| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "Batch Mean": -2.9549560546875, | |
| "accuracy": 0.5078125, | |
| "epoch": 0, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 0.0025, | |
| "grad_norm": 38.43654251098633, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 0.8271, | |
| "step": 1 | |
| }, | |
| { | |
| "Batch Mean": -2.9178466796875, | |
| "accuracy": 0.46875, | |
| "epoch": 0.0025, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 38.60389709472656, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 0.8459, | |
| "step": 2 | |
| }, | |
| { | |
| "Batch Mean": -2.95965576171875, | |
| "accuracy": 0.4453125, | |
| "epoch": 0.005, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0075, | |
| "grad_norm": 40.155521392822266, | |
| "learning_rate": 4.5e-07, | |
| "loss": 0.8471, | |
| "step": 3 | |
| }, | |
| { | |
| "Batch Mean": -2.93951416015625, | |
| "accuracy": 0.515625, | |
| "epoch": 0.0075, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 39.40812683105469, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 0.8381, | |
| "step": 4 | |
| }, | |
| { | |
| "Batch Mean": -2.9075927734375, | |
| "accuracy": 0.46875, | |
| "epoch": 0.01, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0125, | |
| "grad_norm": 38.975746154785156, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.8312, | |
| "step": 5 | |
| }, | |
| { | |
| "Batch Mean": -2.85748291015625, | |
| "accuracy": 0.3125, | |
| "epoch": 0.0125, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 38.6825065612793, | |
| "learning_rate": 9e-07, | |
| "loss": 0.8466, | |
| "step": 6 | |
| }, | |
| { | |
| "Batch Mean": -2.689208984375, | |
| "accuracy": 0.390625, | |
| "epoch": 0.015, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0175, | |
| "grad_norm": 34.53704833984375, | |
| "learning_rate": 1.05e-06, | |
| "loss": 0.8319, | |
| "step": 7 | |
| }, | |
| { | |
| "Batch Mean": -2.65997314453125, | |
| "accuracy": 0.453125, | |
| "epoch": 0.0175, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 31.157188415527344, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.8268, | |
| "step": 8 | |
| }, | |
| { | |
| "Batch Mean": -2.0892333984375, | |
| "accuracy": 0.4921875, | |
| "epoch": 0.02, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0225, | |
| "grad_norm": 24.8486270904541, | |
| "learning_rate": 1.35e-06, | |
| "loss": 0.7703, | |
| "step": 9 | |
| }, | |
| { | |
| "Batch Mean": -1.9425048828125, | |
| "accuracy": 0.4140625, | |
| "epoch": 0.0225, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 25.407278060913086, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.7765, | |
| "step": 10 | |
| }, | |
| { | |
| "Batch Mean": -1.772979736328125, | |
| "accuracy": 0.34375, | |
| "epoch": 0.025, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0275, | |
| "grad_norm": 24.18885040283203, | |
| "learning_rate": 1.65e-06, | |
| "loss": 0.7768, | |
| "step": 11 | |
| }, | |
| { | |
| "Batch Mean": 0.017196819186210632, | |
| "accuracy": 0.5, | |
| "epoch": 0.0275, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 8.657893180847168, | |
| "learning_rate": 1.8e-06, | |
| "loss": 0.7086, | |
| "step": 12 | |
| }, | |
| { | |
| "Batch Mean": 0.37944215536117554, | |
| "accuracy": 0.4765625, | |
| "epoch": 0.03, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0325, | |
| "grad_norm": 13.965994834899902, | |
| "learning_rate": 1.95e-06, | |
| "loss": 0.6999, | |
| "step": 13 | |
| }, | |
| { | |
| "Batch Mean": 0.5208501815795898, | |
| "accuracy": 0.6171875, | |
| "epoch": 0.0325, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 22.43783950805664, | |
| "learning_rate": 2.1e-06, | |
| "loss": 0.6639, | |
| "step": 14 | |
| }, | |
| { | |
| "Batch Mean": 0.7098770141601562, | |
| "accuracy": 0.5546875, | |
| "epoch": 0.035, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0375, | |
| "grad_norm": 12.728647232055664, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.6735, | |
| "step": 15 | |
| }, | |
| { | |
| "Batch Mean": 0.9353656768798828, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.0375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 18.56553077697754, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.6592, | |
| "step": 16 | |
| }, | |
| { | |
| "Batch Mean": 1.4734210968017578, | |
| "accuracy": 0.640625, | |
| "epoch": 0.04, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0425, | |
| "grad_norm": 27.16295051574707, | |
| "learning_rate": 2.55e-06, | |
| "loss": 0.6713, | |
| "step": 17 | |
| }, | |
| { | |
| "Batch Mean": 1.8671340942382812, | |
| "accuracy": 0.6484375, | |
| "epoch": 0.0425, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 38.08174514770508, | |
| "learning_rate": 2.7e-06, | |
| "loss": 0.6832, | |
| "step": 18 | |
| }, | |
| { | |
| "Batch Mean": 1.8309574127197266, | |
| "accuracy": 0.671875, | |
| "epoch": 0.045, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0475, | |
| "grad_norm": 43.57632827758789, | |
| "learning_rate": 2.85e-06, | |
| "loss": 0.6855, | |
| "step": 19 | |
| }, | |
| { | |
| "Batch Mean": 1.5924930572509766, | |
| "accuracy": 0.6015625, | |
| "epoch": 0.0475, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 35.4539909362793, | |
| "learning_rate": 3e-06, | |
| "loss": 0.7016, | |
| "step": 20 | |
| }, | |
| { | |
| "Batch Mean": 1.2645306587219238, | |
| "accuracy": 0.7109375, | |
| "epoch": 0.05, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0525, | |
| "grad_norm": 33.7216796875, | |
| "learning_rate": 2.992105263157895e-06, | |
| "loss": 0.625, | |
| "step": 21 | |
| }, | |
| { | |
| "Batch Mean": 0.44832003116607666, | |
| "accuracy": 0.71875, | |
| "epoch": 0.0525, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 22.181182861328125, | |
| "learning_rate": 2.9842105263157896e-06, | |
| "loss": 0.5738, | |
| "step": 22 | |
| }, | |
| { | |
| "Batch Mean": -0.5859236717224121, | |
| "accuracy": 0.6796875, | |
| "epoch": 0.055, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0575, | |
| "grad_norm": 19.15841293334961, | |
| "learning_rate": 2.9763157894736843e-06, | |
| "loss": 0.6047, | |
| "step": 23 | |
| }, | |
| { | |
| "Batch Mean": -1.2775471210479736, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.0575, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 46.0495491027832, | |
| "learning_rate": 2.968421052631579e-06, | |
| "loss": 0.5853, | |
| "step": 24 | |
| }, | |
| { | |
| "Batch Mean": -1.3207778930664062, | |
| "accuracy": 0.6953125, | |
| "epoch": 0.06, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 44.94231033325195, | |
| "learning_rate": 2.960526315789474e-06, | |
| "loss": 0.6105, | |
| "step": 25 | |
| }, | |
| { | |
| "Batch Mean": -1.3301990032196045, | |
| "accuracy": 0.75, | |
| "epoch": 0.0625, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 45.24757766723633, | |
| "learning_rate": 2.9526315789473685e-06, | |
| "loss": 0.5729, | |
| "step": 26 | |
| }, | |
| { | |
| "Batch Mean": -0.9073872566223145, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.065, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0675, | |
| "grad_norm": 30.45476531982422, | |
| "learning_rate": 2.9447368421052633e-06, | |
| "loss": 0.5707, | |
| "step": 27 | |
| }, | |
| { | |
| "Batch Mean": -0.3670217990875244, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.0675, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 13.637907981872559, | |
| "learning_rate": 2.936842105263158e-06, | |
| "loss": 0.5046, | |
| "step": 28 | |
| }, | |
| { | |
| "Batch Mean": 0.32126128673553467, | |
| "accuracy": 0.71875, | |
| "epoch": 0.07, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0725, | |
| "grad_norm": 11.712913513183594, | |
| "learning_rate": 2.9289473684210528e-06, | |
| "loss": 0.5753, | |
| "step": 29 | |
| }, | |
| { | |
| "Batch Mean": 0.5725572109222412, | |
| "accuracy": 0.65625, | |
| "epoch": 0.0725, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 13.215094566345215, | |
| "learning_rate": 2.9210526315789475e-06, | |
| "loss": 0.6093, | |
| "step": 30 | |
| }, | |
| { | |
| "Batch Mean": 0.6064486503601074, | |
| "accuracy": 0.71875, | |
| "epoch": 0.075, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0775, | |
| "grad_norm": 17.638071060180664, | |
| "learning_rate": 2.9131578947368423e-06, | |
| "loss": 0.5394, | |
| "step": 31 | |
| }, | |
| { | |
| "Batch Mean": 0.4119257926940918, | |
| "accuracy": 0.796875, | |
| "epoch": 0.0775, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 17.742324829101562, | |
| "learning_rate": 2.905263157894737e-06, | |
| "loss": 0.5049, | |
| "step": 32 | |
| }, | |
| { | |
| "Batch Mean": 0.31667208671569824, | |
| "accuracy": 0.8125, | |
| "epoch": 0.08, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0825, | |
| "grad_norm": 13.98446273803711, | |
| "learning_rate": 2.8973684210526318e-06, | |
| "loss": 0.466, | |
| "step": 33 | |
| }, | |
| { | |
| "Batch Mean": -0.4047205150127411, | |
| "accuracy": 0.78125, | |
| "epoch": 0.0825, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 10.204410552978516, | |
| "learning_rate": 2.8894736842105265e-06, | |
| "loss": 0.4622, | |
| "step": 34 | |
| }, | |
| { | |
| "Batch Mean": -0.3730044364929199, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.085, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0875, | |
| "grad_norm": 12.993864059448242, | |
| "learning_rate": 2.8815789473684213e-06, | |
| "loss": 0.4788, | |
| "step": 35 | |
| }, | |
| { | |
| "Batch Mean": -0.38590008020401, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.0875, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 10.724040031433105, | |
| "learning_rate": 2.873684210526316e-06, | |
| "loss": 0.4847, | |
| "step": 36 | |
| }, | |
| { | |
| "Batch Mean": -0.21977567672729492, | |
| "accuracy": 0.765625, | |
| "epoch": 0.09, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0925, | |
| "grad_norm": 12.729230880737305, | |
| "learning_rate": 2.8657894736842103e-06, | |
| "loss": 0.5396, | |
| "step": 37 | |
| }, | |
| { | |
| "Batch Mean": -0.044023871421813965, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.0925, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 12.698225975036621, | |
| "learning_rate": 2.857894736842105e-06, | |
| "loss": 0.5317, | |
| "step": 38 | |
| }, | |
| { | |
| "Batch Mean": 0.3004276752471924, | |
| "accuracy": 0.84375, | |
| "epoch": 0.095, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0975, | |
| "grad_norm": 15.1500244140625, | |
| "learning_rate": 2.85e-06, | |
| "loss": 0.3625, | |
| "step": 39 | |
| }, | |
| { | |
| "Batch Mean": 0.4614996314048767, | |
| "accuracy": 0.78125, | |
| "epoch": 0.0975, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 14.328938484191895, | |
| "learning_rate": 2.8421052631578946e-06, | |
| "loss": 0.4741, | |
| "step": 40 | |
| }, | |
| { | |
| "Batch Mean": 0.219995379447937, | |
| "accuracy": 0.734375, | |
| "epoch": 0.1, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1025, | |
| "grad_norm": 16.527143478393555, | |
| "learning_rate": 2.8342105263157897e-06, | |
| "loss": 0.5388, | |
| "step": 41 | |
| }, | |
| { | |
| "Batch Mean": 0.24077653884887695, | |
| "accuracy": 0.71875, | |
| "epoch": 0.1025, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "grad_norm": 15.48572826385498, | |
| "learning_rate": 2.8263157894736845e-06, | |
| "loss": 0.5193, | |
| "step": 42 | |
| }, | |
| { | |
| "Batch Mean": -0.29242193698883057, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.105, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1075, | |
| "grad_norm": 14.708074569702148, | |
| "learning_rate": 2.8184210526315792e-06, | |
| "loss": 0.5096, | |
| "step": 43 | |
| }, | |
| { | |
| "Batch Mean": -0.5579910278320312, | |
| "accuracy": 0.765625, | |
| "epoch": 0.1075, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 18.473812103271484, | |
| "learning_rate": 2.810526315789474e-06, | |
| "loss": 0.5251, | |
| "step": 44 | |
| }, | |
| { | |
| "Batch Mean": -0.44131672382354736, | |
| "accuracy": 0.703125, | |
| "epoch": 0.11, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1125, | |
| "grad_norm": 24.496036529541016, | |
| "learning_rate": 2.8026315789473687e-06, | |
| "loss": 0.5768, | |
| "step": 45 | |
| }, | |
| { | |
| "Batch Mean": -0.2054896354675293, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.1125, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "grad_norm": 16.322071075439453, | |
| "learning_rate": 2.7947368421052635e-06, | |
| "loss": 0.441, | |
| "step": 46 | |
| }, | |
| { | |
| "Batch Mean": 0.5062417984008789, | |
| "accuracy": 0.734375, | |
| "epoch": 0.115, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1175, | |
| "grad_norm": 14.525461196899414, | |
| "learning_rate": 2.7868421052631578e-06, | |
| "loss": 0.4942, | |
| "step": 47 | |
| }, | |
| { | |
| "Batch Mean": 0.2660309374332428, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.1175, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 9.259953498840332, | |
| "learning_rate": 2.7789473684210525e-06, | |
| "loss": 0.3931, | |
| "step": 48 | |
| }, | |
| { | |
| "Batch Mean": 0.34576767683029175, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.12, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1225, | |
| "grad_norm": 11.19707202911377, | |
| "learning_rate": 2.7710526315789473e-06, | |
| "loss": 0.4824, | |
| "step": 49 | |
| }, | |
| { | |
| "Batch Mean": -0.02308782935142517, | |
| "accuracy": 0.796875, | |
| "epoch": 0.1225, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 8.539365768432617, | |
| "learning_rate": 2.763157894736842e-06, | |
| "loss": 0.4374, | |
| "step": 50 | |
| }, | |
| { | |
| "Batch Mean": -0.11477279663085938, | |
| "accuracy": 0.796875, | |
| "epoch": 0.125, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1275, | |
| "grad_norm": 8.27216911315918, | |
| "learning_rate": 2.7552631578947368e-06, | |
| "loss": 0.4368, | |
| "step": 51 | |
| }, | |
| { | |
| "Batch Mean": -0.31789374351501465, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.1275, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 10.260517120361328, | |
| "learning_rate": 2.7473684210526315e-06, | |
| "loss": 0.4347, | |
| "step": 52 | |
| }, | |
| { | |
| "Batch Mean": 0.09443974494934082, | |
| "accuracy": 0.8125, | |
| "epoch": 0.13, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1325, | |
| "grad_norm": 7.1499223709106445, | |
| "learning_rate": 2.7394736842105263e-06, | |
| "loss": 0.4101, | |
| "step": 53 | |
| }, | |
| { | |
| "Batch Mean": 0.10455203056335449, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.1325, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.135, | |
| "grad_norm": 8.759523391723633, | |
| "learning_rate": 2.7315789473684214e-06, | |
| "loss": 0.4678, | |
| "step": 54 | |
| }, | |
| { | |
| "Batch Mean": 0.3895939588546753, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.135, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1375, | |
| "grad_norm": 12.878321647644043, | |
| "learning_rate": 2.723684210526316e-06, | |
| "loss": 0.3717, | |
| "step": 55 | |
| }, | |
| { | |
| "Batch Mean": 0.4579277038574219, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.1375, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 11.548985481262207, | |
| "learning_rate": 2.715789473684211e-06, | |
| "loss": 0.5196, | |
| "step": 56 | |
| }, | |
| { | |
| "Batch Mean": 0.0871274471282959, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.14, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1425, | |
| "grad_norm": 9.4905424118042, | |
| "learning_rate": 2.7078947368421052e-06, | |
| "loss": 0.4155, | |
| "step": 57 | |
| }, | |
| { | |
| "Batch Mean": -0.27567076683044434, | |
| "accuracy": 0.8125, | |
| "epoch": 0.1425, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.145, | |
| "grad_norm": 9.461136817932129, | |
| "learning_rate": 2.7e-06, | |
| "loss": 0.4003, | |
| "step": 58 | |
| }, | |
| { | |
| "Batch Mean": -0.5103405714035034, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.145, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1475, | |
| "grad_norm": 13.972933769226074, | |
| "learning_rate": 2.6921052631578947e-06, | |
| "loss": 0.4395, | |
| "step": 59 | |
| }, | |
| { | |
| "Batch Mean": -0.47735142707824707, | |
| "accuracy": 0.734375, | |
| "epoch": 0.1475, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 12.991920471191406, | |
| "learning_rate": 2.6842105263157895e-06, | |
| "loss": 0.5417, | |
| "step": 60 | |
| }, | |
| { | |
| "Batch Mean": -0.2846529483795166, | |
| "accuracy": 0.78125, | |
| "epoch": 0.15, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1525, | |
| "grad_norm": 10.198124885559082, | |
| "learning_rate": 2.6763157894736842e-06, | |
| "loss": 0.4312, | |
| "step": 61 | |
| }, | |
| { | |
| "Batch Mean": 0.15892720222473145, | |
| "accuracy": 0.828125, | |
| "epoch": 0.1525, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.155, | |
| "grad_norm": 8.384869575500488, | |
| "learning_rate": 2.668421052631579e-06, | |
| "loss": 0.3634, | |
| "step": 62 | |
| }, | |
| { | |
| "Batch Mean": 0.16252660751342773, | |
| "accuracy": 0.796875, | |
| "epoch": 0.155, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1575, | |
| "grad_norm": 9.487040519714355, | |
| "learning_rate": 2.6605263157894737e-06, | |
| "loss": 0.4331, | |
| "step": 63 | |
| }, | |
| { | |
| "Batch Mean": 0.39125096797943115, | |
| "accuracy": 0.84375, | |
| "epoch": 0.1575, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 10.764354705810547, | |
| "learning_rate": 2.6526315789473685e-06, | |
| "loss": 0.3796, | |
| "step": 64 | |
| }, | |
| { | |
| "Batch Mean": 0.09885883331298828, | |
| "accuracy": 0.796875, | |
| "epoch": 0.16, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1625, | |
| "grad_norm": 8.251502990722656, | |
| "learning_rate": 2.644736842105263e-06, | |
| "loss": 0.4103, | |
| "step": 65 | |
| }, | |
| { | |
| "Batch Mean": -0.0615391731262207, | |
| "accuracy": 0.78125, | |
| "epoch": 0.1625, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.165, | |
| "grad_norm": 7.180301189422607, | |
| "learning_rate": 2.636842105263158e-06, | |
| "loss": 0.4218, | |
| "step": 66 | |
| }, | |
| { | |
| "Batch Mean": -0.44274067878723145, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.165, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1675, | |
| "grad_norm": 13.95067310333252, | |
| "learning_rate": 2.6289473684210527e-06, | |
| "loss": 0.4196, | |
| "step": 67 | |
| }, | |
| { | |
| "Batch Mean": -0.6870249509811401, | |
| "accuracy": 0.796875, | |
| "epoch": 0.1675, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 15.820197105407715, | |
| "learning_rate": 2.6210526315789474e-06, | |
| "loss": 0.4135, | |
| "step": 68 | |
| }, | |
| { | |
| "Batch Mean": -0.7148702144622803, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.17, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1725, | |
| "grad_norm": 18.115154266357422, | |
| "learning_rate": 2.613157894736842e-06, | |
| "loss": 0.5175, | |
| "step": 69 | |
| }, | |
| { | |
| "Batch Mean": -0.1326247751712799, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.1725, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 8.709199905395508, | |
| "learning_rate": 2.605263157894737e-06, | |
| "loss": 0.4396, | |
| "step": 70 | |
| }, | |
| { | |
| "Batch Mean": 0.15152764320373535, | |
| "accuracy": 0.828125, | |
| "epoch": 0.175, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1775, | |
| "grad_norm": 7.756810665130615, | |
| "learning_rate": 2.5973684210526317e-06, | |
| "loss": 0.4127, | |
| "step": 71 | |
| }, | |
| { | |
| "Batch Mean": 0.47759437561035156, | |
| "accuracy": 0.875, | |
| "epoch": 0.1775, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 11.938055038452148, | |
| "learning_rate": 2.5894736842105264e-06, | |
| "loss": 0.3728, | |
| "step": 72 | |
| }, | |
| { | |
| "Batch Mean": 0.6294691562652588, | |
| "accuracy": 0.8828125, | |
| "epoch": 0.18, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1825, | |
| "grad_norm": 16.090402603149414, | |
| "learning_rate": 2.581578947368421e-06, | |
| "loss": 0.3428, | |
| "step": 73 | |
| }, | |
| { | |
| "Batch Mean": 0.6011961698532104, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.1825, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.185, | |
| "grad_norm": 13.527336120605469, | |
| "learning_rate": 2.573684210526316e-06, | |
| "loss": 0.5287, | |
| "step": 74 | |
| }, | |
| { | |
| "Batch Mean": 0.009085655212402344, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.185, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 7.578335285186768, | |
| "learning_rate": 2.5657894736842107e-06, | |
| "loss": 0.4145, | |
| "step": 75 | |
| }, | |
| { | |
| "Batch Mean": -0.12276363372802734, | |
| "accuracy": 0.78125, | |
| "epoch": 0.1875, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 7.629185676574707, | |
| "learning_rate": 2.5578947368421054e-06, | |
| "loss": 0.4716, | |
| "step": 76 | |
| }, | |
| { | |
| "Batch Mean": -0.34308671951293945, | |
| "accuracy": 0.8125, | |
| "epoch": 0.19, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.1925, | |
| "grad_norm": 8.904648780822754, | |
| "learning_rate": 2.55e-06, | |
| "loss": 0.3838, | |
| "step": 77 | |
| }, | |
| { | |
| "Batch Mean": -0.28826236724853516, | |
| "accuracy": 0.78125, | |
| "epoch": 0.1925, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.195, | |
| "grad_norm": 9.088787078857422, | |
| "learning_rate": 2.542105263157895e-06, | |
| "loss": 0.4531, | |
| "step": 78 | |
| }, | |
| { | |
| "Batch Mean": -0.19193828105926514, | |
| "accuracy": 0.859375, | |
| "epoch": 0.195, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.1975, | |
| "grad_norm": 7.69492769241333, | |
| "learning_rate": 2.5342105263157892e-06, | |
| "loss": 0.3733, | |
| "step": 79 | |
| }, | |
| { | |
| "Batch Mean": 0.3690178394317627, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.1975, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 15.70446491241455, | |
| "learning_rate": 2.526315789473684e-06, | |
| "loss": 0.3847, | |
| "step": 80 | |
| }, | |
| { | |
| "Batch Mean": 0.456756591796875, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.2, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2025, | |
| "grad_norm": 13.275654792785645, | |
| "learning_rate": 2.5184210526315787e-06, | |
| "loss": 0.4081, | |
| "step": 81 | |
| }, | |
| { | |
| "Batch Mean": 0.486045241355896, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.2025, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.205, | |
| "grad_norm": 14.960883140563965, | |
| "learning_rate": 2.510526315789474e-06, | |
| "loss": 0.45, | |
| "step": 82 | |
| }, | |
| { | |
| "Batch Mean": 0.007278919219970703, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.205, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2075, | |
| "grad_norm": 9.315552711486816, | |
| "learning_rate": 2.5026315789473686e-06, | |
| "loss": 0.4603, | |
| "step": 83 | |
| }, | |
| { | |
| "Batch Mean": -0.3312312364578247, | |
| "accuracy": 0.7421875, | |
| "epoch": 0.2075, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 18.19389533996582, | |
| "learning_rate": 2.4947368421052634e-06, | |
| "loss": 0.4748, | |
| "step": 84 | |
| }, | |
| { | |
| "Batch Mean": -0.023685932159423828, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.21, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2125, | |
| "grad_norm": 7.646451473236084, | |
| "learning_rate": 2.486842105263158e-06, | |
| "loss": 0.3291, | |
| "step": 85 | |
| }, | |
| { | |
| "Batch Mean": -0.418212890625, | |
| "accuracy": 0.84375, | |
| "epoch": 0.2125, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.215, | |
| "grad_norm": 11.397950172424316, | |
| "learning_rate": 2.478947368421053e-06, | |
| "loss": 0.3491, | |
| "step": 86 | |
| }, | |
| { | |
| "Batch Mean": -0.2105419635772705, | |
| "accuracy": 0.796875, | |
| "epoch": 0.215, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.2175, | |
| "grad_norm": 16.71412467956543, | |
| "learning_rate": 2.4710526315789476e-06, | |
| "loss": 0.3686, | |
| "step": 87 | |
| }, | |
| { | |
| "Batch Mean": 0.18758773803710938, | |
| "accuracy": 0.78125, | |
| "epoch": 0.2175, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 15.67270278930664, | |
| "learning_rate": 2.4631578947368424e-06, | |
| "loss": 0.4844, | |
| "step": 88 | |
| }, | |
| { | |
| "Batch Mean": 0.20205163955688477, | |
| "accuracy": 0.78125, | |
| "epoch": 0.22, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2225, | |
| "grad_norm": 12.556285858154297, | |
| "learning_rate": 2.4552631578947367e-06, | |
| "loss": 0.4631, | |
| "step": 89 | |
| }, | |
| { | |
| "Batch Mean": 0.2241612672805786, | |
| "accuracy": 0.84375, | |
| "epoch": 0.2225, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.225, | |
| "grad_norm": 13.160058975219727, | |
| "learning_rate": 2.4473684210526314e-06, | |
| "loss": 0.3143, | |
| "step": 90 | |
| }, | |
| { | |
| "Batch Mean": 0.5450854301452637, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.225, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2275, | |
| "grad_norm": 19.004138946533203, | |
| "learning_rate": 2.439473684210526e-06, | |
| "loss": 0.3814, | |
| "step": 91 | |
| }, | |
| { | |
| "Batch Mean": 0.2415924072265625, | |
| "accuracy": 0.78125, | |
| "epoch": 0.2275, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 13.732966423034668, | |
| "learning_rate": 2.431578947368421e-06, | |
| "loss": 0.3925, | |
| "step": 92 | |
| }, | |
| { | |
| "Batch Mean": -0.015282154083251953, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.23, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2325, | |
| "grad_norm": 11.732492446899414, | |
| "learning_rate": 2.4236842105263157e-06, | |
| "loss": 0.3839, | |
| "step": 93 | |
| }, | |
| { | |
| "Batch Mean": -0.3396167755126953, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.2325, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.235, | |
| "grad_norm": 15.799851417541504, | |
| "learning_rate": 2.4157894736842104e-06, | |
| "loss": 0.3893, | |
| "step": 94 | |
| }, | |
| { | |
| "Batch Mean": -0.3651285171508789, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.235, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2375, | |
| "grad_norm": 12.945575714111328, | |
| "learning_rate": 2.4078947368421056e-06, | |
| "loss": 0.3942, | |
| "step": 95 | |
| }, | |
| { | |
| "Batch Mean": -0.24241328239440918, | |
| "accuracy": 0.828125, | |
| "epoch": 0.2375, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 11.39241886138916, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.3606, | |
| "step": 96 | |
| }, | |
| { | |
| "Batch Mean": -0.10072767734527588, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.24, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2425, | |
| "grad_norm": 9.7492094039917, | |
| "learning_rate": 2.392105263157895e-06, | |
| "loss": 0.3818, | |
| "step": 97 | |
| }, | |
| { | |
| "Batch Mean": 0.03002488613128662, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.2425, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.245, | |
| "grad_norm": 6.9692864418029785, | |
| "learning_rate": 2.38421052631579e-06, | |
| "loss": 0.3336, | |
| "step": 98 | |
| }, | |
| { | |
| "Batch Mean": 0.3361194133758545, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.245, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2475, | |
| "grad_norm": 13.135473251342773, | |
| "learning_rate": 2.376315789473684e-06, | |
| "loss": 0.3912, | |
| "step": 99 | |
| }, | |
| { | |
| "Batch Mean": 0.4362337589263916, | |
| "accuracy": 0.796875, | |
| "epoch": 0.2475, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 12.29136848449707, | |
| "learning_rate": 2.368421052631579e-06, | |
| "loss": 0.4137, | |
| "step": 100 | |
| }, | |
| { | |
| "Batch Mean": 0.4257016181945801, | |
| "accuracy": 0.875, | |
| "epoch": 0.25, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2525, | |
| "grad_norm": 13.732154846191406, | |
| "learning_rate": 2.3605263157894736e-06, | |
| "loss": 0.3721, | |
| "step": 101 | |
| }, | |
| { | |
| "Batch Mean": 0.06758689880371094, | |
| "accuracy": 0.8125, | |
| "epoch": 0.2525, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.255, | |
| "grad_norm": 9.70384693145752, | |
| "learning_rate": 2.3526315789473684e-06, | |
| "loss": 0.4345, | |
| "step": 102 | |
| }, | |
| { | |
| "Batch Mean": -0.4097929000854492, | |
| "accuracy": 0.8125, | |
| "epoch": 0.255, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2575, | |
| "grad_norm": 12.665343284606934, | |
| "learning_rate": 2.344736842105263e-06, | |
| "loss": 0.3869, | |
| "step": 103 | |
| }, | |
| { | |
| "Batch Mean": -0.8724770545959473, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.2575, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 20.12427520751953, | |
| "learning_rate": 2.336842105263158e-06, | |
| "loss": 0.4037, | |
| "step": 104 | |
| }, | |
| { | |
| "Batch Mean": -0.4974844455718994, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.26, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.2625, | |
| "grad_norm": 17.464170455932617, | |
| "learning_rate": 2.3289473684210526e-06, | |
| "loss": 0.4492, | |
| "step": 105 | |
| }, | |
| { | |
| "Batch Mean": -0.35894912481307983, | |
| "accuracy": 0.828125, | |
| "epoch": 0.2625, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.265, | |
| "grad_norm": 10.907158851623535, | |
| "learning_rate": 2.3210526315789473e-06, | |
| "loss": 0.3291, | |
| "step": 106 | |
| }, | |
| { | |
| "Batch Mean": 0.3651762008666992, | |
| "accuracy": 0.8125, | |
| "epoch": 0.265, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.2675, | |
| "grad_norm": 11.427133560180664, | |
| "learning_rate": 2.313157894736842e-06, | |
| "loss": 0.4021, | |
| "step": 107 | |
| }, | |
| { | |
| "Batch Mean": 0.2751443386077881, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.2675, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 8.229965209960938, | |
| "learning_rate": 2.305263157894737e-06, | |
| "loss": 0.3729, | |
| "step": 108 | |
| }, | |
| { | |
| "Batch Mean": 0.9130334854125977, | |
| "accuracy": 0.859375, | |
| "epoch": 0.27, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2725, | |
| "grad_norm": 22.57686996459961, | |
| "learning_rate": 2.2973684210526316e-06, | |
| "loss": 0.3397, | |
| "step": 109 | |
| }, | |
| { | |
| "Batch Mean": 0.7281837463378906, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.2725, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.275, | |
| "grad_norm": 16.920743942260742, | |
| "learning_rate": 2.2894736842105263e-06, | |
| "loss": 0.4643, | |
| "step": 110 | |
| }, | |
| { | |
| "Batch Mean": 0.4563823342323303, | |
| "accuracy": 0.8125, | |
| "epoch": 0.275, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2775, | |
| "grad_norm": 15.203326225280762, | |
| "learning_rate": 2.281578947368421e-06, | |
| "loss": 0.3964, | |
| "step": 111 | |
| }, | |
| { | |
| "Batch Mean": -0.07430100440979004, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.2775, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 13.103719711303711, | |
| "learning_rate": 2.273684210526316e-06, | |
| "loss": 0.4149, | |
| "step": 112 | |
| }, | |
| { | |
| "Batch Mean": -0.5845143795013428, | |
| "accuracy": 0.8125, | |
| "epoch": 0.28, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.2825, | |
| "grad_norm": 24.87859535217285, | |
| "learning_rate": 2.2657894736842106e-06, | |
| "loss": 0.4353, | |
| "step": 113 | |
| }, | |
| { | |
| "Batch Mean": -1.1507502794265747, | |
| "accuracy": 0.8671875, | |
| "epoch": 0.2825, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.285, | |
| "grad_norm": 27.043203353881836, | |
| "learning_rate": 2.2578947368421053e-06, | |
| "loss": 0.3758, | |
| "step": 114 | |
| }, | |
| { | |
| "Batch Mean": -1.2163114547729492, | |
| "accuracy": 0.8671875, | |
| "epoch": 0.285, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.2875, | |
| "grad_norm": 24.969430923461914, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.341, | |
| "step": 115 | |
| }, | |
| { | |
| "Batch Mean": -0.6281991004943848, | |
| "accuracy": 0.828125, | |
| "epoch": 0.2875, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 14.463933944702148, | |
| "learning_rate": 2.242105263157895e-06, | |
| "loss": 0.4114, | |
| "step": 116 | |
| }, | |
| { | |
| "Batch Mean": 0.09254121780395508, | |
| "accuracy": 0.84375, | |
| "epoch": 0.29, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.2925, | |
| "grad_norm": 7.876263618469238, | |
| "learning_rate": 2.2342105263157895e-06, | |
| "loss": 0.36, | |
| "step": 117 | |
| }, | |
| { | |
| "Batch Mean": 0.4857252240180969, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.2925, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.295, | |
| "grad_norm": 10.79910659790039, | |
| "learning_rate": 2.2263157894736843e-06, | |
| "loss": 0.376, | |
| "step": 118 | |
| }, | |
| { | |
| "Batch Mean": 0.5527479648590088, | |
| "accuracy": 0.84375, | |
| "epoch": 0.295, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.2975, | |
| "grad_norm": 14.145975112915039, | |
| "learning_rate": 2.218421052631579e-06, | |
| "loss": 0.3598, | |
| "step": 119 | |
| }, | |
| { | |
| "Batch Mean": 0.33617615699768066, | |
| "accuracy": 0.859375, | |
| "epoch": 0.2975, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 9.850839614868164, | |
| "learning_rate": 2.2105263157894738e-06, | |
| "loss": 0.3558, | |
| "step": 120 | |
| }, | |
| { | |
| "Batch Mean": 0.37594175338745117, | |
| "accuracy": 0.765625, | |
| "epoch": 0.3, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3025, | |
| "grad_norm": 10.884904861450195, | |
| "learning_rate": 2.2026315789473685e-06, | |
| "loss": 0.4847, | |
| "step": 121 | |
| }, | |
| { | |
| "Batch Mean": -0.30231380462646484, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.3025, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.305, | |
| "grad_norm": 8.063970565795898, | |
| "learning_rate": 2.1947368421052633e-06, | |
| "loss": 0.3881, | |
| "step": 122 | |
| }, | |
| { | |
| "Batch Mean": -0.4219226837158203, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.305, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3075, | |
| "grad_norm": 11.049520492553711, | |
| "learning_rate": 2.186842105263158e-06, | |
| "loss": 0.3564, | |
| "step": 123 | |
| }, | |
| { | |
| "Batch Mean": -0.015915870666503906, | |
| "accuracy": 0.796875, | |
| "epoch": 0.3075, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 7.677197456359863, | |
| "learning_rate": 2.1789473684210528e-06, | |
| "loss": 0.3923, | |
| "step": 124 | |
| }, | |
| { | |
| "Batch Mean": 0.25323057174682617, | |
| "accuracy": 0.859375, | |
| "epoch": 0.31, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 8.646540641784668, | |
| "learning_rate": 2.1710526315789475e-06, | |
| "loss": 0.4231, | |
| "step": 125 | |
| }, | |
| { | |
| "Batch Mean": -0.45605993270874023, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.3125, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.315, | |
| "grad_norm": 10.95660400390625, | |
| "learning_rate": 2.1631578947368423e-06, | |
| "loss": 0.3905, | |
| "step": 126 | |
| }, | |
| { | |
| "Batch Mean": -0.09001016616821289, | |
| "accuracy": 0.859375, | |
| "epoch": 0.315, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3175, | |
| "grad_norm": 6.532036304473877, | |
| "learning_rate": 2.155263157894737e-06, | |
| "loss": 0.3104, | |
| "step": 127 | |
| }, | |
| { | |
| "Batch Mean": 0.001552581787109375, | |
| "accuracy": 0.78125, | |
| "epoch": 0.3175, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 7.6803178787231445, | |
| "learning_rate": 2.1473684210526317e-06, | |
| "loss": 0.4176, | |
| "step": 128 | |
| }, | |
| { | |
| "Batch Mean": 0.24973249435424805, | |
| "accuracy": 0.84375, | |
| "epoch": 0.32, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.3225, | |
| "grad_norm": 7.414150714874268, | |
| "learning_rate": 2.1394736842105265e-06, | |
| "loss": 0.3664, | |
| "step": 129 | |
| }, | |
| { | |
| "Batch Mean": -0.17685949802398682, | |
| "accuracy": 0.859375, | |
| "epoch": 0.3225, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.325, | |
| "grad_norm": 8.062408447265625, | |
| "learning_rate": 2.1315789473684212e-06, | |
| "loss": 0.3671, | |
| "step": 130 | |
| }, | |
| { | |
| "Batch Mean": 0.3163696527481079, | |
| "accuracy": 0.8125, | |
| "epoch": 0.325, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3275, | |
| "grad_norm": 8.69417953491211, | |
| "learning_rate": 2.123684210526316e-06, | |
| "loss": 0.3946, | |
| "step": 131 | |
| }, | |
| { | |
| "Batch Mean": 0.13493728637695312, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.3275, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 7.916721343994141, | |
| "learning_rate": 2.1157894736842103e-06, | |
| "loss": 0.4373, | |
| "step": 132 | |
| }, | |
| { | |
| "Batch Mean": 0.032731056213378906, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.33, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.3325, | |
| "grad_norm": 6.909370422363281, | |
| "learning_rate": 2.107894736842105e-06, | |
| "loss": 0.3488, | |
| "step": 133 | |
| }, | |
| { | |
| "Batch Mean": -0.6435856819152832, | |
| "accuracy": 0.84375, | |
| "epoch": 0.3325, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.335, | |
| "grad_norm": 13.454378128051758, | |
| "learning_rate": 2.1e-06, | |
| "loss": 0.4012, | |
| "step": 134 | |
| }, | |
| { | |
| "Batch Mean": -0.04024988412857056, | |
| "accuracy": 0.8125, | |
| "epoch": 0.335, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.3375, | |
| "grad_norm": 6.9208502769470215, | |
| "learning_rate": 2.0921052631578945e-06, | |
| "loss": 0.4132, | |
| "step": 135 | |
| }, | |
| { | |
| "Batch Mean": 0.10650634765625, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.3375, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 7.637556552886963, | |
| "learning_rate": 2.0842105263157897e-06, | |
| "loss": 0.4497, | |
| "step": 136 | |
| }, | |
| { | |
| "Batch Mean": -0.2209153175354004, | |
| "accuracy": 0.7734375, | |
| "epoch": 0.34, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3425, | |
| "grad_norm": 8.982176780700684, | |
| "learning_rate": 2.0763157894736845e-06, | |
| "loss": 0.4867, | |
| "step": 137 | |
| }, | |
| { | |
| "Batch Mean": 0.0443209707736969, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.3425, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.345, | |
| "grad_norm": 6.714746475219727, | |
| "learning_rate": 2.068421052631579e-06, | |
| "loss": 0.3642, | |
| "step": 138 | |
| }, | |
| { | |
| "Batch Mean": 0.03779444098472595, | |
| "accuracy": 0.859375, | |
| "epoch": 0.345, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3475, | |
| "grad_norm": 6.019307613372803, | |
| "learning_rate": 2.060526315789474e-06, | |
| "loss": 0.3308, | |
| "step": 139 | |
| }, | |
| { | |
| "Batch Mean": 0.2002730369567871, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.3475, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 7.735702037811279, | |
| "learning_rate": 2.0526315789473687e-06, | |
| "loss": 0.4197, | |
| "step": 140 | |
| }, | |
| { | |
| "Batch Mean": 0.16213250160217285, | |
| "accuracy": 0.828125, | |
| "epoch": 0.35, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3525, | |
| "grad_norm": 7.075012683868408, | |
| "learning_rate": 2.0447368421052634e-06, | |
| "loss": 0.3772, | |
| "step": 141 | |
| }, | |
| { | |
| "Batch Mean": -0.05973696708679199, | |
| "accuracy": 0.859375, | |
| "epoch": 0.3525, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.355, | |
| "grad_norm": 6.793128967285156, | |
| "learning_rate": 2.0368421052631578e-06, | |
| "loss": 0.3782, | |
| "step": 142 | |
| }, | |
| { | |
| "Batch Mean": -0.2323307991027832, | |
| "accuracy": 0.84375, | |
| "epoch": 0.355, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.3575, | |
| "grad_norm": 8.474074363708496, | |
| "learning_rate": 2.0289473684210525e-06, | |
| "loss": 0.412, | |
| "step": 143 | |
| }, | |
| { | |
| "Batch Mean": -0.594693660736084, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.3575, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 11.406280517578125, | |
| "learning_rate": 2.0210526315789473e-06, | |
| "loss": 0.3999, | |
| "step": 144 | |
| }, | |
| { | |
| "Batch Mean": -0.34098196029663086, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.36, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.3625, | |
| "grad_norm": 8.726512908935547, | |
| "learning_rate": 2.013157894736842e-06, | |
| "loss": 0.4033, | |
| "step": 145 | |
| }, | |
| { | |
| "Batch Mean": 0.14231419563293457, | |
| "accuracy": 0.8359375, | |
| "epoch": 0.3625, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.365, | |
| "grad_norm": 6.767786979675293, | |
| "learning_rate": 2.0052631578947367e-06, | |
| "loss": 0.3359, | |
| "step": 146 | |
| }, | |
| { | |
| "Batch Mean": 0.4020230770111084, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.365, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.3675, | |
| "grad_norm": 9.113909721374512, | |
| "learning_rate": 1.9973684210526315e-06, | |
| "loss": 0.4163, | |
| "step": 147 | |
| }, | |
| { | |
| "Batch Mean": 0.46575236320495605, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.3675, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 10.250436782836914, | |
| "learning_rate": 1.9894736842105262e-06, | |
| "loss": 0.4773, | |
| "step": 148 | |
| }, | |
| { | |
| "Batch Mean": 0.1646571159362793, | |
| "accuracy": 0.8125, | |
| "epoch": 0.37, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.3725, | |
| "grad_norm": 8.450485229492188, | |
| "learning_rate": 1.9815789473684214e-06, | |
| "loss": 0.354, | |
| "step": 149 | |
| }, | |
| { | |
| "Batch Mean": 0.20849394798278809, | |
| "accuracy": 0.890625, | |
| "epoch": 0.3725, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 8.217352867126465, | |
| "learning_rate": 1.973684210526316e-06, | |
| "loss": 0.3627, | |
| "step": 150 | |
| }, | |
| { | |
| "Batch Mean": -0.42828369140625, | |
| "accuracy": 0.8125, | |
| "epoch": 0.375, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3775, | |
| "grad_norm": 12.038201332092285, | |
| "learning_rate": 1.965789473684211e-06, | |
| "loss": 0.3728, | |
| "step": 151 | |
| }, | |
| { | |
| "Batch Mean": -0.11544227600097656, | |
| "accuracy": 0.78125, | |
| "epoch": 0.3775, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 7.889610290527344, | |
| "learning_rate": 1.9578947368421052e-06, | |
| "loss": 0.3893, | |
| "step": 152 | |
| }, | |
| { | |
| "Batch Mean": -0.21321868896484375, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.38, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3825, | |
| "grad_norm": 8.342473030090332, | |
| "learning_rate": 1.95e-06, | |
| "loss": 0.4122, | |
| "step": 153 | |
| }, | |
| { | |
| "Batch Mean": -0.15835070610046387, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.3825, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.385, | |
| "grad_norm": 7.926384449005127, | |
| "learning_rate": 1.9421052631578947e-06, | |
| "loss": 0.3922, | |
| "step": 154 | |
| }, | |
| { | |
| "Batch Mean": 0.010342597961425781, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.385, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.3875, | |
| "grad_norm": 8.17468547821045, | |
| "learning_rate": 1.9342105263157895e-06, | |
| "loss": 0.4333, | |
| "step": 155 | |
| }, | |
| { | |
| "Batch Mean": 0.3719363212585449, | |
| "accuracy": 0.8046875, | |
| "epoch": 0.3875, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 10.360675811767578, | |
| "learning_rate": 1.926315789473684e-06, | |
| "loss": 0.4128, | |
| "step": 156 | |
| }, | |
| { | |
| "Batch Mean": 0.12261229753494263, | |
| "accuracy": 0.78125, | |
| "epoch": 0.39, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.3925, | |
| "grad_norm": 9.016860961914062, | |
| "learning_rate": 1.918421052631579e-06, | |
| "loss": 0.443, | |
| "step": 157 | |
| }, | |
| { | |
| "Batch Mean": -0.06574655324220657, | |
| "accuracy": 0.84375, | |
| "epoch": 0.3925, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.395, | |
| "grad_norm": 6.0845255851745605, | |
| "learning_rate": 1.9105263157894737e-06, | |
| "loss": 0.3329, | |
| "step": 158 | |
| }, | |
| { | |
| "Batch Mean": -0.33632707595825195, | |
| "accuracy": 0.796875, | |
| "epoch": 0.395, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.3975, | |
| "grad_norm": 9.574487686157227, | |
| "learning_rate": 1.9026315789473684e-06, | |
| "loss": 0.4283, | |
| "step": 159 | |
| }, | |
| { | |
| "Batch Mean": 0.016783952713012695, | |
| "accuracy": 0.84375, | |
| "epoch": 0.3975, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 6.5984787940979, | |
| "learning_rate": 1.8947368421052632e-06, | |
| "loss": 0.3412, | |
| "step": 160 | |
| }, | |
| { | |
| "Batch Mean": 0.2222914844751358, | |
| "accuracy": 0.84375, | |
| "epoch": 0.4, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4025, | |
| "grad_norm": 7.398411273956299, | |
| "learning_rate": 1.8868421052631577e-06, | |
| "loss": 0.4231, | |
| "step": 161 | |
| }, | |
| { | |
| "Batch Mean": 0.136377215385437, | |
| "accuracy": 0.84375, | |
| "epoch": 0.4025, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.405, | |
| "grad_norm": 8.897592544555664, | |
| "learning_rate": 1.8789473684210525e-06, | |
| "loss": 0.393, | |
| "step": 162 | |
| }, | |
| { | |
| "Batch Mean": 0.03430792689323425, | |
| "accuracy": 0.8125, | |
| "epoch": 0.405, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.4075, | |
| "grad_norm": 6.535599231719971, | |
| "learning_rate": 1.8710526315789476e-06, | |
| "loss": 0.3837, | |
| "step": 163 | |
| }, | |
| { | |
| "Batch Mean": -0.09270691871643066, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.4075, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 6.2713823318481445, | |
| "learning_rate": 1.8631578947368424e-06, | |
| "loss": 0.3364, | |
| "step": 164 | |
| }, | |
| { | |
| "Batch Mean": -0.07146286964416504, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.41, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.4125, | |
| "grad_norm": 6.161220073699951, | |
| "learning_rate": 1.855263157894737e-06, | |
| "loss": 0.3677, | |
| "step": 165 | |
| }, | |
| { | |
| "Batch Mean": -0.20211690664291382, | |
| "accuracy": 0.78125, | |
| "epoch": 0.4125, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.415, | |
| "grad_norm": 7.355227470397949, | |
| "learning_rate": 1.8473684210526317e-06, | |
| "loss": 0.4361, | |
| "step": 166 | |
| }, | |
| { | |
| "Batch Mean": -0.3163893222808838, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.415, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.4175, | |
| "grad_norm": 8.728869438171387, | |
| "learning_rate": 1.8394736842105264e-06, | |
| "loss": 0.3997, | |
| "step": 167 | |
| }, | |
| { | |
| "Batch Mean": 0.3005563020706177, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.4175, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 6.728272914886475, | |
| "learning_rate": 1.8315789473684211e-06, | |
| "loss": 0.329, | |
| "step": 168 | |
| }, | |
| { | |
| "Batch Mean": 0.1099938154220581, | |
| "accuracy": 0.828125, | |
| "epoch": 0.42, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.4225, | |
| "grad_norm": 6.236492156982422, | |
| "learning_rate": 1.8236842105263159e-06, | |
| "loss": 0.3884, | |
| "step": 169 | |
| }, | |
| { | |
| "Batch Mean": 0.3710876703262329, | |
| "accuracy": 0.796875, | |
| "epoch": 0.4225, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.425, | |
| "grad_norm": 8.478776931762695, | |
| "learning_rate": 1.8157894736842106e-06, | |
| "loss": 0.3932, | |
| "step": 170 | |
| }, | |
| { | |
| "Batch Mean": -0.22776031494140625, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.425, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4275, | |
| "grad_norm": 7.591424942016602, | |
| "learning_rate": 1.8078947368421052e-06, | |
| "loss": 0.3521, | |
| "step": 171 | |
| }, | |
| { | |
| "Batch Mean": -0.3130757212638855, | |
| "accuracy": 0.890625, | |
| "epoch": 0.4275, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 7.310946941375732, | |
| "learning_rate": 1.8e-06, | |
| "loss": 0.3295, | |
| "step": 172 | |
| }, | |
| { | |
| "Batch Mean": 0.1858811378479004, | |
| "accuracy": 0.890625, | |
| "epoch": 0.43, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.4325, | |
| "grad_norm": 8.169261932373047, | |
| "learning_rate": 1.7921052631578947e-06, | |
| "loss": 0.313, | |
| "step": 173 | |
| }, | |
| { | |
| "Batch Mean": 0.2934098243713379, | |
| "accuracy": 0.84375, | |
| "epoch": 0.4325, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.435, | |
| "grad_norm": 8.353775978088379, | |
| "learning_rate": 1.7842105263157894e-06, | |
| "loss": 0.3104, | |
| "step": 174 | |
| }, | |
| { | |
| "Batch Mean": 0.1525893211364746, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.435, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 7.484781265258789, | |
| "learning_rate": 1.7763157894736842e-06, | |
| "loss": 0.4333, | |
| "step": 175 | |
| }, | |
| { | |
| "Batch Mean": 0.12224054336547852, | |
| "accuracy": 0.84375, | |
| "epoch": 0.4375, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 7.87322473526001, | |
| "learning_rate": 1.768421052631579e-06, | |
| "loss": 0.3525, | |
| "step": 176 | |
| }, | |
| { | |
| "Batch Mean": -0.12131023406982422, | |
| "accuracy": 0.875, | |
| "epoch": 0.44, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.4425, | |
| "grad_norm": 6.532097339630127, | |
| "learning_rate": 1.7605263157894739e-06, | |
| "loss": 0.3028, | |
| "step": 177 | |
| }, | |
| { | |
| "Batch Mean": -0.17700982093811035, | |
| "accuracy": 0.78125, | |
| "epoch": 0.4425, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.445, | |
| "grad_norm": 10.696880340576172, | |
| "learning_rate": 1.7526315789473686e-06, | |
| "loss": 0.4192, | |
| "step": 178 | |
| }, | |
| { | |
| "Batch Mean": -0.20450687408447266, | |
| "accuracy": 0.859375, | |
| "epoch": 0.445, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.4475, | |
| "grad_norm": 8.799153327941895, | |
| "learning_rate": 1.7447368421052633e-06, | |
| "loss": 0.3349, | |
| "step": 179 | |
| }, | |
| { | |
| "Batch Mean": 0.114410400390625, | |
| "accuracy": 0.828125, | |
| "epoch": 0.4475, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 8.984070777893066, | |
| "learning_rate": 1.736842105263158e-06, | |
| "loss": 0.3446, | |
| "step": 180 | |
| }, | |
| { | |
| "Batch Mean": 0.1458113193511963, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.45, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4525, | |
| "grad_norm": 9.16761302947998, | |
| "learning_rate": 1.7289473684210526e-06, | |
| "loss": 0.346, | |
| "step": 181 | |
| }, | |
| { | |
| "Batch Mean": -0.05868828296661377, | |
| "accuracy": 0.90625, | |
| "epoch": 0.4525, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.455, | |
| "grad_norm": 6.830461025238037, | |
| "learning_rate": 1.7210526315789474e-06, | |
| "loss": 0.2781, | |
| "step": 182 | |
| }, | |
| { | |
| "Batch Mean": 0.0004514455795288086, | |
| "accuracy": 0.8515625, | |
| "epoch": 0.455, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.4575, | |
| "grad_norm": 8.418164253234863, | |
| "learning_rate": 1.7131578947368421e-06, | |
| "loss": 0.3541, | |
| "step": 183 | |
| }, | |
| { | |
| "Batch Mean": -0.24701285362243652, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.4575, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 8.39130687713623, | |
| "learning_rate": 1.7052631578947369e-06, | |
| "loss": 0.3704, | |
| "step": 184 | |
| }, | |
| { | |
| "Batch Mean": 0.25158822536468506, | |
| "accuracy": 0.84375, | |
| "epoch": 0.46, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.4625, | |
| "grad_norm": 8.080472946166992, | |
| "learning_rate": 1.6973684210526316e-06, | |
| "loss": 0.3565, | |
| "step": 185 | |
| }, | |
| { | |
| "Batch Mean": 0.044036865234375, | |
| "accuracy": 0.7578125, | |
| "epoch": 0.4625, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.465, | |
| "grad_norm": 10.760668754577637, | |
| "learning_rate": 1.6894736842105264e-06, | |
| "loss": 0.515, | |
| "step": 186 | |
| }, | |
| { | |
| "Batch Mean": 0.0032491683959960938, | |
| "accuracy": 0.859375, | |
| "epoch": 0.465, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.4675, | |
| "grad_norm": 7.858923435211182, | |
| "learning_rate": 1.6815789473684209e-06, | |
| "loss": 0.3053, | |
| "step": 187 | |
| }, | |
| { | |
| "Batch Mean": -0.0027008056640625, | |
| "accuracy": 0.859375, | |
| "epoch": 0.4675, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 7.517134189605713, | |
| "learning_rate": 1.6736842105263156e-06, | |
| "loss": 0.2864, | |
| "step": 188 | |
| }, | |
| { | |
| "Batch Mean": 0.25811076164245605, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.47, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.4725, | |
| "grad_norm": 7.516969680786133, | |
| "learning_rate": 1.6657894736842104e-06, | |
| "loss": 0.3299, | |
| "step": 189 | |
| }, | |
| { | |
| "Batch Mean": 0.024303913116455078, | |
| "accuracy": 0.796875, | |
| "epoch": 0.4725, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.475, | |
| "grad_norm": 9.072182655334473, | |
| "learning_rate": 1.6578947368421056e-06, | |
| "loss": 0.4424, | |
| "step": 190 | |
| }, | |
| { | |
| "Batch Mean": -0.38180357217788696, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.475, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4775, | |
| "grad_norm": 9.461527824401855, | |
| "learning_rate": 1.65e-06, | |
| "loss": 0.3751, | |
| "step": 191 | |
| }, | |
| { | |
| "Batch Mean": -0.594372034072876, | |
| "accuracy": 0.84375, | |
| "epoch": 0.4775, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 11.741211891174316, | |
| "learning_rate": 1.6421052631578948e-06, | |
| "loss": 0.3127, | |
| "step": 192 | |
| }, | |
| { | |
| "Batch Mean": -0.5924481153488159, | |
| "accuracy": 0.890625, | |
| "epoch": 0.48, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.4825, | |
| "grad_norm": 10.474485397338867, | |
| "learning_rate": 1.6342105263157896e-06, | |
| "loss": 0.276, | |
| "step": 193 | |
| }, | |
| { | |
| "Batch Mean": -0.16649462282657623, | |
| "accuracy": 0.8125, | |
| "epoch": 0.4825, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.485, | |
| "grad_norm": 8.504786491394043, | |
| "learning_rate": 1.6263157894736843e-06, | |
| "loss": 0.3619, | |
| "step": 194 | |
| }, | |
| { | |
| "Batch Mean": 0.15191316604614258, | |
| "accuracy": 0.8671875, | |
| "epoch": 0.485, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.4875, | |
| "grad_norm": 6.697569370269775, | |
| "learning_rate": 1.618421052631579e-06, | |
| "loss": 0.3237, | |
| "step": 195 | |
| }, | |
| { | |
| "Batch Mean": 0.5648140907287598, | |
| "accuracy": 0.828125, | |
| "epoch": 0.4875, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 11.56078815460205, | |
| "learning_rate": 1.6105263157894738e-06, | |
| "loss": 0.3372, | |
| "step": 196 | |
| }, | |
| { | |
| "Batch Mean": 0.6280609369277954, | |
| "accuracy": 0.8203125, | |
| "epoch": 0.49, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.4925, | |
| "grad_norm": 12.10026741027832, | |
| "learning_rate": 1.6026315789473683e-06, | |
| "loss": 0.376, | |
| "step": 197 | |
| }, | |
| { | |
| "Batch Mean": 0.46126890182495117, | |
| "accuracy": 0.796875, | |
| "epoch": 0.4925, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.495, | |
| "grad_norm": 9.432372093200684, | |
| "learning_rate": 1.594736842105263e-06, | |
| "loss": 0.3827, | |
| "step": 198 | |
| }, | |
| { | |
| "Batch Mean": 0.3517181873321533, | |
| "accuracy": 0.796875, | |
| "epoch": 0.495, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.4975, | |
| "grad_norm": 9.432829856872559, | |
| "learning_rate": 1.5868421052631578e-06, | |
| "loss": 0.3766, | |
| "step": 199 | |
| }, | |
| { | |
| "Batch Mean": -0.18610143661499023, | |
| "accuracy": 0.7890625, | |
| "epoch": 0.4975, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 8.5609130859375, | |
| "learning_rate": 1.5789473684210526e-06, | |
| "loss": 0.4419, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |