{ "best_metric": 0.7710575635876841, "best_model_checkpoint": "models/full_xnli_3/checkpoint-552051", "epoch": 3.0, "global_step": 552051, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.9981885731571902e-05, "loss": 1.026, "step": 500 }, { "epoch": 0.01, "learning_rate": 1.9963771463143806e-05, "loss": 0.8874, "step": 1000 }, { "epoch": 0.01, "learning_rate": 1.9945657194715707e-05, "loss": 0.845, "step": 1500 }, { "epoch": 0.01, "learning_rate": 1.9927542926287608e-05, "loss": 0.8122, "step": 2000 }, { "epoch": 0.01, "learning_rate": 1.9909428657859512e-05, "loss": 0.7991, "step": 2500 }, { "epoch": 0.02, "learning_rate": 1.9891314389431413e-05, "loss": 0.7869, "step": 3000 }, { "epoch": 0.02, "learning_rate": 1.9873200121003317e-05, "loss": 0.7801, "step": 3500 }, { "epoch": 0.02, "learning_rate": 1.9855085852575217e-05, "loss": 0.7703, "step": 4000 }, { "epoch": 0.02, "learning_rate": 1.9836971584147118e-05, "loss": 0.7661, "step": 4500 }, { "epoch": 0.03, "learning_rate": 1.981885731571902e-05, "loss": 0.7498, "step": 5000 }, { "epoch": 0.03, "learning_rate": 1.9800743047290923e-05, "loss": 0.7383, "step": 5500 }, { "epoch": 0.03, "learning_rate": 1.9782628778862823e-05, "loss": 0.7452, "step": 6000 }, { "epoch": 0.04, "learning_rate": 1.9764514510434728e-05, "loss": 0.7325, "step": 6500 }, { "epoch": 0.04, "learning_rate": 1.9746400242006628e-05, "loss": 0.7407, "step": 7000 }, { "epoch": 0.04, "learning_rate": 1.972828597357853e-05, "loss": 0.7248, "step": 7500 }, { "epoch": 0.04, "learning_rate": 1.9710171705150433e-05, "loss": 0.7216, "step": 8000 }, { "epoch": 0.05, "learning_rate": 1.9692057436722334e-05, "loss": 0.7197, "step": 8500 }, { "epoch": 0.05, "learning_rate": 1.9673943168294238e-05, "loss": 0.7168, "step": 9000 }, { "epoch": 0.05, "learning_rate": 1.9655828899866135e-05, "loss": 0.7146, "step": 9500 }, { "epoch": 0.05, "learning_rate": 1.963771463143804e-05, "loss": 0.708, "step": 10000 }, { "epoch": 0.06, "learning_rate": 1.961960036300994e-05, "loss": 0.7139, "step": 10500 }, { "epoch": 0.06, "learning_rate": 1.9601486094581844e-05, "loss": 0.7092, "step": 11000 }, { "epoch": 0.06, "learning_rate": 1.9583371826153745e-05, "loss": 0.6994, "step": 11500 }, { "epoch": 0.07, "learning_rate": 1.956525755772565e-05, "loss": 0.6958, "step": 12000 }, { "epoch": 0.07, "learning_rate": 1.954714328929755e-05, "loss": 0.6949, "step": 12500 }, { "epoch": 0.07, "learning_rate": 1.952902902086945e-05, "loss": 0.698, "step": 13000 }, { "epoch": 0.07, "learning_rate": 1.951091475244135e-05, "loss": 0.6803, "step": 13500 }, { "epoch": 0.08, "learning_rate": 1.9492800484013255e-05, "loss": 0.6865, "step": 14000 }, { "epoch": 0.08, "learning_rate": 1.9474686215585155e-05, "loss": 0.7004, "step": 14500 }, { "epoch": 0.08, "learning_rate": 1.9456571947157056e-05, "loss": 0.681, "step": 15000 }, { "epoch": 0.08, "learning_rate": 1.943845767872896e-05, "loss": 0.6864, "step": 15500 }, { "epoch": 0.09, "learning_rate": 1.942034341030086e-05, "loss": 0.6934, "step": 16000 }, { "epoch": 0.09, "learning_rate": 1.9402229141872765e-05, "loss": 0.6798, "step": 16500 }, { "epoch": 0.09, "learning_rate": 1.9384114873444666e-05, "loss": 0.6855, "step": 17000 }, { "epoch": 0.1, "learning_rate": 1.9366000605016566e-05, "loss": 0.6749, "step": 17500 }, { "epoch": 0.1, "learning_rate": 1.9347886336588467e-05, "loss": 0.6704, "step": 18000 }, { "epoch": 0.1, "learning_rate": 1.932977206816037e-05, "loss": 0.676, "step": 18500 }, { "epoch": 0.1, "learning_rate": 1.9311657799732272e-05, "loss": 0.6703, "step": 19000 }, { "epoch": 0.11, "learning_rate": 1.9293543531304176e-05, "loss": 0.6646, "step": 19500 }, { "epoch": 0.11, "learning_rate": 1.9275429262876077e-05, "loss": 0.669, "step": 20000 }, { "epoch": 0.11, "learning_rate": 1.9257314994447977e-05, "loss": 0.6619, "step": 20500 }, { "epoch": 0.11, "learning_rate": 1.923920072601988e-05, "loss": 0.6603, "step": 21000 }, { "epoch": 0.12, "learning_rate": 1.9221086457591782e-05, "loss": 0.6603, "step": 21500 }, { "epoch": 0.12, "learning_rate": 1.9202972189163683e-05, "loss": 0.6694, "step": 22000 }, { "epoch": 0.12, "learning_rate": 1.9184857920735587e-05, "loss": 0.658, "step": 22500 }, { "epoch": 0.12, "learning_rate": 1.9166743652307488e-05, "loss": 0.6506, "step": 23000 }, { "epoch": 0.13, "learning_rate": 1.9148629383879388e-05, "loss": 0.6673, "step": 23500 }, { "epoch": 0.13, "learning_rate": 1.9130515115451292e-05, "loss": 0.6613, "step": 24000 }, { "epoch": 0.13, "learning_rate": 1.9112400847023193e-05, "loss": 0.6597, "step": 24500 }, { "epoch": 0.14, "learning_rate": 1.9094286578595097e-05, "loss": 0.6432, "step": 25000 }, { "epoch": 0.14, "learning_rate": 1.9076172310166994e-05, "loss": 0.6436, "step": 25500 }, { "epoch": 0.14, "learning_rate": 1.90580580417389e-05, "loss": 0.6566, "step": 26000 }, { "epoch": 0.14, "learning_rate": 1.90399437733108e-05, "loss": 0.6467, "step": 26500 }, { "epoch": 0.15, "learning_rate": 1.9021829504882703e-05, "loss": 0.656, "step": 27000 }, { "epoch": 0.15, "learning_rate": 1.9003715236454604e-05, "loss": 0.6633, "step": 27500 }, { "epoch": 0.15, "learning_rate": 1.8985600968026508e-05, "loss": 0.6409, "step": 28000 }, { "epoch": 0.15, "learning_rate": 1.896748669959841e-05, "loss": 0.6562, "step": 28500 }, { "epoch": 0.16, "learning_rate": 1.894937243117031e-05, "loss": 0.6516, "step": 29000 }, { "epoch": 0.16, "learning_rate": 1.8931258162742213e-05, "loss": 0.6502, "step": 29500 }, { "epoch": 0.16, "learning_rate": 1.8913143894314114e-05, "loss": 0.6437, "step": 30000 }, { "epoch": 0.17, "learning_rate": 1.8895029625886018e-05, "loss": 0.6485, "step": 30500 }, { "epoch": 0.17, "learning_rate": 1.8876915357457916e-05, "loss": 0.6357, "step": 31000 }, { "epoch": 0.17, "learning_rate": 1.885880108902982e-05, "loss": 0.6438, "step": 31500 }, { "epoch": 0.17, "learning_rate": 1.884068682060172e-05, "loss": 0.644, "step": 32000 }, { "epoch": 0.18, "learning_rate": 1.8822572552173624e-05, "loss": 0.6493, "step": 32500 }, { "epoch": 0.18, "learning_rate": 1.8804458283745525e-05, "loss": 0.6418, "step": 33000 }, { "epoch": 0.18, "learning_rate": 1.8786344015317426e-05, "loss": 0.6448, "step": 33500 }, { "epoch": 0.18, "learning_rate": 1.876822974688933e-05, "loss": 0.6353, "step": 34000 }, { "epoch": 0.19, "learning_rate": 1.875011547846123e-05, "loss": 0.6332, "step": 34500 }, { "epoch": 0.19, "learning_rate": 1.873200121003313e-05, "loss": 0.6393, "step": 35000 }, { "epoch": 0.19, "learning_rate": 1.8713886941605035e-05, "loss": 0.6309, "step": 35500 }, { "epoch": 0.2, "learning_rate": 1.8695772673176936e-05, "loss": 0.6378, "step": 36000 }, { "epoch": 0.2, "learning_rate": 1.8677658404748837e-05, "loss": 0.6412, "step": 36500 }, { "epoch": 0.2, "learning_rate": 1.865954413632074e-05, "loss": 0.637, "step": 37000 }, { "epoch": 0.2, "learning_rate": 1.864142986789264e-05, "loss": 0.6293, "step": 37500 }, { "epoch": 0.21, "learning_rate": 1.8623315599464545e-05, "loss": 0.6273, "step": 38000 }, { "epoch": 0.21, "learning_rate": 1.8605201331036446e-05, "loss": 0.6205, "step": 38500 }, { "epoch": 0.21, "learning_rate": 1.8587087062608347e-05, "loss": 0.6221, "step": 39000 }, { "epoch": 0.21, "learning_rate": 1.8568972794180248e-05, "loss": 0.6236, "step": 39500 }, { "epoch": 0.22, "learning_rate": 1.855085852575215e-05, "loss": 0.6221, "step": 40000 }, { "epoch": 0.22, "learning_rate": 1.8532744257324052e-05, "loss": 0.618, "step": 40500 }, { "epoch": 0.22, "learning_rate": 1.8514629988895956e-05, "loss": 0.628, "step": 41000 }, { "epoch": 0.23, "learning_rate": 1.8496515720467857e-05, "loss": 0.6069, "step": 41500 }, { "epoch": 0.23, "learning_rate": 1.8478401452039758e-05, "loss": 0.6337, "step": 42000 }, { "epoch": 0.23, "learning_rate": 1.8460287183611662e-05, "loss": 0.6205, "step": 42500 }, { "epoch": 0.23, "learning_rate": 1.8442172915183563e-05, "loss": 0.6287, "step": 43000 }, { "epoch": 0.24, "learning_rate": 1.8424058646755467e-05, "loss": 0.6186, "step": 43500 }, { "epoch": 0.24, "learning_rate": 1.8405944378327367e-05, "loss": 0.6225, "step": 44000 }, { "epoch": 0.24, "learning_rate": 1.8387830109899268e-05, "loss": 0.6171, "step": 44500 }, { "epoch": 0.24, "learning_rate": 1.836971584147117e-05, "loss": 0.6147, "step": 45000 }, { "epoch": 0.25, "learning_rate": 1.8351601573043073e-05, "loss": 0.6293, "step": 45500 }, { "epoch": 0.25, "learning_rate": 1.8333487304614973e-05, "loss": 0.6098, "step": 46000 }, { "epoch": 0.25, "learning_rate": 1.8315373036186878e-05, "loss": 0.6162, "step": 46500 }, { "epoch": 0.26, "learning_rate": 1.8297258767758778e-05, "loss": 0.6195, "step": 47000 }, { "epoch": 0.26, "learning_rate": 1.827914449933068e-05, "loss": 0.6265, "step": 47500 }, { "epoch": 0.26, "learning_rate": 1.826103023090258e-05, "loss": 0.6166, "step": 48000 }, { "epoch": 0.26, "learning_rate": 1.8242915962474484e-05, "loss": 0.6064, "step": 48500 }, { "epoch": 0.27, "learning_rate": 1.8224801694046384e-05, "loss": 0.6251, "step": 49000 }, { "epoch": 0.27, "learning_rate": 1.8206687425618285e-05, "loss": 0.6102, "step": 49500 }, { "epoch": 0.27, "learning_rate": 1.818857315719019e-05, "loss": 0.6213, "step": 50000 }, { "epoch": 0.27, "learning_rate": 1.817045888876209e-05, "loss": 0.6138, "step": 50500 }, { "epoch": 0.28, "learning_rate": 1.8152344620333994e-05, "loss": 0.617, "step": 51000 }, { "epoch": 0.28, "learning_rate": 1.8134230351905895e-05, "loss": 0.6199, "step": 51500 }, { "epoch": 0.28, "learning_rate": 1.81161160834778e-05, "loss": 0.6011, "step": 52000 }, { "epoch": 0.29, "learning_rate": 1.8098001815049696e-05, "loss": 0.6098, "step": 52500 }, { "epoch": 0.29, "learning_rate": 1.80798875466216e-05, "loss": 0.6109, "step": 53000 }, { "epoch": 0.29, "learning_rate": 1.80617732781935e-05, "loss": 0.608, "step": 53500 }, { "epoch": 0.29, "learning_rate": 1.8043659009765405e-05, "loss": 0.6062, "step": 54000 }, { "epoch": 0.3, "learning_rate": 1.8025544741337305e-05, "loss": 0.6072, "step": 54500 }, { "epoch": 0.3, "learning_rate": 1.8007430472909206e-05, "loss": 0.615, "step": 55000 }, { "epoch": 0.3, "learning_rate": 1.798931620448111e-05, "loss": 0.6143, "step": 55500 }, { "epoch": 0.3, "learning_rate": 1.797120193605301e-05, "loss": 0.6119, "step": 56000 }, { "epoch": 0.31, "learning_rate": 1.795308766762491e-05, "loss": 0.6047, "step": 56500 }, { "epoch": 0.31, "learning_rate": 1.7934973399196816e-05, "loss": 0.5979, "step": 57000 }, { "epoch": 0.31, "learning_rate": 1.7916859130768716e-05, "loss": 0.6007, "step": 57500 }, { "epoch": 0.32, "learning_rate": 1.7898744862340617e-05, "loss": 0.5974, "step": 58000 }, { "epoch": 0.32, "learning_rate": 1.788063059391252e-05, "loss": 0.6116, "step": 58500 }, { "epoch": 0.32, "learning_rate": 1.7862516325484422e-05, "loss": 0.6025, "step": 59000 }, { "epoch": 0.32, "learning_rate": 1.7844402057056326e-05, "loss": 0.6033, "step": 59500 }, { "epoch": 0.33, "learning_rate": 1.7826287788628227e-05, "loss": 0.5954, "step": 60000 }, { "epoch": 0.33, "learning_rate": 1.7808173520200127e-05, "loss": 0.594, "step": 60500 }, { "epoch": 0.33, "learning_rate": 1.7790059251772028e-05, "loss": 0.6008, "step": 61000 }, { "epoch": 0.33, "learning_rate": 1.7771944983343932e-05, "loss": 0.5965, "step": 61500 }, { "epoch": 0.34, "learning_rate": 1.7753830714915833e-05, "loss": 0.6063, "step": 62000 }, { "epoch": 0.34, "learning_rate": 1.7735716446487737e-05, "loss": 0.6056, "step": 62500 }, { "epoch": 0.34, "learning_rate": 1.7717602178059638e-05, "loss": 0.5975, "step": 63000 }, { "epoch": 0.35, "learning_rate": 1.7699487909631538e-05, "loss": 0.6032, "step": 63500 }, { "epoch": 0.35, "learning_rate": 1.7681373641203442e-05, "loss": 0.6035, "step": 64000 }, { "epoch": 0.35, "learning_rate": 1.7663259372775343e-05, "loss": 0.5951, "step": 64500 }, { "epoch": 0.35, "learning_rate": 1.7645145104347247e-05, "loss": 0.596, "step": 65000 }, { "epoch": 0.36, "learning_rate": 1.7627030835919144e-05, "loss": 0.6031, "step": 65500 }, { "epoch": 0.36, "learning_rate": 1.760891656749105e-05, "loss": 0.5984, "step": 66000 }, { "epoch": 0.36, "learning_rate": 1.759080229906295e-05, "loss": 0.5867, "step": 66500 }, { "epoch": 0.36, "learning_rate": 1.7572688030634853e-05, "loss": 0.5925, "step": 67000 }, { "epoch": 0.37, "learning_rate": 1.7554573762206754e-05, "loss": 0.6039, "step": 67500 }, { "epoch": 0.37, "learning_rate": 1.7536459493778658e-05, "loss": 0.5921, "step": 68000 }, { "epoch": 0.37, "learning_rate": 1.751834522535056e-05, "loss": 0.5858, "step": 68500 }, { "epoch": 0.37, "learning_rate": 1.750023095692246e-05, "loss": 0.59, "step": 69000 }, { "epoch": 0.38, "learning_rate": 1.748211668849436e-05, "loss": 0.5949, "step": 69500 }, { "epoch": 0.38, "learning_rate": 1.7464002420066264e-05, "loss": 0.583, "step": 70000 }, { "epoch": 0.38, "learning_rate": 1.7445888151638165e-05, "loss": 0.5884, "step": 70500 }, { "epoch": 0.39, "learning_rate": 1.7427773883210065e-05, "loss": 0.58, "step": 71000 }, { "epoch": 0.39, "learning_rate": 1.740965961478197e-05, "loss": 0.5867, "step": 71500 }, { "epoch": 0.39, "learning_rate": 1.739154534635387e-05, "loss": 0.598, "step": 72000 }, { "epoch": 0.39, "learning_rate": 1.7373431077925774e-05, "loss": 0.5783, "step": 72500 }, { "epoch": 0.4, "learning_rate": 1.7355316809497675e-05, "loss": 0.5925, "step": 73000 }, { "epoch": 0.4, "learning_rate": 1.7337202541069576e-05, "loss": 0.584, "step": 73500 }, { "epoch": 0.4, "learning_rate": 1.7319088272641476e-05, "loss": 0.5863, "step": 74000 }, { "epoch": 0.4, "learning_rate": 1.730097400421338e-05, "loss": 0.5757, "step": 74500 }, { "epoch": 0.41, "learning_rate": 1.728285973578528e-05, "loss": 0.5879, "step": 75000 }, { "epoch": 0.41, "learning_rate": 1.7264745467357185e-05, "loss": 0.5988, "step": 75500 }, { "epoch": 0.41, "learning_rate": 1.7246631198929086e-05, "loss": 0.5807, "step": 76000 }, { "epoch": 0.42, "learning_rate": 1.7228516930500987e-05, "loss": 0.5872, "step": 76500 }, { "epoch": 0.42, "learning_rate": 1.721040266207289e-05, "loss": 0.5918, "step": 77000 }, { "epoch": 0.42, "learning_rate": 1.719228839364479e-05, "loss": 0.5845, "step": 77500 }, { "epoch": 0.42, "learning_rate": 1.7174174125216695e-05, "loss": 0.5726, "step": 78000 }, { "epoch": 0.43, "learning_rate": 1.7156059856788596e-05, "loss": 0.5772, "step": 78500 }, { "epoch": 0.43, "learning_rate": 1.7137945588360497e-05, "loss": 0.5966, "step": 79000 }, { "epoch": 0.43, "learning_rate": 1.7119831319932398e-05, "loss": 0.5734, "step": 79500 }, { "epoch": 0.43, "learning_rate": 1.71017170515043e-05, "loss": 0.5851, "step": 80000 }, { "epoch": 0.44, "learning_rate": 1.7083602783076202e-05, "loss": 0.5822, "step": 80500 }, { "epoch": 0.44, "learning_rate": 1.7065488514648106e-05, "loss": 0.5811, "step": 81000 }, { "epoch": 0.44, "learning_rate": 1.7047374246220004e-05, "loss": 0.5805, "step": 81500 }, { "epoch": 0.45, "learning_rate": 1.7029259977791908e-05, "loss": 0.579, "step": 82000 }, { "epoch": 0.45, "learning_rate": 1.701114570936381e-05, "loss": 0.5827, "step": 82500 }, { "epoch": 0.45, "learning_rate": 1.6993031440935713e-05, "loss": 0.5799, "step": 83000 }, { "epoch": 0.45, "learning_rate": 1.6974917172507613e-05, "loss": 0.5742, "step": 83500 }, { "epoch": 0.46, "learning_rate": 1.6956802904079517e-05, "loss": 0.5762, "step": 84000 }, { "epoch": 0.46, "learning_rate": 1.6938688635651418e-05, "loss": 0.57, "step": 84500 }, { "epoch": 0.46, "learning_rate": 1.692057436722332e-05, "loss": 0.5929, "step": 85000 }, { "epoch": 0.46, "learning_rate": 1.6902460098795223e-05, "loss": 0.5797, "step": 85500 }, { "epoch": 0.47, "learning_rate": 1.6884345830367123e-05, "loss": 0.5695, "step": 86000 }, { "epoch": 0.47, "learning_rate": 1.6866231561939028e-05, "loss": 0.5821, "step": 86500 }, { "epoch": 0.47, "learning_rate": 1.6848117293510925e-05, "loss": 0.5718, "step": 87000 }, { "epoch": 0.48, "learning_rate": 1.683000302508283e-05, "loss": 0.5738, "step": 87500 }, { "epoch": 0.48, "learning_rate": 1.681188875665473e-05, "loss": 0.5774, "step": 88000 }, { "epoch": 0.48, "learning_rate": 1.6793774488226634e-05, "loss": 0.5711, "step": 88500 }, { "epoch": 0.48, "learning_rate": 1.6775660219798534e-05, "loss": 0.5854, "step": 89000 }, { "epoch": 0.49, "learning_rate": 1.6757545951370435e-05, "loss": 0.5801, "step": 89500 }, { "epoch": 0.49, "learning_rate": 1.673943168294234e-05, "loss": 0.5647, "step": 90000 }, { "epoch": 0.49, "learning_rate": 1.672131741451424e-05, "loss": 0.5734, "step": 90500 }, { "epoch": 0.49, "learning_rate": 1.670320314608614e-05, "loss": 0.5764, "step": 91000 }, { "epoch": 0.5, "learning_rate": 1.6685088877658045e-05, "loss": 0.5748, "step": 91500 }, { "epoch": 0.5, "learning_rate": 1.6666974609229945e-05, "loss": 0.5715, "step": 92000 }, { "epoch": 0.5, "learning_rate": 1.6648860340801846e-05, "loss": 0.5686, "step": 92500 }, { "epoch": 0.51, "learning_rate": 1.663074607237375e-05, "loss": 0.5705, "step": 93000 }, { "epoch": 0.51, "learning_rate": 1.661263180394565e-05, "loss": 0.5726, "step": 93500 }, { "epoch": 0.51, "learning_rate": 1.6594517535517555e-05, "loss": 0.5719, "step": 94000 }, { "epoch": 0.51, "learning_rate": 1.6576403267089455e-05, "loss": 0.5644, "step": 94500 }, { "epoch": 0.52, "learning_rate": 1.6558288998661356e-05, "loss": 0.5622, "step": 95000 }, { "epoch": 0.52, "learning_rate": 1.6540174730233257e-05, "loss": 0.5754, "step": 95500 }, { "epoch": 0.52, "learning_rate": 1.652206046180516e-05, "loss": 0.5763, "step": 96000 }, { "epoch": 0.52, "learning_rate": 1.650394619337706e-05, "loss": 0.5664, "step": 96500 }, { "epoch": 0.53, "learning_rate": 1.6485831924948966e-05, "loss": 0.5798, "step": 97000 }, { "epoch": 0.53, "learning_rate": 1.6467717656520866e-05, "loss": 0.5722, "step": 97500 }, { "epoch": 0.53, "learning_rate": 1.6449603388092767e-05, "loss": 0.555, "step": 98000 }, { "epoch": 0.54, "learning_rate": 1.643148911966467e-05, "loss": 0.556, "step": 98500 }, { "epoch": 0.54, "learning_rate": 1.6413374851236572e-05, "loss": 0.5571, "step": 99000 }, { "epoch": 0.54, "learning_rate": 1.6395260582808476e-05, "loss": 0.5606, "step": 99500 }, { "epoch": 0.54, "learning_rate": 1.6377146314380377e-05, "loss": 0.5641, "step": 100000 }, { "epoch": 0.55, "learning_rate": 1.6359032045952277e-05, "loss": 0.5617, "step": 100500 }, { "epoch": 0.55, "learning_rate": 1.6340917777524178e-05, "loss": 0.5668, "step": 101000 }, { "epoch": 0.55, "learning_rate": 1.6322803509096082e-05, "loss": 0.566, "step": 101500 }, { "epoch": 0.55, "learning_rate": 1.6304689240667983e-05, "loss": 0.5661, "step": 102000 }, { "epoch": 0.56, "learning_rate": 1.6286574972239887e-05, "loss": 0.5644, "step": 102500 }, { "epoch": 0.56, "learning_rate": 1.6268460703811788e-05, "loss": 0.572, "step": 103000 }, { "epoch": 0.56, "learning_rate": 1.6250346435383688e-05, "loss": 0.5619, "step": 103500 }, { "epoch": 0.57, "learning_rate": 1.623223216695559e-05, "loss": 0.5546, "step": 104000 }, { "epoch": 0.57, "learning_rate": 1.6214117898527493e-05, "loss": 0.5557, "step": 104500 }, { "epoch": 0.57, "learning_rate": 1.6196003630099394e-05, "loss": 0.55, "step": 105000 }, { "epoch": 0.57, "learning_rate": 1.6177889361671294e-05, "loss": 0.5543, "step": 105500 }, { "epoch": 0.58, "learning_rate": 1.61597750932432e-05, "loss": 0.5496, "step": 106000 }, { "epoch": 0.58, "learning_rate": 1.61416608248151e-05, "loss": 0.5631, "step": 106500 }, { "epoch": 0.58, "learning_rate": 1.6123546556387003e-05, "loss": 0.557, "step": 107000 }, { "epoch": 0.58, "learning_rate": 1.6105432287958904e-05, "loss": 0.5533, "step": 107500 }, { "epoch": 0.59, "learning_rate": 1.6087318019530808e-05, "loss": 0.5501, "step": 108000 }, { "epoch": 0.59, "learning_rate": 1.6069203751102705e-05, "loss": 0.5644, "step": 108500 }, { "epoch": 0.59, "learning_rate": 1.605108948267461e-05, "loss": 0.5528, "step": 109000 }, { "epoch": 0.6, "learning_rate": 1.603297521424651e-05, "loss": 0.552, "step": 109500 }, { "epoch": 0.6, "learning_rate": 1.6014860945818414e-05, "loss": 0.5606, "step": 110000 }, { "epoch": 0.6, "learning_rate": 1.5996746677390315e-05, "loss": 0.5507, "step": 110500 }, { "epoch": 0.6, "learning_rate": 1.5978632408962215e-05, "loss": 0.5495, "step": 111000 }, { "epoch": 0.61, "learning_rate": 1.596051814053412e-05, "loss": 0.559, "step": 111500 }, { "epoch": 0.61, "learning_rate": 1.594240387210602e-05, "loss": 0.5575, "step": 112000 }, { "epoch": 0.61, "learning_rate": 1.5924289603677924e-05, "loss": 0.5528, "step": 112500 }, { "epoch": 0.61, "learning_rate": 1.5906175335249825e-05, "loss": 0.5497, "step": 113000 }, { "epoch": 0.62, "learning_rate": 1.5888061066821726e-05, "loss": 0.5522, "step": 113500 }, { "epoch": 0.62, "learning_rate": 1.5869946798393626e-05, "loss": 0.5509, "step": 114000 }, { "epoch": 0.62, "learning_rate": 1.585183252996553e-05, "loss": 0.5534, "step": 114500 }, { "epoch": 0.62, "learning_rate": 1.583371826153743e-05, "loss": 0.5544, "step": 115000 }, { "epoch": 0.63, "learning_rate": 1.5815603993109335e-05, "loss": 0.5469, "step": 115500 }, { "epoch": 0.63, "learning_rate": 1.5797489724681236e-05, "loss": 0.5584, "step": 116000 }, { "epoch": 0.63, "learning_rate": 1.5779375456253137e-05, "loss": 0.554, "step": 116500 }, { "epoch": 0.64, "learning_rate": 1.5761261187825037e-05, "loss": 0.556, "step": 117000 }, { "epoch": 0.64, "learning_rate": 1.574314691939694e-05, "loss": 0.5483, "step": 117500 }, { "epoch": 0.64, "learning_rate": 1.5725032650968842e-05, "loss": 0.5458, "step": 118000 }, { "epoch": 0.64, "learning_rate": 1.5706918382540746e-05, "loss": 0.5445, "step": 118500 }, { "epoch": 0.65, "learning_rate": 1.5688804114112647e-05, "loss": 0.55, "step": 119000 }, { "epoch": 0.65, "learning_rate": 1.5670689845684548e-05, "loss": 0.5505, "step": 119500 }, { "epoch": 0.65, "learning_rate": 1.565257557725645e-05, "loss": 0.5498, "step": 120000 }, { "epoch": 0.65, "learning_rate": 1.5634461308828352e-05, "loss": 0.5477, "step": 120500 }, { "epoch": 0.66, "learning_rate": 1.5616347040400256e-05, "loss": 0.551, "step": 121000 }, { "epoch": 0.66, "learning_rate": 1.5598232771972157e-05, "loss": 0.5459, "step": 121500 }, { "epoch": 0.66, "learning_rate": 1.5580118503544058e-05, "loss": 0.5384, "step": 122000 }, { "epoch": 0.67, "learning_rate": 1.556200423511596e-05, "loss": 0.546, "step": 122500 }, { "epoch": 0.67, "learning_rate": 1.5543889966687863e-05, "loss": 0.5465, "step": 123000 }, { "epoch": 0.67, "learning_rate": 1.5525775698259763e-05, "loss": 0.5476, "step": 123500 }, { "epoch": 0.67, "learning_rate": 1.5507661429831667e-05, "loss": 0.5464, "step": 124000 }, { "epoch": 0.68, "learning_rate": 1.5489547161403568e-05, "loss": 0.5559, "step": 124500 }, { "epoch": 0.68, "learning_rate": 1.547143289297547e-05, "loss": 0.5457, "step": 125000 }, { "epoch": 0.68, "learning_rate": 1.545331862454737e-05, "loss": 0.5378, "step": 125500 }, { "epoch": 0.68, "learning_rate": 1.5435204356119273e-05, "loss": 0.5366, "step": 126000 }, { "epoch": 0.69, "learning_rate": 1.5417090087691174e-05, "loss": 0.5378, "step": 126500 }, { "epoch": 0.69, "learning_rate": 1.5398975819263075e-05, "loss": 0.5389, "step": 127000 }, { "epoch": 0.69, "learning_rate": 1.538086155083498e-05, "loss": 0.5346, "step": 127500 }, { "epoch": 0.7, "learning_rate": 1.536274728240688e-05, "loss": 0.5433, "step": 128000 }, { "epoch": 0.7, "learning_rate": 1.5344633013978784e-05, "loss": 0.5419, "step": 128500 }, { "epoch": 0.7, "learning_rate": 1.5326518745550684e-05, "loss": 0.5466, "step": 129000 }, { "epoch": 0.7, "learning_rate": 1.530840447712259e-05, "loss": 0.5411, "step": 129500 }, { "epoch": 0.71, "learning_rate": 1.5290290208694486e-05, "loss": 0.5319, "step": 130000 }, { "epoch": 0.71, "learning_rate": 1.527217594026639e-05, "loss": 0.5394, "step": 130500 }, { "epoch": 0.71, "learning_rate": 1.5254061671838292e-05, "loss": 0.5399, "step": 131000 }, { "epoch": 0.71, "learning_rate": 1.5235947403410195e-05, "loss": 0.5412, "step": 131500 }, { "epoch": 0.72, "learning_rate": 1.5217833134982097e-05, "loss": 0.5391, "step": 132000 }, { "epoch": 0.72, "learning_rate": 1.5199718866553996e-05, "loss": 0.5384, "step": 132500 }, { "epoch": 0.72, "learning_rate": 1.5181604598125898e-05, "loss": 0.5361, "step": 133000 }, { "epoch": 0.73, "learning_rate": 1.51634903296978e-05, "loss": 0.5432, "step": 133500 }, { "epoch": 0.73, "learning_rate": 1.5145376061269703e-05, "loss": 0.5459, "step": 134000 }, { "epoch": 0.73, "learning_rate": 1.5127261792841605e-05, "loss": 0.5244, "step": 134500 }, { "epoch": 0.73, "learning_rate": 1.5109147524413506e-05, "loss": 0.5311, "step": 135000 }, { "epoch": 0.74, "learning_rate": 1.5091033255985409e-05, "loss": 0.5387, "step": 135500 }, { "epoch": 0.74, "learning_rate": 1.5072918987557311e-05, "loss": 0.5246, "step": 136000 }, { "epoch": 0.74, "learning_rate": 1.5054804719129212e-05, "loss": 0.5395, "step": 136500 }, { "epoch": 0.74, "learning_rate": 1.5036690450701114e-05, "loss": 0.5313, "step": 137000 }, { "epoch": 0.75, "learning_rate": 1.5018576182273016e-05, "loss": 0.5359, "step": 137500 }, { "epoch": 0.75, "learning_rate": 1.5000461913844917e-05, "loss": 0.5185, "step": 138000 }, { "epoch": 0.75, "learning_rate": 1.498234764541682e-05, "loss": 0.529, "step": 138500 }, { "epoch": 0.76, "learning_rate": 1.4964233376988722e-05, "loss": 0.5356, "step": 139000 }, { "epoch": 0.76, "learning_rate": 1.4946119108560624e-05, "loss": 0.537, "step": 139500 }, { "epoch": 0.76, "learning_rate": 1.4928004840132527e-05, "loss": 0.537, "step": 140000 }, { "epoch": 0.76, "learning_rate": 1.4909890571704426e-05, "loss": 0.5379, "step": 140500 }, { "epoch": 0.77, "learning_rate": 1.4891776303276328e-05, "loss": 0.5389, "step": 141000 }, { "epoch": 0.77, "learning_rate": 1.487366203484823e-05, "loss": 0.531, "step": 141500 }, { "epoch": 0.77, "learning_rate": 1.4855547766420133e-05, "loss": 0.5342, "step": 142000 }, { "epoch": 0.77, "learning_rate": 1.4837433497992035e-05, "loss": 0.5316, "step": 142500 }, { "epoch": 0.78, "learning_rate": 1.4819319229563936e-05, "loss": 0.5342, "step": 143000 }, { "epoch": 0.78, "learning_rate": 1.4801204961135838e-05, "loss": 0.5291, "step": 143500 }, { "epoch": 0.78, "learning_rate": 1.478309069270774e-05, "loss": 0.5218, "step": 144000 }, { "epoch": 0.79, "learning_rate": 1.4764976424279643e-05, "loss": 0.5331, "step": 144500 }, { "epoch": 0.79, "learning_rate": 1.4746862155851545e-05, "loss": 0.5213, "step": 145000 }, { "epoch": 0.79, "learning_rate": 1.4728747887423446e-05, "loss": 0.5269, "step": 145500 }, { "epoch": 0.79, "learning_rate": 1.4710633618995347e-05, "loss": 0.526, "step": 146000 }, { "epoch": 0.8, "learning_rate": 1.4692519350567249e-05, "loss": 0.5268, "step": 146500 }, { "epoch": 0.8, "learning_rate": 1.4674405082139151e-05, "loss": 0.5219, "step": 147000 }, { "epoch": 0.8, "learning_rate": 1.4656290813711054e-05, "loss": 0.5286, "step": 147500 }, { "epoch": 0.8, "learning_rate": 1.4638176545282956e-05, "loss": 0.5271, "step": 148000 }, { "epoch": 0.81, "learning_rate": 1.4620062276854857e-05, "loss": 0.5165, "step": 148500 }, { "epoch": 0.81, "learning_rate": 1.4601948008426758e-05, "loss": 0.5255, "step": 149000 }, { "epoch": 0.81, "learning_rate": 1.458383373999866e-05, "loss": 0.5288, "step": 149500 }, { "epoch": 0.82, "learning_rate": 1.4565719471570562e-05, "loss": 0.5226, "step": 150000 }, { "epoch": 0.82, "learning_rate": 1.4547605203142465e-05, "loss": 0.5142, "step": 150500 }, { "epoch": 0.82, "learning_rate": 1.4529490934714365e-05, "loss": 0.52, "step": 151000 }, { "epoch": 0.82, "learning_rate": 1.4511376666286268e-05, "loss": 0.5175, "step": 151500 }, { "epoch": 0.83, "learning_rate": 1.449326239785817e-05, "loss": 0.5263, "step": 152000 }, { "epoch": 0.83, "learning_rate": 1.4475148129430073e-05, "loss": 0.5174, "step": 152500 }, { "epoch": 0.83, "learning_rate": 1.4457033861001975e-05, "loss": 0.5239, "step": 153000 }, { "epoch": 0.83, "learning_rate": 1.4438919592573877e-05, "loss": 0.5187, "step": 153500 }, { "epoch": 0.84, "learning_rate": 1.4420805324145776e-05, "loss": 0.5319, "step": 154000 }, { "epoch": 0.84, "learning_rate": 1.4402691055717679e-05, "loss": 0.5241, "step": 154500 }, { "epoch": 0.84, "learning_rate": 1.4384576787289581e-05, "loss": 0.528, "step": 155000 }, { "epoch": 0.85, "learning_rate": 1.4366462518861484e-05, "loss": 0.5241, "step": 155500 }, { "epoch": 0.85, "learning_rate": 1.4348348250433386e-05, "loss": 0.5145, "step": 156000 }, { "epoch": 0.85, "learning_rate": 1.4330233982005287e-05, "loss": 0.5182, "step": 156500 }, { "epoch": 0.85, "learning_rate": 1.4312119713577189e-05, "loss": 0.5195, "step": 157000 }, { "epoch": 0.86, "learning_rate": 1.4294005445149091e-05, "loss": 0.5316, "step": 157500 }, { "epoch": 0.86, "learning_rate": 1.4275891176720992e-05, "loss": 0.5158, "step": 158000 }, { "epoch": 0.86, "learning_rate": 1.4257776908292894e-05, "loss": 0.5183, "step": 158500 }, { "epoch": 0.86, "learning_rate": 1.4239662639864795e-05, "loss": 0.5197, "step": 159000 }, { "epoch": 0.87, "learning_rate": 1.4221548371436698e-05, "loss": 0.5204, "step": 159500 }, { "epoch": 0.87, "learning_rate": 1.42034341030086e-05, "loss": 0.517, "step": 160000 }, { "epoch": 0.87, "learning_rate": 1.4185319834580502e-05, "loss": 0.502, "step": 160500 }, { "epoch": 0.87, "learning_rate": 1.4167205566152405e-05, "loss": 0.5137, "step": 161000 }, { "epoch": 0.88, "learning_rate": 1.4149091297724307e-05, "loss": 0.5213, "step": 161500 }, { "epoch": 0.88, "learning_rate": 1.4130977029296206e-05, "loss": 0.5108, "step": 162000 }, { "epoch": 0.88, "learning_rate": 1.4112862760868108e-05, "loss": 0.527, "step": 162500 }, { "epoch": 0.89, "learning_rate": 1.409474849244001e-05, "loss": 0.517, "step": 163000 }, { "epoch": 0.89, "learning_rate": 1.4076634224011913e-05, "loss": 0.5206, "step": 163500 }, { "epoch": 0.89, "learning_rate": 1.4058519955583816e-05, "loss": 0.5184, "step": 164000 }, { "epoch": 0.89, "learning_rate": 1.4040405687155716e-05, "loss": 0.5033, "step": 164500 }, { "epoch": 0.9, "learning_rate": 1.4022291418727619e-05, "loss": 0.5171, "step": 165000 }, { "epoch": 0.9, "learning_rate": 1.4004177150299521e-05, "loss": 0.5046, "step": 165500 }, { "epoch": 0.9, "learning_rate": 1.3986062881871423e-05, "loss": 0.5158, "step": 166000 }, { "epoch": 0.9, "learning_rate": 1.3967948613443326e-05, "loss": 0.5076, "step": 166500 }, { "epoch": 0.91, "learning_rate": 1.3949834345015225e-05, "loss": 0.5028, "step": 167000 }, { "epoch": 0.91, "learning_rate": 1.3931720076587127e-05, "loss": 0.5171, "step": 167500 }, { "epoch": 0.91, "learning_rate": 1.391360580815903e-05, "loss": 0.5167, "step": 168000 }, { "epoch": 0.92, "learning_rate": 1.3895491539730932e-05, "loss": 0.5133, "step": 168500 }, { "epoch": 0.92, "learning_rate": 1.3877377271302834e-05, "loss": 0.5075, "step": 169000 }, { "epoch": 0.92, "learning_rate": 1.3859263002874737e-05, "loss": 0.5098, "step": 169500 }, { "epoch": 0.92, "learning_rate": 1.3841148734446637e-05, "loss": 0.5153, "step": 170000 }, { "epoch": 0.93, "learning_rate": 1.382303446601854e-05, "loss": 0.5136, "step": 170500 }, { "epoch": 0.93, "learning_rate": 1.380492019759044e-05, "loss": 0.5199, "step": 171000 }, { "epoch": 0.93, "learning_rate": 1.3786805929162343e-05, "loss": 0.514, "step": 171500 }, { "epoch": 0.93, "learning_rate": 1.3768691660734245e-05, "loss": 0.5127, "step": 172000 }, { "epoch": 0.94, "learning_rate": 1.3750577392306146e-05, "loss": 0.5134, "step": 172500 }, { "epoch": 0.94, "learning_rate": 1.3732463123878048e-05, "loss": 0.5131, "step": 173000 }, { "epoch": 0.94, "learning_rate": 1.371434885544995e-05, "loss": 0.5159, "step": 173500 }, { "epoch": 0.95, "learning_rate": 1.3696234587021853e-05, "loss": 0.501, "step": 174000 }, { "epoch": 0.95, "learning_rate": 1.3678120318593755e-05, "loss": 0.5102, "step": 174500 }, { "epoch": 0.95, "learning_rate": 1.3660006050165654e-05, "loss": 0.5086, "step": 175000 }, { "epoch": 0.95, "learning_rate": 1.3641891781737557e-05, "loss": 0.5087, "step": 175500 }, { "epoch": 0.96, "learning_rate": 1.362377751330946e-05, "loss": 0.505, "step": 176000 }, { "epoch": 0.96, "learning_rate": 1.3605663244881362e-05, "loss": 0.5039, "step": 176500 }, { "epoch": 0.96, "learning_rate": 1.3587548976453264e-05, "loss": 0.5048, "step": 177000 }, { "epoch": 0.96, "learning_rate": 1.3569434708025166e-05, "loss": 0.5114, "step": 177500 }, { "epoch": 0.97, "learning_rate": 1.3551320439597067e-05, "loss": 0.5129, "step": 178000 }, { "epoch": 0.97, "learning_rate": 1.353320617116897e-05, "loss": 0.5156, "step": 178500 }, { "epoch": 0.97, "learning_rate": 1.3515091902740872e-05, "loss": 0.5098, "step": 179000 }, { "epoch": 0.98, "learning_rate": 1.3496977634312774e-05, "loss": 0.5019, "step": 179500 }, { "epoch": 0.98, "learning_rate": 1.3478863365884675e-05, "loss": 0.5057, "step": 180000 }, { "epoch": 0.98, "learning_rate": 1.3460749097456576e-05, "loss": 0.5076, "step": 180500 }, { "epoch": 0.98, "learning_rate": 1.3442634829028478e-05, "loss": 0.4996, "step": 181000 }, { "epoch": 0.99, "learning_rate": 1.342452056060038e-05, "loss": 0.4991, "step": 181500 }, { "epoch": 0.99, "learning_rate": 1.3406406292172283e-05, "loss": 0.5052, "step": 182000 }, { "epoch": 0.99, "learning_rate": 1.3388292023744185e-05, "loss": 0.5078, "step": 182500 }, { "epoch": 0.99, "learning_rate": 1.3370177755316086e-05, "loss": 0.5016, "step": 183000 }, { "epoch": 1.0, "learning_rate": 1.3352063486887986e-05, "loss": 0.4934, "step": 183500 }, { "epoch": 1.0, "learning_rate": 1.3333949218459889e-05, "loss": 0.4921, "step": 184000 }, { "epoch": 1.0, "eval_accuracy": 0.7691834002677376, "eval_loss": 0.608788013458252, "eval_runtime": 73.5075, "eval_samples_per_second": 508.111, "eval_steps_per_second": 63.517, "step": 184017 }, { "epoch": 1.0, "learning_rate": 1.3315834950031791e-05, "loss": 0.4487, "step": 184500 }, { "epoch": 1.01, "learning_rate": 1.3297720681603694e-05, "loss": 0.4546, "step": 185000 }, { "epoch": 1.01, "learning_rate": 1.3279606413175596e-05, "loss": 0.4561, "step": 185500 }, { "epoch": 1.01, "learning_rate": 1.3261492144747497e-05, "loss": 0.4585, "step": 186000 }, { "epoch": 1.01, "learning_rate": 1.3243377876319399e-05, "loss": 0.4593, "step": 186500 }, { "epoch": 1.02, "learning_rate": 1.3225263607891301e-05, "loss": 0.4664, "step": 187000 }, { "epoch": 1.02, "learning_rate": 1.3207149339463204e-05, "loss": 0.445, "step": 187500 }, { "epoch": 1.02, "learning_rate": 1.3189035071035106e-05, "loss": 0.4663, "step": 188000 }, { "epoch": 1.02, "learning_rate": 1.3170920802607005e-05, "loss": 0.4495, "step": 188500 }, { "epoch": 1.03, "learning_rate": 1.3152806534178908e-05, "loss": 0.4525, "step": 189000 }, { "epoch": 1.03, "learning_rate": 1.313469226575081e-05, "loss": 0.4503, "step": 189500 }, { "epoch": 1.03, "learning_rate": 1.3116577997322712e-05, "loss": 0.4409, "step": 190000 }, { "epoch": 1.04, "learning_rate": 1.3098463728894615e-05, "loss": 0.4526, "step": 190500 }, { "epoch": 1.04, "learning_rate": 1.3080349460466515e-05, "loss": 0.4601, "step": 191000 }, { "epoch": 1.04, "learning_rate": 1.3062235192038418e-05, "loss": 0.4621, "step": 191500 }, { "epoch": 1.04, "learning_rate": 1.304412092361032e-05, "loss": 0.4522, "step": 192000 }, { "epoch": 1.05, "learning_rate": 1.3026006655182221e-05, "loss": 0.458, "step": 192500 }, { "epoch": 1.05, "learning_rate": 1.3007892386754123e-05, "loss": 0.4541, "step": 193000 }, { "epoch": 1.05, "learning_rate": 1.2989778118326026e-05, "loss": 0.453, "step": 193500 }, { "epoch": 1.05, "learning_rate": 1.2971663849897926e-05, "loss": 0.4488, "step": 194000 }, { "epoch": 1.06, "learning_rate": 1.2953549581469829e-05, "loss": 0.4524, "step": 194500 }, { "epoch": 1.06, "learning_rate": 1.2935435313041731e-05, "loss": 0.4448, "step": 195000 }, { "epoch": 1.06, "learning_rate": 1.2917321044613634e-05, "loss": 0.451, "step": 195500 }, { "epoch": 1.07, "learning_rate": 1.2899206776185536e-05, "loss": 0.4493, "step": 196000 }, { "epoch": 1.07, "learning_rate": 1.2881092507757435e-05, "loss": 0.4441, "step": 196500 }, { "epoch": 1.07, "learning_rate": 1.2862978239329337e-05, "loss": 0.4514, "step": 197000 }, { "epoch": 1.07, "learning_rate": 1.284486397090124e-05, "loss": 0.4497, "step": 197500 }, { "epoch": 1.08, "learning_rate": 1.2826749702473142e-05, "loss": 0.4515, "step": 198000 }, { "epoch": 1.08, "learning_rate": 1.2808635434045044e-05, "loss": 0.4563, "step": 198500 }, { "epoch": 1.08, "learning_rate": 1.2790521165616945e-05, "loss": 0.4573, "step": 199000 }, { "epoch": 1.08, "learning_rate": 1.2772406897188848e-05, "loss": 0.4535, "step": 199500 }, { "epoch": 1.09, "learning_rate": 1.275429262876075e-05, "loss": 0.446, "step": 200000 }, { "epoch": 1.09, "learning_rate": 1.2736178360332652e-05, "loss": 0.4543, "step": 200500 }, { "epoch": 1.09, "learning_rate": 1.2718064091904555e-05, "loss": 0.4575, "step": 201000 }, { "epoch": 1.1, "learning_rate": 1.2699949823476457e-05, "loss": 0.4424, "step": 201500 }, { "epoch": 1.1, "learning_rate": 1.2681835555048356e-05, "loss": 0.4448, "step": 202000 }, { "epoch": 1.1, "learning_rate": 1.2663721286620258e-05, "loss": 0.4517, "step": 202500 }, { "epoch": 1.1, "learning_rate": 1.264560701819216e-05, "loss": 0.4565, "step": 203000 }, { "epoch": 1.11, "learning_rate": 1.2627492749764063e-05, "loss": 0.4557, "step": 203500 }, { "epoch": 1.11, "learning_rate": 1.2609378481335966e-05, "loss": 0.4407, "step": 204000 }, { "epoch": 1.11, "learning_rate": 1.2591264212907866e-05, "loss": 0.4484, "step": 204500 }, { "epoch": 1.11, "learning_rate": 1.2573149944479767e-05, "loss": 0.4494, "step": 205000 }, { "epoch": 1.12, "learning_rate": 1.255503567605167e-05, "loss": 0.4567, "step": 205500 }, { "epoch": 1.12, "learning_rate": 1.2536921407623572e-05, "loss": 0.4476, "step": 206000 }, { "epoch": 1.12, "learning_rate": 1.2518807139195474e-05, "loss": 0.4602, "step": 206500 }, { "epoch": 1.12, "learning_rate": 1.2500692870767375e-05, "loss": 0.4417, "step": 207000 }, { "epoch": 1.13, "learning_rate": 1.2482578602339277e-05, "loss": 0.45, "step": 207500 }, { "epoch": 1.13, "learning_rate": 1.246446433391118e-05, "loss": 0.4425, "step": 208000 }, { "epoch": 1.13, "learning_rate": 1.2446350065483082e-05, "loss": 0.4494, "step": 208500 }, { "epoch": 1.14, "learning_rate": 1.2428235797054984e-05, "loss": 0.4524, "step": 209000 }, { "epoch": 1.14, "learning_rate": 1.2410121528626887e-05, "loss": 0.4437, "step": 209500 }, { "epoch": 1.14, "learning_rate": 1.2392007260198786e-05, "loss": 0.4477, "step": 210000 }, { "epoch": 1.14, "learning_rate": 1.2373892991770688e-05, "loss": 0.4369, "step": 210500 }, { "epoch": 1.15, "learning_rate": 1.235577872334259e-05, "loss": 0.4425, "step": 211000 }, { "epoch": 1.15, "learning_rate": 1.2337664454914493e-05, "loss": 0.4428, "step": 211500 }, { "epoch": 1.15, "learning_rate": 1.2319550186486395e-05, "loss": 0.4608, "step": 212000 }, { "epoch": 1.15, "learning_rate": 1.2301435918058296e-05, "loss": 0.4512, "step": 212500 }, { "epoch": 1.16, "learning_rate": 1.2283321649630198e-05, "loss": 0.4416, "step": 213000 }, { "epoch": 1.16, "learning_rate": 1.22652073812021e-05, "loss": 0.4542, "step": 213500 }, { "epoch": 1.16, "learning_rate": 1.2247093112774003e-05, "loss": 0.4418, "step": 214000 }, { "epoch": 1.17, "learning_rate": 1.2228978844345904e-05, "loss": 0.4437, "step": 214500 }, { "epoch": 1.17, "learning_rate": 1.2210864575917804e-05, "loss": 0.454, "step": 215000 }, { "epoch": 1.17, "learning_rate": 1.2192750307489707e-05, "loss": 0.4392, "step": 215500 }, { "epoch": 1.17, "learning_rate": 1.217463603906161e-05, "loss": 0.4426, "step": 216000 }, { "epoch": 1.18, "learning_rate": 1.2156521770633512e-05, "loss": 0.455, "step": 216500 }, { "epoch": 1.18, "learning_rate": 1.2138407502205414e-05, "loss": 0.4429, "step": 217000 }, { "epoch": 1.18, "learning_rate": 1.2120293233777316e-05, "loss": 0.4441, "step": 217500 }, { "epoch": 1.18, "learning_rate": 1.2102178965349215e-05, "loss": 0.448, "step": 218000 }, { "epoch": 1.19, "learning_rate": 1.2084064696921118e-05, "loss": 0.4568, "step": 218500 }, { "epoch": 1.19, "learning_rate": 1.206595042849302e-05, "loss": 0.4458, "step": 219000 }, { "epoch": 1.19, "learning_rate": 1.2047836160064922e-05, "loss": 0.4448, "step": 219500 }, { "epoch": 1.2, "learning_rate": 1.2029721891636825e-05, "loss": 0.4444, "step": 220000 }, { "epoch": 1.2, "learning_rate": 1.2011607623208726e-05, "loss": 0.4425, "step": 220500 }, { "epoch": 1.2, "learning_rate": 1.1993493354780628e-05, "loss": 0.4401, "step": 221000 }, { "epoch": 1.2, "learning_rate": 1.197537908635253e-05, "loss": 0.4464, "step": 221500 }, { "epoch": 1.21, "learning_rate": 1.1957264817924433e-05, "loss": 0.44, "step": 222000 }, { "epoch": 1.21, "learning_rate": 1.1939150549496335e-05, "loss": 0.4378, "step": 222500 }, { "epoch": 1.21, "learning_rate": 1.1921036281068234e-05, "loss": 0.4333, "step": 223000 }, { "epoch": 1.21, "learning_rate": 1.1902922012640136e-05, "loss": 0.442, "step": 223500 }, { "epoch": 1.22, "learning_rate": 1.1884807744212039e-05, "loss": 0.4402, "step": 224000 }, { "epoch": 1.22, "learning_rate": 1.1866693475783941e-05, "loss": 0.4532, "step": 224500 }, { "epoch": 1.22, "learning_rate": 1.1848579207355844e-05, "loss": 0.4469, "step": 225000 }, { "epoch": 1.23, "learning_rate": 1.1830464938927746e-05, "loss": 0.4428, "step": 225500 }, { "epoch": 1.23, "learning_rate": 1.1812350670499647e-05, "loss": 0.4448, "step": 226000 }, { "epoch": 1.23, "learning_rate": 1.1794236402071549e-05, "loss": 0.4431, "step": 226500 }, { "epoch": 1.23, "learning_rate": 1.177612213364345e-05, "loss": 0.4407, "step": 227000 }, { "epoch": 1.24, "learning_rate": 1.1758007865215352e-05, "loss": 0.4364, "step": 227500 }, { "epoch": 1.24, "learning_rate": 1.1739893596787255e-05, "loss": 0.4269, "step": 228000 }, { "epoch": 1.24, "learning_rate": 1.1721779328359155e-05, "loss": 0.4421, "step": 228500 }, { "epoch": 1.24, "learning_rate": 1.1703665059931058e-05, "loss": 0.4366, "step": 229000 }, { "epoch": 1.25, "learning_rate": 1.168555079150296e-05, "loss": 0.4459, "step": 229500 }, { "epoch": 1.25, "learning_rate": 1.1667436523074862e-05, "loss": 0.4415, "step": 230000 }, { "epoch": 1.25, "learning_rate": 1.1649322254646765e-05, "loss": 0.4333, "step": 230500 }, { "epoch": 1.26, "learning_rate": 1.1631207986218664e-05, "loss": 0.4407, "step": 231000 }, { "epoch": 1.26, "learning_rate": 1.1613093717790566e-05, "loss": 0.4346, "step": 231500 }, { "epoch": 1.26, "learning_rate": 1.1594979449362469e-05, "loss": 0.4321, "step": 232000 }, { "epoch": 1.26, "learning_rate": 1.1576865180934371e-05, "loss": 0.4289, "step": 232500 }, { "epoch": 1.27, "learning_rate": 1.1558750912506273e-05, "loss": 0.432, "step": 233000 }, { "epoch": 1.27, "learning_rate": 1.1540636644078176e-05, "loss": 0.4404, "step": 233500 }, { "epoch": 1.27, "learning_rate": 1.1522522375650076e-05, "loss": 0.4398, "step": 234000 }, { "epoch": 1.27, "learning_rate": 1.1504408107221979e-05, "loss": 0.4326, "step": 234500 }, { "epoch": 1.28, "learning_rate": 1.1486293838793881e-05, "loss": 0.4309, "step": 235000 }, { "epoch": 1.28, "learning_rate": 1.1468179570365784e-05, "loss": 0.4455, "step": 235500 }, { "epoch": 1.28, "learning_rate": 1.1450065301937686e-05, "loss": 0.4274, "step": 236000 }, { "epoch": 1.29, "learning_rate": 1.1431951033509585e-05, "loss": 0.4313, "step": 236500 }, { "epoch": 1.29, "learning_rate": 1.1413836765081487e-05, "loss": 0.4412, "step": 237000 }, { "epoch": 1.29, "learning_rate": 1.139572249665339e-05, "loss": 0.4319, "step": 237500 }, { "epoch": 1.29, "learning_rate": 1.1377608228225292e-05, "loss": 0.432, "step": 238000 }, { "epoch": 1.3, "learning_rate": 1.1359493959797194e-05, "loss": 0.4306, "step": 238500 }, { "epoch": 1.3, "learning_rate": 1.1341379691369097e-05, "loss": 0.4291, "step": 239000 }, { "epoch": 1.3, "learning_rate": 1.1323265422940996e-05, "loss": 0.4266, "step": 239500 }, { "epoch": 1.3, "learning_rate": 1.1305151154512898e-05, "loss": 0.4338, "step": 240000 }, { "epoch": 1.31, "learning_rate": 1.12870368860848e-05, "loss": 0.4323, "step": 240500 }, { "epoch": 1.31, "learning_rate": 1.1268922617656703e-05, "loss": 0.4307, "step": 241000 }, { "epoch": 1.31, "learning_rate": 1.1250808349228605e-05, "loss": 0.4382, "step": 241500 }, { "epoch": 1.32, "learning_rate": 1.1232694080800506e-05, "loss": 0.4332, "step": 242000 }, { "epoch": 1.32, "learning_rate": 1.1214579812372408e-05, "loss": 0.4299, "step": 242500 }, { "epoch": 1.32, "learning_rate": 1.119646554394431e-05, "loss": 0.4319, "step": 243000 }, { "epoch": 1.32, "learning_rate": 1.1178351275516213e-05, "loss": 0.4387, "step": 243500 }, { "epoch": 1.33, "learning_rate": 1.1160237007088116e-05, "loss": 0.4247, "step": 244000 }, { "epoch": 1.33, "learning_rate": 1.1142122738660015e-05, "loss": 0.425, "step": 244500 }, { "epoch": 1.33, "learning_rate": 1.1124008470231917e-05, "loss": 0.4255, "step": 245000 }, { "epoch": 1.33, "learning_rate": 1.110589420180382e-05, "loss": 0.4355, "step": 245500 }, { "epoch": 1.34, "learning_rate": 1.1087779933375722e-05, "loss": 0.4358, "step": 246000 }, { "epoch": 1.34, "learning_rate": 1.1069665664947624e-05, "loss": 0.4247, "step": 246500 }, { "epoch": 1.34, "learning_rate": 1.1051551396519526e-05, "loss": 0.4384, "step": 247000 }, { "epoch": 1.34, "learning_rate": 1.1033437128091427e-05, "loss": 0.4423, "step": 247500 }, { "epoch": 1.35, "learning_rate": 1.101532285966333e-05, "loss": 0.4361, "step": 248000 }, { "epoch": 1.35, "learning_rate": 1.0997208591235232e-05, "loss": 0.4414, "step": 248500 }, { "epoch": 1.35, "learning_rate": 1.0979094322807133e-05, "loss": 0.4313, "step": 249000 }, { "epoch": 1.36, "learning_rate": 1.0960980054379035e-05, "loss": 0.4205, "step": 249500 }, { "epoch": 1.36, "learning_rate": 1.0942865785950936e-05, "loss": 0.431, "step": 250000 }, { "epoch": 1.36, "learning_rate": 1.0924751517522838e-05, "loss": 0.4307, "step": 250500 }, { "epoch": 1.36, "learning_rate": 1.090663724909474e-05, "loss": 0.4341, "step": 251000 }, { "epoch": 1.37, "learning_rate": 1.0888522980666643e-05, "loss": 0.4334, "step": 251500 }, { "epoch": 1.37, "learning_rate": 1.0870408712238545e-05, "loss": 0.4262, "step": 252000 }, { "epoch": 1.37, "learning_rate": 1.0852294443810444e-05, "loss": 0.4367, "step": 252500 }, { "epoch": 1.37, "learning_rate": 1.0834180175382347e-05, "loss": 0.4278, "step": 253000 }, { "epoch": 1.38, "learning_rate": 1.0816065906954249e-05, "loss": 0.4359, "step": 253500 }, { "epoch": 1.38, "learning_rate": 1.0797951638526151e-05, "loss": 0.4341, "step": 254000 }, { "epoch": 1.38, "learning_rate": 1.0779837370098054e-05, "loss": 0.4285, "step": 254500 }, { "epoch": 1.39, "learning_rate": 1.0761723101669956e-05, "loss": 0.4346, "step": 255000 }, { "epoch": 1.39, "learning_rate": 1.0743608833241857e-05, "loss": 0.4232, "step": 255500 }, { "epoch": 1.39, "learning_rate": 1.072549456481376e-05, "loss": 0.4334, "step": 256000 }, { "epoch": 1.39, "learning_rate": 1.0707380296385662e-05, "loss": 0.4303, "step": 256500 }, { "epoch": 1.4, "learning_rate": 1.0689266027957564e-05, "loss": 0.4312, "step": 257000 }, { "epoch": 1.4, "learning_rate": 1.0671151759529466e-05, "loss": 0.4251, "step": 257500 }, { "epoch": 1.4, "learning_rate": 1.0653037491101365e-05, "loss": 0.4317, "step": 258000 }, { "epoch": 1.4, "learning_rate": 1.0634923222673268e-05, "loss": 0.4249, "step": 258500 }, { "epoch": 1.41, "learning_rate": 1.061680895424517e-05, "loss": 0.4256, "step": 259000 }, { "epoch": 1.41, "learning_rate": 1.0598694685817072e-05, "loss": 0.419, "step": 259500 }, { "epoch": 1.41, "learning_rate": 1.0580580417388975e-05, "loss": 0.4262, "step": 260000 }, { "epoch": 1.42, "learning_rate": 1.0562466148960876e-05, "loss": 0.4272, "step": 260500 }, { "epoch": 1.42, "learning_rate": 1.0544351880532778e-05, "loss": 0.4283, "step": 261000 }, { "epoch": 1.42, "learning_rate": 1.0526237612104679e-05, "loss": 0.4168, "step": 261500 }, { "epoch": 1.42, "learning_rate": 1.0508123343676581e-05, "loss": 0.4246, "step": 262000 }, { "epoch": 1.43, "learning_rate": 1.0490009075248483e-05, "loss": 0.4214, "step": 262500 }, { "epoch": 1.43, "learning_rate": 1.0471894806820386e-05, "loss": 0.4246, "step": 263000 }, { "epoch": 1.43, "learning_rate": 1.0453780538392286e-05, "loss": 0.4225, "step": 263500 }, { "epoch": 1.43, "learning_rate": 1.0435666269964189e-05, "loss": 0.416, "step": 264000 }, { "epoch": 1.44, "learning_rate": 1.0417552001536091e-05, "loss": 0.4195, "step": 264500 }, { "epoch": 1.44, "learning_rate": 1.0399437733107994e-05, "loss": 0.4237, "step": 265000 }, { "epoch": 1.44, "learning_rate": 1.0381323464679896e-05, "loss": 0.4198, "step": 265500 }, { "epoch": 1.45, "learning_rate": 1.0363209196251795e-05, "loss": 0.4213, "step": 266000 }, { "epoch": 1.45, "learning_rate": 1.0345094927823697e-05, "loss": 0.4221, "step": 266500 }, { "epoch": 1.45, "learning_rate": 1.03269806593956e-05, "loss": 0.4242, "step": 267000 }, { "epoch": 1.45, "learning_rate": 1.0308866390967502e-05, "loss": 0.4248, "step": 267500 }, { "epoch": 1.46, "learning_rate": 1.0290752122539405e-05, "loss": 0.4233, "step": 268000 }, { "epoch": 1.46, "learning_rate": 1.0272637854111305e-05, "loss": 0.4348, "step": 268500 }, { "epoch": 1.46, "learning_rate": 1.0254523585683208e-05, "loss": 0.4205, "step": 269000 }, { "epoch": 1.46, "learning_rate": 1.023640931725511e-05, "loss": 0.425, "step": 269500 }, { "epoch": 1.47, "learning_rate": 1.0218295048827012e-05, "loss": 0.422, "step": 270000 }, { "epoch": 1.47, "learning_rate": 1.0200180780398915e-05, "loss": 0.416, "step": 270500 }, { "epoch": 1.47, "learning_rate": 1.0182066511970815e-05, "loss": 0.425, "step": 271000 }, { "epoch": 1.48, "learning_rate": 1.0163952243542716e-05, "loss": 0.4111, "step": 271500 }, { "epoch": 1.48, "learning_rate": 1.0145837975114619e-05, "loss": 0.4122, "step": 272000 }, { "epoch": 1.48, "learning_rate": 1.0127723706686521e-05, "loss": 0.4197, "step": 272500 }, { "epoch": 1.48, "learning_rate": 1.0109609438258423e-05, "loss": 0.4158, "step": 273000 }, { "epoch": 1.49, "learning_rate": 1.0091495169830326e-05, "loss": 0.4223, "step": 273500 }, { "epoch": 1.49, "learning_rate": 1.0073380901402225e-05, "loss": 0.421, "step": 274000 }, { "epoch": 1.49, "learning_rate": 1.0055266632974127e-05, "loss": 0.4187, "step": 274500 }, { "epoch": 1.49, "learning_rate": 1.003715236454603e-05, "loss": 0.4184, "step": 275000 }, { "epoch": 1.5, "learning_rate": 1.0019038096117932e-05, "loss": 0.4247, "step": 275500 }, { "epoch": 1.5, "learning_rate": 1.0000923827689834e-05, "loss": 0.4215, "step": 276000 }, { "epoch": 1.5, "learning_rate": 9.982809559261737e-06, "loss": 0.4205, "step": 276500 }, { "epoch": 1.51, "learning_rate": 9.964695290833637e-06, "loss": 0.4129, "step": 277000 }, { "epoch": 1.51, "learning_rate": 9.94658102240554e-06, "loss": 0.4107, "step": 277500 }, { "epoch": 1.51, "learning_rate": 9.928466753977442e-06, "loss": 0.4163, "step": 278000 }, { "epoch": 1.51, "learning_rate": 9.910352485549343e-06, "loss": 0.4215, "step": 278500 }, { "epoch": 1.52, "learning_rate": 9.892238217121245e-06, "loss": 0.4195, "step": 279000 }, { "epoch": 1.52, "learning_rate": 9.874123948693147e-06, "loss": 0.4166, "step": 279500 }, { "epoch": 1.52, "learning_rate": 9.856009680265048e-06, "loss": 0.4144, "step": 280000 }, { "epoch": 1.52, "learning_rate": 9.83789541183695e-06, "loss": 0.4196, "step": 280500 }, { "epoch": 1.53, "learning_rate": 9.819781143408853e-06, "loss": 0.419, "step": 281000 }, { "epoch": 1.53, "learning_rate": 9.801666874980754e-06, "loss": 0.4086, "step": 281500 }, { "epoch": 1.53, "learning_rate": 9.783552606552656e-06, "loss": 0.414, "step": 282000 }, { "epoch": 1.54, "learning_rate": 9.765438338124558e-06, "loss": 0.4138, "step": 282500 }, { "epoch": 1.54, "learning_rate": 9.74732406969646e-06, "loss": 0.419, "step": 283000 }, { "epoch": 1.54, "learning_rate": 9.729209801268361e-06, "loss": 0.4183, "step": 283500 }, { "epoch": 1.54, "learning_rate": 9.711095532840264e-06, "loss": 0.418, "step": 284000 }, { "epoch": 1.55, "learning_rate": 9.692981264412166e-06, "loss": 0.4183, "step": 284500 }, { "epoch": 1.55, "learning_rate": 9.674866995984069e-06, "loss": 0.411, "step": 285000 }, { "epoch": 1.55, "learning_rate": 9.65675272755597e-06, "loss": 0.4199, "step": 285500 }, { "epoch": 1.55, "learning_rate": 9.638638459127872e-06, "loss": 0.4087, "step": 286000 }, { "epoch": 1.56, "learning_rate": 9.620524190699772e-06, "loss": 0.4163, "step": 286500 }, { "epoch": 1.56, "learning_rate": 9.602409922271675e-06, "loss": 0.4207, "step": 287000 }, { "epoch": 1.56, "learning_rate": 9.584295653843577e-06, "loss": 0.4079, "step": 287500 }, { "epoch": 1.57, "learning_rate": 9.566181385415478e-06, "loss": 0.42, "step": 288000 }, { "epoch": 1.57, "learning_rate": 9.54806711698738e-06, "loss": 0.4193, "step": 288500 }, { "epoch": 1.57, "learning_rate": 9.529952848559283e-06, "loss": 0.4206, "step": 289000 }, { "epoch": 1.57, "learning_rate": 9.511838580131183e-06, "loss": 0.4255, "step": 289500 }, { "epoch": 1.58, "learning_rate": 9.493724311703086e-06, "loss": 0.4177, "step": 290000 }, { "epoch": 1.58, "learning_rate": 9.475610043274988e-06, "loss": 0.4164, "step": 290500 }, { "epoch": 1.58, "learning_rate": 9.45749577484689e-06, "loss": 0.4086, "step": 291000 }, { "epoch": 1.58, "learning_rate": 9.439381506418793e-06, "loss": 0.4062, "step": 291500 }, { "epoch": 1.59, "learning_rate": 9.421267237990694e-06, "loss": 0.4027, "step": 292000 }, { "epoch": 1.59, "learning_rate": 9.403152969562596e-06, "loss": 0.4084, "step": 292500 }, { "epoch": 1.59, "learning_rate": 9.385038701134498e-06, "loss": 0.4199, "step": 293000 }, { "epoch": 1.59, "learning_rate": 9.366924432706399e-06, "loss": 0.4071, "step": 293500 }, { "epoch": 1.6, "learning_rate": 9.348810164278301e-06, "loss": 0.4062, "step": 294000 }, { "epoch": 1.6, "learning_rate": 9.330695895850202e-06, "loss": 0.4148, "step": 294500 }, { "epoch": 1.6, "learning_rate": 9.312581627422104e-06, "loss": 0.408, "step": 295000 }, { "epoch": 1.61, "learning_rate": 9.294467358994007e-06, "loss": 0.4072, "step": 295500 }, { "epoch": 1.61, "learning_rate": 9.276353090565907e-06, "loss": 0.4084, "step": 296000 }, { "epoch": 1.61, "learning_rate": 9.25823882213781e-06, "loss": 0.4089, "step": 296500 }, { "epoch": 1.61, "learning_rate": 9.240124553709712e-06, "loss": 0.4154, "step": 297000 }, { "epoch": 1.62, "learning_rate": 9.222010285281615e-06, "loss": 0.4074, "step": 297500 }, { "epoch": 1.62, "learning_rate": 9.203896016853517e-06, "loss": 0.4097, "step": 298000 }, { "epoch": 1.62, "learning_rate": 9.185781748425418e-06, "loss": 0.4162, "step": 298500 }, { "epoch": 1.62, "learning_rate": 9.16766747999732e-06, "loss": 0.4076, "step": 299000 }, { "epoch": 1.63, "learning_rate": 9.149553211569222e-06, "loss": 0.4, "step": 299500 }, { "epoch": 1.63, "learning_rate": 9.131438943141123e-06, "loss": 0.4035, "step": 300000 }, { "epoch": 1.63, "learning_rate": 9.113324674713026e-06, "loss": 0.4042, "step": 300500 }, { "epoch": 1.64, "learning_rate": 9.095210406284928e-06, "loss": 0.4115, "step": 301000 }, { "epoch": 1.64, "learning_rate": 9.077096137856829e-06, "loss": 0.4042, "step": 301500 }, { "epoch": 1.64, "learning_rate": 9.058981869428731e-06, "loss": 0.4112, "step": 302000 }, { "epoch": 1.64, "learning_rate": 9.040867601000632e-06, "loss": 0.4039, "step": 302500 }, { "epoch": 1.65, "learning_rate": 9.022753332572534e-06, "loss": 0.4083, "step": 303000 }, { "epoch": 1.65, "learning_rate": 9.004639064144436e-06, "loss": 0.4055, "step": 303500 }, { "epoch": 1.65, "learning_rate": 8.986524795716339e-06, "loss": 0.4026, "step": 304000 }, { "epoch": 1.65, "learning_rate": 8.968410527288241e-06, "loss": 0.4144, "step": 304500 }, { "epoch": 1.66, "learning_rate": 8.950296258860142e-06, "loss": 0.4055, "step": 305000 }, { "epoch": 1.66, "learning_rate": 8.932181990432044e-06, "loss": 0.4084, "step": 305500 }, { "epoch": 1.66, "learning_rate": 8.914067722003947e-06, "loss": 0.4082, "step": 306000 }, { "epoch": 1.67, "learning_rate": 8.895953453575847e-06, "loss": 0.4095, "step": 306500 }, { "epoch": 1.67, "learning_rate": 8.87783918514775e-06, "loss": 0.4107, "step": 307000 }, { "epoch": 1.67, "learning_rate": 8.859724916719652e-06, "loss": 0.4046, "step": 307500 }, { "epoch": 1.67, "learning_rate": 8.841610648291553e-06, "loss": 0.4032, "step": 308000 }, { "epoch": 1.68, "learning_rate": 8.823496379863455e-06, "loss": 0.411, "step": 308500 }, { "epoch": 1.68, "learning_rate": 8.805382111435358e-06, "loss": 0.4027, "step": 309000 }, { "epoch": 1.68, "learning_rate": 8.787267843007258e-06, "loss": 0.3982, "step": 309500 }, { "epoch": 1.68, "learning_rate": 8.76915357457916e-06, "loss": 0.3971, "step": 310000 }, { "epoch": 1.69, "learning_rate": 8.751039306151063e-06, "loss": 0.4027, "step": 310500 }, { "epoch": 1.69, "learning_rate": 8.732925037722965e-06, "loss": 0.4059, "step": 311000 }, { "epoch": 1.69, "learning_rate": 8.714810769294866e-06, "loss": 0.4021, "step": 311500 }, { "epoch": 1.7, "learning_rate": 8.696696500866769e-06, "loss": 0.4134, "step": 312000 }, { "epoch": 1.7, "learning_rate": 8.678582232438671e-06, "loss": 0.3985, "step": 312500 }, { "epoch": 1.7, "learning_rate": 8.660467964010573e-06, "loss": 0.3918, "step": 313000 }, { "epoch": 1.7, "learning_rate": 8.642353695582474e-06, "loss": 0.394, "step": 313500 }, { "epoch": 1.71, "learning_rate": 8.624239427154376e-06, "loss": 0.4117, "step": 314000 }, { "epoch": 1.71, "learning_rate": 8.606125158726277e-06, "loss": 0.4086, "step": 314500 }, { "epoch": 1.71, "learning_rate": 8.58801089029818e-06, "loss": 0.4041, "step": 315000 }, { "epoch": 1.71, "learning_rate": 8.569896621870082e-06, "loss": 0.4001, "step": 315500 }, { "epoch": 1.72, "learning_rate": 8.551782353441982e-06, "loss": 0.3984, "step": 316000 }, { "epoch": 1.72, "learning_rate": 8.533668085013885e-06, "loss": 0.4075, "step": 316500 }, { "epoch": 1.72, "learning_rate": 8.515553816585787e-06, "loss": 0.3936, "step": 317000 }, { "epoch": 1.73, "learning_rate": 8.49743954815769e-06, "loss": 0.4087, "step": 317500 }, { "epoch": 1.73, "learning_rate": 8.47932527972959e-06, "loss": 0.4097, "step": 318000 }, { "epoch": 1.73, "learning_rate": 8.461211011301493e-06, "loss": 0.3958, "step": 318500 }, { "epoch": 1.73, "learning_rate": 8.443096742873395e-06, "loss": 0.3968, "step": 319000 }, { "epoch": 1.74, "learning_rate": 8.424982474445297e-06, "loss": 0.4095, "step": 319500 }, { "epoch": 1.74, "learning_rate": 8.406868206017198e-06, "loss": 0.398, "step": 320000 }, { "epoch": 1.74, "learning_rate": 8.3887539375891e-06, "loss": 0.3995, "step": 320500 }, { "epoch": 1.74, "learning_rate": 8.370639669161003e-06, "loss": 0.3942, "step": 321000 }, { "epoch": 1.75, "learning_rate": 8.352525400732904e-06, "loss": 0.3973, "step": 321500 }, { "epoch": 1.75, "learning_rate": 8.334411132304806e-06, "loss": 0.3907, "step": 322000 }, { "epoch": 1.75, "learning_rate": 8.316296863876707e-06, "loss": 0.3982, "step": 322500 }, { "epoch": 1.76, "learning_rate": 8.298182595448609e-06, "loss": 0.3928, "step": 323000 }, { "epoch": 1.76, "learning_rate": 8.280068327020511e-06, "loss": 0.4021, "step": 323500 }, { "epoch": 1.76, "learning_rate": 8.261954058592412e-06, "loss": 0.4004, "step": 324000 }, { "epoch": 1.76, "learning_rate": 8.243839790164315e-06, "loss": 0.4082, "step": 324500 }, { "epoch": 1.77, "learning_rate": 8.225725521736217e-06, "loss": 0.3951, "step": 325000 }, { "epoch": 1.77, "learning_rate": 8.20761125330812e-06, "loss": 0.3935, "step": 325500 }, { "epoch": 1.77, "learning_rate": 8.189496984880022e-06, "loss": 0.4066, "step": 326000 }, { "epoch": 1.77, "learning_rate": 8.171382716451922e-06, "loss": 0.3934, "step": 326500 }, { "epoch": 1.78, "learning_rate": 8.153268448023825e-06, "loss": 0.3937, "step": 327000 }, { "epoch": 1.78, "learning_rate": 8.135154179595727e-06, "loss": 0.3965, "step": 327500 }, { "epoch": 1.78, "learning_rate": 8.117039911167628e-06, "loss": 0.4002, "step": 328000 }, { "epoch": 1.79, "learning_rate": 8.09892564273953e-06, "loss": 0.399, "step": 328500 }, { "epoch": 1.79, "learning_rate": 8.080811374311433e-06, "loss": 0.4041, "step": 329000 }, { "epoch": 1.79, "learning_rate": 8.062697105883333e-06, "loss": 0.397, "step": 329500 }, { "epoch": 1.79, "learning_rate": 8.044582837455236e-06, "loss": 0.3902, "step": 330000 }, { "epoch": 1.8, "learning_rate": 8.026468569027136e-06, "loss": 0.4092, "step": 330500 }, { "epoch": 1.8, "learning_rate": 8.008354300599039e-06, "loss": 0.3937, "step": 331000 }, { "epoch": 1.8, "learning_rate": 7.990240032170941e-06, "loss": 0.3857, "step": 331500 }, { "epoch": 1.8, "learning_rate": 7.972125763742843e-06, "loss": 0.3958, "step": 332000 }, { "epoch": 1.81, "learning_rate": 7.954011495314746e-06, "loss": 0.3934, "step": 332500 }, { "epoch": 1.81, "learning_rate": 7.935897226886648e-06, "loss": 0.3971, "step": 333000 }, { "epoch": 1.81, "learning_rate": 7.917782958458549e-06, "loss": 0.3908, "step": 333500 }, { "epoch": 1.82, "learning_rate": 7.899668690030451e-06, "loss": 0.3913, "step": 334000 }, { "epoch": 1.82, "learning_rate": 7.881554421602352e-06, "loss": 0.3912, "step": 334500 }, { "epoch": 1.82, "learning_rate": 7.863440153174254e-06, "loss": 0.3939, "step": 335000 }, { "epoch": 1.82, "learning_rate": 7.845325884746157e-06, "loss": 0.3955, "step": 335500 }, { "epoch": 1.83, "learning_rate": 7.827211616318057e-06, "loss": 0.3877, "step": 336000 }, { "epoch": 1.83, "learning_rate": 7.80909734788996e-06, "loss": 0.3938, "step": 336500 }, { "epoch": 1.83, "learning_rate": 7.790983079461862e-06, "loss": 0.3938, "step": 337000 }, { "epoch": 1.83, "learning_rate": 7.772868811033763e-06, "loss": 0.4011, "step": 337500 }, { "epoch": 1.84, "learning_rate": 7.754754542605665e-06, "loss": 0.3809, "step": 338000 }, { "epoch": 1.84, "learning_rate": 7.736640274177568e-06, "loss": 0.3949, "step": 338500 }, { "epoch": 1.84, "learning_rate": 7.71852600574947e-06, "loss": 0.3888, "step": 339000 }, { "epoch": 1.84, "learning_rate": 7.70041173732137e-06, "loss": 0.3905, "step": 339500 }, { "epoch": 1.85, "learning_rate": 7.682297468893273e-06, "loss": 0.3878, "step": 340000 }, { "epoch": 1.85, "learning_rate": 7.664183200465176e-06, "loss": 0.3882, "step": 340500 }, { "epoch": 1.85, "learning_rate": 7.646068932037078e-06, "loss": 0.3965, "step": 341000 }, { "epoch": 1.86, "learning_rate": 7.627954663608979e-06, "loss": 0.3884, "step": 341500 }, { "epoch": 1.86, "learning_rate": 7.609840395180881e-06, "loss": 0.3865, "step": 342000 }, { "epoch": 1.86, "learning_rate": 7.591726126752782e-06, "loss": 0.3914, "step": 342500 }, { "epoch": 1.86, "learning_rate": 7.573611858324684e-06, "loss": 0.3807, "step": 343000 }, { "epoch": 1.87, "learning_rate": 7.5554975898965864e-06, "loss": 0.3878, "step": 343500 }, { "epoch": 1.87, "learning_rate": 7.537383321468488e-06, "loss": 0.392, "step": 344000 }, { "epoch": 1.87, "learning_rate": 7.51926905304039e-06, "loss": 0.3938, "step": 344500 }, { "epoch": 1.87, "learning_rate": 7.501154784612292e-06, "loss": 0.3954, "step": 345000 }, { "epoch": 1.88, "learning_rate": 7.4830405161841934e-06, "loss": 0.3897, "step": 345500 }, { "epoch": 1.88, "learning_rate": 7.464926247756096e-06, "loss": 0.4023, "step": 346000 }, { "epoch": 1.88, "learning_rate": 7.4468119793279965e-06, "loss": 0.3944, "step": 346500 }, { "epoch": 1.89, "learning_rate": 7.428697710899899e-06, "loss": 0.3836, "step": 347000 }, { "epoch": 1.89, "learning_rate": 7.410583442471801e-06, "loss": 0.3894, "step": 347500 }, { "epoch": 1.89, "learning_rate": 7.392469174043703e-06, "loss": 0.3939, "step": 348000 }, { "epoch": 1.89, "learning_rate": 7.374354905615605e-06, "loss": 0.38, "step": 348500 }, { "epoch": 1.9, "learning_rate": 7.356240637187508e-06, "loss": 0.3906, "step": 349000 }, { "epoch": 1.9, "learning_rate": 7.338126368759408e-06, "loss": 0.3881, "step": 349500 }, { "epoch": 1.9, "learning_rate": 7.320012100331311e-06, "loss": 0.3777, "step": 350000 }, { "epoch": 1.9, "learning_rate": 7.301897831903212e-06, "loss": 0.3849, "step": 350500 }, { "epoch": 1.91, "learning_rate": 7.2837835634751146e-06, "loss": 0.3947, "step": 351000 }, { "epoch": 1.91, "learning_rate": 7.265669295047016e-06, "loss": 0.3896, "step": 351500 }, { "epoch": 1.91, "learning_rate": 7.247555026618918e-06, "loss": 0.3954, "step": 352000 }, { "epoch": 1.92, "learning_rate": 7.22944075819082e-06, "loss": 0.3864, "step": 352500 }, { "epoch": 1.92, "learning_rate": 7.211326489762722e-06, "loss": 0.3811, "step": 353000 }, { "epoch": 1.92, "learning_rate": 7.193212221334623e-06, "loss": 0.3902, "step": 353500 }, { "epoch": 1.92, "learning_rate": 7.1750979529065255e-06, "loss": 0.3776, "step": 354000 }, { "epoch": 1.93, "learning_rate": 7.156983684478428e-06, "loss": 0.383, "step": 354500 }, { "epoch": 1.93, "learning_rate": 7.138869416050329e-06, "loss": 0.3809, "step": 355000 }, { "epoch": 1.93, "learning_rate": 7.120755147622232e-06, "loss": 0.385, "step": 355500 }, { "epoch": 1.93, "learning_rate": 7.1026408791941325e-06, "loss": 0.387, "step": 356000 }, { "epoch": 1.94, "learning_rate": 7.084526610766035e-06, "loss": 0.3834, "step": 356500 }, { "epoch": 1.94, "learning_rate": 7.066412342337937e-06, "loss": 0.3801, "step": 357000 }, { "epoch": 1.94, "learning_rate": 7.048298073909838e-06, "loss": 0.3801, "step": 357500 }, { "epoch": 1.95, "learning_rate": 7.03018380548174e-06, "loss": 0.3878, "step": 358000 }, { "epoch": 1.95, "learning_rate": 7.012069537053643e-06, "loss": 0.3814, "step": 358500 }, { "epoch": 1.95, "learning_rate": 6.993955268625544e-06, "loss": 0.3841, "step": 359000 }, { "epoch": 1.95, "learning_rate": 6.975841000197447e-06, "loss": 0.3708, "step": 359500 }, { "epoch": 1.96, "learning_rate": 6.957726731769347e-06, "loss": 0.3828, "step": 360000 }, { "epoch": 1.96, "learning_rate": 6.93961246334125e-06, "loss": 0.3919, "step": 360500 }, { "epoch": 1.96, "learning_rate": 6.921498194913152e-06, "loss": 0.3845, "step": 361000 }, { "epoch": 1.96, "learning_rate": 6.903383926485054e-06, "loss": 0.379, "step": 361500 }, { "epoch": 1.97, "learning_rate": 6.885269658056956e-06, "loss": 0.3895, "step": 362000 }, { "epoch": 1.97, "learning_rate": 6.8671553896288575e-06, "loss": 0.3765, "step": 362500 }, { "epoch": 1.97, "learning_rate": 6.849041121200759e-06, "loss": 0.3773, "step": 363000 }, { "epoch": 1.98, "learning_rate": 6.8309268527726614e-06, "loss": 0.3943, "step": 363500 }, { "epoch": 1.98, "learning_rate": 6.812812584344562e-06, "loss": 0.3799, "step": 364000 }, { "epoch": 1.98, "learning_rate": 6.7946983159164645e-06, "loss": 0.3829, "step": 364500 }, { "epoch": 1.98, "learning_rate": 6.776584047488367e-06, "loss": 0.3889, "step": 365000 }, { "epoch": 1.99, "learning_rate": 6.7584697790602684e-06, "loss": 0.375, "step": 365500 }, { "epoch": 1.99, "learning_rate": 6.740355510632171e-06, "loss": 0.3787, "step": 366000 }, { "epoch": 1.99, "learning_rate": 6.722241242204073e-06, "loss": 0.3792, "step": 366500 }, { "epoch": 1.99, "learning_rate": 6.704126973775974e-06, "loss": 0.3944, "step": 367000 }, { "epoch": 2.0, "learning_rate": 6.686012705347876e-06, "loss": 0.3909, "step": 367500 }, { "epoch": 2.0, "learning_rate": 6.667898436919778e-06, "loss": 0.3905, "step": 368000 }, { "epoch": 2.0, "eval_accuracy": 0.770441767068273, "eval_loss": 0.7063438892364502, "eval_runtime": 74.5232, "eval_samples_per_second": 501.186, "eval_steps_per_second": 62.652, "step": 368034 }, { "epoch": 2.0, "learning_rate": 6.649784168491679e-06, "loss": 0.3327, "step": 368500 }, { "epoch": 2.01, "learning_rate": 6.631669900063582e-06, "loss": 0.3324, "step": 369000 }, { "epoch": 2.01, "learning_rate": 6.613555631635483e-06, "loss": 0.3303, "step": 369500 }, { "epoch": 2.01, "learning_rate": 6.595441363207386e-06, "loss": 0.3386, "step": 370000 }, { "epoch": 2.01, "learning_rate": 6.577327094779288e-06, "loss": 0.3314, "step": 370500 }, { "epoch": 2.02, "learning_rate": 6.559212826351189e-06, "loss": 0.3249, "step": 371000 }, { "epoch": 2.02, "learning_rate": 6.541098557923091e-06, "loss": 0.3242, "step": 371500 }, { "epoch": 2.02, "learning_rate": 6.522984289494993e-06, "loss": 0.3312, "step": 372000 }, { "epoch": 2.02, "learning_rate": 6.504870021066895e-06, "loss": 0.334, "step": 372500 }, { "epoch": 2.03, "learning_rate": 6.4867557526387966e-06, "loss": 0.3307, "step": 373000 }, { "epoch": 2.03, "learning_rate": 6.468641484210698e-06, "loss": 0.3311, "step": 373500 }, { "epoch": 2.03, "learning_rate": 6.4505272157826005e-06, "loss": 0.3233, "step": 374000 }, { "epoch": 2.04, "learning_rate": 6.432412947354503e-06, "loss": 0.3323, "step": 374500 }, { "epoch": 2.04, "learning_rate": 6.4142986789264035e-06, "loss": 0.3191, "step": 375000 }, { "epoch": 2.04, "learning_rate": 6.396184410498306e-06, "loss": 0.3294, "step": 375500 }, { "epoch": 2.04, "learning_rate": 6.3780701420702075e-06, "loss": 0.3317, "step": 376000 }, { "epoch": 2.05, "learning_rate": 6.35995587364211e-06, "loss": 0.3356, "step": 376500 }, { "epoch": 2.05, "learning_rate": 6.341841605214012e-06, "loss": 0.3266, "step": 377000 }, { "epoch": 2.05, "learning_rate": 6.323727336785913e-06, "loss": 0.3246, "step": 377500 }, { "epoch": 2.05, "learning_rate": 6.305613068357815e-06, "loss": 0.322, "step": 378000 }, { "epoch": 2.06, "learning_rate": 6.287498799929718e-06, "loss": 0.3238, "step": 378500 }, { "epoch": 2.06, "learning_rate": 6.269384531501619e-06, "loss": 0.3319, "step": 379000 }, { "epoch": 2.06, "learning_rate": 6.251270263073521e-06, "loss": 0.3215, "step": 379500 }, { "epoch": 2.07, "learning_rate": 6.233155994645422e-06, "loss": 0.3225, "step": 380000 }, { "epoch": 2.07, "learning_rate": 6.215041726217325e-06, "loss": 0.3282, "step": 380500 }, { "epoch": 2.07, "learning_rate": 6.196927457789227e-06, "loss": 0.331, "step": 381000 }, { "epoch": 2.07, "learning_rate": 6.178813189361128e-06, "loss": 0.3234, "step": 381500 }, { "epoch": 2.08, "learning_rate": 6.16069892093303e-06, "loss": 0.3316, "step": 382000 }, { "epoch": 2.08, "learning_rate": 6.1425846525049325e-06, "loss": 0.3183, "step": 382500 }, { "epoch": 2.08, "learning_rate": 6.124470384076834e-06, "loss": 0.3203, "step": 383000 }, { "epoch": 2.08, "learning_rate": 6.1063561156487364e-06, "loss": 0.3341, "step": 383500 }, { "epoch": 2.09, "learning_rate": 6.088241847220637e-06, "loss": 0.3238, "step": 384000 }, { "epoch": 2.09, "learning_rate": 6.0701275787925395e-06, "loss": 0.33, "step": 384500 }, { "epoch": 2.09, "learning_rate": 6.052013310364442e-06, "loss": 0.3208, "step": 385000 }, { "epoch": 2.09, "learning_rate": 6.0338990419363434e-06, "loss": 0.3271, "step": 385500 }, { "epoch": 2.1, "learning_rate": 6.015784773508245e-06, "loss": 0.3296, "step": 386000 }, { "epoch": 2.1, "learning_rate": 5.997670505080147e-06, "loss": 0.3259, "step": 386500 }, { "epoch": 2.1, "learning_rate": 5.979556236652049e-06, "loss": 0.3241, "step": 387000 }, { "epoch": 2.11, "learning_rate": 5.961441968223951e-06, "loss": 0.3187, "step": 387500 }, { "epoch": 2.11, "learning_rate": 5.943327699795852e-06, "loss": 0.3211, "step": 388000 }, { "epoch": 2.11, "learning_rate": 5.925213431367754e-06, "loss": 0.3265, "step": 388500 }, { "epoch": 2.11, "learning_rate": 5.907099162939657e-06, "loss": 0.3233, "step": 389000 }, { "epoch": 2.12, "learning_rate": 5.888984894511558e-06, "loss": 0.3191, "step": 389500 }, { "epoch": 2.12, "learning_rate": 5.870870626083461e-06, "loss": 0.3254, "step": 390000 }, { "epoch": 2.12, "learning_rate": 5.852756357655362e-06, "loss": 0.3185, "step": 390500 }, { "epoch": 2.12, "learning_rate": 5.834642089227264e-06, "loss": 0.3197, "step": 391000 }, { "epoch": 2.13, "learning_rate": 5.816527820799166e-06, "loss": 0.3278, "step": 391500 }, { "epoch": 2.13, "learning_rate": 5.798413552371067e-06, "loss": 0.3269, "step": 392000 }, { "epoch": 2.13, "learning_rate": 5.780299283942969e-06, "loss": 0.3243, "step": 392500 }, { "epoch": 2.14, "learning_rate": 5.7621850155148716e-06, "loss": 0.3174, "step": 393000 }, { "epoch": 2.14, "learning_rate": 5.744070747086773e-06, "loss": 0.3188, "step": 393500 }, { "epoch": 2.14, "learning_rate": 5.7259564786586755e-06, "loss": 0.3301, "step": 394000 }, { "epoch": 2.14, "learning_rate": 5.707842210230578e-06, "loss": 0.3162, "step": 394500 }, { "epoch": 2.15, "learning_rate": 5.6897279418024785e-06, "loss": 0.3206, "step": 395000 }, { "epoch": 2.15, "learning_rate": 5.671613673374381e-06, "loss": 0.3179, "step": 395500 }, { "epoch": 2.15, "learning_rate": 5.6534994049462825e-06, "loss": 0.3274, "step": 396000 }, { "epoch": 2.15, "learning_rate": 5.635385136518184e-06, "loss": 0.322, "step": 396500 }, { "epoch": 2.16, "learning_rate": 5.617270868090086e-06, "loss": 0.3134, "step": 397000 }, { "epoch": 2.16, "learning_rate": 5.599156599661988e-06, "loss": 0.3213, "step": 397500 }, { "epoch": 2.16, "learning_rate": 5.58104233123389e-06, "loss": 0.3103, "step": 398000 }, { "epoch": 2.17, "learning_rate": 5.562928062805793e-06, "loss": 0.3338, "step": 398500 }, { "epoch": 2.17, "learning_rate": 5.544813794377693e-06, "loss": 0.3216, "step": 399000 }, { "epoch": 2.17, "learning_rate": 5.526699525949596e-06, "loss": 0.3245, "step": 399500 }, { "epoch": 2.17, "learning_rate": 5.508585257521497e-06, "loss": 0.3249, "step": 400000 }, { "epoch": 2.18, "learning_rate": 5.4904709890934e-06, "loss": 0.3168, "step": 400500 }, { "epoch": 2.18, "learning_rate": 5.472356720665302e-06, "loss": 0.3207, "step": 401000 }, { "epoch": 2.18, "learning_rate": 5.454242452237203e-06, "loss": 0.3269, "step": 401500 }, { "epoch": 2.18, "learning_rate": 5.436128183809105e-06, "loss": 0.3082, "step": 402000 }, { "epoch": 2.19, "learning_rate": 5.4180139153810075e-06, "loss": 0.3296, "step": 402500 }, { "epoch": 2.19, "learning_rate": 5.399899646952908e-06, "loss": 0.3191, "step": 403000 }, { "epoch": 2.19, "learning_rate": 5.381785378524811e-06, "loss": 0.3091, "step": 403500 }, { "epoch": 2.2, "learning_rate": 5.363671110096712e-06, "loss": 0.3171, "step": 404000 }, { "epoch": 2.2, "learning_rate": 5.3455568416686145e-06, "loss": 0.3215, "step": 404500 }, { "epoch": 2.2, "learning_rate": 5.327442573240517e-06, "loss": 0.3137, "step": 405000 }, { "epoch": 2.2, "learning_rate": 5.3093283048124176e-06, "loss": 0.3252, "step": 405500 }, { "epoch": 2.21, "learning_rate": 5.29121403638432e-06, "loss": 0.3205, "step": 406000 }, { "epoch": 2.21, "learning_rate": 5.273099767956222e-06, "loss": 0.3262, "step": 406500 }, { "epoch": 2.21, "learning_rate": 5.254985499528124e-06, "loss": 0.3187, "step": 407000 }, { "epoch": 2.21, "learning_rate": 5.236871231100025e-06, "loss": 0.3104, "step": 407500 }, { "epoch": 2.22, "learning_rate": 5.218756962671927e-06, "loss": 0.3193, "step": 408000 }, { "epoch": 2.22, "learning_rate": 5.200642694243829e-06, "loss": 0.3203, "step": 408500 }, { "epoch": 2.22, "learning_rate": 5.182528425815732e-06, "loss": 0.3218, "step": 409000 }, { "epoch": 2.23, "learning_rate": 5.164414157387632e-06, "loss": 0.3234, "step": 409500 }, { "epoch": 2.23, "learning_rate": 5.146299888959535e-06, "loss": 0.3153, "step": 410000 }, { "epoch": 2.23, "learning_rate": 5.128185620531437e-06, "loss": 0.3163, "step": 410500 }, { "epoch": 2.23, "learning_rate": 5.110071352103339e-06, "loss": 0.3253, "step": 411000 }, { "epoch": 2.24, "learning_rate": 5.091957083675241e-06, "loss": 0.3221, "step": 411500 }, { "epoch": 2.24, "learning_rate": 5.073842815247142e-06, "loss": 0.3189, "step": 412000 }, { "epoch": 2.24, "learning_rate": 5.055728546819044e-06, "loss": 0.3084, "step": 412500 }, { "epoch": 2.24, "learning_rate": 5.0376142783909465e-06, "loss": 0.3185, "step": 413000 }, { "epoch": 2.25, "learning_rate": 5.019500009962848e-06, "loss": 0.3149, "step": 413500 }, { "epoch": 2.25, "learning_rate": 5.00138574153475e-06, "loss": 0.3249, "step": 414000 }, { "epoch": 2.25, "learning_rate": 4.983271473106652e-06, "loss": 0.3187, "step": 414500 }, { "epoch": 2.26, "learning_rate": 4.9651572046785535e-06, "loss": 0.3179, "step": 415000 }, { "epoch": 2.26, "learning_rate": 4.947042936250456e-06, "loss": 0.3156, "step": 415500 }, { "epoch": 2.26, "learning_rate": 4.9289286678223575e-06, "loss": 0.3176, "step": 416000 }, { "epoch": 2.26, "learning_rate": 4.910814399394259e-06, "loss": 0.3172, "step": 416500 }, { "epoch": 2.27, "learning_rate": 4.8927001309661605e-06, "loss": 0.3225, "step": 417000 }, { "epoch": 2.27, "learning_rate": 4.874585862538063e-06, "loss": 0.3123, "step": 417500 }, { "epoch": 2.27, "learning_rate": 4.856471594109965e-06, "loss": 0.323, "step": 418000 }, { "epoch": 2.27, "learning_rate": 4.838357325681867e-06, "loss": 0.312, "step": 418500 }, { "epoch": 2.28, "learning_rate": 4.820243057253768e-06, "loss": 0.3177, "step": 419000 }, { "epoch": 2.28, "learning_rate": 4.802128788825671e-06, "loss": 0.3103, "step": 419500 }, { "epoch": 2.28, "learning_rate": 4.784014520397572e-06, "loss": 0.3129, "step": 420000 }, { "epoch": 2.29, "learning_rate": 4.765900251969474e-06, "loss": 0.3263, "step": 420500 }, { "epoch": 2.29, "learning_rate": 4.747785983541376e-06, "loss": 0.3068, "step": 421000 }, { "epoch": 2.29, "learning_rate": 4.729671715113278e-06, "loss": 0.3114, "step": 421500 }, { "epoch": 2.29, "learning_rate": 4.71155744668518e-06, "loss": 0.3218, "step": 422000 }, { "epoch": 2.3, "learning_rate": 4.693443178257082e-06, "loss": 0.3237, "step": 422500 }, { "epoch": 2.3, "learning_rate": 4.675328909828983e-06, "loss": 0.323, "step": 423000 }, { "epoch": 2.3, "learning_rate": 4.657214641400886e-06, "loss": 0.3315, "step": 423500 }, { "epoch": 2.3, "learning_rate": 4.639100372972787e-06, "loss": 0.317, "step": 424000 }, { "epoch": 2.31, "learning_rate": 4.6209861045446895e-06, "loss": 0.3129, "step": 424500 }, { "epoch": 2.31, "learning_rate": 4.602871836116591e-06, "loss": 0.319, "step": 425000 }, { "epoch": 2.31, "learning_rate": 4.584757567688493e-06, "loss": 0.3066, "step": 425500 }, { "epoch": 2.32, "learning_rate": 4.566643299260395e-06, "loss": 0.3144, "step": 426000 }, { "epoch": 2.32, "learning_rate": 4.5485290308322965e-06, "loss": 0.3187, "step": 426500 }, { "epoch": 2.32, "learning_rate": 4.530414762404198e-06, "loss": 0.3157, "step": 427000 }, { "epoch": 2.32, "learning_rate": 4.5123004939761e-06, "loss": 0.3108, "step": 427500 }, { "epoch": 2.33, "learning_rate": 4.494186225548002e-06, "loss": 0.3138, "step": 428000 }, { "epoch": 2.33, "learning_rate": 4.476071957119904e-06, "loss": 0.3132, "step": 428500 }, { "epoch": 2.33, "learning_rate": 4.457957688691806e-06, "loss": 0.3145, "step": 429000 }, { "epoch": 2.33, "learning_rate": 4.439843420263708e-06, "loss": 0.3175, "step": 429500 }, { "epoch": 2.34, "learning_rate": 4.42172915183561e-06, "loss": 0.3146, "step": 430000 }, { "epoch": 2.34, "learning_rate": 4.403614883407511e-06, "loss": 0.3142, "step": 430500 }, { "epoch": 2.34, "learning_rate": 4.385500614979413e-06, "loss": 0.3209, "step": 431000 }, { "epoch": 2.34, "learning_rate": 4.367386346551315e-06, "loss": 0.3088, "step": 431500 }, { "epoch": 2.35, "learning_rate": 4.349272078123218e-06, "loss": 0.3215, "step": 432000 }, { "epoch": 2.35, "learning_rate": 4.331157809695119e-06, "loss": 0.3235, "step": 432500 }, { "epoch": 2.35, "learning_rate": 4.313043541267021e-06, "loss": 0.3181, "step": 433000 }, { "epoch": 2.36, "learning_rate": 4.294929272838923e-06, "loss": 0.3111, "step": 433500 }, { "epoch": 2.36, "learning_rate": 4.276815004410825e-06, "loss": 0.3144, "step": 434000 }, { "epoch": 2.36, "learning_rate": 4.258700735982726e-06, "loss": 0.3135, "step": 434500 }, { "epoch": 2.36, "learning_rate": 4.2405864675546285e-06, "loss": 0.3088, "step": 435000 }, { "epoch": 2.37, "learning_rate": 4.222472199126531e-06, "loss": 0.3086, "step": 435500 }, { "epoch": 2.37, "learning_rate": 4.2043579306984324e-06, "loss": 0.3203, "step": 436000 }, { "epoch": 2.37, "learning_rate": 4.186243662270334e-06, "loss": 0.3093, "step": 436500 }, { "epoch": 2.37, "learning_rate": 4.1681293938422355e-06, "loss": 0.311, "step": 437000 }, { "epoch": 2.38, "learning_rate": 4.150015125414138e-06, "loss": 0.3084, "step": 437500 }, { "epoch": 2.38, "learning_rate": 4.1319008569860394e-06, "loss": 0.3176, "step": 438000 }, { "epoch": 2.38, "learning_rate": 4.113786588557942e-06, "loss": 0.3035, "step": 438500 }, { "epoch": 2.39, "learning_rate": 4.095672320129843e-06, "loss": 0.308, "step": 439000 }, { "epoch": 2.39, "learning_rate": 4.077558051701746e-06, "loss": 0.3134, "step": 439500 }, { "epoch": 2.39, "learning_rate": 4.059443783273647e-06, "loss": 0.2974, "step": 440000 }, { "epoch": 2.39, "learning_rate": 4.041329514845549e-06, "loss": 0.3137, "step": 440500 }, { "epoch": 2.4, "learning_rate": 4.02321524641745e-06, "loss": 0.3142, "step": 441000 }, { "epoch": 2.4, "learning_rate": 4.005100977989353e-06, "loss": 0.3102, "step": 441500 }, { "epoch": 2.4, "learning_rate": 3.986986709561254e-06, "loss": 0.3107, "step": 442000 }, { "epoch": 2.4, "learning_rate": 3.968872441133157e-06, "loss": 0.3053, "step": 442500 }, { "epoch": 2.41, "learning_rate": 3.950758172705058e-06, "loss": 0.3134, "step": 443000 }, { "epoch": 2.41, "learning_rate": 3.9326439042769606e-06, "loss": 0.3072, "step": 443500 }, { "epoch": 2.41, "learning_rate": 3.914529635848862e-06, "loss": 0.3073, "step": 444000 }, { "epoch": 2.42, "learning_rate": 3.896415367420764e-06, "loss": 0.3058, "step": 444500 }, { "epoch": 2.42, "learning_rate": 3.878301098992665e-06, "loss": 0.3052, "step": 445000 }, { "epoch": 2.42, "learning_rate": 3.8601868305645676e-06, "loss": 0.3153, "step": 445500 }, { "epoch": 2.42, "learning_rate": 3.84207256213647e-06, "loss": 0.3158, "step": 446000 }, { "epoch": 2.43, "learning_rate": 3.8239582937083715e-06, "loss": 0.3132, "step": 446500 }, { "epoch": 2.43, "learning_rate": 3.805844025280273e-06, "loss": 0.316, "step": 447000 }, { "epoch": 2.43, "learning_rate": 3.7877297568521754e-06, "loss": 0.3138, "step": 447500 }, { "epoch": 2.43, "learning_rate": 3.769615488424077e-06, "loss": 0.312, "step": 448000 }, { "epoch": 2.44, "learning_rate": 3.751501219995979e-06, "loss": 0.3064, "step": 448500 }, { "epoch": 2.44, "learning_rate": 3.7333869515678804e-06, "loss": 0.3072, "step": 449000 }, { "epoch": 2.44, "learning_rate": 3.715272683139783e-06, "loss": 0.3068, "step": 449500 }, { "epoch": 2.45, "learning_rate": 3.6971584147116848e-06, "loss": 0.3157, "step": 450000 }, { "epoch": 2.45, "learning_rate": 3.6790441462835863e-06, "loss": 0.3047, "step": 450500 }, { "epoch": 2.45, "learning_rate": 3.660929877855488e-06, "loss": 0.3107, "step": 451000 }, { "epoch": 2.45, "learning_rate": 3.6428156094273902e-06, "loss": 0.3156, "step": 451500 }, { "epoch": 2.46, "learning_rate": 3.624701340999292e-06, "loss": 0.2987, "step": 452000 }, { "epoch": 2.46, "learning_rate": 3.6065870725711937e-06, "loss": 0.3088, "step": 452500 }, { "epoch": 2.46, "learning_rate": 3.5884728041430957e-06, "loss": 0.3117, "step": 453000 }, { "epoch": 2.46, "learning_rate": 3.5703585357149976e-06, "loss": 0.3109, "step": 453500 }, { "epoch": 2.47, "learning_rate": 3.5522442672868996e-06, "loss": 0.3197, "step": 454000 }, { "epoch": 2.47, "learning_rate": 3.534129998858801e-06, "loss": 0.3121, "step": 454500 }, { "epoch": 2.47, "learning_rate": 3.516015730430703e-06, "loss": 0.3017, "step": 455000 }, { "epoch": 2.48, "learning_rate": 3.4979014620026055e-06, "loss": 0.3129, "step": 455500 }, { "epoch": 2.48, "learning_rate": 3.479787193574507e-06, "loss": 0.3093, "step": 456000 }, { "epoch": 2.48, "learning_rate": 3.4616729251464086e-06, "loss": 0.3062, "step": 456500 }, { "epoch": 2.48, "learning_rate": 3.4435586567183105e-06, "loss": 0.301, "step": 457000 }, { "epoch": 2.49, "learning_rate": 3.425444388290213e-06, "loss": 0.3082, "step": 457500 }, { "epoch": 2.49, "learning_rate": 3.4073301198621144e-06, "loss": 0.3069, "step": 458000 }, { "epoch": 2.49, "learning_rate": 3.3892158514340164e-06, "loss": 0.3084, "step": 458500 }, { "epoch": 2.49, "learning_rate": 3.371101583005918e-06, "loss": 0.3104, "step": 459000 }, { "epoch": 2.5, "learning_rate": 3.3529873145778203e-06, "loss": 0.3015, "step": 459500 }, { "epoch": 2.5, "learning_rate": 3.334873046149722e-06, "loss": 0.3113, "step": 460000 }, { "epoch": 2.5, "learning_rate": 3.316758777721624e-06, "loss": 0.3018, "step": 460500 }, { "epoch": 2.51, "learning_rate": 3.2986445092935253e-06, "loss": 0.3158, "step": 461000 }, { "epoch": 2.51, "learning_rate": 3.2805302408654277e-06, "loss": 0.3079, "step": 461500 }, { "epoch": 2.51, "learning_rate": 3.2624159724373293e-06, "loss": 0.3153, "step": 462000 }, { "epoch": 2.51, "learning_rate": 3.2443017040092312e-06, "loss": 0.2989, "step": 462500 }, { "epoch": 2.52, "learning_rate": 3.2261874355811328e-06, "loss": 0.3113, "step": 463000 }, { "epoch": 2.52, "learning_rate": 3.208073167153035e-06, "loss": 0.3077, "step": 463500 }, { "epoch": 2.52, "learning_rate": 3.189958898724937e-06, "loss": 0.3, "step": 464000 }, { "epoch": 2.52, "learning_rate": 3.1718446302968386e-06, "loss": 0.3044, "step": 464500 }, { "epoch": 2.53, "learning_rate": 3.15373036186874e-06, "loss": 0.296, "step": 465000 }, { "epoch": 2.53, "learning_rate": 3.1356160934406426e-06, "loss": 0.3072, "step": 465500 }, { "epoch": 2.53, "learning_rate": 3.1175018250125445e-06, "loss": 0.3002, "step": 466000 }, { "epoch": 2.54, "learning_rate": 3.099387556584446e-06, "loss": 0.3048, "step": 466500 }, { "epoch": 2.54, "learning_rate": 3.081273288156348e-06, "loss": 0.2984, "step": 467000 }, { "epoch": 2.54, "learning_rate": 3.06315901972825e-06, "loss": 0.3168, "step": 467500 }, { "epoch": 2.54, "learning_rate": 3.045044751300152e-06, "loss": 0.2973, "step": 468000 }, { "epoch": 2.55, "learning_rate": 3.0269304828720535e-06, "loss": 0.3085, "step": 468500 }, { "epoch": 2.55, "learning_rate": 3.0088162144439554e-06, "loss": 0.3066, "step": 469000 }, { "epoch": 2.55, "learning_rate": 2.990701946015858e-06, "loss": 0.3099, "step": 469500 }, { "epoch": 2.55, "learning_rate": 2.9725876775877593e-06, "loss": 0.2948, "step": 470000 }, { "epoch": 2.56, "learning_rate": 2.954473409159661e-06, "loss": 0.3089, "step": 470500 }, { "epoch": 2.56, "learning_rate": 2.9363591407315633e-06, "loss": 0.3003, "step": 471000 }, { "epoch": 2.56, "learning_rate": 2.9182448723034652e-06, "loss": 0.297, "step": 471500 }, { "epoch": 2.56, "learning_rate": 2.9001306038753668e-06, "loss": 0.302, "step": 472000 }, { "epoch": 2.57, "learning_rate": 2.8820163354472687e-06, "loss": 0.3137, "step": 472500 }, { "epoch": 2.57, "learning_rate": 2.8639020670191707e-06, "loss": 0.3104, "step": 473000 }, { "epoch": 2.57, "learning_rate": 2.8457877985910726e-06, "loss": 0.3063, "step": 473500 }, { "epoch": 2.58, "learning_rate": 2.827673530162974e-06, "loss": 0.3039, "step": 474000 }, { "epoch": 2.58, "learning_rate": 2.809559261734876e-06, "loss": 0.3042, "step": 474500 }, { "epoch": 2.58, "learning_rate": 2.7914449933067785e-06, "loss": 0.3072, "step": 475000 }, { "epoch": 2.58, "learning_rate": 2.77333072487868e-06, "loss": 0.3025, "step": 475500 }, { "epoch": 2.59, "learning_rate": 2.7552164564505816e-06, "loss": 0.3048, "step": 476000 }, { "epoch": 2.59, "learning_rate": 2.7371021880224836e-06, "loss": 0.314, "step": 476500 }, { "epoch": 2.59, "learning_rate": 2.718987919594386e-06, "loss": 0.3, "step": 477000 }, { "epoch": 2.59, "learning_rate": 2.7008736511662875e-06, "loss": 0.3074, "step": 477500 }, { "epoch": 2.6, "learning_rate": 2.6827593827381894e-06, "loss": 0.3116, "step": 478000 }, { "epoch": 2.6, "learning_rate": 2.664645114310091e-06, "loss": 0.2957, "step": 478500 }, { "epoch": 2.6, "learning_rate": 2.6465308458819933e-06, "loss": 0.307, "step": 479000 }, { "epoch": 2.61, "learning_rate": 2.628416577453895e-06, "loss": 0.304, "step": 479500 }, { "epoch": 2.61, "learning_rate": 2.610302309025797e-06, "loss": 0.2963, "step": 480000 }, { "epoch": 2.61, "learning_rate": 2.5921880405976984e-06, "loss": 0.306, "step": 480500 }, { "epoch": 2.61, "learning_rate": 2.5740737721696008e-06, "loss": 0.3084, "step": 481000 }, { "epoch": 2.62, "learning_rate": 2.5559595037415023e-06, "loss": 0.3028, "step": 481500 }, { "epoch": 2.62, "learning_rate": 2.5378452353134043e-06, "loss": 0.3041, "step": 482000 }, { "epoch": 2.62, "learning_rate": 2.519730966885306e-06, "loss": 0.3007, "step": 482500 }, { "epoch": 2.62, "learning_rate": 2.501616698457208e-06, "loss": 0.3054, "step": 483000 }, { "epoch": 2.63, "learning_rate": 2.48350243002911e-06, "loss": 0.3012, "step": 483500 }, { "epoch": 2.63, "learning_rate": 2.4653881616010117e-06, "loss": 0.3051, "step": 484000 }, { "epoch": 2.63, "learning_rate": 2.4472738931729136e-06, "loss": 0.2977, "step": 484500 }, { "epoch": 2.64, "learning_rate": 2.4291596247448156e-06, "loss": 0.2999, "step": 485000 }, { "epoch": 2.64, "learning_rate": 2.4110453563167176e-06, "loss": 0.3, "step": 485500 }, { "epoch": 2.64, "learning_rate": 2.392931087888619e-06, "loss": 0.2982, "step": 486000 }, { "epoch": 2.64, "learning_rate": 2.374816819460521e-06, "loss": 0.2997, "step": 486500 }, { "epoch": 2.65, "learning_rate": 2.356702551032423e-06, "loss": 0.3103, "step": 487000 }, { "epoch": 2.65, "learning_rate": 2.338588282604325e-06, "loss": 0.2953, "step": 487500 }, { "epoch": 2.65, "learning_rate": 2.3204740141762265e-06, "loss": 0.299, "step": 488000 }, { "epoch": 2.65, "learning_rate": 2.3023597457481285e-06, "loss": 0.3016, "step": 488500 }, { "epoch": 2.66, "learning_rate": 2.2842454773200304e-06, "loss": 0.3065, "step": 489000 }, { "epoch": 2.66, "learning_rate": 2.2661312088919324e-06, "loss": 0.2985, "step": 489500 }, { "epoch": 2.66, "learning_rate": 2.248016940463834e-06, "loss": 0.2986, "step": 490000 }, { "epoch": 2.67, "learning_rate": 2.2299026720357363e-06, "loss": 0.2939, "step": 490500 }, { "epoch": 2.67, "learning_rate": 2.211788403607638e-06, "loss": 0.2975, "step": 491000 }, { "epoch": 2.67, "learning_rate": 2.19367413517954e-06, "loss": 0.297, "step": 491500 }, { "epoch": 2.67, "learning_rate": 2.1755598667514418e-06, "loss": 0.2951, "step": 492000 }, { "epoch": 2.68, "learning_rate": 2.1574455983233437e-06, "loss": 0.2988, "step": 492500 }, { "epoch": 2.68, "learning_rate": 2.1393313298952453e-06, "loss": 0.301, "step": 493000 }, { "epoch": 2.68, "learning_rate": 2.121217061467147e-06, "loss": 0.3037, "step": 493500 }, { "epoch": 2.68, "learning_rate": 2.103102793039049e-06, "loss": 0.2951, "step": 494000 }, { "epoch": 2.69, "learning_rate": 2.084988524610951e-06, "loss": 0.3028, "step": 494500 }, { "epoch": 2.69, "learning_rate": 2.0668742561828527e-06, "loss": 0.2997, "step": 495000 }, { "epoch": 2.69, "learning_rate": 2.0487599877547546e-06, "loss": 0.3091, "step": 495500 }, { "epoch": 2.7, "learning_rate": 2.0306457193266566e-06, "loss": 0.2846, "step": 496000 }, { "epoch": 2.7, "learning_rate": 2.0125314508985585e-06, "loss": 0.2981, "step": 496500 }, { "epoch": 2.7, "learning_rate": 1.99441718247046e-06, "loss": 0.3015, "step": 497000 }, { "epoch": 2.7, "learning_rate": 1.9763029140423625e-06, "loss": 0.3045, "step": 497500 }, { "epoch": 2.71, "learning_rate": 1.958188645614264e-06, "loss": 0.3114, "step": 498000 }, { "epoch": 2.71, "learning_rate": 1.940074377186166e-06, "loss": 0.2938, "step": 498500 }, { "epoch": 2.71, "learning_rate": 1.921960108758068e-06, "loss": 0.2945, "step": 499000 }, { "epoch": 2.71, "learning_rate": 1.9038458403299699e-06, "loss": 0.3022, "step": 499500 }, { "epoch": 2.72, "learning_rate": 1.8857315719018714e-06, "loss": 0.2936, "step": 500000 }, { "epoch": 2.72, "learning_rate": 1.8676173034737736e-06, "loss": 0.3015, "step": 500500 }, { "epoch": 2.72, "learning_rate": 1.8495030350456753e-06, "loss": 0.2953, "step": 501000 }, { "epoch": 2.73, "learning_rate": 1.8313887666175773e-06, "loss": 0.2917, "step": 501500 }, { "epoch": 2.73, "learning_rate": 1.813274498189479e-06, "loss": 0.3005, "step": 502000 }, { "epoch": 2.73, "learning_rate": 1.795160229761381e-06, "loss": 0.2939, "step": 502500 }, { "epoch": 2.73, "learning_rate": 1.7770459613332827e-06, "loss": 0.2995, "step": 503000 }, { "epoch": 2.74, "learning_rate": 1.7589316929051847e-06, "loss": 0.3113, "step": 503500 }, { "epoch": 2.74, "learning_rate": 1.7408174244770865e-06, "loss": 0.3078, "step": 504000 }, { "epoch": 2.74, "learning_rate": 1.7227031560489884e-06, "loss": 0.3027, "step": 504500 }, { "epoch": 2.74, "learning_rate": 1.7045888876208902e-06, "loss": 0.2968, "step": 505000 }, { "epoch": 2.75, "learning_rate": 1.6864746191927921e-06, "loss": 0.3045, "step": 505500 }, { "epoch": 2.75, "learning_rate": 1.6683603507646939e-06, "loss": 0.3058, "step": 506000 }, { "epoch": 2.75, "learning_rate": 1.650246082336596e-06, "loss": 0.2926, "step": 506500 }, { "epoch": 2.76, "learning_rate": 1.6321318139084976e-06, "loss": 0.3029, "step": 507000 }, { "epoch": 2.76, "learning_rate": 1.6140175454803997e-06, "loss": 0.3055, "step": 507500 }, { "epoch": 2.76, "learning_rate": 1.5959032770523015e-06, "loss": 0.2957, "step": 508000 }, { "epoch": 2.76, "learning_rate": 1.5777890086242035e-06, "loss": 0.3008, "step": 508500 }, { "epoch": 2.77, "learning_rate": 1.5596747401961052e-06, "loss": 0.2984, "step": 509000 }, { "epoch": 2.77, "learning_rate": 1.5415604717680072e-06, "loss": 0.2984, "step": 509500 }, { "epoch": 2.77, "learning_rate": 1.523446203339909e-06, "loss": 0.2904, "step": 510000 }, { "epoch": 2.77, "learning_rate": 1.5053319349118109e-06, "loss": 0.3063, "step": 510500 }, { "epoch": 2.78, "learning_rate": 1.4872176664837126e-06, "loss": 0.2866, "step": 511000 }, { "epoch": 2.78, "learning_rate": 1.4691033980556146e-06, "loss": 0.2963, "step": 511500 }, { "epoch": 2.78, "learning_rate": 1.4509891296275163e-06, "loss": 0.2982, "step": 512000 }, { "epoch": 2.79, "learning_rate": 1.4328748611994183e-06, "loss": 0.2941, "step": 512500 }, { "epoch": 2.79, "learning_rate": 1.41476059277132e-06, "loss": 0.2851, "step": 513000 }, { "epoch": 2.79, "learning_rate": 1.3966463243432222e-06, "loss": 0.2976, "step": 513500 }, { "epoch": 2.79, "learning_rate": 1.3785320559151237e-06, "loss": 0.2935, "step": 514000 }, { "epoch": 2.8, "learning_rate": 1.360417787487026e-06, "loss": 0.3003, "step": 514500 }, { "epoch": 2.8, "learning_rate": 1.3423035190589277e-06, "loss": 0.3009, "step": 515000 }, { "epoch": 2.8, "learning_rate": 1.3241892506308296e-06, "loss": 0.2948, "step": 515500 }, { "epoch": 2.8, "learning_rate": 1.3060749822027314e-06, "loss": 0.2905, "step": 516000 }, { "epoch": 2.81, "learning_rate": 1.2879607137746333e-06, "loss": 0.296, "step": 516500 }, { "epoch": 2.81, "learning_rate": 1.269846445346535e-06, "loss": 0.2953, "step": 517000 }, { "epoch": 2.81, "learning_rate": 1.251732176918437e-06, "loss": 0.2974, "step": 517500 }, { "epoch": 2.81, "learning_rate": 1.2336179084903388e-06, "loss": 0.2864, "step": 518000 }, { "epoch": 2.82, "learning_rate": 1.2155036400622407e-06, "loss": 0.2926, "step": 518500 }, { "epoch": 2.82, "learning_rate": 1.1973893716341425e-06, "loss": 0.3051, "step": 519000 }, { "epoch": 2.82, "learning_rate": 1.1792751032060445e-06, "loss": 0.2924, "step": 519500 }, { "epoch": 2.83, "learning_rate": 1.1611608347779462e-06, "loss": 0.2983, "step": 520000 }, { "epoch": 2.83, "learning_rate": 1.1430465663498482e-06, "loss": 0.297, "step": 520500 }, { "epoch": 2.83, "learning_rate": 1.1249322979217501e-06, "loss": 0.2863, "step": 521000 }, { "epoch": 2.83, "learning_rate": 1.1068180294936519e-06, "loss": 0.2988, "step": 521500 }, { "epoch": 2.84, "learning_rate": 1.0887037610655538e-06, "loss": 0.2848, "step": 522000 }, { "epoch": 2.84, "learning_rate": 1.0705894926374556e-06, "loss": 0.2922, "step": 522500 }, { "epoch": 2.84, "learning_rate": 1.0524752242093575e-06, "loss": 0.2935, "step": 523000 }, { "epoch": 2.84, "learning_rate": 1.0343609557812593e-06, "loss": 0.296, "step": 523500 }, { "epoch": 2.85, "learning_rate": 1.0162466873531612e-06, "loss": 0.2974, "step": 524000 }, { "epoch": 2.85, "learning_rate": 9.981324189250632e-07, "loss": 0.2866, "step": 524500 }, { "epoch": 2.85, "learning_rate": 9.80018150496965e-07, "loss": 0.301, "step": 525000 }, { "epoch": 2.86, "learning_rate": 9.61903882068867e-07, "loss": 0.2959, "step": 525500 }, { "epoch": 2.86, "learning_rate": 9.437896136407688e-07, "loss": 0.3035, "step": 526000 }, { "epoch": 2.86, "learning_rate": 9.256753452126706e-07, "loss": 0.2796, "step": 526500 }, { "epoch": 2.86, "learning_rate": 9.075610767845725e-07, "loss": 0.2928, "step": 527000 }, { "epoch": 2.87, "learning_rate": 8.894468083564743e-07, "loss": 0.2943, "step": 527500 }, { "epoch": 2.87, "learning_rate": 8.713325399283762e-07, "loss": 0.293, "step": 528000 }, { "epoch": 2.87, "learning_rate": 8.53218271500278e-07, "loss": 0.2813, "step": 528500 }, { "epoch": 2.87, "learning_rate": 8.351040030721799e-07, "loss": 0.2936, "step": 529000 }, { "epoch": 2.88, "learning_rate": 8.169897346440818e-07, "loss": 0.2967, "step": 529500 }, { "epoch": 2.88, "learning_rate": 7.988754662159838e-07, "loss": 0.2939, "step": 530000 }, { "epoch": 2.88, "learning_rate": 7.807611977878857e-07, "loss": 0.2938, "step": 530500 }, { "epoch": 2.89, "learning_rate": 7.626469293597875e-07, "loss": 0.2956, "step": 531000 }, { "epoch": 2.89, "learning_rate": 7.445326609316894e-07, "loss": 0.2902, "step": 531500 }, { "epoch": 2.89, "learning_rate": 7.264183925035913e-07, "loss": 0.2943, "step": 532000 }, { "epoch": 2.89, "learning_rate": 7.083041240754932e-07, "loss": 0.2999, "step": 532500 }, { "epoch": 2.9, "learning_rate": 6.90189855647395e-07, "loss": 0.2913, "step": 533000 }, { "epoch": 2.9, "learning_rate": 6.720755872192969e-07, "loss": 0.291, "step": 533500 }, { "epoch": 2.9, "learning_rate": 6.539613187911987e-07, "loss": 0.3031, "step": 534000 }, { "epoch": 2.9, "learning_rate": 6.358470503631006e-07, "loss": 0.2961, "step": 534500 }, { "epoch": 2.91, "learning_rate": 6.177327819350024e-07, "loss": 0.2979, "step": 535000 }, { "epoch": 2.91, "learning_rate": 5.996185135069043e-07, "loss": 0.2888, "step": 535500 }, { "epoch": 2.91, "learning_rate": 5.815042450788062e-07, "loss": 0.3008, "step": 536000 }, { "epoch": 2.92, "learning_rate": 5.63389976650708e-07, "loss": 0.3043, "step": 536500 }, { "epoch": 2.92, "learning_rate": 5.452757082226099e-07, "loss": 0.2952, "step": 537000 }, { "epoch": 2.92, "learning_rate": 5.271614397945118e-07, "loss": 0.3015, "step": 537500 }, { "epoch": 2.92, "learning_rate": 5.090471713664137e-07, "loss": 0.2915, "step": 538000 }, { "epoch": 2.93, "learning_rate": 4.909329029383155e-07, "loss": 0.3014, "step": 538500 }, { "epoch": 2.93, "learning_rate": 4.728186345102174e-07, "loss": 0.2994, "step": 539000 }, { "epoch": 2.93, "learning_rate": 4.5470436608211923e-07, "loss": 0.3036, "step": 539500 }, { "epoch": 2.93, "learning_rate": 4.3659009765402114e-07, "loss": 0.29, "step": 540000 }, { "epoch": 2.94, "learning_rate": 4.18475829225923e-07, "loss": 0.2824, "step": 540500 }, { "epoch": 2.94, "learning_rate": 4.0036156079782485e-07, "loss": 0.2917, "step": 541000 }, { "epoch": 2.94, "learning_rate": 3.8224729236972675e-07, "loss": 0.2915, "step": 541500 }, { "epoch": 2.95, "learning_rate": 3.641330239416286e-07, "loss": 0.2932, "step": 542000 }, { "epoch": 2.95, "learning_rate": 3.4601875551353046e-07, "loss": 0.3033, "step": 542500 }, { "epoch": 2.95, "learning_rate": 3.279044870854323e-07, "loss": 0.2907, "step": 543000 }, { "epoch": 2.95, "learning_rate": 3.097902186573342e-07, "loss": 0.2925, "step": 543500 }, { "epoch": 2.96, "learning_rate": 2.916759502292361e-07, "loss": 0.2901, "step": 544000 }, { "epoch": 2.96, "learning_rate": 2.73561681801138e-07, "loss": 0.2898, "step": 544500 }, { "epoch": 2.96, "learning_rate": 2.5544741337303984e-07, "loss": 0.2861, "step": 545000 }, { "epoch": 2.96, "learning_rate": 2.3733314494494172e-07, "loss": 0.2947, "step": 545500 }, { "epoch": 2.97, "learning_rate": 2.192188765168436e-07, "loss": 0.2855, "step": 546000 }, { "epoch": 2.97, "learning_rate": 2.0110460808874545e-07, "loss": 0.2899, "step": 546500 }, { "epoch": 2.97, "learning_rate": 1.8299033966064733e-07, "loss": 0.2993, "step": 547000 }, { "epoch": 2.98, "learning_rate": 1.6487607123254918e-07, "loss": 0.3013, "step": 547500 }, { "epoch": 2.98, "learning_rate": 1.4676180280445104e-07, "loss": 0.2946, "step": 548000 }, { "epoch": 2.98, "learning_rate": 1.2864753437635292e-07, "loss": 0.2937, "step": 548500 }, { "epoch": 2.98, "learning_rate": 1.1053326594825478e-07, "loss": 0.2912, "step": 549000 }, { "epoch": 2.99, "learning_rate": 9.241899752015665e-08, "loss": 0.2912, "step": 549500 }, { "epoch": 2.99, "learning_rate": 7.430472909205853e-08, "loss": 0.2927, "step": 550000 }, { "epoch": 2.99, "learning_rate": 5.6190460663960404e-08, "loss": 0.2956, "step": 550500 }, { "epoch": 2.99, "learning_rate": 3.807619223586227e-08, "loss": 0.2959, "step": 551000 }, { "epoch": 3.0, "learning_rate": 1.9961923807764138e-08, "loss": 0.2791, "step": 551500 }, { "epoch": 3.0, "learning_rate": 1.8476553796660092e-09, "loss": 0.2951, "step": 552000 }, { "epoch": 3.0, "eval_accuracy": 0.7710575635876841, "eval_loss": 0.8383136987686157, "eval_runtime": 72.6822, "eval_samples_per_second": 513.881, "eval_steps_per_second": 64.239, "step": 552051 } ], "max_steps": 552051, "num_train_epochs": 3, "total_flos": 1.162013440270395e+18, "trial_name": null, "trial_params": null }