| { | |
| "best_metric": 1.0657285451889038, | |
| "best_model_checkpoint": "actsa-distilbert/checkpoint-3246", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 3246, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02310536044362292, | |
| "grad_norm": 2.318068265914917, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 1.0841, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04621072088724584, | |
| "grad_norm": 3.620454788208008, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.0888, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06931608133086876, | |
| "grad_norm": 2.4006574153900146, | |
| "learning_rate": 0.0001153846153846154, | |
| "loss": 1.0742, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09242144177449169, | |
| "grad_norm": 4.676277160644531, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 1.0871, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11552680221811461, | |
| "grad_norm": 6.01164436340332, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 1.1146, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.13863216266173753, | |
| "grad_norm": 2.2937514781951904, | |
| "learning_rate": 0.0002307692307692308, | |
| "loss": 1.0578, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16173752310536044, | |
| "grad_norm": 2.6013343334198, | |
| "learning_rate": 0.0002692307692307692, | |
| "loss": 1.0571, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.18484288354898337, | |
| "grad_norm": 3.571342945098877, | |
| "learning_rate": 0.0003076923076923077, | |
| "loss": 1.145, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20794824399260628, | |
| "grad_norm": 2.3125054836273193, | |
| "learning_rate": 0.00034615384615384613, | |
| "loss": 1.0901, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.23105360443622922, | |
| "grad_norm": 5.343853950500488, | |
| "learning_rate": 0.00038461538461538467, | |
| "loss": 1.0198, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2541589648798521, | |
| "grad_norm": 4.148077487945557, | |
| "learning_rate": 0.0004230769230769231, | |
| "loss": 1.0066, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.27726432532347506, | |
| "grad_norm": 3.7557380199432373, | |
| "learning_rate": 0.0004615384615384616, | |
| "loss": 1.0734, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.300369685767098, | |
| "grad_norm": 3.485323190689087, | |
| "learning_rate": 0.0005, | |
| "loss": 1.0569, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.3234750462107209, | |
| "grad_norm": 2.63746976852417, | |
| "learning_rate": 0.0004957206436152003, | |
| "loss": 1.1081, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3465804066543438, | |
| "grad_norm": 5.485255718231201, | |
| "learning_rate": 0.0004914412872304005, | |
| "loss": 1.1346, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.36968576709796674, | |
| "grad_norm": 2.920285940170288, | |
| "learning_rate": 0.00048716193084560086, | |
| "loss": 1.0998, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3927911275415896, | |
| "grad_norm": 2.696606397628784, | |
| "learning_rate": 0.0004828825744608011, | |
| "loss": 1.1216, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.41589648798521256, | |
| "grad_norm": 2.0741255283355713, | |
| "learning_rate": 0.0004786032180760014, | |
| "loss": 1.1092, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4390018484288355, | |
| "grad_norm": 2.102992534637451, | |
| "learning_rate": 0.0004743238616912017, | |
| "loss": 1.1172, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.46210720887245843, | |
| "grad_norm": 1.4443374872207642, | |
| "learning_rate": 0.0004700445053064019, | |
| "loss": 1.0929, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4852125693160813, | |
| "grad_norm": 2.7878777980804443, | |
| "learning_rate": 0.0004657651489216022, | |
| "loss": 1.125, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5083179297597042, | |
| "grad_norm": 2.387270212173462, | |
| "learning_rate": 0.00046148579253680244, | |
| "loss": 1.1069, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5314232902033271, | |
| "grad_norm": 2.1369564533233643, | |
| "learning_rate": 0.00045720643615200274, | |
| "loss": 1.085, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5545286506469501, | |
| "grad_norm": 2.407505989074707, | |
| "learning_rate": 0.00045292707976720304, | |
| "loss": 1.095, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.577634011090573, | |
| "grad_norm": 1.3333139419555664, | |
| "learning_rate": 0.0004486477233824033, | |
| "loss": 1.1035, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.600739371534196, | |
| "grad_norm": 1.891635537147522, | |
| "learning_rate": 0.0004443683669976036, | |
| "loss": 0.9419, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6238447319778189, | |
| "grad_norm": 2.536003589630127, | |
| "learning_rate": 0.00044008901061280383, | |
| "loss": 1.1685, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.6469500924214417, | |
| "grad_norm": 2.3016841411590576, | |
| "learning_rate": 0.00043580965422800413, | |
| "loss": 1.0619, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6700554528650647, | |
| "grad_norm": 1.4672470092773438, | |
| "learning_rate": 0.00043153029784320443, | |
| "loss": 1.1276, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.6931608133086876, | |
| "grad_norm": 2.2047739028930664, | |
| "learning_rate": 0.0004272509414584047, | |
| "loss": 1.0428, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7162661737523105, | |
| "grad_norm": 4.394761562347412, | |
| "learning_rate": 0.000422971585073605, | |
| "loss": 1.082, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.7393715341959335, | |
| "grad_norm": 1.6812162399291992, | |
| "learning_rate": 0.00041869222868880517, | |
| "loss": 1.1325, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7624768946395564, | |
| "grad_norm": 2.4136714935302734, | |
| "learning_rate": 0.00041441287230400547, | |
| "loss": 1.0486, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.7855822550831792, | |
| "grad_norm": 1.2103418111801147, | |
| "learning_rate": 0.00041013351591920577, | |
| "loss": 1.093, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8086876155268022, | |
| "grad_norm": 2.494950771331787, | |
| "learning_rate": 0.000405854159534406, | |
| "loss": 1.0638, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.8317929759704251, | |
| "grad_norm": 1.8322207927703857, | |
| "learning_rate": 0.0004015748031496063, | |
| "loss": 0.9711, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8548983364140481, | |
| "grad_norm": 2.9408106803894043, | |
| "learning_rate": 0.00039729544676480656, | |
| "loss": 1.1413, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.878003696857671, | |
| "grad_norm": 1.0680229663848877, | |
| "learning_rate": 0.00039301609038000686, | |
| "loss": 1.0609, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.9011090573012939, | |
| "grad_norm": 1.952222466468811, | |
| "learning_rate": 0.00038873673399520716, | |
| "loss": 1.0954, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.9242144177449169, | |
| "grad_norm": 3.1969923973083496, | |
| "learning_rate": 0.0003844573776104074, | |
| "loss": 1.0895, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9473197781885397, | |
| "grad_norm": 2.0018506050109863, | |
| "learning_rate": 0.0003801780212256077, | |
| "loss": 1.0697, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.9704251386321626, | |
| "grad_norm": 2.0683329105377197, | |
| "learning_rate": 0.00037589866484080795, | |
| "loss": 1.0999, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.9935304990757856, | |
| "grad_norm": 2.1113333702087402, | |
| "learning_rate": 0.00037161930845600825, | |
| "loss": 1.1089, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4584103512014787, | |
| "eval_f1_macro": 0.2095479509928179, | |
| "eval_f1_micro": 0.4584103512014787, | |
| "eval_f1_weighted": 0.2881768494245037, | |
| "eval_loss": 1.0685529708862305, | |
| "eval_precision_macro": 0.1528034504004929, | |
| "eval_precision_micro": 0.4584103512014787, | |
| "eval_precision_weighted": 0.21014005008866307, | |
| "eval_recall_macro": 0.3333333333333333, | |
| "eval_recall_micro": 0.4584103512014787, | |
| "eval_recall_weighted": 0.4584103512014787, | |
| "eval_runtime": 103.9446, | |
| "eval_samples_per_second": 10.409, | |
| "eval_steps_per_second": 1.308, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 1.0166358595194085, | |
| "grad_norm": 2.078071117401123, | |
| "learning_rate": 0.0003673399520712085, | |
| "loss": 1.0538, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0397412199630314, | |
| "grad_norm": 1.2932239770889282, | |
| "learning_rate": 0.00036306059568640874, | |
| "loss": 1.1108, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.0628465804066543, | |
| "grad_norm": 1.8026275634765625, | |
| "learning_rate": 0.00035878123930160904, | |
| "loss": 1.0782, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.0859519408502774, | |
| "grad_norm": 2.0047168731689453, | |
| "learning_rate": 0.0003545018829168093, | |
| "loss": 1.0754, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.1090573012939002, | |
| "grad_norm": 2.5215866565704346, | |
| "learning_rate": 0.0003502225265320096, | |
| "loss": 1.0822, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.1321626617375231, | |
| "grad_norm": 1.7528326511383057, | |
| "learning_rate": 0.0003459431701472099, | |
| "loss": 1.0956, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.155268022181146, | |
| "grad_norm": 2.345102548599243, | |
| "learning_rate": 0.00034166381376241013, | |
| "loss": 1.0284, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.1783733826247689, | |
| "grad_norm": 2.051119327545166, | |
| "learning_rate": 0.00033738445737761043, | |
| "loss": 1.0811, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.201478743068392, | |
| "grad_norm": 2.405728340148926, | |
| "learning_rate": 0.0003331051009928107, | |
| "loss": 1.0661, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.2245841035120149, | |
| "grad_norm": 2.118389368057251, | |
| "learning_rate": 0.000328825744608011, | |
| "loss": 1.0821, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.2476894639556377, | |
| "grad_norm": 1.383575677871704, | |
| "learning_rate": 0.0003245463882232113, | |
| "loss": 1.0988, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.2707948243992606, | |
| "grad_norm": 0.9262095093727112, | |
| "learning_rate": 0.00032026703183841147, | |
| "loss": 1.0855, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.2939001848428835, | |
| "grad_norm": 0.8497403860092163, | |
| "learning_rate": 0.00031598767545361177, | |
| "loss": 1.0734, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.3170055452865066, | |
| "grad_norm": 2.554072856903076, | |
| "learning_rate": 0.000311708319068812, | |
| "loss": 1.0495, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.3401109057301293, | |
| "grad_norm": 2.196169853210449, | |
| "learning_rate": 0.0003074289626840123, | |
| "loss": 1.0611, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.3632162661737524, | |
| "grad_norm": 1.9735369682312012, | |
| "learning_rate": 0.0003031496062992126, | |
| "loss": 1.0689, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.3863216266173752, | |
| "grad_norm": 1.28324556350708, | |
| "learning_rate": 0.00029887024991441286, | |
| "loss": 1.1195, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.4094269870609981, | |
| "grad_norm": 2.870333671569824, | |
| "learning_rate": 0.00029459089352961316, | |
| "loss": 1.0909, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.432532347504621, | |
| "grad_norm": 2.790924549102783, | |
| "learning_rate": 0.00029031153714481346, | |
| "loss": 1.1001, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.4556377079482439, | |
| "grad_norm": 1.2432293891906738, | |
| "learning_rate": 0.0002860321807600137, | |
| "loss": 1.124, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.478743068391867, | |
| "grad_norm": 0.8692905306816101, | |
| "learning_rate": 0.000281752824375214, | |
| "loss": 1.0717, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.5018484288354899, | |
| "grad_norm": 1.2673799991607666, | |
| "learning_rate": 0.00027747346799041425, | |
| "loss": 1.086, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.5249537892791127, | |
| "grad_norm": 1.9591180086135864, | |
| "learning_rate": 0.00027319411160561455, | |
| "loss": 1.0408, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.5480591497227358, | |
| "grad_norm": 1.8689022064208984, | |
| "learning_rate": 0.00026891475522081485, | |
| "loss": 1.0499, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.5711645101663585, | |
| "grad_norm": 2.0180625915527344, | |
| "learning_rate": 0.00026463539883601504, | |
| "loss": 1.0936, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.5942698706099816, | |
| "grad_norm": 0.9715362191200256, | |
| "learning_rate": 0.00026035604245121534, | |
| "loss": 1.0886, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.6173752310536045, | |
| "grad_norm": 1.5542079210281372, | |
| "learning_rate": 0.0002560766860664156, | |
| "loss": 1.0825, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.6404805914972274, | |
| "grad_norm": 2.8334264755249023, | |
| "learning_rate": 0.0002517973296816159, | |
| "loss": 1.0932, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.6635859519408502, | |
| "grad_norm": 0.5704463720321655, | |
| "learning_rate": 0.0002475179732968162, | |
| "loss": 1.1057, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.6866913123844731, | |
| "grad_norm": 2.452209949493408, | |
| "learning_rate": 0.00024323861691201643, | |
| "loss": 1.0569, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.7097966728280962, | |
| "grad_norm": 1.304701805114746, | |
| "learning_rate": 0.0002389592605272167, | |
| "loss": 1.0859, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.7329020332717189, | |
| "grad_norm": 1.5926436185836792, | |
| "learning_rate": 0.000234679904142417, | |
| "loss": 1.0832, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.756007393715342, | |
| "grad_norm": 2.683790445327759, | |
| "learning_rate": 0.00023040054775761728, | |
| "loss": 1.0539, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.7791127541589649, | |
| "grad_norm": 1.4463739395141602, | |
| "learning_rate": 0.00022612119137281752, | |
| "loss": 1.0358, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1.8022181146025877, | |
| "grad_norm": 3.22567081451416, | |
| "learning_rate": 0.0002218418349880178, | |
| "loss": 0.9887, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.8253234750462108, | |
| "grad_norm": 0.9853553771972656, | |
| "learning_rate": 0.00021756247860321807, | |
| "loss": 1.0566, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 1.8484288354898335, | |
| "grad_norm": 1.0822279453277588, | |
| "learning_rate": 0.00021328312221841837, | |
| "loss": 1.0437, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.8715341959334566, | |
| "grad_norm": 1.9909262657165527, | |
| "learning_rate": 0.00020900376583361864, | |
| "loss": 1.0059, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 1.8946395563770795, | |
| "grad_norm": 1.8531982898712158, | |
| "learning_rate": 0.0002047244094488189, | |
| "loss": 1.0671, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.9177449168207024, | |
| "grad_norm": 1.0466595888137817, | |
| "learning_rate": 0.00020044505306401916, | |
| "loss": 1.0766, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 1.9408502772643255, | |
| "grad_norm": 0.8994802236557007, | |
| "learning_rate": 0.00019616569667921946, | |
| "loss": 0.9991, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.9639556377079481, | |
| "grad_norm": 1.929488182067871, | |
| "learning_rate": 0.00019188634029441973, | |
| "loss": 1.0905, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 1.9870609981515712, | |
| "grad_norm": 1.9165269136428833, | |
| "learning_rate": 0.00018760698390962, | |
| "loss": 1.039, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4584103512014787, | |
| "eval_f1_macro": 0.2095479509928179, | |
| "eval_f1_micro": 0.4584103512014787, | |
| "eval_f1_weighted": 0.2881768494245037, | |
| "eval_loss": 1.0747383832931519, | |
| "eval_precision_macro": 0.1528034504004929, | |
| "eval_precision_micro": 0.4584103512014787, | |
| "eval_precision_weighted": 0.21014005008866307, | |
| "eval_recall_macro": 0.3333333333333333, | |
| "eval_recall_micro": 0.4584103512014787, | |
| "eval_recall_weighted": 0.4584103512014787, | |
| "eval_runtime": 105.3751, | |
| "eval_samples_per_second": 10.268, | |
| "eval_steps_per_second": 1.291, | |
| "step": 2164 | |
| }, | |
| { | |
| "epoch": 2.010166358595194, | |
| "grad_norm": 4.0738606452941895, | |
| "learning_rate": 0.00018332762752482028, | |
| "loss": 1.0268, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.033271719038817, | |
| "grad_norm": 2.0423989295959473, | |
| "learning_rate": 0.00017904827114002055, | |
| "loss": 1.0547, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.05637707948244, | |
| "grad_norm": 2.3596909046173096, | |
| "learning_rate": 0.00017476891475522082, | |
| "loss": 1.0647, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2.0794824399260627, | |
| "grad_norm": 1.9593594074249268, | |
| "learning_rate": 0.0001704895583704211, | |
| "loss": 1.1023, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.102587800369686, | |
| "grad_norm": 1.8953109979629517, | |
| "learning_rate": 0.00016621020198562137, | |
| "loss": 1.093, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2.1256931608133085, | |
| "grad_norm": 1.6998157501220703, | |
| "learning_rate": 0.00016193084560082164, | |
| "loss": 1.0777, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.1487985212569316, | |
| "grad_norm": 1.0082741975784302, | |
| "learning_rate": 0.0001576514892160219, | |
| "loss": 1.0999, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 2.1719038817005547, | |
| "grad_norm": 1.887078046798706, | |
| "learning_rate": 0.0001533721328312222, | |
| "loss": 1.1067, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.1950092421441774, | |
| "grad_norm": 1.8659969568252563, | |
| "learning_rate": 0.00014909277644642246, | |
| "loss": 1.0769, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 2.2181146025878005, | |
| "grad_norm": 0.916480302810669, | |
| "learning_rate": 0.00014481342006162273, | |
| "loss": 1.048, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.241219963031423, | |
| "grad_norm": 1.9037351608276367, | |
| "learning_rate": 0.000140534063676823, | |
| "loss": 1.0509, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 2.2643253234750462, | |
| "grad_norm": 1.9867937564849854, | |
| "learning_rate": 0.00013625470729202328, | |
| "loss": 1.0609, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.287430683918669, | |
| "grad_norm": 2.044760227203369, | |
| "learning_rate": 0.00013197535090722358, | |
| "loss": 1.0351, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 2.310536044362292, | |
| "grad_norm": 2.0097403526306152, | |
| "learning_rate": 0.00012769599452242385, | |
| "loss": 1.0433, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.333641404805915, | |
| "grad_norm": 1.9191139936447144, | |
| "learning_rate": 0.0001234166381376241, | |
| "loss": 1.0219, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 2.3567467652495377, | |
| "grad_norm": 1.9857523441314697, | |
| "learning_rate": 0.00011913728175282437, | |
| "loss": 1.0892, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.379852125693161, | |
| "grad_norm": 2.7910494804382324, | |
| "learning_rate": 0.00011485792536802465, | |
| "loss": 1.1069, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 2.402957486136784, | |
| "grad_norm": 1.5788651704788208, | |
| "learning_rate": 0.00011057856898322493, | |
| "loss": 1.0685, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.4260628465804066, | |
| "grad_norm": 2.1729698181152344, | |
| "learning_rate": 0.0001062992125984252, | |
| "loss": 1.0369, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 2.4491682070240297, | |
| "grad_norm": 1.842307686805725, | |
| "learning_rate": 0.00010201985621362547, | |
| "loss": 1.0777, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.4722735674676524, | |
| "grad_norm": 1.7603636980056763, | |
| "learning_rate": 9.774049982882574e-05, | |
| "loss": 1.0776, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 2.4953789279112755, | |
| "grad_norm": 3.0491414070129395, | |
| "learning_rate": 9.346114344402602e-05, | |
| "loss": 1.04, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.518484288354898, | |
| "grad_norm": 1.8501389026641846, | |
| "learning_rate": 8.918178705922629e-05, | |
| "loss": 1.0217, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 2.5415896487985212, | |
| "grad_norm": 1.788746953010559, | |
| "learning_rate": 8.490243067442658e-05, | |
| "loss": 1.086, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.5646950092421443, | |
| "grad_norm": 1.6955204010009766, | |
| "learning_rate": 8.062307428962684e-05, | |
| "loss": 1.0784, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 2.587800369685767, | |
| "grad_norm": 1.7728503942489624, | |
| "learning_rate": 7.634371790482711e-05, | |
| "loss": 1.0826, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.61090573012939, | |
| "grad_norm": 1.9343187808990479, | |
| "learning_rate": 7.20643615200274e-05, | |
| "loss": 1.0258, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 2.634011090573013, | |
| "grad_norm": 1.7846380472183228, | |
| "learning_rate": 6.778500513522765e-05, | |
| "loss": 1.1017, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.657116451016636, | |
| "grad_norm": 0.9427468180656433, | |
| "learning_rate": 6.350564875042794e-05, | |
| "loss": 1.0762, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 2.6802218114602585, | |
| "grad_norm": 2.756263017654419, | |
| "learning_rate": 5.9226292365628206e-05, | |
| "loss": 1.0642, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.7033271719038816, | |
| "grad_norm": 1.782007098197937, | |
| "learning_rate": 5.4946935980828486e-05, | |
| "loss": 1.0402, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 2.7264325323475047, | |
| "grad_norm": 2.0735743045806885, | |
| "learning_rate": 5.066757959602876e-05, | |
| "loss": 1.0347, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.7495378927911274, | |
| "grad_norm": 1.935968279838562, | |
| "learning_rate": 4.638822321122903e-05, | |
| "loss": 1.0703, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 2.7726432532347505, | |
| "grad_norm": 1.8476896286010742, | |
| "learning_rate": 4.2108866826429304e-05, | |
| "loss": 1.0754, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.7957486136783736, | |
| "grad_norm": 1.8447425365447998, | |
| "learning_rate": 3.782951044162958e-05, | |
| "loss": 1.0004, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 2.8188539741219962, | |
| "grad_norm": 1.811383605003357, | |
| "learning_rate": 3.355015405682985e-05, | |
| "loss": 1.108, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.8419593345656193, | |
| "grad_norm": 1.8410310745239258, | |
| "learning_rate": 2.927079767203013e-05, | |
| "loss": 1.0884, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 2.865064695009242, | |
| "grad_norm": 1.8326698541641235, | |
| "learning_rate": 2.49914412872304e-05, | |
| "loss": 1.0986, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.888170055452865, | |
| "grad_norm": 1.9954646825790405, | |
| "learning_rate": 2.0712084902430675e-05, | |
| "loss": 1.0926, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 2.9112754158964878, | |
| "grad_norm": 0.8552793264389038, | |
| "learning_rate": 1.643272851763095e-05, | |
| "loss": 1.1081, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.934380776340111, | |
| "grad_norm": 1.6706448793411255, | |
| "learning_rate": 1.2153372132831224e-05, | |
| "loss": 1.1125, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 2.957486136783734, | |
| "grad_norm": 1.8879237174987793, | |
| "learning_rate": 7.874015748031496e-06, | |
| "loss": 1.0289, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.9805914972273566, | |
| "grad_norm": 1.7822940349578857, | |
| "learning_rate": 3.59465936323177e-06, | |
| "loss": 1.0718, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4584103512014787, | |
| "eval_f1_macro": 0.2095479509928179, | |
| "eval_f1_micro": 0.4584103512014787, | |
| "eval_f1_weighted": 0.2881768494245037, | |
| "eval_loss": 1.0657285451889038, | |
| "eval_precision_macro": 0.1528034504004929, | |
| "eval_precision_micro": 0.4584103512014787, | |
| "eval_precision_weighted": 0.21014005008866307, | |
| "eval_recall_macro": 0.3333333333333333, | |
| "eval_recall_micro": 0.4584103512014787, | |
| "eval_recall_weighted": 0.4584103512014787, | |
| "eval_runtime": 112.831, | |
| "eval_samples_per_second": 9.59, | |
| "eval_steps_per_second": 1.205, | |
| "step": 3246 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 3246, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 429996844283904.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |