1703186035156, | |
| "logps/rejected": -299.92340087890625, | |
| "loss": 0.6357, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -0.2554694712162018, | |
| "rewards/margins": 0.12284588813781738, | |
| "rewards/rejected": -0.37831538915634155, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.999463737538052e-07, | |
| "logits/chosen": 0.35799938440322876, | |
| "logits/rejected": 0.3899138271808624, | |
| "logps/chosen": -318.7712097167969, | |
| "logps/rejected": -348.5688781738281, | |
| "loss": 0.6201, | |
| "rewards/accuracies": 0.6312500238418579, | |
| "rewards/chosen": -0.3124231994152069, | |
| "rewards/margins": 0.19829413294792175, | |
| "rewards/rejected": -0.5107173323631287, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_logits/chosen": 0.3705582916736603, | |
| "eval_logits/rejected": 0.4172414541244507, | |
| "eval_logps/chosen": -331.11236572265625, | |
| "eval_logps/rejected": -378.240478515625, | |
| "eval_loss": 0.6252639293670654, | |
| "eval_rewards/accuracies": 0.703125, | |
| "eval_rewards/chosen": -0.27527713775634766, | |
| "eval_rewards/margins": 0.3908771872520447, | |
| "eval_rewards/rejected": -0.6661543846130371, | |
| "eval_runtime": 64.993, | |
| "eval_samples_per_second": 30.773, | |
| "eval_steps_per_second": 0.492, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.993432105822034e-07, | |
| "logits/chosen": 0.3002661168575287, | |
| "logits/rejected": 0.3483879864215851, | |
| "logps/chosen": -350.9095458984375, | |
| "logps/rejected": -360.30963134765625, | |
| "loss": 0.6093, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -0.37449145317077637, | |
| "rewards/margins": 0.3816668689250946, | |
| "rewards/rejected": -0.7561584115028381, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.980706626858607e-07, | |
| "logits/chosen": 0.2088731825351715, | |
| "logits/rejected": 0.2899537980556488, | |
| "logps/chosen": -395.3984069824219, | |
| "logps/rejected": -433.7286682128906, | |
| "loss": 0.5905, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -0.4185329079627991, | |
| "rewards/margins": 0.4517739713191986, | |
| "rewards/rejected": -0.8703069686889648, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.961304359538434e-07, | |
| "logits/chosen": 0.09751267731189728, | |
| "logits/rejected": 0.22797170281410217, | |
| "logps/chosen": -374.6502380371094, | |
| "logps/rejected": -373.14263916015625, | |
| "loss": 0.5998, | |
| "rewards/accuracies": 0.6312500238418579, | |
| "rewards/chosen": -0.4483565390110016, | |
| "rewards/margins": 0.3120550811290741, | |
| "rewards/rejected": -0.7604116201400757, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.935251313189563e-07, | |
| "logits/chosen": 0.23218217492103577, | |
| "logits/rejected": 0.28826406598091125, | |
| "logps/chosen": -363.15338134765625, | |
| "logps/rejected": -381.83795166015625, | |
| "loss": 0.5847, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -0.49422675371170044, | |
| "rewards/margins": 0.38399404287338257, | |
| "rewards/rejected": -0.8782208561897278, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.902582412711118e-07, | |
| "logits/chosen": 0.29499703645706177, | |
| "logits/rejected": 0.49714046716690063, | |
| "logps/chosen": -342.9471130371094, | |
| "logps/rejected": -372.1763610839844, | |
| "loss": 0.5681, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -0.6186890602111816, | |
| "rewards/margins": 0.5347500443458557, | |
| "rewards/rejected": -1.1534390449523926, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.86334145175542e-07, | |
| "logits/chosen": 0.35773637890815735, | |
| "logits/rejected": 0.4941268861293793, | |
| "logps/chosen": -370.3203125, | |
| "logps/rejected": -428.2557067871094, | |
| "loss": 0.5792, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -0.7682583928108215, | |
| "rewards/margins": 0.6092099547386169, | |
| "rewards/rejected": -1.377468228340149, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.817581034021272e-07, | |
| "logits/chosen": 0.19401590526103973, | |
| "logits/rejected": 0.3156794607639313, | |
| "logps/chosen": -415.65313720703125, | |
| "logps/rejected": -425.68963623046875, | |
| "loss": 0.5747, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -0.5680743455886841, | |
| "rewards/margins": 0.4286484122276306, | |
| "rewards/rejected": -0.9967228174209595, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.765362502737097e-07, | |
| "logits/chosen": 0.2572034001350403, | |
| "logits/rejected": 0.27328386902809143, | |
| "logps/chosen": -358.0533447265625, | |
| "logps/rejected": -398.5332946777344, | |
| "loss": 0.5634, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -0.644694447517395, | |
| "rewards/margins": 0.5251447558403015, | |
| "rewards/rejected": -1.1698391437530518, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 9.706755858428485e-07, | |
| "logits/chosen": 0.3962785303592682, | |
| "logits/rejected": 0.4539657235145569, | |
| "logps/chosen": -347.5164794921875, | |
| "logps/rejected": -378.83184814453125, | |
| "loss": 0.5423, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -0.7963652610778809, | |
| "rewards/margins": 0.5720622539520264, | |
| "rewards/rejected": -1.3684275150299072, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 9.641839665080363e-07, | |
| "logits/chosen": 0.3198946714401245, | |
| "logits/rejected": 0.4063253402709961, | |
| "logps/chosen": -352.0743713378906, | |
| "logps/rejected": -419.7388610839844, | |
| "loss": 0.5547, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/chosen": -0.7651049494743347, | |
| "rewards/margins": 0.6531444787979126, | |
| "rewards/rejected": -1.418249487876892, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_logits/chosen": 0.3908616304397583, | |
| "eval_logits/rejected": 0.4261176884174347, | |
| "eval_logps/chosen": -373.46612548828125, | |
| "eval_logps/rejected": -458.88629150390625, | |
| "eval_loss": 0.5549300312995911, | |
| "eval_rewards/accuracies": 0.765625, | |
| "eval_rewards/chosen": -0.6988146305084229, | |
| "eval_rewards/margins": 0.7737974524497986, | |
| "eval_rewards/rejected": -1.4726121425628662, | |
| "eval_runtime": 65.2313, | |
| "eval_samples_per_second": 30.66, | |
| "eval_steps_per_second": 0.491, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 9.570700944819582e-07, | |
| "logits/chosen": 0.3505176901817322, | |
| "logits/rejected": 0.42375579476356506, | |
| "logps/chosen": -397.61199951171875, | |
| "logps/rejected": -454.89776611328125, | |
| "loss": 0.5265, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -0.7523492574691772, | |
| "rewards/margins": 0.7344074845314026, | |
| "rewards/rejected": -1.486756682395935, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.493435061259129e-07, | |
| "logits/chosen": 0.2726442813873291, | |
| "logits/rejected": 0.4434526860713959, | |
| "logps/chosen": -410.77667236328125, | |
| "logps/rejected": -431.207275390625, | |
| "loss": 0.555, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -0.8984044194221497, | |
| "rewards/margins": 0.5839776992797852, | |
| "rewards/rejected": -1.48238205909729, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.4101455916603e-07, | |
| "logits/chosen": 0.28837597370147705, | |
| "logits/rejected": 0.35526323318481445, | |
| "logps/chosen": -363.0335998535156, | |
| "logps/rejected": -436.46612548828125, | |
| "loss": 0.5498, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -0.8101651072502136, | |
| "rewards/margins": 0.737695574760437, | |
| "rewards/rejected": -1.5478605031967163, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.320944188084241e-07, | |
| "logits/chosen": 0.23826150596141815, | |
| "logits/rejected": 0.285171240568161, | |
| "logps/chosen": -432.6297912597656, | |
| "logps/rejected": -497.56341552734375, | |
| "loss": 0.5392, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -0.7939236164093018, | |
| "rewards/margins": 0.7111212611198425, | |
| "rewards/rejected": -1.505044937133789, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.225950427718974e-07, | |
| "logits/chosen": 0.2762988209724426, | |
| "logits/rejected": 0.31130319833755493, | |
| "logps/chosen": -399.399169921875, | |
| "logps/rejected": -445.702880859375, | |
| "loss": 0.5465, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -0.83611661195755, | |
| "rewards/margins": 0.7073522806167603, | |
| "rewards/rejected": -1.5434690713882446, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.125291652582547e-07, | |
| "logits/chosen": 0.1327328383922577, | |
| "logits/rejected": 0.3085227310657501, | |
| "logps/chosen": -436.08135986328125, | |
| "logps/rejected": -457.634765625, | |
| "loss": 0.5194, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -0.9428914785385132, | |
| "rewards/margins": 0.6950392723083496, | |
| "rewards/rejected": -1.6379308700561523, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.019102798817195e-07, | |
| "logits/chosen": 0.23745720088481903, | |
| "logits/rejected": 0.34172096848487854, | |
| "logps/chosen": -421.8299865722656, | |
| "logps/rejected": -466.4856872558594, | |
| "loss": 0.5496, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -0.9325121641159058, | |
| "rewards/margins": 0.7680062651634216, | |
| "rewards/rejected": -1.7005186080932617, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8.90752621580335e-07, | |
| "logits/chosen": 0.16251161694526672, | |
| "logits/rejected": 0.2581509053707123, | |
| "logps/chosen": -418.5828552246094, | |
| "logps/rejected": -507.22412109375, | |
| "loss": 0.5168, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/chosen": -1.113261342048645, | |
| "rewards/margins": 0.7757157683372498, | |
| "rewards/rejected": -1.88897705078125, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 8.79071147533597e-07, | |
| "logits/chosen": 0.18345972895622253, | |
| "logits/rejected": 0.24752414226531982, | |
| "logps/chosen": -374.2388916015625, | |
| "logps/rejected": -421.7548828125, | |
| "loss": 0.5452, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -0.7729798555374146, | |
| "rewards/margins": 0.6754422187805176, | |
| "rewards/rejected": -1.448421835899353, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.668815171119019e-07, | |
| "logits/chosen": 0.11917382478713989, | |
| "logits/rejected": 0.2862890362739563, | |
| "logps/chosen": -396.6165466308594, | |
| "logps/rejected": -400.9344787597656, | |
| "loss": 0.5343, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": -0.8496394157409668, | |
| "rewards/margins": 0.5671547055244446, | |
| "rewards/rejected": -1.4167941808700562, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_logits/chosen": 0.24486932158470154, | |
| "eval_logits/rejected": 0.2851215898990631, | |
| "eval_logps/chosen": -384.0199279785156, | |
| "eval_logps/rejected": -476.3627624511719, | |
| "eval_loss": 0.5315821766853333, | |
| "eval_rewards/accuracies": 0.765625, | |
| "eval_rewards/chosen": -0.8043524026870728, | |
| "eval_rewards/margins": 0.8430246114730835, | |
| "eval_rewards/rejected": -1.6473771333694458, | |
| "eval_runtime": 64.8898, | |
| "eval_samples_per_second": 30.822, | |
| "eval_steps_per_second": 0.493, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 8.54200070884685e-07, | |
| "logits/chosen": 0.21563191711902618, | |
| "logits/rejected": 0.1952591836452484, | |
| "logps/chosen": -438.91552734375, | |
| "logps/rejected": -499.61395263671875, | |
| "loss": 0.5567, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -1.173762559890747, | |
| "rewards/margins": 0.5995947122573853, | |
| "rewards/rejected": -1.7733571529388428, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 8.410438087153911e-07, | |
| "logits/chosen": 0.031750187277793884, | |
| "logits/rejected": 0.14312420785427094, | |
| "logps/chosen": -457.0936584472656, | |
| "logps/rejected": -459.15411376953125, | |
| "loss": 0.5366, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/chosen": -1.0222933292388916, | |
| "rewards/margins": 0.4668423533439636, | |
| "rewards/rejected": -1.4891356229782104, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 8.274303669726426e-07, | |
| "logits/chosen": 0.07745673507452011, | |
| "logits/rejected": 0.07082104682922363, | |
| "logps/chosen": -399.32464599609375, | |
| "logps/rejected": -523.4277954101562, | |
| "loss": 0.532, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/chosen": -0.9549884796142578, | |
| "rewards/margins": 0.8862001299858093, | |
| "rewards/rejected": -1.8411887884140015, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.133779948881513e-07, | |
| "logits/chosen": 0.10294970124959946, | |
| "logits/rejected": 0.09352216869592667, | |
| "logps/chosen": -409.33770751953125, | |
| "logps/rejected": -510.10089111328125, | |
| "loss": 0.5217, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -1.1990526914596558, | |
| "rewards/margins": 0.7596696615219116, | |
| "rewards/rejected": -1.958722472190857, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 7.989055300930704e-07, | |
| "logits/chosen": 0.16737070679664612, | |
| "logits/rejected": 0.21901166439056396, | |
| "logps/chosen": -437.2059020996094, | |
| "logps/rejected": -538.3087158203125, | |
| "loss": 0.5091, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -1.2976617813110352, | |
| "rewards/margins": 0.8197441101074219, | |
| "rewards/rejected": -2.117405891418457, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.840323733655778e-07, | |
| "logits/chosen": 0.1267612874507904, | |
| "logits/rejected": 0.20460394024848938, | |
| "logps/chosen": -465.1019592285156, | |
| "logps/rejected": -518.5805053710938, | |
| "loss": 0.5185, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -1.174440860748291, | |
| "rewards/margins": 0.9074214696884155, | |
| "rewards/rejected": -2.081862211227417, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.687784626235447e-07, | |
| "logits/chosen": 0.18740633130073547, | |
| "logits/rejected": 0.27840983867645264, | |
| "logps/chosen": -468.21807861328125, | |
| "logps/rejected": -493.06646728515625, | |
| "loss": 0.5158, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -1.1525232791900635, | |
| "rewards/margins": 0.7130603790283203, | |
| "rewards/rejected": -1.8655836582183838, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.531642461971514e-07, | |
| "logits/chosen": 0.15459200739860535, | |
| "logits/rejected": 0.23283176124095917, | |
| "logps/chosen": -453.07904052734375, | |
| "logps/rejected": -535.761474609375, | |
| "loss": 0.5392, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -1.2102587223052979, | |
| "rewards/margins": 1.0239769220352173, | |
| "rewards/rejected": -2.2342355251312256, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.372106554172801e-07, | |
| "logits/chosen": 0.19951777160167694, | |
| "logits/rejected": 0.2895793318748474, | |
| "logps/chosen": -411.4781799316406, | |
| "logps/rejected": -466.41253662109375, | |
| "loss": 0.5356, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -0.8807674646377563, | |
| "rewards/margins": 0.7255697846412659, | |
| "rewards/rejected": -1.606337308883667, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.209390765564318e-07, | |
| "logits/chosen": 0.1757899820804596, | |
| "logits/rejected": 0.23791635036468506, | |
| "logps/chosen": -390.8957214355469, | |
| "logps/rejected": -478.49407958984375, | |
| "loss": 0.5323, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -0.9380720257759094, | |
| "rewards/margins": 0.7229949235916138, | |
| "rewards/rejected": -1.661067008972168, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_logits/chosen": 0.25136542320251465, | |
| "eval_logits/rejected": 0.28342366218566895, | |
| "eval_logps/chosen": -394.2620849609375, | |
| "eval_logps/rejected": -494.46002197265625, | |
| "eval_loss": 0.521114706993103, | |
| "eval_rewards/accuracies": 0.78125, | |
| "eval_rewards/chosen": -0.90677410364151, | |
| "eval_rewards/margins": 0.9215754270553589, | |
| "eval_rewards/rejected": -1.8283497095108032, | |
| "eval_runtime": 65.2477, | |
| "eval_samples_per_second": 30.652, | |
| "eval_steps_per_second": 0.49, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.043713221597773e-07, | |
| "logits/chosen": 0.1401471644639969, | |
| "logits/rejected": 0.17819848656654358, | |
| "logps/chosen": -401.8942565917969, | |
| "logps/rejected": -474.2579650878906, | |
| "loss": 0.5225, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/chosen": -0.8892021179199219, | |
| "rewards/margins": 0.906479001045227, | |
| "rewards/rejected": -1.7956812381744385, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.875296018047809e-07, | |
| "logits/chosen": 0.1304786652326584, | |
| "logits/rejected": 0.15569528937339783, | |
| "logps/chosen": -400.5438537597656, | |
| "logps/rejected": -468.2953186035156, | |
| "loss": 0.5065, | |
| "rewards/accuracies": 0.8187500238418579, | |
| "rewards/chosen": -0.9208317995071411, | |
| "rewards/margins": 0.9665653109550476, | |
| "rewards/rejected": -1.887397050857544, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 6.704364923285857e-07, | |
| "logits/chosen": 0.09775003790855408, | |
| "logits/rejected": 0.1501173973083496, | |
| "logps/chosen": -476.73065185546875, | |
| "logps/rejected": -533.7389526367188, | |
| "loss": 0.5285, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -1.26286780834198, | |
| "rewards/margins": 0.8789494633674622, | |
| "rewards/rejected": -2.141817569732666, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 6.531149075630796e-07, | |
| "logits/chosen": 0.1202029138803482, | |
| "logits/rejected": 0.1756385862827301, | |
| "logps/chosen": -400.1629333496094, | |
| "logps/rejected": -469.0196838378906, | |
| "loss": 0.5074, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": -1.0582826137542725, | |
| "rewards/margins": 0.9171028137207031, | |
| "rewards/rejected": -1.975385308265686, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 6.355880676182085e-07, | |
| "logits/chosen": 0.01758761703968048, | |
| "logits/rejected": 0.15642888844013214, | |
| "logps/chosen": -443.065185546875, | |
| "logps/rejected": -484.41473388671875, | |
| "loss": 0.5295, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -1.004433035850525, | |
| "rewards/margins": 0.8090255856513977, | |
| "rewards/rejected": -1.8134586811065674, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 6.178794677547137e-07, | |
| "logits/chosen": 0.012063628062605858, | |
| "logits/rejected": 0.10572747141122818, | |
| "logps/chosen": -408.4104919433594, | |
| "logps/rejected": -449.46881103515625, | |
| "loss": 0.5267, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -1.0622318983078003, | |
| "rewards/margins": 0.6900007724761963, | |
| "rewards/rejected": -1.752232551574707, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.000128468880222e-07, | |
| "logits/chosen": -0.05889149755239487, | |
| "logits/rejected": -0.014351313933730125, | |
| "logps/chosen": -449.07061767578125, | |
| "logps/rejected": -538.423828125, | |
| "loss": 0.5042, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -1.1122030019760132, | |
| "rewards/margins": 0.9293983578681946, | |
| "rewards/rejected": -2.0416014194488525, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.820121557655108e-07, | |
| "logits/chosen": -0.045923542231321335, | |
| "logits/rejected": 0.03086056187748909, | |
| "logps/chosen": -422.5347595214844, | |
| "logps/rejected": -529.2613525390625, | |
| "loss": 0.4682, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -1.275895118713379, | |
| "rewards/margins": 1.037326455116272, | |
| "rewards/rejected": -2.3132214546203613, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.639015248598023e-07, | |
| "logits/chosen": -0.05794327333569527, | |
| "logits/rejected": -0.09440571069717407, | |
| "logps/chosen": -441.08990478515625, | |
| "logps/rejected": -601.30419921875, | |
| "loss": 0.3493, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -1.3565930128097534, | |
| "rewards/margins": 1.8090267181396484, | |
| "rewards/rejected": -3.1656198501586914, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.457052320211339e-07, | |
| "logits/chosen": -0.23803594708442688, | |
| "logits/rejected": -0.29828980565071106, | |
| "logps/chosen": -474.3367614746094, | |
| "logps/rejected": -656.8623046875, | |
| "loss": 0.352, | |
| "rewards/accuracies": 0.8187500238418579, | |
| "rewards/chosen": -1.730020523071289, | |
| "rewards/margins": 1.8847625255584717, | |
| "rewards/rejected": -3.6147830486297607, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_logits/chosen": -0.06535135954618454, | |
| "eval_logits/rejected": -0.08458372950553894, | |
| "eval_logps/chosen": -498.9117431640625, | |
| "eval_logps/rejected": -653.2899169921875, | |
| "eval_loss": 0.525809109210968, | |
| "eval_rewards/accuracies": 0.796875, | |
| "eval_rewards/chosen": -1.9532711505889893, | |
| "eval_rewards/margins": 1.4633771181106567, | |
| "eval_rewards/rejected": -3.4166483879089355, | |
| "eval_runtime": 64.5447, | |
| "eval_samples_per_second": 30.986, | |
| "eval_steps_per_second": 0.496, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.274476699321637e-07, | |
| "logits/chosen": -0.17468394339084625, | |
| "logits/rejected": -0.19271844625473022, | |
| "logps/chosen": -464.8907165527344, | |
| "logps/rejected": -632.8477172851562, | |
| "loss": 0.3423, | |
| "rewards/accuracies": 0.893750011920929, | |
| "rewards/chosen": -1.695770263671875, | |
| "rewards/margins": 1.8958046436309814, | |
| "rewards/rejected": -3.5915749073028564, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.091533134088387e-07, | |
| "logits/chosen": -0.23788562417030334, | |
| "logits/rejected": -0.20414999127388, | |
| "logps/chosen": -485.94415283203125, | |
| "logps/rejected": -640.9654541015625, | |
| "loss": 0.3236, | |
| "rewards/accuracies": 0.8999999761581421, | |
| "rewards/chosen": -1.8264538049697876, | |
| "rewards/margins": 1.7633371353149414, | |
| "rewards/rejected": -3.5897908210754395, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.908466865911614e-07, | |
| "logits/chosen": -0.11999205499887466, | |
| "logits/rejected": -0.09423510730266571, | |
| "logps/chosen": -487.30810546875, | |
| "logps/rejected": -646.9547119140625, | |
| "loss": 0.3424, | |
| "rewards/accuracies": 0.84375, | |
| "rewards/chosen": -1.7824156284332275, | |
| "rewards/margins": 1.7626768350601196, | |
| "rewards/rejected": -3.5450921058654785, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.7255233006783624e-07, | |
| "logits/chosen": -0.16903451085090637, | |
| "logits/rejected": -0.06715662032365799, | |
| "logps/chosen": -530.5585327148438, | |
| "logps/rejected": -645.1633911132812, | |
| "loss": 0.3301, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -1.7870140075683594, | |
| "rewards/margins": 1.8271121978759766, | |
| "rewards/rejected": -3.614126682281494, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.5429476797886617e-07, | |
| "logits/chosen": -0.03496643900871277, | |
| "logits/rejected": -0.04560618847608566, | |
| "logps/chosen": -483.15203857421875, | |
| "logps/rejected": -634.9447631835938, | |
| "loss": 0.3501, | |
| "rewards/accuracies": 0.8187500238418579, | |
| "rewards/chosen": -1.8454551696777344, | |
| "rewards/margins": 1.5336250066757202, | |
| "rewards/rejected": -3.379080295562744, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.3609847514019763e-07, | |
| "logits/chosen": 0.06872721016407013, | |
| "logits/rejected": 0.0859331339597702, | |
| "logps/chosen": -506.5009765625, | |
| "logps/rejected": -646.7543334960938, | |
| "loss": 0.3359, | |
| "rewards/accuracies": 0.875, | |
| "rewards/chosen": -1.7461020946502686, | |
| "rewards/margins": 1.8654359579086304, | |
| "rewards/rejected": -3.6115379333496094, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.179878442344892e-07, | |
| "logits/chosen": -0.04321649298071861, | |
| "logits/rejected": 0.051123034209012985, | |
| "logps/chosen": -496.735595703125, | |
| "logps/rejected": -647.29150390625, | |
| "loss": 0.3464, | |
| "rewards/accuracies": 0.8062499761581421, | |
| "rewards/chosen": -2.0714824199676514, | |
| "rewards/margins": 1.762717843055725, | |
| "rewards/rejected": -3.834200620651245, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.9998715311197783e-07, | |
| "logits/chosen": -0.004042728338390589, | |
| "logits/rejected": 0.04070080816745758, | |
| "logps/chosen": -512.9417724609375, | |
| "logps/rejected": -696.821044921875, | |
| "loss": 0.3365, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -2.097195863723755, | |
| "rewards/margins": 1.831916093826294, | |
| "rewards/rejected": -3.9291114807128906, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.821205322452863e-07, | |
| "logits/chosen": 0.09215477854013443, | |
| "logits/rejected": 0.05737446993589401, | |
| "logps/chosen": -525.1434936523438, | |
| "logps/rejected": -705.9063110351562, | |
| "loss": 0.3158, | |
| "rewards/accuracies": 0.856249988079071, | |
| "rewards/chosen": -2.0721964836120605, | |
| "rewards/margins": 1.9721500873565674, | |
| "rewards/rejected": -4.044346809387207, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.6441193238179146e-07, | |
| "logits/chosen": 0.07227401435375214, | |
| "logits/rejected": 0.03988388180732727, | |
| "logps/chosen": -549.4615478515625, | |
| "logps/rejected": -771.7275390625, | |
| "loss": 0.3342, | |
| "rewards/accuracies": 0.856249988079071, | |
| "rewards/chosen": -2.2555530071258545, | |
| "rewards/margins": 2.014453649520874, | |
| "rewards/rejected": -4.2700066566467285, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_logits/chosen": 0.1344175487756729, | |
| "eval_logits/rejected": 0.11280365288257599, | |
| "eval_logps/chosen": -534.8101196289062, | |
| "eval_logps/rejected": -684.085693359375, | |
| "eval_loss": 0.5267595648765564, | |
| "eval_rewards/accuracies": 0.79296875, | |
| "eval_rewards/chosen": -2.3122546672821045, | |
| "eval_rewards/margins": 1.412351369857788, | |
| "eval_rewards/rejected": -3.7246060371398926, | |
| "eval_runtime": 64.3013, | |
| "eval_samples_per_second": 31.104, | |
| "eval_steps_per_second": 0.498, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.4688509243692034e-07, | |
| "logits/chosen": 0.021421348676085472, | |
| "logits/rejected": 0.08866464346647263, | |
| "logps/chosen": -535.4236450195312, | |
| "logps/rejected": -694.8360595703125, | |
| "loss": 0.344, | |
| "rewards/accuracies": 0.8687499761581421, | |
| "rewards/chosen": -2.009089946746826, | |
| "rewards/margins": 1.8043378591537476, | |
| "rewards/rejected": -3.8134284019470215, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.295635076714144e-07, | |
| "logits/chosen": -0.06299210339784622, | |
| "logits/rejected": -0.04097691923379898, | |
| "logps/chosen": -499.0265197753906, | |
| "logps/rejected": -653.1188354492188, | |
| "loss": 0.3317, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -1.9393279552459717, | |
| "rewards/margins": 1.6952606439590454, | |
| "rewards/rejected": -3.6345887184143066, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.12470398195219e-07, | |
| "logits/chosen": -0.013870243914425373, | |
| "logits/rejected": 0.0671583041548729, | |
| "logps/chosen": -512.1448974609375, | |
| "logps/rejected": -680.2833251953125, | |
| "loss": 0.3283, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -1.9993736743927002, | |
| "rewards/margins": 1.9316644668579102, | |
| "rewards/rejected": -3.9310379028320312, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.956286778402226e-07, | |
| "logits/chosen": -0.11906696856021881, | |
| "logits/rejected": -0.17396704852581024, | |
| "logps/chosen": -495.10345458984375, | |
| "logps/rejected": -677.45556640625, | |
| "loss": 0.319, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -2.2106266021728516, | |
| "rewards/margins": 1.9618394374847412, | |
| "rewards/rejected": -4.172466278076172, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.7906092344356826e-07, | |
| "logits/chosen": -0.07961982488632202, | |
| "logits/rejected": -0.12522803246974945, | |
| "logps/chosen": -516.12890625, | |
| "logps/rejected": -696.549560546875, | |
| "loss": 0.3233, | |
| "rewards/accuracies": 0.8374999761581421, | |
| "rewards/chosen": -2.1828126907348633, | |
| "rewards/margins": 1.8567641973495483, | |
| "rewards/rejected": -4.039577007293701, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.6278934458271996e-07, | |
| "logits/chosen": -0.15696656703948975, | |
| "logits/rejected": -0.12818947434425354, | |
| "logps/chosen": -568.789794921875, | |
| "logps/rejected": -722.9078369140625, | |
| "loss": 0.3273, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -2.1225264072418213, | |
| "rewards/margins": 1.9797760248184204, | |
| "rewards/rejected": -4.102302551269531, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.468357538028487e-07, | |
| "logits/chosen": 0.01013887207955122, | |
| "logits/rejected": 0.029213298112154007, | |
| "logps/chosen": -541.7221069335938, | |
| "logps/rejected": -720.105712890625, | |
| "loss": 0.3153, | |
| "rewards/accuracies": 0.856249988079071, | |
| "rewards/chosen": -2.205817461013794, | |
| "rewards/margins": 2.0757954120635986, | |
| "rewards/rejected": -4.281612396240234, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.312215373764551e-07, | |
| "logits/chosen": -0.06487278640270233, | |
| "logits/rejected": -0.01965305209159851, | |
| "logps/chosen": -516.360107421875, | |
| "logps/rejected": -694.418212890625, | |
| "loss": 0.3262, | |
| "rewards/accuracies": 0.856249988079071, | |
| "rewards/chosen": -2.184447765350342, | |
| "rewards/margins": 1.861135721206665, | |
| "rewards/rejected": -4.045583248138428, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.1596762663442213e-07, | |
| "logits/chosen": -0.16129662096500397, | |
| "logits/rejected": -0.09581325948238373, | |
| "logps/chosen": -546.6666259765625, | |
| "logps/rejected": -722.95263671875, | |
| "loss": 0.3194, | |
| "rewards/accuracies": 0.8500000238418579, | |
| "rewards/chosen": -2.1821353435516357, | |
| "rewards/margins": 2.131826877593994, | |
| "rewards/rejected": -4.313961982727051, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.0109446990692963e-07, | |
| "logits/chosen": -0.11689990758895874, | |
| "logits/rejected": -0.2061731368303299, | |
| "logps/chosen": -537.8167724609375, | |
| "logps/rejected": -781.1466674804688, | |
| "loss": 0.337, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -2.2769298553466797, | |
| "rewards/margins": 2.1021370887756348, | |
| "rewards/rejected": -4.3790669441223145, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_logits/chosen": 0.041396014392375946, | |
| "eval_logits/rejected": 0.009947247803211212, | |
| "eval_logps/chosen": -541.1116333007812, | |
| "eval_logps/rejected": -699.990966796875, | |
| "eval_loss": 0.5290427207946777, | |
| "eval_rewards/accuracies": 0.77734375, | |
| "eval_rewards/chosen": -2.375269651412964, | |
| "eval_rewards/margins": 1.5083887577056885, | |
| "eval_rewards/rejected": -3.883657932281494, | |
| "eval_runtime": 64.3756, | |
| "eval_samples_per_second": 31.068, | |
| "eval_steps_per_second": 0.497, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.8662200511184872e-07, | |
| "logits/chosen": -0.05749096721410751, | |
| "logits/rejected": -0.05046076700091362, | |
| "logps/chosen": -522.4590454101562, | |
| "logps/rejected": -701.3648071289062, | |
| "loss": 0.3387, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -2.1689815521240234, | |
| "rewards/margins": 2.023318290710449, | |
| "rewards/rejected": -4.192299842834473, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 1.725696330273575e-07, | |
| "logits/chosen": -0.12996384501457214, | |
| "logits/rejected": -0.20302283763885498, | |
| "logps/chosen": -513.8458251953125, | |
| "logps/rejected": -704.156982421875, | |
| "loss": 0.3363, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -1.9350038766860962, | |
| "rewards/margins": 2.0845541954040527, | |
| "rewards/rejected": -4.019558429718018, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.589561912846089e-07, | |
| "logits/chosen": -0.02087187021970749, | |
| "logits/rejected": -0.01297883689403534, | |
| "logps/chosen": -513.4478149414062, | |
| "logps/rejected": -715.5861206054688, | |
| "loss": 0.3311, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -2.01027512550354, | |
| "rewards/margins": 1.9698785543441772, | |
| "rewards/rejected": -3.9801535606384277, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.4579992911531496e-07, | |
| "logits/chosen": -0.08378951251506805, | |
| "logits/rejected": -0.10333013534545898, | |
| "logps/chosen": -528.8599853515625, | |
| "logps/rejected": -697.0358276367188, | |
| "loss": 0.31, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -2.1352083683013916, | |
| "rewards/margins": 2.004941940307617, | |
| "rewards/rejected": -4.140150547027588, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.3311848288809813e-07, | |
| "logits/chosen": -0.021279722452163696, | |
| "logits/rejected": -0.07772192358970642, | |
| "logps/chosen": -553.6995239257812, | |
| "logps/rejected": -696.1124267578125, | |
| "loss": 0.3325, | |
| "rewards/accuracies": 0.856249988079071, | |
| "rewards/chosen": -2.2102222442626953, | |
| "rewards/margins": 1.8731515407562256, | |
| "rewards/rejected": -4.083374500274658, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 1.209288524664029e-07, | |
| "logits/chosen": -0.1553444117307663, | |
| "logits/rejected": -0.07370997965335846, | |
| "logps/chosen": -559.6234130859375, | |
| "logps/rejected": -718.3536376953125, | |
| "loss": 0.3318, | |
| "rewards/accuracies": 0.84375, | |
| "rewards/chosen": -2.2175405025482178, | |
| "rewards/margins": 2.087991714477539, | |
| "rewards/rejected": -4.305531978607178, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 1.0924737841966497e-07, | |
| "logits/chosen": 0.06289811432361603, | |
| "logits/rejected": 0.08451451361179352, | |
| "logps/chosen": -502.3817443847656, | |
| "logps/rejected": -655.4021606445312, | |
| "loss": 0.3065, | |
| "rewards/accuracies": 0.856249988079071, | |
| "rewards/chosen": -2.215487241744995, | |
| "rewards/margins": 1.8723819255828857, | |
| "rewards/rejected": -4.087869644165039, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.808972011828054e-08, | |
| "logits/chosen": -0.028034457936882973, | |
| "logits/rejected": -0.07584713399410248, | |
| "logps/chosen": -507.1363220214844, | |
| "logps/rejected": -684.7667236328125, | |
| "loss": 0.321, | |
| "rewards/accuracies": 0.831250011920929, | |
| "rewards/chosen": -2.1353392601013184, | |
| "rewards/margins": 1.854984998703003, | |
| "rewards/rejected": -3.9903244972229004, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.747083474174527e-08, | |
| "logits/chosen": -0.027467548847198486, | |
| "logits/rejected": -0.11992067098617554, | |
| "logps/chosen": -513.2483520507812, | |
| "logps/rejected": -773.5486450195312, | |
| "loss": 0.3106, | |
| "rewards/accuracies": 0.9125000238418579, | |
| "rewards/chosen": -2.409447431564331, | |
| "rewards/margins": 2.4787163734436035, | |
| "rewards/rejected": -4.8881635665893555, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 7.740495722810269e-08, | |
| "logits/chosen": -0.22111931443214417, | |
| "logits/rejected": -0.16927292943000793, | |
| "logps/chosen": -594.322998046875, | |
| "logps/rejected": -767.4426879882812, | |
| "loss": 0.3398, | |
| "rewards/accuracies": 0.84375, | |
| "rewards/chosen": -2.4693970680236816, | |
| "rewards/margins": 2.0875487327575684, | |
| "rewards/rejected": -4.55694580078125, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_logits/chosen": 0.0749908834695816, | |
| "eval_logits/rejected": 0.0380852147936821, | |
| "eval_logps/chosen": -554.5546264648438, | |
| "eval_logps/rejected": -712.9505615234375, | |
| "eval_loss": 0.5297122001647949, | |
| "eval_rewards/accuracies": 0.7734375, | |
| "eval_rewards/chosen": -2.509699821472168, | |
| "eval_rewards/margins": 1.5035548210144043, | |
| "eval_rewards/rejected": -4.013254642486572, | |
| "eval_runtime": 65.3757, | |
| "eval_samples_per_second": 30.592, | |
| "eval_steps_per_second": 0.489, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 6.790558119157597e-08, | |
| "logits/chosen": -0.03027234971523285, | |
| "logits/rejected": -0.026968132704496384, | |
| "logps/chosen": -558.7872924804688, | |
| "logps/rejected": -744.04736328125, | |
| "loss": 0.3134, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -2.323040246963501, | |
| "rewards/margins": 2.1539111137390137, | |
| "rewards/rejected": -4.476951599121094, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 5.898544083397e-08, | |
| "logits/chosen": -0.06089891865849495, | |
| "logits/rejected": -0.11520856618881226, | |
| "logps/chosen": -516.7492065429688, | |
| "logps/rejected": -698.2511596679688, | |
| "loss": 0.3131, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -2.2953174114227295, | |
| "rewards/margins": 2.0010485649108887, | |
| "rewards/rejected": -4.296365737915039, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 5.065649387408705e-08, | |
| "logits/chosen": -0.026049736887216568, | |
| "logits/rejected": -0.11464808881282806, | |
| "logps/chosen": -556.2135620117188, | |
| "logps/rejected": -718.17578125, | |
| "loss": 0.3145, | |
| "rewards/accuracies": 0.8687499761581421, | |
| "rewards/chosen": -2.405728816986084, | |
| "rewards/margins": 1.908630132675171, | |
| "rewards/rejected": -4.314358711242676, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.292990551804171e-08, | |
| "logits/chosen": -0.12712730467319489, | |
| "logits/rejected": -0.10675887763500214, | |
| "logps/chosen": -529.3737182617188, | |
| "logps/rejected": -723.229248046875, | |
| "loss": 0.327, | |
| "rewards/accuracies": 0.8500000238418579, | |
| "rewards/chosen": -2.146822929382324, | |
| "rewards/margins": 2.177410125732422, | |
| "rewards/rejected": -4.324233055114746, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.581603349196371e-08, | |
| "logits/chosen": 0.01494809053838253, | |
| "logits/rejected": -0.08690011501312256, | |
| "logps/chosen": -540.9631958007812, | |
| "logps/rejected": -735.3316650390625, | |
| "loss": 0.3262, | |
| "rewards/accuracies": 0.918749988079071, | |
| "rewards/chosen": -2.145940065383911, | |
| "rewards/margins": 2.0986034870147705, | |
| "rewards/rejected": -4.24454402923584, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.9324414157151367e-08, | |
| "logits/chosen": -0.10003119707107544, | |
| "logits/rejected": -0.13639459013938904, | |
| "logps/chosen": -504.34552001953125, | |
| "logps/rejected": -681.4578247070312, | |
| "loss": 0.3261, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -2.0967519283294678, | |
| "rewards/margins": 1.8127696514129639, | |
| "rewards/rejected": -3.9095215797424316, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.3463749726290284e-08, | |
| "logits/chosen": -0.005720620043575764, | |
| "logits/rejected": -0.09044505655765533, | |
| "logps/chosen": -550.0, | |
| "logps/rejected": -727.3507690429688, | |
| "loss": 0.3221, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -2.1374850273132324, | |
| "rewards/margins": 2.060269355773926, | |
| "rewards/rejected": -4.197754859924316, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.824189659787284e-08, | |
| "logits/chosen": -0.07426755130290985, | |
| "logits/rejected": -0.09251859039068222, | |
| "logps/chosen": -551.6723022460938, | |
| "logps/rejected": -753.9895629882812, | |
| "loss": 0.3162, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -2.1559104919433594, | |
| "rewards/margins": 2.1075100898742676, | |
| "rewards/rejected": -4.263420581817627, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.3665854824458035e-08, | |
| "logits/chosen": -0.05439913272857666, | |
| "logits/rejected": -0.06511974334716797, | |
| "logps/chosen": -540.4793090820312, | |
| "logps/rejected": -690.4094848632812, | |
| "loss": 0.3265, | |
| "rewards/accuracies": 0.8500000238418579, | |
| "rewards/chosen": -2.1754844188690186, | |
| "rewards/margins": 1.7633205652236938, | |
| "rewards/rejected": -3.938805103302002, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 9.741758728888217e-09, | |
| "logits/chosen": -0.06001782417297363, | |
| "logits/rejected": -0.016363339498639107, | |
| "logps/chosen": -546.7725830078125, | |
| "logps/rejected": -690.0701293945312, | |
| "loss": 0.307, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -2.229912281036377, | |
| "rewards/margins": 1.9347511529922485, | |
| "rewards/rejected": -4.164663314819336, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_logits/chosen": 0.06628188490867615, | |
| "eval_logits/rejected": 0.02886618673801422, | |
| "eval_logps/chosen": -549.4910278320312, | |
| "eval_logps/rejected": -703.8400268554688, | |
| "eval_loss": 0.5260834097862244, | |
| "eval_rewards/accuracies": 0.77734375, | |
| "eval_rewards/chosen": -2.4590635299682617, | |
| "eval_rewards/margins": 1.4630858898162842, | |
| "eval_rewards/rejected": -3.922149658203125, | |
| "eval_runtime": 65.2404, | |
| "eval_samples_per_second": 30.656, | |
| "eval_steps_per_second": 0.49, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 6.474868681043577e-09, | |
| "logits/chosen": -0.0006331875920295715, | |
| "logits/rejected": 0.06078674644231796, | |
| "logps/chosen": -526.890869140625, | |
| "logps/rejected": -696.57080078125, | |
| "loss": 0.3133, | |
| "rewards/accuracies": 0.84375, | |
| "rewards/chosen": -2.2198734283447266, | |
| "rewards/margins": 1.9986340999603271, | |
| "rewards/rejected": -4.218507289886475, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3.869564046156459e-09, | |
| "logits/chosen": -0.17484715580940247, | |
| "logits/rejected": -0.2491791695356369, | |
| "logps/chosen": -560.9608154296875, | |
| "logps/rejected": -718.45703125, | |
| "loss": 0.3088, | |
| "rewards/accuracies": 0.9125000238418579, | |
| "rewards/chosen": -2.2493414878845215, | |
| "rewards/margins": 2.0530190467834473, | |
| "rewards/rejected": -4.3023600578308105, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.929337314139412e-09, | |
| "logits/chosen": -0.0817941427230835, | |
| "logits/rejected": -0.2032664567232132, | |
| "logps/chosen": -562.2503662109375, | |
| "logps/rejected": -765.2064208984375, | |
| "loss": 0.3264, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -2.2634310722351074, | |
| "rewards/margins": 2.2729239463806152, | |
| "rewards/rejected": -4.536355018615723, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.567894177967325e-10, | |
| "logits/chosen": -0.061837755143642426, | |
| "logits/rejected": -0.09424273669719696, | |
| "logps/chosen": -570.0264892578125, | |
| "logps/rejected": -782.4632568359375, | |
| "loss": 0.3155, | |
| "rewards/accuracies": 0.8999999761581421, | |
| "rewards/chosen": -2.259819984436035, | |
| "rewards/margins": 2.1893467903137207, | |
| "rewards/rejected": -4.449166297912598, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 5.3626246194704575e-11, | |
| "logits/chosen": 0.019718965515494347, | |
| "logits/rejected": -0.05742845684289932, | |
| "logps/chosen": -491.19879150390625, | |
| "logps/rejected": -698.8577880859375, | |
| "loss": 0.3247, | |
| "rewards/accuracies": 0.8687499761581421, | |
| "rewards/chosen": -2.148132801055908, | |
| "rewards/margins": 2.056044816970825, | |
| "rewards/rejected": -4.204176902770996, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 954, | |
| "total_flos": 0.0, | |
| "train_loss": 0.44779854000739333, | |
| "train_runtime": 8782.9823, | |
| "train_samples_per_second": 13.921, | |
| "train_steps_per_second": 0.109 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 954, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |