| { | |
| "best_metric": 0.4919222295284271, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.10395010395010396, | |
| "eval_steps": 25, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005197505197505198, | |
| "grad_norm": 0.32254523038864136, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.4008, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005197505197505198, | |
| "eval_loss": 0.7325336933135986, | |
| "eval_runtime": 11.447, | |
| "eval_samples_per_second": 4.368, | |
| "eval_steps_per_second": 0.612, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010395010395010396, | |
| "grad_norm": 0.20825836062431335, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.477, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015592515592515593, | |
| "grad_norm": 0.22193248569965363, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.5648, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002079002079002079, | |
| "grad_norm": 0.2992827594280243, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.5735, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002598752598752599, | |
| "grad_norm": 0.21446818113327026, | |
| "learning_rate": 0.00015, | |
| "loss": 0.5238, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0031185031185031187, | |
| "grad_norm": 0.2041025012731552, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.5336, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0036382536382536385, | |
| "grad_norm": 0.3615117073059082, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.5941, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004158004158004158, | |
| "grad_norm": 0.3850712180137634, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.5643, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004677754677754678, | |
| "grad_norm": 0.2402263879776001, | |
| "learning_rate": 0.00027, | |
| "loss": 0.5537, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005197505197505198, | |
| "grad_norm": 0.23989036679267883, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5733, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005717255717255718, | |
| "grad_norm": 0.22981992363929749, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.5729, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006237006237006237, | |
| "grad_norm": 0.27373000979423523, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.5999, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006756756756756757, | |
| "grad_norm": 0.30983805656433105, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.5903, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007276507276507277, | |
| "grad_norm": 0.2732364237308502, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.5295, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007796257796257797, | |
| "grad_norm": 0.2508494257926941, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.5413, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008316008316008316, | |
| "grad_norm": 0.2607696056365967, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.6063, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008835758835758836, | |
| "grad_norm": 0.2565303444862366, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.574, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009355509355509356, | |
| "grad_norm": 0.35899603366851807, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.5968, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009875259875259876, | |
| "grad_norm": 0.27378013730049133, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.6434, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010395010395010396, | |
| "grad_norm": 0.26049938797950745, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.6407, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010914760914760915, | |
| "grad_norm": 0.23414486646652222, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.5113, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011434511434511435, | |
| "grad_norm": 0.26911309361457825, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.6066, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.011954261954261955, | |
| "grad_norm": 0.26919862627983093, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.6391, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012474012474012475, | |
| "grad_norm": 0.28419116139411926, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.5721, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012993762993762994, | |
| "grad_norm": 0.3130952715873718, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.5899, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012993762993762994, | |
| "eval_loss": 0.540122389793396, | |
| "eval_runtime": 9.7128, | |
| "eval_samples_per_second": 5.148, | |
| "eval_steps_per_second": 0.721, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013513513513513514, | |
| "grad_norm": 0.4303876459598541, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.6755, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.014033264033264034, | |
| "grad_norm": 0.36919379234313965, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.5538, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.014553014553014554, | |
| "grad_norm": 0.33030325174331665, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.6243, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.015072765072765074, | |
| "grad_norm": 0.34687164425849915, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.604, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.015592515592515593, | |
| "grad_norm": 0.3886769115924835, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.5096, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016112266112266113, | |
| "grad_norm": 0.3807097375392914, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.6, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.016632016632016633, | |
| "grad_norm": 0.36538225412368774, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.6471, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.017151767151767153, | |
| "grad_norm": 0.5048696994781494, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.6444, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.017671517671517672, | |
| "grad_norm": 0.553619921207428, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.6453, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.018191268191268192, | |
| "grad_norm": 0.4972146153450012, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.6088, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018711018711018712, | |
| "grad_norm": 0.47668373584747314, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.6455, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.019230769230769232, | |
| "grad_norm": 0.4956304728984833, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.6739, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01975051975051975, | |
| "grad_norm": 0.4820132851600647, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.6184, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02027027027027027, | |
| "grad_norm": 0.5695618987083435, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.6457, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02079002079002079, | |
| "grad_norm": 0.6215941905975342, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.7308, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02130977130977131, | |
| "grad_norm": 0.7127547264099121, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.6398, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02182952182952183, | |
| "grad_norm": 0.7794021368026733, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.7203, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02234927234927235, | |
| "grad_norm": 0.6468542814254761, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.7176, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02286902286902287, | |
| "grad_norm": 0.7985377311706543, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.7033, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02338877338877339, | |
| "grad_norm": 0.7809744477272034, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.8077, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02390852390852391, | |
| "grad_norm": 0.9611108303070068, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.841, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02442827442827443, | |
| "grad_norm": 1.0788683891296387, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.8095, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02494802494802495, | |
| "grad_norm": 0.8641987442970276, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.8089, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02546777546777547, | |
| "grad_norm": 1.215991497039795, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.7884, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02598752598752599, | |
| "grad_norm": 1.888974905014038, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.9488, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02598752598752599, | |
| "eval_loss": 0.5958743691444397, | |
| "eval_runtime": 9.7046, | |
| "eval_samples_per_second": 5.152, | |
| "eval_steps_per_second": 0.721, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02650727650727651, | |
| "grad_norm": 0.4678969085216522, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.427, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.02702702702702703, | |
| "grad_norm": 0.3184508681297302, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.5281, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02754677754677755, | |
| "grad_norm": 0.25341641902923584, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.4908, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.028066528066528068, | |
| "grad_norm": 0.23108318448066711, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.483, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.028586278586278588, | |
| "grad_norm": 0.2675793170928955, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.4906, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.029106029106029108, | |
| "grad_norm": 0.26088351011276245, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.5292, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.029625779625779627, | |
| "grad_norm": 0.23946167528629303, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.5545, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.030145530145530147, | |
| "grad_norm": 0.26028525829315186, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.5487, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.030665280665280667, | |
| "grad_norm": 0.26847925782203674, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.4912, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.031185031185031187, | |
| "grad_norm": 0.2771508991718292, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.5403, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03170478170478171, | |
| "grad_norm": 0.2898350954055786, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.5789, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.032224532224532226, | |
| "grad_norm": 0.25867152214050293, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.5064, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.032744282744282746, | |
| "grad_norm": 0.2536691129207611, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.5948, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.033264033264033266, | |
| "grad_norm": 0.26933252811431885, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.5598, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.033783783783783786, | |
| "grad_norm": 0.24513447284698486, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.5593, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.034303534303534305, | |
| "grad_norm": 0.3047233819961548, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.5761, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.034823284823284825, | |
| "grad_norm": 0.258892685174942, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.5551, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.035343035343035345, | |
| "grad_norm": 0.22836266458034515, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.541, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.035862785862785865, | |
| "grad_norm": 0.25990796089172363, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.5461, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.036382536382536385, | |
| "grad_norm": 0.25337180495262146, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.6029, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.036902286902286904, | |
| "grad_norm": 0.2999207079410553, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.5432, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.037422037422037424, | |
| "grad_norm": 0.3323523700237274, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.585, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.037941787941787944, | |
| "grad_norm": 0.3124600648880005, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.5428, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 0.30299338698387146, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.5492, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.03898128898128898, | |
| "grad_norm": 0.32373517751693726, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.5737, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03898128898128898, | |
| "eval_loss": 0.5234647989273071, | |
| "eval_runtime": 10.397, | |
| "eval_samples_per_second": 4.809, | |
| "eval_steps_per_second": 0.673, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0395010395010395, | |
| "grad_norm": 0.2775340974330902, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.5398, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.04002079002079002, | |
| "grad_norm": 0.34127601981163025, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.5863, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.04054054054054054, | |
| "grad_norm": 0.32936781644821167, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.5702, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.04106029106029106, | |
| "grad_norm": 0.32185012102127075, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.5604, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.04158004158004158, | |
| "grad_norm": 0.3725656270980835, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.5096, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0420997920997921, | |
| "grad_norm": 0.43758270144462585, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.6213, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04261954261954262, | |
| "grad_norm": 0.4397500157356262, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.5776, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.04313929313929314, | |
| "grad_norm": 0.41127029061317444, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.5965, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.04365904365904366, | |
| "grad_norm": 0.41310176253318787, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.5568, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.04417879417879418, | |
| "grad_norm": 0.5008036494255066, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.5604, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0446985446985447, | |
| "grad_norm": 0.5008141398429871, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.6194, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.04521829521829522, | |
| "grad_norm": 0.5280492901802063, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.5421, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.04573804573804574, | |
| "grad_norm": 0.509255588054657, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.5172, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.04625779625779626, | |
| "grad_norm": 0.5679823160171509, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.6475, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.04677754677754678, | |
| "grad_norm": 0.6964303851127625, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.6635, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0472972972972973, | |
| "grad_norm": 0.6682361960411072, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.6719, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.04781704781704782, | |
| "grad_norm": 0.6329060792922974, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.5602, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.04833679833679834, | |
| "grad_norm": 0.7174376249313354, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.5954, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.04885654885654886, | |
| "grad_norm": 0.8649759888648987, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.7054, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.04937629937629938, | |
| "grad_norm": 0.8587183356285095, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.7378, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.0498960498960499, | |
| "grad_norm": 0.9487538933753967, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.673, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.05041580041580042, | |
| "grad_norm": 0.9698479771614075, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.6394, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.05093555093555094, | |
| "grad_norm": 1.1705135107040405, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.7881, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.05145530145530146, | |
| "grad_norm": 1.147175908088684, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.8175, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.05197505197505198, | |
| "grad_norm": 1.5819910764694214, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.8187, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05197505197505198, | |
| "eval_loss": 0.5713622570037842, | |
| "eval_runtime": 10.7862, | |
| "eval_samples_per_second": 4.636, | |
| "eval_steps_per_second": 0.649, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0524948024948025, | |
| "grad_norm": 0.3077780604362488, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.3882, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.05301455301455302, | |
| "grad_norm": 0.33069512248039246, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.4347, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.05353430353430354, | |
| "grad_norm": 0.2965315580368042, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.4631, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 0.2445397824048996, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.5486, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.05457380457380458, | |
| "grad_norm": 0.24396640062332153, | |
| "learning_rate": 0.00015, | |
| "loss": 0.5298, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.0550935550935551, | |
| "grad_norm": 0.2391216903924942, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.5678, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.055613305613305616, | |
| "grad_norm": 0.2599236071109772, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.5262, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.056133056133056136, | |
| "grad_norm": 0.2846571207046509, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.5928, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.056652806652806656, | |
| "grad_norm": 0.23013561964035034, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.5225, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.057172557172557176, | |
| "grad_norm": 0.2311960905790329, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.5661, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.057692307692307696, | |
| "grad_norm": 0.2271488606929779, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.5381, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.058212058212058215, | |
| "grad_norm": 0.30388909578323364, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.5819, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.058731808731808735, | |
| "grad_norm": 0.23286861181259155, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.5441, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.059251559251559255, | |
| "grad_norm": 0.21719612181186676, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.5258, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.059771309771309775, | |
| "grad_norm": 0.23778563737869263, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.592, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.060291060291060294, | |
| "grad_norm": 0.25448745489120483, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.5558, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.060810810810810814, | |
| "grad_norm": 0.2358551174402237, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.5425, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.061330561330561334, | |
| "grad_norm": 0.2500148415565491, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.5688, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.061850311850311854, | |
| "grad_norm": 0.23617619276046753, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.569, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.062370062370062374, | |
| "grad_norm": 0.2460618019104004, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.5258, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0628898128898129, | |
| "grad_norm": 0.25035300850868225, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.5452, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.06340956340956341, | |
| "grad_norm": 0.2552037835121155, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.5386, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.06392931392931393, | |
| "grad_norm": 0.2568017244338989, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.5054, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.06444906444906445, | |
| "grad_norm": 0.3237874507904053, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.5206, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.06496881496881497, | |
| "grad_norm": 0.32453036308288574, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.6088, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06496881496881497, | |
| "eval_loss": 0.5060738325119019, | |
| "eval_runtime": 10.7588, | |
| "eval_samples_per_second": 4.647, | |
| "eval_steps_per_second": 0.651, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06548856548856549, | |
| "grad_norm": 0.33183586597442627, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.5469, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.06600831600831601, | |
| "grad_norm": 0.35012179613113403, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.597, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.06652806652806653, | |
| "grad_norm": 0.3140457570552826, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.5094, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.06704781704781705, | |
| "grad_norm": 0.34678980708122253, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.5487, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.06756756756756757, | |
| "grad_norm": 0.33957555890083313, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.5276, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06808731808731809, | |
| "grad_norm": 0.3753758370876312, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.5253, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.06860706860706861, | |
| "grad_norm": 0.36970919370651245, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.5681, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.06912681912681913, | |
| "grad_norm": 0.38359901309013367, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.5572, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.06964656964656965, | |
| "grad_norm": 0.40657931566238403, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.5439, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.07016632016632017, | |
| "grad_norm": 0.46938619017601013, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.6336, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.07068607068607069, | |
| "grad_norm": 0.5070523619651794, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.6577, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.07120582120582121, | |
| "grad_norm": 0.499677836894989, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.6595, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.07172557172557173, | |
| "grad_norm": 0.5089967250823975, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.6318, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.07224532224532225, | |
| "grad_norm": 0.5152573585510254, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.5942, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.07276507276507277, | |
| "grad_norm": 0.60390305519104, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.6321, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07328482328482329, | |
| "grad_norm": 0.6076339483261108, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.5815, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.07380457380457381, | |
| "grad_norm": 0.6375054121017456, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.6469, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.07432432432432433, | |
| "grad_norm": 0.6294693350791931, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.6006, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.07484407484407485, | |
| "grad_norm": 0.7831677794456482, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.5724, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.07536382536382537, | |
| "grad_norm": 0.7516241073608398, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.5826, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.07588357588357589, | |
| "grad_norm": 0.9946649074554443, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.7365, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.07640332640332641, | |
| "grad_norm": 0.8894773125648499, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.7055, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 1.0826866626739502, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.6749, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.07744282744282745, | |
| "grad_norm": 1.1890193223953247, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.7258, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.07796257796257797, | |
| "grad_norm": 1.688950538635254, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.8355, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07796257796257797, | |
| "eval_loss": 0.5096783638000488, | |
| "eval_runtime": 9.6989, | |
| "eval_samples_per_second": 5.155, | |
| "eval_steps_per_second": 0.722, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07848232848232849, | |
| "grad_norm": 0.22046735882759094, | |
| "learning_rate": 4.659698863221513e-05, | |
| "loss": 0.3254, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.079002079002079, | |
| "grad_norm": 0.2166861742734909, | |
| "learning_rate": 4.481448235912671e-05, | |
| "loss": 0.4457, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.07952182952182953, | |
| "grad_norm": 0.2074378877878189, | |
| "learning_rate": 4.306073275629044e-05, | |
| "loss": 0.5091, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.08004158004158005, | |
| "grad_norm": 0.221967875957489, | |
| "learning_rate": 4.133621928133665e-05, | |
| "loss": 0.4409, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.08056133056133057, | |
| "grad_norm": 0.20840375125408173, | |
| "learning_rate": 3.964141339903026e-05, | |
| "loss": 0.4149, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.08108108108108109, | |
| "grad_norm": 0.23525193333625793, | |
| "learning_rate": 3.797677845237696e-05, | |
| "loss": 0.4934, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.0816008316008316, | |
| "grad_norm": 0.25270870327949524, | |
| "learning_rate": 3.634276953594982e-05, | |
| "loss": 0.5205, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.08212058212058213, | |
| "grad_norm": 0.22861601412296295, | |
| "learning_rate": 3.473983337147118e-05, | |
| "loss": 0.4039, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.08264033264033264, | |
| "grad_norm": 0.2319110780954361, | |
| "learning_rate": 3.316840818568315e-05, | |
| "loss": 0.4785, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.08316008316008316, | |
| "grad_norm": 0.22803109884262085, | |
| "learning_rate": 3.162892359054098e-05, | |
| "loss": 0.486, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08367983367983368, | |
| "grad_norm": 0.24335117638111115, | |
| "learning_rate": 3.0121800465761293e-05, | |
| "loss": 0.4956, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.0841995841995842, | |
| "grad_norm": 0.23986086249351501, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 0.566, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.08471933471933472, | |
| "grad_norm": 0.24391090869903564, | |
| "learning_rate": 2.7206277796996144e-05, | |
| "loss": 0.5142, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.08523908523908524, | |
| "grad_norm": 0.29568424820899963, | |
| "learning_rate": 2.5798675327796993e-05, | |
| "loss": 0.6023, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.08575883575883576, | |
| "grad_norm": 0.2564331591129303, | |
| "learning_rate": 2.4425028260620715e-05, | |
| "loss": 0.5528, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.08627858627858628, | |
| "grad_norm": 0.2405325472354889, | |
| "learning_rate": 2.3085712136859668e-05, | |
| "loss": 0.4999, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.0867983367983368, | |
| "grad_norm": 0.2567991018295288, | |
| "learning_rate": 2.178109311216913e-05, | |
| "loss": 0.5486, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.08731808731808732, | |
| "grad_norm": 0.2838067412376404, | |
| "learning_rate": 2.0511527856363912e-05, | |
| "loss": 0.5459, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.08783783783783784, | |
| "grad_norm": 0.2707315683364868, | |
| "learning_rate": 1.927736345590839e-05, | |
| "loss": 0.5376, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.08835758835758836, | |
| "grad_norm": 0.26636192202568054, | |
| "learning_rate": 1.8078937319026654e-05, | |
| "loss": 0.535, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.08887733887733888, | |
| "grad_norm": 0.26214924454689026, | |
| "learning_rate": 1.6916577083458228e-05, | |
| "loss": 0.5322, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.0893970893970894, | |
| "grad_norm": 0.2562224566936493, | |
| "learning_rate": 1.579060052688548e-05, | |
| "loss": 0.5278, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.08991683991683992, | |
| "grad_norm": 0.30574294924736023, | |
| "learning_rate": 1.4701315480056164e-05, | |
| "loss": 0.5209, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.09043659043659044, | |
| "grad_norm": 0.3442355692386627, | |
| "learning_rate": 1.3649019742625623e-05, | |
| "loss": 0.5682, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.09095634095634096, | |
| "grad_norm": 0.2936060428619385, | |
| "learning_rate": 1.2634001001741373e-05, | |
| "loss": 0.5359, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.09095634095634096, | |
| "eval_loss": 0.4958566725254059, | |
| "eval_runtime": 10.7748, | |
| "eval_samples_per_second": 4.64, | |
| "eval_steps_per_second": 0.65, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.09147609147609148, | |
| "grad_norm": 0.34981048107147217, | |
| "learning_rate": 1.1656536753392287e-05, | |
| "loss": 0.543, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.091995841995842, | |
| "grad_norm": 0.38105377554893494, | |
| "learning_rate": 1.0716894226543953e-05, | |
| "loss": 0.573, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.09251559251559252, | |
| "grad_norm": 0.3455210328102112, | |
| "learning_rate": 9.815330310080887e-06, | |
| "loss": 0.4597, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.09303534303534304, | |
| "grad_norm": 0.388644814491272, | |
| "learning_rate": 8.952091482575824e-06, | |
| "loss": 0.5382, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.09355509355509356, | |
| "grad_norm": 0.3758420944213867, | |
| "learning_rate": 8.127413744904804e-06, | |
| "loss": 0.5452, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.09407484407484408, | |
| "grad_norm": 0.4773421585559845, | |
| "learning_rate": 7.34152255572697e-06, | |
| "loss": 0.5899, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.0945945945945946, | |
| "grad_norm": 0.3917699158191681, | |
| "learning_rate": 6.594632769846353e-06, | |
| "loss": 0.5736, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.09511434511434512, | |
| "grad_norm": 0.5945054292678833, | |
| "learning_rate": 5.886948579472778e-06, | |
| "loss": 0.629, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.09563409563409564, | |
| "grad_norm": 0.49390462040901184, | |
| "learning_rate": 5.218663458397715e-06, | |
| "loss": 0.5509, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.09615384615384616, | |
| "grad_norm": 0.4783254861831665, | |
| "learning_rate": 4.589960109100444e-06, | |
| "loss": 0.5791, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.09667359667359668, | |
| "grad_norm": 0.5506903529167175, | |
| "learning_rate": 4.001010412799138e-06, | |
| "loss": 0.52, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.0971933471933472, | |
| "grad_norm": 0.5402777194976807, | |
| "learning_rate": 3.451975382460109e-06, | |
| "loss": 0.6098, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.09771309771309772, | |
| "grad_norm": 0.6247908473014832, | |
| "learning_rate": 2.9430051187785962e-06, | |
| "loss": 0.5823, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.09823284823284824, | |
| "grad_norm": 0.6075006723403931, | |
| "learning_rate": 2.4742387691426445e-06, | |
| "loss": 0.6047, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.09875259875259876, | |
| "grad_norm": 0.6293641328811646, | |
| "learning_rate": 2.0458044895916513e-06, | |
| "loss": 0.648, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.09927234927234928, | |
| "grad_norm": 0.656559944152832, | |
| "learning_rate": 1.6578194097797258e-06, | |
| "loss": 0.5545, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.0997920997920998, | |
| "grad_norm": 0.6681039333343506, | |
| "learning_rate": 1.3103896009537207e-06, | |
| "loss": 0.6438, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.10031185031185032, | |
| "grad_norm": 0.9185191988945007, | |
| "learning_rate": 1.0036100469542786e-06, | |
| "loss": 0.625, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.10083160083160084, | |
| "grad_norm": 0.7245170474052429, | |
| "learning_rate": 7.375646182482875e-07, | |
| "loss": 0.6581, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.10135135135135136, | |
| "grad_norm": 0.8444747924804688, | |
| "learning_rate": 5.123260489995229e-07, | |
| "loss": 0.7302, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.10187110187110188, | |
| "grad_norm": 0.8954965472221375, | |
| "learning_rate": 3.2795591718381975e-07, | |
| "loss": 0.6679, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.1023908523908524, | |
| "grad_norm": 0.9438778758049011, | |
| "learning_rate": 1.8450462775428942e-07, | |
| "loss": 0.6426, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.10291060291060292, | |
| "grad_norm": 0.9339571595191956, | |
| "learning_rate": 8.201139886109264e-08, | |
| "loss": 0.7167, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.10343035343035344, | |
| "grad_norm": 1.101068377494812, | |
| "learning_rate": 2.0504251129649374e-08, | |
| "loss": 0.7554, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.10395010395010396, | |
| "grad_norm": 1.1291167736053467, | |
| "learning_rate": 0.0, | |
| "loss": 0.687, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10395010395010396, | |
| "eval_loss": 0.4919222295284271, | |
| "eval_runtime": 10.7529, | |
| "eval_samples_per_second": 4.65, | |
| "eval_steps_per_second": 0.651, | |
| "step": 200 | |
| } | |
| ], | |
| "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": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.350084764827648e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |