| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 1563, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.1847133757961784e-09, | |
| "logits/generated": -2.9043595790863037, | |
| "logits/real": -3.0318443775177, | |
| "logps/generated": -95.60806274414062, | |
| "logps/real": -162.11865234375, | |
| "loss": 0.6931, | |
| "rewards/accuracies": 0.0, | |
| "rewards/generated": 0.0, | |
| "rewards/margins": 0.0, | |
| "rewards/real": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.184713375796178e-08, | |
| "logits/generated": -2.9496052265167236, | |
| "logits/real": -2.9726288318634033, | |
| "logps/generated": -115.16079711914062, | |
| "logps/real": -126.27457427978516, | |
| "loss": 0.6927, | |
| "rewards/accuracies": 0.4305555522441864, | |
| "rewards/generated": -0.0005613141693174839, | |
| "rewards/margins": 0.0011329095577821136, | |
| "rewards/real": 0.0005715956795029342, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.369426751592356e-08, | |
| "logits/generated": -2.925844192504883, | |
| "logits/real": -3.0148582458496094, | |
| "logps/generated": -126.58709716796875, | |
| "logps/real": -159.16970825195312, | |
| "loss": 0.6895, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/generated": 0.0016155906487256289, | |
| "rewards/margins": 0.008952249772846699, | |
| "rewards/real": 0.010567841120064259, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.554140127388536e-08, | |
| "logits/generated": -2.950205087661743, | |
| "logits/real": -2.9246954917907715, | |
| "logps/generated": -130.9630126953125, | |
| "logps/real": -128.04364013671875, | |
| "loss": 0.6701, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/generated": -0.04806157201528549, | |
| "rewards/margins": 0.03640877455472946, | |
| "rewards/real": -0.01165279932320118, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.2738853503184713e-07, | |
| "logits/generated": -2.9109079837799072, | |
| "logits/real": -2.967057704925537, | |
| "logps/generated": -126.64833068847656, | |
| "logps/real": -141.5502166748047, | |
| "loss": 0.6662, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/generated": -0.1246229037642479, | |
| "rewards/margins": 0.0738920345902443, | |
| "rewards/real": -0.0507308654487133, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.592356687898089e-07, | |
| "logits/generated": -2.944676160812378, | |
| "logits/real": -2.973489284515381, | |
| "logps/generated": -133.49766540527344, | |
| "logps/real": -141.7188262939453, | |
| "loss": 0.6462, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/generated": -0.1534460484981537, | |
| "rewards/margins": 0.09793341904878616, | |
| "rewards/real": -0.05551263689994812, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9108280254777072e-07, | |
| "logits/generated": -2.92313814163208, | |
| "logits/real": -2.9491844177246094, | |
| "logps/generated": -123.59134674072266, | |
| "logps/real": -135.57339477539062, | |
| "loss": 0.6571, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/generated": -0.2681542634963989, | |
| "rewards/margins": 0.09540877491235733, | |
| "rewards/real": -0.172745481133461, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.2292993630573247e-07, | |
| "logits/generated": -2.9296579360961914, | |
| "logits/real": -2.9948348999023438, | |
| "logps/generated": -124.77592468261719, | |
| "logps/real": -141.3092041015625, | |
| "loss": 0.6272, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -0.36597520112991333, | |
| "rewards/margins": 0.23450367152690887, | |
| "rewards/real": -0.13147154450416565, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.5477707006369425e-07, | |
| "logits/generated": -2.9382827281951904, | |
| "logits/real": -2.950681209564209, | |
| "logps/generated": -126.6854476928711, | |
| "logps/real": -116.08744049072266, | |
| "loss": 0.6279, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/generated": -0.6447240114212036, | |
| "rewards/margins": 0.15082275867462158, | |
| "rewards/real": -0.49390116333961487, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.86624203821656e-07, | |
| "logits/generated": -2.9626991748809814, | |
| "logits/real": -2.985078811645508, | |
| "logps/generated": -151.97203063964844, | |
| "logps/real": -147.793212890625, | |
| "loss": 0.5941, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -0.64665687084198, | |
| "rewards/margins": 0.40791407227516174, | |
| "rewards/real": -0.23874275386333466, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.184713375796178e-07, | |
| "logits/generated": -2.9504504203796387, | |
| "logits/real": -3.009941577911377, | |
| "logps/generated": -127.89019775390625, | |
| "logps/real": -142.78115844726562, | |
| "loss": 0.6035, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/generated": -0.4942631125450134, | |
| "rewards/margins": 0.39962121844291687, | |
| "rewards/real": -0.09464187920093536, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_logits/generated": -2.9112277030944824, | |
| "eval_logits/real": -2.963428497314453, | |
| "eval_logps/generated": -120.85581970214844, | |
| "eval_logps/real": -134.36163330078125, | |
| "eval_loss": 0.592494010925293, | |
| "eval_rewards/accuracies": 0.6871019005775452, | |
| "eval_rewards/generated": -0.46135851740837097, | |
| "eval_rewards/margins": 0.483438104391098, | |
| "eval_rewards/real": 0.022079583257436752, | |
| "eval_runtime": 320.9946, | |
| "eval_samples_per_second": 15.577, | |
| "eval_steps_per_second": 0.489, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.5031847133757957e-07, | |
| "logits/generated": -2.94885516166687, | |
| "logits/real": -2.9667720794677734, | |
| "logps/generated": -132.24411010742188, | |
| "logps/real": -138.70401000976562, | |
| "loss": 0.5939, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -0.4684581756591797, | |
| "rewards/margins": 0.5189403891563416, | |
| "rewards/real": 0.050482142716646194, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3.8216560509554143e-07, | |
| "logits/generated": -2.914760112762451, | |
| "logits/real": -2.9669089317321777, | |
| "logps/generated": -131.27503967285156, | |
| "logps/real": -147.97238159179688, | |
| "loss": 0.602, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -0.41060376167297363, | |
| "rewards/margins": 0.492185115814209, | |
| "rewards/real": 0.08158136159181595, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.140127388535032e-07, | |
| "logits/generated": -2.9110288619995117, | |
| "logits/real": -2.9508092403411865, | |
| "logps/generated": -129.82977294921875, | |
| "logps/real": -144.04708862304688, | |
| "loss": 0.655, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/generated": -0.6899576187133789, | |
| "rewards/margins": 0.29959696531295776, | |
| "rewards/real": -0.3903607130050659, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.4585987261146494e-07, | |
| "logits/generated": -2.8934552669525146, | |
| "logits/real": -2.918970823287964, | |
| "logps/generated": -116.09012603759766, | |
| "logps/real": -121.42826080322266, | |
| "loss": 0.6225, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/generated": -0.5983424186706543, | |
| "rewards/margins": 0.2791465222835541, | |
| "rewards/real": -0.31919583678245544, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.777070063694267e-07, | |
| "logits/generated": -2.8588805198669434, | |
| "logits/real": -2.905513048171997, | |
| "logps/generated": -123.76139068603516, | |
| "logps/real": -135.1915283203125, | |
| "loss": 0.6297, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -0.826836884021759, | |
| "rewards/margins": 0.6088964343070984, | |
| "rewards/real": -0.21794041991233826, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.989331436699858e-07, | |
| "logits/generated": -2.8500113487243652, | |
| "logits/real": -2.9133572578430176, | |
| "logps/generated": -138.90496826171875, | |
| "logps/real": -147.51112365722656, | |
| "loss": 0.5997, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -0.5559502840042114, | |
| "rewards/margins": 0.44744768738746643, | |
| "rewards/real": -0.10850252956151962, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.953769559032717e-07, | |
| "logits/generated": -2.7749171257019043, | |
| "logits/real": -2.8795857429504395, | |
| "logps/generated": -112.4853515625, | |
| "logps/real": -137.61013793945312, | |
| "loss": 0.5703, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -1.144225835800171, | |
| "rewards/margins": 0.8240048289299011, | |
| "rewards/real": -0.32022103667259216, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.918207681365576e-07, | |
| "logits/generated": -2.8241965770721436, | |
| "logits/real": -2.899482250213623, | |
| "logps/generated": -123.1147232055664, | |
| "logps/real": -140.4021759033203, | |
| "loss": 0.6273, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -0.580504298210144, | |
| "rewards/margins": 0.6617487668991089, | |
| "rewards/real": 0.08124445378780365, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.882645803698435e-07, | |
| "logits/generated": -2.8152451515197754, | |
| "logits/real": -2.8969357013702393, | |
| "logps/generated": -118.85482025146484, | |
| "logps/real": -131.64207458496094, | |
| "loss": 0.626, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -0.8428341150283813, | |
| "rewards/margins": 0.712174654006958, | |
| "rewards/real": -0.13065943121910095, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.847083926031294e-07, | |
| "logits/generated": -2.8368003368377686, | |
| "logits/real": -2.8934528827667236, | |
| "logps/generated": -124.17633056640625, | |
| "logps/real": -133.32460021972656, | |
| "loss": 0.6154, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -1.0640162229537964, | |
| "rewards/margins": 0.585637629032135, | |
| "rewards/real": -0.47837844491004944, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_logits/generated": -2.846381902694702, | |
| "eval_logits/real": -2.8926753997802734, | |
| "eval_logps/generated": -124.88420867919922, | |
| "eval_logps/real": -137.59585571289062, | |
| "eval_loss": 0.5945761799812317, | |
| "eval_rewards/accuracies": 0.6886942386627197, | |
| "eval_rewards/generated": -0.8641979694366455, | |
| "eval_rewards/margins": 0.5628555417060852, | |
| "eval_rewards/real": -0.3013423681259155, | |
| "eval_runtime": 314.2657, | |
| "eval_samples_per_second": 15.91, | |
| "eval_steps_per_second": 0.5, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.811522048364154e-07, | |
| "logits/generated": -2.8265631198883057, | |
| "logits/real": -2.872185468673706, | |
| "logps/generated": -116.153564453125, | |
| "logps/real": -129.70101928710938, | |
| "loss": 0.6439, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -0.9046352505683899, | |
| "rewards/margins": 0.5383676290512085, | |
| "rewards/real": -0.3662675619125366, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.775960170697012e-07, | |
| "logits/generated": -2.8761754035949707, | |
| "logits/real": -2.8833699226379395, | |
| "logps/generated": -143.34608459472656, | |
| "logps/real": -140.4290771484375, | |
| "loss": 0.7048, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/generated": -0.5727646350860596, | |
| "rewards/margins": 0.421123743057251, | |
| "rewards/real": -0.1516408622264862, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.7403982930298717e-07, | |
| "logits/generated": -2.8488383293151855, | |
| "logits/real": -2.86686372756958, | |
| "logps/generated": -124.8054428100586, | |
| "logps/real": -137.43142700195312, | |
| "loss": 0.6624, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -0.386758029460907, | |
| "rewards/margins": 0.39915674924850464, | |
| "rewards/real": 0.012398702092468739, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.7048364153627306e-07, | |
| "logits/generated": -2.8755905628204346, | |
| "logits/real": -2.850111722946167, | |
| "logps/generated": -144.16363525390625, | |
| "logps/real": -137.38861083984375, | |
| "loss": 0.6973, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -0.42233890295028687, | |
| "rewards/margins": 0.6668346524238586, | |
| "rewards/real": 0.2444957047700882, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.66927453769559e-07, | |
| "logits/generated": -2.8914976119995117, | |
| "logits/real": -2.909574508666992, | |
| "logps/generated": -134.83218383789062, | |
| "logps/real": -144.05287170410156, | |
| "loss": 0.6039, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -0.9402686953544617, | |
| "rewards/margins": 0.6465772390365601, | |
| "rewards/real": -0.2936915159225464, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.633712660028449e-07, | |
| "logits/generated": -2.8130080699920654, | |
| "logits/real": -2.9388322830200195, | |
| "logps/generated": -131.2688751220703, | |
| "logps/real": -148.659423828125, | |
| "loss": 0.6259, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -0.9782902598381042, | |
| "rewards/margins": 0.6731352806091309, | |
| "rewards/real": -0.30515503883361816, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.5981507823613085e-07, | |
| "logits/generated": -2.8650355339050293, | |
| "logits/real": -2.8830349445343018, | |
| "logps/generated": -133.54998779296875, | |
| "logps/real": -143.64295959472656, | |
| "loss": 0.6478, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.038545846939087, | |
| "rewards/margins": 0.5988888144493103, | |
| "rewards/real": -0.43965697288513184, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.562588904694168e-07, | |
| "logits/generated": -2.8448922634124756, | |
| "logits/real": -2.893357515335083, | |
| "logps/generated": -126.46229553222656, | |
| "logps/real": -135.95480346679688, | |
| "loss": 0.6228, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.1257703304290771, | |
| "rewards/margins": 0.6330925822257996, | |
| "rewards/real": -0.4926776885986328, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.5270270270270264e-07, | |
| "logits/generated": -2.8617606163024902, | |
| "logits/real": -2.907224416732788, | |
| "logps/generated": -127.72086334228516, | |
| "logps/real": -138.37338256835938, | |
| "loss": 0.6585, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -0.6692047119140625, | |
| "rewards/margins": 0.41642865538597107, | |
| "rewards/real": -0.2527760863304138, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.491465149359886e-07, | |
| "logits/generated": -2.8157684803009033, | |
| "logits/real": -2.9448578357696533, | |
| "logps/generated": -115.7210464477539, | |
| "logps/real": -135.6936798095703, | |
| "loss": 0.7218, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -0.04884980991482735, | |
| "rewards/margins": 0.3899938464164734, | |
| "rewards/real": 0.34114405512809753, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_logits/generated": -2.8557660579681396, | |
| "eval_logits/real": -2.938932180404663, | |
| "eval_logps/generated": -117.34172058105469, | |
| "eval_logps/real": -130.4615478515625, | |
| "eval_loss": 0.6092967987060547, | |
| "eval_rewards/accuracies": 0.6791401505470276, | |
| "eval_rewards/generated": -0.10995037853717804, | |
| "eval_rewards/margins": 0.5220382809638977, | |
| "eval_rewards/real": 0.41208788752555847, | |
| "eval_runtime": 313.617, | |
| "eval_samples_per_second": 15.943, | |
| "eval_steps_per_second": 0.501, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.4559032716927454e-07, | |
| "logits/generated": -2.820242404937744, | |
| "logits/real": -2.932029962539673, | |
| "logps/generated": -110.3979721069336, | |
| "logps/real": -128.57955932617188, | |
| "loss": 0.7051, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/generated": -0.46763068437576294, | |
| "rewards/margins": 0.7681630849838257, | |
| "rewards/real": 0.3005323112010956, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.420341394025605e-07, | |
| "logits/generated": -2.867724895477295, | |
| "logits/real": -2.9374239444732666, | |
| "logps/generated": -121.03181457519531, | |
| "logps/real": -131.03138732910156, | |
| "loss": 0.613, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -0.9018260836601257, | |
| "rewards/margins": 0.7947210073471069, | |
| "rewards/real": -0.10710500180721283, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.384779516358463e-07, | |
| "logits/generated": -2.9186887741088867, | |
| "logits/real": -2.9603030681610107, | |
| "logps/generated": -136.2305145263672, | |
| "logps/real": -141.52938842773438, | |
| "loss": 0.7222, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.0479620695114136, | |
| "rewards/margins": 0.24121908843517303, | |
| "rewards/real": -0.8067429661750793, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.3492176386913227e-07, | |
| "logits/generated": -2.884328603744507, | |
| "logits/real": -2.9852678775787354, | |
| "logps/generated": -134.2027130126953, | |
| "logps/real": -157.81533813476562, | |
| "loss": 0.6392, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.0355875492095947, | |
| "rewards/margins": 0.5947176218032837, | |
| "rewards/real": -0.44086989760398865, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.313655761024182e-07, | |
| "logits/generated": -2.9303040504455566, | |
| "logits/real": -2.9080405235290527, | |
| "logps/generated": -133.62733459472656, | |
| "logps/real": -135.67965698242188, | |
| "loss": 0.7259, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -0.7619242072105408, | |
| "rewards/margins": 0.7297625541687012, | |
| "rewards/real": -0.03216175362467766, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.278093883357041e-07, | |
| "logits/generated": -2.907813549041748, | |
| "logits/real": -2.8927502632141113, | |
| "logps/generated": -135.63803100585938, | |
| "logps/real": -127.85164642333984, | |
| "loss": 0.6128, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -0.8036858439445496, | |
| "rewards/margins": 0.7827543020248413, | |
| "rewards/real": -0.020931486040353775, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.2425320056899e-07, | |
| "logits/generated": -2.8933119773864746, | |
| "logits/real": -2.90037202835083, | |
| "logps/generated": -123.38737487792969, | |
| "logps/real": -129.03187561035156, | |
| "loss": 0.6147, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -0.838703453540802, | |
| "rewards/margins": 0.6072388291358948, | |
| "rewards/real": -0.2314646691083908, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.2069701280227595e-07, | |
| "logits/generated": -2.8591134548187256, | |
| "logits/real": -2.924983263015747, | |
| "logps/generated": -133.0351104736328, | |
| "logps/real": -132.64010620117188, | |
| "loss": 0.6723, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/generated": -0.3996178209781647, | |
| "rewards/margins": 0.408294141292572, | |
| "rewards/real": 0.008676335215568542, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.1714082503556185e-07, | |
| "logits/generated": -2.829285144805908, | |
| "logits/real": -2.9132728576660156, | |
| "logps/generated": -115.08140563964844, | |
| "logps/real": -116.62813568115234, | |
| "loss": 0.6199, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -0.39587754011154175, | |
| "rewards/margins": 0.7312180995941162, | |
| "rewards/real": 0.33534055948257446, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.135846372688478e-07, | |
| "logits/generated": -2.896308422088623, | |
| "logits/real": -2.9679720401763916, | |
| "logps/generated": -134.25875854492188, | |
| "logps/real": -145.1576385498047, | |
| "loss": 0.6415, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -0.8689187169075012, | |
| "rewards/margins": 0.8677636981010437, | |
| "rewards/real": -0.0011550008784979582, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_logits/generated": -2.863023519515991, | |
| "eval_logits/real": -2.934311866760254, | |
| "eval_logps/generated": -123.05078125, | |
| "eval_logps/real": -134.793212890625, | |
| "eval_loss": 0.6002771258354187, | |
| "eval_rewards/accuracies": 0.6942675113677979, | |
| "eval_rewards/generated": -0.6808551549911499, | |
| "eval_rewards/margins": 0.6597769260406494, | |
| "eval_rewards/real": -0.0210782028734684, | |
| "eval_runtime": 312.5846, | |
| "eval_samples_per_second": 15.996, | |
| "eval_steps_per_second": 0.502, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.100284495021337e-07, | |
| "logits/generated": -2.9025797843933105, | |
| "logits/real": -2.8970775604248047, | |
| "logps/generated": -138.23733520507812, | |
| "logps/real": -131.90760803222656, | |
| "loss": 0.6279, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -0.9198619723320007, | |
| "rewards/margins": 0.8169810175895691, | |
| "rewards/real": -0.10288095474243164, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.064722617354196e-07, | |
| "logits/generated": -2.9897818565368652, | |
| "logits/real": -2.8572428226470947, | |
| "logps/generated": -155.53582763671875, | |
| "logps/real": -140.32861328125, | |
| "loss": 0.7277, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/generated": -0.9986831545829773, | |
| "rewards/margins": 0.6315004825592041, | |
| "rewards/real": -0.3671826422214508, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.0291607396870553e-07, | |
| "logits/generated": -2.8571627140045166, | |
| "logits/real": -2.9783432483673096, | |
| "logps/generated": -129.95596313476562, | |
| "logps/real": -152.39735412597656, | |
| "loss": 0.7234, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/generated": -0.7651321887969971, | |
| "rewards/margins": 0.3509063124656677, | |
| "rewards/real": -0.41422587633132935, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.993598862019915e-07, | |
| "logits/generated": -2.90661883354187, | |
| "logits/real": -2.907402515411377, | |
| "logps/generated": -126.6184310913086, | |
| "logps/real": -135.4339599609375, | |
| "loss": 0.5952, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/generated": -0.9488459825515747, | |
| "rewards/margins": 0.9613292813301086, | |
| "rewards/real": 0.012483302503824234, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.9580369843527737e-07, | |
| "logits/generated": -2.8979873657226562, | |
| "logits/real": -2.978975296020508, | |
| "logps/generated": -144.71261596679688, | |
| "logps/real": -157.7671661376953, | |
| "loss": 0.6472, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -0.828133225440979, | |
| "rewards/margins": 0.6528965830802917, | |
| "rewards/real": -0.17523646354675293, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.9224751066856327e-07, | |
| "logits/generated": -2.9304752349853516, | |
| "logits/real": -2.9112486839294434, | |
| "logps/generated": -150.48779296875, | |
| "logps/real": -142.08993530273438, | |
| "loss": 0.617, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.05068039894104, | |
| "rewards/margins": 0.7404968738555908, | |
| "rewards/real": -0.31018346548080444, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.886913229018492e-07, | |
| "logits/generated": -2.833413600921631, | |
| "logits/real": -2.927903652191162, | |
| "logps/generated": -137.7316436767578, | |
| "logps/real": -149.27978515625, | |
| "loss": 0.7084, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/generated": -1.6642704010009766, | |
| "rewards/margins": 0.5741457939147949, | |
| "rewards/real": -1.090124487876892, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.851351351351351e-07, | |
| "logits/generated": -2.876814126968384, | |
| "logits/real": -2.9213833808898926, | |
| "logps/generated": -137.88467407226562, | |
| "logps/real": -141.27908325195312, | |
| "loss": 0.6283, | |
| "rewards/accuracies": 0.75, | |
| "rewards/generated": -1.994659423828125, | |
| "rewards/margins": 0.8866125345230103, | |
| "rewards/real": -1.1080471277236938, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.8157894736842105e-07, | |
| "logits/generated": -2.867941379547119, | |
| "logits/real": -2.907710075378418, | |
| "logps/generated": -148.14093017578125, | |
| "logps/real": -143.94232177734375, | |
| "loss": 0.6579, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.7410551309585571, | |
| "rewards/margins": 1.0998215675354004, | |
| "rewards/real": -0.6412338018417358, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.7802275960170695e-07, | |
| "logits/generated": -2.893672466278076, | |
| "logits/real": -2.9028027057647705, | |
| "logps/generated": -145.03538513183594, | |
| "logps/real": -139.4706268310547, | |
| "loss": 0.6876, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -1.2101993560791016, | |
| "rewards/margins": 0.6310919523239136, | |
| "rewards/real": -0.5791072249412537, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_logits/generated": -2.836423873901367, | |
| "eval_logits/real": -2.910181999206543, | |
| "eval_logps/generated": -130.0467987060547, | |
| "eval_logps/real": -141.91192626953125, | |
| "eval_loss": 0.6061537861824036, | |
| "eval_rewards/accuracies": 0.6727706789970398, | |
| "eval_rewards/generated": -1.3804560899734497, | |
| "eval_rewards/margins": 0.6475077271461487, | |
| "eval_rewards/real": -0.7329482436180115, | |
| "eval_runtime": 312.1361, | |
| "eval_samples_per_second": 16.019, | |
| "eval_steps_per_second": 0.503, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.7446657183499284e-07, | |
| "logits/generated": -2.8054213523864746, | |
| "logits/real": -2.8959434032440186, | |
| "logps/generated": -137.50283813476562, | |
| "logps/real": -146.76283264160156, | |
| "loss": 0.6911, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/generated": -1.2926948070526123, | |
| "rewards/margins": 0.6764450669288635, | |
| "rewards/real": -0.6162497997283936, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.709103840682788e-07, | |
| "logits/generated": -2.8815009593963623, | |
| "logits/real": -2.8959944248199463, | |
| "logps/generated": -139.5189666748047, | |
| "logps/real": -146.14120483398438, | |
| "loss": 0.6903, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.8085136413574219, | |
| "rewards/margins": 0.8203228712081909, | |
| "rewards/real": -0.988190770149231, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.6735419630156474e-07, | |
| "logits/generated": -2.8573758602142334, | |
| "logits/real": -2.890807628631592, | |
| "logps/generated": -132.2734375, | |
| "logps/real": -136.5230255126953, | |
| "loss": 0.5943, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.7565529346466064, | |
| "rewards/margins": 0.6700723767280579, | |
| "rewards/real": -1.0864803791046143, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.637980085348506e-07, | |
| "logits/generated": -2.7691547870635986, | |
| "logits/real": -2.9011363983154297, | |
| "logps/generated": -123.21565246582031, | |
| "logps/real": -140.19796752929688, | |
| "loss": 0.6908, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.4617164134979248, | |
| "rewards/margins": 0.5445016026496887, | |
| "rewards/real": -0.9172147512435913, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.602418207681365e-07, | |
| "logits/generated": -2.863327980041504, | |
| "logits/real": -2.8315365314483643, | |
| "logps/generated": -139.07894897460938, | |
| "logps/real": -139.32464599609375, | |
| "loss": 0.7007, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/generated": -1.1674206256866455, | |
| "rewards/margins": 0.35725370049476624, | |
| "rewards/real": -0.8101669549942017, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.5668563300142247e-07, | |
| "logits/generated": -2.84228777885437, | |
| "logits/real": -2.9253830909729004, | |
| "logps/generated": -138.79415893554688, | |
| "logps/real": -131.2203826904297, | |
| "loss": 0.6865, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.115051507949829, | |
| "rewards/margins": 1.0375287532806396, | |
| "rewards/real": -0.07752259820699692, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.5312944523470837e-07, | |
| "logits/generated": -2.8042409420013428, | |
| "logits/real": -2.951826810836792, | |
| "logps/generated": -134.45884704589844, | |
| "logps/real": -145.27365112304688, | |
| "loss": 0.6188, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.4238983392715454, | |
| "rewards/margins": 0.7379240393638611, | |
| "rewards/real": -0.6859742999076843, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.495732574679943e-07, | |
| "logits/generated": -2.7836008071899414, | |
| "logits/real": -2.9870457649230957, | |
| "logps/generated": -135.55392456054688, | |
| "logps/real": -158.0802459716797, | |
| "loss": 0.6584, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/generated": -1.674433946609497, | |
| "rewards/margins": 0.6915053129196167, | |
| "rewards/real": -0.982928454875946, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.460170697012802e-07, | |
| "logits/generated": -2.854656219482422, | |
| "logits/real": -2.8894591331481934, | |
| "logps/generated": -128.78138732910156, | |
| "logps/real": -123.89408874511719, | |
| "loss": 0.6294, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.5515716075897217, | |
| "rewards/margins": 0.5374225378036499, | |
| "rewards/real": -1.0141491889953613, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.424608819345661e-07, | |
| "logits/generated": -2.8014330863952637, | |
| "logits/real": -2.9254088401794434, | |
| "logps/generated": -132.14515686035156, | |
| "logps/real": -152.46603393554688, | |
| "loss": 0.5849, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/generated": -2.0465548038482666, | |
| "rewards/margins": 1.0699055194854736, | |
| "rewards/real": -0.976649284362793, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_logits/generated": -2.8346359729766846, | |
| "eval_logits/real": -2.925360918045044, | |
| "eval_logps/generated": -134.65505981445312, | |
| "eval_logps/real": -144.80482482910156, | |
| "eval_loss": 0.6078768372535706, | |
| "eval_rewards/accuracies": 0.6831210255622864, | |
| "eval_rewards/generated": -1.8412829637527466, | |
| "eval_rewards/margins": 0.8190432786941528, | |
| "eval_rewards/real": -1.0222396850585938, | |
| "eval_runtime": 309.6541, | |
| "eval_samples_per_second": 16.147, | |
| "eval_steps_per_second": 0.507, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.3890469416785205e-07, | |
| "logits/generated": -2.8233141899108887, | |
| "logits/real": -2.9481401443481445, | |
| "logps/generated": -137.22264099121094, | |
| "logps/real": -152.15045166015625, | |
| "loss": 0.6745, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -1.7551801204681396, | |
| "rewards/margins": 0.62352454662323, | |
| "rewards/real": -1.1316556930541992, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.35348506401138e-07, | |
| "logits/generated": -2.8389840126037598, | |
| "logits/real": -2.824481725692749, | |
| "logps/generated": -123.14152526855469, | |
| "logps/real": -124.35445404052734, | |
| "loss": 0.6733, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/generated": -1.4588735103607178, | |
| "rewards/margins": 0.8291076421737671, | |
| "rewards/real": -0.6297658681869507, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.3179231863442384e-07, | |
| "logits/generated": -2.910172700881958, | |
| "logits/real": -2.9429709911346436, | |
| "logps/generated": -144.48809814453125, | |
| "logps/real": -145.07113647460938, | |
| "loss": 0.6497, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.015930414199829, | |
| "rewards/margins": 1.0248924493789673, | |
| "rewards/real": 0.008962005376815796, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.282361308677098e-07, | |
| "logits/generated": -2.8567841053009033, | |
| "logits/real": -2.9329147338867188, | |
| "logps/generated": -131.82077026367188, | |
| "logps/real": -135.8273162841797, | |
| "loss": 0.5926, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/generated": -1.1058717966079712, | |
| "rewards/margins": 0.9077954292297363, | |
| "rewards/real": -0.1980762630701065, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.2467994310099573e-07, | |
| "logits/generated": -2.872140407562256, | |
| "logits/real": -2.9000673294067383, | |
| "logps/generated": -135.03431701660156, | |
| "logps/real": -147.93064880371094, | |
| "loss": 0.6806, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -1.2050108909606934, | |
| "rewards/margins": 0.7183829545974731, | |
| "rewards/real": -0.4866279065608978, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.211237553342817e-07, | |
| "logits/generated": -2.859281063079834, | |
| "logits/real": -2.9440739154815674, | |
| "logps/generated": -125.93595123291016, | |
| "logps/real": -129.65621948242188, | |
| "loss": 0.6927, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/generated": -0.940774142742157, | |
| "rewards/margins": 0.5372705459594727, | |
| "rewards/real": -0.4035035967826843, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.175675675675675e-07, | |
| "logits/generated": -2.888960123062134, | |
| "logits/real": -2.9022905826568604, | |
| "logps/generated": -134.37814331054688, | |
| "logps/real": -136.43983459472656, | |
| "loss": 0.5954, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -1.0395607948303223, | |
| "rewards/margins": 0.8729231953620911, | |
| "rewards/real": -0.1666376292705536, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.1401137980085347e-07, | |
| "logits/generated": -2.8475449085235596, | |
| "logits/real": -2.931452512741089, | |
| "logps/generated": -123.19482421875, | |
| "logps/real": -129.654052734375, | |
| "loss": 0.6247, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -0.7638888955116272, | |
| "rewards/margins": 0.6824823021888733, | |
| "rewards/real": -0.08140657842159271, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.104551920341394e-07, | |
| "logits/generated": -2.7857539653778076, | |
| "logits/real": -2.9635262489318848, | |
| "logps/generated": -121.25040435791016, | |
| "logps/real": -137.65020751953125, | |
| "loss": 0.7093, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -0.8186511993408203, | |
| "rewards/margins": 0.8126083612442017, | |
| "rewards/real": -0.006042912602424622, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.068990042674253e-07, | |
| "logits/generated": -2.8002536296844482, | |
| "logits/real": -2.9356870651245117, | |
| "logps/generated": -126.85771179199219, | |
| "logps/real": -136.75582885742188, | |
| "loss": 0.5948, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -1.1403062343597412, | |
| "rewards/margins": 0.7472094893455505, | |
| "rewards/real": -0.3930967450141907, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_logits/generated": -2.840470314025879, | |
| "eval_logits/real": -2.9281880855560303, | |
| "eval_logps/generated": -127.03143310546875, | |
| "eval_logps/real": -138.53179931640625, | |
| "eval_loss": 0.6026215553283691, | |
| "eval_rewards/accuracies": 0.6815286874771118, | |
| "eval_rewards/generated": -1.0789220333099365, | |
| "eval_rewards/margins": 0.6839848756790161, | |
| "eval_rewards/real": -0.3949371576309204, | |
| "eval_runtime": 310.5622, | |
| "eval_samples_per_second": 16.1, | |
| "eval_steps_per_second": 0.506, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.033428165007112e-07, | |
| "logits/generated": -2.837271213531494, | |
| "logits/real": -2.9325520992279053, | |
| "logps/generated": -140.0005645751953, | |
| "logps/real": -148.47731018066406, | |
| "loss": 0.6166, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.002680778503418, | |
| "rewards/margins": 0.6050243377685547, | |
| "rewards/real": -0.39765650033950806, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.9978662873399715e-07, | |
| "logits/generated": -2.873455047607422, | |
| "logits/real": -2.873136520385742, | |
| "logps/generated": -129.134521484375, | |
| "logps/real": -130.46888732910156, | |
| "loss": 0.6923, | |
| "rewards/accuracies": 0.75, | |
| "rewards/generated": -1.0006587505340576, | |
| "rewards/margins": 0.7794184684753418, | |
| "rewards/real": -0.22124037146568298, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.9623044096728305e-07, | |
| "logits/generated": -2.8776352405548096, | |
| "logits/real": -2.9416308403015137, | |
| "logps/generated": -126.6672592163086, | |
| "logps/real": -134.09780883789062, | |
| "loss": 0.6886, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -0.7552564740180969, | |
| "rewards/margins": 0.2777866721153259, | |
| "rewards/real": -0.47746968269348145, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.92674253200569e-07, | |
| "logits/generated": -2.9088470935821533, | |
| "logits/real": -2.9304256439208984, | |
| "logps/generated": -137.3657989501953, | |
| "logps/real": -139.28189086914062, | |
| "loss": 0.5841, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.2612388134002686, | |
| "rewards/margins": 1.034172773361206, | |
| "rewards/real": -0.22706612944602966, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.8911806543385494e-07, | |
| "logits/generated": -2.801848888397217, | |
| "logits/real": -2.9571499824523926, | |
| "logps/generated": -125.8072509765625, | |
| "logps/real": -146.98782348632812, | |
| "loss": 0.6015, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -1.6273508071899414, | |
| "rewards/margins": 0.8402755856513977, | |
| "rewards/real": -0.7870752811431885, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.855618776671408e-07, | |
| "logits/generated": -2.848889112472534, | |
| "logits/real": -2.877046585083008, | |
| "logps/generated": -124.48414611816406, | |
| "logps/real": -129.13226318359375, | |
| "loss": 0.6204, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -1.2502113580703735, | |
| "rewards/margins": 0.6051310896873474, | |
| "rewards/real": -0.6450802087783813, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.8200568990042673e-07, | |
| "logits/generated": -2.8570446968078613, | |
| "logits/real": -2.9029502868652344, | |
| "logps/generated": -133.1268768310547, | |
| "logps/real": -136.430419921875, | |
| "loss": 0.6282, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.4829145669937134, | |
| "rewards/margins": 0.9649866223335266, | |
| "rewards/real": -0.5179279446601868, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.784495021337127e-07, | |
| "logits/generated": -2.8677666187286377, | |
| "logits/real": -2.9021925926208496, | |
| "logps/generated": -146.73191833496094, | |
| "logps/real": -141.13995361328125, | |
| "loss": 0.6747, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -2.041520595550537, | |
| "rewards/margins": 1.0659831762313843, | |
| "rewards/real": -0.9755374789237976, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.7489331436699857e-07, | |
| "logits/generated": -2.824852228164673, | |
| "logits/real": -2.926391124725342, | |
| "logps/generated": -147.2328643798828, | |
| "logps/real": -149.10507202148438, | |
| "loss": 0.7098, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/generated": -1.700987458229065, | |
| "rewards/margins": 0.7294310331344604, | |
| "rewards/real": -0.9715563654899597, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.7133712660028446e-07, | |
| "logits/generated": -2.7972347736358643, | |
| "logits/real": -2.9038093090057373, | |
| "logps/generated": -125.4245834350586, | |
| "logps/real": -133.38829040527344, | |
| "loss": 0.6723, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/generated": -1.891131043434143, | |
| "rewards/margins": 0.7512563467025757, | |
| "rewards/real": -1.1398746967315674, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_logits/generated": -2.8397910594940186, | |
| "eval_logits/real": -2.9189207553863525, | |
| "eval_logps/generated": -133.5920867919922, | |
| "eval_logps/real": -144.62881469726562, | |
| "eval_loss": 0.6016955971717834, | |
| "eval_rewards/accuracies": 0.6791401505470276, | |
| "eval_rewards/generated": -1.7349849939346313, | |
| "eval_rewards/margins": 0.7303467988967896, | |
| "eval_rewards/real": -1.0046383142471313, | |
| "eval_runtime": 309.8404, | |
| "eval_samples_per_second": 16.137, | |
| "eval_steps_per_second": 0.507, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.677809388335704e-07, | |
| "logits/generated": -2.8365445137023926, | |
| "logits/real": -2.9331562519073486, | |
| "logps/generated": -140.5518035888672, | |
| "logps/real": -158.63702392578125, | |
| "loss": 0.6647, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/generated": -1.3855249881744385, | |
| "rewards/margins": 0.2608424127101898, | |
| "rewards/real": -1.1246826648712158, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.642247510668563e-07, | |
| "logits/generated": -2.8873796463012695, | |
| "logits/real": -2.878711223602295, | |
| "logps/generated": -145.9031982421875, | |
| "logps/real": -143.15829467773438, | |
| "loss": 0.6455, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -2.0597965717315674, | |
| "rewards/margins": 1.2405303716659546, | |
| "rewards/real": -0.8192662000656128, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.6066856330014225e-07, | |
| "logits/generated": -2.8116676807403564, | |
| "logits/real": -2.9269957542419434, | |
| "logps/generated": -147.27291870117188, | |
| "logps/real": -154.99942016601562, | |
| "loss": 0.5998, | |
| "rewards/accuracies": 0.7875000238418579, | |
| "rewards/generated": -1.8391478061676025, | |
| "rewards/margins": 1.1881417036056519, | |
| "rewards/real": -0.6510059237480164, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.5711237553342815e-07, | |
| "logits/generated": -2.8869619369506836, | |
| "logits/real": -2.904590129852295, | |
| "logps/generated": -148.45867919921875, | |
| "logps/real": -142.796142578125, | |
| "loss": 0.721, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -0.9768039584159851, | |
| "rewards/margins": 0.4294663071632385, | |
| "rewards/real": -0.5473376512527466, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.5355618776671404e-07, | |
| "logits/generated": -2.839021682739258, | |
| "logits/real": -2.905735492706299, | |
| "logps/generated": -130.4958953857422, | |
| "logps/real": -147.63864135742188, | |
| "loss": 0.7021, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -1.1018455028533936, | |
| "rewards/margins": 0.7128327488899231, | |
| "rewards/real": -0.3890126347541809, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.5e-07, | |
| "logits/generated": -2.824007034301758, | |
| "logits/real": -2.857182741165161, | |
| "logps/generated": -146.1483154296875, | |
| "logps/real": -139.19387817382812, | |
| "loss": 0.5886, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.458707571029663, | |
| "rewards/margins": 1.0141663551330566, | |
| "rewards/real": -0.44454121589660645, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.4644381223328594e-07, | |
| "logits/generated": -2.7840158939361572, | |
| "logits/real": -2.9017128944396973, | |
| "logps/generated": -137.39535522460938, | |
| "logps/real": -148.0748291015625, | |
| "loss": 0.6859, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.5387979745864868, | |
| "rewards/margins": 0.8355327844619751, | |
| "rewards/real": -0.7032652497291565, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.4288762446657183e-07, | |
| "logits/generated": -2.7799668312072754, | |
| "logits/real": -2.915595531463623, | |
| "logps/generated": -130.84051513671875, | |
| "logps/real": -133.69252014160156, | |
| "loss": 0.6446, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -1.3767451047897339, | |
| "rewards/margins": 0.6831783652305603, | |
| "rewards/real": -0.6935667395591736, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.393314366998578e-07, | |
| "logits/generated": -2.716787576675415, | |
| "logits/real": -2.8902299404144287, | |
| "logps/generated": -122.82936096191406, | |
| "logps/real": -143.2957000732422, | |
| "loss": 0.5669, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/generated": -1.140442132949829, | |
| "rewards/margins": 1.021167516708374, | |
| "rewards/real": -0.1192745715379715, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.3577524893314365e-07, | |
| "logits/generated": -2.8401942253112793, | |
| "logits/real": -2.8803598880767822, | |
| "logps/generated": -135.40391540527344, | |
| "logps/real": -136.9019012451172, | |
| "loss": 0.6436, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.2338757514953613, | |
| "rewards/margins": 0.8897522687911987, | |
| "rewards/real": -0.3441234230995178, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_logits/generated": -2.806016445159912, | |
| "eval_logits/real": -2.88619327545166, | |
| "eval_logps/generated": -132.06158447265625, | |
| "eval_logps/real": -143.32131958007812, | |
| "eval_loss": 0.6029496192932129, | |
| "eval_rewards/accuracies": 0.668789803981781, | |
| "eval_rewards/generated": -1.5819348096847534, | |
| "eval_rewards/margins": 0.7080464959144592, | |
| "eval_rewards/real": -0.873888373374939, | |
| "eval_runtime": 310.4392, | |
| "eval_samples_per_second": 16.106, | |
| "eval_steps_per_second": 0.506, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.322190611664296e-07, | |
| "logits/generated": -2.836130142211914, | |
| "logits/real": -2.796046733856201, | |
| "logps/generated": -154.68153381347656, | |
| "logps/real": -142.09814453125, | |
| "loss": 0.6133, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/generated": -1.767498254776001, | |
| "rewards/margins": 1.2376995086669922, | |
| "rewards/real": -0.5297988653182983, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.2866287339971549e-07, | |
| "logits/generated": -2.8319737911224365, | |
| "logits/real": -2.9071972370147705, | |
| "logps/generated": -141.31478881835938, | |
| "logps/real": -146.1092987060547, | |
| "loss": 0.6595, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.810842514038086, | |
| "rewards/margins": 1.001710057258606, | |
| "rewards/real": -0.80913245677948, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.251066856330014e-07, | |
| "logits/generated": -2.82523775100708, | |
| "logits/real": -2.8914453983306885, | |
| "logps/generated": -147.71463012695312, | |
| "logps/real": -142.40274047851562, | |
| "loss": 0.6592, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -1.7439014911651611, | |
| "rewards/margins": 0.4922804832458496, | |
| "rewards/real": -1.2516210079193115, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.2155049786628733e-07, | |
| "logits/generated": -2.7898082733154297, | |
| "logits/real": -2.882514476776123, | |
| "logps/generated": -129.53775024414062, | |
| "logps/real": -147.6808624267578, | |
| "loss": 0.6296, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -1.6545770168304443, | |
| "rewards/margins": 1.0049636363983154, | |
| "rewards/real": -0.6496134996414185, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.1799431009957325e-07, | |
| "logits/generated": -2.7571780681610107, | |
| "logits/real": -2.923750877380371, | |
| "logps/generated": -140.4619598388672, | |
| "logps/real": -149.5252227783203, | |
| "loss": 0.5661, | |
| "rewards/accuracies": 0.800000011920929, | |
| "rewards/generated": -1.4804662466049194, | |
| "rewards/margins": 1.0741474628448486, | |
| "rewards/real": -0.40631866455078125, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.1443812233285914e-07, | |
| "logits/generated": -2.8211305141448975, | |
| "logits/real": -2.8674416542053223, | |
| "logps/generated": -131.8004608154297, | |
| "logps/real": -130.39474487304688, | |
| "loss": 0.6535, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.2931689023971558, | |
| "rewards/margins": 0.6902718544006348, | |
| "rewards/real": -0.602897047996521, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.108819345661451e-07, | |
| "logits/generated": -2.880394458770752, | |
| "logits/real": -2.881556272506714, | |
| "logps/generated": -138.2687225341797, | |
| "logps/real": -140.81362915039062, | |
| "loss": 0.7122, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -1.508469820022583, | |
| "rewards/margins": 0.4812171459197998, | |
| "rewards/real": -1.027252435684204, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.0732574679943098e-07, | |
| "logits/generated": -2.8477933406829834, | |
| "logits/real": -2.845597267150879, | |
| "logps/generated": -132.1406707763672, | |
| "logps/real": -134.79180908203125, | |
| "loss": 0.6927, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/generated": -1.4040391445159912, | |
| "rewards/margins": 0.5953569412231445, | |
| "rewards/real": -0.8086821436882019, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.0376955903271693e-07, | |
| "logits/generated": -2.8082008361816406, | |
| "logits/real": -2.863212823867798, | |
| "logps/generated": -125.87931823730469, | |
| "logps/real": -136.62237548828125, | |
| "loss": 0.626, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.4956855773925781, | |
| "rewards/margins": 0.9534099698066711, | |
| "rewards/real": -0.5422756671905518, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.0021337126600283e-07, | |
| "logits/generated": -2.8578667640686035, | |
| "logits/real": -2.847013235092163, | |
| "logps/generated": -136.9371337890625, | |
| "logps/real": -140.67221069335938, | |
| "loss": 0.6163, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.597415566444397, | |
| "rewards/margins": 1.0458736419677734, | |
| "rewards/real": -0.5515419244766235, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_logits/generated": -2.8002965450286865, | |
| "eval_logits/real": -2.877998113632202, | |
| "eval_logps/generated": -132.6573944091797, | |
| "eval_logps/real": -142.48568725585938, | |
| "eval_loss": 0.6010281443595886, | |
| "eval_rewards/accuracies": 0.6783439517021179, | |
| "eval_rewards/generated": -1.6415162086486816, | |
| "eval_rewards/margins": 0.8511907458305359, | |
| "eval_rewards/real": -0.7903255820274353, | |
| "eval_runtime": 309.9825, | |
| "eval_samples_per_second": 16.13, | |
| "eval_steps_per_second": 0.506, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.9665718349928875e-07, | |
| "logits/generated": -2.791100025177002, | |
| "logits/real": -2.860755205154419, | |
| "logps/generated": -132.28335571289062, | |
| "logps/real": -139.66653442382812, | |
| "loss": 0.6156, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/generated": -1.8716294765472412, | |
| "rewards/margins": 0.7458978891372681, | |
| "rewards/real": -1.1257317066192627, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.931009957325747e-07, | |
| "logits/generated": -2.827510356903076, | |
| "logits/real": -2.8029284477233887, | |
| "logps/generated": -136.11270141601562, | |
| "logps/real": -141.502685546875, | |
| "loss": 0.6067, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -1.962308645248413, | |
| "rewards/margins": 0.9203013181686401, | |
| "rewards/real": -1.0420072078704834, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.895448079658606e-07, | |
| "logits/generated": -2.835878849029541, | |
| "logits/real": -2.8575656414031982, | |
| "logps/generated": -140.47169494628906, | |
| "logps/real": -139.37342834472656, | |
| "loss": 0.6224, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.8097025156021118, | |
| "rewards/margins": 0.8532291650772095, | |
| "rewards/real": -0.9564734697341919, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.859886201991465e-07, | |
| "logits/generated": -2.856842279434204, | |
| "logits/real": -2.8842849731445312, | |
| "logps/generated": -143.2516326904297, | |
| "logps/real": -137.08316040039062, | |
| "loss": 0.6052, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/generated": -1.759925127029419, | |
| "rewards/margins": 0.6329267621040344, | |
| "rewards/real": -1.1269984245300293, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.8243243243243243e-07, | |
| "logits/generated": -2.7838127613067627, | |
| "logits/real": -2.9055399894714355, | |
| "logps/generated": -135.84683227539062, | |
| "logps/real": -142.11846923828125, | |
| "loss": 0.5939, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -1.581358551979065, | |
| "rewards/margins": 0.7179355621337891, | |
| "rewards/real": -0.8634229898452759, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.7887624466571835e-07, | |
| "logits/generated": -2.8574728965759277, | |
| "logits/real": -2.812835931777954, | |
| "logps/generated": -152.22988891601562, | |
| "logps/real": -149.8922119140625, | |
| "loss": 0.7048, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -1.644396185874939, | |
| "rewards/margins": 0.46123242378234863, | |
| "rewards/real": -1.1831638813018799, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.7532005689900424e-07, | |
| "logits/generated": -2.7940242290496826, | |
| "logits/real": -2.878798484802246, | |
| "logps/generated": -133.0207977294922, | |
| "logps/real": -146.09625244140625, | |
| "loss": 0.566, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/generated": -1.9005569219589233, | |
| "rewards/margins": 0.8525867462158203, | |
| "rewards/real": -1.0479700565338135, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.717638691322902e-07, | |
| "logits/generated": -2.803427219390869, | |
| "logits/real": -2.829939603805542, | |
| "logps/generated": -129.09408569335938, | |
| "logps/real": -127.91636657714844, | |
| "loss": 0.6161, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/generated": -1.7060725688934326, | |
| "rewards/margins": 0.62469083070755, | |
| "rewards/real": -1.081381916999817, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.6820768136557609e-07, | |
| "logits/generated": -2.8071236610412598, | |
| "logits/real": -2.9175212383270264, | |
| "logps/generated": -146.45791625976562, | |
| "logps/real": -160.84805297851562, | |
| "loss": 0.6539, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/generated": -1.475184679031372, | |
| "rewards/margins": 0.6628782153129578, | |
| "rewards/real": -0.8123064041137695, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.64651493598862e-07, | |
| "logits/generated": -2.7803986072540283, | |
| "logits/real": -2.913085460662842, | |
| "logps/generated": -143.08621215820312, | |
| "logps/real": -150.99246215820312, | |
| "loss": 0.6297, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.4718377590179443, | |
| "rewards/margins": 0.9155041575431824, | |
| "rewards/real": -0.5563336610794067, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_logits/generated": -2.7847776412963867, | |
| "eval_logits/real": -2.8600666522979736, | |
| "eval_logps/generated": -132.0778045654297, | |
| "eval_logps/real": -143.10504150390625, | |
| "eval_loss": 0.602670431137085, | |
| "eval_rewards/accuracies": 0.668789803981781, | |
| "eval_rewards/generated": -1.5835580825805664, | |
| "eval_rewards/margins": 0.7312976717948914, | |
| "eval_rewards/real": -0.852260410785675, | |
| "eval_runtime": 309.4229, | |
| "eval_samples_per_second": 16.159, | |
| "eval_steps_per_second": 0.507, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.6109530583214793e-07, | |
| "logits/generated": -2.826133966445923, | |
| "logits/real": -2.843700885772705, | |
| "logps/generated": -140.56655883789062, | |
| "logps/real": -131.9547882080078, | |
| "loss": 0.6182, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/generated": -1.5958125591278076, | |
| "rewards/margins": 0.5843857526779175, | |
| "rewards/real": -1.0114269256591797, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5753911806543385e-07, | |
| "logits/generated": -2.782074213027954, | |
| "logits/real": -2.852107286453247, | |
| "logps/generated": -132.11264038085938, | |
| "logps/real": -148.32745361328125, | |
| "loss": 0.5487, | |
| "rewards/accuracies": 0.75, | |
| "rewards/generated": -1.654834508895874, | |
| "rewards/margins": 0.9943686723709106, | |
| "rewards/real": -0.6604658365249634, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5398293029871974e-07, | |
| "logits/generated": -2.818897247314453, | |
| "logits/real": -2.832937717437744, | |
| "logps/generated": -136.17401123046875, | |
| "logps/real": -132.2439727783203, | |
| "loss": 0.6491, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -1.2890915870666504, | |
| "rewards/margins": 0.7559572458267212, | |
| "rewards/real": -0.5331342816352844, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.504267425320057e-07, | |
| "logits/generated": -2.793853521347046, | |
| "logits/real": -2.85860538482666, | |
| "logps/generated": -131.0358428955078, | |
| "logps/real": -138.73953247070312, | |
| "loss": 0.6312, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.8077558279037476, | |
| "rewards/margins": 1.0804661512374878, | |
| "rewards/real": -0.727289617061615, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.4687055476529158e-07, | |
| "logits/generated": -2.846921682357788, | |
| "logits/real": -2.8571791648864746, | |
| "logps/generated": -133.85690307617188, | |
| "logps/real": -143.62088012695312, | |
| "loss": 0.6423, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.475096344947815, | |
| "rewards/margins": 1.1357142925262451, | |
| "rewards/real": -0.33938202261924744, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.4331436699857753e-07, | |
| "logits/generated": -2.784996509552002, | |
| "logits/real": -2.9016330242156982, | |
| "logps/generated": -126.00093078613281, | |
| "logps/real": -136.3924102783203, | |
| "loss": 0.565, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/generated": -1.6021381616592407, | |
| "rewards/margins": 1.1204952001571655, | |
| "rewards/real": -0.48164302110671997, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.3975817923186345e-07, | |
| "logits/generated": -2.7846155166625977, | |
| "logits/real": -2.8495097160339355, | |
| "logps/generated": -133.8337860107422, | |
| "logps/real": -135.71499633789062, | |
| "loss": 0.6058, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/generated": -1.8828033208847046, | |
| "rewards/margins": 1.3056962490081787, | |
| "rewards/real": -0.577107310295105, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.3620199146514935e-07, | |
| "logits/generated": -2.807847499847412, | |
| "logits/real": -2.829408645629883, | |
| "logps/generated": -142.19052124023438, | |
| "logps/real": -143.4310302734375, | |
| "loss": 0.6029, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -1.7980120182037354, | |
| "rewards/margins": 0.9354388117790222, | |
| "rewards/real": -0.8625731468200684, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.326458036984353e-07, | |
| "logits/generated": -2.7362117767333984, | |
| "logits/real": -2.907681941986084, | |
| "logps/generated": -128.86277770996094, | |
| "logps/real": -142.07115173339844, | |
| "loss": 0.6165, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.450605869293213, | |
| "rewards/margins": 0.6606342792510986, | |
| "rewards/real": -0.7899715304374695, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.290896159317212e-07, | |
| "logits/generated": -2.8074393272399902, | |
| "logits/real": -2.8899171352386475, | |
| "logps/generated": -135.86477661132812, | |
| "logps/real": -140.34536743164062, | |
| "loss": 0.6468, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.600224256515503, | |
| "rewards/margins": 0.8596419095993042, | |
| "rewards/real": -0.7405821681022644, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_logits/generated": -2.786166191101074, | |
| "eval_logits/real": -2.860841989517212, | |
| "eval_logps/generated": -133.3330078125, | |
| "eval_logps/real": -143.56629943847656, | |
| "eval_loss": 0.5992889404296875, | |
| "eval_rewards/accuracies": 0.683917224407196, | |
| "eval_rewards/generated": -1.7090762853622437, | |
| "eval_rewards/margins": 0.8106896281242371, | |
| "eval_rewards/real": -0.8983866572380066, | |
| "eval_runtime": 310.5461, | |
| "eval_samples_per_second": 16.101, | |
| "eval_steps_per_second": 0.506, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.255334281650071e-07, | |
| "logits/generated": -2.8380236625671387, | |
| "logits/real": -2.8380062580108643, | |
| "logps/generated": -149.90982055664062, | |
| "logps/real": -147.6665802001953, | |
| "loss": 0.6125, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.7763712406158447, | |
| "rewards/margins": 1.0066322088241577, | |
| "rewards/real": -0.769739031791687, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.2197724039829303e-07, | |
| "logits/generated": -2.7586867809295654, | |
| "logits/real": -2.841038703918457, | |
| "logps/generated": -122.13557434082031, | |
| "logps/real": -128.7981719970703, | |
| "loss": 0.6361, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/generated": -1.813408613204956, | |
| "rewards/margins": 0.9969779253005981, | |
| "rewards/real": -0.8164307475090027, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.1842105263157894e-07, | |
| "logits/generated": -2.7697105407714844, | |
| "logits/real": -2.8138997554779053, | |
| "logps/generated": -130.04222106933594, | |
| "logps/real": -121.92604064941406, | |
| "loss": 0.6316, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.6964250802993774, | |
| "rewards/margins": 0.9563926458358765, | |
| "rewards/real": -0.740032434463501, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.1486486486486487e-07, | |
| "logits/generated": -2.753065586090088, | |
| "logits/real": -2.874058246612549, | |
| "logps/generated": -130.30264282226562, | |
| "logps/real": -153.7810821533203, | |
| "loss": 0.6369, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.8373348712921143, | |
| "rewards/margins": 1.0876656770706177, | |
| "rewards/real": -0.7496690154075623, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1130867709815078e-07, | |
| "logits/generated": -2.8708550930023193, | |
| "logits/real": -2.8094139099121094, | |
| "logps/generated": -136.15113830566406, | |
| "logps/real": -138.6972198486328, | |
| "loss": 0.6281, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.595159888267517, | |
| "rewards/margins": 0.705752968788147, | |
| "rewards/real": -0.889406681060791, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.077524893314367e-07, | |
| "logits/generated": -2.817417860031128, | |
| "logits/real": -2.835923910140991, | |
| "logps/generated": -133.7835235595703, | |
| "logps/real": -143.9755859375, | |
| "loss": 0.6229, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/generated": -1.5798323154449463, | |
| "rewards/margins": 0.8425194025039673, | |
| "rewards/real": -0.7373130321502686, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0419630156472262e-07, | |
| "logits/generated": -2.8372952938079834, | |
| "logits/real": -2.8386409282684326, | |
| "logps/generated": -135.59951782226562, | |
| "logps/real": -135.88104248046875, | |
| "loss": 0.5656, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -1.450683355331421, | |
| "rewards/margins": 1.1043708324432373, | |
| "rewards/real": -0.3463127017021179, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.0064011379800854e-07, | |
| "logits/generated": -2.791853904724121, | |
| "logits/real": -2.883375644683838, | |
| "logps/generated": -126.54823303222656, | |
| "logps/real": -142.61856079101562, | |
| "loss": 0.6473, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -1.1970711946487427, | |
| "rewards/margins": 0.7306603193283081, | |
| "rewards/real": -0.4664107859134674, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.708392603129445e-08, | |
| "logits/generated": -2.7650647163391113, | |
| "logits/real": -2.790853261947632, | |
| "logps/generated": -127.62080383300781, | |
| "logps/real": -134.742431640625, | |
| "loss": 0.6052, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -1.3538134098052979, | |
| "rewards/margins": 0.8441446423530579, | |
| "rewards/real": -0.5096686482429504, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.352773826458037e-08, | |
| "logits/generated": -2.792762279510498, | |
| "logits/real": -2.795624256134033, | |
| "logps/generated": -142.76382446289062, | |
| "logps/real": -141.875244140625, | |
| "loss": 0.5741, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.515129804611206, | |
| "rewards/margins": 0.7379931211471558, | |
| "rewards/real": -0.7771366238594055, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_logits/generated": -2.774766445159912, | |
| "eval_logits/real": -2.8526883125305176, | |
| "eval_logps/generated": -132.890625, | |
| "eval_logps/real": -143.34512329101562, | |
| "eval_loss": 0.6018590927124023, | |
| "eval_rewards/accuracies": 0.6871019005775452, | |
| "eval_rewards/generated": -1.664839267730713, | |
| "eval_rewards/margins": 0.788568913936615, | |
| "eval_rewards/real": -0.8762705326080322, | |
| "eval_runtime": 309.8754, | |
| "eval_samples_per_second": 16.136, | |
| "eval_steps_per_second": 0.507, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.997155049786629e-08, | |
| "logits/generated": -2.7696619033813477, | |
| "logits/real": -2.8957486152648926, | |
| "logps/generated": -137.81674194335938, | |
| "logps/real": -151.4634552001953, | |
| "loss": 0.6453, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/generated": -1.5495209693908691, | |
| "rewards/margins": 0.5234196782112122, | |
| "rewards/real": -1.0261012315750122, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.64153627311522e-08, | |
| "logits/generated": -2.7855117321014404, | |
| "logits/real": -2.881375551223755, | |
| "logps/generated": -146.25650024414062, | |
| "logps/real": -159.53533935546875, | |
| "loss": 0.5948, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/generated": -1.6503632068634033, | |
| "rewards/margins": 0.9353766441345215, | |
| "rewards/real": -0.7149866819381714, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.285917496443812e-08, | |
| "logits/generated": -2.839664936065674, | |
| "logits/real": -2.8154075145721436, | |
| "logps/generated": -152.0926513671875, | |
| "logps/real": -141.4612579345703, | |
| "loss": 0.6361, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.6590524911880493, | |
| "rewards/margins": 0.7780254483222961, | |
| "rewards/real": -0.881027102470398, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.930298719772404e-08, | |
| "logits/generated": -2.76212477684021, | |
| "logits/real": -2.8543272018432617, | |
| "logps/generated": -144.95997619628906, | |
| "logps/real": -153.9541778564453, | |
| "loss": 0.6119, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -1.4291819334030151, | |
| "rewards/margins": 0.6051322221755981, | |
| "rewards/real": -0.8240497708320618, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.574679943100994e-08, | |
| "logits/generated": -2.7643582820892334, | |
| "logits/real": -2.803393840789795, | |
| "logps/generated": -138.57437133789062, | |
| "logps/real": -143.98910522460938, | |
| "loss": 0.6042, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/generated": -1.851440191268921, | |
| "rewards/margins": 1.1676199436187744, | |
| "rewards/real": -0.6838203072547913, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.219061166429587e-08, | |
| "logits/generated": -2.842731475830078, | |
| "logits/real": -2.75618314743042, | |
| "logps/generated": -153.87928771972656, | |
| "logps/real": -137.30043029785156, | |
| "loss": 0.6227, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.66205632686615, | |
| "rewards/margins": 0.847110390663147, | |
| "rewards/real": -0.8149459958076477, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.863442389758179e-08, | |
| "logits/generated": -2.720419406890869, | |
| "logits/real": -2.8356549739837646, | |
| "logps/generated": -132.40487670898438, | |
| "logps/real": -142.2407684326172, | |
| "loss": 0.6505, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.8278366327285767, | |
| "rewards/margins": 1.0291211605072021, | |
| "rewards/real": -0.7987155914306641, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.507823613086771e-08, | |
| "logits/generated": -2.7388923168182373, | |
| "logits/real": -2.8658761978149414, | |
| "logps/generated": -129.93698120117188, | |
| "logps/real": -150.47926330566406, | |
| "loss": 0.6557, | |
| "rewards/accuracies": 0.625, | |
| "rewards/generated": -1.5377349853515625, | |
| "rewards/margins": 0.5789148807525635, | |
| "rewards/real": -0.9588201642036438, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.152204836415363e-08, | |
| "logits/generated": -2.7871286869049072, | |
| "logits/real": -2.8277242183685303, | |
| "logps/generated": -135.78118896484375, | |
| "logps/real": -132.1021270751953, | |
| "loss": 0.5725, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/generated": -1.9688875675201416, | |
| "rewards/margins": 0.9650619626045227, | |
| "rewards/real": -1.0038254261016846, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.796586059743954e-08, | |
| "logits/generated": -2.7154223918914795, | |
| "logits/real": -2.880283832550049, | |
| "logps/generated": -124.3189926147461, | |
| "logps/real": -141.7947998046875, | |
| "loss": 0.5778, | |
| "rewards/accuracies": 0.75, | |
| "rewards/generated": -1.4083908796310425, | |
| "rewards/margins": 0.8421765565872192, | |
| "rewards/real": -0.5662142634391785, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_logits/generated": -2.7595629692077637, | |
| "eval_logits/real": -2.8409905433654785, | |
| "eval_logps/generated": -132.63201904296875, | |
| "eval_logps/real": -143.1669158935547, | |
| "eval_loss": 0.5983285307884216, | |
| "eval_rewards/accuracies": 0.683917224407196, | |
| "eval_rewards/generated": -1.638979196548462, | |
| "eval_rewards/margins": 0.7805317044258118, | |
| "eval_rewards/real": -0.858447253704071, | |
| "eval_runtime": 311.6921, | |
| "eval_samples_per_second": 16.041, | |
| "eval_steps_per_second": 0.504, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.4409672830725456e-08, | |
| "logits/generated": -2.8682186603546143, | |
| "logits/real": -2.770561695098877, | |
| "logps/generated": -145.3868408203125, | |
| "logps/real": -134.76119995117188, | |
| "loss": 0.5696, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.4525306224822998, | |
| "rewards/margins": 0.9229253530502319, | |
| "rewards/real": -0.5296052694320679, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 5.0853485064011376e-08, | |
| "logits/generated": -2.7014617919921875, | |
| "logits/real": -2.881330966949463, | |
| "logps/generated": -130.04843139648438, | |
| "logps/real": -142.1650390625, | |
| "loss": 0.5766, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/generated": -1.7901127338409424, | |
| "rewards/margins": 1.182373285293579, | |
| "rewards/real": -0.6077393293380737, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.72972972972973e-08, | |
| "logits/generated": -2.776926040649414, | |
| "logits/real": -2.816567897796631, | |
| "logps/generated": -138.56385803222656, | |
| "logps/real": -138.20372009277344, | |
| "loss": 0.5432, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/generated": -1.6850738525390625, | |
| "rewards/margins": 1.1410996913909912, | |
| "rewards/real": -0.5439742803573608, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.374110953058322e-08, | |
| "logits/generated": -2.717988967895508, | |
| "logits/real": -2.7903523445129395, | |
| "logps/generated": -127.56498718261719, | |
| "logps/real": -131.7296600341797, | |
| "loss": 0.574, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/generated": -1.8308528661727905, | |
| "rewards/margins": 0.9762704968452454, | |
| "rewards/real": -0.8545824289321899, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.018492176386913e-08, | |
| "logits/generated": -2.794159412384033, | |
| "logits/real": -2.820596933364868, | |
| "logps/generated": -138.13177490234375, | |
| "logps/real": -137.43312072753906, | |
| "loss": 0.5975, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -2.0723748207092285, | |
| "rewards/margins": 1.080757737159729, | |
| "rewards/real": -0.9916172027587891, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.6628733997155046e-08, | |
| "logits/generated": -2.792384624481201, | |
| "logits/real": -2.7937417030334473, | |
| "logps/generated": -143.66940307617188, | |
| "logps/real": -130.21682739257812, | |
| "loss": 0.652, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.7282785177230835, | |
| "rewards/margins": 1.0712766647338867, | |
| "rewards/real": -0.6570018529891968, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.3072546230440967e-08, | |
| "logits/generated": -2.8024961948394775, | |
| "logits/real": -2.8199470043182373, | |
| "logps/generated": -140.53408813476562, | |
| "logps/real": -150.7724151611328, | |
| "loss": 0.628, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/generated": -1.6441261768341064, | |
| "rewards/margins": 0.8207837343215942, | |
| "rewards/real": -0.823342502117157, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.9516358463726884e-08, | |
| "logits/generated": -2.7492637634277344, | |
| "logits/real": -2.858729839324951, | |
| "logps/generated": -134.35336303710938, | |
| "logps/real": -142.91067504882812, | |
| "loss": 0.572, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.3461004495620728, | |
| "rewards/margins": 0.9981536865234375, | |
| "rewards/real": -0.34794679284095764, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.59601706970128e-08, | |
| "logits/generated": -2.7729005813598633, | |
| "logits/real": -2.873631715774536, | |
| "logps/generated": -150.54849243164062, | |
| "logps/real": -151.95889282226562, | |
| "loss": 0.6035, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.5365216732025146, | |
| "rewards/margins": 1.0391191244125366, | |
| "rewards/real": -0.4974023699760437, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.240398293029872e-08, | |
| "logits/generated": -2.760676622390747, | |
| "logits/real": -2.839698553085327, | |
| "logps/generated": -132.1126708984375, | |
| "logps/real": -144.00076293945312, | |
| "loss": 0.5929, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.4845622777938843, | |
| "rewards/margins": 0.9012053608894348, | |
| "rewards/real": -0.5833569765090942, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_logits/generated": -2.753782272338867, | |
| "eval_logits/real": -2.8343567848205566, | |
| "eval_logps/generated": -132.1463165283203, | |
| "eval_logps/real": -142.78977966308594, | |
| "eval_loss": 0.5982768535614014, | |
| "eval_rewards/accuracies": 0.6831210255622864, | |
| "eval_rewards/generated": -1.5904085636138916, | |
| "eval_rewards/margins": 0.7696728706359863, | |
| "eval_rewards/real": -0.82073575258255, | |
| "eval_runtime": 310.8083, | |
| "eval_samples_per_second": 16.087, | |
| "eval_steps_per_second": 0.505, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.8847795163584636e-08, | |
| "logits/generated": -2.786104679107666, | |
| "logits/real": -2.843632698059082, | |
| "logps/generated": -135.99102783203125, | |
| "logps/real": -146.1920928955078, | |
| "loss": 0.5737, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -1.6939281225204468, | |
| "rewards/margins": 0.7886837124824524, | |
| "rewards/real": -0.9052446484565735, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.5291607396870554e-08, | |
| "logits/generated": -2.7616968154907227, | |
| "logits/real": -2.8508548736572266, | |
| "logps/generated": -134.79690551757812, | |
| "logps/real": -145.90550231933594, | |
| "loss": 0.646, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/generated": -1.472129464149475, | |
| "rewards/margins": 0.7121609449386597, | |
| "rewards/real": -0.7599684000015259, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.1735419630156473e-08, | |
| "logits/generated": -2.7698681354522705, | |
| "logits/real": -2.822406768798828, | |
| "logps/generated": -137.62112426757812, | |
| "logps/real": -144.58047485351562, | |
| "loss": 0.6169, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/generated": -1.6243680715560913, | |
| "rewards/margins": 1.031085729598999, | |
| "rewards/real": -0.5932824611663818, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 8.179231863442388e-09, | |
| "logits/generated": -2.7279772758483887, | |
| "logits/real": -2.8418853282928467, | |
| "logps/generated": -128.5863800048828, | |
| "logps/real": -140.18991088867188, | |
| "loss": 0.7108, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/generated": -1.8496240377426147, | |
| "rewards/margins": 0.7590233683586121, | |
| "rewards/real": -1.090600848197937, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.623044096728307e-09, | |
| "logits/generated": -2.738799810409546, | |
| "logits/real": -2.8188023567199707, | |
| "logps/generated": -128.40736389160156, | |
| "logps/real": -141.7828826904297, | |
| "loss": 0.6033, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/generated": -1.6743981838226318, | |
| "rewards/margins": 1.010298728942871, | |
| "rewards/real": -0.6640995740890503, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.0668563300142248e-09, | |
| "logits/generated": -2.787738084793091, | |
| "logits/real": -2.819310188293457, | |
| "logps/generated": -142.7244415283203, | |
| "logps/real": -137.14144897460938, | |
| "loss": 0.6264, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/generated": -1.5642173290252686, | |
| "rewards/margins": 0.8839362859725952, | |
| "rewards/real": -0.6802809238433838, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 1563, | |
| "total_flos": 0.0, | |
| "train_loss": 0.6356648667378831, | |
| "train_runtime": 12633.5214, | |
| "train_samples_per_second": 3.958, | |
| "train_steps_per_second": 0.124 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1563, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |