| { | |
| "best_metric": 0.9988826815642458, | |
| "best_model_checkpoint": "convnext-large-224-22k-1k-LongSleeveCleanedData/checkpoint-287", | |
| "epoch": 9.94041708043694, | |
| "global_step": 1430, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.126, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.982332155477032e-05, | |
| "loss": 0.4641, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.946996466431096e-05, | |
| "loss": 0.1498, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.9116607773851593e-05, | |
| "loss": 0.0822, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.8763250883392234e-05, | |
| "loss": 0.0971, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.840989399293286e-05, | |
| "loss": 0.1169, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.8056537102473495e-05, | |
| "loss": 0.0601, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.7703180212014135e-05, | |
| "loss": 0.0768, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.734982332155477e-05, | |
| "loss": 0.0824, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.699646643109541e-05, | |
| "loss": 0.1023, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.664310954063604e-05, | |
| "loss": 0.0724, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.6289752650176684e-05, | |
| "loss": 0.0838, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.593639575971732e-05, | |
| "loss": 0.0706, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.558303886925796e-05, | |
| "loss": 0.0805, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.9977653631284916, | |
| "eval_loss": 0.009151672944426537, | |
| "eval_runtime": 385.1025, | |
| "eval_samples_per_second": 2.324, | |
| "eval_steps_per_second": 0.291, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.5229681978798585e-05, | |
| "loss": 0.082, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.4876325088339225e-05, | |
| "loss": 0.0348, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.452296819787986e-05, | |
| "loss": 0.1542, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.416961130742049e-05, | |
| "loss": 0.0675, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.381625441696113e-05, | |
| "loss": 0.096, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 4.346289752650177e-05, | |
| "loss": 0.0616, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 4.310954063604241e-05, | |
| "loss": 0.0636, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.275618374558304e-05, | |
| "loss": 0.0508, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.240282685512368e-05, | |
| "loss": 0.0825, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.204946996466431e-05, | |
| "loss": 0.0513, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.169611307420495e-05, | |
| "loss": 0.0455, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 4.134275618374558e-05, | |
| "loss": 0.105, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.0989399293286223e-05, | |
| "loss": 0.0822, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.063604240282686e-05, | |
| "loss": 0.0396, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9988826815642458, | |
| "eval_loss": 0.005963917821645737, | |
| "eval_runtime": 41.4755, | |
| "eval_samples_per_second": 21.579, | |
| "eval_steps_per_second": 2.7, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.028268551236749e-05, | |
| "loss": 0.075, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.992932862190813e-05, | |
| "loss": 0.0661, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.9575971731448765e-05, | |
| "loss": 0.0343, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.9222614840989406e-05, | |
| "loss": 0.0574, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.886925795053003e-05, | |
| "loss": 0.1035, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 3.851590106007067e-05, | |
| "loss": 0.0878, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.816254416961131e-05, | |
| "loss": 0.0474, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.780918727915195e-05, | |
| "loss": 0.0357, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 3.745583038869258e-05, | |
| "loss": 0.0574, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.710247349823322e-05, | |
| "loss": 0.0671, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.6749116607773855e-05, | |
| "loss": 0.0608, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.639575971731449e-05, | |
| "loss": 0.0706, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.604240282685513e-05, | |
| "loss": 0.0404, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 3.5689045936395756e-05, | |
| "loss": 0.0663, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 3.53356890459364e-05, | |
| "loss": 0.0382, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9988826815642458, | |
| "eval_loss": 0.0049131326377391815, | |
| "eval_runtime": 40.5246, | |
| "eval_samples_per_second": 22.085, | |
| "eval_steps_per_second": 2.764, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 3.498233215547703e-05, | |
| "loss": 0.0474, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 3.462897526501767e-05, | |
| "loss": 0.0526, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.4275618374558305e-05, | |
| "loss": 0.053, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.3922261484098945e-05, | |
| "loss": 0.064, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3.356890459363958e-05, | |
| "loss": 0.0414, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 3.321554770318021e-05, | |
| "loss": 0.0448, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 3.286219081272085e-05, | |
| "loss": 0.0379, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 3.250883392226148e-05, | |
| "loss": 0.0506, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.215547703180212e-05, | |
| "loss": 0.0412, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 3.1802120141342755e-05, | |
| "loss": 0.0684, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.1448763250883395e-05, | |
| "loss": 0.0738, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 3.109540636042403e-05, | |
| "loss": 0.0408, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 3.074204946996467e-05, | |
| "loss": 0.0344, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 3.03886925795053e-05, | |
| "loss": 0.0394, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9977653631284916, | |
| "eval_loss": 0.003506433218717575, | |
| "eval_runtime": 40.9642, | |
| "eval_samples_per_second": 21.848, | |
| "eval_steps_per_second": 2.734, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 3.003533568904594e-05, | |
| "loss": 0.0404, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 2.9681978798586574e-05, | |
| "loss": 0.0426, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 2.9328621908127208e-05, | |
| "loss": 0.0365, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 2.8975265017667848e-05, | |
| "loss": 0.0488, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 2.862190812720848e-05, | |
| "loss": 0.0381, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.826855123674912e-05, | |
| "loss": 0.0633, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 2.7915194346289753e-05, | |
| "loss": 0.046, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 2.7561837455830393e-05, | |
| "loss": 0.0665, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 2.7208480565371023e-05, | |
| "loss": 0.0397, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.6855123674911664e-05, | |
| "loss": 0.0605, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.6501766784452298e-05, | |
| "loss": 0.019, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.6148409893992938e-05, | |
| "loss": 0.0394, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 2.5795053003533572e-05, | |
| "loss": 0.0488, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.5441696113074202e-05, | |
| "loss": 0.0269, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9988826815642458, | |
| "eval_loss": 0.0033426920417696238, | |
| "eval_runtime": 40.8952, | |
| "eval_samples_per_second": 21.885, | |
| "eval_steps_per_second": 2.739, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.5088339222614843e-05, | |
| "loss": 0.021, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 2.473498233215548e-05, | |
| "loss": 0.0635, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 2.4381625441696117e-05, | |
| "loss": 0.0391, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 2.4028268551236747e-05, | |
| "loss": 0.0583, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 2.3674911660777384e-05, | |
| "loss": 0.0248, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 2.332155477031802e-05, | |
| "loss": 0.0309, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.296819787985866e-05, | |
| "loss": 0.0403, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 2.2614840989399292e-05, | |
| "loss": 0.0602, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 2.226148409893993e-05, | |
| "loss": 0.0152, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 2.1908127208480567e-05, | |
| "loss": 0.0581, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 2.1554770318021204e-05, | |
| "loss": 0.0292, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 2.120141342756184e-05, | |
| "loss": 0.045, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 2.0848056537102475e-05, | |
| "loss": 0.0278, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 2.0494699646643112e-05, | |
| "loss": 0.0743, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 2.0141342756183745e-05, | |
| "loss": 0.0249, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9988826815642458, | |
| "eval_loss": 0.0035183620639145374, | |
| "eval_runtime": 39.497, | |
| "eval_samples_per_second": 22.66, | |
| "eval_steps_per_second": 2.836, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.9787985865724383e-05, | |
| "loss": 0.0336, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 1.9434628975265016e-05, | |
| "loss": 0.0408, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 1.9081272084805653e-05, | |
| "loss": 0.0255, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 1.872791519434629e-05, | |
| "loss": 0.0309, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 1.8374558303886928e-05, | |
| "loss": 0.0479, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.8021201413427565e-05, | |
| "loss": 0.0268, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 1.76678445229682e-05, | |
| "loss": 0.0553, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.7314487632508836e-05, | |
| "loss": 0.0169, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 1.6961130742049473e-05, | |
| "loss": 0.0245, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1.6607773851590106e-05, | |
| "loss": 0.0242, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.625441696113074e-05, | |
| "loss": 0.0303, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 1.5901060070671377e-05, | |
| "loss": 0.0527, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 1.5547703180212014e-05, | |
| "loss": 0.0296, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 1.519434628975265e-05, | |
| "loss": 0.0388, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9988826815642458, | |
| "eval_loss": 0.005780559964478016, | |
| "eval_runtime": 41.8587, | |
| "eval_samples_per_second": 21.381, | |
| "eval_steps_per_second": 2.676, | |
| "step": 1007 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 1.4840989399293287e-05, | |
| "loss": 0.0124, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 1.4487632508833924e-05, | |
| "loss": 0.0487, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 1.413427561837456e-05, | |
| "loss": 0.0464, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 1.3780918727915197e-05, | |
| "loss": 0.013, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 1.3427561837455832e-05, | |
| "loss": 0.0411, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 1.3074204946996469e-05, | |
| "loss": 0.0318, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.2720848056537101e-05, | |
| "loss": 0.0382, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 1.236749116607774e-05, | |
| "loss": 0.0275, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 1.2014134275618374e-05, | |
| "loss": 0.0168, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 1.166077738515901e-05, | |
| "loss": 0.0452, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "learning_rate": 1.1307420494699646e-05, | |
| "loss": 0.0307, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 1.0954063604240283e-05, | |
| "loss": 0.0359, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 1.060070671378092e-05, | |
| "loss": 0.0341, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 1.0247349823321556e-05, | |
| "loss": 0.0587, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 9.893992932862191e-06, | |
| "loss": 0.0175, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_accuracy": 0.9988826815642458, | |
| "eval_loss": 0.003908189013600349, | |
| "eval_runtime": 41.7986, | |
| "eval_samples_per_second": 21.412, | |
| "eval_steps_per_second": 2.68, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 9.540636042402827e-06, | |
| "loss": 0.0397, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 9.187279151943464e-06, | |
| "loss": 0.0422, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 8.8339222614841e-06, | |
| "loss": 0.0324, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 8.480565371024736e-06, | |
| "loss": 0.0206, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 8.12720848056537e-06, | |
| "loss": 0.0306, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 7.773851590106007e-06, | |
| "loss": 0.0436, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.4204946996466435e-06, | |
| "loss": 0.0125, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 7.06713780918728e-06, | |
| "loss": 0.0265, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 6.713780918727916e-06, | |
| "loss": 0.0232, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 6.3604240282685506e-06, | |
| "loss": 0.039, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 6.007067137809187e-06, | |
| "loss": 0.0245, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 5.653710247349823e-06, | |
| "loss": 0.0447, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 5.30035335689046e-06, | |
| "loss": 0.0179, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 4.946996466431096e-06, | |
| "loss": 0.041, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9988826815642458, | |
| "eval_loss": 0.0022225547581911087, | |
| "eval_runtime": 41.6857, | |
| "eval_samples_per_second": 21.47, | |
| "eval_steps_per_second": 2.687, | |
| "step": 1294 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.593639575971732e-06, | |
| "loss": 0.0294, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 4.240282685512368e-06, | |
| "loss": 0.0258, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 3.886925795053004e-06, | |
| "loss": 0.0357, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.53356890459364e-06, | |
| "loss": 0.0065, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 3.1802120141342753e-06, | |
| "loss": 0.0199, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 2.8268551236749116e-06, | |
| "loss": 0.0175, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 2.473498233215548e-06, | |
| "loss": 0.023, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 2.120141342756184e-06, | |
| "loss": 0.026, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 1.76678445229682e-06, | |
| "loss": 0.0327, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 1.4134275618374558e-06, | |
| "loss": 0.0374, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 1.060070671378092e-06, | |
| "loss": 0.0272, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 7.067137809187279e-07, | |
| "loss": 0.0303, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 3.5335689045936394e-07, | |
| "loss": 0.0343, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 0.0, | |
| "loss": 0.0432, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_accuracy": 0.9988826815642458, | |
| "eval_loss": 0.0024573865812271833, | |
| "eval_runtime": 40.191, | |
| "eval_samples_per_second": 22.269, | |
| "eval_steps_per_second": 2.787, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "step": 1430, | |
| "total_flos": 1.4186448226450612e+19, | |
| "train_loss": 0.0581204283070731, | |
| "train_runtime": 12121.0022, | |
| "train_samples_per_second": 6.643, | |
| "train_steps_per_second": 0.118 | |
| } | |
| ], | |
| "max_steps": 1430, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.4186448226450612e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |