{ "best_metric": null, "best_model_checkpoint": null, "epoch": 6.0, "global_step": 73008, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04, "learning_rate": 4.965757177295639e-05, "loss": 3.431, "step": 500 }, { "epoch": 0.08, "learning_rate": 4.931514354591278e-05, "loss": 3.3117, "step": 1000 }, { "epoch": 0.12, "learning_rate": 4.8972715318869165e-05, "loss": 3.2778, "step": 1500 }, { "epoch": 0.16, "learning_rate": 4.863028709182555e-05, "loss": 3.2331, "step": 2000 }, { "epoch": 0.21, "learning_rate": 4.828785886478194e-05, "loss": 3.2122, "step": 2500 }, { "epoch": 0.25, "learning_rate": 4.794543063773833e-05, "loss": 3.1961, "step": 3000 }, { "epoch": 0.29, "learning_rate": 4.7603002410694716e-05, "loss": 3.1842, "step": 3500 }, { "epoch": 0.33, "learning_rate": 4.726057418365111e-05, "loss": 3.1603, "step": 4000 }, { "epoch": 0.37, "learning_rate": 4.69181459566075e-05, "loss": 3.147, "step": 4500 }, { "epoch": 0.41, "learning_rate": 4.6575717729563886e-05, "loss": 3.1572, "step": 5000 }, { "epoch": 0.45, "learning_rate": 4.623328950252027e-05, "loss": 3.1329, "step": 5500 }, { "epoch": 0.49, "learning_rate": 4.589086127547666e-05, "loss": 3.1132, "step": 6000 }, { "epoch": 0.53, "learning_rate": 4.554843304843305e-05, "loss": 3.1188, "step": 6500 }, { "epoch": 0.58, "learning_rate": 4.520600482138944e-05, "loss": 3.1141, "step": 7000 }, { "epoch": 0.62, "learning_rate": 4.486357659434583e-05, "loss": 3.1044, "step": 7500 }, { "epoch": 0.66, "learning_rate": 4.452114836730222e-05, "loss": 3.0998, "step": 8000 }, { "epoch": 0.7, "learning_rate": 4.4178720140258606e-05, "loss": 3.0963, "step": 8500 }, { "epoch": 0.74, "learning_rate": 4.3836291913214994e-05, "loss": 3.0978, "step": 9000 }, { "epoch": 0.78, "learning_rate": 4.349386368617138e-05, "loss": 3.0674, "step": 9500 }, { "epoch": 0.82, "learning_rate": 4.315143545912777e-05, "loss": 3.0855, "step": 10000 }, { "epoch": 0.86, "learning_rate": 4.2809007232084157e-05, "loss": 3.0664, "step": 10500 }, { "epoch": 0.9, "learning_rate": 4.2466579005040544e-05, "loss": 3.0678, "step": 11000 }, { "epoch": 0.95, "learning_rate": 4.212415077799693e-05, "loss": 3.0681, "step": 11500 }, { "epoch": 0.99, "learning_rate": 4.178172255095332e-05, "loss": 3.0565, "step": 12000 }, { "epoch": 1.03, "learning_rate": 4.1439294323909714e-05, "loss": 3.0114, "step": 12500 }, { "epoch": 1.07, "learning_rate": 4.10968660968661e-05, "loss": 2.9869, "step": 13000 }, { "epoch": 1.11, "learning_rate": 4.075443786982249e-05, "loss": 2.9743, "step": 13500 }, { "epoch": 1.15, "learning_rate": 4.041200964277888e-05, "loss": 2.9838, "step": 14000 }, { "epoch": 1.19, "learning_rate": 4.0069581415735264e-05, "loss": 2.9806, "step": 14500 }, { "epoch": 1.23, "learning_rate": 3.972715318869165e-05, "loss": 2.9715, "step": 15000 }, { "epoch": 1.27, "learning_rate": 3.938472496164804e-05, "loss": 2.9702, "step": 15500 }, { "epoch": 1.31, "learning_rate": 3.904229673460443e-05, "loss": 2.9667, "step": 16000 }, { "epoch": 1.36, "learning_rate": 3.8699868507560815e-05, "loss": 2.9737, "step": 16500 }, { "epoch": 1.4, "learning_rate": 3.83574402805172e-05, "loss": 2.9569, "step": 17000 }, { "epoch": 1.44, "learning_rate": 3.801501205347359e-05, "loss": 2.9759, "step": 17500 }, { "epoch": 1.48, "learning_rate": 3.767258382642998e-05, "loss": 2.9749, "step": 18000 }, { "epoch": 1.52, "learning_rate": 3.7330155599386366e-05, "loss": 2.9742, "step": 18500 }, { "epoch": 1.56, "learning_rate": 3.698772737234275e-05, "loss": 2.97, "step": 19000 }, { "epoch": 1.6, "learning_rate": 3.664529914529915e-05, "loss": 2.9551, "step": 19500 }, { "epoch": 1.64, "learning_rate": 3.6302870918255535e-05, "loss": 2.9464, "step": 20000 }, { "epoch": 1.68, "learning_rate": 3.596044269121192e-05, "loss": 2.9549, "step": 20500 }, { "epoch": 1.73, "learning_rate": 3.561801446416832e-05, "loss": 2.969, "step": 21000 }, { "epoch": 1.77, "learning_rate": 3.5275586237124705e-05, "loss": 2.9478, "step": 21500 }, { "epoch": 1.81, "learning_rate": 3.493315801008109e-05, "loss": 2.9568, "step": 22000 }, { "epoch": 1.85, "learning_rate": 3.459072978303748e-05, "loss": 2.9509, "step": 22500 }, { "epoch": 1.89, "learning_rate": 3.424830155599387e-05, "loss": 2.9484, "step": 23000 }, { "epoch": 1.93, "learning_rate": 3.3905873328950256e-05, "loss": 2.9646, "step": 23500 }, { "epoch": 1.97, "learning_rate": 3.356344510190664e-05, "loss": 2.9476, "step": 24000 }, { "epoch": 2.01, "learning_rate": 3.322101687486303e-05, "loss": 2.9165, "step": 24500 }, { "epoch": 2.05, "learning_rate": 3.287858864781942e-05, "loss": 2.8741, "step": 25000 }, { "epoch": 2.1, "learning_rate": 3.2536160420775806e-05, "loss": 2.8902, "step": 25500 }, { "epoch": 2.14, "learning_rate": 3.2193732193732194e-05, "loss": 2.8788, "step": 26000 }, { "epoch": 2.18, "learning_rate": 3.185130396668858e-05, "loss": 2.8775, "step": 26500 }, { "epoch": 2.22, "learning_rate": 3.150887573964497e-05, "loss": 2.885, "step": 27000 }, { "epoch": 2.26, "learning_rate": 3.116644751260136e-05, "loss": 2.8678, "step": 27500 }, { "epoch": 2.3, "learning_rate": 3.082401928555775e-05, "loss": 2.8771, "step": 28000 }, { "epoch": 2.34, "learning_rate": 3.0481591058514136e-05, "loss": 2.8873, "step": 28500 }, { "epoch": 2.38, "learning_rate": 3.0139162831470523e-05, "loss": 2.8768, "step": 29000 }, { "epoch": 2.42, "learning_rate": 2.979673460442691e-05, "loss": 2.8938, "step": 29500 }, { "epoch": 2.47, "learning_rate": 2.9454306377383302e-05, "loss": 2.8774, "step": 30000 }, { "epoch": 2.51, "learning_rate": 2.911187815033969e-05, "loss": 2.8761, "step": 30500 }, { "epoch": 2.55, "learning_rate": 2.8769449923296077e-05, "loss": 2.8824, "step": 31000 }, { "epoch": 2.59, "learning_rate": 2.8427021696252465e-05, "loss": 2.8737, "step": 31500 }, { "epoch": 2.63, "learning_rate": 2.8084593469208852e-05, "loss": 2.8802, "step": 32000 }, { "epoch": 2.67, "learning_rate": 2.774216524216524e-05, "loss": 2.8744, "step": 32500 }, { "epoch": 2.71, "learning_rate": 2.7399737015121628e-05, "loss": 2.8713, "step": 33000 }, { "epoch": 2.75, "learning_rate": 2.705730878807802e-05, "loss": 2.8822, "step": 33500 }, { "epoch": 2.79, "learning_rate": 2.671488056103441e-05, "loss": 2.8809, "step": 34000 }, { "epoch": 2.84, "learning_rate": 2.63724523339908e-05, "loss": 2.8694, "step": 34500 }, { "epoch": 2.88, "learning_rate": 2.603002410694719e-05, "loss": 2.8723, "step": 35000 }, { "epoch": 2.92, "learning_rate": 2.5687595879903576e-05, "loss": 2.8734, "step": 35500 }, { "epoch": 2.96, "learning_rate": 2.5345167652859964e-05, "loss": 2.8757, "step": 36000 }, { "epoch": 3.0, "learning_rate": 2.500273942581635e-05, "loss": 2.8737, "step": 36500 }, { "epoch": 3.04, "learning_rate": 2.466031119877274e-05, "loss": 2.8095, "step": 37000 }, { "epoch": 3.08, "learning_rate": 2.4317882971729127e-05, "loss": 2.8181, "step": 37500 }, { "epoch": 3.12, "learning_rate": 2.3975454744685514e-05, "loss": 2.8102, "step": 38000 }, { "epoch": 3.16, "learning_rate": 2.3633026517641905e-05, "loss": 2.8261, "step": 38500 }, { "epoch": 3.21, "learning_rate": 2.3290598290598293e-05, "loss": 2.8121, "step": 39000 }, { "epoch": 3.25, "learning_rate": 2.294817006355468e-05, "loss": 2.8127, "step": 39500 }, { "epoch": 3.29, "learning_rate": 2.260574183651107e-05, "loss": 2.8246, "step": 40000 }, { "epoch": 3.33, "learning_rate": 2.2263313609467456e-05, "loss": 2.8188, "step": 40500 }, { "epoch": 3.37, "learning_rate": 2.1920885382423844e-05, "loss": 2.8247, "step": 41000 }, { "epoch": 3.41, "learning_rate": 2.157845715538023e-05, "loss": 2.8087, "step": 41500 }, { "epoch": 3.45, "learning_rate": 2.1236028928336622e-05, "loss": 2.8135, "step": 42000 }, { "epoch": 3.49, "learning_rate": 2.089360070129301e-05, "loss": 2.8208, "step": 42500 }, { "epoch": 3.53, "learning_rate": 2.0551172474249398e-05, "loss": 2.8227, "step": 43000 }, { "epoch": 3.57, "learning_rate": 2.0208744247205785e-05, "loss": 2.8272, "step": 43500 }, { "epoch": 3.62, "learning_rate": 1.9866316020162176e-05, "loss": 2.8168, "step": 44000 }, { "epoch": 3.66, "learning_rate": 1.9523887793118564e-05, "loss": 2.8304, "step": 44500 }, { "epoch": 3.7, "learning_rate": 1.918145956607495e-05, "loss": 2.8102, "step": 45000 }, { "epoch": 3.74, "learning_rate": 1.883903133903134e-05, "loss": 2.8139, "step": 45500 }, { "epoch": 3.78, "learning_rate": 1.849660311198773e-05, "loss": 2.806, "step": 46000 }, { "epoch": 3.82, "learning_rate": 1.8154174884944118e-05, "loss": 2.8253, "step": 46500 }, { "epoch": 3.86, "learning_rate": 1.7811746657900506e-05, "loss": 2.8237, "step": 47000 }, { "epoch": 3.9, "learning_rate": 1.7469318430856893e-05, "loss": 2.8118, "step": 47500 }, { "epoch": 3.94, "learning_rate": 1.712689020381328e-05, "loss": 2.8203, "step": 48000 }, { "epoch": 3.99, "learning_rate": 1.678446197676967e-05, "loss": 2.8142, "step": 48500 }, { "epoch": 4.03, "learning_rate": 1.6442033749726056e-05, "loss": 2.7918, "step": 49000 }, { "epoch": 4.07, "learning_rate": 1.6099605522682447e-05, "loss": 2.7683, "step": 49500 }, { "epoch": 4.11, "learning_rate": 1.5757177295638835e-05, "loss": 2.7645, "step": 50000 }, { "epoch": 4.15, "learning_rate": 1.5414749068595226e-05, "loss": 2.7562, "step": 50500 }, { "epoch": 4.19, "learning_rate": 1.5072320841551612e-05, "loss": 2.7706, "step": 51000 }, { "epoch": 4.23, "learning_rate": 1.4729892614508001e-05, "loss": 2.779, "step": 51500 }, { "epoch": 4.27, "learning_rate": 1.4387464387464389e-05, "loss": 2.7665, "step": 52000 }, { "epoch": 4.31, "learning_rate": 1.4045036160420776e-05, "loss": 2.7696, "step": 52500 }, { "epoch": 4.36, "learning_rate": 1.3702607933377166e-05, "loss": 2.7725, "step": 53000 }, { "epoch": 4.4, "learning_rate": 1.3360179706333553e-05, "loss": 2.7724, "step": 53500 }, { "epoch": 4.44, "learning_rate": 1.3017751479289941e-05, "loss": 2.7725, "step": 54000 }, { "epoch": 4.48, "learning_rate": 1.2675323252246329e-05, "loss": 2.7759, "step": 54500 }, { "epoch": 4.52, "learning_rate": 1.2332895025202718e-05, "loss": 2.7655, "step": 55000 }, { "epoch": 4.56, "learning_rate": 1.1990466798159107e-05, "loss": 2.7836, "step": 55500 }, { "epoch": 4.6, "learning_rate": 1.1648038571115495e-05, "loss": 2.7709, "step": 56000 }, { "epoch": 4.64, "learning_rate": 1.1305610344071883e-05, "loss": 2.7758, "step": 56500 }, { "epoch": 4.68, "learning_rate": 1.0963182117028272e-05, "loss": 2.7825, "step": 57000 }, { "epoch": 4.73, "learning_rate": 1.062075388998466e-05, "loss": 2.7641, "step": 57500 }, { "epoch": 4.77, "learning_rate": 1.0278325662941047e-05, "loss": 2.7886, "step": 58000 }, { "epoch": 4.81, "learning_rate": 9.935897435897435e-06, "loss": 2.7784, "step": 58500 }, { "epoch": 4.85, "learning_rate": 9.593469208853826e-06, "loss": 2.7692, "step": 59000 }, { "epoch": 4.89, "learning_rate": 9.251040981810214e-06, "loss": 2.7633, "step": 59500 }, { "epoch": 4.93, "learning_rate": 8.908612754766601e-06, "loss": 2.7832, "step": 60000 }, { "epoch": 4.97, "learning_rate": 8.566184527722989e-06, "loss": 2.7778, "step": 60500 }, { "epoch": 5.01, "learning_rate": 8.223756300679378e-06, "loss": 2.7643, "step": 61000 }, { "epoch": 5.05, "learning_rate": 7.881328073635766e-06, "loss": 2.7539, "step": 61500 }, { "epoch": 5.1, "learning_rate": 7.538899846592154e-06, "loss": 2.7482, "step": 62000 }, { "epoch": 5.14, "learning_rate": 7.196471619548544e-06, "loss": 2.7536, "step": 62500 }, { "epoch": 5.18, "learning_rate": 6.854043392504931e-06, "loss": 2.7419, "step": 63000 }, { "epoch": 5.22, "learning_rate": 6.51161516546132e-06, "loss": 2.731, "step": 63500 }, { "epoch": 5.26, "learning_rate": 6.1691869384177075e-06, "loss": 2.7355, "step": 64000 }, { "epoch": 5.3, "learning_rate": 5.826758711374096e-06, "loss": 2.7378, "step": 64500 }, { "epoch": 5.34, "learning_rate": 5.4843304843304845e-06, "loss": 2.7447, "step": 65000 }, { "epoch": 5.38, "learning_rate": 5.141902257286873e-06, "loss": 2.7548, "step": 65500 }, { "epoch": 5.42, "learning_rate": 4.799474030243261e-06, "loss": 2.7362, "step": 66000 }, { "epoch": 5.47, "learning_rate": 4.45704580319965e-06, "loss": 2.7434, "step": 66500 }, { "epoch": 5.51, "learning_rate": 4.114617576156038e-06, "loss": 2.7424, "step": 67000 }, { "epoch": 5.55, "learning_rate": 3.772189349112426e-06, "loss": 2.7468, "step": 67500 }, { "epoch": 5.59, "learning_rate": 3.429761122068815e-06, "loss": 2.7451, "step": 68000 }, { "epoch": 5.63, "learning_rate": 3.087332895025203e-06, "loss": 2.7504, "step": 68500 }, { "epoch": 5.67, "learning_rate": 2.744904667981591e-06, "loss": 2.7372, "step": 69000 }, { "epoch": 5.71, "learning_rate": 2.4024764409379797e-06, "loss": 2.7349, "step": 69500 }, { "epoch": 5.75, "learning_rate": 2.0600482138943677e-06, "loss": 2.7477, "step": 70000 }, { "epoch": 5.79, "learning_rate": 1.7176199868507562e-06, "loss": 2.7394, "step": 70500 }, { "epoch": 5.83, "learning_rate": 1.3751917598071445e-06, "loss": 2.7303, "step": 71000 }, { "epoch": 5.88, "learning_rate": 1.0327635327635328e-06, "loss": 2.7408, "step": 71500 }, { "epoch": 5.92, "learning_rate": 6.903353057199211e-07, "loss": 2.7455, "step": 72000 }, { "epoch": 5.96, "learning_rate": 3.479070786763094e-07, "loss": 2.7378, "step": 72500 }, { "epoch": 6.0, "learning_rate": 5.478851632697787e-09, "loss": 2.7414, "step": 73000 }, { "epoch": 6.0, "step": 73008, "total_flos": 3.8152817344512e+16, "train_loss": 2.887446778400044, "train_runtime": 18728.1376, "train_samples_per_second": 3.898, "train_steps_per_second": 3.898 } ], "max_steps": 73008, "num_train_epochs": 6, "total_flos": 3.8152817344512e+16, "trial_name": null, "trial_params": null }