{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "global_step": 230695, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.989293222653287e-05, "loss": 9.2291, "step": 500 }, { "epoch": 0.02, "learning_rate": 4.978456403476452e-05, "loss": 8.5435, "step": 1000 }, { "epoch": 0.03, "learning_rate": 4.967619584299617e-05, "loss": 8.4546, "step": 1500 }, { "epoch": 0.04, "learning_rate": 4.9567827651227814e-05, "loss": 8.3564, "step": 2000 }, { "epoch": 0.05, "learning_rate": 4.945945945945946e-05, "loss": 8.3088, "step": 2500 }, { "epoch": 0.07, "learning_rate": 4.935109126769111e-05, "loss": 8.2156, "step": 3000 }, { "epoch": 0.08, "learning_rate": 4.924272307592276e-05, "loss": 8.1808, "step": 3500 }, { "epoch": 0.09, "learning_rate": 4.9134354884154406e-05, "loss": 8.1035, "step": 4000 }, { "epoch": 0.1, "learning_rate": 4.902598669238606e-05, "loss": 8.032, "step": 4500 }, { "epoch": 0.11, "learning_rate": 4.89176185006177e-05, "loss": 7.9508, "step": 5000 }, { "epoch": 0.12, "learning_rate": 4.8809250308849345e-05, "loss": 7.8717, "step": 5500 }, { "epoch": 0.13, "learning_rate": 4.8700882117081e-05, "loss": 7.8179, "step": 6000 }, { "epoch": 0.14, "learning_rate": 4.8592513925312644e-05, "loss": 7.729, "step": 6500 }, { "epoch": 0.15, "learning_rate": 4.84841457335443e-05, "loss": 7.7062, "step": 7000 }, { "epoch": 0.16, "learning_rate": 4.837577754177594e-05, "loss": 7.623, "step": 7500 }, { "epoch": 0.17, "learning_rate": 4.826740935000759e-05, "loss": 7.5969, "step": 8000 }, { "epoch": 0.18, "learning_rate": 4.8159041158239236e-05, "loss": 7.5306, "step": 8500 }, { "epoch": 0.2, "learning_rate": 4.805067296647088e-05, "loss": 7.4785, "step": 9000 }, { "epoch": 0.21, "learning_rate": 4.794252151108607e-05, "loss": 7.4348, "step": 9500 }, { "epoch": 0.22, "learning_rate": 4.7834153319317714e-05, "loss": 7.399, "step": 10000 }, { "epoch": 0.23, "learning_rate": 4.772578512754937e-05, "loss": 7.3493, "step": 10500 }, { "epoch": 0.24, "learning_rate": 4.7617416935781014e-05, "loss": 7.287, "step": 11000 }, { "epoch": 0.25, "learning_rate": 4.750904874401266e-05, "loss": 7.2254, "step": 11500 }, { "epoch": 0.26, "learning_rate": 4.7400897288627846e-05, "loss": 7.1961, "step": 12000 }, { "epoch": 0.27, "learning_rate": 4.729252909685949e-05, "loss": 7.1299, "step": 12500 }, { "epoch": 0.28, "learning_rate": 4.718416090509114e-05, "loss": 7.1257, "step": 13000 }, { "epoch": 0.29, "learning_rate": 4.7075792713322785e-05, "loss": 7.074, "step": 13500 }, { "epoch": 0.3, "learning_rate": 4.696742452155444e-05, "loss": 7.052, "step": 14000 }, { "epoch": 0.31, "learning_rate": 4.685927306616962e-05, "loss": 6.9863, "step": 14500 }, { "epoch": 0.33, "learning_rate": 4.675090487440127e-05, "loss": 6.9617, "step": 15000 }, { "epoch": 0.34, "learning_rate": 4.664253668263292e-05, "loss": 6.9034, "step": 15500 }, { "epoch": 0.35, "learning_rate": 4.653416849086456e-05, "loss": 6.8683, "step": 16000 }, { "epoch": 0.36, "learning_rate": 4.642601703547975e-05, "loss": 6.8567, "step": 16500 }, { "epoch": 0.37, "learning_rate": 4.6317865580094936e-05, "loss": 6.8268, "step": 17000 }, { "epoch": 0.38, "learning_rate": 4.6209497388326575e-05, "loss": 6.7758, "step": 17500 }, { "epoch": 0.39, "learning_rate": 4.610112919655823e-05, "loss": 6.7915, "step": 18000 }, { "epoch": 0.4, "learning_rate": 4.5992761004789874e-05, "loss": 6.7391, "step": 18500 }, { "epoch": 0.41, "learning_rate": 4.588439281302153e-05, "loss": 6.7204, "step": 19000 }, { "epoch": 0.42, "learning_rate": 4.5776024621253173e-05, "loss": 6.6562, "step": 19500 }, { "epoch": 0.43, "learning_rate": 4.566765642948482e-05, "loss": 6.6638, "step": 20000 }, { "epoch": 0.44, "learning_rate": 4.5559288237716466e-05, "loss": 6.6292, "step": 20500 }, { "epoch": 0.46, "learning_rate": 4.545092004594811e-05, "loss": 6.6086, "step": 21000 }, { "epoch": 0.47, "learning_rate": 4.5342551854179765e-05, "loss": 6.5568, "step": 21500 }, { "epoch": 0.48, "learning_rate": 4.523418366241141e-05, "loss": 6.5345, "step": 22000 }, { "epoch": 0.49, "learning_rate": 4.512581547064306e-05, "loss": 6.556, "step": 22500 }, { "epoch": 0.5, "learning_rate": 4.501744727887471e-05, "loss": 6.5297, "step": 23000 }, { "epoch": 0.51, "learning_rate": 4.490907908710636e-05, "loss": 6.4959, "step": 23500 }, { "epoch": 0.52, "learning_rate": 4.4800710895338e-05, "loss": 6.4772, "step": 24000 }, { "epoch": 0.53, "learning_rate": 4.469255943995318e-05, "loss": 6.4633, "step": 24500 }, { "epoch": 0.54, "learning_rate": 4.4584191248184836e-05, "loss": 6.4274, "step": 25000 }, { "epoch": 0.55, "learning_rate": 4.447582305641648e-05, "loss": 6.4137, "step": 25500 }, { "epoch": 0.56, "learning_rate": 4.436745486464813e-05, "loss": 6.3865, "step": 26000 }, { "epoch": 0.57, "learning_rate": 4.4259303409263314e-05, "loss": 6.4233, "step": 26500 }, { "epoch": 0.59, "learning_rate": 4.415093521749497e-05, "loss": 6.3557, "step": 27000 }, { "epoch": 0.6, "learning_rate": 4.404278376211015e-05, "loss": 6.3371, "step": 27500 }, { "epoch": 0.61, "learning_rate": 4.39344155703418e-05, "loss": 6.3477, "step": 28000 }, { "epoch": 0.62, "learning_rate": 4.382604737857344e-05, "loss": 6.3256, "step": 28500 }, { "epoch": 0.63, "learning_rate": 4.3717679186805086e-05, "loss": 6.3146, "step": 29000 }, { "epoch": 0.64, "learning_rate": 4.360931099503674e-05, "loss": 6.2812, "step": 29500 }, { "epoch": 0.65, "learning_rate": 4.3500942803268385e-05, "loss": 6.2653, "step": 30000 }, { "epoch": 0.66, "learning_rate": 4.339257461150004e-05, "loss": 6.2625, "step": 30500 }, { "epoch": 0.67, "learning_rate": 4.3284206419731684e-05, "loss": 6.2311, "step": 31000 }, { "epoch": 0.68, "learning_rate": 4.317583822796333e-05, "loss": 6.2153, "step": 31500 }, { "epoch": 0.69, "learning_rate": 4.306747003619498e-05, "loss": 6.2252, "step": 32000 }, { "epoch": 0.7, "learning_rate": 4.295910184442662e-05, "loss": 6.2012, "step": 32500 }, { "epoch": 0.72, "learning_rate": 4.2850733652658276e-05, "loss": 6.1814, "step": 33000 }, { "epoch": 0.73, "learning_rate": 4.274236546088992e-05, "loss": 6.1341, "step": 33500 }, { "epoch": 0.74, "learning_rate": 4.263399726912157e-05, "loss": 6.1333, "step": 34000 }, { "epoch": 0.75, "learning_rate": 4.252562907735322e-05, "loss": 6.137, "step": 34500 }, { "epoch": 0.76, "learning_rate": 4.241726088558486e-05, "loss": 6.1115, "step": 35000 }, { "epoch": 0.77, "learning_rate": 4.230932616658359e-05, "loss": 6.1138, "step": 35500 }, { "epoch": 0.78, "learning_rate": 4.2200957974815234e-05, "loss": 6.1054, "step": 36000 }, { "epoch": 0.79, "learning_rate": 4.209258978304688e-05, "loss": 6.0865, "step": 36500 }, { "epoch": 0.8, "learning_rate": 4.1984438327662066e-05, "loss": 6.0722, "step": 37000 }, { "epoch": 0.81, "learning_rate": 4.187607013589371e-05, "loss": 6.0801, "step": 37500 }, { "epoch": 0.82, "learning_rate": 4.1767701944125365e-05, "loss": 6.0378, "step": 38000 }, { "epoch": 0.83, "learning_rate": 4.165933375235701e-05, "loss": 6.0162, "step": 38500 }, { "epoch": 0.85, "learning_rate": 4.155096556058866e-05, "loss": 6.0366, "step": 39000 }, { "epoch": 0.86, "learning_rate": 4.1442597368820304e-05, "loss": 6.0294, "step": 39500 }, { "epoch": 0.87, "learning_rate": 4.133422917705195e-05, "loss": 6.0124, "step": 40000 }, { "epoch": 0.88, "learning_rate": 4.12258609852836e-05, "loss": 5.9881, "step": 40500 }, { "epoch": 0.89, "learning_rate": 4.111749279351525e-05, "loss": 5.9678, "step": 41000 }, { "epoch": 0.9, "learning_rate": 4.1009124601746896e-05, "loss": 5.9707, "step": 41500 }, { "epoch": 0.91, "learning_rate": 4.090097314636208e-05, "loss": 5.976, "step": 42000 }, { "epoch": 0.92, "learning_rate": 4.079260495459373e-05, "loss": 5.9419, "step": 42500 }, { "epoch": 0.93, "learning_rate": 4.0684453499208915e-05, "loss": 5.9158, "step": 43000 }, { "epoch": 0.94, "learning_rate": 4.057608530744057e-05, "loss": 5.9611, "step": 43500 }, { "epoch": 0.95, "learning_rate": 4.046771711567221e-05, "loss": 5.9104, "step": 44000 }, { "epoch": 0.96, "learning_rate": 4.035934892390385e-05, "loss": 5.914, "step": 44500 }, { "epoch": 0.98, "learning_rate": 4.0250980732135506e-05, "loss": 5.8819, "step": 45000 }, { "epoch": 0.99, "learning_rate": 4.014261254036715e-05, "loss": 5.891, "step": 45500 }, { "epoch": 1.0, "learning_rate": 4.0034244348598806e-05, "loss": 5.8627, "step": 46000 }, { "epoch": 1.01, "learning_rate": 3.992587615683045e-05, "loss": 5.8258, "step": 46500 }, { "epoch": 1.02, "learning_rate": 3.98175079650621e-05, "loss": 5.8346, "step": 47000 }, { "epoch": 1.03, "learning_rate": 3.970957324606082e-05, "loss": 5.8269, "step": 47500 }, { "epoch": 1.04, "learning_rate": 3.960120505429247e-05, "loss": 5.8253, "step": 48000 }, { "epoch": 1.05, "learning_rate": 3.949283686252411e-05, "loss": 5.8178, "step": 48500 }, { "epoch": 1.06, "learning_rate": 3.938446867075576e-05, "loss": 5.7758, "step": 49000 }, { "epoch": 1.07, "learning_rate": 3.927610047898741e-05, "loss": 5.7911, "step": 49500 }, { "epoch": 1.08, "learning_rate": 3.9167732287219056e-05, "loss": 5.7876, "step": 50000 }, { "epoch": 1.09, "learning_rate": 3.905936409545071e-05, "loss": 5.7695, "step": 50500 }, { "epoch": 1.11, "learning_rate": 3.895121264006589e-05, "loss": 5.7523, "step": 51000 }, { "epoch": 1.12, "learning_rate": 3.884284444829754e-05, "loss": 5.7571, "step": 51500 }, { "epoch": 1.13, "learning_rate": 3.873447625652919e-05, "loss": 5.7947, "step": 52000 }, { "epoch": 1.14, "learning_rate": 3.8626108064760834e-05, "loss": 5.7286, "step": 52500 }, { "epoch": 1.15, "learning_rate": 3.851773987299248e-05, "loss": 5.7481, "step": 53000 }, { "epoch": 1.16, "learning_rate": 3.8409371681224126e-05, "loss": 5.7334, "step": 53500 }, { "epoch": 1.17, "learning_rate": 3.830100348945578e-05, "loss": 5.7235, "step": 54000 }, { "epoch": 1.18, "learning_rate": 3.8192852034070965e-05, "loss": 5.6954, "step": 54500 }, { "epoch": 1.19, "learning_rate": 3.808448384230261e-05, "loss": 5.7148, "step": 55000 }, { "epoch": 1.2, "learning_rate": 3.797611565053426e-05, "loss": 5.6986, "step": 55500 }, { "epoch": 1.21, "learning_rate": 3.7867747458765904e-05, "loss": 5.693, "step": 56000 }, { "epoch": 1.22, "learning_rate": 3.775937926699755e-05, "loss": 5.6841, "step": 56500 }, { "epoch": 1.24, "learning_rate": 3.7651011075229197e-05, "loss": 5.6561, "step": 57000 }, { "epoch": 1.25, "learning_rate": 3.754264288346085e-05, "loss": 5.634, "step": 57500 }, { "epoch": 1.26, "learning_rate": 3.7434274691692496e-05, "loss": 5.641, "step": 58000 }, { "epoch": 1.27, "learning_rate": 3.732612323630768e-05, "loss": 5.6495, "step": 58500 }, { "epoch": 1.28, "learning_rate": 3.721775504453933e-05, "loss": 5.6402, "step": 59000 }, { "epoch": 1.29, "learning_rate": 3.7109386852770975e-05, "loss": 5.5963, "step": 59500 }, { "epoch": 1.3, "learning_rate": 3.700101866100262e-05, "loss": 5.6276, "step": 60000 }, { "epoch": 1.31, "learning_rate": 3.6892650469234274e-05, "loss": 5.6346, "step": 60500 }, { "epoch": 1.32, "learning_rate": 3.678428227746592e-05, "loss": 5.6149, "step": 61000 }, { "epoch": 1.33, "learning_rate": 3.6676130822081106e-05, "loss": 5.5947, "step": 61500 }, { "epoch": 1.34, "learning_rate": 3.656776263031275e-05, "loss": 5.5881, "step": 62000 }, { "epoch": 1.35, "learning_rate": 3.64593944385444e-05, "loss": 5.5827, "step": 62500 }, { "epoch": 1.37, "learning_rate": 3.635102624677605e-05, "loss": 5.5667, "step": 63000 }, { "epoch": 1.38, "learning_rate": 3.624265805500769e-05, "loss": 5.5804, "step": 63500 }, { "epoch": 1.39, "learning_rate": 3.6134289863239344e-05, "loss": 5.5845, "step": 64000 }, { "epoch": 1.4, "learning_rate": 3.602592167147099e-05, "loss": 5.5827, "step": 64500 }, { "epoch": 1.41, "learning_rate": 3.591755347970264e-05, "loss": 5.5525, "step": 65000 }, { "epoch": 1.42, "learning_rate": 3.580918528793429e-05, "loss": 5.5575, "step": 65500 }, { "epoch": 1.43, "learning_rate": 3.5700817096165936e-05, "loss": 5.5406, "step": 66000 }, { "epoch": 1.44, "learning_rate": 3.559266564078112e-05, "loss": 5.5457, "step": 66500 }, { "epoch": 1.45, "learning_rate": 3.548429744901277e-05, "loss": 5.5298, "step": 67000 }, { "epoch": 1.46, "learning_rate": 3.5375929257244415e-05, "loss": 5.5226, "step": 67500 }, { "epoch": 1.47, "learning_rate": 3.526756106547606e-05, "loss": 5.4872, "step": 68000 }, { "epoch": 1.48, "learning_rate": 3.5159192873707714e-05, "loss": 5.496, "step": 68500 }, { "epoch": 1.5, "learning_rate": 3.5051041418322894e-05, "loss": 5.4846, "step": 69000 }, { "epoch": 1.51, "learning_rate": 3.494267322655455e-05, "loss": 5.494, "step": 69500 }, { "epoch": 1.52, "learning_rate": 3.483430503478619e-05, "loss": 5.4753, "step": 70000 }, { "epoch": 1.53, "learning_rate": 3.472593684301784e-05, "loss": 5.5017, "step": 70500 }, { "epoch": 1.54, "learning_rate": 3.4618002124016566e-05, "loss": 5.489, "step": 71000 }, { "epoch": 1.55, "learning_rate": 3.450963393224821e-05, "loss": 5.4613, "step": 71500 }, { "epoch": 1.56, "learning_rate": 3.440126574047985e-05, "loss": 5.4371, "step": 72000 }, { "epoch": 1.57, "learning_rate": 3.4292897548711504e-05, "loss": 5.4453, "step": 72500 }, { "epoch": 1.58, "learning_rate": 3.418452935694315e-05, "loss": 5.4485, "step": 73000 }, { "epoch": 1.59, "learning_rate": 3.40761611651748e-05, "loss": 5.4734, "step": 73500 }, { "epoch": 1.6, "learning_rate": 3.396779297340645e-05, "loss": 5.4371, "step": 74000 }, { "epoch": 1.61, "learning_rate": 3.3859641518021636e-05, "loss": 5.4367, "step": 74500 }, { "epoch": 1.63, "learning_rate": 3.375127332625328e-05, "loss": 5.4137, "step": 75000 }, { "epoch": 1.64, "learning_rate": 3.364290513448493e-05, "loss": 5.4397, "step": 75500 }, { "epoch": 1.65, "learning_rate": 3.3534536942716575e-05, "loss": 5.4075, "step": 76000 }, { "epoch": 1.66, "learning_rate": 3.342616875094822e-05, "loss": 5.426, "step": 76500 }, { "epoch": 1.67, "learning_rate": 3.3317800559179874e-05, "loss": 5.4072, "step": 77000 }, { "epoch": 1.68, "learning_rate": 3.320943236741152e-05, "loss": 5.3822, "step": 77500 }, { "epoch": 1.69, "learning_rate": 3.3101064175643166e-05, "loss": 5.3867, "step": 78000 }, { "epoch": 1.7, "learning_rate": 3.299291272025835e-05, "loss": 5.4032, "step": 78500 }, { "epoch": 1.71, "learning_rate": 3.288454452849e-05, "loss": 5.3875, "step": 79000 }, { "epoch": 1.72, "learning_rate": 3.2776176336721645e-05, "loss": 5.382, "step": 79500 }, { "epoch": 1.73, "learning_rate": 3.266802488133683e-05, "loss": 5.3784, "step": 80000 }, { "epoch": 1.74, "learning_rate": 3.255965668956848e-05, "loss": 5.3607, "step": 80500 }, { "epoch": 1.76, "learning_rate": 3.2451288497800124e-05, "loss": 5.3523, "step": 81000 }, { "epoch": 1.77, "learning_rate": 3.234292030603178e-05, "loss": 5.3397, "step": 81500 }, { "epoch": 1.78, "learning_rate": 3.223455211426342e-05, "loss": 5.3615, "step": 82000 }, { "epoch": 1.79, "learning_rate": 3.2126183922495076e-05, "loss": 5.3337, "step": 82500 }, { "epoch": 1.8, "learning_rate": 3.2017815730726716e-05, "loss": 5.3297, "step": 83000 }, { "epoch": 1.81, "learning_rate": 3.190944753895836e-05, "loss": 5.3278, "step": 83500 }, { "epoch": 1.82, "learning_rate": 3.1801079347190015e-05, "loss": 5.3225, "step": 84000 }, { "epoch": 1.83, "learning_rate": 3.1692927891805194e-05, "loss": 5.3084, "step": 84500 }, { "epoch": 1.84, "learning_rate": 3.158477643642038e-05, "loss": 5.3226, "step": 85000 }, { "epoch": 1.85, "learning_rate": 3.1476408244652034e-05, "loss": 5.3311, "step": 85500 }, { "epoch": 1.86, "learning_rate": 3.136804005288368e-05, "loss": 5.3289, "step": 86000 }, { "epoch": 1.87, "learning_rate": 3.1259671861115326e-05, "loss": 5.3217, "step": 86500 }, { "epoch": 1.89, "learning_rate": 3.115152040573051e-05, "loss": 5.3092, "step": 87000 }, { "epoch": 1.9, "learning_rate": 3.104315221396216e-05, "loss": 5.3042, "step": 87500 }, { "epoch": 1.91, "learning_rate": 3.0934784022193805e-05, "loss": 5.3147, "step": 88000 }, { "epoch": 1.92, "learning_rate": 3.082641583042545e-05, "loss": 5.2633, "step": 88500 }, { "epoch": 1.93, "learning_rate": 3.0718047638657104e-05, "loss": 5.2619, "step": 89000 }, { "epoch": 1.94, "learning_rate": 3.0609896183272284e-05, "loss": 5.3033, "step": 89500 }, { "epoch": 1.95, "learning_rate": 3.0501527991503937e-05, "loss": 5.2377, "step": 90000 }, { "epoch": 1.96, "learning_rate": 3.0393159799735583e-05, "loss": 5.266, "step": 90500 }, { "epoch": 1.97, "learning_rate": 3.0284791607967233e-05, "loss": 5.2726, "step": 91000 }, { "epoch": 1.98, "learning_rate": 3.017642341619888e-05, "loss": 5.2806, "step": 91500 }, { "epoch": 1.99, "learning_rate": 3.0068271960814065e-05, "loss": 5.2758, "step": 92000 }, { "epoch": 2.0, "learning_rate": 2.995990376904571e-05, "loss": 5.2737, "step": 92500 }, { "epoch": 2.02, "learning_rate": 2.9851535577277358e-05, "loss": 5.2566, "step": 93000 }, { "epoch": 2.03, "learning_rate": 2.9743384121892544e-05, "loss": 5.2196, "step": 93500 }, { "epoch": 2.04, "learning_rate": 2.9635015930124194e-05, "loss": 5.2356, "step": 94000 }, { "epoch": 2.05, "learning_rate": 2.952664773835584e-05, "loss": 5.2116, "step": 94500 }, { "epoch": 2.06, "learning_rate": 2.9418279546587486e-05, "loss": 5.235, "step": 95000 }, { "epoch": 2.07, "learning_rate": 2.9309911354819136e-05, "loss": 5.2186, "step": 95500 }, { "epoch": 2.08, "learning_rate": 2.9201543163050782e-05, "loss": 5.2145, "step": 96000 }, { "epoch": 2.09, "learning_rate": 2.909317497128243e-05, "loss": 5.1935, "step": 96500 }, { "epoch": 2.1, "learning_rate": 2.8984806779514078e-05, "loss": 5.2145, "step": 97000 }, { "epoch": 2.11, "learning_rate": 2.8876438587745724e-05, "loss": 5.2262, "step": 97500 }, { "epoch": 2.12, "learning_rate": 2.876828713236091e-05, "loss": 5.211, "step": 98000 }, { "epoch": 2.13, "learning_rate": 2.8659918940592557e-05, "loss": 5.1676, "step": 98500 }, { "epoch": 2.15, "learning_rate": 2.8551550748824206e-05, "loss": 5.1791, "step": 99000 }, { "epoch": 2.16, "learning_rate": 2.8443182557055852e-05, "loss": 5.1993, "step": 99500 }, { "epoch": 2.17, "learning_rate": 2.833503110167104e-05, "loss": 5.1698, "step": 100000 }, { "epoch": 2.18, "learning_rate": 2.8226662909902685e-05, "loss": 5.1661, "step": 100500 }, { "epoch": 2.19, "learning_rate": 2.8118294718134335e-05, "loss": 5.1772, "step": 101000 }, { "epoch": 2.2, "learning_rate": 2.800992652636598e-05, "loss": 5.1629, "step": 101500 }, { "epoch": 2.21, "learning_rate": 2.7901558334597634e-05, "loss": 5.1636, "step": 102000 }, { "epoch": 2.22, "learning_rate": 2.7793406879212813e-05, "loss": 5.1611, "step": 102500 }, { "epoch": 2.23, "learning_rate": 2.7685038687444463e-05, "loss": 5.172, "step": 103000 }, { "epoch": 2.24, "learning_rate": 2.757667049567611e-05, "loss": 5.1525, "step": 103500 }, { "epoch": 2.25, "learning_rate": 2.7468302303907756e-05, "loss": 5.1161, "step": 104000 }, { "epoch": 2.26, "learning_rate": 2.735993411213941e-05, "loss": 5.159, "step": 104500 }, { "epoch": 2.28, "learning_rate": 2.725178265675459e-05, "loss": 5.1327, "step": 105000 }, { "epoch": 2.29, "learning_rate": 2.7143414464986238e-05, "loss": 5.1263, "step": 105500 }, { "epoch": 2.3, "learning_rate": 2.7035046273217884e-05, "loss": 5.1287, "step": 106000 }, { "epoch": 2.31, "learning_rate": 2.6926678081449537e-05, "loss": 5.1209, "step": 106500 }, { "epoch": 2.32, "learning_rate": 2.681830988968118e-05, "loss": 5.1138, "step": 107000 }, { "epoch": 2.33, "learning_rate": 2.6709941697912833e-05, "loss": 5.1045, "step": 107500 }, { "epoch": 2.34, "learning_rate": 2.660157350614448e-05, "loss": 5.1258, "step": 108000 }, { "epoch": 2.35, "learning_rate": 2.6493205314376125e-05, "loss": 5.1379, "step": 108500 }, { "epoch": 2.36, "learning_rate": 2.6384837122607775e-05, "loss": 5.0773, "step": 109000 }, { "epoch": 2.37, "learning_rate": 2.6276685667222954e-05, "loss": 5.1031, "step": 109500 }, { "epoch": 2.38, "learning_rate": 2.6168317475454607e-05, "loss": 5.0969, "step": 110000 }, { "epoch": 2.39, "learning_rate": 2.6059949283686254e-05, "loss": 5.0868, "step": 110500 }, { "epoch": 2.41, "learning_rate": 2.5951581091917903e-05, "loss": 5.0737, "step": 111000 }, { "epoch": 2.42, "learning_rate": 2.5843429636533083e-05, "loss": 5.0793, "step": 111500 }, { "epoch": 2.43, "learning_rate": 2.5735061444764736e-05, "loss": 5.0712, "step": 112000 }, { "epoch": 2.44, "learning_rate": 2.5626693252996382e-05, "loss": 5.0871, "step": 112500 }, { "epoch": 2.45, "learning_rate": 2.5518325061228032e-05, "loss": 5.064, "step": 113000 }, { "epoch": 2.46, "learning_rate": 2.5409956869459678e-05, "loss": 5.0995, "step": 113500 }, { "epoch": 2.47, "learning_rate": 2.5301588677691324e-05, "loss": 5.0805, "step": 114000 }, { "epoch": 2.48, "learning_rate": 2.5193220485922974e-05, "loss": 5.0899, "step": 114500 }, { "epoch": 2.49, "learning_rate": 2.508485229415462e-05, "loss": 5.0422, "step": 115000 }, { "epoch": 2.5, "learning_rate": 2.4976700838769806e-05, "loss": 5.0442, "step": 115500 }, { "epoch": 2.51, "learning_rate": 2.4868332647001453e-05, "loss": 5.0505, "step": 116000 }, { "epoch": 2.52, "learning_rate": 2.4759964455233102e-05, "loss": 5.0718, "step": 116500 }, { "epoch": 2.54, "learning_rate": 2.4651812999848285e-05, "loss": 5.0682, "step": 117000 }, { "epoch": 2.55, "learning_rate": 2.454344480807993e-05, "loss": 5.0645, "step": 117500 }, { "epoch": 2.56, "learning_rate": 2.443507661631158e-05, "loss": 5.0679, "step": 118000 }, { "epoch": 2.57, "learning_rate": 2.432670842454323e-05, "loss": 5.0509, "step": 118500 }, { "epoch": 2.58, "learning_rate": 2.4218340232774877e-05, "loss": 5.0678, "step": 119000 }, { "epoch": 2.59, "learning_rate": 2.4109972041006526e-05, "loss": 5.0296, "step": 119500 }, { "epoch": 2.6, "learning_rate": 2.4001603849238173e-05, "loss": 5.0411, "step": 120000 }, { "epoch": 2.61, "learning_rate": 2.389323565746982e-05, "loss": 5.0054, "step": 120500 }, { "epoch": 2.62, "learning_rate": 2.378486746570147e-05, "loss": 5.0269, "step": 121000 }, { "epoch": 2.63, "learning_rate": 2.367671601031665e-05, "loss": 5.0299, "step": 121500 }, { "epoch": 2.64, "learning_rate": 2.35683478185483e-05, "loss": 5.0179, "step": 122000 }, { "epoch": 2.66, "learning_rate": 2.3460196363163487e-05, "loss": 5.0287, "step": 122500 }, { "epoch": 2.67, "learning_rate": 2.3351828171395134e-05, "loss": 5.0147, "step": 123000 }, { "epoch": 2.68, "learning_rate": 2.324345997962678e-05, "loss": 5.0182, "step": 123500 }, { "epoch": 2.69, "learning_rate": 2.313509178785843e-05, "loss": 4.9981, "step": 124000 }, { "epoch": 2.7, "learning_rate": 2.3026723596090076e-05, "loss": 4.9984, "step": 124500 }, { "epoch": 2.71, "learning_rate": 2.2918355404321725e-05, "loss": 4.9986, "step": 125000 }, { "epoch": 2.72, "learning_rate": 2.280998721255337e-05, "loss": 4.9822, "step": 125500 }, { "epoch": 2.73, "learning_rate": 2.270161902078502e-05, "loss": 4.9897, "step": 126000 }, { "epoch": 2.74, "learning_rate": 2.2593467565400208e-05, "loss": 5.0029, "step": 126500 }, { "epoch": 2.75, "learning_rate": 2.248531611001539e-05, "loss": 4.9913, "step": 127000 }, { "epoch": 2.76, "learning_rate": 2.2376947918247037e-05, "loss": 4.9867, "step": 127500 }, { "epoch": 2.77, "learning_rate": 2.2268579726478686e-05, "loss": 4.9702, "step": 128000 }, { "epoch": 2.79, "learning_rate": 2.2160211534710333e-05, "loss": 5.0042, "step": 128500 }, { "epoch": 2.8, "learning_rate": 2.205184334294198e-05, "loss": 4.9958, "step": 129000 }, { "epoch": 2.81, "learning_rate": 2.1943691887557165e-05, "loss": 4.969, "step": 129500 }, { "epoch": 2.82, "learning_rate": 2.183532369578881e-05, "loss": 4.9888, "step": 130000 }, { "epoch": 2.83, "learning_rate": 2.172695550402046e-05, "loss": 4.9643, "step": 130500 }, { "epoch": 2.84, "learning_rate": 2.1618804048635647e-05, "loss": 4.9661, "step": 131000 }, { "epoch": 2.85, "learning_rate": 2.1510435856867294e-05, "loss": 4.9511, "step": 131500 }, { "epoch": 2.86, "learning_rate": 2.140206766509894e-05, "loss": 4.9586, "step": 132000 }, { "epoch": 2.87, "learning_rate": 2.129369947333059e-05, "loss": 4.9791, "step": 132500 }, { "epoch": 2.88, "learning_rate": 2.118533128156224e-05, "loss": 4.9457, "step": 133000 }, { "epoch": 2.89, "learning_rate": 2.1076963089793885e-05, "loss": 4.9577, "step": 133500 }, { "epoch": 2.9, "learning_rate": 2.096859489802553e-05, "loss": 4.9646, "step": 134000 }, { "epoch": 2.92, "learning_rate": 2.086022670625718e-05, "loss": 4.9457, "step": 134500 }, { "epoch": 2.93, "learning_rate": 2.0751858514488827e-05, "loss": 4.9405, "step": 135000 }, { "epoch": 2.94, "learning_rate": 2.064370705910401e-05, "loss": 4.9576, "step": 135500 }, { "epoch": 2.95, "learning_rate": 2.053533886733566e-05, "loss": 4.9494, "step": 136000 }, { "epoch": 2.96, "learning_rate": 2.042697067556731e-05, "loss": 4.9348, "step": 136500 }, { "epoch": 2.97, "learning_rate": 2.0318819220182492e-05, "loss": 4.938, "step": 137000 }, { "epoch": 2.98, "learning_rate": 2.021045102841414e-05, "loss": 4.9657, "step": 137500 }, { "epoch": 2.99, "learning_rate": 2.0102082836645788e-05, "loss": 4.9181, "step": 138000 }, { "epoch": 3.0, "learning_rate": 1.9993714644877438e-05, "loss": 4.9687, "step": 138500 }, { "epoch": 3.01, "learning_rate": 1.9885346453109084e-05, "loss": 4.9063, "step": 139000 }, { "epoch": 3.02, "learning_rate": 1.977697826134073e-05, "loss": 4.9311, "step": 139500 }, { "epoch": 3.03, "learning_rate": 1.966861006957238e-05, "loss": 4.887, "step": 140000 }, { "epoch": 3.05, "learning_rate": 1.956024187780403e-05, "loss": 4.9098, "step": 140500 }, { "epoch": 3.06, "learning_rate": 1.9451873686035676e-05, "loss": 4.8869, "step": 141000 }, { "epoch": 3.07, "learning_rate": 1.9343505494267325e-05, "loss": 4.9259, "step": 141500 }, { "epoch": 3.08, "learning_rate": 1.9235137302498972e-05, "loss": 4.8914, "step": 142000 }, { "epoch": 3.09, "learning_rate": 1.9126769110730618e-05, "loss": 4.8805, "step": 142500 }, { "epoch": 3.1, "learning_rate": 1.9018617655345804e-05, "loss": 4.8959, "step": 143000 }, { "epoch": 3.11, "learning_rate": 1.891024946357745e-05, "loss": 4.9006, "step": 143500 }, { "epoch": 3.12, "learning_rate": 1.8802098008192637e-05, "loss": 4.8775, "step": 144000 }, { "epoch": 3.13, "learning_rate": 1.8693729816424286e-05, "loss": 4.8962, "step": 144500 }, { "epoch": 3.14, "learning_rate": 1.858536162465593e-05, "loss": 4.8837, "step": 145000 }, { "epoch": 3.15, "learning_rate": 1.847699343288758e-05, "loss": 4.8987, "step": 145500 }, { "epoch": 3.16, "learning_rate": 1.836862524111923e-05, "loss": 4.8875, "step": 146000 }, { "epoch": 3.18, "learning_rate": 1.8260257049350875e-05, "loss": 4.8839, "step": 146500 }, { "epoch": 3.19, "learning_rate": 1.815188885758252e-05, "loss": 4.8876, "step": 147000 }, { "epoch": 3.2, "learning_rate": 1.804352066581417e-05, "loss": 4.9015, "step": 147500 }, { "epoch": 3.21, "learning_rate": 1.793515247404582e-05, "loss": 4.8669, "step": 148000 }, { "epoch": 3.22, "learning_rate": 1.782721775504454e-05, "loss": 4.9037, "step": 148500 }, { "epoch": 3.23, "learning_rate": 1.771884956327619e-05, "loss": 4.8772, "step": 149000 }, { "epoch": 3.24, "learning_rate": 1.7610481371507836e-05, "loss": 4.8542, "step": 149500 }, { "epoch": 3.25, "learning_rate": 1.7502113179739485e-05, "loss": 4.8429, "step": 150000 }, { "epoch": 3.26, "learning_rate": 1.7393961724354668e-05, "loss": 4.8799, "step": 150500 }, { "epoch": 3.27, "learning_rate": 1.7285593532586318e-05, "loss": 4.8603, "step": 151000 }, { "epoch": 3.28, "learning_rate": 1.7177225340817964e-05, "loss": 4.8515, "step": 151500 }, { "epoch": 3.29, "learning_rate": 1.706885714904961e-05, "loss": 4.8639, "step": 152000 }, { "epoch": 3.31, "learning_rate": 1.696048895728126e-05, "loss": 4.8507, "step": 152500 }, { "epoch": 3.32, "learning_rate": 1.6852120765512906e-05, "loss": 4.8426, "step": 153000 }, { "epoch": 3.33, "learning_rate": 1.6743752573744556e-05, "loss": 4.8277, "step": 153500 }, { "epoch": 3.34, "learning_rate": 1.6635384381976205e-05, "loss": 4.8831, "step": 154000 }, { "epoch": 3.35, "learning_rate": 1.6527016190207852e-05, "loss": 4.8377, "step": 154500 }, { "epoch": 3.36, "learning_rate": 1.6418647998439498e-05, "loss": 4.8549, "step": 155000 }, { "epoch": 3.37, "learning_rate": 1.6310279806671148e-05, "loss": 4.8403, "step": 155500 }, { "epoch": 3.38, "learning_rate": 1.6201911614902797e-05, "loss": 4.8526, "step": 156000 }, { "epoch": 3.39, "learning_rate": 1.609354342313444e-05, "loss": 4.8472, "step": 156500 }, { "epoch": 3.4, "learning_rate": 1.5985391967749626e-05, "loss": 4.8356, "step": 157000 }, { "epoch": 3.41, "learning_rate": 1.5877023775981276e-05, "loss": 4.8552, "step": 157500 }, { "epoch": 3.42, "learning_rate": 1.5768655584212922e-05, "loss": 4.8528, "step": 158000 }, { "epoch": 3.44, "learning_rate": 1.566028739244457e-05, "loss": 4.8505, "step": 158500 }, { "epoch": 3.45, "learning_rate": 1.5552135937059755e-05, "loss": 4.8677, "step": 159000 }, { "epoch": 3.46, "learning_rate": 1.54437677452914e-05, "loss": 4.844, "step": 159500 }, { "epoch": 3.47, "learning_rate": 1.533539955352305e-05, "loss": 4.8299, "step": 160000 }, { "epoch": 3.48, "learning_rate": 1.5227248098138235e-05, "loss": 4.8197, "step": 160500 }, { "epoch": 3.49, "learning_rate": 1.5118879906369885e-05, "loss": 4.8289, "step": 161000 }, { "epoch": 3.5, "learning_rate": 1.501051171460153e-05, "loss": 4.8317, "step": 161500 }, { "epoch": 3.51, "learning_rate": 1.4902360259216716e-05, "loss": 4.8262, "step": 162000 }, { "epoch": 3.52, "learning_rate": 1.4793992067448365e-05, "loss": 4.8332, "step": 162500 }, { "epoch": 3.53, "learning_rate": 1.468562387568001e-05, "loss": 4.8332, "step": 163000 }, { "epoch": 3.54, "learning_rate": 1.457725568391166e-05, "loss": 4.839, "step": 163500 }, { "epoch": 3.55, "learning_rate": 1.4468887492143307e-05, "loss": 4.8062, "step": 164000 }, { "epoch": 3.57, "learning_rate": 1.4360519300374955e-05, "loss": 4.8388, "step": 164500 }, { "epoch": 3.58, "learning_rate": 1.4252151108606602e-05, "loss": 4.7874, "step": 165000 }, { "epoch": 3.59, "learning_rate": 1.414378291683825e-05, "loss": 4.8314, "step": 165500 }, { "epoch": 3.6, "learning_rate": 1.4035414725069897e-05, "loss": 4.8281, "step": 166000 }, { "epoch": 3.61, "learning_rate": 1.3927046533301547e-05, "loss": 4.805, "step": 166500 }, { "epoch": 3.62, "learning_rate": 1.3818678341533195e-05, "loss": 4.8146, "step": 167000 }, { "epoch": 3.63, "learning_rate": 1.3710310149764841e-05, "loss": 4.8093, "step": 167500 }, { "epoch": 3.64, "learning_rate": 1.360194195799649e-05, "loss": 4.8045, "step": 168000 }, { "epoch": 3.65, "learning_rate": 1.3493790502611675e-05, "loss": 4.812, "step": 168500 }, { "epoch": 3.66, "learning_rate": 1.338542231084332e-05, "loss": 4.8153, "step": 169000 }, { "epoch": 3.67, "learning_rate": 1.327705411907497e-05, "loss": 4.7973, "step": 169500 }, { "epoch": 3.68, "learning_rate": 1.3168685927306618e-05, "loss": 4.7848, "step": 170000 }, { "epoch": 3.7, "learning_rate": 1.3060317735538265e-05, "loss": 4.7788, "step": 170500 }, { "epoch": 3.71, "learning_rate": 1.2951949543769915e-05, "loss": 4.7904, "step": 171000 }, { "epoch": 3.72, "learning_rate": 1.284358135200156e-05, "loss": 4.8071, "step": 171500 }, { "epoch": 3.73, "learning_rate": 1.273521316023321e-05, "loss": 4.7705, "step": 172000 }, { "epoch": 3.74, "learning_rate": 1.2627061704848394e-05, "loss": 4.7761, "step": 172500 }, { "epoch": 3.75, "learning_rate": 1.251869351308004e-05, "loss": 4.7745, "step": 173000 }, { "epoch": 3.76, "learning_rate": 1.2410325321311688e-05, "loss": 4.8037, "step": 173500 }, { "epoch": 3.77, "learning_rate": 1.2301957129543338e-05, "loss": 4.7899, "step": 174000 }, { "epoch": 3.78, "learning_rate": 1.2193805674158522e-05, "loss": 4.7707, "step": 174500 }, { "epoch": 3.79, "learning_rate": 1.2085437482390169e-05, "loss": 4.7628, "step": 175000 }, { "epoch": 3.8, "learning_rate": 1.1977069290621818e-05, "loss": 4.8077, "step": 175500 }, { "epoch": 3.81, "learning_rate": 1.1868701098853464e-05, "loss": 4.7716, "step": 176000 }, { "epoch": 3.83, "learning_rate": 1.1760549643468649e-05, "loss": 4.7809, "step": 176500 }, { "epoch": 3.84, "learning_rate": 1.1652181451700297e-05, "loss": 4.7824, "step": 177000 }, { "epoch": 3.85, "learning_rate": 1.1543813259931947e-05, "loss": 4.7673, "step": 177500 }, { "epoch": 3.86, "learning_rate": 1.1435445068163593e-05, "loss": 4.7763, "step": 178000 }, { "epoch": 3.87, "learning_rate": 1.132707687639524e-05, "loss": 4.7798, "step": 178500 }, { "epoch": 3.88, "learning_rate": 1.1218708684626889e-05, "loss": 4.7793, "step": 179000 }, { "epoch": 3.89, "learning_rate": 1.1110557229242073e-05, "loss": 4.7544, "step": 179500 }, { "epoch": 3.9, "learning_rate": 1.1002189037473721e-05, "loss": 4.7661, "step": 180000 }, { "epoch": 3.91, "learning_rate": 1.0893820845705369e-05, "loss": 4.7634, "step": 180500 }, { "epoch": 3.92, "learning_rate": 1.0785452653937017e-05, "loss": 4.784, "step": 181000 }, { "epoch": 3.93, "learning_rate": 1.0677084462168665e-05, "loss": 4.7577, "step": 181500 }, { "epoch": 3.94, "learning_rate": 1.0568716270400313e-05, "loss": 4.7507, "step": 182000 }, { "epoch": 3.96, "learning_rate": 1.0460348078631961e-05, "loss": 4.7365, "step": 182500 }, { "epoch": 3.97, "learning_rate": 1.0351979886863609e-05, "loss": 4.7678, "step": 183000 }, { "epoch": 3.98, "learning_rate": 1.0243828431478793e-05, "loss": 4.7701, "step": 183500 }, { "epoch": 3.99, "learning_rate": 1.0135460239710441e-05, "loss": 4.7522, "step": 184000 }, { "epoch": 4.0, "learning_rate": 1.0027092047942088e-05, "loss": 4.7454, "step": 184500 }, { "epoch": 4.01, "learning_rate": 9.918723856173737e-06, "loss": 4.7236, "step": 185000 }, { "epoch": 4.02, "learning_rate": 9.810355664405383e-06, "loss": 4.7409, "step": 185500 }, { "epoch": 4.03, "learning_rate": 9.701987472637031e-06, "loss": 4.74, "step": 186000 }, { "epoch": 4.04, "learning_rate": 9.593836017252216e-06, "loss": 4.7351, "step": 186500 }, { "epoch": 4.05, "learning_rate": 9.485467825483864e-06, "loss": 4.7128, "step": 187000 }, { "epoch": 4.06, "learning_rate": 9.377316370099049e-06, "loss": 4.7234, "step": 187500 }, { "epoch": 4.07, "learning_rate": 9.268948178330696e-06, "loss": 4.7467, "step": 188000 }, { "epoch": 4.09, "learning_rate": 9.160579986562344e-06, "loss": 4.7249, "step": 188500 }, { "epoch": 4.1, "learning_rate": 9.052211794793992e-06, "loss": 4.7212, "step": 189000 }, { "epoch": 4.11, "learning_rate": 8.94384360302564e-06, "loss": 4.7368, "step": 189500 }, { "epoch": 4.12, "learning_rate": 8.835475411257288e-06, "loss": 4.7173, "step": 190000 }, { "epoch": 4.13, "learning_rate": 8.727107219488936e-06, "loss": 4.748, "step": 190500 }, { "epoch": 4.14, "learning_rate": 8.618739027720584e-06, "loss": 4.7198, "step": 191000 }, { "epoch": 4.15, "learning_rate": 8.510370835952232e-06, "loss": 4.7166, "step": 191500 }, { "epoch": 4.16, "learning_rate": 8.402219380567417e-06, "loss": 4.7247, "step": 192000 }, { "epoch": 4.17, "learning_rate": 8.293851188799063e-06, "loss": 4.7295, "step": 192500 }, { "epoch": 4.18, "learning_rate": 8.185482997030712e-06, "loss": 4.7058, "step": 193000 }, { "epoch": 4.19, "learning_rate": 8.077114805262359e-06, "loss": 4.6972, "step": 193500 }, { "epoch": 4.2, "learning_rate": 7.968963349877543e-06, "loss": 4.7311, "step": 194000 }, { "epoch": 4.22, "learning_rate": 7.860595158109193e-06, "loss": 4.7356, "step": 194500 }, { "epoch": 4.23, "learning_rate": 7.752443702724378e-06, "loss": 4.7023, "step": 195000 }, { "epoch": 4.24, "learning_rate": 7.644292247339562e-06, "loss": 4.7178, "step": 195500 }, { "epoch": 4.25, "learning_rate": 7.535924055571208e-06, "loss": 4.7288, "step": 196000 }, { "epoch": 4.26, "learning_rate": 7.427555863802857e-06, "loss": 4.735, "step": 196500 }, { "epoch": 4.27, "learning_rate": 7.319187672034505e-06, "loss": 4.742, "step": 197000 }, { "epoch": 4.28, "learning_rate": 7.210819480266152e-06, "loss": 4.7199, "step": 197500 }, { "epoch": 4.29, "learning_rate": 7.102451288497801e-06, "loss": 4.7203, "step": 198000 }, { "epoch": 4.3, "learning_rate": 6.994083096729448e-06, "loss": 4.6962, "step": 198500 }, { "epoch": 4.31, "learning_rate": 6.885714904961097e-06, "loss": 4.7219, "step": 199000 }, { "epoch": 4.32, "learning_rate": 6.777563449576281e-06, "loss": 4.705, "step": 199500 }, { "epoch": 4.33, "learning_rate": 6.6691952578079285e-06, "loss": 4.7085, "step": 200000 }, { "epoch": 4.35, "learning_rate": 6.560827066039576e-06, "loss": 4.7082, "step": 200500 }, { "epoch": 4.36, "learning_rate": 6.4524588742712235e-06, "loss": 4.705, "step": 201000 }, { "epoch": 4.37, "learning_rate": 6.344090682502872e-06, "loss": 4.6962, "step": 201500 }, { "epoch": 4.38, "learning_rate": 6.235722490734519e-06, "loss": 4.706, "step": 202000 }, { "epoch": 4.39, "learning_rate": 6.127354298966167e-06, "loss": 4.7202, "step": 202500 }, { "epoch": 4.4, "learning_rate": 6.018986107197815e-06, "loss": 4.7005, "step": 203000 }, { "epoch": 4.41, "learning_rate": 5.910617915429464e-06, "loss": 4.701, "step": 203500 }, { "epoch": 4.42, "learning_rate": 5.802466460044648e-06, "loss": 4.6878, "step": 204000 }, { "epoch": 4.43, "learning_rate": 5.694098268276296e-06, "loss": 4.7178, "step": 204500 }, { "epoch": 4.44, "learning_rate": 5.585730076507944e-06, "loss": 4.6609, "step": 205000 }, { "epoch": 4.45, "learning_rate": 5.4773618847395916e-06, "loss": 4.7039, "step": 205500 }, { "epoch": 4.46, "learning_rate": 5.369210429354776e-06, "loss": 4.7098, "step": 206000 }, { "epoch": 4.48, "learning_rate": 5.260842237586424e-06, "loss": 4.7026, "step": 206500 }, { "epoch": 4.49, "learning_rate": 5.152474045818072e-06, "loss": 4.6955, "step": 207000 }, { "epoch": 4.5, "learning_rate": 5.044105854049719e-06, "loss": 4.7102, "step": 207500 }, { "epoch": 4.51, "learning_rate": 4.935737662281367e-06, "loss": 4.6803, "step": 208000 }, { "epoch": 4.52, "learning_rate": 4.827586206896552e-06, "loss": 4.7065, "step": 208500 }, { "epoch": 4.53, "learning_rate": 4.7192180151282e-06, "loss": 4.7135, "step": 209000 }, { "epoch": 4.54, "learning_rate": 4.6108498233598475e-06, "loss": 4.7195, "step": 209500 }, { "epoch": 4.55, "learning_rate": 4.5024816315914954e-06, "loss": 4.7074, "step": 210000 }, { "epoch": 4.56, "learning_rate": 4.39433017620668e-06, "loss": 4.6901, "step": 210500 }, { "epoch": 4.57, "learning_rate": 4.286178720821865e-06, "loss": 4.7073, "step": 211000 }, { "epoch": 4.58, "learning_rate": 4.177810529053512e-06, "loss": 4.7132, "step": 211500 }, { "epoch": 4.59, "learning_rate": 4.06944233728516e-06, "loss": 4.6883, "step": 212000 }, { "epoch": 4.61, "learning_rate": 3.9610741455168085e-06, "loss": 4.6894, "step": 212500 }, { "epoch": 4.62, "learning_rate": 3.852705953748456e-06, "loss": 4.6735, "step": 213000 }, { "epoch": 4.63, "learning_rate": 3.744337761980104e-06, "loss": 4.6991, "step": 213500 }, { "epoch": 4.64, "learning_rate": 3.6359695702117514e-06, "loss": 4.6894, "step": 214000 }, { "epoch": 4.65, "learning_rate": 3.5276013784433993e-06, "loss": 4.6913, "step": 214500 }, { "epoch": 4.66, "learning_rate": 3.4192331866750473e-06, "loss": 4.6822, "step": 215000 }, { "epoch": 4.67, "learning_rate": 3.3108649949066948e-06, "loss": 4.7032, "step": 215500 }, { "epoch": 4.68, "learning_rate": 3.2027135395218794e-06, "loss": 4.6878, "step": 216000 }, { "epoch": 4.69, "learning_rate": 3.0943453477535277e-06, "loss": 4.6907, "step": 216500 }, { "epoch": 4.7, "learning_rate": 2.9859771559851752e-06, "loss": 4.7031, "step": 217000 }, { "epoch": 4.71, "learning_rate": 2.877608964216823e-06, "loss": 4.6638, "step": 217500 }, { "epoch": 4.72, "learning_rate": 2.769240772448471e-06, "loss": 4.6622, "step": 218000 }, { "epoch": 4.74, "learning_rate": 2.6610893170636553e-06, "loss": 4.6783, "step": 218500 }, { "epoch": 4.75, "learning_rate": 2.5527211252953036e-06, "loss": 4.7027, "step": 219000 }, { "epoch": 4.76, "learning_rate": 2.444352933526951e-06, "loss": 4.6681, "step": 219500 }, { "epoch": 4.77, "learning_rate": 2.335984741758599e-06, "loss": 4.6985, "step": 220000 }, { "epoch": 4.78, "learning_rate": 2.2278332863737837e-06, "loss": 4.693, "step": 220500 }, { "epoch": 4.79, "learning_rate": 2.1196818309889683e-06, "loss": 4.6522, "step": 221000 }, { "epoch": 4.8, "learning_rate": 2.0113136392206162e-06, "loss": 4.6671, "step": 221500 }, { "epoch": 4.81, "learning_rate": 1.902945447452264e-06, "loss": 4.6676, "step": 222000 }, { "epoch": 4.82, "learning_rate": 1.7945772556839117e-06, "loss": 4.6786, "step": 222500 }, { "epoch": 4.83, "learning_rate": 1.6862090639155596e-06, "loss": 4.673, "step": 223000 }, { "epoch": 4.84, "learning_rate": 1.5778408721472075e-06, "loss": 4.6652, "step": 223500 }, { "epoch": 4.85, "learning_rate": 1.4694726803788553e-06, "loss": 4.666, "step": 224000 }, { "epoch": 4.87, "learning_rate": 1.3613212249940399e-06, "loss": 4.7056, "step": 224500 }, { "epoch": 4.88, "learning_rate": 1.2529530332256876e-06, "loss": 4.6693, "step": 225000 }, { "epoch": 4.89, "learning_rate": 1.1445848414573355e-06, "loss": 4.6729, "step": 225500 }, { "epoch": 4.9, "learning_rate": 1.0362166496889832e-06, "loss": 4.6815, "step": 226000 }, { "epoch": 4.91, "learning_rate": 9.278484579206312e-07, "loss": 4.6881, "step": 226500 }, { "epoch": 4.92, "learning_rate": 8.194802661522789e-07, "loss": 4.6657, "step": 227000 }, { "epoch": 4.93, "learning_rate": 7.111120743839268e-07, "loss": 4.6779, "step": 227500 }, { "epoch": 4.94, "learning_rate": 6.027438826155747e-07, "loss": 4.6812, "step": 228000 }, { "epoch": 4.95, "learning_rate": 4.943756908472226e-07, "loss": 4.6778, "step": 228500 }, { "epoch": 4.96, "learning_rate": 3.862242354624071e-07, "loss": 4.6756, "step": 229000 }, { "epoch": 4.97, "learning_rate": 2.778560436940549e-07, "loss": 4.673, "step": 229500 }, { "epoch": 4.98, "learning_rate": 1.6948785192570278e-07, "loss": 4.6745, "step": 230000 }, { "epoch": 5.0, "learning_rate": 6.111966015735062e-08, "loss": 4.6569, "step": 230500 }, { "epoch": 5.0, "step": 230695, "total_flos": 4.869967130385408e+17, "train_loss": 5.372212270862655, "train_runtime": 34970.0124, "train_samples_per_second": 52.775, "train_steps_per_second": 6.597 } ], "max_steps": 230695, "num_train_epochs": 5, "total_flos": 4.869967130385408e+17, "trial_name": null, "trial_params": null }