| { | |
| "best_metric": 0.8297674418604651, | |
| "best_model_checkpoint": "resnet-18-finetuned-resnet-18-1/checkpoint-450", | |
| "epoch": 49.95238095238095, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1e-05, | |
| "loss": 5.5547, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.004186046511627907, | |
| "eval_loss": 5.4745025634765625, | |
| "eval_runtime": 6.1733, | |
| "eval_samples_per_second": 348.276, | |
| "eval_steps_per_second": 0.81, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2e-05, | |
| "loss": 5.668, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_accuracy": 0.019069767441860466, | |
| "eval_loss": 5.200634479522705, | |
| "eval_runtime": 5.9989, | |
| "eval_samples_per_second": 358.401, | |
| "eval_steps_per_second": 0.833, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3e-05, | |
| "loss": 5.3055, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_accuracy": 0.09023255813953489, | |
| "eval_loss": 4.731231212615967, | |
| "eval_runtime": 5.9716, | |
| "eval_samples_per_second": 360.039, | |
| "eval_steps_per_second": 0.837, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 4e-05, | |
| "loss": 4.7641, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_accuracy": 0.21813953488372093, | |
| "eval_loss": 4.053351879119873, | |
| "eval_runtime": 5.9761, | |
| "eval_samples_per_second": 359.764, | |
| "eval_steps_per_second": 0.837, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0761, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_accuracy": 0.34325581395348836, | |
| "eval_loss": 3.1956703662872314, | |
| "eval_runtime": 6.1144, | |
| "eval_samples_per_second": 351.631, | |
| "eval_steps_per_second": 0.818, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 3.3846, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "eval_accuracy": 0.4786046511627907, | |
| "eval_loss": 2.493035078048706, | |
| "eval_runtime": 5.9735, | |
| "eval_samples_per_second": 359.926, | |
| "eval_steps_per_second": 0.837, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 2.8319, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "eval_accuracy": 0.5623255813953488, | |
| "eval_loss": 2.0251505374908447, | |
| "eval_runtime": 5.9942, | |
| "eval_samples_per_second": 358.678, | |
| "eval_steps_per_second": 0.834, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 2.4358, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_accuracy": 0.6334883720930232, | |
| "eval_loss": 1.6915886402130127, | |
| "eval_runtime": 5.9886, | |
| "eval_samples_per_second": 359.016, | |
| "eval_steps_per_second": 0.835, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 2.1433, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "eval_accuracy": 0.6637209302325582, | |
| "eval_loss": 1.456493616104126, | |
| "eval_runtime": 6.0018, | |
| "eval_samples_per_second": 358.223, | |
| "eval_steps_per_second": 0.833, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.9315, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "eval_accuracy": 0.7013953488372093, | |
| "eval_loss": 1.2676024436950684, | |
| "eval_runtime": 5.9984, | |
| "eval_samples_per_second": 358.426, | |
| "eval_steps_per_second": 0.834, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 1.7746, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "eval_accuracy": 0.7237209302325581, | |
| "eval_loss": 1.1530412435531616, | |
| "eval_runtime": 5.9931, | |
| "eval_samples_per_second": 358.749, | |
| "eval_steps_per_second": 0.834, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 1.6467, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "eval_accuracy": 0.74, | |
| "eval_loss": 1.0685006380081177, | |
| "eval_runtime": 6.2755, | |
| "eval_samples_per_second": 342.602, | |
| "eval_steps_per_second": 0.797, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 1.546, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "eval_accuracy": 0.7572093023255814, | |
| "eval_loss": 0.999431312084198, | |
| "eval_runtime": 5.987, | |
| "eval_samples_per_second": 359.114, | |
| "eval_steps_per_second": 0.835, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4734, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "eval_accuracy": 0.7660465116279069, | |
| "eval_loss": 0.946732223033905, | |
| "eval_runtime": 5.9853, | |
| "eval_samples_per_second": 359.213, | |
| "eval_steps_per_second": 0.835, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.4163, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "eval_accuracy": 0.7753488372093024, | |
| "eval_loss": 0.9061232209205627, | |
| "eval_runtime": 5.9975, | |
| "eval_samples_per_second": 358.485, | |
| "eval_steps_per_second": 0.834, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 1.3593, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 15.95, | |
| "eval_accuracy": 0.7832558139534884, | |
| "eval_loss": 0.8717327117919922, | |
| "eval_runtime": 5.9972, | |
| "eval_samples_per_second": 358.502, | |
| "eval_steps_per_second": 0.834, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 1.3129, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "eval_accuracy": 0.7902325581395349, | |
| "eval_loss": 0.8438239097595215, | |
| "eval_runtime": 5.9855, | |
| "eval_samples_per_second": 359.203, | |
| "eval_steps_per_second": 0.835, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 1.2843, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "eval_accuracy": 0.7986046511627907, | |
| "eval_loss": 0.8182681798934937, | |
| "eval_runtime": 5.985, | |
| "eval_samples_per_second": 359.23, | |
| "eval_steps_per_second": 0.835, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 1.2527, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "eval_accuracy": 0.804186046511628, | |
| "eval_loss": 0.8000912070274353, | |
| "eval_runtime": 5.9829, | |
| "eval_samples_per_second": 359.357, | |
| "eval_steps_per_second": 0.836, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.2127, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "eval_accuracy": 0.804186046511628, | |
| "eval_loss": 0.7860467433929443, | |
| "eval_runtime": 5.9859, | |
| "eval_samples_per_second": 359.177, | |
| "eval_steps_per_second": 0.835, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 1.1854, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "eval_accuracy": 0.8093023255813954, | |
| "eval_loss": 0.7675830125808716, | |
| "eval_runtime": 6.0054, | |
| "eval_samples_per_second": 358.008, | |
| "eval_steps_per_second": 0.833, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 21.95, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 1.1574, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 21.95, | |
| "eval_accuracy": 0.8079069767441861, | |
| "eval_loss": 0.7555623650550842, | |
| "eval_runtime": 5.9751, | |
| "eval_samples_per_second": 359.829, | |
| "eval_steps_per_second": 0.837, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1283, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "eval_accuracy": 0.8130232558139535, | |
| "eval_loss": 0.7396910190582275, | |
| "eval_runtime": 5.9779, | |
| "eval_samples_per_second": 359.658, | |
| "eval_steps_per_second": 0.836, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 1.1302, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "eval_accuracy": 0.8111627906976744, | |
| "eval_loss": 0.7319375276565552, | |
| "eval_runtime": 5.9855, | |
| "eval_samples_per_second": 359.199, | |
| "eval_steps_per_second": 0.835, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 24.95, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.1032, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 24.95, | |
| "eval_accuracy": 0.8176744186046512, | |
| "eval_loss": 0.718932569026947, | |
| "eval_runtime": 5.977, | |
| "eval_samples_per_second": 359.71, | |
| "eval_steps_per_second": 0.837, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 1.0891, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 25.95, | |
| "eval_accuracy": 0.82, | |
| "eval_loss": 0.7135240435600281, | |
| "eval_runtime": 5.9814, | |
| "eval_samples_per_second": 359.449, | |
| "eval_steps_per_second": 0.836, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 26.95, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 1.0738, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 26.95, | |
| "eval_accuracy": 0.8195348837209302, | |
| "eval_loss": 0.7008457779884338, | |
| "eval_runtime": 5.9894, | |
| "eval_samples_per_second": 358.966, | |
| "eval_steps_per_second": 0.835, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 1.0665, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "eval_accuracy": 0.8218604651162791, | |
| "eval_loss": 0.6941251754760742, | |
| "eval_runtime": 5.9997, | |
| "eval_samples_per_second": 358.352, | |
| "eval_steps_per_second": 0.833, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 1.0354, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 28.95, | |
| "eval_accuracy": 0.8223255813953488, | |
| "eval_loss": 0.690199613571167, | |
| "eval_runtime": 5.992, | |
| "eval_samples_per_second": 358.814, | |
| "eval_steps_per_second": 0.834, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 29.95, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.0404, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 29.95, | |
| "eval_accuracy": 0.8237209302325581, | |
| "eval_loss": 0.684846043586731, | |
| "eval_runtime": 5.9904, | |
| "eval_samples_per_second": 358.908, | |
| "eval_steps_per_second": 0.835, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 30.95, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 1.0251, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 30.95, | |
| "eval_accuracy": 0.8218604651162791, | |
| "eval_loss": 0.678667426109314, | |
| "eval_runtime": 5.9867, | |
| "eval_samples_per_second": 359.129, | |
| "eval_steps_per_second": 0.835, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0127, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 31.95, | |
| "eval_accuracy": 0.8246511627906977, | |
| "eval_loss": 0.673900306224823, | |
| "eval_runtime": 5.9929, | |
| "eval_samples_per_second": 358.756, | |
| "eval_steps_per_second": 0.834, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 32.95, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 1.0023, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 32.95, | |
| "eval_accuracy": 0.8255813953488372, | |
| "eval_loss": 0.6712960004806519, | |
| "eval_runtime": 5.9994, | |
| "eval_samples_per_second": 358.368, | |
| "eval_steps_per_second": 0.833, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 33.95, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 1.0012, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 33.95, | |
| "eval_accuracy": 0.8246511627906977, | |
| "eval_loss": 0.6670580506324768, | |
| "eval_runtime": 6.0038, | |
| "eval_samples_per_second": 358.108, | |
| "eval_steps_per_second": 0.833, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 34.95, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.9835, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 34.95, | |
| "eval_accuracy": 0.8251162790697675, | |
| "eval_loss": 0.6612110733985901, | |
| "eval_runtime": 5.9862, | |
| "eval_samples_per_second": 359.158, | |
| "eval_steps_per_second": 0.835, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 35.95, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.982, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 35.95, | |
| "eval_accuracy": 0.8251162790697675, | |
| "eval_loss": 0.6587132215499878, | |
| "eval_runtime": 6.0051, | |
| "eval_samples_per_second": 358.031, | |
| "eval_steps_per_second": 0.833, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 36.95, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.9849, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 36.95, | |
| "eval_accuracy": 0.8251162790697675, | |
| "eval_loss": 0.6563166975975037, | |
| "eval_runtime": 6.0073, | |
| "eval_samples_per_second": 357.899, | |
| "eval_steps_per_second": 0.832, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 37.95, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.9645, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 37.95, | |
| "eval_accuracy": 0.8232558139534883, | |
| "eval_loss": 0.652894914150238, | |
| "eval_runtime": 6.0024, | |
| "eval_samples_per_second": 358.193, | |
| "eval_steps_per_second": 0.833, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 38.95, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.947, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 38.95, | |
| "eval_accuracy": 0.8283720930232558, | |
| "eval_loss": 0.6512119770050049, | |
| "eval_runtime": 5.9854, | |
| "eval_samples_per_second": 359.208, | |
| "eval_steps_per_second": 0.835, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 39.95, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.9563, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 39.95, | |
| "eval_accuracy": 0.8265116279069767, | |
| "eval_loss": 0.6485108733177185, | |
| "eval_runtime": 5.9994, | |
| "eval_samples_per_second": 358.371, | |
| "eval_steps_per_second": 0.833, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 40.95, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9619, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 40.95, | |
| "eval_accuracy": 0.826046511627907, | |
| "eval_loss": 0.6457317471504211, | |
| "eval_runtime": 5.9978, | |
| "eval_samples_per_second": 358.466, | |
| "eval_steps_per_second": 0.834, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 41.95, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.9399, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 41.95, | |
| "eval_accuracy": 0.8283720930232558, | |
| "eval_loss": 0.6446535587310791, | |
| "eval_runtime": 5.9698, | |
| "eval_samples_per_second": 360.144, | |
| "eval_steps_per_second": 0.838, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 42.95, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.9423, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 42.95, | |
| "eval_accuracy": 0.8288372093023256, | |
| "eval_loss": 0.6421455144882202, | |
| "eval_runtime": 5.9718, | |
| "eval_samples_per_second": 360.027, | |
| "eval_steps_per_second": 0.837, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 43.95, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.9482, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 43.95, | |
| "eval_accuracy": 0.8283720930232558, | |
| "eval_loss": 0.6426512002944946, | |
| "eval_runtime": 6.012, | |
| "eval_samples_per_second": 357.619, | |
| "eval_steps_per_second": 0.832, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 44.95, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.9315, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 44.95, | |
| "eval_accuracy": 0.8297674418604651, | |
| "eval_loss": 0.6420783400535583, | |
| "eval_runtime": 6.2892, | |
| "eval_samples_per_second": 341.856, | |
| "eval_steps_per_second": 0.795, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 45.95, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.9411, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 45.95, | |
| "eval_accuracy": 0.8293023255813954, | |
| "eval_loss": 0.6401400566101074, | |
| "eval_runtime": 5.9778, | |
| "eval_samples_per_second": 359.664, | |
| "eval_steps_per_second": 0.836, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 46.95, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.9249, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 46.95, | |
| "eval_accuracy": 0.8297674418604651, | |
| "eval_loss": 0.639735758304596, | |
| "eval_runtime": 5.9937, | |
| "eval_samples_per_second": 358.711, | |
| "eval_steps_per_second": 0.834, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 47.95, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.9361, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 47.95, | |
| "eval_accuracy": 0.8293023255813954, | |
| "eval_loss": 0.6406731605529785, | |
| "eval_runtime": 5.9924, | |
| "eval_samples_per_second": 358.789, | |
| "eval_steps_per_second": 0.834, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 48.95, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.952, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 48.95, | |
| "eval_accuracy": 0.8297674418604651, | |
| "eval_loss": 0.6389557719230652, | |
| "eval_runtime": 5.9868, | |
| "eval_samples_per_second": 359.122, | |
| "eval_steps_per_second": 0.835, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 49.95, | |
| "learning_rate": 0.0, | |
| "loss": 0.9358, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 49.95, | |
| "eval_accuracy": 0.8297674418604651, | |
| "eval_loss": 0.6392757296562195, | |
| "eval_runtime": 6.0005, | |
| "eval_samples_per_second": 358.304, | |
| "eval_steps_per_second": 0.833, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 49.95, | |
| "step": 500, | |
| "total_flos": 1.0940562332139848e+19, | |
| "train_loss": 1.65314315032959, | |
| "train_runtime": 3746.3389, | |
| "train_samples_per_second": 286.947, | |
| "train_steps_per_second": 0.133 | |
| } | |
| ], | |
| "max_steps": 500, | |
| "num_train_epochs": 50, | |
| "total_flos": 1.0940562332139848e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |