{ "best_metric": null, "best_model_checkpoint": null, "epoch": 30.0, "global_step": 486870, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03, "learning_rate": 1.0000000000000002e-06, "loss": 3.6192, "step": 500 }, { "epoch": 0.06, "learning_rate": 2.0000000000000003e-06, "loss": 3.0017, "step": 1000 }, { "epoch": 0.09, "learning_rate": 3e-06, "loss": 2.7552, "step": 1500 }, { "epoch": 0.12, "learning_rate": 4.000000000000001e-06, "loss": 2.632, "step": 2000 }, { "epoch": 0.15, "learning_rate": 5e-06, "loss": 2.5416, "step": 2500 }, { "epoch": 0.18, "learning_rate": 6e-06, "loss": 2.468, "step": 3000 }, { "epoch": 0.22, "learning_rate": 7e-06, "loss": 2.404, "step": 3500 }, { "epoch": 0.25, "learning_rate": 8.000000000000001e-06, "loss": 2.3388, "step": 4000 }, { "epoch": 0.28, "learning_rate": 9e-06, "loss": 2.2985, "step": 4500 }, { "epoch": 0.31, "learning_rate": 1e-05, "loss": 2.2616, "step": 5000 }, { "epoch": 0.34, "learning_rate": 1.1000000000000001e-05, "loss": 2.2156, "step": 5500 }, { "epoch": 0.37, "learning_rate": 1.2e-05, "loss": 2.1814, "step": 6000 }, { "epoch": 0.4, "learning_rate": 1.3000000000000001e-05, "loss": 2.1473, "step": 6500 }, { "epoch": 0.43, "learning_rate": 1.4e-05, "loss": 2.1205, "step": 7000 }, { "epoch": 0.46, "learning_rate": 1.5000000000000002e-05, "loss": 2.1008, "step": 7500 }, { "epoch": 0.49, "learning_rate": 1.6000000000000003e-05, "loss": 2.0718, "step": 8000 }, { "epoch": 0.52, "learning_rate": 1.7e-05, "loss": 2.0496, "step": 8500 }, { "epoch": 0.55, "learning_rate": 1.8e-05, "loss": 2.0264, "step": 9000 }, { "epoch": 0.59, "learning_rate": 1.9e-05, "loss": 2.0085, "step": 9500 }, { "epoch": 0.62, "learning_rate": 2e-05, "loss": 1.9873, "step": 10000 }, { "epoch": 0.65, "learning_rate": 1.9979029924298028e-05, "loss": 1.9619, "step": 10500 }, { "epoch": 0.68, "learning_rate": 1.9958059848596054e-05, "loss": 1.952, "step": 11000 }, { "epoch": 0.71, "learning_rate": 1.9937089772894084e-05, "loss": 1.9409, "step": 11500 }, { "epoch": 0.74, "learning_rate": 1.991611969719211e-05, "loss": 1.9217, "step": 12000 }, { "epoch": 0.77, "learning_rate": 1.9895149621490136e-05, "loss": 1.9073, "step": 12500 }, { "epoch": 0.8, "learning_rate": 1.9874179545788163e-05, "loss": 1.8983, "step": 13000 }, { "epoch": 0.83, "learning_rate": 1.985320947008619e-05, "loss": 1.8814, "step": 13500 }, { "epoch": 0.86, "learning_rate": 1.9832239394384215e-05, "loss": 1.8657, "step": 14000 }, { "epoch": 0.89, "learning_rate": 1.981126931868224e-05, "loss": 1.8473, "step": 14500 }, { "epoch": 0.92, "learning_rate": 1.9790299242980267e-05, "loss": 1.8407, "step": 15000 }, { "epoch": 0.96, "learning_rate": 1.9769329167278294e-05, "loss": 1.8356, "step": 15500 }, { "epoch": 0.99, "learning_rate": 1.974835909157632e-05, "loss": 1.8291, "step": 16000 }, { "epoch": 1.02, "learning_rate": 1.972738901587435e-05, "loss": 1.8095, "step": 16500 }, { "epoch": 1.05, "learning_rate": 1.9706418940172376e-05, "loss": 1.8137, "step": 17000 }, { "epoch": 1.08, "learning_rate": 1.9685448864470402e-05, "loss": 1.8022, "step": 17500 }, { "epoch": 1.11, "learning_rate": 1.966447878876843e-05, "loss": 1.7933, "step": 18000 }, { "epoch": 1.14, "learning_rate": 1.9643508713066455e-05, "loss": 1.7749, "step": 18500 }, { "epoch": 1.17, "learning_rate": 1.9622538637364484e-05, "loss": 1.7731, "step": 19000 }, { "epoch": 1.2, "learning_rate": 1.960156856166251e-05, "loss": 1.7717, "step": 19500 }, { "epoch": 1.23, "learning_rate": 1.9580598485960537e-05, "loss": 1.769, "step": 20000 }, { "epoch": 1.26, "learning_rate": 1.9559628410258563e-05, "loss": 1.7564, "step": 20500 }, { "epoch": 1.29, "learning_rate": 1.953865833455659e-05, "loss": 1.7541, "step": 21000 }, { "epoch": 1.32, "learning_rate": 1.9517688258854615e-05, "loss": 1.7503, "step": 21500 }, { "epoch": 1.36, "learning_rate": 1.9496718183152642e-05, "loss": 1.7405, "step": 22000 }, { "epoch": 1.39, "learning_rate": 1.9475748107450668e-05, "loss": 1.7392, "step": 22500 }, { "epoch": 1.42, "learning_rate": 1.9454778031748694e-05, "loss": 1.7311, "step": 23000 }, { "epoch": 1.45, "learning_rate": 1.943380795604672e-05, "loss": 1.728, "step": 23500 }, { "epoch": 1.48, "learning_rate": 1.941283788034475e-05, "loss": 1.7181, "step": 24000 }, { "epoch": 1.51, "learning_rate": 1.9391867804642776e-05, "loss": 1.7145, "step": 24500 }, { "epoch": 1.54, "learning_rate": 1.9370897728940803e-05, "loss": 1.7176, "step": 25000 }, { "epoch": 1.57, "learning_rate": 1.934992765323883e-05, "loss": 1.7116, "step": 25500 }, { "epoch": 1.6, "learning_rate": 1.9328957577536855e-05, "loss": 1.7063, "step": 26000 }, { "epoch": 1.63, "learning_rate": 1.9307987501834885e-05, "loss": 1.6982, "step": 26500 }, { "epoch": 1.66, "learning_rate": 1.928701742613291e-05, "loss": 1.6941, "step": 27000 }, { "epoch": 1.69, "learning_rate": 1.9266047350430937e-05, "loss": 1.6868, "step": 27500 }, { "epoch": 1.73, "learning_rate": 1.9245077274728963e-05, "loss": 1.6887, "step": 28000 }, { "epoch": 1.76, "learning_rate": 1.922410719902699e-05, "loss": 1.6855, "step": 28500 }, { "epoch": 1.79, "learning_rate": 1.9203137123325016e-05, "loss": 1.6802, "step": 29000 }, { "epoch": 1.82, "learning_rate": 1.9182167047623042e-05, "loss": 1.6739, "step": 29500 }, { "epoch": 1.85, "learning_rate": 1.916119697192107e-05, "loss": 1.674, "step": 30000 }, { "epoch": 1.88, "learning_rate": 1.9140226896219095e-05, "loss": 1.667, "step": 30500 }, { "epoch": 1.91, "learning_rate": 1.9119256820517124e-05, "loss": 1.6611, "step": 31000 }, { "epoch": 1.94, "learning_rate": 1.909828674481515e-05, "loss": 1.6597, "step": 31500 }, { "epoch": 1.97, "learning_rate": 1.9077316669113177e-05, "loss": 1.6639, "step": 32000 }, { "epoch": 2.0, "learning_rate": 1.9056346593411203e-05, "loss": 1.651, "step": 32500 }, { "epoch": 2.03, "learning_rate": 1.903537651770923e-05, "loss": 1.6532, "step": 33000 }, { "epoch": 2.06, "learning_rate": 1.901440644200726e-05, "loss": 1.6374, "step": 33500 }, { "epoch": 2.1, "learning_rate": 1.8993436366305285e-05, "loss": 1.6437, "step": 34000 }, { "epoch": 2.13, "learning_rate": 1.897246629060331e-05, "loss": 1.6372, "step": 34500 }, { "epoch": 2.16, "learning_rate": 1.8951496214901338e-05, "loss": 1.6427, "step": 35000 }, { "epoch": 2.19, "learning_rate": 1.8930526139199364e-05, "loss": 1.6327, "step": 35500 }, { "epoch": 2.22, "learning_rate": 1.890955606349739e-05, "loss": 1.6289, "step": 36000 }, { "epoch": 2.25, "learning_rate": 1.8888585987795416e-05, "loss": 1.6294, "step": 36500 }, { "epoch": 2.28, "learning_rate": 1.8867615912093443e-05, "loss": 1.6255, "step": 37000 }, { "epoch": 2.31, "learning_rate": 1.884664583639147e-05, "loss": 1.6289, "step": 37500 }, { "epoch": 2.34, "learning_rate": 1.88256757606895e-05, "loss": 1.6217, "step": 38000 }, { "epoch": 2.37, "learning_rate": 1.8804705684987525e-05, "loss": 1.6137, "step": 38500 }, { "epoch": 2.4, "learning_rate": 1.878373560928555e-05, "loss": 1.6145, "step": 39000 }, { "epoch": 2.43, "learning_rate": 1.8762765533583577e-05, "loss": 1.6193, "step": 39500 }, { "epoch": 2.46, "learning_rate": 1.8741795457881604e-05, "loss": 1.6082, "step": 40000 }, { "epoch": 2.5, "learning_rate": 1.872082538217963e-05, "loss": 1.6114, "step": 40500 }, { "epoch": 2.53, "learning_rate": 1.869985530647766e-05, "loss": 1.6123, "step": 41000 }, { "epoch": 2.56, "learning_rate": 1.8678885230775686e-05, "loss": 1.605, "step": 41500 }, { "epoch": 2.59, "learning_rate": 1.8657915155073712e-05, "loss": 1.6008, "step": 42000 }, { "epoch": 2.62, "learning_rate": 1.8636945079371738e-05, "loss": 1.5934, "step": 42500 }, { "epoch": 2.65, "learning_rate": 1.8615975003669764e-05, "loss": 1.6007, "step": 43000 }, { "epoch": 2.68, "learning_rate": 1.8595004927967794e-05, "loss": 1.5928, "step": 43500 }, { "epoch": 2.71, "learning_rate": 1.857403485226582e-05, "loss": 1.5988, "step": 44000 }, { "epoch": 2.74, "learning_rate": 1.8553064776563847e-05, "loss": 1.5943, "step": 44500 }, { "epoch": 2.77, "learning_rate": 1.8532094700861873e-05, "loss": 1.5842, "step": 45000 }, { "epoch": 2.8, "learning_rate": 1.85111246251599e-05, "loss": 1.5901, "step": 45500 }, { "epoch": 2.83, "learning_rate": 1.8490154549457925e-05, "loss": 1.5841, "step": 46000 }, { "epoch": 2.87, "learning_rate": 1.846918447375595e-05, "loss": 1.5784, "step": 46500 }, { "epoch": 2.9, "learning_rate": 1.8448214398053978e-05, "loss": 1.58, "step": 47000 }, { "epoch": 2.93, "learning_rate": 1.8427244322352004e-05, "loss": 1.5736, "step": 47500 }, { "epoch": 2.96, "learning_rate": 1.840627424665003e-05, "loss": 1.5697, "step": 48000 }, { "epoch": 2.99, "learning_rate": 1.838530417094806e-05, "loss": 1.5739, "step": 48500 }, { "epoch": 3.02, "learning_rate": 1.8364334095246086e-05, "loss": 1.5688, "step": 49000 }, { "epoch": 3.05, "learning_rate": 1.8343364019544112e-05, "loss": 1.5644, "step": 49500 }, { "epoch": 3.08, "learning_rate": 1.832239394384214e-05, "loss": 1.562, "step": 50000 }, { "epoch": 3.11, "learning_rate": 1.8301423868140165e-05, "loss": 1.5709, "step": 50500 }, { "epoch": 3.14, "learning_rate": 1.8280453792438195e-05, "loss": 1.5617, "step": 51000 }, { "epoch": 3.17, "learning_rate": 1.825948371673622e-05, "loss": 1.5603, "step": 51500 }, { "epoch": 3.2, "learning_rate": 1.8238513641034247e-05, "loss": 1.5625, "step": 52000 }, { "epoch": 3.23, "learning_rate": 1.8217543565332273e-05, "loss": 1.5583, "step": 52500 }, { "epoch": 3.27, "learning_rate": 1.81965734896303e-05, "loss": 1.5597, "step": 53000 }, { "epoch": 3.3, "learning_rate": 1.8175603413928326e-05, "loss": 1.553, "step": 53500 }, { "epoch": 3.33, "learning_rate": 1.8154633338226352e-05, "loss": 1.5525, "step": 54000 }, { "epoch": 3.36, "learning_rate": 1.8133663262524378e-05, "loss": 1.5521, "step": 54500 }, { "epoch": 3.39, "learning_rate": 1.8112693186822404e-05, "loss": 1.5501, "step": 55000 }, { "epoch": 3.42, "learning_rate": 1.809172311112043e-05, "loss": 1.55, "step": 55500 }, { "epoch": 3.45, "learning_rate": 1.807075303541846e-05, "loss": 1.5504, "step": 56000 }, { "epoch": 3.48, "learning_rate": 1.8049782959716487e-05, "loss": 1.5451, "step": 56500 }, { "epoch": 3.51, "learning_rate": 1.8028812884014513e-05, "loss": 1.5443, "step": 57000 }, { "epoch": 3.54, "learning_rate": 1.800784280831254e-05, "loss": 1.5412, "step": 57500 }, { "epoch": 3.57, "learning_rate": 1.7986872732610565e-05, "loss": 1.5398, "step": 58000 }, { "epoch": 3.6, "learning_rate": 1.7965902656908595e-05, "loss": 1.5425, "step": 58500 }, { "epoch": 3.64, "learning_rate": 1.794493258120662e-05, "loss": 1.538, "step": 59000 }, { "epoch": 3.67, "learning_rate": 1.7923962505504647e-05, "loss": 1.5406, "step": 59500 }, { "epoch": 3.7, "learning_rate": 1.7902992429802674e-05, "loss": 1.5365, "step": 60000 }, { "epoch": 3.73, "learning_rate": 1.78820223541007e-05, "loss": 1.5344, "step": 60500 }, { "epoch": 3.76, "learning_rate": 1.7861052278398726e-05, "loss": 1.5332, "step": 61000 }, { "epoch": 3.79, "learning_rate": 1.7840082202696752e-05, "loss": 1.5311, "step": 61500 }, { "epoch": 3.82, "learning_rate": 1.781911212699478e-05, "loss": 1.5316, "step": 62000 }, { "epoch": 3.85, "learning_rate": 1.7798142051292805e-05, "loss": 1.5241, "step": 62500 }, { "epoch": 3.88, "learning_rate": 1.777717197559083e-05, "loss": 1.523, "step": 63000 }, { "epoch": 3.91, "learning_rate": 1.775620189988886e-05, "loss": 1.5247, "step": 63500 }, { "epoch": 3.94, "learning_rate": 1.7735231824186887e-05, "loss": 1.5246, "step": 64000 }, { "epoch": 3.97, "learning_rate": 1.7714261748484913e-05, "loss": 1.5215, "step": 64500 }, { "epoch": 4.01, "learning_rate": 1.769329167278294e-05, "loss": 1.5256, "step": 65000 }, { "epoch": 4.04, "learning_rate": 1.7672321597080966e-05, "loss": 1.5244, "step": 65500 }, { "epoch": 4.07, "learning_rate": 1.7651351521378995e-05, "loss": 1.5104, "step": 66000 }, { "epoch": 4.1, "learning_rate": 1.7630381445677022e-05, "loss": 1.5083, "step": 66500 }, { "epoch": 4.13, "learning_rate": 1.7609411369975048e-05, "loss": 1.5076, "step": 67000 }, { "epoch": 4.16, "learning_rate": 1.7588441294273074e-05, "loss": 1.5132, "step": 67500 }, { "epoch": 4.19, "learning_rate": 1.75674712185711e-05, "loss": 1.5163, "step": 68000 }, { "epoch": 4.22, "learning_rate": 1.7546501142869127e-05, "loss": 1.5133, "step": 68500 }, { "epoch": 4.25, "learning_rate": 1.7525531067167153e-05, "loss": 1.5099, "step": 69000 }, { "epoch": 4.28, "learning_rate": 1.750456099146518e-05, "loss": 1.5054, "step": 69500 }, { "epoch": 4.31, "learning_rate": 1.7483590915763205e-05, "loss": 1.5081, "step": 70000 }, { "epoch": 4.34, "learning_rate": 1.7462620840061235e-05, "loss": 1.5063, "step": 70500 }, { "epoch": 4.37, "learning_rate": 1.744165076435926e-05, "loss": 1.5016, "step": 71000 }, { "epoch": 4.41, "learning_rate": 1.7420680688657288e-05, "loss": 1.5061, "step": 71500 }, { "epoch": 4.44, "learning_rate": 1.7399710612955314e-05, "loss": 1.5001, "step": 72000 }, { "epoch": 4.47, "learning_rate": 1.737874053725334e-05, "loss": 1.5002, "step": 72500 }, { "epoch": 4.5, "learning_rate": 1.735777046155137e-05, "loss": 1.5027, "step": 73000 }, { "epoch": 4.53, "learning_rate": 1.7336800385849396e-05, "loss": 1.4996, "step": 73500 }, { "epoch": 4.56, "learning_rate": 1.7315830310147422e-05, "loss": 1.4975, "step": 74000 }, { "epoch": 4.59, "learning_rate": 1.729486023444545e-05, "loss": 1.5008, "step": 74500 }, { "epoch": 4.62, "learning_rate": 1.7273890158743475e-05, "loss": 1.4927, "step": 75000 }, { "epoch": 4.65, "learning_rate": 1.72529200830415e-05, "loss": 1.4955, "step": 75500 }, { "epoch": 4.68, "learning_rate": 1.7231950007339527e-05, "loss": 1.4892, "step": 76000 }, { "epoch": 4.71, "learning_rate": 1.7210979931637553e-05, "loss": 1.4918, "step": 76500 }, { "epoch": 4.74, "learning_rate": 1.719000985593558e-05, "loss": 1.4886, "step": 77000 }, { "epoch": 4.78, "learning_rate": 1.7169039780233606e-05, "loss": 1.4964, "step": 77500 }, { "epoch": 4.81, "learning_rate": 1.7148069704531636e-05, "loss": 1.4863, "step": 78000 }, { "epoch": 4.84, "learning_rate": 1.7127099628829662e-05, "loss": 1.4895, "step": 78500 }, { "epoch": 4.87, "learning_rate": 1.7106129553127688e-05, "loss": 1.4893, "step": 79000 }, { "epoch": 4.9, "learning_rate": 1.7085159477425714e-05, "loss": 1.4906, "step": 79500 }, { "epoch": 4.93, "learning_rate": 1.706418940172374e-05, "loss": 1.4911, "step": 80000 }, { "epoch": 4.96, "learning_rate": 1.704321932602177e-05, "loss": 1.4903, "step": 80500 }, { "epoch": 4.99, "learning_rate": 1.7022249250319796e-05, "loss": 1.4839, "step": 81000 }, { "epoch": 5.02, "learning_rate": 1.7001279174617823e-05, "loss": 1.4805, "step": 81500 }, { "epoch": 5.05, "learning_rate": 1.698030909891585e-05, "loss": 1.4767, "step": 82000 }, { "epoch": 5.08, "learning_rate": 1.6959339023213875e-05, "loss": 1.4758, "step": 82500 }, { "epoch": 5.11, "learning_rate": 1.69383689475119e-05, "loss": 1.4798, "step": 83000 }, { "epoch": 5.15, "learning_rate": 1.6917398871809928e-05, "loss": 1.4724, "step": 83500 }, { "epoch": 5.18, "learning_rate": 1.6896428796107954e-05, "loss": 1.4736, "step": 84000 }, { "epoch": 5.21, "learning_rate": 1.687545872040598e-05, "loss": 1.4691, "step": 84500 }, { "epoch": 5.24, "learning_rate": 1.6854488644704006e-05, "loss": 1.4756, "step": 85000 }, { "epoch": 5.27, "learning_rate": 1.6833518569002036e-05, "loss": 1.4813, "step": 85500 }, { "epoch": 5.3, "learning_rate": 1.6812548493300062e-05, "loss": 1.4753, "step": 86000 }, { "epoch": 5.33, "learning_rate": 1.679157841759809e-05, "loss": 1.4701, "step": 86500 }, { "epoch": 5.36, "learning_rate": 1.6770608341896115e-05, "loss": 1.4697, "step": 87000 }, { "epoch": 5.39, "learning_rate": 1.674963826619414e-05, "loss": 1.4728, "step": 87500 }, { "epoch": 5.42, "learning_rate": 1.672866819049217e-05, "loss": 1.4701, "step": 88000 }, { "epoch": 5.45, "learning_rate": 1.6707698114790197e-05, "loss": 1.4675, "step": 88500 }, { "epoch": 5.48, "learning_rate": 1.6686728039088223e-05, "loss": 1.4667, "step": 89000 }, { "epoch": 5.51, "learning_rate": 1.666575796338625e-05, "loss": 1.4627, "step": 89500 }, { "epoch": 5.55, "learning_rate": 1.6644787887684276e-05, "loss": 1.4633, "step": 90000 }, { "epoch": 5.58, "learning_rate": 1.6623817811982302e-05, "loss": 1.4629, "step": 90500 }, { "epoch": 5.61, "learning_rate": 1.6602847736280328e-05, "loss": 1.4638, "step": 91000 }, { "epoch": 5.64, "learning_rate": 1.6581877660578354e-05, "loss": 1.4673, "step": 91500 }, { "epoch": 5.67, "learning_rate": 1.656090758487638e-05, "loss": 1.461, "step": 92000 }, { "epoch": 5.7, "learning_rate": 1.6539937509174407e-05, "loss": 1.4613, "step": 92500 }, { "epoch": 5.73, "learning_rate": 1.6518967433472437e-05, "loss": 1.4629, "step": 93000 }, { "epoch": 5.76, "learning_rate": 1.6497997357770463e-05, "loss": 1.4579, "step": 93500 }, { "epoch": 5.79, "learning_rate": 1.647702728206849e-05, "loss": 1.4546, "step": 94000 }, { "epoch": 5.82, "learning_rate": 1.6456057206366515e-05, "loss": 1.4541, "step": 94500 }, { "epoch": 5.85, "learning_rate": 1.643508713066454e-05, "loss": 1.4586, "step": 95000 }, { "epoch": 5.88, "learning_rate": 1.641411705496257e-05, "loss": 1.4567, "step": 95500 }, { "epoch": 5.92, "learning_rate": 1.6393146979260597e-05, "loss": 1.4485, "step": 96000 }, { "epoch": 5.95, "learning_rate": 1.6372176903558624e-05, "loss": 1.4503, "step": 96500 }, { "epoch": 5.98, "learning_rate": 1.635120682785665e-05, "loss": 1.4566, "step": 97000 }, { "epoch": 6.01, "learning_rate": 1.6330236752154676e-05, "loss": 1.4526, "step": 97500 }, { "epoch": 6.04, "learning_rate": 1.6309266676452706e-05, "loss": 1.4417, "step": 98000 }, { "epoch": 6.07, "learning_rate": 1.6288296600750732e-05, "loss": 1.4384, "step": 98500 }, { "epoch": 6.1, "learning_rate": 1.6267326525048758e-05, "loss": 1.4511, "step": 99000 }, { "epoch": 6.13, "learning_rate": 1.6246356449346784e-05, "loss": 1.4437, "step": 99500 }, { "epoch": 6.16, "learning_rate": 1.622538637364481e-05, "loss": 1.4464, "step": 100000 }, { "epoch": 6.19, "learning_rate": 1.6204416297942837e-05, "loss": 1.4437, "step": 100500 }, { "epoch": 6.22, "learning_rate": 1.6183446222240863e-05, "loss": 1.4424, "step": 101000 }, { "epoch": 6.25, "learning_rate": 1.616247614653889e-05, "loss": 1.4423, "step": 101500 }, { "epoch": 6.29, "learning_rate": 1.6141506070836916e-05, "loss": 1.4483, "step": 102000 }, { "epoch": 6.32, "learning_rate": 1.6120535995134942e-05, "loss": 1.4487, "step": 102500 }, { "epoch": 6.35, "learning_rate": 1.609956591943297e-05, "loss": 1.4403, "step": 103000 }, { "epoch": 6.38, "learning_rate": 1.6078595843730998e-05, "loss": 1.4417, "step": 103500 }, { "epoch": 6.41, "learning_rate": 1.6057625768029024e-05, "loss": 1.4403, "step": 104000 }, { "epoch": 6.44, "learning_rate": 1.603665569232705e-05, "loss": 1.4426, "step": 104500 }, { "epoch": 6.47, "learning_rate": 1.6015685616625077e-05, "loss": 1.441, "step": 105000 }, { "epoch": 6.5, "learning_rate": 1.5994715540923106e-05, "loss": 1.4416, "step": 105500 }, { "epoch": 6.53, "learning_rate": 1.5973745465221132e-05, "loss": 1.4478, "step": 106000 }, { "epoch": 6.56, "learning_rate": 1.595277538951916e-05, "loss": 1.4347, "step": 106500 }, { "epoch": 6.59, "learning_rate": 1.5931805313817185e-05, "loss": 1.4347, "step": 107000 }, { "epoch": 6.62, "learning_rate": 1.591083523811521e-05, "loss": 1.4346, "step": 107500 }, { "epoch": 6.65, "learning_rate": 1.5889865162413237e-05, "loss": 1.4344, "step": 108000 }, { "epoch": 6.69, "learning_rate": 1.5868895086711264e-05, "loss": 1.4405, "step": 108500 }, { "epoch": 6.72, "learning_rate": 1.584792501100929e-05, "loss": 1.439, "step": 109000 }, { "epoch": 6.75, "learning_rate": 1.5826954935307316e-05, "loss": 1.4293, "step": 109500 }, { "epoch": 6.78, "learning_rate": 1.5805984859605346e-05, "loss": 1.4289, "step": 110000 }, { "epoch": 6.81, "learning_rate": 1.5785014783903372e-05, "loss": 1.4316, "step": 110500 }, { "epoch": 6.84, "learning_rate": 1.57640447082014e-05, "loss": 1.4329, "step": 111000 }, { "epoch": 6.87, "learning_rate": 1.5743074632499425e-05, "loss": 1.4318, "step": 111500 }, { "epoch": 6.9, "learning_rate": 1.572210455679745e-05, "loss": 1.435, "step": 112000 }, { "epoch": 6.93, "learning_rate": 1.570113448109548e-05, "loss": 1.4323, "step": 112500 }, { "epoch": 6.96, "learning_rate": 1.5680164405393507e-05, "loss": 1.4334, "step": 113000 }, { "epoch": 6.99, "learning_rate": 1.5659194329691533e-05, "loss": 1.4303, "step": 113500 }, { "epoch": 7.02, "learning_rate": 1.563822425398956e-05, "loss": 1.4241, "step": 114000 }, { "epoch": 7.06, "learning_rate": 1.5617254178287585e-05, "loss": 1.4261, "step": 114500 }, { "epoch": 7.09, "learning_rate": 1.559628410258561e-05, "loss": 1.424, "step": 115000 }, { "epoch": 7.12, "learning_rate": 1.5575314026883638e-05, "loss": 1.4229, "step": 115500 }, { "epoch": 7.15, "learning_rate": 1.5554343951181664e-05, "loss": 1.4258, "step": 116000 }, { "epoch": 7.18, "learning_rate": 1.553337387547969e-05, "loss": 1.4203, "step": 116500 }, { "epoch": 7.21, "learning_rate": 1.5512403799777717e-05, "loss": 1.4193, "step": 117000 }, { "epoch": 7.24, "learning_rate": 1.5491433724075746e-05, "loss": 1.4302, "step": 117500 }, { "epoch": 7.27, "learning_rate": 1.5470463648373773e-05, "loss": 1.4206, "step": 118000 }, { "epoch": 7.3, "learning_rate": 1.54494935726718e-05, "loss": 1.4181, "step": 118500 }, { "epoch": 7.33, "learning_rate": 1.5428523496969825e-05, "loss": 1.4179, "step": 119000 }, { "epoch": 7.36, "learning_rate": 1.540755342126785e-05, "loss": 1.4207, "step": 119500 }, { "epoch": 7.39, "learning_rate": 1.538658334556588e-05, "loss": 1.4117, "step": 120000 }, { "epoch": 7.42, "learning_rate": 1.5365613269863907e-05, "loss": 1.4153, "step": 120500 }, { "epoch": 7.46, "learning_rate": 1.5344643194161933e-05, "loss": 1.419, "step": 121000 }, { "epoch": 7.49, "learning_rate": 1.532367311845996e-05, "loss": 1.4232, "step": 121500 }, { "epoch": 7.52, "learning_rate": 1.5302703042757986e-05, "loss": 1.421, "step": 122000 }, { "epoch": 7.55, "learning_rate": 1.5281732967056012e-05, "loss": 1.4236, "step": 122500 }, { "epoch": 7.58, "learning_rate": 1.526076289135404e-05, "loss": 1.4154, "step": 123000 }, { "epoch": 7.61, "learning_rate": 1.5239792815652066e-05, "loss": 1.4103, "step": 123500 }, { "epoch": 7.64, "learning_rate": 1.5218822739950093e-05, "loss": 1.4092, "step": 124000 }, { "epoch": 7.67, "learning_rate": 1.5197852664248119e-05, "loss": 1.4167, "step": 124500 }, { "epoch": 7.7, "learning_rate": 1.5176882588546147e-05, "loss": 1.4183, "step": 125000 }, { "epoch": 7.73, "learning_rate": 1.5155912512844173e-05, "loss": 1.4099, "step": 125500 }, { "epoch": 7.76, "learning_rate": 1.51349424371422e-05, "loss": 1.413, "step": 126000 }, { "epoch": 7.79, "learning_rate": 1.5113972361440226e-05, "loss": 1.411, "step": 126500 }, { "epoch": 7.83, "learning_rate": 1.5093002285738252e-05, "loss": 1.4109, "step": 127000 }, { "epoch": 7.86, "learning_rate": 1.507203221003628e-05, "loss": 1.414, "step": 127500 }, { "epoch": 7.89, "learning_rate": 1.5051062134334306e-05, "loss": 1.4149, "step": 128000 }, { "epoch": 7.92, "learning_rate": 1.5030092058632332e-05, "loss": 1.4143, "step": 128500 }, { "epoch": 7.95, "learning_rate": 1.5009121982930358e-05, "loss": 1.4164, "step": 129000 }, { "epoch": 7.98, "learning_rate": 1.4988151907228385e-05, "loss": 1.4118, "step": 129500 }, { "epoch": 8.01, "learning_rate": 1.4967181831526414e-05, "loss": 1.4053, "step": 130000 }, { "epoch": 8.04, "learning_rate": 1.494621175582444e-05, "loss": 1.4026, "step": 130500 }, { "epoch": 8.07, "learning_rate": 1.4925241680122467e-05, "loss": 1.4048, "step": 131000 }, { "epoch": 8.1, "learning_rate": 1.4904271604420493e-05, "loss": 1.4014, "step": 131500 }, { "epoch": 8.13, "learning_rate": 1.488330152871852e-05, "loss": 1.4036, "step": 132000 }, { "epoch": 8.16, "learning_rate": 1.4862331453016547e-05, "loss": 1.4054, "step": 132500 }, { "epoch": 8.2, "learning_rate": 1.4841361377314574e-05, "loss": 1.4043, "step": 133000 }, { "epoch": 8.23, "learning_rate": 1.48203913016126e-05, "loss": 1.4035, "step": 133500 }, { "epoch": 8.26, "learning_rate": 1.4799421225910626e-05, "loss": 1.4045, "step": 134000 }, { "epoch": 8.29, "learning_rate": 1.4778451150208652e-05, "loss": 1.4024, "step": 134500 }, { "epoch": 8.32, "learning_rate": 1.475748107450668e-05, "loss": 1.3982, "step": 135000 }, { "epoch": 8.35, "learning_rate": 1.4736510998804706e-05, "loss": 1.3996, "step": 135500 }, { "epoch": 8.38, "learning_rate": 1.4715540923102733e-05, "loss": 1.397, "step": 136000 }, { "epoch": 8.41, "learning_rate": 1.469457084740076e-05, "loss": 1.4058, "step": 136500 }, { "epoch": 8.44, "learning_rate": 1.4673600771698787e-05, "loss": 1.3984, "step": 137000 }, { "epoch": 8.47, "learning_rate": 1.4652630695996815e-05, "loss": 1.4037, "step": 137500 }, { "epoch": 8.5, "learning_rate": 1.4631660620294841e-05, "loss": 1.4021, "step": 138000 }, { "epoch": 8.53, "learning_rate": 1.4610690544592867e-05, "loss": 1.3966, "step": 138500 }, { "epoch": 8.56, "learning_rate": 1.4589720468890894e-05, "loss": 1.397, "step": 139000 }, { "epoch": 8.6, "learning_rate": 1.456875039318892e-05, "loss": 1.3994, "step": 139500 }, { "epoch": 8.63, "learning_rate": 1.4547780317486948e-05, "loss": 1.3992, "step": 140000 }, { "epoch": 8.66, "learning_rate": 1.4526810241784974e-05, "loss": 1.399, "step": 140500 }, { "epoch": 8.69, "learning_rate": 1.4505840166083e-05, "loss": 1.4036, "step": 141000 }, { "epoch": 8.72, "learning_rate": 1.4484870090381026e-05, "loss": 1.3949, "step": 141500 }, { "epoch": 8.75, "learning_rate": 1.4463900014679053e-05, "loss": 1.3994, "step": 142000 }, { "epoch": 8.78, "learning_rate": 1.4442929938977082e-05, "loss": 1.3941, "step": 142500 }, { "epoch": 8.81, "learning_rate": 1.4421959863275109e-05, "loss": 1.3963, "step": 143000 }, { "epoch": 8.84, "learning_rate": 1.4400989787573135e-05, "loss": 1.3996, "step": 143500 }, { "epoch": 8.87, "learning_rate": 1.4380019711871161e-05, "loss": 1.3914, "step": 144000 }, { "epoch": 8.9, "learning_rate": 1.4359049636169187e-05, "loss": 1.3923, "step": 144500 }, { "epoch": 8.93, "learning_rate": 1.4338079560467215e-05, "loss": 1.3958, "step": 145000 }, { "epoch": 8.97, "learning_rate": 1.4317109484765242e-05, "loss": 1.3906, "step": 145500 }, { "epoch": 9.0, "learning_rate": 1.4296139409063268e-05, "loss": 1.3867, "step": 146000 }, { "epoch": 9.03, "learning_rate": 1.4275169333361294e-05, "loss": 1.3821, "step": 146500 }, { "epoch": 9.06, "learning_rate": 1.425419925765932e-05, "loss": 1.3917, "step": 147000 }, { "epoch": 9.09, "learning_rate": 1.4233229181957348e-05, "loss": 1.3972, "step": 147500 }, { "epoch": 9.12, "learning_rate": 1.4212259106255374e-05, "loss": 1.3848, "step": 148000 }, { "epoch": 9.15, "learning_rate": 1.41912890305534e-05, "loss": 1.386, "step": 148500 }, { "epoch": 9.18, "learning_rate": 1.4170318954851427e-05, "loss": 1.3855, "step": 149000 }, { "epoch": 9.21, "learning_rate": 1.4149348879149457e-05, "loss": 1.3876, "step": 149500 }, { "epoch": 9.24, "learning_rate": 1.4128378803447483e-05, "loss": 1.3836, "step": 150000 }, { "epoch": 9.27, "learning_rate": 1.4107408727745509e-05, "loss": 1.3841, "step": 150500 }, { "epoch": 9.3, "learning_rate": 1.4086438652043535e-05, "loss": 1.3828, "step": 151000 }, { "epoch": 9.34, "learning_rate": 1.4065468576341562e-05, "loss": 1.3914, "step": 151500 }, { "epoch": 9.37, "learning_rate": 1.404449850063959e-05, "loss": 1.3813, "step": 152000 }, { "epoch": 9.4, "learning_rate": 1.4023528424937616e-05, "loss": 1.3803, "step": 152500 }, { "epoch": 9.43, "learning_rate": 1.4002558349235642e-05, "loss": 1.3852, "step": 153000 }, { "epoch": 9.46, "learning_rate": 1.3981588273533668e-05, "loss": 1.3791, "step": 153500 }, { "epoch": 9.49, "learning_rate": 1.3960618197831695e-05, "loss": 1.3798, "step": 154000 }, { "epoch": 9.52, "learning_rate": 1.3939648122129722e-05, "loss": 1.384, "step": 154500 }, { "epoch": 9.55, "learning_rate": 1.3918678046427749e-05, "loss": 1.3834, "step": 155000 }, { "epoch": 9.58, "learning_rate": 1.3897707970725775e-05, "loss": 1.3852, "step": 155500 }, { "epoch": 9.61, "learning_rate": 1.3876737895023801e-05, "loss": 1.3827, "step": 156000 }, { "epoch": 9.64, "learning_rate": 1.3855767819321827e-05, "loss": 1.3846, "step": 156500 }, { "epoch": 9.67, "learning_rate": 1.3834797743619857e-05, "loss": 1.3849, "step": 157000 }, { "epoch": 9.7, "learning_rate": 1.3813827667917883e-05, "loss": 1.3816, "step": 157500 }, { "epoch": 9.74, "learning_rate": 1.379285759221591e-05, "loss": 1.3777, "step": 158000 }, { "epoch": 9.77, "learning_rate": 1.3771887516513936e-05, "loss": 1.3773, "step": 158500 }, { "epoch": 9.8, "learning_rate": 1.3750917440811962e-05, "loss": 1.379, "step": 159000 }, { "epoch": 9.83, "learning_rate": 1.372994736510999e-05, "loss": 1.3778, "step": 159500 }, { "epoch": 9.86, "learning_rate": 1.3708977289408016e-05, "loss": 1.3772, "step": 160000 }, { "epoch": 9.89, "learning_rate": 1.3688007213706042e-05, "loss": 1.3793, "step": 160500 }, { "epoch": 9.92, "learning_rate": 1.3667037138004069e-05, "loss": 1.3763, "step": 161000 }, { "epoch": 9.95, "learning_rate": 1.3646067062302095e-05, "loss": 1.3781, "step": 161500 }, { "epoch": 9.98, "learning_rate": 1.3625096986600123e-05, "loss": 1.3821, "step": 162000 }, { "epoch": 10.01, "learning_rate": 1.360412691089815e-05, "loss": 1.3729, "step": 162500 }, { "epoch": 10.04, "learning_rate": 1.3583156835196175e-05, "loss": 1.3756, "step": 163000 }, { "epoch": 10.07, "learning_rate": 1.3562186759494202e-05, "loss": 1.3719, "step": 163500 }, { "epoch": 10.11, "learning_rate": 1.354121668379223e-05, "loss": 1.3704, "step": 164000 }, { "epoch": 10.14, "learning_rate": 1.3520246608090258e-05, "loss": 1.3729, "step": 164500 }, { "epoch": 10.17, "learning_rate": 1.3499276532388284e-05, "loss": 1.3721, "step": 165000 }, { "epoch": 10.2, "learning_rate": 1.347830645668631e-05, "loss": 1.3708, "step": 165500 }, { "epoch": 10.23, "learning_rate": 1.3457336380984336e-05, "loss": 1.369, "step": 166000 }, { "epoch": 10.26, "learning_rate": 1.3436366305282363e-05, "loss": 1.3703, "step": 166500 }, { "epoch": 10.29, "learning_rate": 1.341539622958039e-05, "loss": 1.3715, "step": 167000 }, { "epoch": 10.32, "learning_rate": 1.3394426153878417e-05, "loss": 1.3714, "step": 167500 }, { "epoch": 10.35, "learning_rate": 1.3373456078176443e-05, "loss": 1.3711, "step": 168000 }, { "epoch": 10.38, "learning_rate": 1.335248600247447e-05, "loss": 1.3759, "step": 168500 }, { "epoch": 10.41, "learning_rate": 1.3331515926772495e-05, "loss": 1.3701, "step": 169000 }, { "epoch": 10.44, "learning_rate": 1.3310545851070525e-05, "loss": 1.3694, "step": 169500 }, { "epoch": 10.48, "learning_rate": 1.3289575775368551e-05, "loss": 1.3724, "step": 170000 }, { "epoch": 10.51, "learning_rate": 1.3268605699666578e-05, "loss": 1.3705, "step": 170500 }, { "epoch": 10.54, "learning_rate": 1.3247635623964604e-05, "loss": 1.3749, "step": 171000 }, { "epoch": 10.57, "learning_rate": 1.322666554826263e-05, "loss": 1.3747, "step": 171500 }, { "epoch": 10.6, "learning_rate": 1.3205695472560658e-05, "loss": 1.3645, "step": 172000 }, { "epoch": 10.63, "learning_rate": 1.3184725396858684e-05, "loss": 1.3676, "step": 172500 }, { "epoch": 10.66, "learning_rate": 1.316375532115671e-05, "loss": 1.3634, "step": 173000 }, { "epoch": 10.69, "learning_rate": 1.3142785245454737e-05, "loss": 1.3682, "step": 173500 }, { "epoch": 10.72, "learning_rate": 1.3121815169752763e-05, "loss": 1.366, "step": 174000 }, { "epoch": 10.75, "learning_rate": 1.3100845094050791e-05, "loss": 1.3656, "step": 174500 }, { "epoch": 10.78, "learning_rate": 1.3079875018348817e-05, "loss": 1.36, "step": 175000 }, { "epoch": 10.81, "learning_rate": 1.3058904942646843e-05, "loss": 1.3637, "step": 175500 }, { "epoch": 10.84, "learning_rate": 1.303793486694487e-05, "loss": 1.3677, "step": 176000 }, { "epoch": 10.88, "learning_rate": 1.3016964791242896e-05, "loss": 1.3574, "step": 176500 }, { "epoch": 10.91, "learning_rate": 1.2995994715540926e-05, "loss": 1.3666, "step": 177000 }, { "epoch": 10.94, "learning_rate": 1.2975024639838952e-05, "loss": 1.3712, "step": 177500 }, { "epoch": 10.97, "learning_rate": 1.2954054564136978e-05, "loss": 1.3607, "step": 178000 }, { "epoch": 11.0, "learning_rate": 1.2933084488435004e-05, "loss": 1.3613, "step": 178500 }, { "epoch": 11.03, "learning_rate": 1.291211441273303e-05, "loss": 1.3596, "step": 179000 }, { "epoch": 11.06, "learning_rate": 1.2891144337031058e-05, "loss": 1.3634, "step": 179500 }, { "epoch": 11.09, "learning_rate": 1.2870174261329085e-05, "loss": 1.365, "step": 180000 }, { "epoch": 11.12, "learning_rate": 1.2849204185627111e-05, "loss": 1.3575, "step": 180500 }, { "epoch": 11.15, "learning_rate": 1.2828234109925137e-05, "loss": 1.3589, "step": 181000 }, { "epoch": 11.18, "learning_rate": 1.2807264034223163e-05, "loss": 1.3601, "step": 181500 }, { "epoch": 11.21, "learning_rate": 1.2786293958521191e-05, "loss": 1.3621, "step": 182000 }, { "epoch": 11.25, "learning_rate": 1.2765323882819218e-05, "loss": 1.3605, "step": 182500 }, { "epoch": 11.28, "learning_rate": 1.2744353807117244e-05, "loss": 1.3596, "step": 183000 }, { "epoch": 11.31, "learning_rate": 1.272338373141527e-05, "loss": 1.3597, "step": 183500 }, { "epoch": 11.34, "learning_rate": 1.2702413655713296e-05, "loss": 1.3599, "step": 184000 }, { "epoch": 11.37, "learning_rate": 1.2681443580011326e-05, "loss": 1.3595, "step": 184500 }, { "epoch": 11.4, "learning_rate": 1.2660473504309352e-05, "loss": 1.3613, "step": 185000 }, { "epoch": 11.43, "learning_rate": 1.2639503428607379e-05, "loss": 1.3594, "step": 185500 }, { "epoch": 11.46, "learning_rate": 1.2618533352905405e-05, "loss": 1.358, "step": 186000 }, { "epoch": 11.49, "learning_rate": 1.2597563277203431e-05, "loss": 1.3542, "step": 186500 }, { "epoch": 11.52, "learning_rate": 1.2576593201501459e-05, "loss": 1.3655, "step": 187000 }, { "epoch": 11.55, "learning_rate": 1.2555623125799485e-05, "loss": 1.3545, "step": 187500 }, { "epoch": 11.58, "learning_rate": 1.2534653050097511e-05, "loss": 1.3558, "step": 188000 }, { "epoch": 11.62, "learning_rate": 1.2513682974395538e-05, "loss": 1.3526, "step": 188500 }, { "epoch": 11.65, "learning_rate": 1.2492712898693566e-05, "loss": 1.3565, "step": 189000 }, { "epoch": 11.68, "learning_rate": 1.2471742822991592e-05, "loss": 1.3515, "step": 189500 }, { "epoch": 11.71, "learning_rate": 1.2450772747289618e-05, "loss": 1.3506, "step": 190000 }, { "epoch": 11.74, "learning_rate": 1.2429802671587644e-05, "loss": 1.3578, "step": 190500 }, { "epoch": 11.77, "learning_rate": 1.240883259588567e-05, "loss": 1.3566, "step": 191000 }, { "epoch": 11.8, "learning_rate": 1.23878625201837e-05, "loss": 1.3566, "step": 191500 }, { "epoch": 11.83, "learning_rate": 1.2366892444481727e-05, "loss": 1.3562, "step": 192000 }, { "epoch": 11.86, "learning_rate": 1.2345922368779753e-05, "loss": 1.3509, "step": 192500 }, { "epoch": 11.89, "learning_rate": 1.2324952293077779e-05, "loss": 1.3492, "step": 193000 }, { "epoch": 11.92, "learning_rate": 1.2303982217375805e-05, "loss": 1.3487, "step": 193500 }, { "epoch": 11.95, "learning_rate": 1.2283012141673833e-05, "loss": 1.3525, "step": 194000 }, { "epoch": 11.98, "learning_rate": 1.226204206597186e-05, "loss": 1.3531, "step": 194500 }, { "epoch": 12.02, "learning_rate": 1.2241071990269886e-05, "loss": 1.3475, "step": 195000 }, { "epoch": 12.05, "learning_rate": 1.2220101914567912e-05, "loss": 1.3472, "step": 195500 }, { "epoch": 12.08, "learning_rate": 1.2199131838865938e-05, "loss": 1.3536, "step": 196000 }, { "epoch": 12.11, "learning_rate": 1.2178161763163968e-05, "loss": 1.3525, "step": 196500 }, { "epoch": 12.14, "learning_rate": 1.2157191687461994e-05, "loss": 1.3526, "step": 197000 }, { "epoch": 12.17, "learning_rate": 1.213622161176002e-05, "loss": 1.3515, "step": 197500 }, { "epoch": 12.2, "learning_rate": 1.2115251536058047e-05, "loss": 1.3457, "step": 198000 }, { "epoch": 12.23, "learning_rate": 1.2094281460356073e-05, "loss": 1.3538, "step": 198500 }, { "epoch": 12.26, "learning_rate": 1.20733113846541e-05, "loss": 1.3506, "step": 199000 }, { "epoch": 12.29, "learning_rate": 1.2052341308952127e-05, "loss": 1.3438, "step": 199500 }, { "epoch": 12.32, "learning_rate": 1.2031371233250153e-05, "loss": 1.3471, "step": 200000 }, { "epoch": 12.35, "learning_rate": 1.201040115754818e-05, "loss": 1.352, "step": 200500 }, { "epoch": 12.39, "learning_rate": 1.1989431081846206e-05, "loss": 1.3458, "step": 201000 }, { "epoch": 12.42, "learning_rate": 1.1968461006144234e-05, "loss": 1.3539, "step": 201500 }, { "epoch": 12.45, "learning_rate": 1.194749093044226e-05, "loss": 1.3478, "step": 202000 }, { "epoch": 12.48, "learning_rate": 1.1926520854740286e-05, "loss": 1.347, "step": 202500 }, { "epoch": 12.51, "learning_rate": 1.1905550779038312e-05, "loss": 1.3503, "step": 203000 }, { "epoch": 12.54, "learning_rate": 1.1884580703336339e-05, "loss": 1.3459, "step": 203500 }, { "epoch": 12.57, "learning_rate": 1.1863610627634368e-05, "loss": 1.3464, "step": 204000 }, { "epoch": 12.6, "learning_rate": 1.1842640551932395e-05, "loss": 1.3463, "step": 204500 }, { "epoch": 12.63, "learning_rate": 1.182167047623042e-05, "loss": 1.3512, "step": 205000 }, { "epoch": 12.66, "learning_rate": 1.1800700400528447e-05, "loss": 1.344, "step": 205500 }, { "epoch": 12.69, "learning_rate": 1.1779730324826473e-05, "loss": 1.3481, "step": 206000 }, { "epoch": 12.72, "learning_rate": 1.1758760249124501e-05, "loss": 1.3392, "step": 206500 }, { "epoch": 12.75, "learning_rate": 1.1737790173422527e-05, "loss": 1.3333, "step": 207000 }, { "epoch": 12.79, "learning_rate": 1.1716820097720554e-05, "loss": 1.3428, "step": 207500 }, { "epoch": 12.82, "learning_rate": 1.169585002201858e-05, "loss": 1.3449, "step": 208000 }, { "epoch": 12.85, "learning_rate": 1.1674879946316606e-05, "loss": 1.3458, "step": 208500 }, { "epoch": 12.88, "learning_rate": 1.1653909870614634e-05, "loss": 1.3378, "step": 209000 }, { "epoch": 12.91, "learning_rate": 1.163293979491266e-05, "loss": 1.3392, "step": 209500 }, { "epoch": 12.94, "learning_rate": 1.1611969719210687e-05, "loss": 1.3436, "step": 210000 }, { "epoch": 12.97, "learning_rate": 1.1590999643508713e-05, "loss": 1.3411, "step": 210500 }, { "epoch": 13.0, "learning_rate": 1.1570029567806739e-05, "loss": 1.3425, "step": 211000 }, { "epoch": 13.03, "learning_rate": 1.1549059492104769e-05, "loss": 1.3406, "step": 211500 }, { "epoch": 13.06, "learning_rate": 1.1528089416402795e-05, "loss": 1.3393, "step": 212000 }, { "epoch": 13.09, "learning_rate": 1.1507119340700821e-05, "loss": 1.3422, "step": 212500 }, { "epoch": 13.12, "learning_rate": 1.1486149264998848e-05, "loss": 1.3359, "step": 213000 }, { "epoch": 13.16, "learning_rate": 1.1465179189296874e-05, "loss": 1.335, "step": 213500 }, { "epoch": 13.19, "learning_rate": 1.1444209113594902e-05, "loss": 1.3396, "step": 214000 }, { "epoch": 13.22, "learning_rate": 1.1423239037892928e-05, "loss": 1.3373, "step": 214500 }, { "epoch": 13.25, "learning_rate": 1.1402268962190954e-05, "loss": 1.3377, "step": 215000 }, { "epoch": 13.28, "learning_rate": 1.138129888648898e-05, "loss": 1.3372, "step": 215500 }, { "epoch": 13.31, "learning_rate": 1.1360328810787007e-05, "loss": 1.3281, "step": 216000 }, { "epoch": 13.34, "learning_rate": 1.1339358735085035e-05, "loss": 1.3378, "step": 216500 }, { "epoch": 13.37, "learning_rate": 1.1318388659383061e-05, "loss": 1.3313, "step": 217000 }, { "epoch": 13.4, "learning_rate": 1.1297418583681087e-05, "loss": 1.3396, "step": 217500 }, { "epoch": 13.43, "learning_rate": 1.1276448507979113e-05, "loss": 1.3375, "step": 218000 }, { "epoch": 13.46, "learning_rate": 1.125547843227714e-05, "loss": 1.3345, "step": 218500 }, { "epoch": 13.49, "learning_rate": 1.123450835657517e-05, "loss": 1.336, "step": 219000 }, { "epoch": 13.53, "learning_rate": 1.1213538280873195e-05, "loss": 1.336, "step": 219500 }, { "epoch": 13.56, "learning_rate": 1.1192568205171222e-05, "loss": 1.3383, "step": 220000 }, { "epoch": 13.59, "learning_rate": 1.1171598129469248e-05, "loss": 1.3372, "step": 220500 }, { "epoch": 13.62, "learning_rate": 1.1150628053767274e-05, "loss": 1.33, "step": 221000 }, { "epoch": 13.65, "learning_rate": 1.1129657978065302e-05, "loss": 1.3366, "step": 221500 }, { "epoch": 13.68, "learning_rate": 1.1108687902363328e-05, "loss": 1.3339, "step": 222000 }, { "epoch": 13.71, "learning_rate": 1.1087717826661355e-05, "loss": 1.3392, "step": 222500 }, { "epoch": 13.74, "learning_rate": 1.1066747750959381e-05, "loss": 1.3307, "step": 223000 }, { "epoch": 13.77, "learning_rate": 1.1045777675257407e-05, "loss": 1.3412, "step": 223500 }, { "epoch": 13.8, "learning_rate": 1.1024807599555437e-05, "loss": 1.339, "step": 224000 }, { "epoch": 13.83, "learning_rate": 1.1003837523853463e-05, "loss": 1.336, "step": 224500 }, { "epoch": 13.86, "learning_rate": 1.098286744815149e-05, "loss": 1.3337, "step": 225000 }, { "epoch": 13.89, "learning_rate": 1.0961897372449516e-05, "loss": 1.3322, "step": 225500 }, { "epoch": 13.93, "learning_rate": 1.0940927296747542e-05, "loss": 1.3313, "step": 226000 }, { "epoch": 13.96, "learning_rate": 1.091995722104557e-05, "loss": 1.3289, "step": 226500 }, { "epoch": 13.99, "learning_rate": 1.0898987145343596e-05, "loss": 1.3371, "step": 227000 }, { "epoch": 14.02, "learning_rate": 1.0878017069641622e-05, "loss": 1.3318, "step": 227500 }, { "epoch": 14.05, "learning_rate": 1.0857046993939648e-05, "loss": 1.3302, "step": 228000 }, { "epoch": 14.08, "learning_rate": 1.0836076918237676e-05, "loss": 1.3276, "step": 228500 }, { "epoch": 14.11, "learning_rate": 1.0815106842535703e-05, "loss": 1.3294, "step": 229000 }, { "epoch": 14.14, "learning_rate": 1.0794136766833729e-05, "loss": 1.3297, "step": 229500 }, { "epoch": 14.17, "learning_rate": 1.0773166691131755e-05, "loss": 1.3238, "step": 230000 }, { "epoch": 14.2, "learning_rate": 1.0752196615429781e-05, "loss": 1.3286, "step": 230500 }, { "epoch": 14.23, "learning_rate": 1.0731226539727811e-05, "loss": 1.3285, "step": 231000 }, { "epoch": 14.26, "learning_rate": 1.0710256464025837e-05, "loss": 1.3294, "step": 231500 }, { "epoch": 14.3, "learning_rate": 1.0689286388323864e-05, "loss": 1.3311, "step": 232000 }, { "epoch": 14.33, "learning_rate": 1.066831631262189e-05, "loss": 1.3265, "step": 232500 }, { "epoch": 14.36, "learning_rate": 1.0647346236919916e-05, "loss": 1.3249, "step": 233000 }, { "epoch": 14.39, "learning_rate": 1.0626376161217944e-05, "loss": 1.3237, "step": 233500 }, { "epoch": 14.42, "learning_rate": 1.060540608551597e-05, "loss": 1.3308, "step": 234000 }, { "epoch": 14.45, "learning_rate": 1.0584436009813996e-05, "loss": 1.3268, "step": 234500 }, { "epoch": 14.48, "learning_rate": 1.0563465934112023e-05, "loss": 1.3246, "step": 235000 }, { "epoch": 14.51, "learning_rate": 1.0542495858410049e-05, "loss": 1.3308, "step": 235500 }, { "epoch": 14.54, "learning_rate": 1.0521525782708077e-05, "loss": 1.3237, "step": 236000 }, { "epoch": 14.57, "learning_rate": 1.0500555707006103e-05, "loss": 1.33, "step": 236500 }, { "epoch": 14.6, "learning_rate": 1.047958563130413e-05, "loss": 1.3233, "step": 237000 }, { "epoch": 14.63, "learning_rate": 1.0458615555602156e-05, "loss": 1.3297, "step": 237500 }, { "epoch": 14.67, "learning_rate": 1.0437645479900182e-05, "loss": 1.3294, "step": 238000 }, { "epoch": 14.7, "learning_rate": 1.0416675404198212e-05, "loss": 1.3229, "step": 238500 }, { "epoch": 14.73, "learning_rate": 1.0395705328496238e-05, "loss": 1.3252, "step": 239000 }, { "epoch": 14.76, "learning_rate": 1.0374735252794264e-05, "loss": 1.3222, "step": 239500 }, { "epoch": 14.79, "learning_rate": 1.035376517709229e-05, "loss": 1.3243, "step": 240000 }, { "epoch": 14.82, "learning_rate": 1.0332795101390316e-05, "loss": 1.3217, "step": 240500 }, { "epoch": 14.85, "learning_rate": 1.0311825025688344e-05, "loss": 1.3261, "step": 241000 }, { "epoch": 14.88, "learning_rate": 1.029085494998637e-05, "loss": 1.3253, "step": 241500 }, { "epoch": 14.91, "learning_rate": 1.0269884874284397e-05, "loss": 1.3211, "step": 242000 }, { "epoch": 14.94, "learning_rate": 1.0248914798582423e-05, "loss": 1.325, "step": 242500 }, { "epoch": 14.97, "learning_rate": 1.022794472288045e-05, "loss": 1.331, "step": 243000 }, { "epoch": 15.0, "learning_rate": 1.0206974647178477e-05, "loss": 1.3201, "step": 243500 }, { "epoch": 15.03, "learning_rate": 1.0186004571476504e-05, "loss": 1.3229, "step": 244000 }, { "epoch": 15.07, "learning_rate": 1.016503449577453e-05, "loss": 1.3253, "step": 244500 }, { "epoch": 15.1, "learning_rate": 1.0144064420072556e-05, "loss": 1.3235, "step": 245000 }, { "epoch": 15.13, "learning_rate": 1.0123094344370582e-05, "loss": 1.3269, "step": 245500 }, { "epoch": 15.16, "learning_rate": 1.0102124268668612e-05, "loss": 1.3211, "step": 246000 }, { "epoch": 15.19, "learning_rate": 1.0081154192966638e-05, "loss": 1.3222, "step": 246500 }, { "epoch": 15.22, "learning_rate": 1.0060184117264664e-05, "loss": 1.3162, "step": 247000 }, { "epoch": 15.25, "learning_rate": 1.003921404156269e-05, "loss": 1.3243, "step": 247500 }, { "epoch": 15.28, "learning_rate": 1.0018243965860717e-05, "loss": 1.3196, "step": 248000 }, { "epoch": 15.31, "learning_rate": 9.997273890158743e-06, "loss": 1.3228, "step": 248500 }, { "epoch": 15.34, "learning_rate": 9.976303814456771e-06, "loss": 1.3166, "step": 249000 }, { "epoch": 15.37, "learning_rate": 9.955333738754797e-06, "loss": 1.3183, "step": 249500 }, { "epoch": 15.4, "learning_rate": 9.934363663052824e-06, "loss": 1.3199, "step": 250000 }, { "epoch": 15.44, "learning_rate": 9.913393587350852e-06, "loss": 1.316, "step": 250500 }, { "epoch": 15.47, "learning_rate": 9.892423511648878e-06, "loss": 1.3208, "step": 251000 }, { "epoch": 15.5, "learning_rate": 9.871453435946906e-06, "loss": 1.3207, "step": 251500 }, { "epoch": 15.53, "learning_rate": 9.850483360244932e-06, "loss": 1.3233, "step": 252000 }, { "epoch": 15.56, "learning_rate": 9.829513284542958e-06, "loss": 1.3193, "step": 252500 }, { "epoch": 15.59, "learning_rate": 9.808543208840985e-06, "loss": 1.3207, "step": 253000 }, { "epoch": 15.62, "learning_rate": 9.78757313313901e-06, "loss": 1.3271, "step": 253500 }, { "epoch": 15.65, "learning_rate": 9.766603057437039e-06, "loss": 1.3233, "step": 254000 }, { "epoch": 15.68, "learning_rate": 9.745632981735065e-06, "loss": 1.316, "step": 254500 }, { "epoch": 15.71, "learning_rate": 9.724662906033091e-06, "loss": 1.3188, "step": 255000 }, { "epoch": 15.74, "learning_rate": 9.703692830331119e-06, "loss": 1.3183, "step": 255500 }, { "epoch": 15.77, "learning_rate": 9.682722754629145e-06, "loss": 1.3248, "step": 256000 }, { "epoch": 15.81, "learning_rate": 9.661752678927172e-06, "loss": 1.3113, "step": 256500 }, { "epoch": 15.84, "learning_rate": 9.640782603225198e-06, "loss": 1.3195, "step": 257000 }, { "epoch": 15.87, "learning_rate": 9.619812527523226e-06, "loss": 1.3179, "step": 257500 }, { "epoch": 15.9, "learning_rate": 9.598842451821252e-06, "loss": 1.3163, "step": 258000 }, { "epoch": 15.93, "learning_rate": 9.577872376119278e-06, "loss": 1.3124, "step": 258500 }, { "epoch": 15.96, "learning_rate": 9.556902300417306e-06, "loss": 1.3143, "step": 259000 }, { "epoch": 15.99, "learning_rate": 9.535932224715332e-06, "loss": 1.31, "step": 259500 }, { "epoch": 16.02, "learning_rate": 9.514962149013359e-06, "loss": 1.3128, "step": 260000 }, { "epoch": 16.05, "learning_rate": 9.493992073311385e-06, "loss": 1.3154, "step": 260500 }, { "epoch": 16.08, "learning_rate": 9.473021997609411e-06, "loss": 1.3104, "step": 261000 }, { "epoch": 16.11, "learning_rate": 9.45205192190744e-06, "loss": 1.3185, "step": 261500 }, { "epoch": 16.14, "learning_rate": 9.431081846205465e-06, "loss": 1.3144, "step": 262000 }, { "epoch": 16.17, "learning_rate": 9.410111770503493e-06, "loss": 1.318, "step": 262500 }, { "epoch": 16.21, "learning_rate": 9.38914169480152e-06, "loss": 1.3094, "step": 263000 }, { "epoch": 16.24, "learning_rate": 9.368171619099546e-06, "loss": 1.3149, "step": 263500 }, { "epoch": 16.27, "learning_rate": 9.347201543397572e-06, "loss": 1.3144, "step": 264000 }, { "epoch": 16.3, "learning_rate": 9.326231467695598e-06, "loss": 1.3162, "step": 264500 }, { "epoch": 16.33, "learning_rate": 9.305261391993626e-06, "loss": 1.3158, "step": 265000 }, { "epoch": 16.36, "learning_rate": 9.284291316291653e-06, "loss": 1.3096, "step": 265500 }, { "epoch": 16.39, "learning_rate": 9.263321240589679e-06, "loss": 1.3145, "step": 266000 }, { "epoch": 16.42, "learning_rate": 9.242351164887707e-06, "loss": 1.3126, "step": 266500 }, { "epoch": 16.45, "learning_rate": 9.221381089185733e-06, "loss": 1.3086, "step": 267000 }, { "epoch": 16.48, "learning_rate": 9.20041101348376e-06, "loss": 1.3075, "step": 267500 }, { "epoch": 16.51, "learning_rate": 9.179440937781785e-06, "loss": 1.3131, "step": 268000 }, { "epoch": 16.54, "learning_rate": 9.158470862079812e-06, "loss": 1.312, "step": 268500 }, { "epoch": 16.58, "learning_rate": 9.13750078637784e-06, "loss": 1.317, "step": 269000 }, { "epoch": 16.61, "learning_rate": 9.116530710675866e-06, "loss": 1.3111, "step": 269500 }, { "epoch": 16.64, "learning_rate": 9.095560634973894e-06, "loss": 1.3057, "step": 270000 }, { "epoch": 16.67, "learning_rate": 9.07459055927192e-06, "loss": 1.311, "step": 270500 }, { "epoch": 16.7, "learning_rate": 9.053620483569946e-06, "loss": 1.3112, "step": 271000 }, { "epoch": 16.73, "learning_rate": 9.032650407867973e-06, "loss": 1.3145, "step": 271500 }, { "epoch": 16.76, "learning_rate": 9.011680332165999e-06, "loss": 1.3092, "step": 272000 }, { "epoch": 16.79, "learning_rate": 8.990710256464027e-06, "loss": 1.3128, "step": 272500 }, { "epoch": 16.82, "learning_rate": 8.969740180762053e-06, "loss": 1.3098, "step": 273000 }, { "epoch": 16.85, "learning_rate": 8.94877010506008e-06, "loss": 1.3087, "step": 273500 }, { "epoch": 16.88, "learning_rate": 8.927800029358107e-06, "loss": 1.309, "step": 274000 }, { "epoch": 16.91, "learning_rate": 8.906829953656133e-06, "loss": 1.3106, "step": 274500 }, { "epoch": 16.94, "learning_rate": 8.88585987795416e-06, "loss": 1.3093, "step": 275000 }, { "epoch": 16.98, "learning_rate": 8.864889802252186e-06, "loss": 1.3075, "step": 275500 }, { "epoch": 17.01, "learning_rate": 8.843919726550212e-06, "loss": 1.3093, "step": 276000 }, { "epoch": 17.04, "learning_rate": 8.82294965084824e-06, "loss": 1.3107, "step": 276500 }, { "epoch": 17.07, "learning_rate": 8.801979575146266e-06, "loss": 1.3104, "step": 277000 }, { "epoch": 17.1, "learning_rate": 8.781009499444294e-06, "loss": 1.3117, "step": 277500 }, { "epoch": 17.13, "learning_rate": 8.76003942374232e-06, "loss": 1.3042, "step": 278000 }, { "epoch": 17.16, "learning_rate": 8.739069348040349e-06, "loss": 1.3026, "step": 278500 }, { "epoch": 17.19, "learning_rate": 8.718099272338375e-06, "loss": 1.3066, "step": 279000 }, { "epoch": 17.22, "learning_rate": 8.697129196636401e-06, "loss": 1.2996, "step": 279500 }, { "epoch": 17.25, "learning_rate": 8.676159120934427e-06, "loss": 1.3066, "step": 280000 }, { "epoch": 17.28, "learning_rate": 8.655189045232453e-06, "loss": 1.3032, "step": 280500 }, { "epoch": 17.31, "learning_rate": 8.634218969530481e-06, "loss": 1.3055, "step": 281000 }, { "epoch": 17.35, "learning_rate": 8.613248893828508e-06, "loss": 1.3061, "step": 281500 }, { "epoch": 17.38, "learning_rate": 8.592278818126534e-06, "loss": 1.3043, "step": 282000 }, { "epoch": 17.41, "learning_rate": 8.571308742424562e-06, "loss": 1.3089, "step": 282500 }, { "epoch": 17.44, "learning_rate": 8.550338666722588e-06, "loss": 1.3078, "step": 283000 }, { "epoch": 17.47, "learning_rate": 8.529368591020614e-06, "loss": 1.3042, "step": 283500 }, { "epoch": 17.5, "learning_rate": 8.50839851531864e-06, "loss": 1.3045, "step": 284000 }, { "epoch": 17.53, "learning_rate": 8.487428439616667e-06, "loss": 1.3074, "step": 284500 }, { "epoch": 17.56, "learning_rate": 8.466458363914695e-06, "loss": 1.3, "step": 285000 }, { "epoch": 17.59, "learning_rate": 8.445488288212721e-06, "loss": 1.3044, "step": 285500 }, { "epoch": 17.62, "learning_rate": 8.424518212510749e-06, "loss": 1.3092, "step": 286000 }, { "epoch": 17.65, "learning_rate": 8.403548136808775e-06, "loss": 1.2999, "step": 286500 }, { "epoch": 17.68, "learning_rate": 8.382578061106801e-06, "loss": 1.3109, "step": 287000 }, { "epoch": 17.72, "learning_rate": 8.361607985404828e-06, "loss": 1.3071, "step": 287500 }, { "epoch": 17.75, "learning_rate": 8.340637909702854e-06, "loss": 1.3054, "step": 288000 }, { "epoch": 17.78, "learning_rate": 8.319667834000882e-06, "loss": 1.3018, "step": 288500 }, { "epoch": 17.81, "learning_rate": 8.298697758298908e-06, "loss": 1.3061, "step": 289000 }, { "epoch": 17.84, "learning_rate": 8.277727682596934e-06, "loss": 1.3032, "step": 289500 }, { "epoch": 17.87, "learning_rate": 8.256757606894962e-06, "loss": 1.3088, "step": 290000 }, { "epoch": 17.9, "learning_rate": 8.235787531192989e-06, "loss": 1.3006, "step": 290500 }, { "epoch": 17.93, "learning_rate": 8.214817455491015e-06, "loss": 1.3041, "step": 291000 }, { "epoch": 17.96, "learning_rate": 8.193847379789041e-06, "loss": 1.3017, "step": 291500 }, { "epoch": 17.99, "learning_rate": 8.172877304087067e-06, "loss": 1.3003, "step": 292000 }, { "epoch": 18.02, "learning_rate": 8.151907228385095e-06, "loss": 1.3033, "step": 292500 }, { "epoch": 18.05, "learning_rate": 8.130937152683122e-06, "loss": 1.2964, "step": 293000 }, { "epoch": 18.08, "learning_rate": 8.10996707698115e-06, "loss": 1.299, "step": 293500 }, { "epoch": 18.12, "learning_rate": 8.088997001279176e-06, "loss": 1.3047, "step": 294000 }, { "epoch": 18.15, "learning_rate": 8.068026925577202e-06, "loss": 1.3035, "step": 294500 }, { "epoch": 18.18, "learning_rate": 8.047056849875228e-06, "loss": 1.3021, "step": 295000 }, { "epoch": 18.21, "learning_rate": 8.026086774173254e-06, "loss": 1.3094, "step": 295500 }, { "epoch": 18.24, "learning_rate": 8.005116698471282e-06, "loss": 1.2999, "step": 296000 }, { "epoch": 18.27, "learning_rate": 7.984146622769309e-06, "loss": 1.2984, "step": 296500 }, { "epoch": 18.3, "learning_rate": 7.963176547067337e-06, "loss": 1.2982, "step": 297000 }, { "epoch": 18.33, "learning_rate": 7.942206471365363e-06, "loss": 1.3021, "step": 297500 }, { "epoch": 18.36, "learning_rate": 7.921236395663389e-06, "loss": 1.2956, "step": 298000 }, { "epoch": 18.39, "learning_rate": 7.900266319961415e-06, "loss": 1.2943, "step": 298500 }, { "epoch": 18.42, "learning_rate": 7.879296244259442e-06, "loss": 1.3039, "step": 299000 }, { "epoch": 18.45, "learning_rate": 7.85832616855747e-06, "loss": 1.2958, "step": 299500 }, { "epoch": 18.49, "learning_rate": 7.837356092855496e-06, "loss": 1.2928, "step": 300000 }, { "epoch": 18.52, "learning_rate": 7.816386017153522e-06, "loss": 1.2986, "step": 300500 }, { "epoch": 18.55, "learning_rate": 7.79541594145155e-06, "loss": 1.3018, "step": 301000 }, { "epoch": 18.58, "learning_rate": 7.774445865749576e-06, "loss": 1.3009, "step": 301500 }, { "epoch": 18.61, "learning_rate": 7.753475790047602e-06, "loss": 1.3003, "step": 302000 }, { "epoch": 18.64, "learning_rate": 7.732505714345629e-06, "loss": 1.2967, "step": 302500 }, { "epoch": 18.67, "learning_rate": 7.711535638643655e-06, "loss": 1.2978, "step": 303000 }, { "epoch": 18.7, "learning_rate": 7.690565562941683e-06, "loss": 1.2977, "step": 303500 }, { "epoch": 18.73, "learning_rate": 7.669595487239709e-06, "loss": 1.2957, "step": 304000 }, { "epoch": 18.76, "learning_rate": 7.648625411537737e-06, "loss": 1.2994, "step": 304500 }, { "epoch": 18.79, "learning_rate": 7.627655335835763e-06, "loss": 1.2978, "step": 305000 }, { "epoch": 18.82, "learning_rate": 7.6066852601337895e-06, "loss": 1.2934, "step": 305500 }, { "epoch": 18.86, "learning_rate": 7.585715184431817e-06, "loss": 1.2969, "step": 306000 }, { "epoch": 18.89, "learning_rate": 7.564745108729843e-06, "loss": 1.2997, "step": 306500 }, { "epoch": 18.92, "learning_rate": 7.54377503302787e-06, "loss": 1.2984, "step": 307000 }, { "epoch": 18.95, "learning_rate": 7.522804957325896e-06, "loss": 1.2957, "step": 307500 }, { "epoch": 18.98, "learning_rate": 7.5018348816239225e-06, "loss": 1.304, "step": 308000 }, { "epoch": 19.01, "learning_rate": 7.48086480592195e-06, "loss": 1.2993, "step": 308500 }, { "epoch": 19.04, "learning_rate": 7.459894730219977e-06, "loss": 1.2971, "step": 309000 }, { "epoch": 19.07, "learning_rate": 7.438924654518004e-06, "loss": 1.2952, "step": 309500 }, { "epoch": 19.1, "learning_rate": 7.41795457881603e-06, "loss": 1.2903, "step": 310000 }, { "epoch": 19.13, "learning_rate": 7.396984503114056e-06, "loss": 1.2917, "step": 310500 }, { "epoch": 19.16, "learning_rate": 7.376014427412083e-06, "loss": 1.2967, "step": 311000 }, { "epoch": 19.19, "learning_rate": 7.35504435171011e-06, "loss": 1.2945, "step": 311500 }, { "epoch": 19.22, "learning_rate": 7.3340742760081375e-06, "loss": 1.2947, "step": 312000 }, { "epoch": 19.26, "learning_rate": 7.313104200306164e-06, "loss": 1.2929, "step": 312500 }, { "epoch": 19.29, "learning_rate": 7.29213412460419e-06, "loss": 1.2942, "step": 313000 }, { "epoch": 19.32, "learning_rate": 7.271164048902217e-06, "loss": 1.2931, "step": 313500 }, { "epoch": 19.35, "learning_rate": 7.250193973200243e-06, "loss": 1.2932, "step": 314000 }, { "epoch": 19.38, "learning_rate": 7.229223897498271e-06, "loss": 1.2944, "step": 314500 }, { "epoch": 19.41, "learning_rate": 7.2082538217962975e-06, "loss": 1.2957, "step": 315000 }, { "epoch": 19.44, "learning_rate": 7.187283746094324e-06, "loss": 1.2971, "step": 315500 }, { "epoch": 19.47, "learning_rate": 7.166313670392351e-06, "loss": 1.2964, "step": 316000 }, { "epoch": 19.5, "learning_rate": 7.145343594690377e-06, "loss": 1.2943, "step": 316500 }, { "epoch": 19.53, "learning_rate": 7.124373518988404e-06, "loss": 1.2935, "step": 317000 }, { "epoch": 19.56, "learning_rate": 7.1034034432864305e-06, "loss": 1.2963, "step": 317500 }, { "epoch": 19.59, "learning_rate": 7.082433367584458e-06, "loss": 1.2899, "step": 318000 }, { "epoch": 19.63, "learning_rate": 7.061463291882485e-06, "loss": 1.2935, "step": 318500 }, { "epoch": 19.66, "learning_rate": 7.040493216180511e-06, "loss": 1.2964, "step": 319000 }, { "epoch": 19.69, "learning_rate": 7.019523140478538e-06, "loss": 1.2892, "step": 319500 }, { "epoch": 19.72, "learning_rate": 6.998553064776564e-06, "loss": 1.2942, "step": 320000 }, { "epoch": 19.75, "learning_rate": 6.977582989074591e-06, "loss": 1.2943, "step": 320500 }, { "epoch": 19.78, "learning_rate": 6.956612913372618e-06, "loss": 1.2904, "step": 321000 }, { "epoch": 19.81, "learning_rate": 6.935642837670644e-06, "loss": 1.294, "step": 321500 }, { "epoch": 19.84, "learning_rate": 6.914672761968672e-06, "loss": 1.2958, "step": 322000 }, { "epoch": 19.87, "learning_rate": 6.893702686266698e-06, "loss": 1.2941, "step": 322500 }, { "epoch": 19.9, "learning_rate": 6.872732610564725e-06, "loss": 1.2935, "step": 323000 }, { "epoch": 19.93, "learning_rate": 6.851762534862751e-06, "loss": 1.2917, "step": 323500 }, { "epoch": 19.96, "learning_rate": 6.830792459160778e-06, "loss": 1.2899, "step": 324000 }, { "epoch": 20.0, "learning_rate": 6.809822383458805e-06, "loss": 1.2946, "step": 324500 }, { "epoch": 20.03, "learning_rate": 6.788852307756831e-06, "loss": 1.293, "step": 325000 }, { "epoch": 20.06, "learning_rate": 6.767882232054859e-06, "loss": 1.2877, "step": 325500 }, { "epoch": 20.09, "learning_rate": 6.746912156352885e-06, "loss": 1.2873, "step": 326000 }, { "epoch": 20.12, "learning_rate": 6.725942080650911e-06, "loss": 1.2932, "step": 326500 }, { "epoch": 20.15, "learning_rate": 6.7049720049489385e-06, "loss": 1.2928, "step": 327000 }, { "epoch": 20.18, "learning_rate": 6.684001929246965e-06, "loss": 1.2875, "step": 327500 }, { "epoch": 20.21, "learning_rate": 6.663031853544993e-06, "loss": 1.2935, "step": 328000 }, { "epoch": 20.24, "learning_rate": 6.642061777843019e-06, "loss": 1.2839, "step": 328500 }, { "epoch": 20.27, "learning_rate": 6.621091702141045e-06, "loss": 1.2932, "step": 329000 }, { "epoch": 20.3, "learning_rate": 6.600121626439072e-06, "loss": 1.2851, "step": 329500 }, { "epoch": 20.33, "learning_rate": 6.5791515507370985e-06, "loss": 1.293, "step": 330000 }, { "epoch": 20.36, "learning_rate": 6.558181475035126e-06, "loss": 1.2895, "step": 330500 }, { "epoch": 20.4, "learning_rate": 6.537211399333152e-06, "loss": 1.2879, "step": 331000 }, { "epoch": 20.43, "learning_rate": 6.516241323631178e-06, "loss": 1.2901, "step": 331500 }, { "epoch": 20.46, "learning_rate": 6.495271247929206e-06, "loss": 1.289, "step": 332000 }, { "epoch": 20.49, "learning_rate": 6.474301172227232e-06, "loss": 1.2876, "step": 332500 }, { "epoch": 20.52, "learning_rate": 6.453331096525259e-06, "loss": 1.288, "step": 333000 }, { "epoch": 20.55, "learning_rate": 6.432361020823286e-06, "loss": 1.2881, "step": 333500 }, { "epoch": 20.58, "learning_rate": 6.411390945121312e-06, "loss": 1.2891, "step": 334000 }, { "epoch": 20.61, "learning_rate": 6.390420869419339e-06, "loss": 1.2864, "step": 334500 }, { "epoch": 20.64, "learning_rate": 6.369450793717365e-06, "loss": 1.2895, "step": 335000 }, { "epoch": 20.67, "learning_rate": 6.348480718015393e-06, "loss": 1.2865, "step": 335500 }, { "epoch": 20.7, "learning_rate": 6.327510642313419e-06, "loss": 1.2809, "step": 336000 }, { "epoch": 20.73, "learning_rate": 6.3065405666114465e-06, "loss": 1.2884, "step": 336500 }, { "epoch": 20.77, "learning_rate": 6.285570490909473e-06, "loss": 1.2866, "step": 337000 }, { "epoch": 20.8, "learning_rate": 6.264600415207499e-06, "loss": 1.2957, "step": 337500 }, { "epoch": 20.83, "learning_rate": 6.243630339505526e-06, "loss": 1.2829, "step": 338000 }, { "epoch": 20.86, "learning_rate": 6.222660263803552e-06, "loss": 1.2866, "step": 338500 }, { "epoch": 20.89, "learning_rate": 6.20169018810158e-06, "loss": 1.2896, "step": 339000 }, { "epoch": 20.92, "learning_rate": 6.1807201123996065e-06, "loss": 1.2863, "step": 339500 }, { "epoch": 20.95, "learning_rate": 6.159750036697633e-06, "loss": 1.2854, "step": 340000 }, { "epoch": 20.98, "learning_rate": 6.13877996099566e-06, "loss": 1.2834, "step": 340500 }, { "epoch": 21.01, "learning_rate": 6.117809885293686e-06, "loss": 1.2887, "step": 341000 }, { "epoch": 21.04, "learning_rate": 6.096839809591714e-06, "loss": 1.2845, "step": 341500 }, { "epoch": 21.07, "learning_rate": 6.07586973388974e-06, "loss": 1.2899, "step": 342000 }, { "epoch": 21.1, "learning_rate": 6.0548996581877665e-06, "loss": 1.2808, "step": 342500 }, { "epoch": 21.14, "learning_rate": 6.033929582485794e-06, "loss": 1.2853, "step": 343000 }, { "epoch": 21.17, "learning_rate": 6.01295950678382e-06, "loss": 1.2858, "step": 343500 }, { "epoch": 21.2, "learning_rate": 5.991989431081847e-06, "loss": 1.288, "step": 344000 }, { "epoch": 21.23, "learning_rate": 5.971019355379873e-06, "loss": 1.281, "step": 344500 }, { "epoch": 21.26, "learning_rate": 5.9500492796778995e-06, "loss": 1.2854, "step": 345000 }, { "epoch": 21.29, "learning_rate": 5.929079203975927e-06, "loss": 1.2904, "step": 345500 }, { "epoch": 21.32, "learning_rate": 5.908109128273954e-06, "loss": 1.2812, "step": 346000 }, { "epoch": 21.35, "learning_rate": 5.887139052571981e-06, "loss": 1.2815, "step": 346500 }, { "epoch": 21.38, "learning_rate": 5.866168976870007e-06, "loss": 1.2881, "step": 347000 }, { "epoch": 21.41, "learning_rate": 5.845198901168033e-06, "loss": 1.2815, "step": 347500 }, { "epoch": 21.44, "learning_rate": 5.82422882546606e-06, "loss": 1.2813, "step": 348000 }, { "epoch": 21.47, "learning_rate": 5.8032587497640866e-06, "loss": 1.2855, "step": 348500 }, { "epoch": 21.5, "learning_rate": 5.7822886740621145e-06, "loss": 1.2856, "step": 349000 }, { "epoch": 21.54, "learning_rate": 5.761318598360141e-06, "loss": 1.2873, "step": 349500 }, { "epoch": 21.57, "learning_rate": 5.740348522658167e-06, "loss": 1.288, "step": 350000 }, { "epoch": 21.6, "learning_rate": 5.719378446956194e-06, "loss": 1.2841, "step": 350500 }, { "epoch": 21.63, "learning_rate": 5.69840837125422e-06, "loss": 1.2827, "step": 351000 }, { "epoch": 21.66, "learning_rate": 5.6774382955522474e-06, "loss": 1.2872, "step": 351500 }, { "epoch": 21.69, "learning_rate": 5.656468219850274e-06, "loss": 1.2843, "step": 352000 }, { "epoch": 21.72, "learning_rate": 5.6354981441483e-06, "loss": 1.2841, "step": 352500 }, { "epoch": 21.75, "learning_rate": 5.614528068446328e-06, "loss": 1.2853, "step": 353000 }, { "epoch": 21.78, "learning_rate": 5.593557992744354e-06, "loss": 1.2827, "step": 353500 }, { "epoch": 21.81, "learning_rate": 5.572587917042381e-06, "loss": 1.2842, "step": 354000 }, { "epoch": 21.84, "learning_rate": 5.5516178413404075e-06, "loss": 1.283, "step": 354500 }, { "epoch": 21.87, "learning_rate": 5.530647765638434e-06, "loss": 1.2859, "step": 355000 }, { "epoch": 21.91, "learning_rate": 5.509677689936462e-06, "loss": 1.279, "step": 355500 }, { "epoch": 21.94, "learning_rate": 5.488707614234488e-06, "loss": 1.2767, "step": 356000 }, { "epoch": 21.97, "learning_rate": 5.467737538532515e-06, "loss": 1.2789, "step": 356500 }, { "epoch": 22.0, "learning_rate": 5.446767462830541e-06, "loss": 1.2863, "step": 357000 }, { "epoch": 22.03, "learning_rate": 5.425797387128568e-06, "loss": 1.2829, "step": 357500 }, { "epoch": 22.06, "learning_rate": 5.4048273114265946e-06, "loss": 1.2766, "step": 358000 }, { "epoch": 22.09, "learning_rate": 5.383857235724621e-06, "loss": 1.2841, "step": 358500 }, { "epoch": 22.12, "learning_rate": 5.362887160022649e-06, "loss": 1.2837, "step": 359000 }, { "epoch": 22.15, "learning_rate": 5.341917084320675e-06, "loss": 1.2837, "step": 359500 }, { "epoch": 22.18, "learning_rate": 5.320947008618702e-06, "loss": 1.2829, "step": 360000 }, { "epoch": 22.21, "learning_rate": 5.299976932916728e-06, "loss": 1.2827, "step": 360500 }, { "epoch": 22.24, "learning_rate": 5.279006857214755e-06, "loss": 1.286, "step": 361000 }, { "epoch": 22.27, "learning_rate": 5.258036781512782e-06, "loss": 1.2832, "step": 361500 }, { "epoch": 22.31, "learning_rate": 5.237066705810808e-06, "loss": 1.2812, "step": 362000 }, { "epoch": 22.34, "learning_rate": 5.216096630108836e-06, "loss": 1.2797, "step": 362500 }, { "epoch": 22.37, "learning_rate": 5.195126554406862e-06, "loss": 1.2752, "step": 363000 }, { "epoch": 22.4, "learning_rate": 5.174156478704888e-06, "loss": 1.2824, "step": 363500 }, { "epoch": 22.43, "learning_rate": 5.1531864030029155e-06, "loss": 1.2782, "step": 364000 }, { "epoch": 22.46, "learning_rate": 5.132216327300942e-06, "loss": 1.2891, "step": 364500 }, { "epoch": 22.49, "learning_rate": 5.111246251598969e-06, "loss": 1.2871, "step": 365000 }, { "epoch": 22.52, "learning_rate": 5.090276175896995e-06, "loss": 1.2844, "step": 365500 }, { "epoch": 22.55, "learning_rate": 5.069306100195021e-06, "loss": 1.2804, "step": 366000 }, { "epoch": 22.58, "learning_rate": 5.048336024493049e-06, "loss": 1.2774, "step": 366500 }, { "epoch": 22.61, "learning_rate": 5.0273659487910755e-06, "loss": 1.2817, "step": 367000 }, { "epoch": 22.64, "learning_rate": 5.0063958730891026e-06, "loss": 1.2802, "step": 367500 }, { "epoch": 22.68, "learning_rate": 4.985425797387129e-06, "loss": 1.2757, "step": 368000 }, { "epoch": 22.71, "learning_rate": 4.964455721685156e-06, "loss": 1.2831, "step": 368500 }, { "epoch": 22.74, "learning_rate": 4.943485645983183e-06, "loss": 1.2814, "step": 369000 }, { "epoch": 22.77, "learning_rate": 4.922515570281209e-06, "loss": 1.2796, "step": 369500 }, { "epoch": 22.8, "learning_rate": 4.9015454945792355e-06, "loss": 1.2783, "step": 370000 }, { "epoch": 22.83, "learning_rate": 4.880575418877263e-06, "loss": 1.2782, "step": 370500 }, { "epoch": 22.86, "learning_rate": 4.85960534317529e-06, "loss": 1.28, "step": 371000 }, { "epoch": 22.89, "learning_rate": 4.838635267473316e-06, "loss": 1.2813, "step": 371500 }, { "epoch": 22.92, "learning_rate": 4.817665191771343e-06, "loss": 1.2784, "step": 372000 }, { "epoch": 22.95, "learning_rate": 4.796695116069369e-06, "loss": 1.2782, "step": 372500 }, { "epoch": 22.98, "learning_rate": 4.775725040367396e-06, "loss": 1.2735, "step": 373000 }, { "epoch": 23.01, "learning_rate": 4.754754964665423e-06, "loss": 1.2787, "step": 373500 }, { "epoch": 23.05, "learning_rate": 4.73378488896345e-06, "loss": 1.2787, "step": 374000 }, { "epoch": 23.08, "learning_rate": 4.712814813261477e-06, "loss": 1.2744, "step": 374500 }, { "epoch": 23.11, "learning_rate": 4.691844737559503e-06, "loss": 1.2754, "step": 375000 }, { "epoch": 23.14, "learning_rate": 4.670874661857529e-06, "loss": 1.2789, "step": 375500 }, { "epoch": 23.17, "learning_rate": 4.649904586155556e-06, "loss": 1.2795, "step": 376000 }, { "epoch": 23.2, "learning_rate": 4.6289345104535835e-06, "loss": 1.2757, "step": 376500 }, { "epoch": 23.23, "learning_rate": 4.60796443475161e-06, "loss": 1.2772, "step": 377000 }, { "epoch": 23.26, "learning_rate": 4.586994359049636e-06, "loss": 1.274, "step": 377500 }, { "epoch": 23.29, "learning_rate": 4.566024283347663e-06, "loss": 1.2771, "step": 378000 }, { "epoch": 23.32, "learning_rate": 4.54505420764569e-06, "loss": 1.277, "step": 378500 }, { "epoch": 23.35, "learning_rate": 4.524084131943716e-06, "loss": 1.2804, "step": 379000 }, { "epoch": 23.38, "learning_rate": 4.5031140562417435e-06, "loss": 1.2783, "step": 379500 }, { "epoch": 23.41, "learning_rate": 4.48214398053977e-06, "loss": 1.2762, "step": 380000 }, { "epoch": 23.45, "learning_rate": 4.461173904837797e-06, "loss": 1.2779, "step": 380500 }, { "epoch": 23.48, "learning_rate": 4.440203829135823e-06, "loss": 1.273, "step": 381000 }, { "epoch": 23.51, "learning_rate": 4.41923375343385e-06, "loss": 1.2811, "step": 381500 }, { "epoch": 23.54, "learning_rate": 4.398263677731877e-06, "loss": 1.2747, "step": 382000 }, { "epoch": 23.57, "learning_rate": 4.3772936020299035e-06, "loss": 1.2711, "step": 382500 }, { "epoch": 23.6, "learning_rate": 4.356323526327931e-06, "loss": 1.2784, "step": 383000 }, { "epoch": 23.63, "learning_rate": 4.335353450625957e-06, "loss": 1.2776, "step": 383500 }, { "epoch": 23.66, "learning_rate": 4.314383374923984e-06, "loss": 1.2702, "step": 384000 }, { "epoch": 23.69, "learning_rate": 4.293413299222011e-06, "loss": 1.2728, "step": 384500 }, { "epoch": 23.72, "learning_rate": 4.272443223520037e-06, "loss": 1.279, "step": 385000 }, { "epoch": 23.75, "learning_rate": 4.2514731478180635e-06, "loss": 1.2786, "step": 385500 }, { "epoch": 23.78, "learning_rate": 4.230503072116091e-06, "loss": 1.2733, "step": 386000 }, { "epoch": 23.82, "learning_rate": 4.209532996414118e-06, "loss": 1.2778, "step": 386500 }, { "epoch": 23.85, "learning_rate": 4.188562920712144e-06, "loss": 1.2726, "step": 387000 }, { "epoch": 23.88, "learning_rate": 4.167592845010171e-06, "loss": 1.2729, "step": 387500 }, { "epoch": 23.91, "learning_rate": 4.146622769308197e-06, "loss": 1.2781, "step": 388000 }, { "epoch": 23.94, "learning_rate": 4.125652693606224e-06, "loss": 1.2811, "step": 388500 }, { "epoch": 23.97, "learning_rate": 4.104682617904251e-06, "loss": 1.2833, "step": 389000 }, { "epoch": 24.0, "learning_rate": 4.083712542202278e-06, "loss": 1.2734, "step": 389500 }, { "epoch": 24.03, "learning_rate": 4.062742466500305e-06, "loss": 1.2759, "step": 390000 }, { "epoch": 24.06, "learning_rate": 4.041772390798331e-06, "loss": 1.2716, "step": 390500 }, { "epoch": 24.09, "learning_rate": 4.020802315096357e-06, "loss": 1.2753, "step": 391000 }, { "epoch": 24.12, "learning_rate": 3.9998322393943844e-06, "loss": 1.2755, "step": 391500 }, { "epoch": 24.15, "learning_rate": 3.9788621636924115e-06, "loss": 1.2715, "step": 392000 }, { "epoch": 24.19, "learning_rate": 3.957892087990438e-06, "loss": 1.2727, "step": 392500 }, { "epoch": 24.22, "learning_rate": 3.936922012288465e-06, "loss": 1.2693, "step": 393000 }, { "epoch": 24.25, "learning_rate": 3.915951936586491e-06, "loss": 1.2767, "step": 393500 }, { "epoch": 24.28, "learning_rate": 3.894981860884518e-06, "loss": 1.271, "step": 394000 }, { "epoch": 24.31, "learning_rate": 3.8740117851825445e-06, "loss": 1.2744, "step": 394500 }, { "epoch": 24.34, "learning_rate": 3.8530417094805716e-06, "loss": 1.2777, "step": 395000 }, { "epoch": 24.37, "learning_rate": 3.832071633778599e-06, "loss": 1.2758, "step": 395500 }, { "epoch": 24.4, "learning_rate": 3.811101558076625e-06, "loss": 1.2717, "step": 396000 }, { "epoch": 24.43, "learning_rate": 3.7901314823746516e-06, "loss": 1.2728, "step": 396500 }, { "epoch": 24.46, "learning_rate": 3.7691614066726782e-06, "loss": 1.2732, "step": 397000 }, { "epoch": 24.49, "learning_rate": 3.7481913309707053e-06, "loss": 1.2742, "step": 397500 }, { "epoch": 24.52, "learning_rate": 3.727221255268732e-06, "loss": 1.2731, "step": 398000 }, { "epoch": 24.55, "learning_rate": 3.7062511795667582e-06, "loss": 1.2732, "step": 398500 }, { "epoch": 24.59, "learning_rate": 3.685281103864785e-06, "loss": 1.2652, "step": 399000 }, { "epoch": 24.62, "learning_rate": 3.664311028162812e-06, "loss": 1.2754, "step": 399500 }, { "epoch": 24.65, "learning_rate": 3.6433409524608387e-06, "loss": 1.2714, "step": 400000 }, { "epoch": 24.68, "learning_rate": 3.6223708767588658e-06, "loss": 1.2773, "step": 400500 }, { "epoch": 24.71, "learning_rate": 3.6014008010568924e-06, "loss": 1.2697, "step": 401000 }, { "epoch": 24.74, "learning_rate": 3.5804307253549187e-06, "loss": 1.2769, "step": 401500 }, { "epoch": 24.77, "learning_rate": 3.5594606496529454e-06, "loss": 1.2767, "step": 402000 }, { "epoch": 24.8, "learning_rate": 3.5384905739509724e-06, "loss": 1.2758, "step": 402500 }, { "epoch": 24.83, "learning_rate": 3.517520498248999e-06, "loss": 1.2686, "step": 403000 }, { "epoch": 24.86, "learning_rate": 3.496550422547026e-06, "loss": 1.2733, "step": 403500 }, { "epoch": 24.89, "learning_rate": 3.475580346845052e-06, "loss": 1.2718, "step": 404000 }, { "epoch": 24.92, "learning_rate": 3.454610271143079e-06, "loss": 1.2678, "step": 404500 }, { "epoch": 24.96, "learning_rate": 3.433640195441106e-06, "loss": 1.2721, "step": 405000 }, { "epoch": 24.99, "learning_rate": 3.4126701197391325e-06, "loss": 1.2799, "step": 405500 }, { "epoch": 25.02, "learning_rate": 3.3917000440371596e-06, "loss": 1.2721, "step": 406000 }, { "epoch": 25.05, "learning_rate": 3.370729968335186e-06, "loss": 1.268, "step": 406500 }, { "epoch": 25.08, "learning_rate": 3.3497598926332125e-06, "loss": 1.2737, "step": 407000 }, { "epoch": 25.11, "learning_rate": 3.3287898169312396e-06, "loss": 1.2692, "step": 407500 }, { "epoch": 25.14, "learning_rate": 3.3078197412292662e-06, "loss": 1.2697, "step": 408000 }, { "epoch": 25.17, "learning_rate": 3.286849665527293e-06, "loss": 1.271, "step": 408500 }, { "epoch": 25.2, "learning_rate": 3.265879589825319e-06, "loss": 1.2711, "step": 409000 }, { "epoch": 25.23, "learning_rate": 3.2449095141233463e-06, "loss": 1.2736, "step": 409500 }, { "epoch": 25.26, "learning_rate": 3.223939438421373e-06, "loss": 1.2667, "step": 410000 }, { "epoch": 25.29, "learning_rate": 3.2029693627193996e-06, "loss": 1.2706, "step": 410500 }, { "epoch": 25.33, "learning_rate": 3.1819992870174267e-06, "loss": 1.276, "step": 411000 }, { "epoch": 25.36, "learning_rate": 3.1610292113154534e-06, "loss": 1.2682, "step": 411500 }, { "epoch": 25.39, "learning_rate": 3.1400591356134796e-06, "loss": 1.2695, "step": 412000 }, { "epoch": 25.42, "learning_rate": 3.1190890599115063e-06, "loss": 1.2733, "step": 412500 }, { "epoch": 25.45, "learning_rate": 3.0981189842095334e-06, "loss": 1.273, "step": 413000 }, { "epoch": 25.48, "learning_rate": 3.07714890850756e-06, "loss": 1.2699, "step": 413500 }, { "epoch": 25.51, "learning_rate": 3.0561788328055867e-06, "loss": 1.2692, "step": 414000 }, { "epoch": 25.54, "learning_rate": 3.0352087571036134e-06, "loss": 1.2688, "step": 414500 }, { "epoch": 25.57, "learning_rate": 3.01423868140164e-06, "loss": 1.27, "step": 415000 }, { "epoch": 25.6, "learning_rate": 2.9932686056996667e-06, "loss": 1.2701, "step": 415500 }, { "epoch": 25.63, "learning_rate": 2.972298529997694e-06, "loss": 1.2712, "step": 416000 }, { "epoch": 25.66, "learning_rate": 2.9513284542957205e-06, "loss": 1.272, "step": 416500 }, { "epoch": 25.69, "learning_rate": 2.9303583785937467e-06, "loss": 1.264, "step": 417000 }, { "epoch": 25.73, "learning_rate": 2.9093883028917734e-06, "loss": 1.2692, "step": 417500 }, { "epoch": 25.76, "learning_rate": 2.8884182271898005e-06, "loss": 1.2689, "step": 418000 }, { "epoch": 25.79, "learning_rate": 2.867448151487827e-06, "loss": 1.2705, "step": 418500 }, { "epoch": 25.82, "learning_rate": 2.846478075785854e-06, "loss": 1.2724, "step": 419000 }, { "epoch": 25.85, "learning_rate": 2.82550800008388e-06, "loss": 1.2646, "step": 419500 }, { "epoch": 25.88, "learning_rate": 2.804537924381907e-06, "loss": 1.2666, "step": 420000 }, { "epoch": 25.91, "learning_rate": 2.783567848679934e-06, "loss": 1.2604, "step": 420500 }, { "epoch": 25.94, "learning_rate": 2.7625977729779605e-06, "loss": 1.2696, "step": 421000 }, { "epoch": 25.97, "learning_rate": 2.7416276972759876e-06, "loss": 1.2694, "step": 421500 }, { "epoch": 26.0, "learning_rate": 2.7206576215740143e-06, "loss": 1.268, "step": 422000 }, { "epoch": 26.03, "learning_rate": 2.6996875458720405e-06, "loss": 1.2649, "step": 422500 }, { "epoch": 26.06, "learning_rate": 2.6787174701700676e-06, "loss": 1.2719, "step": 423000 }, { "epoch": 26.1, "learning_rate": 2.6577473944680943e-06, "loss": 1.2722, "step": 423500 }, { "epoch": 26.13, "learning_rate": 2.636777318766121e-06, "loss": 1.2684, "step": 424000 }, { "epoch": 26.16, "learning_rate": 2.615807243064148e-06, "loss": 1.2734, "step": 424500 }, { "epoch": 26.19, "learning_rate": 2.5948371673621743e-06, "loss": 1.2674, "step": 425000 }, { "epoch": 26.22, "learning_rate": 2.573867091660201e-06, "loss": 1.2631, "step": 425500 }, { "epoch": 26.25, "learning_rate": 2.5528970159582276e-06, "loss": 1.2697, "step": 426000 }, { "epoch": 26.28, "learning_rate": 2.5319269402562547e-06, "loss": 1.2682, "step": 426500 }, { "epoch": 26.31, "learning_rate": 2.5109568645542814e-06, "loss": 1.2729, "step": 427000 }, { "epoch": 26.34, "learning_rate": 2.489986788852308e-06, "loss": 1.2661, "step": 427500 }, { "epoch": 26.37, "learning_rate": 2.4690167131503347e-06, "loss": 1.2705, "step": 428000 }, { "epoch": 26.4, "learning_rate": 2.4480466374483614e-06, "loss": 1.2699, "step": 428500 }, { "epoch": 26.43, "learning_rate": 2.427076561746388e-06, "loss": 1.2705, "step": 429000 }, { "epoch": 26.46, "learning_rate": 2.4061064860444148e-06, "loss": 1.2708, "step": 429500 }, { "epoch": 26.5, "learning_rate": 2.3851364103424414e-06, "loss": 1.2694, "step": 430000 }, { "epoch": 26.53, "learning_rate": 2.3641663346404685e-06, "loss": 1.2632, "step": 430500 }, { "epoch": 26.56, "learning_rate": 2.3431962589384948e-06, "loss": 1.2693, "step": 431000 }, { "epoch": 26.59, "learning_rate": 2.322226183236522e-06, "loss": 1.2687, "step": 431500 }, { "epoch": 26.62, "learning_rate": 2.301256107534548e-06, "loss": 1.2635, "step": 432000 }, { "epoch": 26.65, "learning_rate": 2.280286031832575e-06, "loss": 1.2701, "step": 432500 }, { "epoch": 26.68, "learning_rate": 2.259315956130602e-06, "loss": 1.27, "step": 433000 }, { "epoch": 26.71, "learning_rate": 2.2383458804286285e-06, "loss": 1.2635, "step": 433500 }, { "epoch": 26.74, "learning_rate": 2.2173758047266552e-06, "loss": 1.2722, "step": 434000 }, { "epoch": 26.77, "learning_rate": 2.196405729024682e-06, "loss": 1.2657, "step": 434500 }, { "epoch": 26.8, "learning_rate": 2.1754356533227086e-06, "loss": 1.2601, "step": 435000 }, { "epoch": 26.83, "learning_rate": 2.1544655776207356e-06, "loss": 1.2641, "step": 435500 }, { "epoch": 26.87, "learning_rate": 2.133495501918762e-06, "loss": 1.267, "step": 436000 }, { "epoch": 26.9, "learning_rate": 2.112525426216789e-06, "loss": 1.2722, "step": 436500 }, { "epoch": 26.93, "learning_rate": 2.0915553505148157e-06, "loss": 1.2638, "step": 437000 }, { "epoch": 26.96, "learning_rate": 2.0705852748128423e-06, "loss": 1.269, "step": 437500 }, { "epoch": 26.99, "learning_rate": 2.049615199110869e-06, "loss": 1.2711, "step": 438000 }, { "epoch": 27.02, "learning_rate": 2.0286451234088957e-06, "loss": 1.266, "step": 438500 }, { "epoch": 27.05, "learning_rate": 2.0076750477069223e-06, "loss": 1.2658, "step": 439000 }, { "epoch": 27.08, "learning_rate": 1.986704972004949e-06, "loss": 1.2638, "step": 439500 }, { "epoch": 27.11, "learning_rate": 1.9657348963029757e-06, "loss": 1.2662, "step": 440000 }, { "epoch": 27.14, "learning_rate": 1.9447648206010023e-06, "loss": 1.2596, "step": 440500 }, { "epoch": 27.17, "learning_rate": 1.9237947448990294e-06, "loss": 1.268, "step": 441000 }, { "epoch": 27.2, "learning_rate": 1.902824669197056e-06, "loss": 1.264, "step": 441500 }, { "epoch": 27.24, "learning_rate": 1.8818545934950828e-06, "loss": 1.2689, "step": 442000 }, { "epoch": 27.27, "learning_rate": 1.8608845177931095e-06, "loss": 1.2614, "step": 442500 }, { "epoch": 27.3, "learning_rate": 1.8399144420911361e-06, "loss": 1.2648, "step": 443000 }, { "epoch": 27.33, "learning_rate": 1.8189443663891628e-06, "loss": 1.2694, "step": 443500 }, { "epoch": 27.36, "learning_rate": 1.7979742906871895e-06, "loss": 1.2676, "step": 444000 }, { "epoch": 27.39, "learning_rate": 1.7770042149852163e-06, "loss": 1.2672, "step": 444500 }, { "epoch": 27.42, "learning_rate": 1.756034139283243e-06, "loss": 1.2616, "step": 445000 }, { "epoch": 27.45, "learning_rate": 1.7350640635812697e-06, "loss": 1.2684, "step": 445500 }, { "epoch": 27.48, "learning_rate": 1.7140939878792964e-06, "loss": 1.27, "step": 446000 }, { "epoch": 27.51, "learning_rate": 1.693123912177323e-06, "loss": 1.2657, "step": 446500 }, { "epoch": 27.54, "learning_rate": 1.6721538364753497e-06, "loss": 1.2603, "step": 447000 }, { "epoch": 27.57, "learning_rate": 1.6511837607733766e-06, "loss": 1.2679, "step": 447500 }, { "epoch": 27.6, "learning_rate": 1.6302136850714032e-06, "loss": 1.2692, "step": 448000 }, { "epoch": 27.64, "learning_rate": 1.60924360936943e-06, "loss": 1.2659, "step": 448500 }, { "epoch": 27.67, "learning_rate": 1.5882735336674568e-06, "loss": 1.2624, "step": 449000 }, { "epoch": 27.7, "learning_rate": 1.5673034579654833e-06, "loss": 1.2632, "step": 449500 }, { "epoch": 27.73, "learning_rate": 1.5463333822635101e-06, "loss": 1.264, "step": 450000 }, { "epoch": 27.76, "learning_rate": 1.5253633065615366e-06, "loss": 1.2651, "step": 450500 }, { "epoch": 27.79, "learning_rate": 1.5043932308595635e-06, "loss": 1.262, "step": 451000 }, { "epoch": 27.82, "learning_rate": 1.4834231551575904e-06, "loss": 1.2618, "step": 451500 }, { "epoch": 27.85, "learning_rate": 1.4624530794556168e-06, "loss": 1.2625, "step": 452000 }, { "epoch": 27.88, "learning_rate": 1.4414830037536437e-06, "loss": 1.2667, "step": 452500 }, { "epoch": 27.91, "learning_rate": 1.4205129280516706e-06, "loss": 1.2566, "step": 453000 }, { "epoch": 27.94, "learning_rate": 1.399542852349697e-06, "loss": 1.2645, "step": 453500 }, { "epoch": 27.97, "learning_rate": 1.378572776647724e-06, "loss": 1.2661, "step": 454000 }, { "epoch": 28.01, "learning_rate": 1.3576027009457504e-06, "loss": 1.272, "step": 454500 }, { "epoch": 28.04, "learning_rate": 1.3366326252437773e-06, "loss": 1.2631, "step": 455000 }, { "epoch": 28.07, "learning_rate": 1.3156625495418041e-06, "loss": 1.2666, "step": 455500 }, { "epoch": 28.1, "learning_rate": 1.2946924738398306e-06, "loss": 1.2583, "step": 456000 }, { "epoch": 28.13, "learning_rate": 1.2737223981378575e-06, "loss": 1.2597, "step": 456500 }, { "epoch": 28.16, "learning_rate": 1.252752322435884e-06, "loss": 1.2678, "step": 457000 }, { "epoch": 28.19, "learning_rate": 1.2317822467339108e-06, "loss": 1.265, "step": 457500 }, { "epoch": 28.22, "learning_rate": 1.2108121710319375e-06, "loss": 1.2601, "step": 458000 }, { "epoch": 28.25, "learning_rate": 1.1898420953299644e-06, "loss": 1.2625, "step": 458500 }, { "epoch": 28.28, "learning_rate": 1.168872019627991e-06, "loss": 1.2695, "step": 459000 }, { "epoch": 28.31, "learning_rate": 1.1479019439260177e-06, "loss": 1.2688, "step": 459500 }, { "epoch": 28.34, "learning_rate": 1.1269318682240444e-06, "loss": 1.2643, "step": 460000 }, { "epoch": 28.38, "learning_rate": 1.105961792522071e-06, "loss": 1.2694, "step": 460500 }, { "epoch": 28.41, "learning_rate": 1.0849917168200977e-06, "loss": 1.264, "step": 461000 }, { "epoch": 28.44, "learning_rate": 1.0640216411181244e-06, "loss": 1.266, "step": 461500 }, { "epoch": 28.47, "learning_rate": 1.0430515654161513e-06, "loss": 1.268, "step": 462000 }, { "epoch": 28.5, "learning_rate": 1.022081489714178e-06, "loss": 1.2654, "step": 462500 }, { "epoch": 28.53, "learning_rate": 1.0011114140122046e-06, "loss": 1.2625, "step": 463000 }, { "epoch": 28.56, "learning_rate": 9.801413383102313e-07, "loss": 1.2651, "step": 463500 }, { "epoch": 28.59, "learning_rate": 9.59171262608258e-07, "loss": 1.2644, "step": 464000 }, { "epoch": 28.62, "learning_rate": 9.382011869062848e-07, "loss": 1.2602, "step": 464500 }, { "epoch": 28.65, "learning_rate": 9.172311112043115e-07, "loss": 1.2597, "step": 465000 }, { "epoch": 28.68, "learning_rate": 8.962610355023382e-07, "loss": 1.2638, "step": 465500 }, { "epoch": 28.71, "learning_rate": 8.75290959800365e-07, "loss": 1.2593, "step": 466000 }, { "epoch": 28.74, "learning_rate": 8.543208840983917e-07, "loss": 1.2641, "step": 466500 }, { "epoch": 28.78, "learning_rate": 8.333508083964184e-07, "loss": 1.2642, "step": 467000 }, { "epoch": 28.81, "learning_rate": 8.123807326944451e-07, "loss": 1.2659, "step": 467500 }, { "epoch": 28.84, "learning_rate": 7.914106569924717e-07, "loss": 1.2644, "step": 468000 }, { "epoch": 28.87, "learning_rate": 7.704405812904986e-07, "loss": 1.2615, "step": 468500 }, { "epoch": 28.9, "learning_rate": 7.494705055885253e-07, "loss": 1.2662, "step": 469000 }, { "epoch": 28.93, "learning_rate": 7.28500429886552e-07, "loss": 1.2582, "step": 469500 }, { "epoch": 28.96, "learning_rate": 7.075303541845786e-07, "loss": 1.262, "step": 470000 }, { "epoch": 28.99, "learning_rate": 6.865602784826053e-07, "loss": 1.2566, "step": 470500 }, { "epoch": 29.02, "learning_rate": 6.655902027806321e-07, "loss": 1.2596, "step": 471000 }, { "epoch": 29.05, "learning_rate": 6.446201270786589e-07, "loss": 1.2651, "step": 471500 }, { "epoch": 29.08, "learning_rate": 6.236500513766855e-07, "loss": 1.2588, "step": 472000 }, { "epoch": 29.11, "learning_rate": 6.026799756747122e-07, "loss": 1.2596, "step": 472500 }, { "epoch": 29.15, "learning_rate": 5.817098999727389e-07, "loss": 1.2645, "step": 473000 }, { "epoch": 29.18, "learning_rate": 5.607398242707656e-07, "loss": 1.2631, "step": 473500 }, { "epoch": 29.21, "learning_rate": 5.397697485687923e-07, "loss": 1.2614, "step": 474000 }, { "epoch": 29.24, "learning_rate": 5.187996728668191e-07, "loss": 1.2659, "step": 474500 }, { "epoch": 29.27, "learning_rate": 4.978295971648458e-07, "loss": 1.262, "step": 475000 }, { "epoch": 29.3, "learning_rate": 4.768595214628725e-07, "loss": 1.2602, "step": 475500 }, { "epoch": 29.33, "learning_rate": 4.558894457608992e-07, "loss": 1.2637, "step": 476000 }, { "epoch": 29.36, "learning_rate": 4.34919370058926e-07, "loss": 1.2657, "step": 476500 }, { "epoch": 29.39, "learning_rate": 4.1394929435695266e-07, "loss": 1.256, "step": 477000 }, { "epoch": 29.42, "learning_rate": 3.929792186549794e-07, "loss": 1.2673, "step": 477500 }, { "epoch": 29.45, "learning_rate": 3.720091429530061e-07, "loss": 1.2656, "step": 478000 }, { "epoch": 29.48, "learning_rate": 3.5103906725103283e-07, "loss": 1.266, "step": 478500 }, { "epoch": 29.52, "learning_rate": 3.300689915490595e-07, "loss": 1.2594, "step": 479000 }, { "epoch": 29.55, "learning_rate": 3.090989158470862e-07, "loss": 1.2628, "step": 479500 }, { "epoch": 29.58, "learning_rate": 2.8812884014511294e-07, "loss": 1.2628, "step": 480000 }, { "epoch": 29.61, "learning_rate": 2.6715876444313967e-07, "loss": 1.2603, "step": 480500 }, { "epoch": 29.64, "learning_rate": 2.461886887411664e-07, "loss": 1.2595, "step": 481000 }, { "epoch": 29.67, "learning_rate": 2.252186130391931e-07, "loss": 1.2576, "step": 481500 }, { "epoch": 29.7, "learning_rate": 2.042485373372198e-07, "loss": 1.2598, "step": 482000 }, { "epoch": 29.73, "learning_rate": 1.832784616352465e-07, "loss": 1.264, "step": 482500 }, { "epoch": 29.76, "learning_rate": 1.6230838593327323e-07, "loss": 1.2564, "step": 483000 }, { "epoch": 29.79, "learning_rate": 1.4133831023129995e-07, "loss": 1.2626, "step": 483500 }, { "epoch": 29.82, "learning_rate": 1.2036823452932668e-07, "loss": 1.262, "step": 484000 }, { "epoch": 29.85, "learning_rate": 9.939815882735339e-08, "loss": 1.2612, "step": 484500 }, { "epoch": 29.88, "learning_rate": 7.84280831253801e-08, "loss": 1.2666, "step": 485000 }, { "epoch": 29.92, "learning_rate": 5.7458007423406806e-08, "loss": 1.2569, "step": 485500 }, { "epoch": 29.95, "learning_rate": 3.6487931721433516e-08, "loss": 1.2639, "step": 486000 }, { "epoch": 29.98, "learning_rate": 1.5517856019460232e-08, "loss": 1.2638, "step": 486500 }, { "epoch": 30.0, "step": 486870, "total_flos": 8.200903785279652e+18, "train_loss": 1.3885125489469685, "train_runtime": 402878.8865, "train_samples_per_second": 77.338, "train_steps_per_second": 1.208 } ], "max_steps": 486870, "num_train_epochs": 30, "total_flos": 8.200903785279652e+18, "trial_name": null, "trial_params": null }