| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.5702695629416383, | |
| "eval_steps": 100, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.3333333333333334e-09, | |
| "logits/chosen": -2.606384754180908, | |
| "logits/rejected": -2.4982504844665527, | |
| "logps/chosen": -296.16644287109375, | |
| "logps/rejected": -225.2230224609375, | |
| "loss": 0.6931, | |
| "rewards/accuracies": 0.0, | |
| "rewards/chosen": 0.0, | |
| "rewards/margins": 0.0, | |
| "rewards/rejected": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.3333333333333334e-08, | |
| "logits/chosen": -2.517352819442749, | |
| "logits/rejected": -2.4637084007263184, | |
| "logps/chosen": -342.76483154296875, | |
| "logps/rejected": -293.0290222167969, | |
| "loss": 0.6947, | |
| "rewards/accuracies": 0.4305555522441864, | |
| "rewards/chosen": 0.0013976963236927986, | |
| "rewards/margins": -0.0040576523169875145, | |
| "rewards/rejected": 0.005455348175019026, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 6.666666666666667e-08, | |
| "logits/chosen": -2.396883726119995, | |
| "logits/rejected": -2.3743655681610107, | |
| "logps/chosen": -238.6938018798828, | |
| "logps/rejected": -248.8633575439453, | |
| "loss": 0.6943, | |
| "rewards/accuracies": 0.48124998807907104, | |
| "rewards/chosen": -0.0019892356358468533, | |
| "rewards/margins": -0.0029293105471879244, | |
| "rewards/rejected": 0.0009400752605870366, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1e-07, | |
| "logits/chosen": -2.490886688232422, | |
| "logits/rejected": -2.408034563064575, | |
| "logps/chosen": -289.0502014160156, | |
| "logps/rejected": -257.93157958984375, | |
| "loss": 0.6915, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": 8.620424341643229e-05, | |
| "rewards/margins": 0.0004866129602305591, | |
| "rewards/rejected": -0.000400408694986254, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.3333333333333334e-07, | |
| "logits/chosen": -2.479222536087036, | |
| "logits/rejected": -2.4444398880004883, | |
| "logps/chosen": -298.08795166015625, | |
| "logps/rejected": -280.84173583984375, | |
| "loss": 0.6898, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": 0.010273179039359093, | |
| "rewards/margins": 0.005869547836482525, | |
| "rewards/rejected": 0.004403631202876568, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.6666666666666665e-07, | |
| "logits/chosen": -2.505727767944336, | |
| "logits/rejected": -2.4711194038391113, | |
| "logps/chosen": -268.0919494628906, | |
| "logps/rejected": -254.45358276367188, | |
| "loss": 0.6838, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": 0.024473872035741806, | |
| "rewards/margins": 0.018633713945746422, | |
| "rewards/rejected": 0.0058401599526405334, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2e-07, | |
| "logits/chosen": -2.456902265548706, | |
| "logits/rejected": -2.411407947540283, | |
| "logps/chosen": -293.38934326171875, | |
| "logps/rejected": -269.47882080078125, | |
| "loss": 0.677, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": 0.04791393131017685, | |
| "rewards/margins": 0.03436511009931564, | |
| "rewards/rejected": 0.01354882400482893, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.3333333333333333e-07, | |
| "logits/chosen": -2.463378429412842, | |
| "logits/rejected": -2.385895013809204, | |
| "logps/chosen": -290.9529724121094, | |
| "logps/rejected": -276.04107666015625, | |
| "loss": 0.6614, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": 0.09689084440469742, | |
| "rewards/margins": 0.058380376547575, | |
| "rewards/rejected": 0.03851046413183212, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.6666666666666667e-07, | |
| "logits/chosen": -2.4076247215270996, | |
| "logits/rejected": -2.3244595527648926, | |
| "logps/chosen": -321.92596435546875, | |
| "logps/rejected": -284.5071105957031, | |
| "loss": 0.6387, | |
| "rewards/accuracies": 0.668749988079071, | |
| "rewards/chosen": 0.15204539895057678, | |
| "rewards/margins": 0.11996610462665558, | |
| "rewards/rejected": 0.032079294323921204, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 3e-07, | |
| "logits/chosen": -2.3717925548553467, | |
| "logits/rejected": -2.362457752227783, | |
| "logps/chosen": -314.3221435546875, | |
| "logps/rejected": -272.3472595214844, | |
| "loss": 0.6254, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": 0.159285306930542, | |
| "rewards/margins": 0.18115119636058807, | |
| "rewards/rejected": -0.02186589315533638, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 3.333333333333333e-07, | |
| "logits/chosen": -2.3045754432678223, | |
| "logits/rejected": -2.326310634613037, | |
| "logps/chosen": -290.2933349609375, | |
| "logps/rejected": -319.2317199707031, | |
| "loss": 0.6163, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": 0.04698774218559265, | |
| "rewards/margins": 0.2375941276550293, | |
| "rewards/rejected": -0.19060640037059784, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_logits/chosen": -2.3541910648345947, | |
| "eval_logits/rejected": -2.306934118270874, | |
| "eval_logps/chosen": -296.0254211425781, | |
| "eval_logps/rejected": -276.9588623046875, | |
| "eval_loss": 0.6145145297050476, | |
| "eval_rewards/accuracies": 0.7023809552192688, | |
| "eval_rewards/chosen": 0.01473198737949133, | |
| "eval_rewards/margins": 0.2757962942123413, | |
| "eval_rewards/rejected": -0.2610643208026886, | |
| "eval_runtime": 413.5508, | |
| "eval_samples_per_second": 4.836, | |
| "eval_steps_per_second": 0.152, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 3.666666666666666e-07, | |
| "logits/chosen": -2.4004225730895996, | |
| "logits/rejected": -2.336871385574341, | |
| "logps/chosen": -265.05352783203125, | |
| "logps/rejected": -254.93212890625, | |
| "loss": 0.6078, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -0.014697420410811901, | |
| "rewards/margins": 0.27927759289741516, | |
| "rewards/rejected": -0.29397499561309814, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4e-07, | |
| "logits/chosen": -2.400813579559326, | |
| "logits/rejected": -2.317667245864868, | |
| "logps/chosen": -289.80938720703125, | |
| "logps/rejected": -268.9970703125, | |
| "loss": 0.6067, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": 0.11111988872289658, | |
| "rewards/margins": 0.3709365725517273, | |
| "rewards/rejected": -0.2598166763782501, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3333333333333335e-07, | |
| "logits/chosen": -2.4633655548095703, | |
| "logits/rejected": -2.370208263397217, | |
| "logps/chosen": -321.96954345703125, | |
| "logps/rejected": -289.915771484375, | |
| "loss": 0.5958, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": 0.06524975597858429, | |
| "rewards/margins": 0.3465055525302887, | |
| "rewards/rejected": -0.2812557816505432, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.6666666666666666e-07, | |
| "logits/chosen": -2.4572839736938477, | |
| "logits/rejected": -2.402984857559204, | |
| "logps/chosen": -267.6603088378906, | |
| "logps/rejected": -240.7797088623047, | |
| "loss": 0.5789, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": 0.05029069632291794, | |
| "rewards/margins": 0.3604304790496826, | |
| "rewards/rejected": -0.3101397752761841, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5e-07, | |
| "logits/chosen": -2.3665835857391357, | |
| "logits/rejected": -2.3545050621032715, | |
| "logps/chosen": -304.1943054199219, | |
| "logps/rejected": -298.508056640625, | |
| "loss": 0.6084, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": 0.032247237861156464, | |
| "rewards/margins": 0.392182320356369, | |
| "rewards/rejected": -0.35993510484695435, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.999323102948654e-07, | |
| "logits/chosen": -2.453312397003174, | |
| "logits/rejected": -2.3983371257781982, | |
| "logps/chosen": -269.2843322753906, | |
| "logps/rejected": -277.93682861328125, | |
| "loss": 0.5419, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": 0.10002978146076202, | |
| "rewards/margins": 0.553473174571991, | |
| "rewards/rejected": -0.4534434676170349, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.997292778346312e-07, | |
| "logits/chosen": -2.493710517883301, | |
| "logits/rejected": -2.4315335750579834, | |
| "logps/chosen": -300.1785888671875, | |
| "logps/rejected": -257.55157470703125, | |
| "loss": 0.562, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.0674915537238121, | |
| "rewards/margins": 0.48717761039733887, | |
| "rewards/rejected": -0.5546691417694092, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.99391012564956e-07, | |
| "logits/chosen": -2.3834595680236816, | |
| "logits/rejected": -2.3311541080474854, | |
| "logps/chosen": -271.11114501953125, | |
| "logps/rejected": -289.841552734375, | |
| "loss": 0.5335, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -0.27489790320396423, | |
| "rewards/margins": 0.6237329244613647, | |
| "rewards/rejected": -0.8986309170722961, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.989176976624511e-07, | |
| "logits/chosen": -2.546043634414673, | |
| "logits/rejected": -2.4504528045654297, | |
| "logps/chosen": -307.6429138183594, | |
| "logps/rejected": -274.8311462402344, | |
| "loss": 0.5298, | |
| "rewards/accuracies": 0.793749988079071, | |
| "rewards/chosen": 0.14119036495685577, | |
| "rewards/margins": 0.8371874094009399, | |
| "rewards/rejected": -0.6959971189498901, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.983095894354857e-07, | |
| "logits/chosen": -2.489591121673584, | |
| "logits/rejected": -2.4581377506256104, | |
| "logps/chosen": -268.5490417480469, | |
| "logps/rejected": -291.10986328125, | |
| "loss": 0.5608, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -0.1413675844669342, | |
| "rewards/margins": 0.6023878455162048, | |
| "rewards/rejected": -0.7437554597854614, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_logits/chosen": -2.4285523891448975, | |
| "eval_logits/rejected": -2.3805854320526123, | |
| "eval_logps/chosen": -298.1169128417969, | |
| "eval_logps/rejected": -287.88702392578125, | |
| "eval_loss": 0.5506500005722046, | |
| "eval_rewards/accuracies": 0.7400793433189392, | |
| "eval_rewards/chosen": -0.08984197676181793, | |
| "eval_rewards/margins": 0.7176319360733032, | |
| "eval_rewards/rejected": -0.80747389793396, | |
| "eval_runtime": 409.3127, | |
| "eval_samples_per_second": 4.886, | |
| "eval_steps_per_second": 0.154, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.975670171853925e-07, | |
| "logits/chosen": -2.48987078666687, | |
| "logits/rejected": -2.4578893184661865, | |
| "logps/chosen": -309.9327087402344, | |
| "logps/rejected": -268.804443359375, | |
| "loss": 0.5555, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/chosen": 0.00010260194540023804, | |
| "rewards/margins": 0.6477264165878296, | |
| "rewards/rejected": -0.6476237773895264, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.966903830281448e-07, | |
| "logits/chosen": -2.5101141929626465, | |
| "logits/rejected": -2.5068182945251465, | |
| "logps/chosen": -302.55804443359375, | |
| "logps/rejected": -306.7073059082031, | |
| "loss": 0.5371, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": 0.022780220955610275, | |
| "rewards/margins": 0.6337054371833801, | |
| "rewards/rejected": -0.6109251379966736, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.956801616766034e-07, | |
| "logits/chosen": -2.477936267852783, | |
| "logits/rejected": -2.4627578258514404, | |
| "logps/chosen": -334.6808776855469, | |
| "logps/rejected": -300.4921569824219, | |
| "loss": 0.5438, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -0.660649299621582, | |
| "rewards/margins": 0.6745242476463318, | |
| "rewards/rejected": -1.3351736068725586, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.945369001834514e-07, | |
| "logits/chosen": -2.4449329376220703, | |
| "logits/rejected": -2.3937153816223145, | |
| "logps/chosen": -280.98468017578125, | |
| "logps/rejected": -243.7540283203125, | |
| "loss": 0.5362, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": -0.5287132263183594, | |
| "rewards/margins": 0.6548066139221191, | |
| "rewards/rejected": -1.1835198402404785, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.932612176449559e-07, | |
| "logits/chosen": -2.3831703662872314, | |
| "logits/rejected": -2.3532094955444336, | |
| "logps/chosen": -308.6506042480469, | |
| "logps/rejected": -295.2610778808594, | |
| "loss": 0.5517, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -0.20035383105278015, | |
| "rewards/margins": 0.6892730593681335, | |
| "rewards/rejected": -0.8896268606185913, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.918538048657159e-07, | |
| "logits/chosen": -2.381070852279663, | |
| "logits/rejected": -2.356685161590576, | |
| "logps/chosen": -260.6903076171875, | |
| "logps/rejected": -273.7911682128906, | |
| "loss": 0.5333, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": -0.3518093228340149, | |
| "rewards/margins": 0.6164388060569763, | |
| "rewards/rejected": -0.9682480692863464, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.903154239845797e-07, | |
| "logits/chosen": -2.385469436645508, | |
| "logits/rejected": -2.3523507118225098, | |
| "logps/chosen": -312.2256774902344, | |
| "logps/rejected": -312.83526611328125, | |
| "loss": 0.5092, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -0.35005810856819153, | |
| "rewards/margins": 0.9718685150146484, | |
| "rewards/rejected": -1.3219265937805176, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.88646908061933e-07, | |
| "logits/chosen": -2.4627230167388916, | |
| "logits/rejected": -2.418569564819336, | |
| "logps/chosen": -317.95703125, | |
| "logps/rejected": -289.7148742675781, | |
| "loss": 0.5104, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -0.29435399174690247, | |
| "rewards/margins": 0.9088577032089233, | |
| "rewards/rejected": -1.2032116651535034, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.868491606285823e-07, | |
| "logits/chosen": -2.4506328105926514, | |
| "logits/rejected": -2.3806400299072266, | |
| "logps/chosen": -302.1065673828125, | |
| "logps/rejected": -251.01498413085938, | |
| "loss": 0.5353, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -0.43174147605895996, | |
| "rewards/margins": 0.6914370656013489, | |
| "rewards/rejected": -1.123178482055664, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.849231551964771e-07, | |
| "logits/chosen": -2.431826591491699, | |
| "logits/rejected": -2.354094982147217, | |
| "logps/chosen": -268.3138122558594, | |
| "logps/rejected": -259.5442199707031, | |
| "loss": 0.4934, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -0.18001610040664673, | |
| "rewards/margins": 0.8297437429428101, | |
| "rewards/rejected": -1.009759783744812, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_logits/chosen": -2.3849596977233887, | |
| "eval_logits/rejected": -2.3416402339935303, | |
| "eval_logps/chosen": -299.6116638183594, | |
| "eval_logps/rejected": -292.5220947265625, | |
| "eval_loss": 0.5225438475608826, | |
| "eval_rewards/accuracies": 0.7579365372657776, | |
| "eval_rewards/chosen": -0.16457918286323547, | |
| "eval_rewards/margins": 0.8746477365493774, | |
| "eval_rewards/rejected": -1.03922700881958, | |
| "eval_runtime": 407.614, | |
| "eval_samples_per_second": 4.907, | |
| "eval_steps_per_second": 0.155, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.828699347315356e-07, | |
| "logits/chosen": -2.3300023078918457, | |
| "logits/rejected": -2.291306972503662, | |
| "logps/chosen": -281.8946228027344, | |
| "logps/rejected": -328.680908203125, | |
| "loss": 0.4757, | |
| "rewards/accuracies": 0.8374999761581421, | |
| "rewards/chosen": -0.23267221450805664, | |
| "rewards/margins": 1.1307260990142822, | |
| "rewards/rejected": -1.3633983135223389, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.806906110888606e-07, | |
| "logits/chosen": -2.2734484672546387, | |
| "logits/rejected": -2.2220654487609863, | |
| "logps/chosen": -344.95184326171875, | |
| "logps/rejected": -317.2240295410156, | |
| "loss": 0.5251, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -0.40918412804603577, | |
| "rewards/margins": 1.0021181106567383, | |
| "rewards/rejected": -1.4113022089004517, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.783863644106502e-07, | |
| "logits/chosen": -2.2840628623962402, | |
| "logits/rejected": -2.2298922538757324, | |
| "logps/chosen": -281.0782775878906, | |
| "logps/rejected": -242.35263061523438, | |
| "loss": 0.553, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -0.017911773175001144, | |
| "rewards/margins": 0.6968544721603394, | |
| "rewards/rejected": -0.714766263961792, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.759584424871301e-07, | |
| "logits/chosen": -2.270648717880249, | |
| "logits/rejected": -2.2538352012634277, | |
| "logps/chosen": -297.785888671875, | |
| "logps/rejected": -256.94305419921875, | |
| "loss": 0.5741, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": 0.040852271020412445, | |
| "rewards/margins": 0.6195092797279358, | |
| "rewards/rejected": -0.5786570310592651, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.7340816008085305e-07, | |
| "logits/chosen": -2.3321385383605957, | |
| "logits/rejected": -2.301793336868286, | |
| "logps/chosen": -321.775390625, | |
| "logps/rejected": -314.6920471191406, | |
| "loss": 0.5205, | |
| "rewards/accuracies": 0.8187500238418579, | |
| "rewards/chosen": -0.3098350465297699, | |
| "rewards/margins": 0.9677619934082031, | |
| "rewards/rejected": -1.2775970697402954, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.707368982147317e-07, | |
| "logits/chosen": -2.460111379623413, | |
| "logits/rejected": -2.429689884185791, | |
| "logps/chosen": -289.2377014160156, | |
| "logps/rejected": -296.45123291015625, | |
| "loss": 0.5145, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": -0.8857641220092773, | |
| "rewards/margins": 0.7435467839241028, | |
| "rewards/rejected": -1.6293108463287354, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.6794610342419056e-07, | |
| "logits/chosen": -2.403916120529175, | |
| "logits/rejected": -2.338923931121826, | |
| "logps/chosen": -287.01434326171875, | |
| "logps/rejected": -307.77728271484375, | |
| "loss": 0.4818, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -0.28949111700057983, | |
| "rewards/margins": 1.0141589641571045, | |
| "rewards/rejected": -1.303650140762329, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.650372869738414e-07, | |
| "logits/chosen": -2.4299778938293457, | |
| "logits/rejected": -2.404153347015381, | |
| "logps/chosen": -310.12152099609375, | |
| "logps/rejected": -294.5881652832031, | |
| "loss": 0.5046, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -0.4136735796928406, | |
| "rewards/margins": 0.9840124249458313, | |
| "rewards/rejected": -1.3976860046386719, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.6201202403910643e-07, | |
| "logits/chosen": -2.3376293182373047, | |
| "logits/rejected": -2.289973020553589, | |
| "logps/chosen": -299.35546875, | |
| "logps/rejected": -284.88323974609375, | |
| "loss": 0.5184, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -0.6497005224227905, | |
| "rewards/margins": 1.0391151905059814, | |
| "rewards/rejected": -1.688815712928772, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.588719528532341e-07, | |
| "logits/chosen": -2.458130359649658, | |
| "logits/rejected": -2.4228129386901855, | |
| "logps/chosen": -315.5902404785156, | |
| "logps/rejected": -292.9128112792969, | |
| "loss": 0.4812, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -0.5732877254486084, | |
| "rewards/margins": 0.7860868573188782, | |
| "rewards/rejected": -1.359374761581421, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_logits/chosen": -2.369720458984375, | |
| "eval_logits/rejected": -2.3284802436828613, | |
| "eval_logps/chosen": -300.5794982910156, | |
| "eval_logps/rejected": -295.33331298828125, | |
| "eval_loss": 0.5147603154182434, | |
| "eval_rewards/accuracies": 0.7599206566810608, | |
| "eval_rewards/chosen": -0.21297024190425873, | |
| "eval_rewards/margins": 0.9668172597885132, | |
| "eval_rewards/rejected": -1.179787516593933, | |
| "eval_runtime": 407.8456, | |
| "eval_samples_per_second": 4.904, | |
| "eval_steps_per_second": 0.154, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.5561877382016553e-07, | |
| "logits/chosen": -2.4733567237854004, | |
| "logits/rejected": -2.429727792739868, | |
| "logps/chosen": -300.5076599121094, | |
| "logps/rejected": -275.7524108886719, | |
| "loss": 0.5144, | |
| "rewards/accuracies": 0.6937500238418579, | |
| "rewards/chosen": -0.15985186398029327, | |
| "rewards/margins": 0.7756703495979309, | |
| "rewards/rejected": -0.935522198677063, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.5225424859373684e-07, | |
| "logits/chosen": -2.3798115253448486, | |
| "logits/rejected": -2.3424534797668457, | |
| "logps/chosen": -243.74472045898438, | |
| "logps/rejected": -266.5513916015625, | |
| "loss": 0.5302, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": -0.005200001411139965, | |
| "rewards/margins": 0.7427350878715515, | |
| "rewards/rejected": -0.7479350566864014, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.487801991237119e-07, | |
| "logits/chosen": -2.441993236541748, | |
| "logits/rejected": -2.414069890975952, | |
| "logps/chosen": -303.46893310546875, | |
| "logps/rejected": -286.26470947265625, | |
| "loss": 0.5387, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -0.12445823103189468, | |
| "rewards/margins": 0.7546092867851257, | |
| "rewards/rejected": -0.8790675401687622, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.451985066691648e-07, | |
| "logits/chosen": -2.444979429244995, | |
| "logits/rejected": -2.402029514312744, | |
| "logps/chosen": -300.88037109375, | |
| "logps/rejected": -275.1875915527344, | |
| "loss": 0.4965, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -0.5577610731124878, | |
| "rewards/margins": 0.7658098340034485, | |
| "rewards/rejected": -1.323570966720581, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.415111107797445e-07, | |
| "logits/chosen": -2.290574550628662, | |
| "logits/rejected": -2.2670164108276367, | |
| "logps/chosen": -236.2515106201172, | |
| "logps/rejected": -255.0359344482422, | |
| "loss": 0.5183, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -0.5639761090278625, | |
| "rewards/margins": 0.8503490686416626, | |
| "rewards/rejected": -1.4143251180648804, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.377200082453748e-07, | |
| "logits/chosen": -2.467921495437622, | |
| "logits/rejected": -2.422136068344116, | |
| "logps/chosen": -329.4405822753906, | |
| "logps/rejected": -305.3108825683594, | |
| "loss": 0.4962, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -0.41245952248573303, | |
| "rewards/margins": 0.9212630987167358, | |
| "rewards/rejected": -1.333722710609436, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.3382725201495717e-07, | |
| "logits/chosen": -2.3804707527160645, | |
| "logits/rejected": -2.3205363750457764, | |
| "logps/chosen": -282.99945068359375, | |
| "logps/rejected": -292.9880065917969, | |
| "loss": 0.4927, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -0.5624107718467712, | |
| "rewards/margins": 0.8573344349861145, | |
| "rewards/rejected": -1.4197450876235962, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.2983495008466273e-07, | |
| "logits/chosen": -2.302927255630493, | |
| "logits/rejected": -2.272263765335083, | |
| "logps/chosen": -271.0894470214844, | |
| "logps/rejected": -286.90118408203125, | |
| "loss": 0.5345, | |
| "rewards/accuracies": 0.6937500238418579, | |
| "rewards/chosen": -0.5512509346008301, | |
| "rewards/margins": 0.8141476511955261, | |
| "rewards/rejected": -1.365398645401001, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.2574526435641546e-07, | |
| "logits/chosen": -2.311328172683716, | |
| "logits/rejected": -2.276010274887085, | |
| "logps/chosen": -285.27960205078125, | |
| "logps/rejected": -270.05401611328125, | |
| "loss": 0.5116, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -0.49702826142311096, | |
| "rewards/margins": 0.8841336369514465, | |
| "rewards/rejected": -1.3811619281768799, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.2156040946718343e-07, | |
| "logits/chosen": -2.3711423873901367, | |
| "logits/rejected": -2.286292552947998, | |
| "logps/chosen": -304.9607238769531, | |
| "logps/rejected": -297.2706604003906, | |
| "loss": 0.5217, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -0.5594313740730286, | |
| "rewards/margins": 1.1461693048477173, | |
| "rewards/rejected": -1.7056007385253906, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_logits/chosen": -2.3431873321533203, | |
| "eval_logits/rejected": -2.3073697090148926, | |
| "eval_logps/chosen": -299.8136291503906, | |
| "eval_logps/rejected": -294.8787841796875, | |
| "eval_loss": 0.5093801617622375, | |
| "eval_rewards/accuracies": 0.7599206566810608, | |
| "eval_rewards/chosen": -0.17467793822288513, | |
| "eval_rewards/margins": 0.982383131980896, | |
| "eval_rewards/rejected": -1.157060980796814, | |
| "eval_runtime": 409.4153, | |
| "eval_samples_per_second": 4.885, | |
| "eval_steps_per_second": 0.154, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.172826515897145e-07, | |
| "logits/chosen": -2.380160331726074, | |
| "logits/rejected": -2.3342180252075195, | |
| "logps/chosen": -285.99005126953125, | |
| "logps/rejected": -262.095703125, | |
| "loss": 0.4819, | |
| "rewards/accuracies": 0.8062499761581421, | |
| "rewards/chosen": -0.1991649866104126, | |
| "rewards/margins": 0.9838080406188965, | |
| "rewards/rejected": -1.1829731464385986, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.129143072053638e-07, | |
| "logits/chosen": -2.430504322052002, | |
| "logits/rejected": -2.3967652320861816, | |
| "logps/chosen": -295.1175842285156, | |
| "logps/rejected": -298.79034423828125, | |
| "loss": 0.4879, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": -0.2341586798429489, | |
| "rewards/margins": 0.9701293110847473, | |
| "rewards/rejected": -1.2042880058288574, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.084577418496775e-07, | |
| "logits/chosen": -2.459068775177002, | |
| "logits/rejected": -2.4153661727905273, | |
| "logps/chosen": -303.06683349609375, | |
| "logps/rejected": -333.80609130859375, | |
| "loss": 0.4868, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -0.4716320037841797, | |
| "rewards/margins": 1.0053110122680664, | |
| "rewards/rejected": -1.4769428968429565, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.039153688314145e-07, | |
| "logits/chosen": -2.4637537002563477, | |
| "logits/rejected": -2.4269044399261475, | |
| "logps/chosen": -304.27166748046875, | |
| "logps/rejected": -302.20477294921875, | |
| "loss": 0.4986, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -0.45887041091918945, | |
| "rewards/margins": 1.0204750299453735, | |
| "rewards/rejected": -1.4793453216552734, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.9928964792569654e-07, | |
| "logits/chosen": -2.4167208671569824, | |
| "logits/rejected": -2.3573527336120605, | |
| "logps/chosen": -303.3789978027344, | |
| "logps/rejected": -296.81060791015625, | |
| "loss": 0.5343, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -0.59644615650177, | |
| "rewards/margins": 0.9994708895683289, | |
| "rewards/rejected": -1.595916986465454, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.945830840419966e-07, | |
| "logits/chosen": -2.3017094135284424, | |
| "logits/rejected": -2.2486953735351562, | |
| "logps/chosen": -298.501708984375, | |
| "logps/rejected": -250.04556274414062, | |
| "loss": 0.5037, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -0.4263156056404114, | |
| "rewards/margins": 0.9166458249092102, | |
| "rewards/rejected": -1.3429615497589111, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.8979822586768666e-07, | |
| "logits/chosen": -2.308485507965088, | |
| "logits/rejected": -2.259333610534668, | |
| "logps/chosen": -274.44329833984375, | |
| "logps/rejected": -297.6800537109375, | |
| "loss": 0.5011, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/chosen": -0.19708169996738434, | |
| "rewards/margins": 0.9468144178390503, | |
| "rewards/rejected": -1.1438961029052734, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.849376644878782e-07, | |
| "logits/chosen": -2.3406989574432373, | |
| "logits/rejected": -2.2872297763824463, | |
| "logps/chosen": -293.8192443847656, | |
| "logps/rejected": -292.8212585449219, | |
| "loss": 0.5012, | |
| "rewards/accuracies": 0.8062499761581421, | |
| "rewards/chosen": -0.24491167068481445, | |
| "rewards/margins": 1.1491771936416626, | |
| "rewards/rejected": -1.394088864326477, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.800040319823038e-07, | |
| "logits/chosen": -2.2375845909118652, | |
| "logits/rejected": -2.21081280708313, | |
| "logps/chosen": -281.64678955078125, | |
| "logps/rejected": -281.1907958984375, | |
| "loss": 0.5189, | |
| "rewards/accuracies": 0.668749988079071, | |
| "rewards/chosen": -0.33811599016189575, | |
| "rewards/margins": 0.640630841255188, | |
| "rewards/rejected": -0.9787468910217285, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.75e-07, | |
| "logits/chosen": -2.336167812347412, | |
| "logits/rejected": -2.3122599124908447, | |
| "logps/chosen": -316.1159362792969, | |
| "logps/rejected": -348.52728271484375, | |
| "loss": 0.5069, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": 0.08971457183361053, | |
| "rewards/margins": 1.1014090776443481, | |
| "rewards/rejected": -1.0116945505142212, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_logits/chosen": -2.2853615283966064, | |
| "eval_logits/rejected": -2.2443532943725586, | |
| "eval_logps/chosen": -297.127197265625, | |
| "eval_logps/rejected": -292.7251281738281, | |
| "eval_loss": 0.5037240982055664, | |
| "eval_rewards/accuracies": 0.7658730149269104, | |
| "eval_rewards/chosen": -0.04035760462284088, | |
| "eval_rewards/margins": 1.009021520614624, | |
| "eval_rewards/rejected": -1.0493791103363037, | |
| "eval_runtime": 411.3039, | |
| "eval_samples_per_second": 4.863, | |
| "eval_steps_per_second": 0.153, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.699282783125616e-07, | |
| "logits/chosen": -2.29797625541687, | |
| "logits/rejected": -2.2567286491394043, | |
| "logps/chosen": -333.64312744140625, | |
| "logps/rejected": -276.2323913574219, | |
| "loss": 0.4939, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -0.5196839570999146, | |
| "rewards/margins": 0.9884433746337891, | |
| "rewards/rejected": -1.508127212524414, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.647916133467529e-07, | |
| "logits/chosen": -2.3571763038635254, | |
| "logits/rejected": -2.2932493686676025, | |
| "logps/chosen": -308.9863586425781, | |
| "logps/rejected": -301.33367919921875, | |
| "loss": 0.4919, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/chosen": -1.0287619829177856, | |
| "rewards/margins": 0.9334309697151184, | |
| "rewards/rejected": -1.9621927738189697, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.595927866972693e-07, | |
| "logits/chosen": -2.352038860321045, | |
| "logits/rejected": -2.2862563133239746, | |
| "logps/chosen": -293.9407958984375, | |
| "logps/rejected": -288.50885009765625, | |
| "loss": 0.4733, | |
| "rewards/accuracies": 0.7875000238418579, | |
| "rewards/chosen": -0.5753384828567505, | |
| "rewards/margins": 1.169237494468689, | |
| "rewards/rejected": -1.744576096534729, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.5433461362045447e-07, | |
| "logits/chosen": -2.3236405849456787, | |
| "logits/rejected": -2.302849054336548, | |
| "logps/chosen": -262.9497375488281, | |
| "logps/rejected": -284.64642333984375, | |
| "loss": 0.4962, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -0.15619780123233795, | |
| "rewards/margins": 1.1346657276153564, | |
| "rewards/rejected": -1.2908635139465332, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.490199415097892e-07, | |
| "logits/chosen": -2.3758909702301025, | |
| "logits/rejected": -2.300546169281006, | |
| "logps/chosen": -324.71881103515625, | |
| "logps/rejected": -303.84881591796875, | |
| "loss": 0.494, | |
| "rewards/accuracies": 0.8062499761581421, | |
| "rewards/chosen": 0.004534644540399313, | |
| "rewards/margins": 1.049611210823059, | |
| "rewards/rejected": -1.045076608657837, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.43651648353978e-07, | |
| "logits/chosen": -2.4268946647644043, | |
| "logits/rejected": -2.3779337406158447, | |
| "logps/chosen": -320.46429443359375, | |
| "logps/rejected": -281.7370910644531, | |
| "loss": 0.5142, | |
| "rewards/accuracies": 0.65625, | |
| "rewards/chosen": -0.28596049547195435, | |
| "rewards/margins": 0.7663468718528748, | |
| "rewards/rejected": -1.052307367324829, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.3823264117846717e-07, | |
| "logits/chosen": -2.353480100631714, | |
| "logits/rejected": -2.3156867027282715, | |
| "logps/chosen": -294.9992980957031, | |
| "logps/rejected": -279.8269958496094, | |
| "loss": 0.5042, | |
| "rewards/accuracies": 0.8125, | |
| "rewards/chosen": -0.3519328236579895, | |
| "rewards/margins": 1.0733650922775269, | |
| "rewards/rejected": -1.4252979755401611, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.327658544712395e-07, | |
| "logits/chosen": -2.349534273147583, | |
| "logits/rejected": -2.2964000701904297, | |
| "logps/chosen": -302.86798095703125, | |
| "logps/rejected": -278.29827880859375, | |
| "loss": 0.5219, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.47534093260765076, | |
| "rewards/margins": 0.663826584815979, | |
| "rewards/rejected": -1.1391674280166626, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.272542485937368e-07, | |
| "logits/chosen": -2.3173270225524902, | |
| "logits/rejected": -2.2520382404327393, | |
| "logps/chosen": -266.728515625, | |
| "logps/rejected": -234.1517333984375, | |
| "loss": 0.5044, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -0.2846493721008301, | |
| "rewards/margins": 0.9897111058235168, | |
| "rewards/rejected": -1.2743605375289917, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.2170080817777257e-07, | |
| "logits/chosen": -2.3343617916107178, | |
| "logits/rejected": -2.2195441722869873, | |
| "logps/chosen": -297.25250244140625, | |
| "logps/rejected": -286.7340393066406, | |
| "loss": 0.4582, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -0.5840951800346375, | |
| "rewards/margins": 1.0429940223693848, | |
| "rewards/rejected": -1.6270891427993774, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_logits/chosen": -2.289731979370117, | |
| "eval_logits/rejected": -2.246857166290283, | |
| "eval_logps/chosen": -308.9957580566406, | |
| "eval_logps/rejected": -306.2008056640625, | |
| "eval_loss": 0.500346839427948, | |
| "eval_rewards/accuracies": 0.7599206566810608, | |
| "eval_rewards/chosen": -0.6337829232215881, | |
| "eval_rewards/margins": 1.0893793106079102, | |
| "eval_rewards/rejected": -1.7231621742248535, | |
| "eval_runtime": 438.5736, | |
| "eval_samples_per_second": 4.56, | |
| "eval_steps_per_second": 0.144, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.1610854050930057e-07, | |
| "logits/chosen": -2.3422415256500244, | |
| "logits/rejected": -2.2789344787597656, | |
| "logps/chosen": -298.95867919921875, | |
| "logps/rejected": -271.91290283203125, | |
| "loss": 0.474, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -0.5943951606750488, | |
| "rewards/margins": 0.9698866009712219, | |
| "rewards/rejected": -1.5642818212509155, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.104804738999169e-07, | |
| "logits/chosen": -2.296921968460083, | |
| "logits/rejected": -2.277675151824951, | |
| "logps/chosen": -288.68511962890625, | |
| "logps/rejected": -294.5284729003906, | |
| "loss": 0.4741, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -0.4995554983615875, | |
| "rewards/margins": 1.2392946481704712, | |
| "rewards/rejected": -1.7388503551483154, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.048196560469758e-07, | |
| "logits/chosen": -2.320403575897217, | |
| "logits/rejected": -2.276542901992798, | |
| "logps/chosen": -317.94012451171875, | |
| "logps/rejected": -283.49920654296875, | |
| "loss": 0.4819, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -0.4403966963291168, | |
| "rewards/margins": 1.0142490863800049, | |
| "rewards/rejected": -1.4546458721160889, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.991291523832075e-07, | |
| "logits/chosen": -2.3161144256591797, | |
| "logits/rejected": -2.2607274055480957, | |
| "logps/chosen": -326.93829345703125, | |
| "logps/rejected": -328.2031555175781, | |
| "loss": 0.4746, | |
| "rewards/accuracies": 0.8125, | |
| "rewards/chosen": -0.6947178840637207, | |
| "rewards/margins": 1.2727077007293701, | |
| "rewards/rejected": -1.9674255847930908, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.934120444167326e-07, | |
| "logits/chosen": -2.292912006378174, | |
| "logits/rejected": -2.2443642616271973, | |
| "logps/chosen": -282.31536865234375, | |
| "logps/rejected": -312.34735107421875, | |
| "loss": 0.4777, | |
| "rewards/accuracies": 0.793749988079071, | |
| "rewards/chosen": -0.9387601017951965, | |
| "rewards/margins": 1.1481364965438843, | |
| "rewards/rejected": -2.0868964195251465, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.8767142806237077e-07, | |
| "logits/chosen": -2.369844913482666, | |
| "logits/rejected": -2.368522882461548, | |
| "logps/chosen": -308.49700927734375, | |
| "logps/rejected": -300.10455322265625, | |
| "loss": 0.4665, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": -0.539741039276123, | |
| "rewards/margins": 1.0256460905075073, | |
| "rewards/rejected": -1.5653870105743408, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.819104119651487e-07, | |
| "logits/chosen": -2.3911471366882324, | |
| "logits/rejected": -2.3795692920684814, | |
| "logps/chosen": -315.2966613769531, | |
| "logps/rejected": -321.0699157714844, | |
| "loss": 0.5096, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -0.39289337396621704, | |
| "rewards/margins": 1.0190023183822632, | |
| "rewards/rejected": -1.411895751953125, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.761321158169134e-07, | |
| "logits/chosen": -2.3824098110198975, | |
| "logits/rejected": -2.333876132965088, | |
| "logps/chosen": -309.57403564453125, | |
| "logps/rejected": -271.635009765625, | |
| "loss": 0.4965, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -0.31998205184936523, | |
| "rewards/margins": 1.0204508304595947, | |
| "rewards/rejected": -1.3404327630996704, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 2.703396686669646e-07, | |
| "logits/chosen": -2.3626012802124023, | |
| "logits/rejected": -2.336550235748291, | |
| "logps/chosen": -282.4324035644531, | |
| "logps/rejected": -289.73907470703125, | |
| "loss": 0.4969, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -0.40831103920936584, | |
| "rewards/margins": 0.9678645133972168, | |
| "rewards/rejected": -1.3761756420135498, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.6453620722761895e-07, | |
| "logits/chosen": -2.2754549980163574, | |
| "logits/rejected": -2.227632999420166, | |
| "logps/chosen": -324.36065673828125, | |
| "logps/rejected": -315.53265380859375, | |
| "loss": 0.457, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -0.40555134415626526, | |
| "rewards/margins": 1.2698910236358643, | |
| "rewards/rejected": -1.6754423379898071, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_logits/chosen": -2.3341588973999023, | |
| "eval_logits/rejected": -2.292834520339966, | |
| "eval_logps/chosen": -306.1227722167969, | |
| "eval_logps/rejected": -303.84637451171875, | |
| "eval_loss": 0.4906502664089203, | |
| "eval_rewards/accuracies": 0.7638888955116272, | |
| "eval_rewards/chosen": -0.4901339113712311, | |
| "eval_rewards/margins": 1.1153074502944946, | |
| "eval_rewards/rejected": -1.6054412126541138, | |
| "eval_runtime": 442.4535, | |
| "eval_samples_per_second": 4.52, | |
| "eval_steps_per_second": 0.142, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.5872487417562527e-07, | |
| "logits/chosen": -2.3688154220581055, | |
| "logits/rejected": -2.2756457328796387, | |
| "logps/chosen": -302.0091552734375, | |
| "logps/rejected": -267.61712646484375, | |
| "loss": 0.5048, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -0.739054799079895, | |
| "rewards/margins": 0.9176353216171265, | |
| "rewards/rejected": -1.656690001487732, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 2.5290881645034926e-07, | |
| "logits/chosen": -2.371279239654541, | |
| "logits/rejected": -2.3216042518615723, | |
| "logps/chosen": -307.4602966308594, | |
| "logps/rejected": -276.8441162109375, | |
| "loss": 0.5156, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/chosen": -0.4735354781150818, | |
| "rewards/margins": 1.1825616359710693, | |
| "rewards/rejected": -1.656097173690796, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.4709118354965077e-07, | |
| "logits/chosen": -2.3698923587799072, | |
| "logits/rejected": -2.3812479972839355, | |
| "logps/chosen": -283.11395263671875, | |
| "logps/rejected": -314.9549865722656, | |
| "loss": 0.4728, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -0.5311114192008972, | |
| "rewards/margins": 0.8778692483901978, | |
| "rewards/rejected": -1.4089806079864502, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.412751258243748e-07, | |
| "logits/chosen": -2.377016305923462, | |
| "logits/rejected": -2.3782734870910645, | |
| "logps/chosen": -294.67608642578125, | |
| "logps/rejected": -310.6152038574219, | |
| "loss": 0.4955, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -0.6087425351142883, | |
| "rewards/margins": 0.8135608434677124, | |
| "rewards/rejected": -1.4223034381866455, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 2.3546379277238103e-07, | |
| "logits/chosen": -2.422614574432373, | |
| "logits/rejected": -2.39127779006958, | |
| "logps/chosen": -313.9159240722656, | |
| "logps/rejected": -270.3652648925781, | |
| "loss": 0.4874, | |
| "rewards/accuracies": 0.7875000238418579, | |
| "rewards/chosen": -0.7056568264961243, | |
| "rewards/margins": 0.9642340540885925, | |
| "rewards/rejected": -1.6698909997940063, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.2966033133303545e-07, | |
| "logits/chosen": -2.378150463104248, | |
| "logits/rejected": -2.3483357429504395, | |
| "logps/chosen": -326.0942687988281, | |
| "logps/rejected": -330.057373046875, | |
| "loss": 0.4994, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -0.8599470257759094, | |
| "rewards/margins": 0.9078429341316223, | |
| "rewards/rejected": -1.7677898406982422, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.2386788418308665e-07, | |
| "logits/chosen": -2.4225101470947266, | |
| "logits/rejected": -2.4114060401916504, | |
| "logps/chosen": -266.55108642578125, | |
| "logps/rejected": -283.1296081542969, | |
| "loss": 0.501, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -0.5755284428596497, | |
| "rewards/margins": 1.0859739780426025, | |
| "rewards/rejected": -1.6615022420883179, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.1808958803485133e-07, | |
| "logits/chosen": -2.483870506286621, | |
| "logits/rejected": -2.426514148712158, | |
| "logps/chosen": -305.41119384765625, | |
| "logps/rejected": -296.4634704589844, | |
| "loss": 0.4761, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -0.4832102358341217, | |
| "rewards/margins": 0.9984723925590515, | |
| "rewards/rejected": -1.481682538986206, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.123285719376292e-07, | |
| "logits/chosen": -2.4902679920196533, | |
| "logits/rejected": -2.4276280403137207, | |
| "logps/chosen": -306.55987548828125, | |
| "logps/rejected": -308.28216552734375, | |
| "loss": 0.4792, | |
| "rewards/accuracies": 0.831250011920929, | |
| "rewards/chosen": -0.5795844793319702, | |
| "rewards/margins": 1.21144700050354, | |
| "rewards/rejected": -1.7910315990447998, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.065879555832674e-07, | |
| "logits/chosen": -2.3825860023498535, | |
| "logits/rejected": -2.32081937789917, | |
| "logps/chosen": -300.0443115234375, | |
| "logps/rejected": -298.1470642089844, | |
| "loss": 0.4723, | |
| "rewards/accuracies": 0.7875000238418579, | |
| "rewards/chosen": -0.6022388339042664, | |
| "rewards/margins": 1.1292412281036377, | |
| "rewards/rejected": -1.7314800024032593, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_logits/chosen": -2.3762104511260986, | |
| "eval_logits/rejected": -2.3354876041412354, | |
| "eval_logps/chosen": -305.15618896484375, | |
| "eval_logps/rejected": -302.8718566894531, | |
| "eval_loss": 0.4933333098888397, | |
| "eval_rewards/accuracies": 0.7658730149269104, | |
| "eval_rewards/chosen": -0.4418059289455414, | |
| "eval_rewards/margins": 1.114911437034607, | |
| "eval_rewards/rejected": -1.5567171573638916, | |
| "eval_runtime": 427.8237, | |
| "eval_samples_per_second": 4.675, | |
| "eval_steps_per_second": 0.147, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.0087084761679243e-07, | |
| "logits/chosen": -2.433973789215088, | |
| "logits/rejected": -2.3652501106262207, | |
| "logps/chosen": -312.04620361328125, | |
| "logps/rejected": -285.4141540527344, | |
| "loss": 0.4747, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -0.3190104365348816, | |
| "rewards/margins": 1.0960520505905151, | |
| "rewards/rejected": -1.4150625467300415, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.9518034395302412e-07, | |
| "logits/chosen": -2.3947741985321045, | |
| "logits/rejected": -2.349290370941162, | |
| "logps/chosen": -300.0207214355469, | |
| "logps/rejected": -293.3101501464844, | |
| "loss": 0.4644, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/chosen": -0.2700619399547577, | |
| "rewards/margins": 1.2211670875549316, | |
| "rewards/rejected": -1.4912290573120117, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.895195261000831e-07, | |
| "logits/chosen": -2.426356792449951, | |
| "logits/rejected": -2.363300323486328, | |
| "logps/chosen": -273.56988525390625, | |
| "logps/rejected": -281.79144287109375, | |
| "loss": 0.4792, | |
| "rewards/accuracies": 0.8125, | |
| "rewards/chosen": -0.19313231110572815, | |
| "rewards/margins": 1.6159725189208984, | |
| "rewards/rejected": -1.8091049194335938, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.8389145949069951e-07, | |
| "logits/chosen": -2.504002094268799, | |
| "logits/rejected": -2.434199810028076, | |
| "logps/chosen": -312.13922119140625, | |
| "logps/rejected": -303.17279052734375, | |
| "loss": 0.4749, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": -0.8358801603317261, | |
| "rewards/margins": 1.0024197101593018, | |
| "rewards/rejected": -1.8382999897003174, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.782991918222275e-07, | |
| "logits/chosen": -2.4335973262786865, | |
| "logits/rejected": -2.371967315673828, | |
| "logps/chosen": -297.8493957519531, | |
| "logps/rejected": -308.2081604003906, | |
| "loss": 0.5115, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -1.042378544807434, | |
| "rewards/margins": 0.9967982172966003, | |
| "rewards/rejected": -2.0391769409179688, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.7274575140626315e-07, | |
| "logits/chosen": -2.4119739532470703, | |
| "logits/rejected": -2.3814332485198975, | |
| "logps/chosen": -291.4102478027344, | |
| "logps/rejected": -332.5351257324219, | |
| "loss": 0.3924, | |
| "rewards/accuracies": 0.824999988079071, | |
| "rewards/chosen": -0.6064465045928955, | |
| "rewards/margins": 1.3707728385925293, | |
| "rewards/rejected": -1.9772193431854248, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.672341455287605e-07, | |
| "logits/chosen": -2.4356229305267334, | |
| "logits/rejected": -2.380049228668213, | |
| "logps/chosen": -317.14300537109375, | |
| "logps/rejected": -315.25616455078125, | |
| "loss": 0.2962, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -0.3146964907646179, | |
| "rewards/margins": 1.8185898065567017, | |
| "rewards/rejected": -2.133286237716675, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.617673588215328e-07, | |
| "logits/chosen": -2.4142088890075684, | |
| "logits/rejected": -2.3693430423736572, | |
| "logps/chosen": -248.46224975585938, | |
| "logps/rejected": -285.1511535644531, | |
| "loss": 0.2886, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -0.18761667609214783, | |
| "rewards/margins": 1.7726829051971436, | |
| "rewards/rejected": -1.9602997303009033, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.5634835164602196e-07, | |
| "logits/chosen": -2.4898295402526855, | |
| "logits/rejected": -2.4521660804748535, | |
| "logps/chosen": -336.2506103515625, | |
| "logps/rejected": -302.1678161621094, | |
| "loss": 0.2961, | |
| "rewards/accuracies": 0.875, | |
| "rewards/chosen": -0.21727129817008972, | |
| "rewards/margins": 1.7004649639129639, | |
| "rewards/rejected": -1.917736291885376, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.5098005849021078e-07, | |
| "logits/chosen": -2.4500224590301514, | |
| "logits/rejected": -2.4026894569396973, | |
| "logps/chosen": -296.7429504394531, | |
| "logps/rejected": -283.27789306640625, | |
| "loss": 0.3094, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -0.8134616017341614, | |
| "rewards/margins": 1.605277419090271, | |
| "rewards/rejected": -2.418738842010498, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_logits/chosen": -2.40937876701355, | |
| "eval_logits/rejected": -2.369751214981079, | |
| "eval_logps/chosen": -312.38043212890625, | |
| "eval_logps/rejected": -312.68560791015625, | |
| "eval_loss": 0.49218976497650146, | |
| "eval_rewards/accuracies": 0.7638888955116272, | |
| "eval_rewards/chosen": -0.803017795085907, | |
| "eval_rewards/margins": 1.2443830966949463, | |
| "eval_rewards/rejected": -2.04740047454834, | |
| "eval_runtime": 407.9979, | |
| "eval_samples_per_second": 4.902, | |
| "eval_steps_per_second": 0.154, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.4566538637954554e-07, | |
| "logits/chosen": -2.456105947494507, | |
| "logits/rejected": -2.391247272491455, | |
| "logps/chosen": -317.70330810546875, | |
| "logps/rejected": -292.7303771972656, | |
| "loss": 0.2867, | |
| "rewards/accuracies": 0.856249988079071, | |
| "rewards/chosen": -0.4770506024360657, | |
| "rewards/margins": 1.7201404571533203, | |
| "rewards/rejected": -2.1971912384033203, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.404072133027306e-07, | |
| "logits/chosen": -2.468541383743286, | |
| "logits/rejected": -2.4047131538391113, | |
| "logps/chosen": -324.1610107421875, | |
| "logps/rejected": -310.6138610839844, | |
| "loss": 0.3011, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -0.3531934320926666, | |
| "rewards/margins": 1.7022035121917725, | |
| "rewards/rejected": -2.055396795272827, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.3520838665324703e-07, | |
| "logits/chosen": -2.451047658920288, | |
| "logits/rejected": -2.426084280014038, | |
| "logps/chosen": -289.8973083496094, | |
| "logps/rejected": -315.23968505859375, | |
| "loss": 0.2848, | |
| "rewards/accuracies": 0.9125000238418579, | |
| "rewards/chosen": -0.3617556095123291, | |
| "rewards/margins": 1.7169090509414673, | |
| "rewards/rejected": -2.078664779663086, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.3007172168743852e-07, | |
| "logits/chosen": -2.4811718463897705, | |
| "logits/rejected": -2.442286968231201, | |
| "logps/chosen": -315.90509033203125, | |
| "logps/rejected": -345.96820068359375, | |
| "loss": 0.2943, | |
| "rewards/accuracies": 0.875, | |
| "rewards/chosen": -0.2960956394672394, | |
| "rewards/margins": 1.6934324502944946, | |
| "rewards/rejected": -1.9895280599594116, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.2500000000000005e-07, | |
| "logits/chosen": -2.4405837059020996, | |
| "logits/rejected": -2.38596773147583, | |
| "logps/chosen": -287.0311279296875, | |
| "logps/rejected": -303.80535888671875, | |
| "loss": 0.2866, | |
| "rewards/accuracies": 0.893750011920929, | |
| "rewards/chosen": -0.2767558693885803, | |
| "rewards/margins": 1.9063446521759033, | |
| "rewards/rejected": -2.183100461959839, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1.1999596801769616e-07, | |
| "logits/chosen": -2.440513849258423, | |
| "logits/rejected": -2.3295609951019287, | |
| "logps/chosen": -326.0518493652344, | |
| "logps/rejected": -333.1617431640625, | |
| "loss": 0.2744, | |
| "rewards/accuracies": 0.918749988079071, | |
| "rewards/chosen": -0.25197187066078186, | |
| "rewards/margins": 2.045137882232666, | |
| "rewards/rejected": -2.297109603881836, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.1506233551212185e-07, | |
| "logits/chosen": -2.414334535598755, | |
| "logits/rejected": -2.3740944862365723, | |
| "logps/chosen": -306.10992431640625, | |
| "logps/rejected": -327.01959228515625, | |
| "loss": 0.2711, | |
| "rewards/accuracies": 0.90625, | |
| "rewards/chosen": -0.261447936296463, | |
| "rewards/margins": 2.056182384490967, | |
| "rewards/rejected": -2.3176300525665283, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.1020177413231332e-07, | |
| "logits/chosen": -2.424375057220459, | |
| "logits/rejected": -2.3422465324401855, | |
| "logps/chosen": -267.51129150390625, | |
| "logps/rejected": -272.04876708984375, | |
| "loss": 0.2992, | |
| "rewards/accuracies": 0.84375, | |
| "rewards/chosen": -0.5566546320915222, | |
| "rewards/margins": 1.5810120105743408, | |
| "rewards/rejected": -2.1376664638519287, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 1.0541691595800336e-07, | |
| "logits/chosen": -2.4174036979675293, | |
| "logits/rejected": -2.417484760284424, | |
| "logps/chosen": -288.2060852050781, | |
| "logps/rejected": -316.9212341308594, | |
| "loss": 0.2776, | |
| "rewards/accuracies": 0.918749988079071, | |
| "rewards/chosen": -0.14382892847061157, | |
| "rewards/margins": 1.983428716659546, | |
| "rewards/rejected": -2.127257823944092, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.007103520743035e-07, | |
| "logits/chosen": -2.4386072158813477, | |
| "logits/rejected": -2.383044719696045, | |
| "logps/chosen": -316.8988342285156, | |
| "logps/rejected": -311.27642822265625, | |
| "loss": 0.2725, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -0.27822011709213257, | |
| "rewards/margins": 1.802807092666626, | |
| "rewards/rejected": -2.081026792526245, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_logits/chosen": -2.3785088062286377, | |
| "eval_logits/rejected": -2.3381552696228027, | |
| "eval_logps/chosen": -307.5903015136719, | |
| "eval_logps/rejected": -309.0183410644531, | |
| "eval_loss": 0.49208447337150574, | |
| "eval_rewards/accuracies": 0.7460317611694336, | |
| "eval_rewards/chosen": -0.5635129809379578, | |
| "eval_rewards/margins": 1.3005269765853882, | |
| "eval_rewards/rejected": -1.8640400171279907, | |
| "eval_runtime": 431.8636, | |
| "eval_samples_per_second": 4.631, | |
| "eval_steps_per_second": 0.146, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.608463116858542e-08, | |
| "logits/chosen": -2.4096856117248535, | |
| "logits/rejected": -2.3269238471984863, | |
| "logps/chosen": -319.33123779296875, | |
| "logps/rejected": -314.37982177734375, | |
| "loss": 0.2832, | |
| "rewards/accuracies": 0.893750011920929, | |
| "rewards/chosen": -0.4104345738887787, | |
| "rewards/margins": 1.9642629623413086, | |
| "rewards/rejected": -2.37469744682312, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 9.15422581503224e-08, | |
| "logits/chosen": -2.4082019329071045, | |
| "logits/rejected": -2.3823094367980957, | |
| "logps/chosen": -281.8961181640625, | |
| "logps/rejected": -310.1343078613281, | |
| "loss": 0.2659, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -0.4686800539493561, | |
| "rewards/margins": 1.9623409509658813, | |
| "rewards/rejected": -2.431021213531494, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 8.70856927946362e-08, | |
| "logits/chosen": -2.4076130390167236, | |
| "logits/rejected": -2.377281427383423, | |
| "logps/chosen": -313.17877197265625, | |
| "logps/rejected": -320.7528381347656, | |
| "loss": 0.2712, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -0.3578185439109802, | |
| "rewards/margins": 1.8895679712295532, | |
| "rewards/rejected": -2.2473864555358887, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 8.271734841028552e-08, | |
| "logits/chosen": -2.4748058319091797, | |
| "logits/rejected": -2.3889963626861572, | |
| "logps/chosen": -317.75933837890625, | |
| "logps/rejected": -335.86553955078125, | |
| "loss": 0.2587, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -0.460686057806015, | |
| "rewards/margins": 1.9483623504638672, | |
| "rewards/rejected": -2.409048557281494, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 7.843959053281663e-08, | |
| "logits/chosen": -2.419320583343506, | |
| "logits/rejected": -2.3716225624084473, | |
| "logps/chosen": -308.89141845703125, | |
| "logps/rejected": -291.35797119140625, | |
| "loss": 0.3091, | |
| "rewards/accuracies": 0.90625, | |
| "rewards/chosen": -0.3241550624370575, | |
| "rewards/margins": 1.9242489337921143, | |
| "rewards/rejected": -2.248404026031494, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 7.425473564358456e-08, | |
| "logits/chosen": -2.4155445098876953, | |
| "logits/rejected": -2.374995708465576, | |
| "logps/chosen": -285.75823974609375, | |
| "logps/rejected": -320.6084899902344, | |
| "loss": 0.2787, | |
| "rewards/accuracies": 0.893750011920929, | |
| "rewards/chosen": -0.321144163608551, | |
| "rewards/margins": 2.070187568664551, | |
| "rewards/rejected": -2.391331911087036, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 7.016504991533726e-08, | |
| "logits/chosen": -2.4452130794525146, | |
| "logits/rejected": -2.416900157928467, | |
| "logps/chosen": -333.56890869140625, | |
| "logps/rejected": -288.9085998535156, | |
| "loss": 0.2819, | |
| "rewards/accuracies": 0.893750011920929, | |
| "rewards/chosen": -0.34982940554618835, | |
| "rewards/margins": 1.8246349096298218, | |
| "rewards/rejected": -2.174464702606201, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.617274798504286e-08, | |
| "logits/chosen": -2.4035491943359375, | |
| "logits/rejected": -2.3629653453826904, | |
| "logps/chosen": -306.9756164550781, | |
| "logps/rejected": -289.35479736328125, | |
| "loss": 0.2805, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -0.36044904589653015, | |
| "rewards/margins": 1.8948723077774048, | |
| "rewards/rejected": -2.2553212642669678, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.22799917546252e-08, | |
| "logits/chosen": -2.459360361099243, | |
| "logits/rejected": -2.391692638397217, | |
| "logps/chosen": -314.09185791015625, | |
| "logps/rejected": -300.3113098144531, | |
| "loss": 0.2546, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -0.302379310131073, | |
| "rewards/margins": 2.0588433742523193, | |
| "rewards/rejected": -2.361222743988037, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 5.848888922025552e-08, | |
| "logits/chosen": -2.473045825958252, | |
| "logits/rejected": -2.456024408340454, | |
| "logps/chosen": -312.7765808105469, | |
| "logps/rejected": -322.79498291015625, | |
| "loss": 0.2932, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -0.290397971868515, | |
| "rewards/margins": 1.813227653503418, | |
| "rewards/rejected": -2.103625774383545, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_logits/chosen": -2.391538381576538, | |
| "eval_logits/rejected": -2.351095199584961, | |
| "eval_logps/chosen": -309.3631591796875, | |
| "eval_logps/rejected": -311.79766845703125, | |
| "eval_loss": 0.49240604043006897, | |
| "eval_rewards/accuracies": 0.7579365372657776, | |
| "eval_rewards/chosen": -0.6521540880203247, | |
| "eval_rewards/margins": 1.3508530855178833, | |
| "eval_rewards/rejected": -2.003007173538208, | |
| "eval_runtime": 414.0649, | |
| "eval_samples_per_second": 4.83, | |
| "eval_steps_per_second": 0.152, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 5.48014933308352e-08, | |
| "logits/chosen": -2.407109022140503, | |
| "logits/rejected": -2.3259758949279785, | |
| "logps/chosen": -230.8815155029297, | |
| "logps/rejected": -267.571044921875, | |
| "loss": 0.3043, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -0.5537179112434387, | |
| "rewards/margins": 1.7985881567001343, | |
| "rewards/rejected": -2.3523058891296387, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 5.121980087628802e-08, | |
| "logits/chosen": -2.468632221221924, | |
| "logits/rejected": -2.407593250274658, | |
| "logps/chosen": -321.1299133300781, | |
| "logps/rejected": -319.76788330078125, | |
| "loss": 0.2968, | |
| "rewards/accuracies": 0.893750011920929, | |
| "rewards/chosen": -0.3099203407764435, | |
| "rewards/margins": 2.04097580909729, | |
| "rewards/rejected": -2.350896120071411, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.774575140626316e-08, | |
| "logits/chosen": -2.399498462677002, | |
| "logits/rejected": -2.317718982696533, | |
| "logps/chosen": -311.56378173828125, | |
| "logps/rejected": -322.6271057128906, | |
| "loss": 0.2885, | |
| "rewards/accuracies": 0.893750011920929, | |
| "rewards/chosen": -0.34509938955307007, | |
| "rewards/margins": 1.8977705240249634, | |
| "rewards/rejected": -2.2428698539733887, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.438122617983442e-08, | |
| "logits/chosen": -2.3652095794677734, | |
| "logits/rejected": -2.3344194889068604, | |
| "logps/chosen": -290.28790283203125, | |
| "logps/rejected": -294.1825866699219, | |
| "loss": 0.2989, | |
| "rewards/accuracies": 0.875, | |
| "rewards/chosen": -0.4549785256385803, | |
| "rewards/margins": 1.7224676609039307, | |
| "rewards/rejected": -2.177445888519287, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 4.112804714676593e-08, | |
| "logits/chosen": -2.459439754486084, | |
| "logits/rejected": -2.4127402305603027, | |
| "logps/chosen": -292.1894226074219, | |
| "logps/rejected": -307.1498107910156, | |
| "loss": 0.2864, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -0.346891850233078, | |
| "rewards/margins": 1.9702911376953125, | |
| "rewards/rejected": -2.317183017730713, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.798797596089351e-08, | |
| "logits/chosen": -2.427961587905884, | |
| "logits/rejected": -2.4093945026397705, | |
| "logps/chosen": -316.4217224121094, | |
| "logps/rejected": -341.4559631347656, | |
| "loss": 0.2918, | |
| "rewards/accuracies": 0.90625, | |
| "rewards/chosen": -0.42415857315063477, | |
| "rewards/margins": 1.8887336254119873, | |
| "rewards/rejected": -2.312892198562622, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.496271302615869e-08, | |
| "logits/chosen": -2.4277498722076416, | |
| "logits/rejected": -2.35754656791687, | |
| "logps/chosen": -290.10235595703125, | |
| "logps/rejected": -304.0705261230469, | |
| "loss": 0.2807, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -0.38870421051979065, | |
| "rewards/margins": 2.0075557231903076, | |
| "rewards/rejected": -2.3962597846984863, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.205389657580943e-08, | |
| "logits/chosen": -2.438321590423584, | |
| "logits/rejected": -2.3755178451538086, | |
| "logps/chosen": -283.269775390625, | |
| "logps/rejected": -337.3073425292969, | |
| "loss": 0.2519, | |
| "rewards/accuracies": 0.90625, | |
| "rewards/chosen": -0.2695261836051941, | |
| "rewards/margins": 2.0451509952545166, | |
| "rewards/rejected": -2.3146772384643555, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.9263101785268252e-08, | |
| "logits/chosen": -2.4288270473480225, | |
| "logits/rejected": -2.39312481880188, | |
| "logps/chosen": -325.607421875, | |
| "logps/rejected": -317.9021911621094, | |
| "loss": 0.2867, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -0.3596641421318054, | |
| "rewards/margins": 1.9093034267425537, | |
| "rewards/rejected": -2.268967390060425, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.659183991914696e-08, | |
| "logits/chosen": -2.419738531112671, | |
| "logits/rejected": -2.362929105758667, | |
| "logps/chosen": -296.9184875488281, | |
| "logps/rejected": -324.33587646484375, | |
| "loss": 0.275, | |
| "rewards/accuracies": 0.918749988079071, | |
| "rewards/chosen": -0.3492244482040405, | |
| "rewards/margins": 2.0286529064178467, | |
| "rewards/rejected": -2.3778772354125977, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_logits/chosen": -2.39336895942688, | |
| "eval_logits/rejected": -2.353144407272339, | |
| "eval_logps/chosen": -309.0525817871094, | |
| "eval_logps/rejected": -311.2369079589844, | |
| "eval_loss": 0.4915713965892792, | |
| "eval_rewards/accuracies": 0.7599206566810608, | |
| "eval_rewards/chosen": -0.6366247534751892, | |
| "eval_rewards/margins": 1.3383426666259766, | |
| "eval_rewards/rejected": -1.9749674797058105, | |
| "eval_runtime": 412.9249, | |
| "eval_samples_per_second": 4.843, | |
| "eval_steps_per_second": 0.153, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.4041557512869876e-08, | |
| "logits/chosen": -2.3756937980651855, | |
| "logits/rejected": -2.3104584217071533, | |
| "logps/chosen": -307.74395751953125, | |
| "logps/rejected": -316.4643859863281, | |
| "loss": 0.301, | |
| "rewards/accuracies": 0.856249988079071, | |
| "rewards/chosen": -0.6529245972633362, | |
| "rewards/margins": 1.7977030277252197, | |
| "rewards/rejected": -2.4506278038024902, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1613635589349756e-08, | |
| "logits/chosen": -2.4178683757781982, | |
| "logits/rejected": -2.3683836460113525, | |
| "logps/chosen": -293.5295715332031, | |
| "logps/rejected": -329.43756103515625, | |
| "loss": 0.2802, | |
| "rewards/accuracies": 0.918749988079071, | |
| "rewards/chosen": -0.4704504907131195, | |
| "rewards/margins": 1.998552680015564, | |
| "rewards/rejected": -2.469003200531006, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.9309388911139424e-08, | |
| "logits/chosen": -2.4530060291290283, | |
| "logits/rejected": -2.417515993118286, | |
| "logps/chosen": -303.9961853027344, | |
| "logps/rejected": -316.8196716308594, | |
| "loss": 0.2883, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -0.4491092562675476, | |
| "rewards/margins": 1.8476078510284424, | |
| "rewards/rejected": -2.2967171669006348, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.713006526846439e-08, | |
| "logits/chosen": -2.3352913856506348, | |
| "logits/rejected": -2.3332459926605225, | |
| "logps/chosen": -309.6740417480469, | |
| "logps/rejected": -316.5276184082031, | |
| "loss": 0.3034, | |
| "rewards/accuracies": 0.831250011920929, | |
| "rewards/chosen": -0.5785962343215942, | |
| "rewards/margins": 1.668442964553833, | |
| "rewards/rejected": -2.247039318084717, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.507684480352292e-08, | |
| "logits/chosen": -2.444365978240967, | |
| "logits/rejected": -2.3748979568481445, | |
| "logps/chosen": -273.01177978515625, | |
| "logps/rejected": -300.568115234375, | |
| "loss": 0.2704, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -0.5734509229660034, | |
| "rewards/margins": 1.8402652740478516, | |
| "rewards/rejected": -2.4137163162231445, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.3150839371417699e-08, | |
| "logits/chosen": -2.3913302421569824, | |
| "logits/rejected": -2.3794515132904053, | |
| "logps/chosen": -270.5587463378906, | |
| "logps/rejected": -277.6205749511719, | |
| "loss": 0.3003, | |
| "rewards/accuracies": 0.893750011920929, | |
| "rewards/chosen": -0.3957940936088562, | |
| "rewards/margins": 1.739976167678833, | |
| "rewards/rejected": -2.135770320892334, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.1353091938067023e-08, | |
| "logits/chosen": -2.40122652053833, | |
| "logits/rejected": -2.317656993865967, | |
| "logps/chosen": -306.97454833984375, | |
| "logps/rejected": -288.46038818359375, | |
| "loss": 0.2884, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -0.4694311022758484, | |
| "rewards/margins": 1.7464059591293335, | |
| "rewards/rejected": -2.215837240219116, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.684576015420275e-09, | |
| "logits/chosen": -2.429955005645752, | |
| "logits/rejected": -2.340874433517456, | |
| "logps/chosen": -284.2897033691406, | |
| "logps/rejected": -346.4473571777344, | |
| "loss": 0.259, | |
| "rewards/accuracies": 0.9312499761581421, | |
| "rewards/chosen": -0.4956478178501129, | |
| "rewards/margins": 2.128859043121338, | |
| "rewards/rejected": -2.624507188796997, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.14619513428405e-09, | |
| "logits/chosen": -2.41424822807312, | |
| "logits/rejected": -2.4188144207000732, | |
| "logps/chosen": -284.09356689453125, | |
| "logps/rejected": -301.265380859375, | |
| "loss": 0.3023, | |
| "rewards/accuracies": 0.8687499761581421, | |
| "rewards/chosen": -0.6043499708175659, | |
| "rewards/margins": 1.725403070449829, | |
| "rewards/rejected": -2.3297529220581055, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 6.738782355044048e-09, | |
| "logits/chosen": -2.420943260192871, | |
| "logits/rejected": -2.3737356662750244, | |
| "logps/chosen": -295.2271423339844, | |
| "logps/rejected": -300.8685607910156, | |
| "loss": 0.2768, | |
| "rewards/accuracies": 0.9125000238418579, | |
| "rewards/chosen": -0.4684749245643616, | |
| "rewards/margins": 2.138996124267578, | |
| "rewards/rejected": -2.607471227645874, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_logits/chosen": -2.3908376693725586, | |
| "eval_logits/rejected": -2.3505396842956543, | |
| "eval_logps/chosen": -310.34185791015625, | |
| "eval_logps/rejected": -312.6646423339844, | |
| "eval_loss": 0.49215617775917053, | |
| "eval_rewards/accuracies": 0.7579365372657776, | |
| "eval_rewards/chosen": -0.7010902166366577, | |
| "eval_rewards/margins": 1.345264196395874, | |
| "eval_rewards/rejected": -2.0463547706604004, | |
| "eval_runtime": 434.5194, | |
| "eval_samples_per_second": 4.603, | |
| "eval_steps_per_second": 0.145, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.463099816548577e-09, | |
| "logits/chosen": -2.435065269470215, | |
| "logits/rejected": -2.368187427520752, | |
| "logps/chosen": -305.482666015625, | |
| "logps/rejected": -319.5362548828125, | |
| "loss": 0.2907, | |
| "rewards/accuracies": 0.8999999761581421, | |
| "rewards/chosen": -0.512501060962677, | |
| "rewards/margins": 1.8626611232757568, | |
| "rewards/rejected": -2.375162124633789, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.319838323396691e-09, | |
| "logits/chosen": -2.425668239593506, | |
| "logits/rejected": -2.394260883331299, | |
| "logps/chosen": -285.38983154296875, | |
| "logps/rejected": -326.1392822265625, | |
| "loss": 0.28, | |
| "rewards/accuracies": 0.9312499761581421, | |
| "rewards/chosen": -0.43002137541770935, | |
| "rewards/margins": 1.9287302494049072, | |
| "rewards/rejected": -2.3587517738342285, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.309616971855195e-09, | |
| "logits/chosen": -2.3961329460144043, | |
| "logits/rejected": -2.3518338203430176, | |
| "logps/chosen": -313.55267333984375, | |
| "logps/rejected": -286.34320068359375, | |
| "loss": 0.2816, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -0.41422533988952637, | |
| "rewards/margins": 1.944323182106018, | |
| "rewards/rejected": -2.358548402786255, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.4329828146074096e-09, | |
| "logits/chosen": -2.386317491531372, | |
| "logits/rejected": -2.3524794578552246, | |
| "logps/chosen": -313.0305480957031, | |
| "logps/rejected": -332.1868896484375, | |
| "loss": 0.2798, | |
| "rewards/accuracies": 0.8999999761581421, | |
| "rewards/chosen": -0.3209957182407379, | |
| "rewards/margins": 2.147188663482666, | |
| "rewards/rejected": -2.46818470954895, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.690410564514244e-09, | |
| "logits/chosen": -2.411320209503174, | |
| "logits/rejected": -2.3845181465148926, | |
| "logps/chosen": -296.78228759765625, | |
| "logps/rejected": -306.8433837890625, | |
| "loss": 0.2898, | |
| "rewards/accuracies": 0.893750011920929, | |
| "rewards/chosen": -0.4139639735221863, | |
| "rewards/margins": 1.8331149816513062, | |
| "rewards/rejected": -2.2470791339874268, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.0823023375489126e-09, | |
| "logits/chosen": -2.468296766281128, | |
| "logits/rejected": -2.4058051109313965, | |
| "logps/chosen": -282.4747619628906, | |
| "logps/rejected": -294.89923095703125, | |
| "loss": 0.2817, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -0.3540436029434204, | |
| "rewards/margins": 1.8670495748519897, | |
| "rewards/rejected": -2.22109317779541, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 6.089874350439505e-10, | |
| "logits/chosen": -2.4278903007507324, | |
| "logits/rejected": -2.412611961364746, | |
| "logps/chosen": -309.91180419921875, | |
| "logps/rejected": -351.41607666015625, | |
| "loss": 0.2826, | |
| "rewards/accuracies": 0.8812500238418579, | |
| "rewards/chosen": -0.38388413190841675, | |
| "rewards/margins": 1.9360164403915405, | |
| "rewards/rejected": -2.3199005126953125, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.707221653688585e-10, | |
| "logits/chosen": -2.3936755657196045, | |
| "logits/rejected": -2.3537259101867676, | |
| "logps/chosen": -316.6966247558594, | |
| "logps/rejected": -323.77154541015625, | |
| "loss": 0.2674, | |
| "rewards/accuracies": 0.918749988079071, | |
| "rewards/chosen": -0.3255850076675415, | |
| "rewards/margins": 2.003681182861328, | |
| "rewards/rejected": -2.329266309738159, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.768970513457151e-11, | |
| "logits/chosen": -2.3720383644104004, | |
| "logits/rejected": -2.346740245819092, | |
| "logps/chosen": -301.3364562988281, | |
| "logps/rejected": -312.578125, | |
| "loss": 0.2749, | |
| "rewards/accuracies": 0.8687499761581421, | |
| "rewards/chosen": -0.46938952803611755, | |
| "rewards/margins": 1.996596097946167, | |
| "rewards/rejected": -2.4659857749938965, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0, | |
| "logits/chosen": -2.345372200012207, | |
| "logits/rejected": -2.3051817417144775, | |
| "logps/chosen": -275.92779541015625, | |
| "logps/rejected": -335.74761962890625, | |
| "loss": 0.2863, | |
| "rewards/accuracies": 0.856249988079071, | |
| "rewards/chosen": -0.5277979969978333, | |
| "rewards/margins": 2.0437979698181152, | |
| "rewards/rejected": -2.5715959072113037, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_logits/chosen": -2.3900513648986816, | |
| "eval_logits/rejected": -2.3497886657714844, | |
| "eval_logps/chosen": -310.23736572265625, | |
| "eval_logps/rejected": -312.59942626953125, | |
| "eval_loss": 0.4916023015975952, | |
| "eval_rewards/accuracies": 0.7579365372657776, | |
| "eval_rewards/chosen": -0.6958636045455933, | |
| "eval_rewards/margins": 1.3472286462783813, | |
| "eval_rewards/rejected": -2.0430922508239746, | |
| "eval_runtime": 454.0528, | |
| "eval_samples_per_second": 4.405, | |
| "eval_steps_per_second": 0.139, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "step": 1500, | |
| "total_flos": 0.0, | |
| "train_loss": 0.4390208276112874, | |
| "train_runtime": 42485.337, | |
| "train_samples_per_second": 2.26, | |
| "train_steps_per_second": 0.035 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |