| { | |
| "best_metric": 0.4137542277339346, | |
| "best_model_checkpoint": "resnet-50-finetuned-galaxy10-decals/checkpoint-1122", | |
| "epoch": 9.939879759519037, | |
| "eval_steps": 500, | |
| "global_step": 1240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08016032064128256, | |
| "grad_norm": 0.5629293918609619, | |
| "learning_rate": 1.9838709677419358e-05, | |
| "loss": 2.3002, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16032064128256512, | |
| "grad_norm": 0.6315276026725769, | |
| "learning_rate": 1.967741935483871e-05, | |
| "loss": 2.2945, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24048096192384769, | |
| "grad_norm": 0.6637193560600281, | |
| "learning_rate": 1.9516129032258068e-05, | |
| "loss": 2.2901, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32064128256513025, | |
| "grad_norm": 0.6203126907348633, | |
| "learning_rate": 1.935483870967742e-05, | |
| "loss": 2.2838, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.40080160320641284, | |
| "grad_norm": 0.7069018483161926, | |
| "learning_rate": 1.9193548387096777e-05, | |
| "loss": 2.2765, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48096192384769537, | |
| "grad_norm": 0.6753049492835999, | |
| "learning_rate": 1.903225806451613e-05, | |
| "loss": 2.2719, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.561122244488978, | |
| "grad_norm": 0.7277663946151733, | |
| "learning_rate": 1.8870967741935487e-05, | |
| "loss": 2.2691, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6412825651302605, | |
| "grad_norm": 0.6369321346282959, | |
| "learning_rate": 1.870967741935484e-05, | |
| "loss": 2.2662, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7214428857715431, | |
| "grad_norm": 0.9763292074203491, | |
| "learning_rate": 1.8548387096774193e-05, | |
| "loss": 2.2536, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8016032064128257, | |
| "grad_norm": 0.7406184077262878, | |
| "learning_rate": 1.838709677419355e-05, | |
| "loss": 2.2497, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8817635270541082, | |
| "grad_norm": 0.7439438700675964, | |
| "learning_rate": 1.8225806451612903e-05, | |
| "loss": 2.2429, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9619238476953907, | |
| "grad_norm": 0.772075891494751, | |
| "learning_rate": 1.806451612903226e-05, | |
| "loss": 2.2417, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9939879759519038, | |
| "eval_accuracy": 0.23731679819616686, | |
| "eval_f1": 0.10768730389550502, | |
| "eval_loss": 2.2265095710754395, | |
| "eval_precision": 0.06968947596402092, | |
| "eval_recall": 0.23731679819616686, | |
| "eval_runtime": 10.4766, | |
| "eval_samples_per_second": 169.33, | |
| "eval_steps_per_second": 5.345, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.0420841683366733, | |
| "grad_norm": 0.690293550491333, | |
| "learning_rate": 1.7903225806451612e-05, | |
| "loss": 2.2289, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.122244488977956, | |
| "grad_norm": 0.9022379517555237, | |
| "learning_rate": 1.774193548387097e-05, | |
| "loss": 2.2309, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2024048096192386, | |
| "grad_norm": 0.8783809542655945, | |
| "learning_rate": 1.7580645161290325e-05, | |
| "loss": 2.2224, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.282565130260521, | |
| "grad_norm": 0.7563625574111938, | |
| "learning_rate": 1.741935483870968e-05, | |
| "loss": 2.2067, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3627254509018036, | |
| "grad_norm": 0.7573732137680054, | |
| "learning_rate": 1.7258064516129035e-05, | |
| "loss": 2.2092, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.4428857715430863, | |
| "grad_norm": 0.6887681484222412, | |
| "learning_rate": 1.7096774193548388e-05, | |
| "loss": 2.1874, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.5230460921843687, | |
| "grad_norm": 0.8253772854804993, | |
| "learning_rate": 1.6935483870967744e-05, | |
| "loss": 2.1956, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6032064128256514, | |
| "grad_norm": 0.930928647518158, | |
| "learning_rate": 1.6774193548387098e-05, | |
| "loss": 2.188, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6833667334669338, | |
| "grad_norm": 0.7987092733383179, | |
| "learning_rate": 1.6612903225806454e-05, | |
| "loss": 2.1865, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.7635270541082164, | |
| "grad_norm": 0.9516962170600891, | |
| "learning_rate": 1.6451612903225807e-05, | |
| "loss": 2.1816, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.843687374749499, | |
| "grad_norm": 0.7769425511360168, | |
| "learning_rate": 1.6290322580645164e-05, | |
| "loss": 2.1487, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.9238476953907817, | |
| "grad_norm": 0.9441273212432861, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 2.1616, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.9959919839679359, | |
| "eval_accuracy": 0.19503945885005636, | |
| "eval_f1": 0.08885289259144245, | |
| "eval_loss": 2.1268093585968018, | |
| "eval_precision": 0.11324255277888252, | |
| "eval_recall": 0.19503945885005636, | |
| "eval_runtime": 21.372, | |
| "eval_samples_per_second": 83.006, | |
| "eval_steps_per_second": 2.62, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.004008016032064, | |
| "grad_norm": 1.0876325368881226, | |
| "learning_rate": 1.596774193548387e-05, | |
| "loss": 2.1485, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0841683366733466, | |
| "grad_norm": 1.0379817485809326, | |
| "learning_rate": 1.5806451612903226e-05, | |
| "loss": 2.1385, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.164328657314629, | |
| "grad_norm": 1.0472718477249146, | |
| "learning_rate": 1.5645161290322583e-05, | |
| "loss": 2.1171, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.244488977955912, | |
| "grad_norm": 1.1123789548873901, | |
| "learning_rate": 1.5483870967741936e-05, | |
| "loss": 2.1185, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.3246492985971945, | |
| "grad_norm": 1.0969492197036743, | |
| "learning_rate": 1.5322580645161292e-05, | |
| "loss": 2.1059, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.404809619238477, | |
| "grad_norm": 1.0305417776107788, | |
| "learning_rate": 1.5161290322580646e-05, | |
| "loss": 2.094, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.4849699398797593, | |
| "grad_norm": 1.1403542757034302, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 2.0992, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.565130260521042, | |
| "grad_norm": 1.1770292520523071, | |
| "learning_rate": 1.4838709677419357e-05, | |
| "loss": 2.0758, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.6452905811623246, | |
| "grad_norm": 0.9762546420097351, | |
| "learning_rate": 1.4677419354838712e-05, | |
| "loss": 2.0753, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.7254509018036073, | |
| "grad_norm": 1.0303020477294922, | |
| "learning_rate": 1.4516129032258066e-05, | |
| "loss": 2.0721, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.80561122244489, | |
| "grad_norm": 1.1007182598114014, | |
| "learning_rate": 1.4354838709677421e-05, | |
| "loss": 2.0442, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.8857715430861726, | |
| "grad_norm": 1.0562711954116821, | |
| "learning_rate": 1.4193548387096776e-05, | |
| "loss": 2.0467, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.9659318637274548, | |
| "grad_norm": 1.0534286499023438, | |
| "learning_rate": 1.4032258064516131e-05, | |
| "loss": 2.0459, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.997995991983968, | |
| "eval_accuracy": 0.24013528748590757, | |
| "eval_f1": 0.12897223772636482, | |
| "eval_loss": 1.990055799484253, | |
| "eval_precision": 0.10291028503169428, | |
| "eval_recall": 0.24013528748590757, | |
| "eval_runtime": 9.0597, | |
| "eval_samples_per_second": 195.812, | |
| "eval_steps_per_second": 6.181, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 3.0460921843687374, | |
| "grad_norm": 1.340589165687561, | |
| "learning_rate": 1.3870967741935486e-05, | |
| "loss": 2.0286, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.12625250501002, | |
| "grad_norm": 1.260714054107666, | |
| "learning_rate": 1.3709677419354839e-05, | |
| "loss": 2.0037, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.2064128256513027, | |
| "grad_norm": 1.1234012842178345, | |
| "learning_rate": 1.3548387096774194e-05, | |
| "loss": 1.9998, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.2865731462925853, | |
| "grad_norm": 1.1667792797088623, | |
| "learning_rate": 1.3387096774193548e-05, | |
| "loss": 1.9845, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.3667334669338675, | |
| "grad_norm": 1.4682308435440063, | |
| "learning_rate": 1.3225806451612903e-05, | |
| "loss": 1.9663, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.44689378757515, | |
| "grad_norm": 1.1297812461853027, | |
| "learning_rate": 1.3064516129032258e-05, | |
| "loss": 1.9711, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.527054108216433, | |
| "grad_norm": 1.2213447093963623, | |
| "learning_rate": 1.2903225806451613e-05, | |
| "loss": 1.9557, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.6072144288577155, | |
| "grad_norm": 1.1665083169937134, | |
| "learning_rate": 1.274193548387097e-05, | |
| "loss": 1.962, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.687374749498998, | |
| "grad_norm": 1.3926866054534912, | |
| "learning_rate": 1.2580645161290324e-05, | |
| "loss": 1.9647, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.7675350701402808, | |
| "grad_norm": 1.1469335556030273, | |
| "learning_rate": 1.2419354838709679e-05, | |
| "loss": 1.9533, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.847695390781563, | |
| "grad_norm": 1.259191870689392, | |
| "learning_rate": 1.2258064516129034e-05, | |
| "loss": 1.9532, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.9278557114228456, | |
| "grad_norm": 1.181053876876831, | |
| "learning_rate": 1.2096774193548388e-05, | |
| "loss": 1.9203, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.33032694475760993, | |
| "eval_f1": 0.20520589850554893, | |
| "eval_loss": 1.8571178913116455, | |
| "eval_precision": 0.3115828631860488, | |
| "eval_recall": 0.33032694475760993, | |
| "eval_runtime": 9.5098, | |
| "eval_samples_per_second": 186.545, | |
| "eval_steps_per_second": 5.889, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 4.008016032064128, | |
| "grad_norm": 1.2856674194335938, | |
| "learning_rate": 1.1935483870967743e-05, | |
| "loss": 1.938, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0881763527054105, | |
| "grad_norm": 1.263211727142334, | |
| "learning_rate": 1.1774193548387098e-05, | |
| "loss": 1.9092, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.168336673346693, | |
| "grad_norm": 1.5177675485610962, | |
| "learning_rate": 1.1612903225806453e-05, | |
| "loss": 1.9162, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.248496993987976, | |
| "grad_norm": 1.1196962594985962, | |
| "learning_rate": 1.1451612903225808e-05, | |
| "loss": 1.9038, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.328657314629258, | |
| "grad_norm": 1.2426973581314087, | |
| "learning_rate": 1.1290322580645164e-05, | |
| "loss": 1.8824, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.408817635270541, | |
| "grad_norm": 1.224511981010437, | |
| "learning_rate": 1.1129032258064516e-05, | |
| "loss": 1.8817, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.488977955911824, | |
| "grad_norm": 1.370235562324524, | |
| "learning_rate": 1.096774193548387e-05, | |
| "loss": 1.8781, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.569138276553106, | |
| "grad_norm": 1.3393809795379639, | |
| "learning_rate": 1.0806451612903225e-05, | |
| "loss": 1.8472, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.649298597194389, | |
| "grad_norm": 1.3370624780654907, | |
| "learning_rate": 1.0645161290322582e-05, | |
| "loss": 1.8535, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.729458917835672, | |
| "grad_norm": 1.1478331089019775, | |
| "learning_rate": 1.0483870967741936e-05, | |
| "loss": 1.8508, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.809619238476954, | |
| "grad_norm": 1.4004801511764526, | |
| "learning_rate": 1.0322580645161291e-05, | |
| "loss": 1.8861, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.889779559118237, | |
| "grad_norm": 1.399299144744873, | |
| "learning_rate": 1.0161290322580646e-05, | |
| "loss": 1.8537, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.969939879759519, | |
| "grad_norm": 1.3188832998275757, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8347, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.993987975951904, | |
| "eval_accuracy": 0.3613303269447576, | |
| "eval_f1": 0.24569343378869493, | |
| "eval_loss": 1.7692168951034546, | |
| "eval_precision": 0.2693815240199387, | |
| "eval_recall": 0.3613303269447576, | |
| "eval_runtime": 11.1509, | |
| "eval_samples_per_second": 159.09, | |
| "eval_steps_per_second": 5.022, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 5.050100200400801, | |
| "grad_norm": 1.2819945812225342, | |
| "learning_rate": 9.838709677419356e-06, | |
| "loss": 1.8244, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.130260521042084, | |
| "grad_norm": 1.291672706604004, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 1.8077, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.210420841683367, | |
| "grad_norm": 1.4084501266479492, | |
| "learning_rate": 9.516129032258065e-06, | |
| "loss": 1.8432, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.290581162324649, | |
| "grad_norm": 1.527843713760376, | |
| "learning_rate": 9.35483870967742e-06, | |
| "loss": 1.815, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.370741482965932, | |
| "grad_norm": 1.317143440246582, | |
| "learning_rate": 9.193548387096775e-06, | |
| "loss": 1.8104, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.4509018036072145, | |
| "grad_norm": 1.344497561454773, | |
| "learning_rate": 9.03225806451613e-06, | |
| "loss": 1.8064, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.531062124248497, | |
| "grad_norm": 1.4130953550338745, | |
| "learning_rate": 8.870967741935484e-06, | |
| "loss": 1.7957, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.61122244488978, | |
| "grad_norm": 1.5459003448486328, | |
| "learning_rate": 8.70967741935484e-06, | |
| "loss": 1.8051, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.6913827655310625, | |
| "grad_norm": 1.7455060482025146, | |
| "learning_rate": 8.548387096774194e-06, | |
| "loss": 1.8146, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.771543086172345, | |
| "grad_norm": 1.362961769104004, | |
| "learning_rate": 8.387096774193549e-06, | |
| "loss": 1.7706, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.851703406813627, | |
| "grad_norm": 1.503525972366333, | |
| "learning_rate": 8.225806451612904e-06, | |
| "loss": 1.7877, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.9318637274549095, | |
| "grad_norm": 1.4291051626205444, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 1.7628, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.995991983967936, | |
| "eval_accuracy": 0.3850056369785795, | |
| "eval_f1": 0.27578049224836065, | |
| "eval_loss": 1.692612886428833, | |
| "eval_precision": 0.417174096805733, | |
| "eval_recall": 0.3850056369785795, | |
| "eval_runtime": 15.8797, | |
| "eval_samples_per_second": 111.715, | |
| "eval_steps_per_second": 3.527, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 6.012024048096192, | |
| "grad_norm": 1.2377204895019531, | |
| "learning_rate": 7.903225806451613e-06, | |
| "loss": 1.7717, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.092184368737475, | |
| "grad_norm": 1.7056549787521362, | |
| "learning_rate": 7.741935483870968e-06, | |
| "loss": 1.7749, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 6.1723446893787575, | |
| "grad_norm": 1.51571524143219, | |
| "learning_rate": 7.580645161290323e-06, | |
| "loss": 1.7649, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 6.25250501002004, | |
| "grad_norm": 1.6524779796600342, | |
| "learning_rate": 7.4193548387096784e-06, | |
| "loss": 1.7556, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.332665330661323, | |
| "grad_norm": 1.4005558490753174, | |
| "learning_rate": 7.258064516129033e-06, | |
| "loss": 1.7437, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.412825651302605, | |
| "grad_norm": 1.567458987236023, | |
| "learning_rate": 7.096774193548388e-06, | |
| "loss": 1.7587, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.492985971943888, | |
| "grad_norm": 1.843725323677063, | |
| "learning_rate": 6.935483870967743e-06, | |
| "loss": 1.7568, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.573146292585171, | |
| "grad_norm": 1.5228469371795654, | |
| "learning_rate": 6.774193548387097e-06, | |
| "loss": 1.7507, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.653306613226453, | |
| "grad_norm": 1.6213654279708862, | |
| "learning_rate": 6.612903225806452e-06, | |
| "loss": 1.7625, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.733466933867735, | |
| "grad_norm": 1.5784552097320557, | |
| "learning_rate": 6.451612903225806e-06, | |
| "loss": 1.7321, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.813627254509018, | |
| "grad_norm": 1.5368263721466064, | |
| "learning_rate": 6.290322580645162e-06, | |
| "loss": 1.7395, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.8937875751503, | |
| "grad_norm": 2.3605217933654785, | |
| "learning_rate": 6.129032258064517e-06, | |
| "loss": 1.7604, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.973947895791583, | |
| "grad_norm": 1.6296197175979614, | |
| "learning_rate": 5.967741935483872e-06, | |
| "loss": 1.723, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.997995991983968, | |
| "eval_accuracy": 0.39853438556933485, | |
| "eval_f1": 0.292163872939456, | |
| "eval_loss": 1.6341866254806519, | |
| "eval_precision": 0.4427833264577748, | |
| "eval_recall": 0.39853438556933485, | |
| "eval_runtime": 12.0064, | |
| "eval_samples_per_second": 147.755, | |
| "eval_steps_per_second": 4.664, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 7.054108216432866, | |
| "grad_norm": 1.5017938613891602, | |
| "learning_rate": 5.806451612903226e-06, | |
| "loss": 1.733, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 7.134268537074148, | |
| "grad_norm": 1.9987595081329346, | |
| "learning_rate": 5.645161290322582e-06, | |
| "loss": 1.7058, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 7.214428857715431, | |
| "grad_norm": 1.6970964670181274, | |
| "learning_rate": 5.483870967741935e-06, | |
| "loss": 1.7472, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.294589178356714, | |
| "grad_norm": 1.8042755126953125, | |
| "learning_rate": 5.322580645161291e-06, | |
| "loss": 1.7119, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 7.374749498997996, | |
| "grad_norm": 1.4862197637557983, | |
| "learning_rate": 5.161290322580646e-06, | |
| "loss": 1.7166, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 7.454909819639279, | |
| "grad_norm": 1.9236266613006592, | |
| "learning_rate": 5e-06, | |
| "loss": 1.7088, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 7.5350701402805615, | |
| "grad_norm": 1.7879084348678589, | |
| "learning_rate": 4.838709677419355e-06, | |
| "loss": 1.7041, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 7.615230460921843, | |
| "grad_norm": 1.80990731716156, | |
| "learning_rate": 4.67741935483871e-06, | |
| "loss": 1.7119, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.695390781563126, | |
| "grad_norm": 1.5909008979797363, | |
| "learning_rate": 4.516129032258065e-06, | |
| "loss": 1.6927, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.775551102204409, | |
| "grad_norm": 1.6026943922042847, | |
| "learning_rate": 4.35483870967742e-06, | |
| "loss": 1.7155, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.855711422845691, | |
| "grad_norm": 1.5704305171966553, | |
| "learning_rate": 4.193548387096774e-06, | |
| "loss": 1.7243, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.935871743486974, | |
| "grad_norm": 1.7837029695510864, | |
| "learning_rate": 4.032258064516129e-06, | |
| "loss": 1.71, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.41037204058624577, | |
| "eval_f1": 0.31215257466998775, | |
| "eval_loss": 1.6071045398712158, | |
| "eval_precision": 0.4369322578217754, | |
| "eval_recall": 0.41037204058624577, | |
| "eval_runtime": 17.7431, | |
| "eval_samples_per_second": 99.983, | |
| "eval_steps_per_second": 3.156, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 8.016032064128256, | |
| "grad_norm": 1.6631461381912231, | |
| "learning_rate": 3.870967741935484e-06, | |
| "loss": 1.6681, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.09619238476954, | |
| "grad_norm": 1.4949766397476196, | |
| "learning_rate": 3.7096774193548392e-06, | |
| "loss": 1.6996, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 8.176352705410821, | |
| "grad_norm": 1.4516801834106445, | |
| "learning_rate": 3.548387096774194e-06, | |
| "loss": 1.6857, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 8.256513026052104, | |
| "grad_norm": 1.3758476972579956, | |
| "learning_rate": 3.3870967741935484e-06, | |
| "loss": 1.7096, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 8.336673346693386, | |
| "grad_norm": 1.5905085802078247, | |
| "learning_rate": 3.225806451612903e-06, | |
| "loss": 1.6934, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 8.41683366733467, | |
| "grad_norm": 1.5107113122940063, | |
| "learning_rate": 3.0645161290322584e-06, | |
| "loss": 1.7023, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 8.496993987975952, | |
| "grad_norm": 1.2995082139968872, | |
| "learning_rate": 2.903225806451613e-06, | |
| "loss": 1.7065, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 8.577154308617235, | |
| "grad_norm": 1.4054443836212158, | |
| "learning_rate": 2.7419354838709676e-06, | |
| "loss": 1.6596, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 8.657314629258517, | |
| "grad_norm": 1.3404021263122559, | |
| "learning_rate": 2.580645161290323e-06, | |
| "loss": 1.7036, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.7374749498998, | |
| "grad_norm": 1.8194636106491089, | |
| "learning_rate": 2.4193548387096776e-06, | |
| "loss": 1.6631, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 8.817635270541082, | |
| "grad_norm": 1.8533542156219482, | |
| "learning_rate": 2.2580645161290324e-06, | |
| "loss": 1.6714, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.897795591182366, | |
| "grad_norm": 1.6438981294631958, | |
| "learning_rate": 2.096774193548387e-06, | |
| "loss": 1.6751, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.977955911823647, | |
| "grad_norm": 1.6241378784179688, | |
| "learning_rate": 1.935483870967742e-06, | |
| "loss": 1.6948, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.993987975951903, | |
| "eval_accuracy": 0.4137542277339346, | |
| "eval_f1": 0.3134270193161171, | |
| "eval_loss": 1.5789121389389038, | |
| "eval_precision": 0.44930477829595117, | |
| "eval_recall": 0.4137542277339346, | |
| "eval_runtime": 8.6347, | |
| "eval_samples_per_second": 205.451, | |
| "eval_steps_per_second": 6.485, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 9.05811623246493, | |
| "grad_norm": 1.6152193546295166, | |
| "learning_rate": 1.774193548387097e-06, | |
| "loss": 1.6929, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 9.138276553106213, | |
| "grad_norm": 1.3725346326828003, | |
| "learning_rate": 1.6129032258064516e-06, | |
| "loss": 1.7029, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 9.218436873747494, | |
| "grad_norm": 1.3589799404144287, | |
| "learning_rate": 1.4516129032258066e-06, | |
| "loss": 1.6856, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 9.298597194388778, | |
| "grad_norm": 1.686957836151123, | |
| "learning_rate": 1.2903225806451614e-06, | |
| "loss": 1.6604, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 9.37875751503006, | |
| "grad_norm": 1.3393840789794922, | |
| "learning_rate": 1.1290322580645162e-06, | |
| "loss": 1.6799, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 9.458917835671343, | |
| "grad_norm": 1.6881558895111084, | |
| "learning_rate": 9.67741935483871e-07, | |
| "loss": 1.6635, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 9.539078156312625, | |
| "grad_norm": 1.545275092124939, | |
| "learning_rate": 8.064516129032258e-07, | |
| "loss": 1.6886, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 9.619238476953909, | |
| "grad_norm": 1.2983485460281372, | |
| "learning_rate": 6.451612903225807e-07, | |
| "loss": 1.6443, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.69939879759519, | |
| "grad_norm": 1.5959370136260986, | |
| "learning_rate": 4.838709677419355e-07, | |
| "loss": 1.67, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 9.779559118236474, | |
| "grad_norm": 1.5400179624557495, | |
| "learning_rate": 3.2258064516129035e-07, | |
| "loss": 1.6754, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 9.859719438877756, | |
| "grad_norm": 1.5355889797210693, | |
| "learning_rate": 1.6129032258064518e-07, | |
| "loss": 1.6881, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 9.939879759519037, | |
| "grad_norm": 1.6926000118255615, | |
| "learning_rate": 0.0, | |
| "loss": 1.656, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.939879759519037, | |
| "eval_accuracy": 0.40529875986471253, | |
| "eval_f1": 0.3033691615952433, | |
| "eval_loss": 1.5805104970932007, | |
| "eval_precision": 0.41756755609133844, | |
| "eval_recall": 0.40529875986471253, | |
| "eval_runtime": 16.4801, | |
| "eval_samples_per_second": 107.645, | |
| "eval_steps_per_second": 3.398, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.939879759519037, | |
| "step": 1240, | |
| "total_flos": 3.3716855275489935e+18, | |
| "train_loss": 1.9026473429895217, | |
| "train_runtime": 1845.6703, | |
| "train_samples_per_second": 86.483, | |
| "train_steps_per_second": 0.672 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3716855275489935e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |