| { |
| "best_metric": 0.7384898710865562, |
| "best_model_checkpoint": "musical_instrument_detection/checkpoint-1360", |
| "epoch": 15.0, |
| "global_step": 2040, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "learning_rate": 2.2058823529411767e-06, |
| "loss": 1.3866, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 4.65686274509804e-06, |
| "loss": 1.383, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 7.107843137254902e-06, |
| "loss": 1.3851, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 9.31372549019608e-06, |
| "loss": 1.3729, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 1.1764705882352942e-05, |
| "loss": 1.3689, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 1.4215686274509804e-05, |
| "loss": 1.3561, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 1.3463, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 1.9117647058823528e-05, |
| "loss": 1.3176, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 2.1568627450980395e-05, |
| "loss": 1.3063, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 2.3774509803921568e-05, |
| "loss": 1.2662, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 2.6225490196078435e-05, |
| "loss": 1.2082, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 2.8676470588235295e-05, |
| "loss": 1.205, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 3.112745098039216e-05, |
| "loss": 1.1802, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5322283609576427, |
| "eval_loss": 1.038236141204834, |
| "eval_runtime": 5.4332, |
| "eval_samples_per_second": 99.942, |
| "eval_steps_per_second": 6.258, |
| "step": 136 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 3.357843137254902e-05, |
| "loss": 1.1219, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 3.5784313725490195e-05, |
| "loss": 1.0772, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 3.8235294117647055e-05, |
| "loss": 1.016, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 4.068627450980392e-05, |
| "loss": 0.9292, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 4.313725490196079e-05, |
| "loss": 0.8552, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 4.558823529411765e-05, |
| "loss": 0.7906, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 4.803921568627452e-05, |
| "loss": 0.7561, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 4.994553376906319e-05, |
| "loss": 0.7469, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 4.967320261437909e-05, |
| "loss": 0.7354, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 4.940087145969499e-05, |
| "loss": 0.7026, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 4.91285403050109e-05, |
| "loss": 0.6496, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 4.88562091503268e-05, |
| "loss": 0.5919, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 4.85838779956427e-05, |
| "loss": 0.6196, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 4.8338779956427017e-05, |
| "loss": 0.5676, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7090239410681399, |
| "eval_loss": 0.5477131009101868, |
| "eval_runtime": 5.4026, |
| "eval_samples_per_second": 100.508, |
| "eval_steps_per_second": 6.293, |
| "step": 272 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 4.809368191721133e-05, |
| "loss": 0.5971, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 4.7821350762527234e-05, |
| "loss": 0.6122, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 4.7549019607843135e-05, |
| "loss": 0.4923, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 4.7276688453159044e-05, |
| "loss": 0.528, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 4.700435729847495e-05, |
| "loss": 0.5466, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 4.673202614379085e-05, |
| "loss": 0.5894, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 4.6459694989106755e-05, |
| "loss": 0.5512, |
| "step": 340 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 4.6187363834422656e-05, |
| "loss": 0.4994, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 4.5915032679738564e-05, |
| "loss": 0.5158, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 4.564270152505447e-05, |
| "loss": 0.5905, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 4.5370370370370374e-05, |
| "loss": 0.5186, |
| "step": 380 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 4.5098039215686275e-05, |
| "loss": 0.729, |
| "step": 390 |
| }, |
| { |
| "epoch": 2.94, |
| "learning_rate": 4.482570806100218e-05, |
| "loss": 0.5502, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7255985267034991, |
| "eval_loss": 0.5312222242355347, |
| "eval_runtime": 5.3808, |
| "eval_samples_per_second": 100.915, |
| "eval_steps_per_second": 6.319, |
| "step": 408 |
| }, |
| { |
| "epoch": 3.01, |
| "learning_rate": 4.4553376906318085e-05, |
| "loss": 0.5265, |
| "step": 410 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 4.4281045751633986e-05, |
| "loss": 0.5098, |
| "step": 420 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 4.400871459694989e-05, |
| "loss": 0.5669, |
| "step": 430 |
| }, |
| { |
| "epoch": 3.24, |
| "learning_rate": 4.37363834422658e-05, |
| "loss": 0.474, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.31, |
| "learning_rate": 4.3464052287581704e-05, |
| "loss": 0.4687, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 4.3191721132897605e-05, |
| "loss": 0.5691, |
| "step": 460 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 4.291938997821351e-05, |
| "loss": 0.7491, |
| "step": 470 |
| }, |
| { |
| "epoch": 3.53, |
| "learning_rate": 4.2647058823529415e-05, |
| "loss": 0.4712, |
| "step": 480 |
| }, |
| { |
| "epoch": 3.6, |
| "learning_rate": 4.2374727668845316e-05, |
| "loss": 0.489, |
| "step": 490 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 4.2102396514161224e-05, |
| "loss": 0.5199, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.75, |
| "learning_rate": 4.1830065359477126e-05, |
| "loss": 0.6991, |
| "step": 510 |
| }, |
| { |
| "epoch": 3.82, |
| "learning_rate": 4.1557734204793034e-05, |
| "loss": 0.5455, |
| "step": 520 |
| }, |
| { |
| "epoch": 3.9, |
| "learning_rate": 4.1285403050108935e-05, |
| "loss": 0.4854, |
| "step": 530 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 4.101307189542484e-05, |
| "loss": 0.5191, |
| "step": 540 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7182320441988951, |
| "eval_loss": 0.49646708369255066, |
| "eval_runtime": 5.3289, |
| "eval_samples_per_second": 101.896, |
| "eval_steps_per_second": 6.38, |
| "step": 544 |
| }, |
| { |
| "epoch": 4.04, |
| "learning_rate": 4.074074074074074e-05, |
| "loss": 0.4407, |
| "step": 550 |
| }, |
| { |
| "epoch": 4.12, |
| "learning_rate": 4.0468409586056646e-05, |
| "loss": 0.6965, |
| "step": 560 |
| }, |
| { |
| "epoch": 4.19, |
| "learning_rate": 4.0196078431372555e-05, |
| "loss": 0.6421, |
| "step": 570 |
| }, |
| { |
| "epoch": 4.26, |
| "learning_rate": 3.9923747276688456e-05, |
| "loss": 0.4867, |
| "step": 580 |
| }, |
| { |
| "epoch": 4.34, |
| "learning_rate": 3.965141612200436e-05, |
| "loss": 0.4978, |
| "step": 590 |
| }, |
| { |
| "epoch": 4.41, |
| "learning_rate": 3.9379084967320266e-05, |
| "loss": 0.467, |
| "step": 600 |
| }, |
| { |
| "epoch": 4.49, |
| "learning_rate": 3.910675381263617e-05, |
| "loss": 0.4662, |
| "step": 610 |
| }, |
| { |
| "epoch": 4.56, |
| "learning_rate": 3.8834422657952075e-05, |
| "loss": 0.4233, |
| "step": 620 |
| }, |
| { |
| "epoch": 4.63, |
| "learning_rate": 3.8562091503267977e-05, |
| "loss": 0.4864, |
| "step": 630 |
| }, |
| { |
| "epoch": 4.71, |
| "learning_rate": 3.828976034858388e-05, |
| "loss": 0.5433, |
| "step": 640 |
| }, |
| { |
| "epoch": 4.78, |
| "learning_rate": 3.8017429193899786e-05, |
| "loss": 0.4851, |
| "step": 650 |
| }, |
| { |
| "epoch": 4.85, |
| "learning_rate": 3.774509803921569e-05, |
| "loss": 0.4162, |
| "step": 660 |
| }, |
| { |
| "epoch": 4.93, |
| "learning_rate": 3.747276688453159e-05, |
| "loss": 0.4304, |
| "step": 670 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 3.72004357298475e-05, |
| "loss": 0.4473, |
| "step": 680 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7292817679558011, |
| "eval_loss": 0.437788724899292, |
| "eval_runtime": 5.426, |
| "eval_samples_per_second": 100.073, |
| "eval_steps_per_second": 6.266, |
| "step": 680 |
| }, |
| { |
| "epoch": 5.07, |
| "learning_rate": 3.6928104575163405e-05, |
| "loss": 0.4891, |
| "step": 690 |
| }, |
| { |
| "epoch": 5.15, |
| "learning_rate": 3.665577342047931e-05, |
| "loss": 0.5293, |
| "step": 700 |
| }, |
| { |
| "epoch": 5.22, |
| "learning_rate": 3.638344226579521e-05, |
| "loss": 0.4155, |
| "step": 710 |
| }, |
| { |
| "epoch": 5.29, |
| "learning_rate": 3.611111111111111e-05, |
| "loss": 0.4949, |
| "step": 720 |
| }, |
| { |
| "epoch": 5.37, |
| "learning_rate": 3.583877995642702e-05, |
| "loss": 0.4764, |
| "step": 730 |
| }, |
| { |
| "epoch": 5.44, |
| "learning_rate": 3.556644880174292e-05, |
| "loss": 0.4032, |
| "step": 740 |
| }, |
| { |
| "epoch": 5.51, |
| "learning_rate": 3.529411764705883e-05, |
| "loss": 0.4569, |
| "step": 750 |
| }, |
| { |
| "epoch": 5.59, |
| "learning_rate": 3.502178649237473e-05, |
| "loss": 0.4646, |
| "step": 760 |
| }, |
| { |
| "epoch": 5.66, |
| "learning_rate": 3.474945533769064e-05, |
| "loss": 0.4825, |
| "step": 770 |
| }, |
| { |
| "epoch": 5.74, |
| "learning_rate": 3.447712418300654e-05, |
| "loss": 0.3938, |
| "step": 780 |
| }, |
| { |
| "epoch": 5.81, |
| "learning_rate": 3.420479302832244e-05, |
| "loss": 0.4213, |
| "step": 790 |
| }, |
| { |
| "epoch": 5.88, |
| "learning_rate": 3.393246187363834e-05, |
| "loss": 0.4944, |
| "step": 800 |
| }, |
| { |
| "epoch": 5.96, |
| "learning_rate": 3.366013071895425e-05, |
| "loss": 0.466, |
| "step": 810 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.714548802946593, |
| "eval_loss": 0.4857429563999176, |
| "eval_runtime": 5.4083, |
| "eval_samples_per_second": 100.401, |
| "eval_steps_per_second": 6.287, |
| "step": 816 |
| }, |
| { |
| "epoch": 6.03, |
| "learning_rate": 3.341503267973856e-05, |
| "loss": 0.4864, |
| "step": 820 |
| }, |
| { |
| "epoch": 6.1, |
| "learning_rate": 3.314270152505447e-05, |
| "loss": 0.44, |
| "step": 830 |
| }, |
| { |
| "epoch": 6.18, |
| "learning_rate": 3.2870370370370375e-05, |
| "loss": 0.3961, |
| "step": 840 |
| }, |
| { |
| "epoch": 6.25, |
| "learning_rate": 3.2598039215686276e-05, |
| "loss": 0.4105, |
| "step": 850 |
| }, |
| { |
| "epoch": 6.32, |
| "learning_rate": 3.232570806100218e-05, |
| "loss": 0.5326, |
| "step": 860 |
| }, |
| { |
| "epoch": 6.4, |
| "learning_rate": 3.2053376906318086e-05, |
| "loss": 0.4599, |
| "step": 870 |
| }, |
| { |
| "epoch": 6.47, |
| "learning_rate": 3.178104575163399e-05, |
| "loss": 0.4831, |
| "step": 880 |
| }, |
| { |
| "epoch": 6.54, |
| "learning_rate": 3.150871459694989e-05, |
| "loss": 0.4039, |
| "step": 890 |
| }, |
| { |
| "epoch": 6.62, |
| "learning_rate": 3.12363834422658e-05, |
| "loss": 0.3581, |
| "step": 900 |
| }, |
| { |
| "epoch": 6.69, |
| "learning_rate": 3.0964052287581705e-05, |
| "loss": 0.4457, |
| "step": 910 |
| }, |
| { |
| "epoch": 6.76, |
| "learning_rate": 3.0691721132897606e-05, |
| "loss": 0.4416, |
| "step": 920 |
| }, |
| { |
| "epoch": 6.84, |
| "learning_rate": 3.0419389978213508e-05, |
| "loss": 0.4405, |
| "step": 930 |
| }, |
| { |
| "epoch": 6.91, |
| "learning_rate": 3.0147058823529413e-05, |
| "loss": 0.4472, |
| "step": 940 |
| }, |
| { |
| "epoch": 6.99, |
| "learning_rate": 2.9874727668845314e-05, |
| "loss": 0.418, |
| "step": 950 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.7348066298342542, |
| "eval_loss": 0.4276367425918579, |
| "eval_runtime": 5.4265, |
| "eval_samples_per_second": 100.065, |
| "eval_steps_per_second": 6.266, |
| "step": 952 |
| }, |
| { |
| "epoch": 7.06, |
| "learning_rate": 2.9602396514161222e-05, |
| "loss": 0.3682, |
| "step": 960 |
| }, |
| { |
| "epoch": 7.13, |
| "learning_rate": 2.9330065359477127e-05, |
| "loss": 0.4173, |
| "step": 970 |
| }, |
| { |
| "epoch": 7.21, |
| "learning_rate": 2.905773420479303e-05, |
| "loss": 0.4664, |
| "step": 980 |
| }, |
| { |
| "epoch": 7.28, |
| "learning_rate": 2.8785403050108933e-05, |
| "loss": 0.4377, |
| "step": 990 |
| }, |
| { |
| "epoch": 7.35, |
| "learning_rate": 2.8513071895424838e-05, |
| "loss": 0.4195, |
| "step": 1000 |
| }, |
| { |
| "epoch": 7.43, |
| "learning_rate": 2.824074074074074e-05, |
| "loss": 0.4867, |
| "step": 1010 |
| }, |
| { |
| "epoch": 7.5, |
| "learning_rate": 2.7968409586056647e-05, |
| "loss": 0.3803, |
| "step": 1020 |
| }, |
| { |
| "epoch": 7.57, |
| "learning_rate": 2.7696078431372552e-05, |
| "loss": 0.4414, |
| "step": 1030 |
| }, |
| { |
| "epoch": 7.65, |
| "learning_rate": 2.7423747276688454e-05, |
| "loss": 0.4085, |
| "step": 1040 |
| }, |
| { |
| "epoch": 7.72, |
| "learning_rate": 2.715141612200436e-05, |
| "loss": 0.4118, |
| "step": 1050 |
| }, |
| { |
| "epoch": 7.79, |
| "learning_rate": 2.6879084967320263e-05, |
| "loss": 0.4142, |
| "step": 1060 |
| }, |
| { |
| "epoch": 7.87, |
| "learning_rate": 2.6606753812636165e-05, |
| "loss": 0.5046, |
| "step": 1070 |
| }, |
| { |
| "epoch": 7.94, |
| "learning_rate": 2.6334422657952073e-05, |
| "loss": 0.4517, |
| "step": 1080 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.7329650092081031, |
| "eval_loss": 0.41673922538757324, |
| "eval_runtime": 5.4273, |
| "eval_samples_per_second": 100.05, |
| "eval_steps_per_second": 6.265, |
| "step": 1088 |
| }, |
| { |
| "epoch": 8.01, |
| "learning_rate": 2.6062091503267978e-05, |
| "loss": 0.4462, |
| "step": 1090 |
| }, |
| { |
| "epoch": 8.09, |
| "learning_rate": 2.578976034858388e-05, |
| "loss": 0.4234, |
| "step": 1100 |
| }, |
| { |
| "epoch": 8.16, |
| "learning_rate": 2.5517429193899784e-05, |
| "loss": 0.346, |
| "step": 1110 |
| }, |
| { |
| "epoch": 8.24, |
| "learning_rate": 2.5245098039215685e-05, |
| "loss": 0.409, |
| "step": 1120 |
| }, |
| { |
| "epoch": 8.31, |
| "learning_rate": 2.4972766884531593e-05, |
| "loss": 0.3963, |
| "step": 1130 |
| }, |
| { |
| "epoch": 8.38, |
| "learning_rate": 2.4700435729847495e-05, |
| "loss": 0.3899, |
| "step": 1140 |
| }, |
| { |
| "epoch": 8.46, |
| "learning_rate": 2.44281045751634e-05, |
| "loss": 0.4712, |
| "step": 1150 |
| }, |
| { |
| "epoch": 8.53, |
| "learning_rate": 2.4155773420479304e-05, |
| "loss": 0.423, |
| "step": 1160 |
| }, |
| { |
| "epoch": 8.6, |
| "learning_rate": 2.388344226579521e-05, |
| "loss": 0.4148, |
| "step": 1170 |
| }, |
| { |
| "epoch": 8.68, |
| "learning_rate": 2.361111111111111e-05, |
| "loss": 0.3559, |
| "step": 1180 |
| }, |
| { |
| "epoch": 8.75, |
| "learning_rate": 2.333877995642702e-05, |
| "loss": 0.4495, |
| "step": 1190 |
| }, |
| { |
| "epoch": 8.82, |
| "learning_rate": 2.306644880174292e-05, |
| "loss": 0.4947, |
| "step": 1200 |
| }, |
| { |
| "epoch": 8.9, |
| "learning_rate": 2.2794117647058825e-05, |
| "loss": 0.4365, |
| "step": 1210 |
| }, |
| { |
| "epoch": 8.97, |
| "learning_rate": 2.2521786492374726e-05, |
| "loss": 0.374, |
| "step": 1220 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.7329650092081031, |
| "eval_loss": 0.4256838262081146, |
| "eval_runtime": 5.3475, |
| "eval_samples_per_second": 101.543, |
| "eval_steps_per_second": 6.358, |
| "step": 1224 |
| }, |
| { |
| "epoch": 9.04, |
| "learning_rate": 2.2249455337690635e-05, |
| "loss": 0.5156, |
| "step": 1230 |
| }, |
| { |
| "epoch": 9.12, |
| "learning_rate": 2.1977124183006536e-05, |
| "loss": 0.4526, |
| "step": 1240 |
| }, |
| { |
| "epoch": 9.19, |
| "learning_rate": 2.170479302832244e-05, |
| "loss": 0.3817, |
| "step": 1250 |
| }, |
| { |
| "epoch": 9.26, |
| "learning_rate": 2.1432461873638345e-05, |
| "loss": 0.4305, |
| "step": 1260 |
| }, |
| { |
| "epoch": 9.34, |
| "learning_rate": 2.116013071895425e-05, |
| "loss": 0.3858, |
| "step": 1270 |
| }, |
| { |
| "epoch": 9.41, |
| "learning_rate": 2.088779956427015e-05, |
| "loss": 0.4399, |
| "step": 1280 |
| }, |
| { |
| "epoch": 9.49, |
| "learning_rate": 2.061546840958606e-05, |
| "loss": 0.4223, |
| "step": 1290 |
| }, |
| { |
| "epoch": 9.56, |
| "learning_rate": 2.034313725490196e-05, |
| "loss": 0.4345, |
| "step": 1300 |
| }, |
| { |
| "epoch": 9.63, |
| "learning_rate": 2.0070806100217866e-05, |
| "loss": 0.4272, |
| "step": 1310 |
| }, |
| { |
| "epoch": 9.71, |
| "learning_rate": 1.979847494553377e-05, |
| "loss": 0.4486, |
| "step": 1320 |
| }, |
| { |
| "epoch": 9.78, |
| "learning_rate": 1.9526143790849676e-05, |
| "loss": 0.3847, |
| "step": 1330 |
| }, |
| { |
| "epoch": 9.85, |
| "learning_rate": 1.9253812636165577e-05, |
| "loss": 0.383, |
| "step": 1340 |
| }, |
| { |
| "epoch": 9.93, |
| "learning_rate": 1.8981481481481482e-05, |
| "loss": 0.3679, |
| "step": 1350 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 1.8709150326797387e-05, |
| "loss": 0.3924, |
| "step": 1360 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.7384898710865562, |
| "eval_loss": 0.4118790924549103, |
| "eval_runtime": 5.3939, |
| "eval_samples_per_second": 100.669, |
| "eval_steps_per_second": 6.303, |
| "step": 1360 |
| }, |
| { |
| "epoch": 10.07, |
| "learning_rate": 1.843681917211329e-05, |
| "loss": 0.386, |
| "step": 1370 |
| }, |
| { |
| "epoch": 10.15, |
| "learning_rate": 1.8164488017429196e-05, |
| "loss": 0.4353, |
| "step": 1380 |
| }, |
| { |
| "epoch": 10.22, |
| "learning_rate": 1.7892156862745098e-05, |
| "loss": 0.39, |
| "step": 1390 |
| }, |
| { |
| "epoch": 10.29, |
| "learning_rate": 1.7619825708061002e-05, |
| "loss": 0.3688, |
| "step": 1400 |
| }, |
| { |
| "epoch": 10.37, |
| "learning_rate": 1.7347494553376907e-05, |
| "loss": 0.4285, |
| "step": 1410 |
| }, |
| { |
| "epoch": 10.44, |
| "learning_rate": 1.7075163398692812e-05, |
| "loss": 0.5032, |
| "step": 1420 |
| }, |
| { |
| "epoch": 10.51, |
| "learning_rate": 1.6802832244008713e-05, |
| "loss": 0.4304, |
| "step": 1430 |
| }, |
| { |
| "epoch": 10.59, |
| "learning_rate": 1.6530501089324618e-05, |
| "loss": 0.3505, |
| "step": 1440 |
| }, |
| { |
| "epoch": 10.66, |
| "learning_rate": 1.6258169934640523e-05, |
| "loss": 0.4244, |
| "step": 1450 |
| }, |
| { |
| "epoch": 10.74, |
| "learning_rate": 1.5985838779956428e-05, |
| "loss": 0.4131, |
| "step": 1460 |
| }, |
| { |
| "epoch": 10.81, |
| "learning_rate": 1.571350762527233e-05, |
| "loss": 0.4014, |
| "step": 1470 |
| }, |
| { |
| "epoch": 10.88, |
| "learning_rate": 1.5441176470588237e-05, |
| "loss": 0.3943, |
| "step": 1480 |
| }, |
| { |
| "epoch": 10.96, |
| "learning_rate": 1.516884531590414e-05, |
| "loss": 0.4171, |
| "step": 1490 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.7348066298342542, |
| "eval_loss": 0.41081544756889343, |
| "eval_runtime": 5.4861, |
| "eval_samples_per_second": 98.977, |
| "eval_steps_per_second": 6.197, |
| "step": 1496 |
| }, |
| { |
| "epoch": 11.03, |
| "learning_rate": 1.4896514161220044e-05, |
| "loss": 0.4396, |
| "step": 1500 |
| }, |
| { |
| "epoch": 11.1, |
| "learning_rate": 1.462418300653595e-05, |
| "loss": 0.3521, |
| "step": 1510 |
| }, |
| { |
| "epoch": 11.18, |
| "learning_rate": 1.4351851851851853e-05, |
| "loss": 0.4112, |
| "step": 1520 |
| }, |
| { |
| "epoch": 11.25, |
| "learning_rate": 1.4079520697167756e-05, |
| "loss": 0.4001, |
| "step": 1530 |
| }, |
| { |
| "epoch": 11.32, |
| "learning_rate": 1.3807189542483661e-05, |
| "loss": 0.3997, |
| "step": 1540 |
| }, |
| { |
| "epoch": 11.4, |
| "learning_rate": 1.3534858387799566e-05, |
| "loss": 0.4178, |
| "step": 1550 |
| }, |
| { |
| "epoch": 11.47, |
| "learning_rate": 1.3262527233115469e-05, |
| "loss": 0.4486, |
| "step": 1560 |
| }, |
| { |
| "epoch": 11.54, |
| "learning_rate": 1.2990196078431374e-05, |
| "loss": 0.4236, |
| "step": 1570 |
| }, |
| { |
| "epoch": 11.62, |
| "learning_rate": 1.2717864923747277e-05, |
| "loss": 0.4001, |
| "step": 1580 |
| }, |
| { |
| "epoch": 11.69, |
| "learning_rate": 1.2445533769063182e-05, |
| "loss": 0.4082, |
| "step": 1590 |
| }, |
| { |
| "epoch": 11.76, |
| "learning_rate": 1.2173202614379085e-05, |
| "loss": 0.3682, |
| "step": 1600 |
| }, |
| { |
| "epoch": 11.84, |
| "learning_rate": 1.190087145969499e-05, |
| "loss": 0.4419, |
| "step": 1610 |
| }, |
| { |
| "epoch": 11.91, |
| "learning_rate": 1.1628540305010893e-05, |
| "loss": 0.4069, |
| "step": 1620 |
| }, |
| { |
| "epoch": 11.99, |
| "learning_rate": 1.1356209150326797e-05, |
| "loss": 0.347, |
| "step": 1630 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.7366482504604052, |
| "eval_loss": 0.40892112255096436, |
| "eval_runtime": 5.4241, |
| "eval_samples_per_second": 100.109, |
| "eval_steps_per_second": 6.268, |
| "step": 1632 |
| }, |
| { |
| "epoch": 12.06, |
| "learning_rate": 1.1083877995642702e-05, |
| "loss": 0.4121, |
| "step": 1640 |
| }, |
| { |
| "epoch": 12.13, |
| "learning_rate": 1.0811546840958605e-05, |
| "loss": 0.3777, |
| "step": 1650 |
| }, |
| { |
| "epoch": 12.21, |
| "learning_rate": 1.053921568627451e-05, |
| "loss": 0.4355, |
| "step": 1660 |
| }, |
| { |
| "epoch": 12.28, |
| "learning_rate": 1.0266884531590415e-05, |
| "loss": 0.4497, |
| "step": 1670 |
| }, |
| { |
| "epoch": 12.35, |
| "learning_rate": 9.994553376906318e-06, |
| "loss": 0.364, |
| "step": 1680 |
| }, |
| { |
| "epoch": 12.43, |
| "learning_rate": 9.722222222222223e-06, |
| "loss": 0.4122, |
| "step": 1690 |
| }, |
| { |
| "epoch": 12.5, |
| "learning_rate": 9.449891067538127e-06, |
| "loss": 0.4069, |
| "step": 1700 |
| }, |
| { |
| "epoch": 12.57, |
| "learning_rate": 9.17755991285403e-06, |
| "loss": 0.4013, |
| "step": 1710 |
| }, |
| { |
| "epoch": 12.65, |
| "learning_rate": 8.905228758169935e-06, |
| "loss": 0.4243, |
| "step": 1720 |
| }, |
| { |
| "epoch": 12.72, |
| "learning_rate": 8.632897603485838e-06, |
| "loss": 0.4243, |
| "step": 1730 |
| }, |
| { |
| "epoch": 12.79, |
| "learning_rate": 8.360566448801743e-06, |
| "loss": 0.3465, |
| "step": 1740 |
| }, |
| { |
| "epoch": 12.87, |
| "learning_rate": 8.088235294117648e-06, |
| "loss": 0.4257, |
| "step": 1750 |
| }, |
| { |
| "epoch": 12.94, |
| "learning_rate": 7.815904139433551e-06, |
| "loss": 0.3374, |
| "step": 1760 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.7366482504604052, |
| "eval_loss": 0.40931233763694763, |
| "eval_runtime": 5.3554, |
| "eval_samples_per_second": 101.393, |
| "eval_steps_per_second": 6.349, |
| "step": 1768 |
| }, |
| { |
| "epoch": 13.01, |
| "learning_rate": 7.543572984749456e-06, |
| "loss": 0.4485, |
| "step": 1770 |
| }, |
| { |
| "epoch": 13.09, |
| "learning_rate": 7.271241830065361e-06, |
| "loss": 0.4297, |
| "step": 1780 |
| }, |
| { |
| "epoch": 13.16, |
| "learning_rate": 6.998910675381264e-06, |
| "loss": 0.4388, |
| "step": 1790 |
| }, |
| { |
| "epoch": 13.24, |
| "learning_rate": 6.726579520697169e-06, |
| "loss": 0.4089, |
| "step": 1800 |
| }, |
| { |
| "epoch": 13.31, |
| "learning_rate": 6.4542483660130726e-06, |
| "loss": 0.4116, |
| "step": 1810 |
| }, |
| { |
| "epoch": 13.38, |
| "learning_rate": 6.1819172113289765e-06, |
| "loss": 0.4153, |
| "step": 1820 |
| }, |
| { |
| "epoch": 13.46, |
| "learning_rate": 5.9095860566448804e-06, |
| "loss": 0.3869, |
| "step": 1830 |
| }, |
| { |
| "epoch": 13.53, |
| "learning_rate": 5.637254901960784e-06, |
| "loss": 0.435, |
| "step": 1840 |
| }, |
| { |
| "epoch": 13.6, |
| "learning_rate": 5.364923747276688e-06, |
| "loss": 0.4082, |
| "step": 1850 |
| }, |
| { |
| "epoch": 13.68, |
| "learning_rate": 5.092592592592592e-06, |
| "loss": 0.3634, |
| "step": 1860 |
| }, |
| { |
| "epoch": 13.75, |
| "learning_rate": 4.820261437908497e-06, |
| "loss": 0.3917, |
| "step": 1870 |
| }, |
| { |
| "epoch": 13.82, |
| "learning_rate": 4.547930283224401e-06, |
| "loss": 0.4081, |
| "step": 1880 |
| }, |
| { |
| "epoch": 13.9, |
| "learning_rate": 4.275599128540305e-06, |
| "loss": 0.3683, |
| "step": 1890 |
| }, |
| { |
| "epoch": 13.97, |
| "learning_rate": 4.003267973856209e-06, |
| "loss": 0.4027, |
| "step": 1900 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.7366482504604052, |
| "eval_loss": 0.4110395312309265, |
| "eval_runtime": 5.4058, |
| "eval_samples_per_second": 100.448, |
| "eval_steps_per_second": 6.29, |
| "step": 1904 |
| }, |
| { |
| "epoch": 14.04, |
| "learning_rate": 3.7309368191721137e-06, |
| "loss": 0.4451, |
| "step": 1910 |
| }, |
| { |
| "epoch": 14.12, |
| "learning_rate": 3.4586056644880176e-06, |
| "loss": 0.4858, |
| "step": 1920 |
| }, |
| { |
| "epoch": 14.19, |
| "learning_rate": 3.1862745098039216e-06, |
| "loss": 0.3586, |
| "step": 1930 |
| }, |
| { |
| "epoch": 14.26, |
| "learning_rate": 2.913943355119826e-06, |
| "loss": 0.43, |
| "step": 1940 |
| }, |
| { |
| "epoch": 14.34, |
| "learning_rate": 2.64161220043573e-06, |
| "loss": 0.3976, |
| "step": 1950 |
| }, |
| { |
| "epoch": 14.41, |
| "learning_rate": 2.369281045751634e-06, |
| "loss": 0.3505, |
| "step": 1960 |
| }, |
| { |
| "epoch": 14.49, |
| "learning_rate": 2.096949891067538e-06, |
| "loss": 0.3981, |
| "step": 1970 |
| }, |
| { |
| "epoch": 14.56, |
| "learning_rate": 1.8246187363834421e-06, |
| "loss": 0.4096, |
| "step": 1980 |
| }, |
| { |
| "epoch": 14.63, |
| "learning_rate": 1.5522875816993465e-06, |
| "loss": 0.447, |
| "step": 1990 |
| }, |
| { |
| "epoch": 14.71, |
| "learning_rate": 1.2799564270152507e-06, |
| "loss": 0.3894, |
| "step": 2000 |
| }, |
| { |
| "epoch": 14.78, |
| "learning_rate": 1.0076252723311548e-06, |
| "loss": 0.3806, |
| "step": 2010 |
| }, |
| { |
| "epoch": 14.85, |
| "learning_rate": 7.352941176470589e-07, |
| "loss": 0.3877, |
| "step": 2020 |
| }, |
| { |
| "epoch": 14.93, |
| "learning_rate": 4.6296296296296297e-07, |
| "loss": 0.3693, |
| "step": 2030 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 1.9063180827886712e-07, |
| "loss": 0.2984, |
| "step": 2040 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.7366482504604052, |
| "eval_loss": 0.4104956090450287, |
| "eval_runtime": 5.3886, |
| "eval_samples_per_second": 100.768, |
| "eval_steps_per_second": 6.31, |
| "step": 2040 |
| } |
| ], |
| "max_steps": 2040, |
| "num_train_epochs": 15, |
| "total_flos": 9.8605146097728e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
