{ "best_metric": null, "best_model_checkpoint": null, "epoch": 11.0, "eval_steps": 500, "global_step": 374517, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.981643022880136e-05, "loss": 6.6691, "step": 500 }, { "epoch": 0.03, "learning_rate": 4.963286045760273e-05, "loss": 6.0224, "step": 1000 }, { "epoch": 0.04, "learning_rate": 4.944929068640409e-05, "loss": 5.9452, "step": 1500 }, { "epoch": 0.06, "learning_rate": 4.926572091520545e-05, "loss": 5.8693, "step": 2000 }, { "epoch": 0.07, "learning_rate": 4.908215114400682e-05, "loss": 5.7055, "step": 2500 }, { "epoch": 0.09, "learning_rate": 4.8898581372808176e-05, "loss": 5.3394, "step": 3000 }, { "epoch": 0.1, "learning_rate": 4.871501160160954e-05, "loss": 4.8459, "step": 3500 }, { "epoch": 0.12, "learning_rate": 4.853144183041091e-05, "loss": 4.4414, "step": 4000 }, { "epoch": 0.13, "learning_rate": 4.834787205921227e-05, "loss": 4.1545, "step": 4500 }, { "epoch": 0.15, "learning_rate": 4.816430228801363e-05, "loss": 3.9574, "step": 5000 }, { "epoch": 0.16, "learning_rate": 4.798073251681499e-05, "loss": 3.8106, "step": 5500 }, { "epoch": 0.18, "learning_rate": 4.779716274561636e-05, "loss": 3.6914, "step": 6000 }, { "epoch": 0.19, "learning_rate": 4.761359297441772e-05, "loss": 3.5966, "step": 6500 }, { "epoch": 0.21, "learning_rate": 4.743002320321908e-05, "loss": 3.5248, "step": 7000 }, { "epoch": 0.22, "learning_rate": 4.724645343202044e-05, "loss": 3.4544, "step": 7500 }, { "epoch": 0.23, "learning_rate": 4.706288366082181e-05, "loss": 3.3976, "step": 8000 }, { "epoch": 0.25, "learning_rate": 4.687931388962317e-05, "loss": 3.3415, "step": 8500 }, { "epoch": 0.26, "learning_rate": 4.669574411842453e-05, "loss": 3.2958, "step": 9000 }, { "epoch": 0.28, "learning_rate": 4.65121743472259e-05, "loss": 3.2533, "step": 9500 }, { "epoch": 0.29, "learning_rate": 4.6328604576027256e-05, "loss": 3.2139, "step": 10000 }, { "epoch": 0.31, "learning_rate": 4.614503480482862e-05, "loss": 3.1807, "step": 10500 }, { "epoch": 0.32, "learning_rate": 4.596146503362999e-05, "loss": 3.1433, "step": 11000 }, { "epoch": 0.34, "learning_rate": 4.5777895262431346e-05, "loss": 3.1161, "step": 11500 }, { "epoch": 0.35, "learning_rate": 4.559432549123271e-05, "loss": 3.0855, "step": 12000 }, { "epoch": 0.37, "learning_rate": 4.541075572003407e-05, "loss": 3.0553, "step": 12500 }, { "epoch": 0.38, "learning_rate": 4.522718594883544e-05, "loss": 3.0269, "step": 13000 }, { "epoch": 0.4, "learning_rate": 4.50436161776368e-05, "loss": 3.0031, "step": 13500 }, { "epoch": 0.41, "learning_rate": 4.486004640643816e-05, "loss": 2.986, "step": 14000 }, { "epoch": 0.43, "learning_rate": 4.467647663523952e-05, "loss": 2.9609, "step": 14500 }, { "epoch": 0.44, "learning_rate": 4.4492906864040886e-05, "loss": 2.9432, "step": 15000 }, { "epoch": 0.46, "learning_rate": 4.430933709284225e-05, "loss": 2.9238, "step": 15500 }, { "epoch": 0.47, "learning_rate": 4.412576732164361e-05, "loss": 2.9081, "step": 16000 }, { "epoch": 0.48, "learning_rate": 4.394219755044498e-05, "loss": 2.8925, "step": 16500 }, { "epoch": 0.5, "learning_rate": 4.3758627779246336e-05, "loss": 2.8701, "step": 17000 }, { "epoch": 0.51, "learning_rate": 4.35750580080477e-05, "loss": 2.856, "step": 17500 }, { "epoch": 0.53, "learning_rate": 4.339148823684907e-05, "loss": 2.8412, "step": 18000 }, { "epoch": 0.54, "learning_rate": 4.3207918465650426e-05, "loss": 2.8267, "step": 18500 }, { "epoch": 0.56, "learning_rate": 4.3024348694451785e-05, "loss": 2.8136, "step": 19000 }, { "epoch": 0.57, "learning_rate": 4.284077892325315e-05, "loss": 2.8015, "step": 19500 }, { "epoch": 0.59, "learning_rate": 4.2657209152054517e-05, "loss": 2.7876, "step": 20000 }, { "epoch": 0.6, "learning_rate": 4.2473639380855875e-05, "loss": 2.7741, "step": 20500 }, { "epoch": 0.62, "learning_rate": 4.229006960965724e-05, "loss": 2.7578, "step": 21000 }, { "epoch": 0.63, "learning_rate": 4.21064998384586e-05, "loss": 2.7494, "step": 21500 }, { "epoch": 0.65, "learning_rate": 4.1922930067259966e-05, "loss": 2.7375, "step": 22000 }, { "epoch": 0.66, "learning_rate": 4.173936029606133e-05, "loss": 2.724, "step": 22500 }, { "epoch": 0.68, "learning_rate": 4.155579052486269e-05, "loss": 2.718, "step": 23000 }, { "epoch": 0.69, "learning_rate": 4.1372220753664056e-05, "loss": 2.7104, "step": 23500 }, { "epoch": 0.7, "learning_rate": 4.1188650982465415e-05, "loss": 2.6971, "step": 24000 }, { "epoch": 0.72, "learning_rate": 4.100508121126678e-05, "loss": 2.6908, "step": 24500 }, { "epoch": 0.73, "learning_rate": 4.082151144006815e-05, "loss": 2.6824, "step": 25000 }, { "epoch": 0.75, "learning_rate": 4.0637941668869506e-05, "loss": 2.6755, "step": 25500 }, { "epoch": 0.76, "learning_rate": 4.0454371897670865e-05, "loss": 2.6597, "step": 26000 }, { "epoch": 0.78, "learning_rate": 4.027080212647223e-05, "loss": 2.6489, "step": 26500 }, { "epoch": 0.79, "learning_rate": 4.0087232355273596e-05, "loss": 2.6471, "step": 27000 }, { "epoch": 0.81, "learning_rate": 3.9903662584074955e-05, "loss": 2.6413, "step": 27500 }, { "epoch": 0.82, "learning_rate": 3.972009281287632e-05, "loss": 2.6255, "step": 28000 }, { "epoch": 0.84, "learning_rate": 3.953652304167768e-05, "loss": 2.6253, "step": 28500 }, { "epoch": 0.85, "learning_rate": 3.9352953270479045e-05, "loss": 2.6137, "step": 29000 }, { "epoch": 0.87, "learning_rate": 3.916938349928041e-05, "loss": 2.6076, "step": 29500 }, { "epoch": 0.88, "learning_rate": 3.898581372808177e-05, "loss": 2.5993, "step": 30000 }, { "epoch": 0.9, "learning_rate": 3.8802243956883136e-05, "loss": 2.5967, "step": 30500 }, { "epoch": 0.91, "learning_rate": 3.8618674185684495e-05, "loss": 2.5867, "step": 31000 }, { "epoch": 0.93, "learning_rate": 3.843510441448586e-05, "loss": 2.5784, "step": 31500 }, { "epoch": 0.94, "learning_rate": 3.8251534643287226e-05, "loss": 2.5768, "step": 32000 }, { "epoch": 0.95, "learning_rate": 3.8067964872088585e-05, "loss": 2.5698, "step": 32500 }, { "epoch": 0.97, "learning_rate": 3.7884395100889944e-05, "loss": 2.5589, "step": 33000 }, { "epoch": 0.98, "learning_rate": 3.770082532969131e-05, "loss": 2.5576, "step": 33500 }, { "epoch": 1.0, "learning_rate": 3.7517255558492676e-05, "loss": 2.5536, "step": 34000 }, { "epoch": 1.01, "learning_rate": 4.4933474314917615e-05, "loss": 2.5485, "step": 34500 }, { "epoch": 1.03, "learning_rate": 4.486004640643816e-05, "loss": 2.538, "step": 35000 }, { "epoch": 1.04, "learning_rate": 4.47866184979587e-05, "loss": 2.5377, "step": 35500 }, { "epoch": 1.06, "learning_rate": 4.4713190589479254e-05, "loss": 2.5319, "step": 36000 }, { "epoch": 1.07, "learning_rate": 4.4639762680999794e-05, "loss": 2.5271, "step": 36500 }, { "epoch": 1.09, "learning_rate": 4.456633477252034e-05, "loss": 2.5166, "step": 37000 }, { "epoch": 1.1, "learning_rate": 4.4492906864040886e-05, "loss": 2.5167, "step": 37500 }, { "epoch": 1.12, "learning_rate": 4.441947895556143e-05, "loss": 2.5056, "step": 38000 }, { "epoch": 1.13, "learning_rate": 4.434605104708198e-05, "loss": 2.5006, "step": 38500 }, { "epoch": 1.15, "learning_rate": 4.427262313860252e-05, "loss": 2.4967, "step": 39000 }, { "epoch": 1.16, "learning_rate": 4.419919523012307e-05, "loss": 2.4878, "step": 39500 }, { "epoch": 1.17, "learning_rate": 4.412576732164361e-05, "loss": 2.4895, "step": 40000 }, { "epoch": 1.19, "learning_rate": 4.405233941316416e-05, "loss": 2.4795, "step": 40500 }, { "epoch": 1.2, "learning_rate": 4.39789115046847e-05, "loss": 2.4732, "step": 41000 }, { "epoch": 1.22, "learning_rate": 4.390548359620525e-05, "loss": 2.4701, "step": 41500 }, { "epoch": 1.23, "learning_rate": 4.383205568772579e-05, "loss": 2.4666, "step": 42000 }, { "epoch": 1.25, "learning_rate": 4.3758627779246336e-05, "loss": 2.46, "step": 42500 }, { "epoch": 1.26, "learning_rate": 4.368519987076688e-05, "loss": 2.4594, "step": 43000 }, { "epoch": 1.28, "learning_rate": 4.361177196228743e-05, "loss": 2.4494, "step": 43500 }, { "epoch": 1.29, "learning_rate": 4.3538344053807975e-05, "loss": 2.4459, "step": 44000 }, { "epoch": 1.31, "learning_rate": 4.3464916145328514e-05, "loss": 2.4392, "step": 44500 }, { "epoch": 1.32, "learning_rate": 4.339148823684907e-05, "loss": 2.4388, "step": 45000 }, { "epoch": 1.34, "learning_rate": 4.331806032836961e-05, "loss": 2.4341, "step": 45500 }, { "epoch": 1.35, "learning_rate": 4.324463241989015e-05, "loss": 2.4285, "step": 46000 }, { "epoch": 1.37, "learning_rate": 4.31712045114107e-05, "loss": 2.4294, "step": 46500 }, { "epoch": 1.38, "learning_rate": 4.3097776602931246e-05, "loss": 2.4258, "step": 47000 }, { "epoch": 1.4, "learning_rate": 4.3024348694451785e-05, "loss": 2.4172, "step": 47500 }, { "epoch": 1.41, "learning_rate": 4.295092078597233e-05, "loss": 2.414, "step": 48000 }, { "epoch": 1.42, "learning_rate": 4.287749287749288e-05, "loss": 2.4119, "step": 48500 }, { "epoch": 1.44, "learning_rate": 4.2804064969013424e-05, "loss": 2.4052, "step": 49000 }, { "epoch": 1.45, "learning_rate": 4.273063706053397e-05, "loss": 2.4068, "step": 49500 }, { "epoch": 1.47, "learning_rate": 4.2657209152054517e-05, "loss": 2.3989, "step": 50000 }, { "epoch": 1.48, "learning_rate": 4.258378124357506e-05, "loss": 2.395, "step": 50500 }, { "epoch": 1.5, "learning_rate": 4.25103533350956e-05, "loss": 2.3924, "step": 51000 }, { "epoch": 1.51, "learning_rate": 4.243692542661615e-05, "loss": 2.3903, "step": 51500 }, { "epoch": 1.53, "learning_rate": 4.2363497518136695e-05, "loss": 2.3871, "step": 52000 }, { "epoch": 1.54, "learning_rate": 4.229006960965724e-05, "loss": 2.3795, "step": 52500 }, { "epoch": 1.56, "learning_rate": 4.221664170117778e-05, "loss": 2.3813, "step": 53000 }, { "epoch": 1.57, "learning_rate": 4.2143213792698334e-05, "loss": 2.3751, "step": 53500 }, { "epoch": 1.59, "learning_rate": 4.206978588421887e-05, "loss": 2.3729, "step": 54000 }, { "epoch": 1.6, "learning_rate": 4.199635797573942e-05, "loss": 2.3667, "step": 54500 }, { "epoch": 1.62, "learning_rate": 4.1922930067259966e-05, "loss": 2.3627, "step": 55000 }, { "epoch": 1.63, "learning_rate": 4.184950215878051e-05, "loss": 2.3608, "step": 55500 }, { "epoch": 1.64, "learning_rate": 4.177607425030106e-05, "loss": 2.3626, "step": 56000 }, { "epoch": 1.66, "learning_rate": 4.17026463418216e-05, "loss": 2.3538, "step": 56500 }, { "epoch": 1.67, "learning_rate": 4.162921843334215e-05, "loss": 2.3539, "step": 57000 }, { "epoch": 1.69, "learning_rate": 4.155579052486269e-05, "loss": 2.3496, "step": 57500 }, { "epoch": 1.7, "learning_rate": 4.148236261638324e-05, "loss": 2.3445, "step": 58000 }, { "epoch": 1.72, "learning_rate": 4.140893470790378e-05, "loss": 2.3473, "step": 58500 }, { "epoch": 1.73, "learning_rate": 4.133550679942433e-05, "loss": 2.342, "step": 59000 }, { "epoch": 1.75, "learning_rate": 4.126207889094487e-05, "loss": 2.3426, "step": 59500 }, { "epoch": 1.76, "learning_rate": 4.1188650982465415e-05, "loss": 2.3373, "step": 60000 }, { "epoch": 1.78, "learning_rate": 4.111522307398596e-05, "loss": 2.3299, "step": 60500 }, { "epoch": 1.79, "learning_rate": 4.104179516550651e-05, "loss": 2.3306, "step": 61000 }, { "epoch": 1.81, "learning_rate": 4.0968367257027054e-05, "loss": 2.3281, "step": 61500 }, { "epoch": 1.82, "learning_rate": 4.08949393485476e-05, "loss": 2.326, "step": 62000 }, { "epoch": 1.84, "learning_rate": 4.082151144006815e-05, "loss": 2.3243, "step": 62500 }, { "epoch": 1.85, "learning_rate": 4.0748083531588686e-05, "loss": 2.3241, "step": 63000 }, { "epoch": 1.87, "learning_rate": 4.067465562310923e-05, "loss": 2.3178, "step": 63500 }, { "epoch": 1.88, "learning_rate": 4.060122771462978e-05, "loss": 2.3177, "step": 64000 }, { "epoch": 1.89, "learning_rate": 4.0527799806150325e-05, "loss": 2.3128, "step": 64500 }, { "epoch": 1.91, "learning_rate": 4.0454371897670865e-05, "loss": 2.3109, "step": 65000 }, { "epoch": 1.92, "learning_rate": 4.038094398919142e-05, "loss": 2.3021, "step": 65500 }, { "epoch": 1.94, "learning_rate": 4.030751608071196e-05, "loss": 2.305, "step": 66000 }, { "epoch": 1.95, "learning_rate": 4.0234088172232504e-05, "loss": 2.3041, "step": 66500 }, { "epoch": 1.97, "learning_rate": 4.016066026375305e-05, "loss": 2.3022, "step": 67000 }, { "epoch": 1.98, "learning_rate": 4.0087232355273596e-05, "loss": 2.3009, "step": 67500 }, { "epoch": 2.0, "learning_rate": 4.001380444679414e-05, "loss": 2.2957, "step": 68000 }, { "epoch": 2.01, "learning_rate": 3.994037653831468e-05, "loss": 2.2897, "step": 68500 }, { "epoch": 2.03, "learning_rate": 3.9866948629835235e-05, "loss": 2.2909, "step": 69000 }, { "epoch": 2.04, "learning_rate": 3.9793520721355775e-05, "loss": 2.2868, "step": 69500 }, { "epoch": 2.06, "learning_rate": 3.972009281287632e-05, "loss": 2.2869, "step": 70000 }, { "epoch": 2.07, "learning_rate": 3.964666490439686e-05, "loss": 2.2871, "step": 70500 }, { "epoch": 2.09, "learning_rate": 3.9573236995917413e-05, "loss": 2.2812, "step": 71000 }, { "epoch": 2.1, "learning_rate": 3.949980908743795e-05, "loss": 2.2839, "step": 71500 }, { "epoch": 2.11, "learning_rate": 3.94263811789585e-05, "loss": 2.278, "step": 72000 }, { "epoch": 2.13, "learning_rate": 3.9352953270479045e-05, "loss": 2.2762, "step": 72500 }, { "epoch": 2.14, "learning_rate": 3.927952536199959e-05, "loss": 2.2747, "step": 73000 }, { "epoch": 2.16, "learning_rate": 3.920609745352014e-05, "loss": 2.2709, "step": 73500 }, { "epoch": 2.17, "learning_rate": 3.913266954504068e-05, "loss": 2.2703, "step": 74000 }, { "epoch": 2.19, "learning_rate": 3.905924163656123e-05, "loss": 2.2653, "step": 74500 }, { "epoch": 2.2, "learning_rate": 3.898581372808177e-05, "loss": 2.2686, "step": 75000 }, { "epoch": 2.22, "learning_rate": 3.8912385819602316e-05, "loss": 2.2631, "step": 75500 }, { "epoch": 2.23, "learning_rate": 3.883895791112286e-05, "loss": 2.2648, "step": 76000 }, { "epoch": 2.25, "learning_rate": 3.876553000264341e-05, "loss": 2.2639, "step": 76500 }, { "epoch": 2.26, "learning_rate": 3.869210209416395e-05, "loss": 2.2578, "step": 77000 }, { "epoch": 2.28, "learning_rate": 3.8618674185684495e-05, "loss": 2.2586, "step": 77500 }, { "epoch": 2.29, "learning_rate": 3.854524627720504e-05, "loss": 2.2527, "step": 78000 }, { "epoch": 2.31, "learning_rate": 3.847181836872559e-05, "loss": 2.2518, "step": 78500 }, { "epoch": 2.32, "learning_rate": 3.8398390460246134e-05, "loss": 2.2538, "step": 79000 }, { "epoch": 2.34, "learning_rate": 3.832496255176668e-05, "loss": 2.2495, "step": 79500 }, { "epoch": 2.35, "learning_rate": 3.8251534643287226e-05, "loss": 2.2501, "step": 80000 }, { "epoch": 2.36, "learning_rate": 3.8178106734807766e-05, "loss": 2.2466, "step": 80500 }, { "epoch": 2.38, "learning_rate": 3.810467882632831e-05, "loss": 2.249, "step": 81000 }, { "epoch": 2.39, "learning_rate": 3.803125091784886e-05, "loss": 2.2462, "step": 81500 }, { "epoch": 2.41, "learning_rate": 3.7957823009369405e-05, "loss": 2.2452, "step": 82000 }, { "epoch": 2.42, "learning_rate": 3.7884395100889944e-05, "loss": 2.2402, "step": 82500 }, { "epoch": 2.44, "learning_rate": 3.78109671924105e-05, "loss": 2.2379, "step": 83000 }, { "epoch": 2.45, "learning_rate": 3.773753928393104e-05, "loss": 2.2356, "step": 83500 }, { "epoch": 2.47, "learning_rate": 3.766411137545158e-05, "loss": 2.2364, "step": 84000 }, { "epoch": 2.48, "learning_rate": 3.759068346697213e-05, "loss": 2.2305, "step": 84500 }, { "epoch": 2.5, "learning_rate": 3.7517255558492676e-05, "loss": 2.2286, "step": 85000 }, { "epoch": 2.51, "learning_rate": 3.744382765001322e-05, "loss": 2.2339, "step": 85500 }, { "epoch": 2.53, "learning_rate": 3.737039974153376e-05, "loss": 2.2304, "step": 86000 }, { "epoch": 2.54, "learning_rate": 3.7296971833054315e-05, "loss": 2.2274, "step": 86500 }, { "epoch": 2.56, "learning_rate": 3.7223543924574854e-05, "loss": 2.2248, "step": 87000 }, { "epoch": 2.57, "learning_rate": 3.71501160160954e-05, "loss": 2.2275, "step": 87500 }, { "epoch": 2.58, "learning_rate": 3.707668810761594e-05, "loss": 2.2245, "step": 88000 }, { "epoch": 2.6, "learning_rate": 3.700326019913649e-05, "loss": 2.2249, "step": 88500 }, { "epoch": 2.61, "learning_rate": 3.692983229065703e-05, "loss": 2.2238, "step": 89000 }, { "epoch": 2.63, "learning_rate": 3.685640438217758e-05, "loss": 2.2197, "step": 89500 }, { "epoch": 2.64, "learning_rate": 3.6782976473698125e-05, "loss": 2.2214, "step": 90000 }, { "epoch": 2.66, "learning_rate": 3.670954856521867e-05, "loss": 2.2199, "step": 90500 }, { "epoch": 2.67, "learning_rate": 3.663612065673922e-05, "loss": 2.2156, "step": 91000 }, { "epoch": 2.69, "learning_rate": 3.656269274825976e-05, "loss": 2.2159, "step": 91500 }, { "epoch": 2.7, "learning_rate": 3.648926483978031e-05, "loss": 2.217, "step": 92000 }, { "epoch": 2.72, "learning_rate": 3.641583693130085e-05, "loss": 2.2145, "step": 92500 }, { "epoch": 2.73, "learning_rate": 3.6342409022821396e-05, "loss": 2.2096, "step": 93000 }, { "epoch": 2.75, "learning_rate": 3.626898111434194e-05, "loss": 2.2078, "step": 93500 }, { "epoch": 2.76, "learning_rate": 3.619555320586249e-05, "loss": 2.2061, "step": 94000 }, { "epoch": 2.78, "learning_rate": 3.612212529738303e-05, "loss": 2.203, "step": 94500 }, { "epoch": 2.79, "learning_rate": 3.6048697388903574e-05, "loss": 2.2053, "step": 95000 }, { "epoch": 2.8, "learning_rate": 3.597526948042412e-05, "loss": 2.2017, "step": 95500 }, { "epoch": 2.82, "learning_rate": 3.590184157194467e-05, "loss": 2.1999, "step": 96000 }, { "epoch": 2.83, "learning_rate": 3.582841366346521e-05, "loss": 2.2005, "step": 96500 }, { "epoch": 2.85, "learning_rate": 3.575498575498576e-05, "loss": 2.1985, "step": 97000 }, { "epoch": 2.86, "learning_rate": 3.5681557846506306e-05, "loss": 2.1972, "step": 97500 }, { "epoch": 2.88, "learning_rate": 3.5608129938026845e-05, "loss": 2.1985, "step": 98000 }, { "epoch": 2.89, "learning_rate": 3.553470202954739e-05, "loss": 2.1961, "step": 98500 }, { "epoch": 2.91, "learning_rate": 3.546127412106794e-05, "loss": 2.1909, "step": 99000 }, { "epoch": 2.92, "learning_rate": 3.5387846212588484e-05, "loss": 2.1899, "step": 99500 }, { "epoch": 2.94, "learning_rate": 3.5314418304109024e-05, "loss": 2.1927, "step": 100000 }, { "epoch": 2.95, "learning_rate": 3.524099039562958e-05, "loss": 2.1916, "step": 100500 }, { "epoch": 2.97, "learning_rate": 3.5167562487150116e-05, "loss": 2.1902, "step": 101000 }, { "epoch": 2.98, "learning_rate": 3.509413457867066e-05, "loss": 2.19, "step": 101500 }, { "epoch": 3.0, "learning_rate": 3.502070667019121e-05, "loss": 2.1792, "step": 102000 }, { "epoch": 3.01, "learning_rate": 3.4947278761711755e-05, "loss": 2.1871, "step": 102500 }, { "epoch": 3.03, "learning_rate": 3.48738508532323e-05, "loss": 2.183, "step": 103000 }, { "epoch": 3.04, "learning_rate": 3.480042294475284e-05, "loss": 2.1846, "step": 103500 }, { "epoch": 3.05, "learning_rate": 3.4726995036273394e-05, "loss": 2.1777, "step": 104000 }, { "epoch": 3.07, "learning_rate": 3.4653567127793934e-05, "loss": 2.1802, "step": 104500 }, { "epoch": 3.08, "learning_rate": 3.458013921931448e-05, "loss": 2.1812, "step": 105000 }, { "epoch": 3.1, "learning_rate": 3.450671131083502e-05, "loss": 2.1771, "step": 105500 }, { "epoch": 3.11, "learning_rate": 3.443328340235557e-05, "loss": 2.1741, "step": 106000 }, { "epoch": 3.13, "learning_rate": 3.435985549387611e-05, "loss": 2.1775, "step": 106500 }, { "epoch": 3.14, "learning_rate": 3.428642758539666e-05, "loss": 2.1723, "step": 107000 }, { "epoch": 3.16, "learning_rate": 3.4212999676917205e-05, "loss": 2.1743, "step": 107500 }, { "epoch": 3.17, "learning_rate": 3.413957176843775e-05, "loss": 2.1738, "step": 108000 }, { "epoch": 3.19, "learning_rate": 3.406614385995829e-05, "loss": 2.1689, "step": 108500 }, { "epoch": 3.2, "learning_rate": 3.399271595147884e-05, "loss": 2.169, "step": 109000 }, { "epoch": 3.22, "learning_rate": 3.391928804299938e-05, "loss": 2.1672, "step": 109500 }, { "epoch": 3.23, "learning_rate": 3.384586013451993e-05, "loss": 2.1705, "step": 110000 }, { "epoch": 3.25, "learning_rate": 3.3772432226040476e-05, "loss": 2.1644, "step": 110500 }, { "epoch": 3.26, "learning_rate": 3.369900431756102e-05, "loss": 2.1651, "step": 111000 }, { "epoch": 3.27, "learning_rate": 3.362557640908157e-05, "loss": 2.165, "step": 111500 }, { "epoch": 3.29, "learning_rate": 3.355214850060211e-05, "loss": 2.1651, "step": 112000 }, { "epoch": 3.3, "learning_rate": 3.3478720592122654e-05, "loss": 2.161, "step": 112500 }, { "epoch": 3.32, "learning_rate": 3.34052926836432e-05, "loss": 2.1635, "step": 113000 }, { "epoch": 3.33, "learning_rate": 3.333186477516375e-05, "loss": 2.1632, "step": 113500 }, { "epoch": 3.35, "learning_rate": 3.3258436866684286e-05, "loss": 2.1634, "step": 114000 }, { "epoch": 3.36, "learning_rate": 3.318500895820484e-05, "loss": 2.158, "step": 114500 }, { "epoch": 3.38, "learning_rate": 3.311158104972538e-05, "loss": 2.1601, "step": 115000 }, { "epoch": 3.39, "learning_rate": 3.3038153141245925e-05, "loss": 2.1577, "step": 115500 }, { "epoch": 3.41, "learning_rate": 3.296472523276647e-05, "loss": 2.1578, "step": 116000 }, { "epoch": 3.42, "learning_rate": 3.289129732428702e-05, "loss": 2.1565, "step": 116500 }, { "epoch": 3.44, "learning_rate": 3.2817869415807564e-05, "loss": 2.1551, "step": 117000 }, { "epoch": 3.45, "learning_rate": 3.2744441507328103e-05, "loss": 2.1556, "step": 117500 }, { "epoch": 3.47, "learning_rate": 3.2671013598848657e-05, "loss": 2.1545, "step": 118000 }, { "epoch": 3.48, "learning_rate": 3.2597585690369196e-05, "loss": 2.1515, "step": 118500 }, { "epoch": 3.5, "learning_rate": 3.252415778188974e-05, "loss": 2.1498, "step": 119000 }, { "epoch": 3.51, "learning_rate": 3.245072987341028e-05, "loss": 2.1519, "step": 119500 }, { "epoch": 3.52, "learning_rate": 3.2377301964930835e-05, "loss": 2.1493, "step": 120000 }, { "epoch": 3.54, "learning_rate": 3.2303874056451374e-05, "loss": 2.149, "step": 120500 }, { "epoch": 3.55, "learning_rate": 3.223044614797192e-05, "loss": 2.1475, "step": 121000 }, { "epoch": 3.57, "learning_rate": 3.215701823949247e-05, "loss": 2.148, "step": 121500 }, { "epoch": 3.58, "learning_rate": 3.208359033101301e-05, "loss": 2.1456, "step": 122000 }, { "epoch": 3.6, "learning_rate": 3.201016242253356e-05, "loss": 2.1439, "step": 122500 }, { "epoch": 3.61, "learning_rate": 3.19367345140541e-05, "loss": 2.1442, "step": 123000 }, { "epoch": 3.63, "learning_rate": 3.186330660557465e-05, "loss": 2.1449, "step": 123500 }, { "epoch": 3.64, "learning_rate": 3.178987869709519e-05, "loss": 2.1429, "step": 124000 }, { "epoch": 3.66, "learning_rate": 3.171645078861574e-05, "loss": 2.1402, "step": 124500 }, { "epoch": 3.67, "learning_rate": 3.1643022880136284e-05, "loss": 2.1378, "step": 125000 }, { "epoch": 3.69, "learning_rate": 3.156959497165683e-05, "loss": 2.1401, "step": 125500 }, { "epoch": 3.7, "learning_rate": 3.149616706317737e-05, "loss": 2.1387, "step": 126000 }, { "epoch": 3.72, "learning_rate": 3.1422739154697916e-05, "loss": 2.1334, "step": 126500 }, { "epoch": 3.73, "learning_rate": 3.134931124621846e-05, "loss": 2.139, "step": 127000 }, { "epoch": 3.74, "learning_rate": 3.127588333773901e-05, "loss": 2.1368, "step": 127500 }, { "epoch": 3.76, "learning_rate": 3.1202455429259555e-05, "loss": 2.1346, "step": 128000 }, { "epoch": 3.77, "learning_rate": 3.11290275207801e-05, "loss": 2.135, "step": 128500 }, { "epoch": 3.79, "learning_rate": 3.105559961230065e-05, "loss": 2.1325, "step": 129000 }, { "epoch": 3.8, "learning_rate": 3.098217170382119e-05, "loss": 2.1329, "step": 129500 }, { "epoch": 3.82, "learning_rate": 3.0908743795341734e-05, "loss": 2.1353, "step": 130000 }, { "epoch": 3.83, "learning_rate": 3.083531588686228e-05, "loss": 2.127, "step": 130500 }, { "epoch": 3.85, "learning_rate": 3.0761887978382826e-05, "loss": 2.134, "step": 131000 }, { "epoch": 3.86, "learning_rate": 3.0688460069903366e-05, "loss": 2.1304, "step": 131500 }, { "epoch": 3.88, "learning_rate": 3.061503216142392e-05, "loss": 2.1294, "step": 132000 }, { "epoch": 3.89, "learning_rate": 3.054160425294446e-05, "loss": 2.1291, "step": 132500 }, { "epoch": 3.91, "learning_rate": 3.0468176344465005e-05, "loss": 2.1284, "step": 133000 }, { "epoch": 3.92, "learning_rate": 3.0394748435985548e-05, "loss": 2.128, "step": 133500 }, { "epoch": 3.94, "learning_rate": 3.0321320527506097e-05, "loss": 2.1242, "step": 134000 }, { "epoch": 3.95, "learning_rate": 3.024789261902664e-05, "loss": 2.1246, "step": 134500 }, { "epoch": 3.97, "learning_rate": 3.0174464710547183e-05, "loss": 2.1272, "step": 135000 }, { "epoch": 3.98, "learning_rate": 3.0101036802067733e-05, "loss": 2.1204, "step": 135500 }, { "epoch": 3.99, "learning_rate": 3.0027608893588276e-05, "loss": 2.1224, "step": 136000 }, { "epoch": 4.01, "learning_rate": 2.9954180985108822e-05, "loss": 2.1176, "step": 136500 }, { "epoch": 4.02, "learning_rate": 2.9880753076629365e-05, "loss": 2.1229, "step": 137000 }, { "epoch": 4.04, "learning_rate": 2.9807325168149915e-05, "loss": 2.1228, "step": 137500 }, { "epoch": 4.05, "learning_rate": 2.9733897259670457e-05, "loss": 2.1189, "step": 138000 }, { "epoch": 4.07, "learning_rate": 2.9660469351191e-05, "loss": 2.1208, "step": 138500 }, { "epoch": 4.08, "learning_rate": 2.958704144271155e-05, "loss": 2.1152, "step": 139000 }, { "epoch": 4.1, "learning_rate": 2.9513613534232093e-05, "loss": 2.1164, "step": 139500 }, { "epoch": 4.11, "learning_rate": 2.9440185625752636e-05, "loss": 2.1179, "step": 140000 }, { "epoch": 4.13, "learning_rate": 2.936675771727318e-05, "loss": 2.1168, "step": 140500 }, { "epoch": 4.14, "learning_rate": 2.929332980879373e-05, "loss": 2.1188, "step": 141000 }, { "epoch": 4.16, "learning_rate": 2.921990190031427e-05, "loss": 2.1162, "step": 141500 }, { "epoch": 4.17, "learning_rate": 2.9146473991834818e-05, "loss": 2.1141, "step": 142000 }, { "epoch": 4.19, "learning_rate": 2.9073046083355364e-05, "loss": 2.1142, "step": 142500 }, { "epoch": 4.2, "learning_rate": 2.899961817487591e-05, "loss": 2.1142, "step": 143000 }, { "epoch": 4.21, "learning_rate": 2.8926190266396453e-05, "loss": 2.1116, "step": 143500 }, { "epoch": 4.23, "learning_rate": 2.8852762357916996e-05, "loss": 2.1097, "step": 144000 }, { "epoch": 4.24, "learning_rate": 2.8779334449437546e-05, "loss": 2.1107, "step": 144500 }, { "epoch": 4.26, "learning_rate": 2.870590654095809e-05, "loss": 2.1115, "step": 145000 }, { "epoch": 4.27, "learning_rate": 2.863247863247863e-05, "loss": 2.1115, "step": 145500 }, { "epoch": 4.29, "learning_rate": 2.855905072399918e-05, "loss": 2.1084, "step": 146000 }, { "epoch": 4.3, "learning_rate": 2.8485622815519724e-05, "loss": 2.109, "step": 146500 }, { "epoch": 4.32, "learning_rate": 2.8412194907040267e-05, "loss": 2.1096, "step": 147000 }, { "epoch": 4.33, "learning_rate": 2.8338766998560813e-05, "loss": 2.1089, "step": 147500 }, { "epoch": 4.35, "learning_rate": 2.826533909008136e-05, "loss": 2.1094, "step": 148000 }, { "epoch": 4.36, "learning_rate": 2.8191911181601906e-05, "loss": 2.106, "step": 148500 }, { "epoch": 4.38, "learning_rate": 2.811848327312245e-05, "loss": 2.107, "step": 149000 }, { "epoch": 4.39, "learning_rate": 2.8045055364643e-05, "loss": 2.1048, "step": 149500 }, { "epoch": 4.41, "learning_rate": 2.797162745616354e-05, "loss": 2.1028, "step": 150000 }, { "epoch": 4.42, "learning_rate": 2.7898199547684084e-05, "loss": 2.1013, "step": 150500 }, { "epoch": 4.44, "learning_rate": 2.7824771639204627e-05, "loss": 2.1015, "step": 151000 }, { "epoch": 4.45, "learning_rate": 2.7751343730725177e-05, "loss": 2.105, "step": 151500 }, { "epoch": 4.46, "learning_rate": 2.767791582224572e-05, "loss": 2.1019, "step": 152000 }, { "epoch": 4.48, "learning_rate": 2.7604487913766263e-05, "loss": 2.102, "step": 152500 }, { "epoch": 4.49, "learning_rate": 2.7531060005286812e-05, "loss": 2.0979, "step": 153000 }, { "epoch": 4.51, "learning_rate": 2.7457632096807355e-05, "loss": 2.0946, "step": 153500 }, { "epoch": 4.52, "learning_rate": 2.73842041883279e-05, "loss": 2.0981, "step": 154000 }, { "epoch": 4.54, "learning_rate": 2.7310776279848444e-05, "loss": 2.0971, "step": 154500 }, { "epoch": 4.55, "learning_rate": 2.7237348371368994e-05, "loss": 2.0979, "step": 155000 }, { "epoch": 4.57, "learning_rate": 2.7163920462889537e-05, "loss": 2.0975, "step": 155500 }, { "epoch": 4.58, "learning_rate": 2.709049255441008e-05, "loss": 2.0993, "step": 156000 }, { "epoch": 4.6, "learning_rate": 2.701706464593063e-05, "loss": 2.0952, "step": 156500 }, { "epoch": 4.61, "learning_rate": 2.6943636737451173e-05, "loss": 2.0926, "step": 157000 }, { "epoch": 4.63, "learning_rate": 2.6870208828971715e-05, "loss": 2.095, "step": 157500 }, { "epoch": 4.64, "learning_rate": 2.679678092049226e-05, "loss": 2.0936, "step": 158000 }, { "epoch": 4.66, "learning_rate": 2.6723353012012808e-05, "loss": 2.0977, "step": 158500 }, { "epoch": 4.67, "learning_rate": 2.664992510353335e-05, "loss": 2.0946, "step": 159000 }, { "epoch": 4.68, "learning_rate": 2.6576497195053894e-05, "loss": 2.0962, "step": 159500 }, { "epoch": 4.7, "learning_rate": 2.6503069286574444e-05, "loss": 2.0941, "step": 160000 }, { "epoch": 4.71, "learning_rate": 2.6429641378094986e-05, "loss": 2.0908, "step": 160500 }, { "epoch": 4.73, "learning_rate": 2.6356213469615533e-05, "loss": 2.095, "step": 161000 }, { "epoch": 4.74, "learning_rate": 2.6282785561136076e-05, "loss": 2.091, "step": 161500 }, { "epoch": 4.76, "learning_rate": 2.6209357652656625e-05, "loss": 2.0873, "step": 162000 }, { "epoch": 4.77, "learning_rate": 2.6135929744177168e-05, "loss": 2.0896, "step": 162500 }, { "epoch": 4.79, "learning_rate": 2.606250183569771e-05, "loss": 2.0887, "step": 163000 }, { "epoch": 4.8, "learning_rate": 2.598907392721826e-05, "loss": 2.0914, "step": 163500 }, { "epoch": 4.82, "learning_rate": 2.5915646018738804e-05, "loss": 2.09, "step": 164000 }, { "epoch": 4.83, "learning_rate": 2.5842218110259347e-05, "loss": 2.0878, "step": 164500 }, { "epoch": 4.85, "learning_rate": 2.576879020177989e-05, "loss": 2.0878, "step": 165000 }, { "epoch": 4.86, "learning_rate": 2.569536229330044e-05, "loss": 2.0865, "step": 165500 }, { "epoch": 4.88, "learning_rate": 2.5621934384820982e-05, "loss": 2.088, "step": 166000 }, { "epoch": 4.89, "learning_rate": 2.554850647634153e-05, "loss": 2.0856, "step": 166500 }, { "epoch": 4.9, "learning_rate": 2.5475078567862075e-05, "loss": 2.0872, "step": 167000 }, { "epoch": 4.92, "learning_rate": 2.540165065938262e-05, "loss": 2.0864, "step": 167500 }, { "epoch": 4.93, "learning_rate": 2.5328222750903164e-05, "loss": 2.0822, "step": 168000 }, { "epoch": 4.95, "learning_rate": 2.5254794842423707e-05, "loss": 2.0795, "step": 168500 }, { "epoch": 4.96, "learning_rate": 2.5181366933944256e-05, "loss": 2.0851, "step": 169000 }, { "epoch": 4.98, "learning_rate": 2.51079390254648e-05, "loss": 2.081, "step": 169500 }, { "epoch": 4.99, "learning_rate": 2.5034511116985342e-05, "loss": 2.0813, "step": 170000 }, { "epoch": 5.01, "learning_rate": 2.496108320850589e-05, "loss": 2.0794, "step": 170500 }, { "epoch": 5.02, "learning_rate": 2.4887655300026435e-05, "loss": 2.0816, "step": 171000 }, { "epoch": 5.04, "learning_rate": 2.4814227391546978e-05, "loss": 2.0745, "step": 171500 }, { "epoch": 5.05, "learning_rate": 2.4740799483067524e-05, "loss": 2.0825, "step": 172000 }, { "epoch": 5.07, "learning_rate": 2.466737157458807e-05, "loss": 2.0782, "step": 172500 }, { "epoch": 5.08, "learning_rate": 2.4593943666108617e-05, "loss": 2.0795, "step": 173000 }, { "epoch": 5.1, "learning_rate": 2.4520515757629163e-05, "loss": 2.0787, "step": 173500 }, { "epoch": 5.11, "learning_rate": 2.4447087849149706e-05, "loss": 2.0749, "step": 174000 }, { "epoch": 5.13, "learning_rate": 2.4373659940670252e-05, "loss": 2.0762, "step": 174500 }, { "epoch": 5.14, "learning_rate": 2.4300232032190795e-05, "loss": 2.0763, "step": 175000 }, { "epoch": 5.15, "learning_rate": 2.422680412371134e-05, "loss": 2.0729, "step": 175500 }, { "epoch": 5.17, "learning_rate": 2.4153376215231888e-05, "loss": 2.0748, "step": 176000 }, { "epoch": 5.18, "learning_rate": 2.407994830675243e-05, "loss": 2.0762, "step": 176500 }, { "epoch": 5.2, "learning_rate": 2.4006520398272977e-05, "loss": 2.0761, "step": 177000 }, { "epoch": 5.21, "learning_rate": 2.393309248979352e-05, "loss": 2.0739, "step": 177500 }, { "epoch": 5.23, "learning_rate": 2.3859664581314066e-05, "loss": 2.073, "step": 178000 }, { "epoch": 5.24, "learning_rate": 2.3786236672834612e-05, "loss": 2.0691, "step": 178500 }, { "epoch": 5.26, "learning_rate": 2.371280876435516e-05, "loss": 2.0735, "step": 179000 }, { "epoch": 5.27, "learning_rate": 2.3639380855875705e-05, "loss": 2.0725, "step": 179500 }, { "epoch": 5.29, "learning_rate": 2.3565952947396248e-05, "loss": 2.0716, "step": 180000 }, { "epoch": 5.3, "learning_rate": 2.3492525038916794e-05, "loss": 2.0694, "step": 180500 }, { "epoch": 5.32, "learning_rate": 2.3419097130437337e-05, "loss": 2.0728, "step": 181000 }, { "epoch": 5.33, "learning_rate": 2.3345669221957883e-05, "loss": 2.0681, "step": 181500 }, { "epoch": 5.35, "learning_rate": 2.3272241313478426e-05, "loss": 2.0706, "step": 182000 }, { "epoch": 5.36, "learning_rate": 2.3198813404998972e-05, "loss": 2.069, "step": 182500 }, { "epoch": 5.37, "learning_rate": 2.312538549651952e-05, "loss": 2.0667, "step": 183000 }, { "epoch": 5.39, "learning_rate": 2.305195758804006e-05, "loss": 2.0717, "step": 183500 }, { "epoch": 5.4, "learning_rate": 2.2978529679560608e-05, "loss": 2.0686, "step": 184000 }, { "epoch": 5.42, "learning_rate": 2.2905101771081154e-05, "loss": 2.0671, "step": 184500 }, { "epoch": 5.43, "learning_rate": 2.28316738626017e-05, "loss": 2.0689, "step": 185000 }, { "epoch": 5.45, "learning_rate": 2.2758245954122243e-05, "loss": 2.0687, "step": 185500 }, { "epoch": 5.46, "learning_rate": 2.268481804564279e-05, "loss": 2.066, "step": 186000 }, { "epoch": 5.48, "learning_rate": 2.2611390137163336e-05, "loss": 2.0663, "step": 186500 }, { "epoch": 5.49, "learning_rate": 2.253796222868388e-05, "loss": 2.0619, "step": 187000 }, { "epoch": 5.51, "learning_rate": 2.2464534320204425e-05, "loss": 2.0682, "step": 187500 }, { "epoch": 5.52, "learning_rate": 2.2391106411724968e-05, "loss": 2.0619, "step": 188000 }, { "epoch": 5.54, "learning_rate": 2.2317678503245514e-05, "loss": 2.066, "step": 188500 }, { "epoch": 5.55, "learning_rate": 2.2244250594766057e-05, "loss": 2.0625, "step": 189000 }, { "epoch": 5.57, "learning_rate": 2.2170822686286604e-05, "loss": 2.0639, "step": 189500 }, { "epoch": 5.58, "learning_rate": 2.209739477780715e-05, "loss": 2.0648, "step": 190000 }, { "epoch": 5.6, "learning_rate": 2.2023966869327696e-05, "loss": 2.0607, "step": 190500 }, { "epoch": 5.61, "learning_rate": 2.1950538960848243e-05, "loss": 2.0634, "step": 191000 }, { "epoch": 5.62, "learning_rate": 2.1877111052368785e-05, "loss": 2.0638, "step": 191500 }, { "epoch": 5.64, "learning_rate": 2.1803683143889332e-05, "loss": 2.0605, "step": 192000 }, { "epoch": 5.65, "learning_rate": 2.1730255235409875e-05, "loss": 2.0614, "step": 192500 }, { "epoch": 5.67, "learning_rate": 2.165682732693042e-05, "loss": 2.06, "step": 193000 }, { "epoch": 5.68, "learning_rate": 2.1583399418450967e-05, "loss": 2.0619, "step": 193500 }, { "epoch": 5.7, "learning_rate": 2.150997150997151e-05, "loss": 2.0581, "step": 194000 }, { "epoch": 5.71, "learning_rate": 2.1436543601492056e-05, "loss": 2.0587, "step": 194500 }, { "epoch": 5.73, "learning_rate": 2.13631156930126e-05, "loss": 2.0588, "step": 195000 }, { "epoch": 5.74, "learning_rate": 2.1289687784533146e-05, "loss": 2.0554, "step": 195500 }, { "epoch": 5.76, "learning_rate": 2.121625987605369e-05, "loss": 2.0568, "step": 196000 }, { "epoch": 5.77, "learning_rate": 2.1142831967574235e-05, "loss": 2.0614, "step": 196500 }, { "epoch": 5.79, "learning_rate": 2.106940405909478e-05, "loss": 2.0553, "step": 197000 }, { "epoch": 5.8, "learning_rate": 2.0995976150615327e-05, "loss": 2.0561, "step": 197500 }, { "epoch": 5.82, "learning_rate": 2.0922548242135874e-05, "loss": 2.0576, "step": 198000 }, { "epoch": 5.83, "learning_rate": 2.0849120333656417e-05, "loss": 2.0562, "step": 198500 }, { "epoch": 5.84, "learning_rate": 2.0775692425176963e-05, "loss": 2.0573, "step": 199000 }, { "epoch": 5.86, "learning_rate": 2.0702264516697506e-05, "loss": 2.0578, "step": 199500 }, { "epoch": 5.87, "learning_rate": 2.0628836608218052e-05, "loss": 2.0563, "step": 200000 }, { "epoch": 5.89, "learning_rate": 2.05554086997386e-05, "loss": 2.056, "step": 200500 }, { "epoch": 5.9, "learning_rate": 2.048198079125914e-05, "loss": 2.0541, "step": 201000 }, { "epoch": 5.92, "learning_rate": 2.0408552882779688e-05, "loss": 2.0552, "step": 201500 }, { "epoch": 5.93, "learning_rate": 2.033512497430023e-05, "loss": 2.0548, "step": 202000 }, { "epoch": 5.95, "learning_rate": 2.0261697065820777e-05, "loss": 2.0565, "step": 202500 }, { "epoch": 5.96, "learning_rate": 2.0188269157341323e-05, "loss": 2.0527, "step": 203000 }, { "epoch": 5.98, "learning_rate": 2.011484124886187e-05, "loss": 2.0531, "step": 203500 }, { "epoch": 5.99, "learning_rate": 2.0041413340382416e-05, "loss": 2.0519, "step": 204000 }, { "epoch": 6.01, "learning_rate": 1.996798543190296e-05, "loss": 2.0501, "step": 204500 }, { "epoch": 6.02, "learning_rate": 1.9894557523423505e-05, "loss": 2.0527, "step": 205000 }, { "epoch": 6.04, "learning_rate": 1.9821129614944048e-05, "loss": 2.0484, "step": 205500 }, { "epoch": 6.05, "learning_rate": 1.9747701706464594e-05, "loss": 2.0485, "step": 206000 }, { "epoch": 6.07, "learning_rate": 1.967427379798514e-05, "loss": 2.0467, "step": 206500 }, { "epoch": 6.08, "learning_rate": 1.9600845889505683e-05, "loss": 2.0513, "step": 207000 }, { "epoch": 6.09, "learning_rate": 1.952741798102623e-05, "loss": 2.0488, "step": 207500 }, { "epoch": 6.11, "learning_rate": 1.9453990072546772e-05, "loss": 2.0513, "step": 208000 }, { "epoch": 6.12, "learning_rate": 1.938056216406732e-05, "loss": 2.0463, "step": 208500 }, { "epoch": 6.14, "learning_rate": 1.9307134255587865e-05, "loss": 2.0496, "step": 209000 }, { "epoch": 6.15, "learning_rate": 1.923370634710841e-05, "loss": 2.0492, "step": 209500 }, { "epoch": 6.17, "learning_rate": 1.9160278438628958e-05, "loss": 2.0437, "step": 210000 }, { "epoch": 6.18, "learning_rate": 1.90868505301495e-05, "loss": 2.0473, "step": 210500 }, { "epoch": 6.2, "learning_rate": 1.9013422621670047e-05, "loss": 2.0482, "step": 211000 }, { "epoch": 6.21, "learning_rate": 1.893999471319059e-05, "loss": 2.0478, "step": 211500 }, { "epoch": 6.23, "learning_rate": 1.8866566804711136e-05, "loss": 2.0463, "step": 212000 }, { "epoch": 6.24, "learning_rate": 1.879313889623168e-05, "loss": 2.0443, "step": 212500 }, { "epoch": 6.26, "learning_rate": 1.8719710987752225e-05, "loss": 2.0445, "step": 213000 }, { "epoch": 6.27, "learning_rate": 1.864628307927277e-05, "loss": 2.0427, "step": 213500 }, { "epoch": 6.29, "learning_rate": 1.8572855170793314e-05, "loss": 2.0404, "step": 214000 }, { "epoch": 6.3, "learning_rate": 1.849942726231386e-05, "loss": 2.046, "step": 214500 }, { "epoch": 6.31, "learning_rate": 1.8425999353834407e-05, "loss": 2.0438, "step": 215000 }, { "epoch": 6.33, "learning_rate": 1.8352571445354953e-05, "loss": 2.044, "step": 215500 }, { "epoch": 6.34, "learning_rate": 1.8279143536875496e-05, "loss": 2.0435, "step": 216000 }, { "epoch": 6.36, "learning_rate": 1.8205715628396043e-05, "loss": 2.0432, "step": 216500 }, { "epoch": 6.37, "learning_rate": 1.813228771991659e-05, "loss": 2.0431, "step": 217000 }, { "epoch": 6.39, "learning_rate": 1.8058859811437132e-05, "loss": 2.0393, "step": 217500 }, { "epoch": 6.4, "learning_rate": 1.7985431902957678e-05, "loss": 2.042, "step": 218000 }, { "epoch": 6.42, "learning_rate": 1.791200399447822e-05, "loss": 2.0402, "step": 218500 }, { "epoch": 6.43, "learning_rate": 1.7838576085998767e-05, "loss": 2.0404, "step": 219000 }, { "epoch": 6.45, "learning_rate": 1.776514817751931e-05, "loss": 2.0432, "step": 219500 }, { "epoch": 6.46, "learning_rate": 1.7691720269039856e-05, "loss": 2.0411, "step": 220000 }, { "epoch": 6.48, "learning_rate": 1.7618292360560403e-05, "loss": 2.0408, "step": 220500 }, { "epoch": 6.49, "learning_rate": 1.754486445208095e-05, "loss": 2.0426, "step": 221000 }, { "epoch": 6.51, "learning_rate": 1.7471436543601495e-05, "loss": 2.0408, "step": 221500 }, { "epoch": 6.52, "learning_rate": 1.7398008635122038e-05, "loss": 2.0406, "step": 222000 }, { "epoch": 6.54, "learning_rate": 1.7324580726642584e-05, "loss": 2.0391, "step": 222500 }, { "epoch": 6.55, "learning_rate": 1.7251152818163127e-05, "loss": 2.0374, "step": 223000 }, { "epoch": 6.56, "learning_rate": 1.7177724909683674e-05, "loss": 2.0374, "step": 223500 }, { "epoch": 6.58, "learning_rate": 1.710429700120422e-05, "loss": 2.0373, "step": 224000 }, { "epoch": 6.59, "learning_rate": 1.7030869092724763e-05, "loss": 2.0347, "step": 224500 }, { "epoch": 6.61, "learning_rate": 1.695744118424531e-05, "loss": 2.0356, "step": 225000 }, { "epoch": 6.62, "learning_rate": 1.6884013275765852e-05, "loss": 2.0407, "step": 225500 }, { "epoch": 6.64, "learning_rate": 1.68105853672864e-05, "loss": 2.0389, "step": 226000 }, { "epoch": 6.65, "learning_rate": 1.6737157458806945e-05, "loss": 2.0347, "step": 226500 }, { "epoch": 6.67, "learning_rate": 1.666372955032749e-05, "loss": 2.0397, "step": 227000 }, { "epoch": 6.68, "learning_rate": 1.6590301641848037e-05, "loss": 2.0348, "step": 227500 }, { "epoch": 6.7, "learning_rate": 1.651687373336858e-05, "loss": 2.0386, "step": 228000 }, { "epoch": 6.71, "learning_rate": 1.6443445824889126e-05, "loss": 2.0351, "step": 228500 }, { "epoch": 6.73, "learning_rate": 1.637001791640967e-05, "loss": 2.0363, "step": 229000 }, { "epoch": 6.74, "learning_rate": 1.6296590007930216e-05, "loss": 2.034, "step": 229500 }, { "epoch": 6.76, "learning_rate": 1.622316209945076e-05, "loss": 2.0386, "step": 230000 }, { "epoch": 6.77, "learning_rate": 1.6149734190971305e-05, "loss": 2.0334, "step": 230500 }, { "epoch": 6.78, "learning_rate": 1.607630628249185e-05, "loss": 2.0346, "step": 231000 }, { "epoch": 6.8, "learning_rate": 1.6002878374012394e-05, "loss": 2.0294, "step": 231500 }, { "epoch": 6.81, "learning_rate": 1.592945046553294e-05, "loss": 2.0342, "step": 232000 }, { "epoch": 6.83, "learning_rate": 1.5856022557053483e-05, "loss": 2.0332, "step": 232500 }, { "epoch": 6.84, "learning_rate": 1.578259464857403e-05, "loss": 2.0337, "step": 233000 }, { "epoch": 6.86, "learning_rate": 1.5709166740094576e-05, "loss": 2.0323, "step": 233500 }, { "epoch": 6.87, "learning_rate": 1.5635738831615122e-05, "loss": 2.0329, "step": 234000 }, { "epoch": 6.89, "learning_rate": 1.556231092313567e-05, "loss": 2.0314, "step": 234500 }, { "epoch": 6.9, "learning_rate": 1.548888301465621e-05, "loss": 2.0294, "step": 235000 }, { "epoch": 6.92, "learning_rate": 1.5415455106176758e-05, "loss": 2.0318, "step": 235500 }, { "epoch": 6.93, "learning_rate": 1.53420271976973e-05, "loss": 2.03, "step": 236000 }, { "epoch": 6.95, "learning_rate": 1.5268599289217847e-05, "loss": 2.0342, "step": 236500 }, { "epoch": 6.96, "learning_rate": 1.519517138073839e-05, "loss": 2.0324, "step": 237000 }, { "epoch": 6.98, "learning_rate": 1.5121743472258936e-05, "loss": 2.0318, "step": 237500 }, { "epoch": 6.99, "learning_rate": 1.5048315563779484e-05, "loss": 2.0309, "step": 238000 }, { "epoch": 7.01, "learning_rate": 1.4974887655300027e-05, "loss": 2.0298, "step": 238500 }, { "epoch": 7.02, "learning_rate": 1.4901459746820573e-05, "loss": 2.0298, "step": 239000 }, { "epoch": 7.03, "learning_rate": 1.4828031838341116e-05, "loss": 2.0289, "step": 239500 }, { "epoch": 7.05, "learning_rate": 1.4754603929861662e-05, "loss": 2.0261, "step": 240000 }, { "epoch": 7.06, "learning_rate": 1.4681176021382207e-05, "loss": 2.0322, "step": 240500 }, { "epoch": 7.08, "learning_rate": 1.4607748112902753e-05, "loss": 2.0266, "step": 241000 }, { "epoch": 7.09, "learning_rate": 1.45343202044233e-05, "loss": 2.0277, "step": 241500 }, { "epoch": 7.11, "learning_rate": 1.4460892295943842e-05, "loss": 2.025, "step": 242000 }, { "epoch": 7.12, "learning_rate": 1.4387464387464389e-05, "loss": 2.0253, "step": 242500 }, { "epoch": 7.14, "learning_rate": 1.4314036478984932e-05, "loss": 2.0283, "step": 243000 }, { "epoch": 7.15, "learning_rate": 1.4240608570505478e-05, "loss": 2.0273, "step": 243500 }, { "epoch": 7.17, "learning_rate": 1.4167180662026023e-05, "loss": 2.0276, "step": 244000 }, { "epoch": 7.18, "learning_rate": 1.4093752753546569e-05, "loss": 2.0274, "step": 244500 }, { "epoch": 7.2, "learning_rate": 1.4020324845067115e-05, "loss": 2.0284, "step": 245000 }, { "epoch": 7.21, "learning_rate": 1.3946896936587658e-05, "loss": 2.027, "step": 245500 }, { "epoch": 7.23, "learning_rate": 1.3873469028108204e-05, "loss": 2.0236, "step": 246000 }, { "epoch": 7.24, "learning_rate": 1.3800041119628749e-05, "loss": 2.0289, "step": 246500 }, { "epoch": 7.25, "learning_rate": 1.3726613211149295e-05, "loss": 2.0229, "step": 247000 }, { "epoch": 7.27, "learning_rate": 1.3653185302669838e-05, "loss": 2.0246, "step": 247500 }, { "epoch": 7.28, "learning_rate": 1.3579757394190384e-05, "loss": 2.0221, "step": 248000 }, { "epoch": 7.3, "learning_rate": 1.350632948571093e-05, "loss": 2.0237, "step": 248500 }, { "epoch": 7.31, "learning_rate": 1.3432901577231474e-05, "loss": 2.0274, "step": 249000 }, { "epoch": 7.33, "learning_rate": 1.335947366875202e-05, "loss": 2.0228, "step": 249500 }, { "epoch": 7.34, "learning_rate": 1.3286045760272565e-05, "loss": 2.0241, "step": 250000 }, { "epoch": 7.36, "learning_rate": 1.321261785179311e-05, "loss": 2.0262, "step": 250500 }, { "epoch": 7.37, "learning_rate": 1.3139189943313654e-05, "loss": 2.0219, "step": 251000 }, { "epoch": 7.39, "learning_rate": 1.30657620348342e-05, "loss": 2.023, "step": 251500 }, { "epoch": 7.4, "learning_rate": 1.2992334126354746e-05, "loss": 2.0245, "step": 252000 }, { "epoch": 7.42, "learning_rate": 1.2918906217875291e-05, "loss": 2.0245, "step": 252500 }, { "epoch": 7.43, "learning_rate": 1.2845478309395837e-05, "loss": 2.0265, "step": 253000 }, { "epoch": 7.45, "learning_rate": 1.277205040091638e-05, "loss": 2.0244, "step": 253500 }, { "epoch": 7.46, "learning_rate": 1.2698622492436926e-05, "loss": 2.0212, "step": 254000 }, { "epoch": 7.47, "learning_rate": 1.262519458395747e-05, "loss": 2.0212, "step": 254500 }, { "epoch": 7.49, "learning_rate": 1.2551766675478016e-05, "loss": 2.02, "step": 255000 }, { "epoch": 7.5, "learning_rate": 1.247833876699856e-05, "loss": 2.0223, "step": 255500 }, { "epoch": 7.52, "learning_rate": 1.2404910858519106e-05, "loss": 2.0222, "step": 256000 }, { "epoch": 7.53, "learning_rate": 1.2331482950039653e-05, "loss": 2.0217, "step": 256500 }, { "epoch": 7.55, "learning_rate": 1.2258055041560197e-05, "loss": 2.0179, "step": 257000 }, { "epoch": 7.56, "learning_rate": 1.2184627133080742e-05, "loss": 2.0218, "step": 257500 }, { "epoch": 7.58, "learning_rate": 1.2111199224601287e-05, "loss": 2.0214, "step": 258000 }, { "epoch": 7.59, "learning_rate": 1.2037771316121831e-05, "loss": 2.0184, "step": 258500 }, { "epoch": 7.61, "learning_rate": 1.1964343407642377e-05, "loss": 2.0222, "step": 259000 }, { "epoch": 7.62, "learning_rate": 1.1890915499162922e-05, "loss": 2.0169, "step": 259500 }, { "epoch": 7.64, "learning_rate": 1.1817487590683468e-05, "loss": 2.0164, "step": 260000 }, { "epoch": 7.65, "learning_rate": 1.1744059682204013e-05, "loss": 2.0156, "step": 260500 }, { "epoch": 7.67, "learning_rate": 1.1670631773724558e-05, "loss": 2.017, "step": 261000 }, { "epoch": 7.68, "learning_rate": 1.1597203865245102e-05, "loss": 2.0181, "step": 261500 }, { "epoch": 7.7, "learning_rate": 1.1523775956765648e-05, "loss": 2.0174, "step": 262000 }, { "epoch": 7.71, "learning_rate": 1.1450348048286193e-05, "loss": 2.0194, "step": 262500 }, { "epoch": 7.72, "learning_rate": 1.1376920139806738e-05, "loss": 2.0185, "step": 263000 }, { "epoch": 7.74, "learning_rate": 1.1303492231327284e-05, "loss": 2.019, "step": 263500 }, { "epoch": 7.75, "learning_rate": 1.1230064322847829e-05, "loss": 2.0173, "step": 264000 }, { "epoch": 7.77, "learning_rate": 1.1156636414368373e-05, "loss": 2.0181, "step": 264500 }, { "epoch": 7.78, "learning_rate": 1.108320850588892e-05, "loss": 2.0172, "step": 265000 }, { "epoch": 7.8, "learning_rate": 1.1009780597409464e-05, "loss": 2.0168, "step": 265500 }, { "epoch": 7.81, "learning_rate": 1.0936352688930009e-05, "loss": 2.0191, "step": 266000 }, { "epoch": 7.83, "learning_rate": 1.0862924780450553e-05, "loss": 2.0172, "step": 266500 }, { "epoch": 7.84, "learning_rate": 1.07894968719711e-05, "loss": 2.0167, "step": 267000 }, { "epoch": 7.86, "learning_rate": 1.0716068963491644e-05, "loss": 2.0157, "step": 267500 }, { "epoch": 7.87, "learning_rate": 1.064264105501219e-05, "loss": 2.0151, "step": 268000 }, { "epoch": 7.89, "learning_rate": 1.0569213146532735e-05, "loss": 2.0165, "step": 268500 }, { "epoch": 7.9, "learning_rate": 1.049578523805328e-05, "loss": 2.0135, "step": 269000 }, { "epoch": 7.92, "learning_rate": 1.0422357329573824e-05, "loss": 2.0153, "step": 269500 }, { "epoch": 7.93, "learning_rate": 1.0348929421094369e-05, "loss": 2.0145, "step": 270000 }, { "epoch": 7.94, "learning_rate": 1.0275501512614915e-05, "loss": 2.0175, "step": 270500 }, { "epoch": 7.96, "learning_rate": 1.0202073604135461e-05, "loss": 2.0149, "step": 271000 }, { "epoch": 7.97, "learning_rate": 1.0128645695656006e-05, "loss": 2.0184, "step": 271500 }, { "epoch": 7.99, "learning_rate": 1.005521778717655e-05, "loss": 2.0161, "step": 272000 }, { "epoch": 8.0, "learning_rate": 9.981789878697095e-06, "loss": 2.015, "step": 272500 }, { "epoch": 8.02, "learning_rate": 9.90836197021764e-06, "loss": 2.0154, "step": 273000 }, { "epoch": 8.03, "learning_rate": 9.834934061738186e-06, "loss": 2.0158, "step": 273500 }, { "epoch": 8.05, "learning_rate": 9.76150615325873e-06, "loss": 2.0139, "step": 274000 }, { "epoch": 8.06, "learning_rate": 9.688078244779277e-06, "loss": 2.0107, "step": 274500 }, { "epoch": 8.08, "learning_rate": 9.614650336299822e-06, "loss": 2.0124, "step": 275000 }, { "epoch": 8.09, "learning_rate": 9.541222427820366e-06, "loss": 2.0123, "step": 275500 }, { "epoch": 8.11, "learning_rate": 9.46779451934091e-06, "loss": 2.0131, "step": 276000 }, { "epoch": 8.12, "learning_rate": 9.394366610861455e-06, "loss": 2.0113, "step": 276500 }, { "epoch": 8.14, "learning_rate": 9.320938702382002e-06, "loss": 2.0085, "step": 277000 }, { "epoch": 8.15, "learning_rate": 9.247510793902548e-06, "loss": 2.0122, "step": 277500 }, { "epoch": 8.17, "learning_rate": 9.174082885423093e-06, "loss": 2.0124, "step": 278000 }, { "epoch": 8.18, "learning_rate": 9.100654976943637e-06, "loss": 2.0118, "step": 278500 }, { "epoch": 8.19, "learning_rate": 9.027227068464182e-06, "loss": 2.0106, "step": 279000 }, { "epoch": 8.21, "learning_rate": 8.953799159984726e-06, "loss": 2.0123, "step": 279500 }, { "epoch": 8.22, "learning_rate": 8.880371251505273e-06, "loss": 2.0113, "step": 280000 }, { "epoch": 8.24, "learning_rate": 8.806943343025819e-06, "loss": 2.0126, "step": 280500 }, { "epoch": 8.25, "learning_rate": 8.733515434546364e-06, "loss": 2.0123, "step": 281000 }, { "epoch": 8.27, "learning_rate": 8.660087526066908e-06, "loss": 2.011, "step": 281500 }, { "epoch": 8.28, "learning_rate": 8.586659617587453e-06, "loss": 2.0082, "step": 282000 }, { "epoch": 8.3, "learning_rate": 8.513231709107997e-06, "loss": 2.0084, "step": 282500 }, { "epoch": 8.31, "learning_rate": 8.439803800628544e-06, "loss": 2.0106, "step": 283000 }, { "epoch": 8.33, "learning_rate": 8.366375892149088e-06, "loss": 2.0123, "step": 283500 }, { "epoch": 8.34, "learning_rate": 8.292947983669635e-06, "loss": 2.0069, "step": 284000 }, { "epoch": 8.36, "learning_rate": 8.219520075190179e-06, "loss": 2.0082, "step": 284500 }, { "epoch": 8.37, "learning_rate": 8.146092166710724e-06, "loss": 2.0102, "step": 285000 }, { "epoch": 8.39, "learning_rate": 8.072664258231268e-06, "loss": 2.0099, "step": 285500 }, { "epoch": 8.4, "learning_rate": 7.999236349751815e-06, "loss": 2.0047, "step": 286000 }, { "epoch": 8.41, "learning_rate": 7.92580844127236e-06, "loss": 2.0122, "step": 286500 }, { "epoch": 8.43, "learning_rate": 7.852380532792904e-06, "loss": 2.01, "step": 287000 }, { "epoch": 8.44, "learning_rate": 7.77895262431345e-06, "loss": 2.0081, "step": 287500 }, { "epoch": 8.46, "learning_rate": 7.705524715833995e-06, "loss": 2.007, "step": 288000 }, { "epoch": 8.47, "learning_rate": 7.63209680735454e-06, "loss": 2.005, "step": 288500 }, { "epoch": 8.49, "learning_rate": 7.558668898875085e-06, "loss": 2.0107, "step": 289000 }, { "epoch": 8.5, "learning_rate": 7.485240990395629e-06, "loss": 2.0109, "step": 289500 }, { "epoch": 8.52, "learning_rate": 7.411813081916175e-06, "loss": 2.0084, "step": 290000 }, { "epoch": 8.53, "learning_rate": 7.338385173436719e-06, "loss": 2.009, "step": 290500 }, { "epoch": 8.55, "learning_rate": 7.264957264957266e-06, "loss": 2.0065, "step": 291000 }, { "epoch": 8.56, "learning_rate": 7.191529356477811e-06, "loss": 2.0098, "step": 291500 }, { "epoch": 8.58, "learning_rate": 7.118101447998356e-06, "loss": 2.0087, "step": 292000 }, { "epoch": 8.59, "learning_rate": 7.0446735395189e-06, "loss": 2.0073, "step": 292500 }, { "epoch": 8.61, "learning_rate": 6.971245631039446e-06, "loss": 2.01, "step": 293000 }, { "epoch": 8.62, "learning_rate": 6.89781772255999e-06, "loss": 2.0087, "step": 293500 }, { "epoch": 8.64, "learning_rate": 6.824389814080535e-06, "loss": 2.0061, "step": 294000 }, { "epoch": 8.65, "learning_rate": 6.750961905601082e-06, "loss": 2.0119, "step": 294500 }, { "epoch": 8.66, "learning_rate": 6.677533997121627e-06, "loss": 2.0071, "step": 295000 }, { "epoch": 8.68, "learning_rate": 6.604106088642171e-06, "loss": 2.0115, "step": 295500 }, { "epoch": 8.69, "learning_rate": 6.530678180162717e-06, "loss": 2.0021, "step": 296000 }, { "epoch": 8.71, "learning_rate": 6.457250271683261e-06, "loss": 2.0075, "step": 296500 }, { "epoch": 8.72, "learning_rate": 6.383822363203806e-06, "loss": 2.0059, "step": 297000 }, { "epoch": 8.74, "learning_rate": 6.310394454724351e-06, "loss": 2.006, "step": 297500 }, { "epoch": 8.75, "learning_rate": 6.236966546244897e-06, "loss": 2.0052, "step": 298000 }, { "epoch": 8.77, "learning_rate": 6.163538637765442e-06, "loss": 2.0064, "step": 298500 }, { "epoch": 8.78, "learning_rate": 6.090110729285988e-06, "loss": 2.0103, "step": 299000 }, { "epoch": 8.8, "learning_rate": 6.016682820806532e-06, "loss": 2.004, "step": 299500 }, { "epoch": 8.81, "learning_rate": 5.943254912327077e-06, "loss": 2.0042, "step": 300000 }, { "epoch": 8.83, "learning_rate": 5.869827003847623e-06, "loss": 2.0072, "step": 300500 }, { "epoch": 8.84, "learning_rate": 5.796399095368168e-06, "loss": 2.0051, "step": 301000 }, { "epoch": 8.86, "learning_rate": 5.7229711868887124e-06, "loss": 2.0044, "step": 301500 }, { "epoch": 8.87, "learning_rate": 5.649543278409259e-06, "loss": 2.0032, "step": 302000 }, { "epoch": 8.88, "learning_rate": 5.576115369929803e-06, "loss": 2.0039, "step": 302500 }, { "epoch": 8.9, "learning_rate": 5.502687461450348e-06, "loss": 2.0084, "step": 303000 }, { "epoch": 8.91, "learning_rate": 5.429259552970893e-06, "loss": 2.0048, "step": 303500 }, { "epoch": 8.93, "learning_rate": 5.355831644491439e-06, "loss": 2.0011, "step": 304000 }, { "epoch": 8.94, "learning_rate": 5.2824037360119834e-06, "loss": 2.0066, "step": 304500 }, { "epoch": 8.96, "learning_rate": 5.208975827532529e-06, "loss": 2.005, "step": 305000 }, { "epoch": 8.97, "learning_rate": 5.135547919053074e-06, "loss": 2.0046, "step": 305500 }, { "epoch": 8.99, "learning_rate": 5.062120010573619e-06, "loss": 2.0027, "step": 306000 }, { "epoch": 9.0, "learning_rate": 4.988692102094164e-06, "loss": 2.0056, "step": 306500 }, { "epoch": 9.02, "learning_rate": 4.915264193614709e-06, "loss": 2.0008, "step": 307000 }, { "epoch": 9.03, "learning_rate": 4.841836285135254e-06, "loss": 2.0039, "step": 307500 }, { "epoch": 9.05, "learning_rate": 4.7684083766558e-06, "loss": 2.0003, "step": 308000 }, { "epoch": 9.06, "learning_rate": 4.6949804681763445e-06, "loss": 2.0001, "step": 308500 }, { "epoch": 9.08, "learning_rate": 4.62155255969689e-06, "loss": 2.003, "step": 309000 }, { "epoch": 9.09, "learning_rate": 4.548124651217435e-06, "loss": 2.0019, "step": 309500 }, { "epoch": 9.11, "learning_rate": 4.47469674273798e-06, "loss": 2.0012, "step": 310000 }, { "epoch": 9.12, "learning_rate": 4.401268834258525e-06, "loss": 2.0018, "step": 310500 }, { "epoch": 9.13, "learning_rate": 4.327840925779071e-06, "loss": 2.0018, "step": 311000 }, { "epoch": 9.15, "learning_rate": 4.2544130172996154e-06, "loss": 2.0024, "step": 311500 }, { "epoch": 9.16, "learning_rate": 4.18098510882016e-06, "loss": 1.9982, "step": 312000 }, { "epoch": 9.18, "learning_rate": 4.1075572003407055e-06, "loss": 2.0031, "step": 312500 }, { "epoch": 9.19, "learning_rate": 4.034129291861251e-06, "loss": 2.0048, "step": 313000 }, { "epoch": 9.21, "learning_rate": 3.9607013833817955e-06, "loss": 2.004, "step": 313500 }, { "epoch": 9.22, "learning_rate": 3.887273474902341e-06, "loss": 2.0027, "step": 314000 }, { "epoch": 9.24, "learning_rate": 3.8138455664228864e-06, "loss": 2.0035, "step": 314500 }, { "epoch": 9.25, "learning_rate": 3.740417657943431e-06, "loss": 2.0036, "step": 315000 }, { "epoch": 9.27, "learning_rate": 3.666989749463976e-06, "loss": 1.9977, "step": 315500 }, { "epoch": 9.28, "learning_rate": 3.593561840984522e-06, "loss": 2.0023, "step": 316000 }, { "epoch": 9.3, "learning_rate": 3.5201339325050665e-06, "loss": 2.0017, "step": 316500 }, { "epoch": 9.31, "learning_rate": 3.4467060240256115e-06, "loss": 2.0015, "step": 317000 }, { "epoch": 9.33, "learning_rate": 3.3732781155461574e-06, "loss": 2.0024, "step": 317500 }, { "epoch": 9.34, "learning_rate": 3.299850207066702e-06, "loss": 2.0012, "step": 318000 }, { "epoch": 9.35, "learning_rate": 3.226422298587247e-06, "loss": 2.0004, "step": 318500 }, { "epoch": 9.37, "learning_rate": 3.152994390107792e-06, "loss": 2.0048, "step": 319000 }, { "epoch": 9.38, "learning_rate": 3.0795664816283375e-06, "loss": 2.0005, "step": 319500 }, { "epoch": 9.4, "learning_rate": 3.0061385731488825e-06, "loss": 2.0022, "step": 320000 }, { "epoch": 9.41, "learning_rate": 2.932710664669428e-06, "loss": 2.0022, "step": 320500 }, { "epoch": 9.43, "learning_rate": 2.8592827561899726e-06, "loss": 1.9982, "step": 321000 }, { "epoch": 9.44, "learning_rate": 2.785854847710518e-06, "loss": 2.0, "step": 321500 }, { "epoch": 9.46, "learning_rate": 2.712426939231063e-06, "loss": 1.9994, "step": 322000 }, { "epoch": 9.47, "learning_rate": 2.638999030751608e-06, "loss": 1.9991, "step": 322500 }, { "epoch": 9.49, "learning_rate": 2.5655711222721535e-06, "loss": 1.9989, "step": 323000 }, { "epoch": 9.5, "learning_rate": 2.4921432137926985e-06, "loss": 2.0017, "step": 323500 }, { "epoch": 9.52, "learning_rate": 2.4187153053132435e-06, "loss": 1.9981, "step": 324000 }, { "epoch": 9.53, "learning_rate": 2.3452873968337886e-06, "loss": 1.9998, "step": 324500 }, { "epoch": 9.55, "learning_rate": 2.271859488354334e-06, "loss": 1.9978, "step": 325000 }, { "epoch": 9.56, "learning_rate": 2.198431579874879e-06, "loss": 1.9981, "step": 325500 }, { "epoch": 9.57, "learning_rate": 2.125003671395424e-06, "loss": 2.001, "step": 326000 }, { "epoch": 9.59, "learning_rate": 2.0515757629159695e-06, "loss": 2.0024, "step": 326500 }, { "epoch": 9.6, "learning_rate": 1.978147854436514e-06, "loss": 1.9995, "step": 327000 }, { "epoch": 9.62, "learning_rate": 1.9047199459570595e-06, "loss": 1.9989, "step": 327500 }, { "epoch": 9.63, "learning_rate": 1.8312920374776044e-06, "loss": 2.0, "step": 328000 }, { "epoch": 9.65, "learning_rate": 1.7578641289981498e-06, "loss": 1.9958, "step": 328500 }, { "epoch": 9.66, "learning_rate": 1.684436220518695e-06, "loss": 1.9983, "step": 329000 }, { "epoch": 9.68, "learning_rate": 1.6110083120392398e-06, "loss": 1.9986, "step": 329500 }, { "epoch": 9.69, "learning_rate": 1.537580403559785e-06, "loss": 2.0003, "step": 330000 }, { "epoch": 9.71, "learning_rate": 1.4641524950803303e-06, "loss": 1.9978, "step": 330500 }, { "epoch": 9.72, "learning_rate": 1.3907245866008753e-06, "loss": 2.0016, "step": 331000 }, { "epoch": 9.74, "learning_rate": 1.3172966781214204e-06, "loss": 2.0, "step": 331500 }, { "epoch": 9.75, "learning_rate": 1.2438687696419656e-06, "loss": 1.9973, "step": 332000 }, { "epoch": 9.77, "learning_rate": 1.1704408611625106e-06, "loss": 2.0012, "step": 332500 }, { "epoch": 9.78, "learning_rate": 1.0970129526830556e-06, "loss": 2.0012, "step": 333000 }, { "epoch": 9.8, "learning_rate": 1.023585044203601e-06, "loss": 1.9966, "step": 333500 }, { "epoch": 9.81, "learning_rate": 9.501571357241461e-07, "loss": 2.0031, "step": 334000 }, { "epoch": 9.82, "learning_rate": 8.767292272446912e-07, "loss": 1.9996, "step": 334500 }, { "epoch": 9.84, "learning_rate": 8.033013187652363e-07, "loss": 1.9967, "step": 335000 }, { "epoch": 9.85, "learning_rate": 7.298734102857815e-07, "loss": 2.0005, "step": 335500 }, { "epoch": 9.87, "learning_rate": 6.564455018063266e-07, "loss": 1.9987, "step": 336000 }, { "epoch": 9.88, "learning_rate": 5.830175933268716e-07, "loss": 1.9945, "step": 336500 }, { "epoch": 9.9, "learning_rate": 5.095896848474169e-07, "loss": 1.9971, "step": 337000 }, { "epoch": 9.91, "learning_rate": 4.3616177636796196e-07, "loss": 1.9995, "step": 337500 }, { "epoch": 9.93, "learning_rate": 3.627338678885071e-07, "loss": 1.9997, "step": 338000 }, { "epoch": 9.94, "learning_rate": 2.893059594090522e-07, "loss": 1.9993, "step": 338500 }, { "epoch": 9.96, "learning_rate": 2.1587805092959734e-07, "loss": 1.9961, "step": 339000 }, { "epoch": 9.97, "learning_rate": 1.4245014245014247e-07, "loss": 1.9989, "step": 339500 }, { "epoch": 9.99, "learning_rate": 6.902223397068759e-08, "loss": 1.9942, "step": 340000 }, { "epoch": 10.0, "learning_rate": 4.541449386810212e-06, "loss": 2.0143, "step": 340500 }, { "epoch": 10.02, "learning_rate": 4.47469674273798e-06, "loss": 1.9987, "step": 341000 }, { "epoch": 10.03, "learning_rate": 4.407944098665749e-06, "loss": 2.0004, "step": 341500 }, { "epoch": 10.04, "learning_rate": 4.341191454593517e-06, "loss": 2.0011, "step": 342000 }, { "epoch": 10.06, "learning_rate": 4.2744388105212845e-06, "loss": 1.9983, "step": 342500 }, { "epoch": 10.07, "learning_rate": 4.207686166449053e-06, "loss": 1.9996, "step": 343000 }, { "epoch": 10.09, "learning_rate": 4.140933522376821e-06, "loss": 1.9999, "step": 343500 }, { "epoch": 10.1, "learning_rate": 4.07418087830459e-06, "loss": 1.9965, "step": 344000 }, { "epoch": 10.12, "learning_rate": 4.007428234232359e-06, "loss": 1.9985, "step": 344500 }, { "epoch": 10.13, "learning_rate": 3.9406755901601265e-06, "loss": 1.996, "step": 345000 }, { "epoch": 10.15, "learning_rate": 3.873922946087894e-06, "loss": 2.0013, "step": 345500 }, { "epoch": 10.16, "learning_rate": 3.8071703020156635e-06, "loss": 1.9996, "step": 346000 }, { "epoch": 10.18, "learning_rate": 3.740417657943431e-06, "loss": 1.998, "step": 346500 }, { "epoch": 10.19, "learning_rate": 3.6736650138711998e-06, "loss": 1.9969, "step": 347000 }, { "epoch": 10.21, "learning_rate": 3.6069123697989677e-06, "loss": 2.0031, "step": 347500 }, { "epoch": 10.22, "learning_rate": 3.540159725726736e-06, "loss": 1.9984, "step": 348000 }, { "epoch": 10.24, "learning_rate": 3.4734070816545047e-06, "loss": 1.9997, "step": 348500 }, { "epoch": 10.25, "learning_rate": 3.4066544375822726e-06, "loss": 2.0024, "step": 349000 }, { "epoch": 10.27, "learning_rate": 3.3399017935100413e-06, "loss": 1.9929, "step": 349500 }, { "epoch": 10.28, "learning_rate": 3.2731491494378097e-06, "loss": 1.9966, "step": 350000 }, { "epoch": 10.29, "learning_rate": 3.2063965053655776e-06, "loss": 1.9985, "step": 350500 }, { "epoch": 10.31, "learning_rate": 3.1396438612933463e-06, "loss": 1.996, "step": 351000 }, { "epoch": 10.32, "learning_rate": 3.072891217221114e-06, "loss": 2.0028, "step": 351500 }, { "epoch": 10.34, "learning_rate": 3.0061385731488825e-06, "loss": 1.9982, "step": 352000 }, { "epoch": 10.35, "learning_rate": 2.939385929076651e-06, "loss": 1.9988, "step": 352500 }, { "epoch": 10.37, "learning_rate": 2.872633285004419e-06, "loss": 2.0011, "step": 353000 }, { "epoch": 10.38, "learning_rate": 2.8058806409321875e-06, "loss": 1.9968, "step": 353500 }, { "epoch": 10.4, "learning_rate": 2.7391279968599558e-06, "loss": 1.9984, "step": 354000 }, { "epoch": 10.41, "learning_rate": 2.672375352787724e-06, "loss": 1.9961, "step": 354500 }, { "epoch": 10.43, "learning_rate": 2.6056227087154924e-06, "loss": 1.9976, "step": 355000 }, { "epoch": 10.44, "learning_rate": 2.5388700646432607e-06, "loss": 1.996, "step": 355500 }, { "epoch": 10.46, "learning_rate": 2.472117420571029e-06, "loss": 2.0002, "step": 356000 }, { "epoch": 10.47, "learning_rate": 2.405364776498797e-06, "loss": 1.9951, "step": 356500 }, { "epoch": 10.49, "learning_rate": 2.3386121324265657e-06, "loss": 1.9955, "step": 357000 }, { "epoch": 10.5, "learning_rate": 2.271859488354334e-06, "loss": 1.9992, "step": 357500 }, { "epoch": 10.51, "learning_rate": 2.205106844282102e-06, "loss": 1.9965, "step": 358000 }, { "epoch": 10.53, "learning_rate": 2.1383542002098702e-06, "loss": 1.9992, "step": 358500 }, { "epoch": 10.54, "learning_rate": 2.071601556137639e-06, "loss": 1.9951, "step": 359000 }, { "epoch": 10.56, "learning_rate": 2.004848912065407e-06, "loss": 1.9972, "step": 359500 }, { "epoch": 10.57, "learning_rate": 1.938096267993175e-06, "loss": 1.9929, "step": 360000 }, { "epoch": 10.59, "learning_rate": 1.8713436239209435e-06, "loss": 2.0001, "step": 360500 }, { "epoch": 10.6, "learning_rate": 1.804590979848712e-06, "loss": 1.9963, "step": 361000 }, { "epoch": 10.62, "learning_rate": 1.7378383357764801e-06, "loss": 1.9988, "step": 361500 }, { "epoch": 10.63, "learning_rate": 1.6710856917042484e-06, "loss": 1.9949, "step": 362000 }, { "epoch": 10.65, "learning_rate": 1.6043330476320166e-06, "loss": 1.9968, "step": 362500 }, { "epoch": 10.66, "learning_rate": 1.537580403559785e-06, "loss": 1.9943, "step": 363000 }, { "epoch": 10.68, "learning_rate": 1.4708277594875534e-06, "loss": 1.9962, "step": 363500 }, { "epoch": 10.69, "learning_rate": 1.4040751154153217e-06, "loss": 1.9959, "step": 364000 }, { "epoch": 10.71, "learning_rate": 1.33732247134309e-06, "loss": 1.9948, "step": 364500 }, { "epoch": 10.72, "learning_rate": 1.2705698272708584e-06, "loss": 1.9995, "step": 365000 }, { "epoch": 10.74, "learning_rate": 1.2038171831986265e-06, "loss": 1.9945, "step": 365500 }, { "epoch": 10.75, "learning_rate": 1.137064539126395e-06, "loss": 1.9973, "step": 366000 }, { "epoch": 10.76, "learning_rate": 1.070311895054163e-06, "loss": 1.9957, "step": 366500 }, { "epoch": 10.78, "learning_rate": 1.0035592509819314e-06, "loss": 1.9979, "step": 367000 }, { "epoch": 10.79, "learning_rate": 9.368066069096997e-07, "loss": 1.9988, "step": 367500 }, { "epoch": 10.81, "learning_rate": 8.70053962837468e-07, "loss": 1.9961, "step": 368000 }, { "epoch": 10.82, "learning_rate": 8.033013187652363e-07, "loss": 1.9977, "step": 368500 }, { "epoch": 10.84, "learning_rate": 7.365486746930046e-07, "loss": 1.9967, "step": 369000 }, { "epoch": 10.85, "learning_rate": 6.697960306207729e-07, "loss": 1.9953, "step": 369500 }, { "epoch": 10.87, "learning_rate": 6.030433865485412e-07, "loss": 1.9931, "step": 370000 }, { "epoch": 10.88, "learning_rate": 5.362907424763095e-07, "loss": 1.9968, "step": 370500 }, { "epoch": 10.9, "learning_rate": 4.695380984040778e-07, "loss": 1.9948, "step": 371000 }, { "epoch": 10.91, "learning_rate": 4.0278545433184606e-07, "loss": 1.9966, "step": 371500 }, { "epoch": 10.93, "learning_rate": 3.360328102596144e-07, "loss": 1.9981, "step": 372000 }, { "epoch": 10.94, "learning_rate": 2.692801661873827e-07, "loss": 1.9984, "step": 372500 }, { "epoch": 10.96, "learning_rate": 2.02527522115151e-07, "loss": 2.0005, "step": 373000 }, { "epoch": 10.97, "learning_rate": 1.3577487804291928e-07, "loss": 1.9957, "step": 373500 }, { "epoch": 10.98, "learning_rate": 6.902223397068759e-08, "loss": 1.9957, "step": 374000 }, { "epoch": 11.0, "learning_rate": 2.2695898984558777e-09, "loss": 1.9939, "step": 374500 }, { "epoch": 11.0, "step": 374517, "total_flos": 9.502046248868659e+17, "train_loss": 0.1815926024128583, "train_runtime": 12938.8886, "train_samples_per_second": 7409.842, "train_steps_per_second": 28.945 } ], "logging_steps": 500, "max_steps": 374517, "num_input_tokens_seen": 0, "num_train_epochs": 11, "save_steps": 100000.0, "total_flos": 9.502046248868659e+17, "train_batch_size": 256, "trial_name": null, "trial_params": null }