| { | |
| "best_metric": 3.239711284637451, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.03716090672612412, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003716090672612412, | |
| "grad_norm": 1.395404577255249, | |
| "learning_rate": 5e-06, | |
| "loss": 3.8589, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003716090672612412, | |
| "eval_loss": 3.698608160018921, | |
| "eval_runtime": 110.3096, | |
| "eval_samples_per_second": 41.084, | |
| "eval_steps_per_second": 20.542, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007432181345224824, | |
| "grad_norm": 1.495450735092163, | |
| "learning_rate": 1e-05, | |
| "loss": 3.8595, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011148272017837235, | |
| "grad_norm": 1.708409309387207, | |
| "learning_rate": 1.5e-05, | |
| "loss": 3.8337, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014864362690449647, | |
| "grad_norm": 1.6244080066680908, | |
| "learning_rate": 2e-05, | |
| "loss": 3.9127, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018580453363062058, | |
| "grad_norm": 1.6346101760864258, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.7906, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002229654403567447, | |
| "grad_norm": 1.5767675638198853, | |
| "learning_rate": 3e-05, | |
| "loss": 3.5424, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002601263470828688, | |
| "grad_norm": 1.6814939975738525, | |
| "learning_rate": 3.5e-05, | |
| "loss": 3.7044, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0029728725380899295, | |
| "grad_norm": 1.6342999935150146, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7866, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033444816053511705, | |
| "grad_norm": 1.6840134859085083, | |
| "learning_rate": 4.5e-05, | |
| "loss": 3.5734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0037160906726124115, | |
| "grad_norm": 1.8313182592391968, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8096, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004087699739873653, | |
| "grad_norm": 1.8736138343811035, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.56, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004459308807134894, | |
| "grad_norm": 1.9644217491149902, | |
| "learning_rate": 6e-05, | |
| "loss": 3.6562, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004830917874396135, | |
| "grad_norm": 1.846778392791748, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 3.502, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005202526941657376, | |
| "grad_norm": 1.958957314491272, | |
| "learning_rate": 7e-05, | |
| "loss": 3.7459, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005574136008918618, | |
| "grad_norm": 1.9100260734558105, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.5192, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005945745076179859, | |
| "grad_norm": 1.9562067985534668, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5551, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0063173541434411, | |
| "grad_norm": 2.0819551944732666, | |
| "learning_rate": 8.5e-05, | |
| "loss": 3.6895, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006688963210702341, | |
| "grad_norm": 2.0404553413391113, | |
| "learning_rate": 9e-05, | |
| "loss": 3.5621, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007060572277963582, | |
| "grad_norm": 2.0112435817718506, | |
| "learning_rate": 9.5e-05, | |
| "loss": 3.4923, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007432181345224823, | |
| "grad_norm": 2.050147771835327, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7079, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007803790412486065, | |
| "grad_norm": 1.969068169593811, | |
| "learning_rate": 9.999238475781957e-05, | |
| "loss": 3.5209, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008175399479747306, | |
| "grad_norm": 2.1419968605041504, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 3.5605, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008547008547008548, | |
| "grad_norm": 1.9498823881149292, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 3.4271, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008918617614269788, | |
| "grad_norm": 2.0768706798553467, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 3.4113, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00929022668153103, | |
| "grad_norm": 2.0907914638519287, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 3.3731, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00966183574879227, | |
| "grad_norm": 2.208066463470459, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 3.3223, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010033444816053512, | |
| "grad_norm": 2.1362009048461914, | |
| "learning_rate": 9.962730758206611e-05, | |
| "loss": 3.1932, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010405053883314752, | |
| "grad_norm": 2.2497036457061768, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.2557, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010776662950575994, | |
| "grad_norm": 2.3101062774658203, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 3.2662, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011148272017837236, | |
| "grad_norm": 2.285050392150879, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 3.3092, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011519881085098476, | |
| "grad_norm": 2.3182809352874756, | |
| "learning_rate": 9.908135917238321e-05, | |
| "loss": 3.2587, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.011891490152359718, | |
| "grad_norm": 2.44177508354187, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 3.2171, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012263099219620958, | |
| "grad_norm": 2.3121793270111084, | |
| "learning_rate": 9.871850323926177e-05, | |
| "loss": 3.2153, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0126347082868822, | |
| "grad_norm": 2.3896982669830322, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 3.3923, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013006317354143442, | |
| "grad_norm": 2.573725700378418, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.0088, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013377926421404682, | |
| "grad_norm": 2.594827175140381, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 3.1635, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013749535488665924, | |
| "grad_norm": 2.49944806098938, | |
| "learning_rate": 9.781523779815179e-05, | |
| "loss": 3.1225, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014121144555927164, | |
| "grad_norm": 2.5924439430236816, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.2409, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.014492753623188406, | |
| "grad_norm": 2.622465133666992, | |
| "learning_rate": 9.727592877996585e-05, | |
| "loss": 2.8234, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014864362690449646, | |
| "grad_norm": 2.6936821937561035, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.1865, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015235971757710888, | |
| "grad_norm": 2.5600905418395996, | |
| "learning_rate": 9.667902132486009e-05, | |
| "loss": 3.2298, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01560758082497213, | |
| "grad_norm": 2.606717824935913, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 3.2275, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.015979189892233372, | |
| "grad_norm": 2.7310972213745117, | |
| "learning_rate": 9.602524267262203e-05, | |
| "loss": 3.1006, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.016350798959494612, | |
| "grad_norm": 2.696859836578369, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 3.2682, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.016722408026755852, | |
| "grad_norm": 3.2989847660064697, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 3.4225, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 2.866588830947876, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 3.248, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017465626161278336, | |
| "grad_norm": 2.8411591053009033, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 2.9874, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.017837235228539576, | |
| "grad_norm": 3.2578847408294678, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 3.248, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018208844295800816, | |
| "grad_norm": 2.9824798107147217, | |
| "learning_rate": 9.373098535696979e-05, | |
| "loss": 3.599, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01858045336306206, | |
| "grad_norm": 3.438220500946045, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.7818, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01858045336306206, | |
| "eval_loss": 3.3963160514831543, | |
| "eval_runtime": 110.1439, | |
| "eval_samples_per_second": 41.146, | |
| "eval_steps_per_second": 20.573, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0189520624303233, | |
| "grad_norm": 3.2213802337646484, | |
| "learning_rate": 9.285836503510562e-05, | |
| "loss": 3.7682, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01932367149758454, | |
| "grad_norm": 2.897183418273926, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 3.6962, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.019695280564845784, | |
| "grad_norm": 2.333893299102783, | |
| "learning_rate": 9.193352839727121e-05, | |
| "loss": 3.55, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.020066889632107024, | |
| "grad_norm": 2.0622718334198, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 3.6484, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.020438498699368264, | |
| "grad_norm": 1.9058257341384888, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 3.5701, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.020810107766629504, | |
| "grad_norm": 1.4503419399261475, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.4605, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.021181716833890748, | |
| "grad_norm": 1.41510808467865, | |
| "learning_rate": 8.993177550236464e-05, | |
| "loss": 3.3843, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.021553325901151988, | |
| "grad_norm": 1.5639384984970093, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 3.2906, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.021924934968413228, | |
| "grad_norm": 1.5347603559494019, | |
| "learning_rate": 8.885729807284856e-05, | |
| "loss": 3.586, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.022296544035674472, | |
| "grad_norm": 1.5613843202590942, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 3.3605, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.022668153102935712, | |
| "grad_norm": 1.5832593441009521, | |
| "learning_rate": 8.773547901113862e-05, | |
| "loss": 3.415, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.023039762170196952, | |
| "grad_norm": 1.6786587238311768, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 3.3806, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.023411371237458192, | |
| "grad_norm": 1.6316285133361816, | |
| "learning_rate": 8.656768508095853e-05, | |
| "loss": 3.4167, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.023782980304719436, | |
| "grad_norm": 1.6437264680862427, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 3.4412, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.024154589371980676, | |
| "grad_norm": 1.5929906368255615, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.379, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.024526198439241916, | |
| "grad_norm": 1.6711010932922363, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 3.2288, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.02489780750650316, | |
| "grad_norm": 1.816035509109497, | |
| "learning_rate": 8.409991800312493e-05, | |
| "loss": 3.2581, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0252694165737644, | |
| "grad_norm": 1.5691595077514648, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 3.3002, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "grad_norm": 1.7285726070404053, | |
| "learning_rate": 8.280295144952536e-05, | |
| "loss": 3.3853, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.026012634708286884, | |
| "grad_norm": 1.6965199708938599, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 3.1998, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.026384243775548124, | |
| "grad_norm": 1.7152042388916016, | |
| "learning_rate": 8.146601955249188e-05, | |
| "loss": 3.304, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.026755852842809364, | |
| "grad_norm": 1.8366388082504272, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 3.1231, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.027127461910070604, | |
| "grad_norm": 1.8617119789123535, | |
| "learning_rate": 8.009075115760243e-05, | |
| "loss": 3.3145, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.027499070977331848, | |
| "grad_norm": 1.8905341625213623, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 3.3134, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.027870680044593088, | |
| "grad_norm": 1.882635474205017, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 3.3169, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.028242289111854328, | |
| "grad_norm": 2.0442984104156494, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 3.1649, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.028613898179115572, | |
| "grad_norm": 1.940576434135437, | |
| "learning_rate": 7.723195175075136e-05, | |
| "loss": 3.1936, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": 2.0615429878234863, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 3.3171, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.029357116313638052, | |
| "grad_norm": 2.0494372844696045, | |
| "learning_rate": 7.575190374550272e-05, | |
| "loss": 3.2035, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.029728725380899292, | |
| "grad_norm": 2.0333774089813232, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.1547, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.030100334448160536, | |
| "grad_norm": 2.141954183578491, | |
| "learning_rate": 7.424048101231686e-05, | |
| "loss": 2.9143, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.030471943515421776, | |
| "grad_norm": 2.22705340385437, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 3.1911, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.030843552582683016, | |
| "grad_norm": 2.196378231048584, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 3.2222, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.03121516164994426, | |
| "grad_norm": 2.2278859615325928, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 3.0329, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.031586770717205497, | |
| "grad_norm": 2.3488399982452393, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 2.9382, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.031958379784466744, | |
| "grad_norm": 2.3422460556030273, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 3.1308, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.032329988851727984, | |
| "grad_norm": 2.4222495555877686, | |
| "learning_rate": 6.953655642446368e-05, | |
| "loss": 2.9883, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.032701597918989224, | |
| "grad_norm": 2.425354242324829, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 3.1242, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.033073206986250464, | |
| "grad_norm": 2.56612491607666, | |
| "learning_rate": 6.7918397477265e-05, | |
| "loss": 3.0771, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.033444816053511704, | |
| "grad_norm": 2.566655397415161, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 2.9399, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.033816425120772944, | |
| "grad_norm": 2.3641583919525146, | |
| "learning_rate": 6.627840772285784e-05, | |
| "loss": 2.9741, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 2.47420334815979, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.7321, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.03455964325529543, | |
| "grad_norm": 2.7138381004333496, | |
| "learning_rate": 6.461858523613684e-05, | |
| "loss": 3.027, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.03493125232255667, | |
| "grad_norm": 2.655938148498535, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 2.9049, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.03530286138981791, | |
| "grad_norm": 2.87831974029541, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.2944, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.03567447045707915, | |
| "grad_norm": 2.891333818435669, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 3.2566, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.03604607952434039, | |
| "grad_norm": 2.8243558406829834, | |
| "learning_rate": 6.124755271719325e-05, | |
| "loss": 3.1022, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.03641768859160163, | |
| "grad_norm": 3.1256723403930664, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 3.3878, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.03678929765886288, | |
| "grad_norm": 3.284562349319458, | |
| "learning_rate": 5.9540449768827246e-05, | |
| "loss": 3.376, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.03716090672612412, | |
| "grad_norm": 3.2456462383270264, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 3.7382, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03716090672612412, | |
| "eval_loss": 3.239711284637451, | |
| "eval_runtime": 109.8084, | |
| "eval_samples_per_second": 41.272, | |
| "eval_steps_per_second": 20.636, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7747803637874688.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |