| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2249212775528565, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002249212775528565, | |
| "grad_norm": 11.230467796325684, | |
| "learning_rate": 0.0, | |
| "loss": 1.6122, | |
| "num_input_tokens_seen": 262144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000449842555105713, | |
| "grad_norm": 5.675804615020752, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.4745, | |
| "num_input_tokens_seen": 524288, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006747638326585695, | |
| "grad_norm": 5.168733596801758, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.2786, | |
| "num_input_tokens_seen": 786432, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000899685110211426, | |
| "grad_norm": 8.481163024902344, | |
| "learning_rate": 3e-06, | |
| "loss": 2.0106, | |
| "num_input_tokens_seen": 1048576, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011246063877642825, | |
| "grad_norm": 7.578442573547363, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.9709, | |
| "num_input_tokens_seen": 1310720, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001349527665317139, | |
| "grad_norm": 5.638476848602295, | |
| "learning_rate": 5e-06, | |
| "loss": 1.4529, | |
| "num_input_tokens_seen": 1572864, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015744489428699954, | |
| "grad_norm": 3.8255815505981445, | |
| "learning_rate": 6e-06, | |
| "loss": 0.9366, | |
| "num_input_tokens_seen": 1835008, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001799370220422852, | |
| "grad_norm": 3.63216495513916, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 1.2574, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0020242914979757085, | |
| "grad_norm": 4.869683265686035, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.9996, | |
| "num_input_tokens_seen": 2359296, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002249212775528565, | |
| "grad_norm": 2.704763889312744, | |
| "learning_rate": 9e-06, | |
| "loss": 1.4956, | |
| "num_input_tokens_seen": 2621440, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0024741340530814214, | |
| "grad_norm": 3.840841054916382, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4626, | |
| "num_input_tokens_seen": 2883584, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002699055330634278, | |
| "grad_norm": 2.593964099884033, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 1.8367, | |
| "num_input_tokens_seen": 3145728, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0029239766081871343, | |
| "grad_norm": 2.4662444591522217, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.6849, | |
| "num_input_tokens_seen": 3407872, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003148897885739991, | |
| "grad_norm": 3.482602596282959, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 1.948, | |
| "num_input_tokens_seen": 3670016, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0033738191632928477, | |
| "grad_norm": 8.98786735534668, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 1.3526, | |
| "num_input_tokens_seen": 3932160, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003598740440845704, | |
| "grad_norm": 1.5205129384994507, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.509, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0038236617183985606, | |
| "grad_norm": 1.9695186614990234, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.0624, | |
| "num_input_tokens_seen": 4456448, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004048582995951417, | |
| "grad_norm": 8.045424461364746, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 1.733, | |
| "num_input_tokens_seen": 4718592, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004273504273504274, | |
| "grad_norm": 1.50222909450531, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.8379, | |
| "num_input_tokens_seen": 4980736, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00449842555105713, | |
| "grad_norm": 1.0556864738464355, | |
| "learning_rate": 1.9e-05, | |
| "loss": 1.1625, | |
| "num_input_tokens_seen": 5242880, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004723346828609987, | |
| "grad_norm": 1.1621472835540771, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7579, | |
| "num_input_tokens_seen": 5505024, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004948268106162843, | |
| "grad_norm": 1.5123505592346191, | |
| "learning_rate": 2.1e-05, | |
| "loss": 1.2971, | |
| "num_input_tokens_seen": 5767168, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0051731893837157, | |
| "grad_norm": 2.0969297885894775, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 1.6729, | |
| "num_input_tokens_seen": 6029312, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005398110661268556, | |
| "grad_norm": 1.5837117433547974, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 2.0662, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005623031938821413, | |
| "grad_norm": 0.7958189249038696, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.8239, | |
| "num_input_tokens_seen": 6553600, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005847953216374269, | |
| "grad_norm": 0.8515807390213013, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.3535, | |
| "num_input_tokens_seen": 6815744, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006072874493927126, | |
| "grad_norm": 0.6959180235862732, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 1.298, | |
| "num_input_tokens_seen": 7077888, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006297795771479982, | |
| "grad_norm": 0.8492688536643982, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 1.4665, | |
| "num_input_tokens_seen": 7340032, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0065227170490328385, | |
| "grad_norm": 0.7743356823921204, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.9326, | |
| "num_input_tokens_seen": 7602176, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006747638326585695, | |
| "grad_norm": 0.6611963510513306, | |
| "learning_rate": 2.9e-05, | |
| "loss": 1.4156, | |
| "num_input_tokens_seen": 7864320, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006972559604138551, | |
| "grad_norm": 0.7195814251899719, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3418, | |
| "num_input_tokens_seen": 8126464, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007197480881691408, | |
| "grad_norm": 0.985824465751648, | |
| "learning_rate": 3.1e-05, | |
| "loss": 1.6413, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.007422402159244264, | |
| "grad_norm": 0.8015071749687195, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 2.1193, | |
| "num_input_tokens_seen": 8650752, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007647323436797121, | |
| "grad_norm": 0.6262965798377991, | |
| "learning_rate": 3.3e-05, | |
| "loss": 1.843, | |
| "num_input_tokens_seen": 8912896, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007872244714349977, | |
| "grad_norm": 0.8492324352264404, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 1.3536, | |
| "num_input_tokens_seen": 9175040, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008097165991902834, | |
| "grad_norm": 0.9331862926483154, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.6696, | |
| "num_input_tokens_seen": 9437184, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.008322087269455691, | |
| "grad_norm": 0.6202940344810486, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.4829, | |
| "num_input_tokens_seen": 9699328, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.008547008547008548, | |
| "grad_norm": 0.7566497921943665, | |
| "learning_rate": 3.7e-05, | |
| "loss": 1.6269, | |
| "num_input_tokens_seen": 9961472, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "grad_norm": 1.3238331079483032, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.2607, | |
| "num_input_tokens_seen": 10223616, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00899685110211426, | |
| "grad_norm": 0.6113777756690979, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 2.1251, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009221772379667117, | |
| "grad_norm": 0.4617583155632019, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6756, | |
| "num_input_tokens_seen": 10747904, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009446693657219974, | |
| "grad_norm": 0.6212331652641296, | |
| "learning_rate": 4.1e-05, | |
| "loss": 1.5033, | |
| "num_input_tokens_seen": 11010048, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009671614934772829, | |
| "grad_norm": 0.40810370445251465, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.3236, | |
| "num_input_tokens_seen": 11272192, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009896536212325686, | |
| "grad_norm": 0.5068628191947937, | |
| "learning_rate": 4.3e-05, | |
| "loss": 1.4815, | |
| "num_input_tokens_seen": 11534336, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.010121457489878543, | |
| "grad_norm": 0.40186524391174316, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.7775, | |
| "num_input_tokens_seen": 11796480, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0103463787674314, | |
| "grad_norm": 0.3428671956062317, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.2417, | |
| "num_input_tokens_seen": 12058624, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.010571300044984255, | |
| "grad_norm": 0.519368588924408, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.7107, | |
| "num_input_tokens_seen": 12320768, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010796221322537112, | |
| "grad_norm": 0.41630029678344727, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.9635, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.011021142600089968, | |
| "grad_norm": 0.3969324827194214, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.5873, | |
| "num_input_tokens_seen": 12845056, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.011246063877642825, | |
| "grad_norm": 0.358235239982605, | |
| "learning_rate": 4.9e-05, | |
| "loss": 1.8371, | |
| "num_input_tokens_seen": 13107200, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011470985155195682, | |
| "grad_norm": 0.40880703926086426, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3239, | |
| "num_input_tokens_seen": 13369344, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "grad_norm": 0.4353587329387665, | |
| "learning_rate": 5.1000000000000006e-05, | |
| "loss": 1.8723, | |
| "num_input_tokens_seen": 13631488, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.011920827710301394, | |
| "grad_norm": 0.4280511736869812, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.3009, | |
| "num_input_tokens_seen": 13893632, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.012145748987854251, | |
| "grad_norm": 0.318153440952301, | |
| "learning_rate": 5.300000000000001e-05, | |
| "loss": 1.4786, | |
| "num_input_tokens_seen": 14155776, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.012370670265407108, | |
| "grad_norm": 0.4111901819705963, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 1.8014, | |
| "num_input_tokens_seen": 14417920, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.012595591542959963, | |
| "grad_norm": 1.1243131160736084, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.3581, | |
| "num_input_tokens_seen": 14680064, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.01282051282051282, | |
| "grad_norm": 0.37373456358909607, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.6183, | |
| "num_input_tokens_seen": 14942208, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.013045434098065677, | |
| "grad_norm": 0.334053635597229, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 1.5023, | |
| "num_input_tokens_seen": 15204352, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.013270355375618534, | |
| "grad_norm": 0.4299324154853821, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.7593, | |
| "num_input_tokens_seen": 15466496, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.01349527665317139, | |
| "grad_norm": 0.3081894516944885, | |
| "learning_rate": 5.9e-05, | |
| "loss": 1.3975, | |
| "num_input_tokens_seen": 15728640, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.013720197930724246, | |
| "grad_norm": 0.38843464851379395, | |
| "learning_rate": 6e-05, | |
| "loss": 1.571, | |
| "num_input_tokens_seen": 15990784, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.013945119208277103, | |
| "grad_norm": 0.6251524090766907, | |
| "learning_rate": 6.1e-05, | |
| "loss": 1.6475, | |
| "num_input_tokens_seen": 16252928, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.01417004048582996, | |
| "grad_norm": 0.3833595812320709, | |
| "learning_rate": 6.2e-05, | |
| "loss": 1.7664, | |
| "num_input_tokens_seen": 16515072, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.014394961763382817, | |
| "grad_norm": 0.4029980003833771, | |
| "learning_rate": 6.3e-05, | |
| "loss": 1.8962, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.014619883040935672, | |
| "grad_norm": 0.5438060164451599, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 1.8436, | |
| "num_input_tokens_seen": 17039360, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.014844804318488529, | |
| "grad_norm": 0.41551777720451355, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.622, | |
| "num_input_tokens_seen": 17301504, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.015069725596041385, | |
| "grad_norm": 0.6011863350868225, | |
| "learning_rate": 6.6e-05, | |
| "loss": 1.3474, | |
| "num_input_tokens_seen": 17563648, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.015294646873594242, | |
| "grad_norm": 0.31412574648857117, | |
| "learning_rate": 6.7e-05, | |
| "loss": 1.6394, | |
| "num_input_tokens_seen": 17825792, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0155195681511471, | |
| "grad_norm": 0.3678301274776459, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 1.1412, | |
| "num_input_tokens_seen": 18087936, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.015744489428699954, | |
| "grad_norm": 0.4133774936199188, | |
| "learning_rate": 6.9e-05, | |
| "loss": 1.8902, | |
| "num_input_tokens_seen": 18350080, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.015969410706252813, | |
| "grad_norm": 0.5994505882263184, | |
| "learning_rate": 7e-05, | |
| "loss": 1.4304, | |
| "num_input_tokens_seen": 18612224, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.016194331983805668, | |
| "grad_norm": 0.40050116181373596, | |
| "learning_rate": 7.1e-05, | |
| "loss": 1.2177, | |
| "num_input_tokens_seen": 18874368, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.016419253261358523, | |
| "grad_norm": 0.4649305045604706, | |
| "learning_rate": 7.2e-05, | |
| "loss": 1.6078, | |
| "num_input_tokens_seen": 19136512, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.016644174538911382, | |
| "grad_norm": 0.42778080701828003, | |
| "learning_rate": 7.3e-05, | |
| "loss": 1.5667, | |
| "num_input_tokens_seen": 19398656, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.016869095816464237, | |
| "grad_norm": 0.44132548570632935, | |
| "learning_rate": 7.4e-05, | |
| "loss": 1.7146, | |
| "num_input_tokens_seen": 19660800, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 0.5165697932243347, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8052, | |
| "num_input_tokens_seen": 19922944, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.01731893837156995, | |
| "grad_norm": 0.32435211539268494, | |
| "learning_rate": 7.6e-05, | |
| "loss": 1.593, | |
| "num_input_tokens_seen": 20185088, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 0.39822056889533997, | |
| "learning_rate": 7.7e-05, | |
| "loss": 1.9039, | |
| "num_input_tokens_seen": 20447232, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.017768780926675665, | |
| "grad_norm": 0.3774968981742859, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 1.9257, | |
| "num_input_tokens_seen": 20709376, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.01799370220422852, | |
| "grad_norm": 0.29441991448402405, | |
| "learning_rate": 7.900000000000001e-05, | |
| "loss": 1.4104, | |
| "num_input_tokens_seen": 20971520, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.018218623481781375, | |
| "grad_norm": 0.31885433197021484, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1657, | |
| "num_input_tokens_seen": 21233664, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.018443544759334234, | |
| "grad_norm": 2.536576986312866, | |
| "learning_rate": 8.1e-05, | |
| "loss": 1.6162, | |
| "num_input_tokens_seen": 21495808, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.01866846603688709, | |
| "grad_norm": 0.42354825139045715, | |
| "learning_rate": 8.2e-05, | |
| "loss": 1.9433, | |
| "num_input_tokens_seen": 21757952, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.018893387314439947, | |
| "grad_norm": 0.33853453397750854, | |
| "learning_rate": 8.3e-05, | |
| "loss": 1.4269, | |
| "num_input_tokens_seen": 22020096, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.019118308591992803, | |
| "grad_norm": 0.3609357476234436, | |
| "learning_rate": 8.4e-05, | |
| "loss": 1.6874, | |
| "num_input_tokens_seen": 22282240, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.019343229869545658, | |
| "grad_norm": 0.4715583324432373, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.7668, | |
| "num_input_tokens_seen": 22544384, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.019568151147098516, | |
| "grad_norm": 0.4518505930900574, | |
| "learning_rate": 8.6e-05, | |
| "loss": 1.5703, | |
| "num_input_tokens_seen": 22806528, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.01979307242465137, | |
| "grad_norm": 0.30384761095046997, | |
| "learning_rate": 8.7e-05, | |
| "loss": 1.0741, | |
| "num_input_tokens_seen": 23068672, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.02001799370220423, | |
| "grad_norm": 0.2828017473220825, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 1.181, | |
| "num_input_tokens_seen": 23330816, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.020242914979757085, | |
| "grad_norm": 0.4779614806175232, | |
| "learning_rate": 8.900000000000001e-05, | |
| "loss": 1.3726, | |
| "num_input_tokens_seen": 23592960, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02046783625730994, | |
| "grad_norm": 0.37162265181541443, | |
| "learning_rate": 9e-05, | |
| "loss": 1.1992, | |
| "num_input_tokens_seen": 23855104, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0206927575348628, | |
| "grad_norm": 0.3957003653049469, | |
| "learning_rate": 9.1e-05, | |
| "loss": 1.9987, | |
| "num_input_tokens_seen": 24117248, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.020917678812415654, | |
| "grad_norm": 0.3890228271484375, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 1.7081, | |
| "num_input_tokens_seen": 24379392, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.02114260008996851, | |
| "grad_norm": 0.4864268898963928, | |
| "learning_rate": 9.300000000000001e-05, | |
| "loss": 1.7492, | |
| "num_input_tokens_seen": 24641536, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.021367521367521368, | |
| "grad_norm": 0.8580865263938904, | |
| "learning_rate": 9.4e-05, | |
| "loss": 1.896, | |
| "num_input_tokens_seen": 24903680, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.021592442645074223, | |
| "grad_norm": 0.3866703510284424, | |
| "learning_rate": 9.5e-05, | |
| "loss": 1.3134, | |
| "num_input_tokens_seen": 25165824, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.02181736392262708, | |
| "grad_norm": 0.46616268157958984, | |
| "learning_rate": 9.6e-05, | |
| "loss": 1.3536, | |
| "num_input_tokens_seen": 25427968, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.022042285200179937, | |
| "grad_norm": 0.33651959896087646, | |
| "learning_rate": 9.7e-05, | |
| "loss": 1.5113, | |
| "num_input_tokens_seen": 25690112, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.022267206477732792, | |
| "grad_norm": 0.6243886351585388, | |
| "learning_rate": 9.8e-05, | |
| "loss": 1.9306, | |
| "num_input_tokens_seen": 25952256, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.02249212775528565, | |
| "grad_norm": 0.3050474524497986, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 1.4151, | |
| "num_input_tokens_seen": 26214400, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.022717049032838506, | |
| "grad_norm": 0.32986557483673096, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6279, | |
| "num_input_tokens_seen": 26476544, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.022941970310391364, | |
| "grad_norm": 0.2438795268535614, | |
| "learning_rate": 9.999969538288952e-05, | |
| "loss": 1.107, | |
| "num_input_tokens_seen": 26738688, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.02316689158794422, | |
| "grad_norm": 0.36484190821647644, | |
| "learning_rate": 9.999878153526974e-05, | |
| "loss": 1.9403, | |
| "num_input_tokens_seen": 27000832, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 0.4290502071380615, | |
| "learning_rate": 9.999725846827562e-05, | |
| "loss": 1.6049, | |
| "num_input_tokens_seen": 27262976, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.023616734143049933, | |
| "grad_norm": 0.3903041183948517, | |
| "learning_rate": 9.999512620046522e-05, | |
| "loss": 1.5587, | |
| "num_input_tokens_seen": 27525120, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02384165542060279, | |
| "grad_norm": 0.3593505918979645, | |
| "learning_rate": 9.999238475781957e-05, | |
| "loss": 1.4838, | |
| "num_input_tokens_seen": 27787264, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.024066576698155647, | |
| "grad_norm": 0.3363569378852844, | |
| "learning_rate": 9.998903417374228e-05, | |
| "loss": 1.8302, | |
| "num_input_tokens_seen": 28049408, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.024291497975708502, | |
| "grad_norm": 0.8137016296386719, | |
| "learning_rate": 9.998507448905917e-05, | |
| "loss": 1.6889, | |
| "num_input_tokens_seen": 28311552, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.024516419253261357, | |
| "grad_norm": 0.3933553695678711, | |
| "learning_rate": 9.998050575201771e-05, | |
| "loss": 1.8229, | |
| "num_input_tokens_seen": 28573696, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.024741340530814216, | |
| "grad_norm": 0.414473295211792, | |
| "learning_rate": 9.997532801828658e-05, | |
| "loss": 1.5831, | |
| "num_input_tokens_seen": 28835840, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02496626180836707, | |
| "grad_norm": 0.2983182370662689, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.0271, | |
| "num_input_tokens_seen": 29097984, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.025191183085919926, | |
| "grad_norm": 0.3780648708343506, | |
| "learning_rate": 9.996314582053106e-05, | |
| "loss": 1.6247, | |
| "num_input_tokens_seen": 29360128, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.025416104363472785, | |
| "grad_norm": 0.3796830177307129, | |
| "learning_rate": 9.995614150494293e-05, | |
| "loss": 1.8959, | |
| "num_input_tokens_seen": 29622272, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "grad_norm": 0.43109461665153503, | |
| "learning_rate": 9.994852848953574e-05, | |
| "loss": 1.6373, | |
| "num_input_tokens_seen": 29884416, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.0258659469185785, | |
| "grad_norm": 0.4484831392765045, | |
| "learning_rate": 9.99403068670717e-05, | |
| "loss": 1.7273, | |
| "num_input_tokens_seen": 30146560, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.026090868196131354, | |
| "grad_norm": 0.37315282225608826, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 1.1327, | |
| "num_input_tokens_seen": 30408704, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 0.4303310513496399, | |
| "learning_rate": 9.992203820909906e-05, | |
| "loss": 1.628, | |
| "num_input_tokens_seen": 30670848, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.026540710751237068, | |
| "grad_norm": 0.4225418269634247, | |
| "learning_rate": 9.991199139618827e-05, | |
| "loss": 1.5496, | |
| "num_input_tokens_seen": 30932992, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.026765632028789923, | |
| "grad_norm": 0.7125269770622253, | |
| "learning_rate": 9.990133642141359e-05, | |
| "loss": 1.8195, | |
| "num_input_tokens_seen": 31195136, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.02699055330634278, | |
| "grad_norm": 0.4084630012512207, | |
| "learning_rate": 9.98900734146025e-05, | |
| "loss": 1.8634, | |
| "num_input_tokens_seen": 31457280, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.027215474583895637, | |
| "grad_norm": 0.441657692193985, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.5867, | |
| "num_input_tokens_seen": 31719424, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.027440395861448492, | |
| "grad_norm": 0.5232109427452087, | |
| "learning_rate": 9.986572386122291e-05, | |
| "loss": 1.9827, | |
| "num_input_tokens_seen": 31981568, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.02766531713900135, | |
| "grad_norm": 0.45924124121665955, | |
| "learning_rate": 9.985263761134602e-05, | |
| "loss": 1.3527, | |
| "num_input_tokens_seen": 32243712, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.027890238416554206, | |
| "grad_norm": 0.3332464396953583, | |
| "learning_rate": 9.983894392281237e-05, | |
| "loss": 1.3638, | |
| "num_input_tokens_seen": 32505856, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.028115159694107064, | |
| "grad_norm": 0.5264614224433899, | |
| "learning_rate": 9.982464296247522e-05, | |
| "loss": 1.2889, | |
| "num_input_tokens_seen": 32768000, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.02834008097165992, | |
| "grad_norm": 0.4572417736053467, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 1.3363, | |
| "num_input_tokens_seen": 33030144, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.028565002249212774, | |
| "grad_norm": 0.36014947295188904, | |
| "learning_rate": 9.979421993079852e-05, | |
| "loss": 1.6632, | |
| "num_input_tokens_seen": 33292288, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.028789923526765633, | |
| "grad_norm": 0.3196695148944855, | |
| "learning_rate": 9.977809823015401e-05, | |
| "loss": 1.5466, | |
| "num_input_tokens_seen": 33554432, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.029014844804318488, | |
| "grad_norm": 0.9590062499046326, | |
| "learning_rate": 9.976136999909156e-05, | |
| "loss": 1.8428, | |
| "num_input_tokens_seen": 33816576, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.029239766081871343, | |
| "grad_norm": 0.3693449795246124, | |
| "learning_rate": 9.974403544143941e-05, | |
| "loss": 1.145, | |
| "num_input_tokens_seen": 34078720, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.029464687359424202, | |
| "grad_norm": 0.3786580264568329, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.3506, | |
| "num_input_tokens_seen": 34340864, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.029689608636977057, | |
| "grad_norm": 0.5296582579612732, | |
| "learning_rate": 9.970754819861577e-05, | |
| "loss": 1.8347, | |
| "num_input_tokens_seen": 34603008, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.029914529914529916, | |
| "grad_norm": 1.3651492595672607, | |
| "learning_rate": 9.968839595802982e-05, | |
| "loss": 1.3145, | |
| "num_input_tokens_seen": 34865152, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.03013945119208277, | |
| "grad_norm": 0.4333643317222595, | |
| "learning_rate": 9.966863828001982e-05, | |
| "loss": 1.6935, | |
| "num_input_tokens_seen": 35127296, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.030364372469635626, | |
| "grad_norm": 0.33044588565826416, | |
| "learning_rate": 9.964827540532685e-05, | |
| "loss": 1.0532, | |
| "num_input_tokens_seen": 35389440, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.030589293747188485, | |
| "grad_norm": 0.4441980719566345, | |
| "learning_rate": 9.962730758206611e-05, | |
| "loss": 1.5709, | |
| "num_input_tokens_seen": 35651584, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.03081421502474134, | |
| "grad_norm": 0.7452576160430908, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 1.378, | |
| "num_input_tokens_seen": 35913728, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.0310391363022942, | |
| "grad_norm": 0.4860914945602417, | |
| "learning_rate": 9.958355811915451e-05, | |
| "loss": 1.6672, | |
| "num_input_tokens_seen": 36175872, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.03126405757984705, | |
| "grad_norm": 0.35408177971839905, | |
| "learning_rate": 9.956077701257709e-05, | |
| "loss": 1.4359, | |
| "num_input_tokens_seen": 36438016, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.03148897885739991, | |
| "grad_norm": 0.4450446665287018, | |
| "learning_rate": 9.953739202357218e-05, | |
| "loss": 1.8872, | |
| "num_input_tokens_seen": 36700160, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03171390013495277, | |
| "grad_norm": 0.3895055949687958, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.7616, | |
| "num_input_tokens_seen": 36962304, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.031938821412505626, | |
| "grad_norm": 0.32615330815315247, | |
| "learning_rate": 9.948881154538945e-05, | |
| "loss": 1.669, | |
| "num_input_tokens_seen": 37224448, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.03216374269005848, | |
| "grad_norm": 0.5241135954856873, | |
| "learning_rate": 9.946361664814943e-05, | |
| "loss": 2.1203, | |
| "num_input_tokens_seen": 37486592, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.032388663967611336, | |
| "grad_norm": 0.36470967531204224, | |
| "learning_rate": 9.94378190523503e-05, | |
| "loss": 1.2967, | |
| "num_input_tokens_seen": 37748736, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.032613585245164195, | |
| "grad_norm": 0.39427393674850464, | |
| "learning_rate": 9.941141907232765e-05, | |
| "loss": 1.8811, | |
| "num_input_tokens_seen": 38010880, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.03283850652271705, | |
| "grad_norm": 0.42225828766822815, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.4219, | |
| "num_input_tokens_seen": 38273024, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.033063427800269905, | |
| "grad_norm": 0.2807534337043762, | |
| "learning_rate": 9.93568132536494e-05, | |
| "loss": 1.3973, | |
| "num_input_tokens_seen": 38535168, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.033288349077822764, | |
| "grad_norm": 0.3927517533302307, | |
| "learning_rate": 9.932860808034848e-05, | |
| "loss": 1.2116, | |
| "num_input_tokens_seen": 38797312, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.033513270355375616, | |
| "grad_norm": 0.38540998101234436, | |
| "learning_rate": 9.929980185352526e-05, | |
| "loss": 1.3159, | |
| "num_input_tokens_seen": 39059456, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.033738191632928474, | |
| "grad_norm": 0.3624691963195801, | |
| "learning_rate": 9.927039492417452e-05, | |
| "loss": 1.5602, | |
| "num_input_tokens_seen": 39321600, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03396311291048133, | |
| "grad_norm": 0.3228714168071747, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.6376, | |
| "num_input_tokens_seen": 39583744, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 0.33287134766578674, | |
| "learning_rate": 9.92097803984621e-05, | |
| "loss": 1.565, | |
| "num_input_tokens_seen": 39845888, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.03441295546558704, | |
| "grad_norm": 1.5335997343063354, | |
| "learning_rate": 9.917857354066931e-05, | |
| "loss": 1.97, | |
| "num_input_tokens_seen": 40108032, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.0346378767431399, | |
| "grad_norm": 0.36973464488983154, | |
| "learning_rate": 9.914676745747772e-05, | |
| "loss": 2.0821, | |
| "num_input_tokens_seen": 40370176, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.03486279802069276, | |
| "grad_norm": 0.3719539940357208, | |
| "learning_rate": 9.911436253643445e-05, | |
| "loss": 2.0158, | |
| "num_input_tokens_seen": 40632320, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 0.4657575488090515, | |
| "learning_rate": 9.908135917238321e-05, | |
| "loss": 1.6059, | |
| "num_input_tokens_seen": 40894464, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.03531264057579847, | |
| "grad_norm": 0.3838348090648651, | |
| "learning_rate": 9.904775776745958e-05, | |
| "loss": 1.7565, | |
| "num_input_tokens_seen": 41156608, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.03553756185335133, | |
| "grad_norm": 0.29375481605529785, | |
| "learning_rate": 9.901355873108609e-05, | |
| "loss": 1.4024, | |
| "num_input_tokens_seen": 41418752, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.03576248313090418, | |
| "grad_norm": 0.30352264642715454, | |
| "learning_rate": 9.89787624799672e-05, | |
| "loss": 1.5428, | |
| "num_input_tokens_seen": 41680896, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.03598740440845704, | |
| "grad_norm": 0.49917876720428467, | |
| "learning_rate": 9.894336943808426e-05, | |
| "loss": 1.9028, | |
| "num_input_tokens_seen": 41943040, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0362123256860099, | |
| "grad_norm": 0.4412113428115845, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.9102, | |
| "num_input_tokens_seen": 42205184, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.03643724696356275, | |
| "grad_norm": 0.5141309499740601, | |
| "learning_rate": 9.88707947143048e-05, | |
| "loss": 1.961, | |
| "num_input_tokens_seen": 42467328, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.03666216824111561, | |
| "grad_norm": 0.423850953578949, | |
| "learning_rate": 9.88336139167084e-05, | |
| "loss": 1.4627, | |
| "num_input_tokens_seen": 42729472, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.03688708951866847, | |
| "grad_norm": 0.2972734570503235, | |
| "learning_rate": 9.879583809693738e-05, | |
| "loss": 1.5094, | |
| "num_input_tokens_seen": 42991616, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.037112010796221326, | |
| "grad_norm": 0.32651349902153015, | |
| "learning_rate": 9.875746771527816e-05, | |
| "loss": 1.2833, | |
| "num_input_tokens_seen": 43253760, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.03733693207377418, | |
| "grad_norm": 0.41867563128471375, | |
| "learning_rate": 9.871850323926177e-05, | |
| "loss": 1.5707, | |
| "num_input_tokens_seen": 43515904, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.037561853351327036, | |
| "grad_norm": 0.2959195375442505, | |
| "learning_rate": 9.867894514365802e-05, | |
| "loss": 1.092, | |
| "num_input_tokens_seen": 43778048, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.037786774628879895, | |
| "grad_norm": 0.25508689880371094, | |
| "learning_rate": 9.863879391046984e-05, | |
| "loss": 1.1717, | |
| "num_input_tokens_seen": 44040192, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.038011695906432746, | |
| "grad_norm": 0.2833406925201416, | |
| "learning_rate": 9.859805002892732e-05, | |
| "loss": 1.553, | |
| "num_input_tokens_seen": 44302336, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.038236617183985605, | |
| "grad_norm": 0.3006632328033447, | |
| "learning_rate": 9.855671399548181e-05, | |
| "loss": 1.2807, | |
| "num_input_tokens_seen": 44564480, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 0.37500298023223877, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.3634, | |
| "num_input_tokens_seen": 44826624, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.038686459739091315, | |
| "grad_norm": 0.4075554311275482, | |
| "learning_rate": 9.847226749475695e-05, | |
| "loss": 1.3434, | |
| "num_input_tokens_seen": 45088768, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.038911381016644174, | |
| "grad_norm": 0.5580770969390869, | |
| "learning_rate": 9.842915805643155e-05, | |
| "loss": 1.6386, | |
| "num_input_tokens_seen": 45350912, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.03913630229419703, | |
| "grad_norm": 0.2714264392852783, | |
| "learning_rate": 9.838545852409857e-05, | |
| "loss": 1.3893, | |
| "num_input_tokens_seen": 45613056, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.039361223571749884, | |
| "grad_norm": 0.2713785171508789, | |
| "learning_rate": 9.834116943022298e-05, | |
| "loss": 1.3902, | |
| "num_input_tokens_seen": 45875200, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03958614484930274, | |
| "grad_norm": 0.38365769386291504, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0312, | |
| "num_input_tokens_seen": 46137344, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.0398110661268556, | |
| "grad_norm": 0.3616935610771179, | |
| "learning_rate": 9.825082472361557e-05, | |
| "loss": 1.8365, | |
| "num_input_tokens_seen": 46399488, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.04003598740440846, | |
| "grad_norm": 0.3607868254184723, | |
| "learning_rate": 9.820477021170551e-05, | |
| "loss": 1.4036, | |
| "num_input_tokens_seen": 46661632, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.04026090868196131, | |
| "grad_norm": 0.3717537224292755, | |
| "learning_rate": 9.815812833988291e-05, | |
| "loss": 1.7118, | |
| "num_input_tokens_seen": 46923776, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.04048582995951417, | |
| "grad_norm": 0.30048802495002747, | |
| "learning_rate": 9.811089967646428e-05, | |
| "loss": 1.6556, | |
| "num_input_tokens_seen": 47185920, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04071075123706703, | |
| "grad_norm": 0.32800036668777466, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.1805, | |
| "num_input_tokens_seen": 47448064, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.04093567251461988, | |
| "grad_norm": 0.30880051851272583, | |
| "learning_rate": 9.801468428384716e-05, | |
| "loss": 1.2028, | |
| "num_input_tokens_seen": 47710208, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.04116059379217274, | |
| "grad_norm": 0.27152401208877563, | |
| "learning_rate": 9.796569872700288e-05, | |
| "loss": 1.5587, | |
| "num_input_tokens_seen": 47972352, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.0413855150697256, | |
| "grad_norm": 0.3760753870010376, | |
| "learning_rate": 9.791612872325667e-05, | |
| "loss": 1.9057, | |
| "num_input_tokens_seen": 48234496, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.04161043634727845, | |
| "grad_norm": 0.31716543436050415, | |
| "learning_rate": 9.786597487660337e-05, | |
| "loss": 1.7082, | |
| "num_input_tokens_seen": 48496640, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.04183535762483131, | |
| "grad_norm": 0.26593077182769775, | |
| "learning_rate": 9.781523779815179e-05, | |
| "loss": 1.1768, | |
| "num_input_tokens_seen": 48758784, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.04206027890238417, | |
| "grad_norm": 0.3927631080150604, | |
| "learning_rate": 9.776391810611718e-05, | |
| "loss": 0.8201, | |
| "num_input_tokens_seen": 49020928, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.04228520017993702, | |
| "grad_norm": 0.43734124302864075, | |
| "learning_rate": 9.771201642581385e-05, | |
| "loss": 1.6303, | |
| "num_input_tokens_seen": 49283072, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.04251012145748988, | |
| "grad_norm": 0.2875794768333435, | |
| "learning_rate": 9.765953338964735e-05, | |
| "loss": 1.373, | |
| "num_input_tokens_seen": 49545216, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.042735042735042736, | |
| "grad_norm": 0.2745586037635803, | |
| "learning_rate": 9.760646963710694e-05, | |
| "loss": 1.1446, | |
| "num_input_tokens_seen": 49807360, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.042959964012595594, | |
| "grad_norm": 0.5311657786369324, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.8471, | |
| "num_input_tokens_seen": 50069504, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.043184885290148446, | |
| "grad_norm": 0.33446601033210754, | |
| "learning_rate": 9.749860257623263e-05, | |
| "loss": 1.0208, | |
| "num_input_tokens_seen": 50331648, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.043409806567701305, | |
| "grad_norm": 0.40774935483932495, | |
| "learning_rate": 9.744380058222483e-05, | |
| "loss": 1.8295, | |
| "num_input_tokens_seen": 50593792, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.04363472784525416, | |
| "grad_norm": 0.41755542159080505, | |
| "learning_rate": 9.73884205004793e-05, | |
| "loss": 1.6565, | |
| "num_input_tokens_seen": 50855936, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.043859649122807015, | |
| "grad_norm": 0.3205357789993286, | |
| "learning_rate": 9.733246300578483e-05, | |
| "loss": 1.3403, | |
| "num_input_tokens_seen": 51118080, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.044084570400359874, | |
| "grad_norm": 0.3782586455345154, | |
| "learning_rate": 9.727592877996585e-05, | |
| "loss": 1.7666, | |
| "num_input_tokens_seen": 51380224, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.04430949167791273, | |
| "grad_norm": 0.2624562978744507, | |
| "learning_rate": 9.721881851187406e-05, | |
| "loss": 1.2044, | |
| "num_input_tokens_seen": 51642368, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.044534412955465584, | |
| "grad_norm": 0.38200780749320984, | |
| "learning_rate": 9.716113289738004e-05, | |
| "loss": 1.6842, | |
| "num_input_tokens_seen": 51904512, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.04475933423301844, | |
| "grad_norm": 0.5644131898880005, | |
| "learning_rate": 9.710287263936484e-05, | |
| "loss": 1.9484, | |
| "num_input_tokens_seen": 52166656, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.0449842555105713, | |
| "grad_norm": 0.8398867845535278, | |
| "learning_rate": 9.704403844771128e-05, | |
| "loss": 1.2177, | |
| "num_input_tokens_seen": 52428800, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04520917678812416, | |
| "grad_norm": 0.33354583382606506, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.4938, | |
| "num_input_tokens_seen": 52690944, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.04543409806567701, | |
| "grad_norm": 0.44575589895248413, | |
| "learning_rate": 9.69246511379778e-05, | |
| "loss": 1.5627, | |
| "num_input_tokens_seen": 52953088, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.04565901934322987, | |
| "grad_norm": 0.2522154450416565, | |
| "learning_rate": 9.686409947459458e-05, | |
| "loss": 1.3527, | |
| "num_input_tokens_seen": 53215232, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.04588394062078273, | |
| "grad_norm": 0.380891352891922, | |
| "learning_rate": 9.680297678694867e-05, | |
| "loss": 1.4753, | |
| "num_input_tokens_seen": 53477376, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.04610886189833558, | |
| "grad_norm": 0.40885552763938904, | |
| "learning_rate": 9.674128381980072e-05, | |
| "loss": 2.038, | |
| "num_input_tokens_seen": 53739520, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.04633378317588844, | |
| "grad_norm": 0.434465229511261, | |
| "learning_rate": 9.667902132486009e-05, | |
| "loss": 1.2983, | |
| "num_input_tokens_seen": 54001664, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.0465587044534413, | |
| "grad_norm": 0.45052337646484375, | |
| "learning_rate": 9.661619006077561e-05, | |
| "loss": 1.6453, | |
| "num_input_tokens_seen": 54263808, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 0.3216852843761444, | |
| "learning_rate": 9.655279079312642e-05, | |
| "loss": 2.0549, | |
| "num_input_tokens_seen": 54525952, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.04700854700854701, | |
| "grad_norm": 0.2805038094520569, | |
| "learning_rate": 9.648882429441257e-05, | |
| "loss": 1.3867, | |
| "num_input_tokens_seen": 54788096, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.04723346828609987, | |
| "grad_norm": 0.34908825159072876, | |
| "learning_rate": 9.642429134404569e-05, | |
| "loss": 1.3238, | |
| "num_input_tokens_seen": 55050240, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04745838956365272, | |
| "grad_norm": 0.42375364899635315, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.3649, | |
| "num_input_tokens_seen": 55312384, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.04768331084120558, | |
| "grad_norm": 0.300839364528656, | |
| "learning_rate": 9.629352924049975e-05, | |
| "loss": 1.7611, | |
| "num_input_tokens_seen": 55574528, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.047908232118758436, | |
| "grad_norm": 0.2923290431499481, | |
| "learning_rate": 9.622730168061567e-05, | |
| "loss": 1.8438, | |
| "num_input_tokens_seen": 55836672, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.048133153396311294, | |
| "grad_norm": 0.28767311573028564, | |
| "learning_rate": 9.616051085564906e-05, | |
| "loss": 1.3909, | |
| "num_input_tokens_seen": 56098816, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.048358074673864146, | |
| "grad_norm": 0.3666403293609619, | |
| "learning_rate": 9.609315757942503e-05, | |
| "loss": 1.6141, | |
| "num_input_tokens_seen": 56360960, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.048582995951417005, | |
| "grad_norm": 0.3564029932022095, | |
| "learning_rate": 9.602524267262203e-05, | |
| "loss": 1.5816, | |
| "num_input_tokens_seen": 56623104, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.04880791722896986, | |
| "grad_norm": 0.3815251588821411, | |
| "learning_rate": 9.595676696276172e-05, | |
| "loss": 0.868, | |
| "num_input_tokens_seen": 56885248, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.049032838506522715, | |
| "grad_norm": 0.4164994955062866, | |
| "learning_rate": 9.588773128419906e-05, | |
| "loss": 1.5668, | |
| "num_input_tokens_seen": 57147392, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.049257759784075573, | |
| "grad_norm": 0.46035948395729065, | |
| "learning_rate": 9.581813647811198e-05, | |
| "loss": 1.7141, | |
| "num_input_tokens_seen": 57409536, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.04948268106162843, | |
| "grad_norm": 0.27215978503227234, | |
| "learning_rate": 9.574798339249125e-05, | |
| "loss": 1.258, | |
| "num_input_tokens_seen": 57671680, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.049707602339181284, | |
| "grad_norm": 0.2921265959739685, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.3348, | |
| "num_input_tokens_seen": 57933824, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.04993252361673414, | |
| "grad_norm": 0.3707129955291748, | |
| "learning_rate": 9.560600580861365e-05, | |
| "loss": 1.6, | |
| "num_input_tokens_seen": 58195968, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.050157444894287, | |
| "grad_norm": 0.2560347616672516, | |
| "learning_rate": 9.553418304030886e-05, | |
| "loss": 1.0974, | |
| "num_input_tokens_seen": 58458112, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.05038236617183985, | |
| "grad_norm": 0.5279447436332703, | |
| "learning_rate": 9.546180545235344e-05, | |
| "loss": 1.5502, | |
| "num_input_tokens_seen": 58720256, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.05060728744939271, | |
| "grad_norm": 0.7471780776977539, | |
| "learning_rate": 9.538887392664544e-05, | |
| "loss": 1.6109, | |
| "num_input_tokens_seen": 58982400, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.05083220872694557, | |
| "grad_norm": 0.37901559472084045, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.4102, | |
| "num_input_tokens_seen": 59244544, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.05105713000449843, | |
| "grad_norm": 0.359701007604599, | |
| "learning_rate": 9.524135262330098e-05, | |
| "loss": 1.6576, | |
| "num_input_tokens_seen": 59506688, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 0.5791448354721069, | |
| "learning_rate": 9.516676464316505e-05, | |
| "loss": 1.618, | |
| "num_input_tokens_seen": 59768832, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.05150697255960414, | |
| "grad_norm": 0.37227171659469604, | |
| "learning_rate": 9.50916263202557e-05, | |
| "loss": 1.6593, | |
| "num_input_tokens_seen": 60030976, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.051731893837157, | |
| "grad_norm": 0.3083772659301758, | |
| "learning_rate": 9.501593857010969e-05, | |
| "loss": 1.5161, | |
| "num_input_tokens_seen": 60293120, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.05195681511470985, | |
| "grad_norm": 0.4033567011356354, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.4406, | |
| "num_input_tokens_seen": 60555264, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.05218173639226271, | |
| "grad_norm": 0.6083555221557617, | |
| "learning_rate": 9.486291848371643e-05, | |
| "loss": 1.9704, | |
| "num_input_tokens_seen": 60817408, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.052406657669815566, | |
| "grad_norm": 0.3136764168739319, | |
| "learning_rate": 9.478558801197065e-05, | |
| "loss": 1.7413, | |
| "num_input_tokens_seen": 61079552, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 0.34223246574401855, | |
| "learning_rate": 9.47077118419684e-05, | |
| "loss": 1.5267, | |
| "num_input_tokens_seen": 61341696, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.05285650022492128, | |
| "grad_norm": 0.41066691279411316, | |
| "learning_rate": 9.462929092260628e-05, | |
| "loss": 1.6758, | |
| "num_input_tokens_seen": 61603840, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.053081421502474135, | |
| "grad_norm": 0.27612629532814026, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 1.3576, | |
| "num_input_tokens_seen": 61865984, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.053306342780026994, | |
| "grad_norm": 0.30329903960227966, | |
| "learning_rate": 9.447081866456489e-05, | |
| "loss": 1.3036, | |
| "num_input_tokens_seen": 62128128, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.053531264057579846, | |
| "grad_norm": 0.5270364880561829, | |
| "learning_rate": 9.439076925682006e-05, | |
| "loss": 1.6004, | |
| "num_input_tokens_seen": 62390272, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.053756185335132704, | |
| "grad_norm": 0.4517534375190735, | |
| "learning_rate": 9.431017896156074e-05, | |
| "loss": 1.8651, | |
| "num_input_tokens_seen": 62652416, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.05398110661268556, | |
| "grad_norm": 0.3612141013145447, | |
| "learning_rate": 9.42290487607542e-05, | |
| "loss": 1.8875, | |
| "num_input_tokens_seen": 62914560, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.054206027890238415, | |
| "grad_norm": 0.3406079411506653, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.179, | |
| "num_input_tokens_seen": 63176704, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.05443094916779127, | |
| "grad_norm": 0.2817097306251526, | |
| "learning_rate": 9.40651726032496e-05, | |
| "loss": 1.1935, | |
| "num_input_tokens_seen": 63438848, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.05465587044534413, | |
| "grad_norm": 0.3395964205265045, | |
| "learning_rate": 9.398242864333083e-05, | |
| "loss": 1.3751, | |
| "num_input_tokens_seen": 63700992, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.054880791722896984, | |
| "grad_norm": 0.35885000228881836, | |
| "learning_rate": 9.389914877139903e-05, | |
| "loss": 1.6456, | |
| "num_input_tokens_seen": 63963136, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.05510571300044984, | |
| "grad_norm": 0.35253003239631653, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 1.2927, | |
| "num_input_tokens_seen": 64225280, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.0553306342780027, | |
| "grad_norm": 0.40748098492622375, | |
| "learning_rate": 9.373098535696979e-05, | |
| "loss": 1.6064, | |
| "num_input_tokens_seen": 64487424, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.41558191180229187, | |
| "learning_rate": 9.364610386349049e-05, | |
| "loss": 1.2848, | |
| "num_input_tokens_seen": 64749568, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.05578047683310841, | |
| "grad_norm": 0.47047188878059387, | |
| "learning_rate": 9.356069055600948e-05, | |
| "loss": 2.0327, | |
| "num_input_tokens_seen": 65011712, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.05600539811066127, | |
| "grad_norm": 0.3283202648162842, | |
| "learning_rate": 9.347474647526095e-05, | |
| "loss": 1.6587, | |
| "num_input_tokens_seen": 65273856, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.05623031938821413, | |
| "grad_norm": 0.36125075817108154, | |
| "learning_rate": 9.338827266844644e-05, | |
| "loss": 1.5436, | |
| "num_input_tokens_seen": 65536000, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05645524066576698, | |
| "grad_norm": 0.5791629552841187, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1172, | |
| "num_input_tokens_seen": 65798144, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.05668016194331984, | |
| "grad_norm": 0.28609782457351685, | |
| "learning_rate": 9.321374009768525e-05, | |
| "loss": 1.2856, | |
| "num_input_tokens_seen": 66060288, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.0569050832208727, | |
| "grad_norm": 0.31573817133903503, | |
| "learning_rate": 9.312568346036288e-05, | |
| "loss": 1.0411, | |
| "num_input_tokens_seen": 66322432, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.05713000449842555, | |
| "grad_norm": 0.3822273910045624, | |
| "learning_rate": 9.30371013501972e-05, | |
| "loss": 2.061, | |
| "num_input_tokens_seen": 66584576, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.05735492577597841, | |
| "grad_norm": 0.2760697901248932, | |
| "learning_rate": 9.294799484653323e-05, | |
| "loss": 1.1583, | |
| "num_input_tokens_seen": 66846720, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.057579847053531266, | |
| "grad_norm": 0.2954143285751343, | |
| "learning_rate": 9.285836503510562e-05, | |
| "loss": 1.4169, | |
| "num_input_tokens_seen": 67108864, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.05780476833108412, | |
| "grad_norm": 0.41817978024482727, | |
| "learning_rate": 9.276821300802534e-05, | |
| "loss": 1.6938, | |
| "num_input_tokens_seen": 67371008, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.058029689608636977, | |
| "grad_norm": 0.31263795495033264, | |
| "learning_rate": 9.267753986376637e-05, | |
| "loss": 1.3342, | |
| "num_input_tokens_seen": 67633152, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.058254610886189835, | |
| "grad_norm": 0.35715246200561523, | |
| "learning_rate": 9.258634670715238e-05, | |
| "loss": 1.6498, | |
| "num_input_tokens_seen": 67895296, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "grad_norm": 0.29079005122184753, | |
| "learning_rate": 9.249463464934321e-05, | |
| "loss": 1.745, | |
| "num_input_tokens_seen": 68157440, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.058704453441295545, | |
| "grad_norm": 0.27173885703086853, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.1948, | |
| "num_input_tokens_seen": 68419584, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.058929374718848404, | |
| "grad_norm": 0.5002535581588745, | |
| "learning_rate": 9.230965830637821e-05, | |
| "loss": 1.5592, | |
| "num_input_tokens_seen": 68681728, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.05915429599640126, | |
| "grad_norm": 0.38698941469192505, | |
| "learning_rate": 9.221639627510076e-05, | |
| "loss": 1.9042, | |
| "num_input_tokens_seen": 68943872, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.059379217273954114, | |
| "grad_norm": 0.4194246828556061, | |
| "learning_rate": 9.212261985035739e-05, | |
| "loss": 1.7498, | |
| "num_input_tokens_seen": 69206016, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.05960413855150697, | |
| "grad_norm": 0.4946896433830261, | |
| "learning_rate": 9.202833017478422e-05, | |
| "loss": 1.4112, | |
| "num_input_tokens_seen": 69468160, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.05982905982905983, | |
| "grad_norm": 0.3843882083892822, | |
| "learning_rate": 9.193352839727121e-05, | |
| "loss": 1.5777, | |
| "num_input_tokens_seen": 69730304, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.06005398110661268, | |
| "grad_norm": 0.4122903048992157, | |
| "learning_rate": 9.183821567294809e-05, | |
| "loss": 1.6184, | |
| "num_input_tokens_seen": 69992448, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.06027890238416554, | |
| "grad_norm": 0.3298034071922302, | |
| "learning_rate": 9.174239316317033e-05, | |
| "loss": 1.3252, | |
| "num_input_tokens_seen": 70254592, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.0605038236617184, | |
| "grad_norm": 0.40769994258880615, | |
| "learning_rate": 9.164606203550497e-05, | |
| "loss": 1.8223, | |
| "num_input_tokens_seen": 70516736, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.06072874493927125, | |
| "grad_norm": 0.6295496821403503, | |
| "learning_rate": 9.154922346371642e-05, | |
| "loss": 1.9614, | |
| "num_input_tokens_seen": 70778880, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.06095366621682411, | |
| "grad_norm": 1.0290013551712036, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 1.3658, | |
| "num_input_tokens_seen": 71041024, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.06117858749437697, | |
| "grad_norm": 0.3666732907295227, | |
| "learning_rate": 9.135402871372808e-05, | |
| "loss": 1.1264, | |
| "num_input_tokens_seen": 71303168, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.06140350877192982, | |
| "grad_norm": 0.35897478461265564, | |
| "learning_rate": 9.125567491391476e-05, | |
| "loss": 1.8494, | |
| "num_input_tokens_seen": 71565312, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.06162843004948268, | |
| "grad_norm": 0.3326916992664337, | |
| "learning_rate": 9.11568184267221e-05, | |
| "loss": 1.3847, | |
| "num_input_tokens_seen": 71827456, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.06185335132703554, | |
| "grad_norm": 0.5763710737228394, | |
| "learning_rate": 9.105746045668521e-05, | |
| "loss": 1.7974, | |
| "num_input_tokens_seen": 72089600, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.0620782726045884, | |
| "grad_norm": 0.2818114757537842, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.096, | |
| "num_input_tokens_seen": 72351744, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.06230319388214125, | |
| "grad_norm": 0.28481417894363403, | |
| "learning_rate": 9.085724491675642e-05, | |
| "loss": 1.5213, | |
| "num_input_tokens_seen": 72613888, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.0625281151596941, | |
| "grad_norm": 0.42331910133361816, | |
| "learning_rate": 9.075638978642771e-05, | |
| "loss": 1.3263, | |
| "num_input_tokens_seen": 72876032, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.06275303643724696, | |
| "grad_norm": 0.3151121437549591, | |
| "learning_rate": 9.065503805235138e-05, | |
| "loss": 1.7154, | |
| "num_input_tokens_seen": 73138176, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.06297795771479982, | |
| "grad_norm": 0.3964519202709198, | |
| "learning_rate": 9.055319094946633e-05, | |
| "loss": 1.4097, | |
| "num_input_tokens_seen": 73400320, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.06320287899235268, | |
| "grad_norm": 0.47799408435821533, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.468, | |
| "num_input_tokens_seen": 73662464, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.06342780026990553, | |
| "grad_norm": 0.30549415946006775, | |
| "learning_rate": 9.034801560719011e-05, | |
| "loss": 1.5141, | |
| "num_input_tokens_seen": 73924608, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.0636527215474584, | |
| "grad_norm": 0.34683847427368164, | |
| "learning_rate": 9.02446898677957e-05, | |
| "loss": 1.5819, | |
| "num_input_tokens_seen": 74186752, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.06387764282501125, | |
| "grad_norm": 0.36312419176101685, | |
| "learning_rate": 9.014087375955573e-05, | |
| "loss": 1.5719, | |
| "num_input_tokens_seen": 74448896, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.0641025641025641, | |
| "grad_norm": 0.3092777132987976, | |
| "learning_rate": 9.003656854743667e-05, | |
| "loss": 1.5536, | |
| "num_input_tokens_seen": 74711040, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.06432748538011696, | |
| "grad_norm": 0.32090455293655396, | |
| "learning_rate": 8.993177550236464e-05, | |
| "loss": 1.4896, | |
| "num_input_tokens_seen": 74973184, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.06455240665766981, | |
| "grad_norm": 0.5772414207458496, | |
| "learning_rate": 8.982649590120982e-05, | |
| "loss": 1.4706, | |
| "num_input_tokens_seen": 75235328, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.06477732793522267, | |
| "grad_norm": 0.3795754611492157, | |
| "learning_rate": 8.972073102677091e-05, | |
| "loss": 1.6924, | |
| "num_input_tokens_seen": 75497472, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.06500224921277553, | |
| "grad_norm": 0.3151102066040039, | |
| "learning_rate": 8.961448216775954e-05, | |
| "loss": 1.332, | |
| "num_input_tokens_seen": 75759616, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.06522717049032839, | |
| "grad_norm": 0.36022424697875977, | |
| "learning_rate": 8.950775061878453e-05, | |
| "loss": 1.7878, | |
| "num_input_tokens_seen": 76021760, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.06545209176788123, | |
| "grad_norm": 0.2842424809932709, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 0.8113, | |
| "num_input_tokens_seen": 76283904, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.0656770130454341, | |
| "grad_norm": 0.31418102979660034, | |
| "learning_rate": 8.92928446587701e-05, | |
| "loss": 1.2891, | |
| "num_input_tokens_seen": 76546048, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.06590193432298695, | |
| "grad_norm": 0.30106377601623535, | |
| "learning_rate": 8.9184672866292e-05, | |
| "loss": 1.4963, | |
| "num_input_tokens_seen": 76808192, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.06612685560053981, | |
| "grad_norm": 0.3311130106449127, | |
| "learning_rate": 8.907602362094094e-05, | |
| "loss": 1.3054, | |
| "num_input_tokens_seen": 77070336, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.06635177687809267, | |
| "grad_norm": 0.31675076484680176, | |
| "learning_rate": 8.896689824657372e-05, | |
| "loss": 1.4281, | |
| "num_input_tokens_seen": 77332480, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.06657669815564553, | |
| "grad_norm": 0.37820813059806824, | |
| "learning_rate": 8.885729807284856e-05, | |
| "loss": 1.7518, | |
| "num_input_tokens_seen": 77594624, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.06680161943319839, | |
| "grad_norm": 0.34154844284057617, | |
| "learning_rate": 8.874722443520899e-05, | |
| "loss": 1.5654, | |
| "num_input_tokens_seen": 77856768, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.06702654071075123, | |
| "grad_norm": 0.6786977052688599, | |
| "learning_rate": 8.863667867486756e-05, | |
| "loss": 2.1024, | |
| "num_input_tokens_seen": 78118912, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.06725146198830409, | |
| "grad_norm": 0.3483034372329712, | |
| "learning_rate": 8.852566213878947e-05, | |
| "loss": 1.5528, | |
| "num_input_tokens_seen": 78381056, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.06747638326585695, | |
| "grad_norm": 0.3642946779727936, | |
| "learning_rate": 8.841417617967618e-05, | |
| "loss": 1.6005, | |
| "num_input_tokens_seen": 78643200, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06770130454340981, | |
| "grad_norm": 0.6624205112457275, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.7759, | |
| "num_input_tokens_seen": 78905344, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.06792622582096267, | |
| "grad_norm": 0.39949551224708557, | |
| "learning_rate": 8.818980143173213e-05, | |
| "loss": 1.8293, | |
| "num_input_tokens_seen": 79167488, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.06815114709851552, | |
| "grad_norm": 0.3008061647415161, | |
| "learning_rate": 8.807691537683685e-05, | |
| "loss": 0.9926, | |
| "num_input_tokens_seen": 79429632, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.36931100487709045, | |
| "learning_rate": 8.796356536674403e-05, | |
| "loss": 1.5408, | |
| "num_input_tokens_seen": 79691776, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.06860098965362123, | |
| "grad_norm": 0.30574414134025574, | |
| "learning_rate": 8.784975278258783e-05, | |
| "loss": 1.5729, | |
| "num_input_tokens_seen": 79953920, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.06882591093117409, | |
| "grad_norm": 0.30279430747032166, | |
| "learning_rate": 8.773547901113862e-05, | |
| "loss": 1.507, | |
| "num_input_tokens_seen": 80216064, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.06905083220872694, | |
| "grad_norm": 0.4457983672618866, | |
| "learning_rate": 8.762074544478623e-05, | |
| "loss": 1.4149, | |
| "num_input_tokens_seen": 80478208, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.0692757534862798, | |
| "grad_norm": 0.4079945683479309, | |
| "learning_rate": 8.750555348152298e-05, | |
| "loss": 1.6881, | |
| "num_input_tokens_seen": 80740352, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.06950067476383266, | |
| "grad_norm": 0.34336355328559875, | |
| "learning_rate": 8.73899045249266e-05, | |
| "loss": 1.4145, | |
| "num_input_tokens_seen": 81002496, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.06972559604138552, | |
| "grad_norm": 0.31312716007232666, | |
| "learning_rate": 8.727379998414311e-05, | |
| "loss": 1.744, | |
| "num_input_tokens_seen": 81264640, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.06995051731893837, | |
| "grad_norm": 0.4761490225791931, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 1.5897, | |
| "num_input_tokens_seen": 81526784, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.29893723130226135, | |
| "learning_rate": 8.70402298143375e-05, | |
| "loss": 1.7682, | |
| "num_input_tokens_seen": 81788928, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.07040035987404408, | |
| "grad_norm": 0.3314342796802521, | |
| "learning_rate": 8.692276703129421e-05, | |
| "loss": 1.5067, | |
| "num_input_tokens_seen": 82051072, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.07062528115159694, | |
| "grad_norm": 0.24790574610233307, | |
| "learning_rate": 8.680485435598673e-05, | |
| "loss": 1.15, | |
| "num_input_tokens_seen": 82313216, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.0708502024291498, | |
| "grad_norm": 0.2895430326461792, | |
| "learning_rate": 8.668649322514382e-05, | |
| "loss": 1.3509, | |
| "num_input_tokens_seen": 82575360, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.07107512370670266, | |
| "grad_norm": 0.3589169681072235, | |
| "learning_rate": 8.656768508095853e-05, | |
| "loss": 1.8632, | |
| "num_input_tokens_seen": 82837504, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.07130004498425552, | |
| "grad_norm": 0.3887437582015991, | |
| "learning_rate": 8.644843137107059e-05, | |
| "loss": 1.395, | |
| "num_input_tokens_seen": 83099648, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.07152496626180836, | |
| "grad_norm": 0.37343311309814453, | |
| "learning_rate": 8.63287335485488e-05, | |
| "loss": 1.7117, | |
| "num_input_tokens_seen": 83361792, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.07174988753936122, | |
| "grad_norm": 0.3545985519886017, | |
| "learning_rate": 8.620859307187339e-05, | |
| "loss": 1.9533, | |
| "num_input_tokens_seen": 83623936, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.07197480881691408, | |
| "grad_norm": 0.38480547070503235, | |
| "learning_rate": 8.608801140491811e-05, | |
| "loss": 1.2177, | |
| "num_input_tokens_seen": 83886080, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.07219973009446694, | |
| "grad_norm": 0.27238497138023376, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.7272, | |
| "num_input_tokens_seen": 84148224, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.0724246513720198, | |
| "grad_norm": 0.3463023602962494, | |
| "learning_rate": 8.584553038252414e-05, | |
| "loss": 1.9201, | |
| "num_input_tokens_seen": 84410368, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.07264957264957266, | |
| "grad_norm": 0.4262174665927887, | |
| "learning_rate": 8.572363398164017e-05, | |
| "loss": 1.8208, | |
| "num_input_tokens_seen": 84672512, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.0728744939271255, | |
| "grad_norm": 0.2797011733055115, | |
| "learning_rate": 8.560130229954984e-05, | |
| "loss": 1.4258, | |
| "num_input_tokens_seen": 84934656, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.07309941520467836, | |
| "grad_norm": 0.3334251940250397, | |
| "learning_rate": 8.547853682682604e-05, | |
| "loss": 1.0541, | |
| "num_input_tokens_seen": 85196800, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.07332433648223122, | |
| "grad_norm": 0.2976478636264801, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3189, | |
| "num_input_tokens_seen": 85458944, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.07354925775978408, | |
| "grad_norm": 0.37758395075798035, | |
| "learning_rate": 8.523171049817974e-05, | |
| "loss": 1.5492, | |
| "num_input_tokens_seen": 85721088, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.07377417903733693, | |
| "grad_norm": 0.3429315388202667, | |
| "learning_rate": 8.510765264975813e-05, | |
| "loss": 1.0107, | |
| "num_input_tokens_seen": 85983232, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.07399910031488979, | |
| "grad_norm": 0.2990742027759552, | |
| "learning_rate": 8.498316702566828e-05, | |
| "loss": 1.4943, | |
| "num_input_tokens_seen": 86245376, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.07422402159244265, | |
| "grad_norm": 0.32602354884147644, | |
| "learning_rate": 8.485825514272824e-05, | |
| "loss": 1.5812, | |
| "num_input_tokens_seen": 86507520, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.0744489428699955, | |
| "grad_norm": 0.26363345980644226, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 1.3136, | |
| "num_input_tokens_seen": 86769664, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.07467386414754835, | |
| "grad_norm": 0.2116805911064148, | |
| "learning_rate": 8.460715869352035e-05, | |
| "loss": 1.2319, | |
| "num_input_tokens_seen": 87031808, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.07489878542510121, | |
| "grad_norm": 0.3987019956111908, | |
| "learning_rate": 8.44809771867835e-05, | |
| "loss": 1.5046, | |
| "num_input_tokens_seen": 87293952, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.07512370670265407, | |
| "grad_norm": 0.3598376214504242, | |
| "learning_rate": 8.435437554022115e-05, | |
| "loss": 1.9093, | |
| "num_input_tokens_seen": 87556096, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.07534862798020693, | |
| "grad_norm": 0.24704904854297638, | |
| "learning_rate": 8.422735529643444e-05, | |
| "loss": 1.0568, | |
| "num_input_tokens_seen": 87818240, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.07557354925775979, | |
| "grad_norm": 0.4237552881240845, | |
| "learning_rate": 8.409991800312493e-05, | |
| "loss": 1.9913, | |
| "num_input_tokens_seen": 88080384, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.07579847053531263, | |
| "grad_norm": 0.29798340797424316, | |
| "learning_rate": 8.397206521307584e-05, | |
| "loss": 1.1693, | |
| "num_input_tokens_seen": 88342528, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.07602339181286549, | |
| "grad_norm": 0.2940386235713959, | |
| "learning_rate": 8.384379848413304e-05, | |
| "loss": 1.3721, | |
| "num_input_tokens_seen": 88604672, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.07624831309041835, | |
| "grad_norm": 0.393265962600708, | |
| "learning_rate": 8.371511937918616e-05, | |
| "loss": 0.7533, | |
| "num_input_tokens_seen": 88866816, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.07647323436797121, | |
| "grad_norm": 0.36260786652565, | |
| "learning_rate": 8.358602946614951e-05, | |
| "loss": 1.481, | |
| "num_input_tokens_seen": 89128960, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.07669815564552407, | |
| "grad_norm": 0.3836679756641388, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.182, | |
| "num_input_tokens_seen": 89391104, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 0.3021415174007416, | |
| "learning_rate": 8.332662351247262e-05, | |
| "loss": 1.317, | |
| "num_input_tokens_seen": 89653248, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.07714799820062979, | |
| "grad_norm": 0.3135571777820587, | |
| "learning_rate": 8.319631063261209e-05, | |
| "loss": 1.4725, | |
| "num_input_tokens_seen": 89915392, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.07737291947818263, | |
| "grad_norm": 0.3524462580680847, | |
| "learning_rate": 8.306559326618259e-05, | |
| "loss": 1.8325, | |
| "num_input_tokens_seen": 90177536, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.07759784075573549, | |
| "grad_norm": 0.3361789584159851, | |
| "learning_rate": 8.293447300593402e-05, | |
| "loss": 1.4591, | |
| "num_input_tokens_seen": 90439680, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.07782276203328835, | |
| "grad_norm": 0.3886992335319519, | |
| "learning_rate": 8.280295144952536e-05, | |
| "loss": 1.2393, | |
| "num_input_tokens_seen": 90701824, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.0780476833108412, | |
| "grad_norm": 0.28349190950393677, | |
| "learning_rate": 8.267103019950529e-05, | |
| "loss": 1.7775, | |
| "num_input_tokens_seen": 90963968, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.07827260458839407, | |
| "grad_norm": 0.3164171874523163, | |
| "learning_rate": 8.253871086329255e-05, | |
| "loss": 1.268, | |
| "num_input_tokens_seen": 91226112, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.07849752586594692, | |
| "grad_norm": 0.9120920300483704, | |
| "learning_rate": 8.240599505315655e-05, | |
| "loss": 1.5009, | |
| "num_input_tokens_seen": 91488256, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.07872244714349977, | |
| "grad_norm": 0.398485392332077, | |
| "learning_rate": 8.227288438619754e-05, | |
| "loss": 1.5468, | |
| "num_input_tokens_seen": 91750400, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 0.27732348442077637, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.5131, | |
| "num_input_tokens_seen": 92012544, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.07917228969860549, | |
| "grad_norm": 0.3714882731437683, | |
| "learning_rate": 8.200548497424778e-05, | |
| "loss": 1.2599, | |
| "num_input_tokens_seen": 92274688, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.07939721097615834, | |
| "grad_norm": 0.48692452907562256, | |
| "learning_rate": 8.18711994874345e-05, | |
| "loss": 1.6234, | |
| "num_input_tokens_seen": 92536832, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.0796221322537112, | |
| "grad_norm": 0.6241424083709717, | |
| "learning_rate": 8.173652566011338e-05, | |
| "loss": 1.4543, | |
| "num_input_tokens_seen": 92798976, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.07984705353126406, | |
| "grad_norm": 0.29428744316101074, | |
| "learning_rate": 8.160146513324254e-05, | |
| "loss": 1.3101, | |
| "num_input_tokens_seen": 93061120, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.08007197480881692, | |
| "grad_norm": 0.28312620520591736, | |
| "learning_rate": 8.146601955249188e-05, | |
| "loss": 1.691, | |
| "num_input_tokens_seen": 93323264, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.08029689608636977, | |
| "grad_norm": 0.3287985920906067, | |
| "learning_rate": 8.133019056822304e-05, | |
| "loss": 1.4051, | |
| "num_input_tokens_seen": 93585408, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.08052181736392262, | |
| "grad_norm": 0.8355076909065247, | |
| "learning_rate": 8.119397983546932e-05, | |
| "loss": 0.8261, | |
| "num_input_tokens_seen": 93847552, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.08074673864147548, | |
| "grad_norm": 0.4442685544490814, | |
| "learning_rate": 8.105738901391552e-05, | |
| "loss": 1.9674, | |
| "num_input_tokens_seen": 94109696, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.08097165991902834, | |
| "grad_norm": 0.39171215891838074, | |
| "learning_rate": 8.09204197678777e-05, | |
| "loss": 1.4591, | |
| "num_input_tokens_seen": 94371840, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.0811965811965812, | |
| "grad_norm": 0.5869056582450867, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.6919, | |
| "num_input_tokens_seen": 94633984, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.08142150247413406, | |
| "grad_norm": 0.3079814910888672, | |
| "learning_rate": 8.064535268264883e-05, | |
| "loss": 1.2014, | |
| "num_input_tokens_seen": 94896128, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.0816464237516869, | |
| "grad_norm": 0.40882888436317444, | |
| "learning_rate": 8.05072581950634e-05, | |
| "loss": 2.0127, | |
| "num_input_tokens_seen": 95158272, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.08187134502923976, | |
| "grad_norm": 0.3157702088356018, | |
| "learning_rate": 8.036879198616434e-05, | |
| "loss": 1.5946, | |
| "num_input_tokens_seen": 95420416, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.08209626630679262, | |
| "grad_norm": 0.2747892439365387, | |
| "learning_rate": 8.022995574311876e-05, | |
| "loss": 1.3058, | |
| "num_input_tokens_seen": 95682560, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.08232118758434548, | |
| "grad_norm": 0.2914641499519348, | |
| "learning_rate": 8.009075115760243e-05, | |
| "loss": 1.3948, | |
| "num_input_tokens_seen": 95944704, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.08254610886189834, | |
| "grad_norm": 0.43341168761253357, | |
| "learning_rate": 7.99511799257793e-05, | |
| "loss": 1.923, | |
| "num_input_tokens_seen": 96206848, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.0827710301394512, | |
| "grad_norm": 0.3780982792377472, | |
| "learning_rate": 7.98112437482808e-05, | |
| "loss": 1.949, | |
| "num_input_tokens_seen": 96468992, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.08299595141700405, | |
| "grad_norm": 0.3152284622192383, | |
| "learning_rate": 7.967094433018508e-05, | |
| "loss": 1.8534, | |
| "num_input_tokens_seen": 96731136, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.0832208726945569, | |
| "grad_norm": 0.41052770614624023, | |
| "learning_rate": 7.953028338099627e-05, | |
| "loss": 1.5833, | |
| "num_input_tokens_seen": 96993280, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.08344579397210976, | |
| "grad_norm": 0.2482951134443283, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.9037, | |
| "num_input_tokens_seen": 97255424, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.08367071524966262, | |
| "grad_norm": 0.2243509441614151, | |
| "learning_rate": 7.924788374936078e-05, | |
| "loss": 1.1509, | |
| "num_input_tokens_seen": 97517568, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.08389563652721548, | |
| "grad_norm": 0.4592084288597107, | |
| "learning_rate": 7.910614850786448e-05, | |
| "loss": 1.454, | |
| "num_input_tokens_seen": 97779712, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.08412055780476833, | |
| "grad_norm": 0.46746399998664856, | |
| "learning_rate": 7.896405861713394e-05, | |
| "loss": 1.883, | |
| "num_input_tokens_seen": 98041856, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.08434547908232119, | |
| "grad_norm": 0.32724547386169434, | |
| "learning_rate": 7.882161580848967e-05, | |
| "loss": 1.892, | |
| "num_input_tokens_seen": 98304000, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.08457040035987404, | |
| "grad_norm": 0.3034023642539978, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 1.6046, | |
| "num_input_tokens_seen": 98566144, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.0847953216374269, | |
| "grad_norm": 0.3898322880268097, | |
| "learning_rate": 7.85356783842216e-05, | |
| "loss": 1.4225, | |
| "num_input_tokens_seen": 98828288, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.08502024291497975, | |
| "grad_norm": 0.3080570101737976, | |
| "learning_rate": 7.839218725265506e-05, | |
| "loss": 2.099, | |
| "num_input_tokens_seen": 99090432, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.08524516419253261, | |
| "grad_norm": 0.3034183084964752, | |
| "learning_rate": 7.82483501712469e-05, | |
| "loss": 2.0276, | |
| "num_input_tokens_seen": 99352576, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 0.2619307339191437, | |
| "learning_rate": 7.810416889260653e-05, | |
| "loss": 1.1334, | |
| "num_input_tokens_seen": 99614720, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.08569500674763833, | |
| "grad_norm": 0.31621718406677246, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.0219, | |
| "num_input_tokens_seen": 99876864, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.08591992802519119, | |
| "grad_norm": 0.3380356729030609, | |
| "learning_rate": 7.781478077501525e-05, | |
| "loss": 1.203, | |
| "num_input_tokens_seen": 100139008, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.08614484930274403, | |
| "grad_norm": 0.3040500581264496, | |
| "learning_rate": 7.766957746216721e-05, | |
| "loss": 1.4343, | |
| "num_input_tokens_seen": 100401152, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.08636977058029689, | |
| "grad_norm": 0.2802172899246216, | |
| "learning_rate": 7.752403700424979e-05, | |
| "loss": 1.6222, | |
| "num_input_tokens_seen": 100663296, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.08659469185784975, | |
| "grad_norm": 0.3306577503681183, | |
| "learning_rate": 7.737816117462752e-05, | |
| "loss": 1.8542, | |
| "num_input_tokens_seen": 100925440, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.08681961313540261, | |
| "grad_norm": 0.30289724469184875, | |
| "learning_rate": 7.723195175075136e-05, | |
| "loss": 1.3011, | |
| "num_input_tokens_seen": 101187584, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.08704453441295547, | |
| "grad_norm": 0.2980553209781647, | |
| "learning_rate": 7.7085410514137e-05, | |
| "loss": 1.6361, | |
| "num_input_tokens_seen": 101449728, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.08726945569050833, | |
| "grad_norm": 0.21399402618408203, | |
| "learning_rate": 7.693853925034315e-05, | |
| "loss": 1.1644, | |
| "num_input_tokens_seen": 101711872, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.08749437696806119, | |
| "grad_norm": 0.43986937403678894, | |
| "learning_rate": 7.679133974894983e-05, | |
| "loss": 1.8904, | |
| "num_input_tokens_seen": 101974016, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.08771929824561403, | |
| "grad_norm": 0.31275415420532227, | |
| "learning_rate": 7.66438138035365e-05, | |
| "loss": 2.0859, | |
| "num_input_tokens_seen": 102236160, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.08794421952316689, | |
| "grad_norm": 0.2997763454914093, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 1.5338, | |
| "num_input_tokens_seen": 102498304, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.08816914080071975, | |
| "grad_norm": 0.2745038866996765, | |
| "learning_rate": 7.634778977483389e-05, | |
| "loss": 1.0397, | |
| "num_input_tokens_seen": 102760448, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.0883940620782726, | |
| "grad_norm": 0.33330515027046204, | |
| "learning_rate": 7.619929529850397e-05, | |
| "loss": 1.5318, | |
| "num_input_tokens_seen": 103022592, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.08861898335582546, | |
| "grad_norm": 0.3642829656600952, | |
| "learning_rate": 7.605048159202883e-05, | |
| "loss": 1.4536, | |
| "num_input_tokens_seen": 103284736, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.08884390463337832, | |
| "grad_norm": 0.44559112191200256, | |
| "learning_rate": 7.590135046865651e-05, | |
| "loss": 1.888, | |
| "num_input_tokens_seen": 103546880, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.08906882591093117, | |
| "grad_norm": 0.3070293962955475, | |
| "learning_rate": 7.575190374550272e-05, | |
| "loss": 1.288, | |
| "num_input_tokens_seen": 103809024, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.08929374718848403, | |
| "grad_norm": 0.3520009517669678, | |
| "learning_rate": 7.560214324352858e-05, | |
| "loss": 1.3505, | |
| "num_input_tokens_seen": 104071168, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.08951866846603689, | |
| "grad_norm": 0.3868756890296936, | |
| "learning_rate": 7.545207078751857e-05, | |
| "loss": 1.9781, | |
| "num_input_tokens_seen": 104333312, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.08974358974358974, | |
| "grad_norm": 0.29797691106796265, | |
| "learning_rate": 7.530168820605818e-05, | |
| "loss": 1.5291, | |
| "num_input_tokens_seen": 104595456, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.0899685110211426, | |
| "grad_norm": 0.5068181157112122, | |
| "learning_rate": 7.515099733151177e-05, | |
| "loss": 1.6532, | |
| "num_input_tokens_seen": 104857600, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09019343229869546, | |
| "grad_norm": 0.4907291531562805, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.9233, | |
| "num_input_tokens_seen": 105119744, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.09041835357624832, | |
| "grad_norm": 0.26997601985931396, | |
| "learning_rate": 7.484869805137778e-05, | |
| "loss": 1.3426, | |
| "num_input_tokens_seen": 105381888, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.09064327485380116, | |
| "grad_norm": 0.31390297412872314, | |
| "learning_rate": 7.469709332921155e-05, | |
| "loss": 1.9555, | |
| "num_input_tokens_seen": 105644032, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.09086819613135402, | |
| "grad_norm": 0.23061801493167877, | |
| "learning_rate": 7.454518768075704e-05, | |
| "loss": 1.3306, | |
| "num_input_tokens_seen": 105906176, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.09109311740890688, | |
| "grad_norm": 0.2531485855579376, | |
| "learning_rate": 7.439298295693665e-05, | |
| "loss": 1.2648, | |
| "num_input_tokens_seen": 106168320, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.09131803868645974, | |
| "grad_norm": 0.3596000373363495, | |
| "learning_rate": 7.424048101231686e-05, | |
| "loss": 1.5472, | |
| "num_input_tokens_seen": 106430464, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.0915429599640126, | |
| "grad_norm": 0.2629176676273346, | |
| "learning_rate": 7.408768370508576e-05, | |
| "loss": 1.351, | |
| "num_input_tokens_seen": 106692608, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.09176788124156546, | |
| "grad_norm": 0.3580552637577057, | |
| "learning_rate": 7.393459289703035e-05, | |
| "loss": 1.7573, | |
| "num_input_tokens_seen": 106954752, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.0919928025191183, | |
| "grad_norm": 0.3975083827972412, | |
| "learning_rate": 7.378121045351378e-05, | |
| "loss": 1.6161, | |
| "num_input_tokens_seen": 107216896, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.09221772379667116, | |
| "grad_norm": 0.28635743260383606, | |
| "learning_rate": 7.362753824345272e-05, | |
| "loss": 1.38, | |
| "num_input_tokens_seen": 107479040, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.09244264507422402, | |
| "grad_norm": 0.37943241000175476, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 1.648, | |
| "num_input_tokens_seen": 107741184, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.09266756635177688, | |
| "grad_norm": 0.27485769987106323, | |
| "learning_rate": 7.331933201699457e-05, | |
| "loss": 1.5141, | |
| "num_input_tokens_seen": 108003328, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.09289248762932974, | |
| "grad_norm": 0.3419206440448761, | |
| "learning_rate": 7.316480175599309e-05, | |
| "loss": 1.2814, | |
| "num_input_tokens_seen": 108265472, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.0931174089068826, | |
| "grad_norm": 0.2868017554283142, | |
| "learning_rate": 7.300998923919259e-05, | |
| "loss": 1.7768, | |
| "num_input_tokens_seen": 108527616, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.09334233018443545, | |
| "grad_norm": 0.49058419466018677, | |
| "learning_rate": 7.285489635293472e-05, | |
| "loss": 1.9471, | |
| "num_input_tokens_seen": 108789760, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 0.26313817501068115, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.2005, | |
| "num_input_tokens_seen": 109051904, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.09379217273954116, | |
| "grad_norm": 0.3596467673778534, | |
| "learning_rate": 7.254387703447154e-05, | |
| "loss": 1.6942, | |
| "num_input_tokens_seen": 109314048, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.09401709401709402, | |
| "grad_norm": 0.2295425832271576, | |
| "learning_rate": 7.238795439193848e-05, | |
| "loss": 1.0696, | |
| "num_input_tokens_seen": 109576192, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.09424201529464687, | |
| "grad_norm": 0.2795259356498718, | |
| "learning_rate": 7.223175895924638e-05, | |
| "loss": 1.602, | |
| "num_input_tokens_seen": 109838336, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.09446693657219973, | |
| "grad_norm": 0.30435189604759216, | |
| "learning_rate": 7.207529263958726e-05, | |
| "loss": 1.6747, | |
| "num_input_tokens_seen": 110100480, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.09469185784975259, | |
| "grad_norm": 0.33711546659469604, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.7159, | |
| "num_input_tokens_seen": 110362624, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.09491677912730544, | |
| "grad_norm": 0.276668518781662, | |
| "learning_rate": 7.176155496861638e-05, | |
| "loss": 1.4798, | |
| "num_input_tokens_seen": 110624768, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.0951417004048583, | |
| "grad_norm": 0.46163132786750793, | |
| "learning_rate": 7.160428744009912e-05, | |
| "loss": 1.9584, | |
| "num_input_tokens_seen": 110886912, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.09536662168241115, | |
| "grad_norm": 0.2237766981124878, | |
| "learning_rate": 7.14467566701573e-05, | |
| "loss": 1.2179, | |
| "num_input_tokens_seen": 111149056, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.09559154295996401, | |
| "grad_norm": 0.40620312094688416, | |
| "learning_rate": 7.128896457825364e-05, | |
| "loss": 1.905, | |
| "num_input_tokens_seen": 111411200, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.09581646423751687, | |
| "grad_norm": 0.3632362186908722, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 1.6545, | |
| "num_input_tokens_seen": 111673344, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.09604138551506973, | |
| "grad_norm": 0.31227433681488037, | |
| "learning_rate": 7.097260412230886e-05, | |
| "loss": 1.7099, | |
| "num_input_tokens_seen": 111935488, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.09626630679262259, | |
| "grad_norm": 0.5832061767578125, | |
| "learning_rate": 7.081403961302006e-05, | |
| "loss": 2.1903, | |
| "num_input_tokens_seen": 112197632, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.09649122807017543, | |
| "grad_norm": 0.26980289816856384, | |
| "learning_rate": 7.06552214912271e-05, | |
| "loss": 1.3692, | |
| "num_input_tokens_seen": 112459776, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.09671614934772829, | |
| "grad_norm": 0.295695960521698, | |
| "learning_rate": 7.049615169207864e-05, | |
| "loss": 1.5653, | |
| "num_input_tokens_seen": 112721920, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.09694107062528115, | |
| "grad_norm": 0.34605613350868225, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 1.5236, | |
| "num_input_tokens_seen": 112984064, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.09716599190283401, | |
| "grad_norm": 0.274335652589798, | |
| "learning_rate": 7.017726481761951e-05, | |
| "loss": 1.356, | |
| "num_input_tokens_seen": 113246208, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.09739091318038687, | |
| "grad_norm": 0.3841763734817505, | |
| "learning_rate": 7.001745162784477e-05, | |
| "loss": 1.2775, | |
| "num_input_tokens_seen": 113508352, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.09761583445793973, | |
| "grad_norm": 0.38481906056404114, | |
| "learning_rate": 6.985739453173903e-05, | |
| "loss": 1.2148, | |
| "num_input_tokens_seen": 113770496, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.09784075573549257, | |
| "grad_norm": 0.5611907839775085, | |
| "learning_rate": 6.969709547954756e-05, | |
| "loss": 1.7437, | |
| "num_input_tokens_seen": 114032640, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.09806567701304543, | |
| "grad_norm": 0.3166041076183319, | |
| "learning_rate": 6.953655642446368e-05, | |
| "loss": 1.1888, | |
| "num_input_tokens_seen": 114294784, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.09829059829059829, | |
| "grad_norm": 0.31839755177497864, | |
| "learning_rate": 6.937577932260515e-05, | |
| "loss": 1.4222, | |
| "num_input_tokens_seen": 114556928, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.09851551956815115, | |
| "grad_norm": 0.34371787309646606, | |
| "learning_rate": 6.921476613299018e-05, | |
| "loss": 1.4687, | |
| "num_input_tokens_seen": 114819072, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.098740440845704, | |
| "grad_norm": 0.23597583174705505, | |
| "learning_rate": 6.905351881751372e-05, | |
| "loss": 0.9579, | |
| "num_input_tokens_seen": 115081216, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.09896536212325686, | |
| "grad_norm": 0.35465583205223083, | |
| "learning_rate": 6.889203934092336e-05, | |
| "loss": 1.765, | |
| "num_input_tokens_seen": 115343360, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.09919028340080972, | |
| "grad_norm": 0.6744416356086731, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.6383, | |
| "num_input_tokens_seen": 115605504, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.09941520467836257, | |
| "grad_norm": 0.27794769406318665, | |
| "learning_rate": 6.856839177751176e-05, | |
| "loss": 1.0429, | |
| "num_input_tokens_seen": 115867648, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.09964012595591543, | |
| "grad_norm": 0.3875754773616791, | |
| "learning_rate": 6.840622763423391e-05, | |
| "loss": 1.2993, | |
| "num_input_tokens_seen": 116129792, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.09986504723346828, | |
| "grad_norm": 0.32801422476768494, | |
| "learning_rate": 6.824383921688098e-05, | |
| "loss": 1.7491, | |
| "num_input_tokens_seen": 116391936, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.10008996851102114, | |
| "grad_norm": 0.46113693714141846, | |
| "learning_rate": 6.808122850410461e-05, | |
| "loss": 1.2563, | |
| "num_input_tokens_seen": 116654080, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.100314889788574, | |
| "grad_norm": 0.3193335235118866, | |
| "learning_rate": 6.7918397477265e-05, | |
| "loss": 1.5971, | |
| "num_input_tokens_seen": 116916224, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.10053981106612686, | |
| "grad_norm": 1.1562225818634033, | |
| "learning_rate": 6.775534812040685e-05, | |
| "loss": 1.1216, | |
| "num_input_tokens_seen": 117178368, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.1007647323436797, | |
| "grad_norm": 0.8205109238624573, | |
| "learning_rate": 6.759208242023509e-05, | |
| "loss": 2.271, | |
| "num_input_tokens_seen": 117440512, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.10098965362123256, | |
| "grad_norm": 0.23773515224456787, | |
| "learning_rate": 6.742860236609077e-05, | |
| "loss": 1.0239, | |
| "num_input_tokens_seen": 117702656, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.10121457489878542, | |
| "grad_norm": 0.4301644265651703, | |
| "learning_rate": 6.726490994992674e-05, | |
| "loss": 1.8923, | |
| "num_input_tokens_seen": 117964800, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.10143949617633828, | |
| "grad_norm": 0.4098486602306366, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.8184, | |
| "num_input_tokens_seen": 118226944, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.10166441745389114, | |
| "grad_norm": 0.4366002678871155, | |
| "learning_rate": 6.693689601226458e-05, | |
| "loss": 1.5744, | |
| "num_input_tokens_seen": 118489088, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.101889338731444, | |
| "grad_norm": 0.3160037100315094, | |
| "learning_rate": 6.677257848751277e-05, | |
| "loss": 0.9482, | |
| "num_input_tokens_seen": 118751232, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.10211426000899686, | |
| "grad_norm": 0.3118400573730469, | |
| "learning_rate": 6.660805659418516e-05, | |
| "loss": 1.3443, | |
| "num_input_tokens_seen": 119013376, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.1023391812865497, | |
| "grad_norm": 0.35094577074050903, | |
| "learning_rate": 6.644333233692916e-05, | |
| "loss": 1.5801, | |
| "num_input_tokens_seen": 119275520, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 1.0213929414749146, | |
| "learning_rate": 6.627840772285784e-05, | |
| "loss": 1.4641, | |
| "num_input_tokens_seen": 119537664, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.10278902384165542, | |
| "grad_norm": 0.3663333058357239, | |
| "learning_rate": 6.611328476152557e-05, | |
| "loss": 1.7087, | |
| "num_input_tokens_seen": 119799808, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.10301394511920828, | |
| "grad_norm": 0.2802916467189789, | |
| "learning_rate": 6.594796546490351e-05, | |
| "loss": 1.4823, | |
| "num_input_tokens_seen": 120061952, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.10323886639676114, | |
| "grad_norm": 0.2548016607761383, | |
| "learning_rate": 6.578245184735513e-05, | |
| "loss": 1.8112, | |
| "num_input_tokens_seen": 120324096, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.103463787674314, | |
| "grad_norm": 0.31046029925346375, | |
| "learning_rate": 6.561674592561163e-05, | |
| "loss": 1.293, | |
| "num_input_tokens_seen": 120586240, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.10368870895186684, | |
| "grad_norm": 0.23766155540943146, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.3626, | |
| "num_input_tokens_seen": 120848384, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.1039136302294197, | |
| "grad_norm": 0.7904400825500488, | |
| "learning_rate": 6.528476524815528e-05, | |
| "loss": 1.1202, | |
| "num_input_tokens_seen": 121110528, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.10413855150697256, | |
| "grad_norm": 0.34406253695487976, | |
| "learning_rate": 6.511849453752223e-05, | |
| "loss": 1.9536, | |
| "num_input_tokens_seen": 121372672, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.10436347278452542, | |
| "grad_norm": 0.3135795295238495, | |
| "learning_rate": 6.495203961280434e-05, | |
| "loss": 1.7353, | |
| "num_input_tokens_seen": 121634816, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.10458839406207827, | |
| "grad_norm": 0.29938840866088867, | |
| "learning_rate": 6.478540250220234e-05, | |
| "loss": 1.4572, | |
| "num_input_tokens_seen": 121896960, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.10481331533963113, | |
| "grad_norm": 0.35105428099632263, | |
| "learning_rate": 6.461858523613684e-05, | |
| "loss": 1.4649, | |
| "num_input_tokens_seen": 122159104, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.10503823661718399, | |
| "grad_norm": 0.4943515956401825, | |
| "learning_rate": 6.445158984722358e-05, | |
| "loss": 1.4881, | |
| "num_input_tokens_seen": 122421248, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.23201408982276917, | |
| "learning_rate": 6.428441837024868e-05, | |
| "loss": 0.8936, | |
| "num_input_tokens_seen": 122683392, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.1054880791722897, | |
| "grad_norm": 0.28961750864982605, | |
| "learning_rate": 6.411707284214384e-05, | |
| "loss": 1.311, | |
| "num_input_tokens_seen": 122945536, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.10571300044984255, | |
| "grad_norm": 0.41510218381881714, | |
| "learning_rate": 6.394955530196147e-05, | |
| "loss": 1.3483, | |
| "num_input_tokens_seen": 123207680, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.10593792172739541, | |
| "grad_norm": 0.6346913576126099, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 1.6187, | |
| "num_input_tokens_seen": 123469824, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.10616284300494827, | |
| "grad_norm": 0.271835058927536, | |
| "learning_rate": 6.361401235202872e-05, | |
| "loss": 1.2083, | |
| "num_input_tokens_seen": 123731968, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.10638776428250113, | |
| "grad_norm": 0.3942575752735138, | |
| "learning_rate": 6.344599103076329e-05, | |
| "loss": 1.8387, | |
| "num_input_tokens_seen": 123994112, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.10661268556005399, | |
| "grad_norm": 0.3236991763114929, | |
| "learning_rate": 6.327780587434044e-05, | |
| "loss": 1.1073, | |
| "num_input_tokens_seen": 124256256, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.10683760683760683, | |
| "grad_norm": 2.949082612991333, | |
| "learning_rate": 6.310945893204324e-05, | |
| "loss": 1.4841, | |
| "num_input_tokens_seen": 124518400, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.10706252811515969, | |
| "grad_norm": 0.35429275035858154, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.4407, | |
| "num_input_tokens_seen": 124780544, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.10728744939271255, | |
| "grad_norm": 0.28357911109924316, | |
| "learning_rate": 6.277228789678953e-05, | |
| "loss": 1.6392, | |
| "num_input_tokens_seen": 125042688, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.10751237067026541, | |
| "grad_norm": 0.2541661560535431, | |
| "learning_rate": 6.26034679121557e-05, | |
| "loss": 1.4364, | |
| "num_input_tokens_seen": 125304832, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.10773729194781827, | |
| "grad_norm": 0.29796111583709717, | |
| "learning_rate": 6.243449435824276e-05, | |
| "loss": 1.5294, | |
| "num_input_tokens_seen": 125566976, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.10796221322537113, | |
| "grad_norm": 0.3105159401893616, | |
| "learning_rate": 6.226536929394013e-05, | |
| "loss": 1.6884, | |
| "num_input_tokens_seen": 125829120, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.10818713450292397, | |
| "grad_norm": 0.3628823459148407, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.4418, | |
| "num_input_tokens_seen": 126091264, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.10841205578047683, | |
| "grad_norm": 0.26390042901039124, | |
| "learning_rate": 6.192667287892905e-05, | |
| "loss": 1.2891, | |
| "num_input_tokens_seen": 126353408, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.10863697705802969, | |
| "grad_norm": 0.8760519623756409, | |
| "learning_rate": 6.17571056551295e-05, | |
| "loss": 1.3306, | |
| "num_input_tokens_seen": 126615552, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.10886189833558255, | |
| "grad_norm": 0.5081838369369507, | |
| "learning_rate": 6.158739517470786e-05, | |
| "loss": 1.5474, | |
| "num_input_tokens_seen": 126877696, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.1090868196131354, | |
| "grad_norm": 0.3239939510822296, | |
| "learning_rate": 6.141754350553279e-05, | |
| "loss": 1.2702, | |
| "num_input_tokens_seen": 127139840, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.10931174089068826, | |
| "grad_norm": 0.3140064477920532, | |
| "learning_rate": 6.124755271719325e-05, | |
| "loss": 1.2157, | |
| "num_input_tokens_seen": 127401984, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.10953666216824112, | |
| "grad_norm": 0.5966137051582336, | |
| "learning_rate": 6.107742488097338e-05, | |
| "loss": 1.5058, | |
| "num_input_tokens_seen": 127664128, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.10976158344579397, | |
| "grad_norm": 0.24960365891456604, | |
| "learning_rate": 6.090716206982714e-05, | |
| "loss": 1.6896, | |
| "num_input_tokens_seen": 127926272, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.10998650472334683, | |
| "grad_norm": 0.22397436201572418, | |
| "learning_rate": 6.073676635835317e-05, | |
| "loss": 0.7462, | |
| "num_input_tokens_seen": 128188416, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.11021142600089968, | |
| "grad_norm": 0.304304301738739, | |
| "learning_rate": 6.056623982276944e-05, | |
| "loss": 1.5282, | |
| "num_input_tokens_seen": 128450560, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.11043634727845254, | |
| "grad_norm": 0.39173880219459534, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 1.2825, | |
| "num_input_tokens_seen": 128712704, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.1106612685560054, | |
| "grad_norm": 0.48953327536582947, | |
| "learning_rate": 6.0224802592089513e-05, | |
| "loss": 1.6419, | |
| "num_input_tokens_seen": 128974848, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.11088618983355826, | |
| "grad_norm": 0.29004979133605957, | |
| "learning_rate": 6.005389605729824e-05, | |
| "loss": 1.4553, | |
| "num_input_tokens_seen": 129236992, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.3265511691570282, | |
| "learning_rate": 5.988286701895631e-05, | |
| "loss": 1.0105, | |
| "num_input_tokens_seen": 129499136, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.11133603238866396, | |
| "grad_norm": 0.2783220708370209, | |
| "learning_rate": 5.97117175609986e-05, | |
| "loss": 1.4261, | |
| "num_input_tokens_seen": 129761280, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.11156095366621682, | |
| "grad_norm": 0.24198879301548004, | |
| "learning_rate": 5.9540449768827246e-05, | |
| "loss": 1.0924, | |
| "num_input_tokens_seen": 130023424, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.11178587494376968, | |
| "grad_norm": 0.43721655011177063, | |
| "learning_rate": 5.9369065729286245e-05, | |
| "loss": 1.5056, | |
| "num_input_tokens_seen": 130285568, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.11201079622132254, | |
| "grad_norm": 0.23090052604675293, | |
| "learning_rate": 5.9197567530636014e-05, | |
| "loss": 1.3582, | |
| "num_input_tokens_seen": 130547712, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.1122357174988754, | |
| "grad_norm": 0.2385416179895401, | |
| "learning_rate": 5.902595726252801e-05, | |
| "loss": 1.0288, | |
| "num_input_tokens_seen": 130809856, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.11246063877642826, | |
| "grad_norm": 0.3970996141433716, | |
| "learning_rate": 5.885423701597917e-05, | |
| "loss": 1.6201, | |
| "num_input_tokens_seen": 131072000, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1126855600539811, | |
| "grad_norm": 0.4963282644748688, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.6411, | |
| "num_input_tokens_seen": 131334144, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.11291048133153396, | |
| "grad_norm": 0.24954336881637573, | |
| "learning_rate": 5.851047495830163e-05, | |
| "loss": 1.082, | |
| "num_input_tokens_seen": 131596288, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.11313540260908682, | |
| "grad_norm": 0.26679301261901855, | |
| "learning_rate": 5.833843733580512e-05, | |
| "loss": 1.4837, | |
| "num_input_tokens_seen": 131858432, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.11336032388663968, | |
| "grad_norm": 0.2640249729156494, | |
| "learning_rate": 5.816629811208112e-05, | |
| "loss": 1.1814, | |
| "num_input_tokens_seen": 132120576, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.11358524516419254, | |
| "grad_norm": 1.2667120695114136, | |
| "learning_rate": 5.799405938459175e-05, | |
| "loss": 1.6477, | |
| "num_input_tokens_seen": 132382720, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.1138101664417454, | |
| "grad_norm": 0.25769752264022827, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 1.4024, | |
| "num_input_tokens_seen": 132644864, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.11403508771929824, | |
| "grad_norm": 0.34863802790641785, | |
| "learning_rate": 5.764929181420191e-05, | |
| "loss": 1.2889, | |
| "num_input_tokens_seen": 132907008, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.1142600089968511, | |
| "grad_norm": 0.2862359881401062, | |
| "learning_rate": 5.747676717218549e-05, | |
| "loss": 1.2924, | |
| "num_input_tokens_seen": 133169152, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.11448493027440396, | |
| "grad_norm": 0.2967565357685089, | |
| "learning_rate": 5.730415142812059e-05, | |
| "loss": 1.3798, | |
| "num_input_tokens_seen": 133431296, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.11470985155195682, | |
| "grad_norm": 0.26725533604621887, | |
| "learning_rate": 5.713144668527559e-05, | |
| "loss": 1.3552, | |
| "num_input_tokens_seen": 133693440, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.11493477282950967, | |
| "grad_norm": 0.3582031726837158, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 1.6537, | |
| "num_input_tokens_seen": 133955584, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.11515969410706253, | |
| "grad_norm": 0.2925718426704407, | |
| "learning_rate": 5.6785778621715225e-05, | |
| "loss": 1.1801, | |
| "num_input_tokens_seen": 134217728, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.11538461538461539, | |
| "grad_norm": 0.3479791581630707, | |
| "learning_rate": 5.661281951285613e-05, | |
| "loss": 1.3978, | |
| "num_input_tokens_seen": 134479872, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.11560953666216824, | |
| "grad_norm": 0.4140552282333374, | |
| "learning_rate": 5.643977982887815e-05, | |
| "loss": 1.566, | |
| "num_input_tokens_seen": 134742016, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.1158344579397211, | |
| "grad_norm": 0.3315996825695038, | |
| "learning_rate": 5.6266661678215216e-05, | |
| "loss": 1.6363, | |
| "num_input_tokens_seen": 135004160, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.11605937921727395, | |
| "grad_norm": 0.3189332187175751, | |
| "learning_rate": 5.6093467170257374e-05, | |
| "loss": 1.475, | |
| "num_input_tokens_seen": 135266304, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.11628430049482681, | |
| "grad_norm": 0.28339698910713196, | |
| "learning_rate": 5.5920198415325064e-05, | |
| "loss": 1.1303, | |
| "num_input_tokens_seen": 135528448, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.11650922177237967, | |
| "grad_norm": 0.22190435230731964, | |
| "learning_rate": 5.574685752464334e-05, | |
| "loss": 1.3556, | |
| "num_input_tokens_seen": 135790592, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.11673414304993253, | |
| "grad_norm": 0.3237098455429077, | |
| "learning_rate": 5.557344661031627e-05, | |
| "loss": 1.9832, | |
| "num_input_tokens_seen": 136052736, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "grad_norm": 0.3498755097389221, | |
| "learning_rate": 5.539996778530115e-05, | |
| "loss": 1.3795, | |
| "num_input_tokens_seen": 136314880, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.11718398560503823, | |
| "grad_norm": 0.2598389983177185, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.3192, | |
| "num_input_tokens_seen": 136577024, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.11740890688259109, | |
| "grad_norm": 0.21834932267665863, | |
| "learning_rate": 5.5052814859147315e-05, | |
| "loss": 1.005, | |
| "num_input_tokens_seen": 136839168, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.11763382816014395, | |
| "grad_norm": 0.4254181981086731, | |
| "learning_rate": 5.487914498795747e-05, | |
| "loss": 1.6294, | |
| "num_input_tokens_seen": 137101312, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.11785874943769681, | |
| "grad_norm": 0.41052109003067017, | |
| "learning_rate": 5.470541566592573e-05, | |
| "loss": 1.5199, | |
| "num_input_tokens_seen": 137363456, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.11808367071524967, | |
| "grad_norm": 0.21535776555538177, | |
| "learning_rate": 5.453162900988902e-05, | |
| "loss": 1.4093, | |
| "num_input_tokens_seen": 137625600, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.11830859199280253, | |
| "grad_norm": 0.2855823040008545, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 1.7458, | |
| "num_input_tokens_seen": 137887744, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.11853351327035537, | |
| "grad_norm": 0.4613701403141022, | |
| "learning_rate": 5.418389216661579e-05, | |
| "loss": 1.6014, | |
| "num_input_tokens_seen": 138149888, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.11875843454790823, | |
| "grad_norm": 0.290487676858902, | |
| "learning_rate": 5.4009946216442944e-05, | |
| "loss": 1.4064, | |
| "num_input_tokens_seen": 138412032, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.11898335582546109, | |
| "grad_norm": 0.3731476664543152, | |
| "learning_rate": 5.383595140634093e-05, | |
| "loss": 1.6748, | |
| "num_input_tokens_seen": 138674176, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.11920827710301395, | |
| "grad_norm": 0.26862120628356934, | |
| "learning_rate": 5.366190985638159e-05, | |
| "loss": 1.9398, | |
| "num_input_tokens_seen": 138936320, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1194331983805668, | |
| "grad_norm": 0.34171062707901, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 1.841, | |
| "num_input_tokens_seen": 139198464, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.11965811965811966, | |
| "grad_norm": 0.352012038230896, | |
| "learning_rate": 5.3313695020000024e-05, | |
| "loss": 1.7402, | |
| "num_input_tokens_seen": 139460608, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.11988304093567251, | |
| "grad_norm": 0.2644294202327728, | |
| "learning_rate": 5.313952597646568e-05, | |
| "loss": 1.4092, | |
| "num_input_tokens_seen": 139722752, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.12010796221322537, | |
| "grad_norm": 0.4258435368537903, | |
| "learning_rate": 5.296531867879809e-05, | |
| "loss": 1.6543, | |
| "num_input_tokens_seen": 139984896, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.12033288349077823, | |
| "grad_norm": 0.26844051480293274, | |
| "learning_rate": 5.279107524965819e-05, | |
| "loss": 0.9761, | |
| "num_input_tokens_seen": 140247040, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.12055780476833108, | |
| "grad_norm": 0.31205376982688904, | |
| "learning_rate": 5.26167978121472e-05, | |
| "loss": 2.008, | |
| "num_input_tokens_seen": 140509184, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.12078272604588394, | |
| "grad_norm": 0.6046432256698608, | |
| "learning_rate": 5.244248848978067e-05, | |
| "loss": 1.9272, | |
| "num_input_tokens_seen": 140771328, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.1210076473234368, | |
| "grad_norm": 0.33107465505599976, | |
| "learning_rate": 5.226814940646269e-05, | |
| "loss": 1.5775, | |
| "num_input_tokens_seen": 141033472, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.12123256860098966, | |
| "grad_norm": 0.3236624300479889, | |
| "learning_rate": 5.209378268645998e-05, | |
| "loss": 1.3686, | |
| "num_input_tokens_seen": 141295616, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.1214574898785425, | |
| "grad_norm": 0.31758353114128113, | |
| "learning_rate": 5.191939045437601e-05, | |
| "loss": 1.69, | |
| "num_input_tokens_seen": 141557760, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.12168241115609536, | |
| "grad_norm": 0.2803833484649658, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.334, | |
| "num_input_tokens_seen": 141819904, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.12190733243364822, | |
| "grad_norm": 0.4177348017692566, | |
| "learning_rate": 5.157053795390642e-05, | |
| "loss": 1.548, | |
| "num_input_tokens_seen": 142082048, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.12213225371120108, | |
| "grad_norm": 0.3638695180416107, | |
| "learning_rate": 5.139608193617845e-05, | |
| "loss": 1.4954, | |
| "num_input_tokens_seen": 142344192, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.12235717498875394, | |
| "grad_norm": 0.3036668598651886, | |
| "learning_rate": 5.1221608907632665e-05, | |
| "loss": 1.156, | |
| "num_input_tokens_seen": 142606336, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.1225820962663068, | |
| "grad_norm": 0.2818496525287628, | |
| "learning_rate": 5.104712099416785e-05, | |
| "loss": 1.4805, | |
| "num_input_tokens_seen": 142868480, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.12280701754385964, | |
| "grad_norm": 0.33742740750312805, | |
| "learning_rate": 5.0872620321864185e-05, | |
| "loss": 1.3688, | |
| "num_input_tokens_seen": 143130624, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.1230319388214125, | |
| "grad_norm": 0.3776567578315735, | |
| "learning_rate": 5.0698109016957274e-05, | |
| "loss": 1.1657, | |
| "num_input_tokens_seen": 143392768, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.12325686009896536, | |
| "grad_norm": 0.24142980575561523, | |
| "learning_rate": 5.052358920581229e-05, | |
| "loss": 1.3581, | |
| "num_input_tokens_seen": 143654912, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.12348178137651822, | |
| "grad_norm": 0.34365004301071167, | |
| "learning_rate": 5.034906301489808e-05, | |
| "loss": 1.4533, | |
| "num_input_tokens_seen": 143917056, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.12370670265407108, | |
| "grad_norm": 0.2355596125125885, | |
| "learning_rate": 5.017453257076119e-05, | |
| "loss": 1.2087, | |
| "num_input_tokens_seen": 144179200, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.12393162393162394, | |
| "grad_norm": 0.2048463225364685, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2536, | |
| "num_input_tokens_seen": 144441344, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.1241565452091768, | |
| "grad_norm": 0.3444722890853882, | |
| "learning_rate": 4.9825467429238834e-05, | |
| "loss": 1.3632, | |
| "num_input_tokens_seen": 144703488, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.12438146648672964, | |
| "grad_norm": 0.3106246292591095, | |
| "learning_rate": 4.965093698510193e-05, | |
| "loss": 1.3921, | |
| "num_input_tokens_seen": 144965632, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.1246063877642825, | |
| "grad_norm": 0.2710109055042267, | |
| "learning_rate": 4.947641079418773e-05, | |
| "loss": 1.2625, | |
| "num_input_tokens_seen": 145227776, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.12483130904183536, | |
| "grad_norm": 0.3017147183418274, | |
| "learning_rate": 4.9301890983042744e-05, | |
| "loss": 1.1092, | |
| "num_input_tokens_seen": 145489920, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.1250562303193882, | |
| "grad_norm": 0.6395849585533142, | |
| "learning_rate": 4.912737967813583e-05, | |
| "loss": 1.3323, | |
| "num_input_tokens_seen": 145752064, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.12528115159694106, | |
| "grad_norm": 0.5051564574241638, | |
| "learning_rate": 4.895287900583216e-05, | |
| "loss": 1.5473, | |
| "num_input_tokens_seen": 146014208, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.12550607287449392, | |
| "grad_norm": 0.3306078016757965, | |
| "learning_rate": 4.8778391092367346e-05, | |
| "loss": 1.532, | |
| "num_input_tokens_seen": 146276352, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.12573099415204678, | |
| "grad_norm": 0.31714704632759094, | |
| "learning_rate": 4.860391806382157e-05, | |
| "loss": 1.5618, | |
| "num_input_tokens_seen": 146538496, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.12595591542959964, | |
| "grad_norm": 0.28177952766418457, | |
| "learning_rate": 4.8429462046093585e-05, | |
| "loss": 1.8316, | |
| "num_input_tokens_seen": 146800640, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.1261808367071525, | |
| "grad_norm": 0.36294594407081604, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.1537, | |
| "num_input_tokens_seen": 147062784, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.12640575798470535, | |
| "grad_norm": 0.3346196115016937, | |
| "learning_rate": 4.8080609545624004e-05, | |
| "loss": 1.2673, | |
| "num_input_tokens_seen": 147324928, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.1266306792622582, | |
| "grad_norm": 0.236924409866333, | |
| "learning_rate": 4.790621731354003e-05, | |
| "loss": 1.114, | |
| "num_input_tokens_seen": 147587072, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.12685560053981107, | |
| "grad_norm": 0.30414605140686035, | |
| "learning_rate": 4.773185059353732e-05, | |
| "loss": 1.4022, | |
| "num_input_tokens_seen": 147849216, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.12708052181736393, | |
| "grad_norm": 0.27126508951187134, | |
| "learning_rate": 4.755751151021934e-05, | |
| "loss": 1.2234, | |
| "num_input_tokens_seen": 148111360, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.1273054430949168, | |
| "grad_norm": 0.27040398120880127, | |
| "learning_rate": 4.738320218785281e-05, | |
| "loss": 1.4393, | |
| "num_input_tokens_seen": 148373504, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.12753036437246965, | |
| "grad_norm": 0.3908785879611969, | |
| "learning_rate": 4.720892475034181e-05, | |
| "loss": 1.652, | |
| "num_input_tokens_seen": 148635648, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.1277552856500225, | |
| "grad_norm": 0.49319472908973694, | |
| "learning_rate": 4.703468132120193e-05, | |
| "loss": 1.7887, | |
| "num_input_tokens_seen": 148897792, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.12798020692757534, | |
| "grad_norm": 0.22037123143672943, | |
| "learning_rate": 4.6860474023534335e-05, | |
| "loss": 1.0219, | |
| "num_input_tokens_seen": 149159936, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.1282051282051282, | |
| "grad_norm": 0.28868696093559265, | |
| "learning_rate": 4.668630498000001e-05, | |
| "loss": 1.4268, | |
| "num_input_tokens_seen": 149422080, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.12843004948268105, | |
| "grad_norm": 0.3060884177684784, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 1.7064, | |
| "num_input_tokens_seen": 149684224, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.1286549707602339, | |
| "grad_norm": 0.4254710376262665, | |
| "learning_rate": 4.633809014361843e-05, | |
| "loss": 1.5773, | |
| "num_input_tokens_seen": 149946368, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.12887989203778677, | |
| "grad_norm": 0.30533093214035034, | |
| "learning_rate": 4.616404859365907e-05, | |
| "loss": 1.2379, | |
| "num_input_tokens_seen": 150208512, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.12910481331533963, | |
| "grad_norm": 0.2888457477092743, | |
| "learning_rate": 4.599005378355706e-05, | |
| "loss": 1.2059, | |
| "num_input_tokens_seen": 150470656, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.1293297345928925, | |
| "grad_norm": 0.2969624400138855, | |
| "learning_rate": 4.5816107833384234e-05, | |
| "loss": 1.5693, | |
| "num_input_tokens_seen": 150732800, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.12955465587044535, | |
| "grad_norm": 0.3754268288612366, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 1.4652, | |
| "num_input_tokens_seen": 150994944, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.1297795771479982, | |
| "grad_norm": 0.35749363899230957, | |
| "learning_rate": 4.5468370990111006e-05, | |
| "loss": 1.4626, | |
| "num_input_tokens_seen": 151257088, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.13000449842555106, | |
| "grad_norm": 0.2594490647315979, | |
| "learning_rate": 4.529458433407429e-05, | |
| "loss": 1.643, | |
| "num_input_tokens_seen": 151519232, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.13022941970310392, | |
| "grad_norm": 0.3177386522293091, | |
| "learning_rate": 4.512085501204253e-05, | |
| "loss": 1.86, | |
| "num_input_tokens_seen": 151781376, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.13045434098065678, | |
| "grad_norm": 0.3247101902961731, | |
| "learning_rate": 4.494718514085268e-05, | |
| "loss": 1.7022, | |
| "num_input_tokens_seen": 152043520, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.13067926225820964, | |
| "grad_norm": 0.2668783664703369, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.9691, | |
| "num_input_tokens_seen": 152305664, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.13090418353576247, | |
| "grad_norm": 0.30591410398483276, | |
| "learning_rate": 4.460003221469886e-05, | |
| "loss": 1.7169, | |
| "num_input_tokens_seen": 152567808, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.13112910481331533, | |
| "grad_norm": 0.22834749519824982, | |
| "learning_rate": 4.442655338968373e-05, | |
| "loss": 1.5456, | |
| "num_input_tokens_seen": 152829952, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.1313540260908682, | |
| "grad_norm": 0.24803908169269562, | |
| "learning_rate": 4.425314247535668e-05, | |
| "loss": 1.4185, | |
| "num_input_tokens_seen": 153092096, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 0.25347429513931274, | |
| "learning_rate": 4.407980158467495e-05, | |
| "loss": 1.5213, | |
| "num_input_tokens_seen": 153354240, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.1318038686459739, | |
| "grad_norm": 0.4988107979297638, | |
| "learning_rate": 4.390653282974264e-05, | |
| "loss": 1.4135, | |
| "num_input_tokens_seen": 153616384, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.13202878992352676, | |
| "grad_norm": 0.27117958664894104, | |
| "learning_rate": 4.373333832178478e-05, | |
| "loss": 1.5608, | |
| "num_input_tokens_seen": 153878528, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.13225371120107962, | |
| "grad_norm": 0.2566024363040924, | |
| "learning_rate": 4.356022017112187e-05, | |
| "loss": 1.3246, | |
| "num_input_tokens_seen": 154140672, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.13247863247863248, | |
| "grad_norm": 0.4258366525173187, | |
| "learning_rate": 4.3387180487143876e-05, | |
| "loss": 1.5825, | |
| "num_input_tokens_seen": 154402816, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.13270355375618534, | |
| "grad_norm": 0.3168386220932007, | |
| "learning_rate": 4.321422137828479e-05, | |
| "loss": 1.4613, | |
| "num_input_tokens_seen": 154664960, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.1329284750337382, | |
| "grad_norm": 0.34318843483924866, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 1.1464, | |
| "num_input_tokens_seen": 154927104, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.13315339631129106, | |
| "grad_norm": 0.321370005607605, | |
| "learning_rate": 4.2868553314724425e-05, | |
| "loss": 1.8339, | |
| "num_input_tokens_seen": 155189248, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.13337831758884391, | |
| "grad_norm": 0.25251543521881104, | |
| "learning_rate": 4.269584857187943e-05, | |
| "loss": 1.0068, | |
| "num_input_tokens_seen": 155451392, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.13360323886639677, | |
| "grad_norm": 0.32410669326782227, | |
| "learning_rate": 4.252323282781453e-05, | |
| "loss": 1.145, | |
| "num_input_tokens_seen": 155713536, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.1338281601439496, | |
| "grad_norm": 0.26194649934768677, | |
| "learning_rate": 4.23507081857981e-05, | |
| "loss": 1.398, | |
| "num_input_tokens_seen": 155975680, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.13405308142150246, | |
| "grad_norm": 0.40847936272621155, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 1.723, | |
| "num_input_tokens_seen": 156237824, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.13427800269905532, | |
| "grad_norm": 0.27586326003074646, | |
| "learning_rate": 4.2005940615408264e-05, | |
| "loss": 1.1967, | |
| "num_input_tokens_seen": 156499968, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.13450292397660818, | |
| "grad_norm": 0.2727280557155609, | |
| "learning_rate": 4.1833701887918904e-05, | |
| "loss": 1.429, | |
| "num_input_tokens_seen": 156762112, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.13472784525416104, | |
| "grad_norm": 0.3165155351161957, | |
| "learning_rate": 4.166156266419489e-05, | |
| "loss": 1.4949, | |
| "num_input_tokens_seen": 157024256, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.1349527665317139, | |
| "grad_norm": 0.3037717342376709, | |
| "learning_rate": 4.1489525041698387e-05, | |
| "loss": 1.777, | |
| "num_input_tokens_seen": 157286400, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.13517768780926676, | |
| "grad_norm": 0.26216423511505127, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.3849, | |
| "num_input_tokens_seen": 157548544, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.13540260908681961, | |
| "grad_norm": 0.4158977270126343, | |
| "learning_rate": 4.114576298402084e-05, | |
| "loss": 1.1767, | |
| "num_input_tokens_seen": 157810688, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.13562753036437247, | |
| "grad_norm": 0.23499810695648193, | |
| "learning_rate": 4.0974042737472006e-05, | |
| "loss": 1.1516, | |
| "num_input_tokens_seen": 158072832, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.13585245164192533, | |
| "grad_norm": 0.30113333463668823, | |
| "learning_rate": 4.080243246936399e-05, | |
| "loss": 1.5608, | |
| "num_input_tokens_seen": 158334976, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.1360773729194782, | |
| "grad_norm": 0.22452431917190552, | |
| "learning_rate": 4.063093427071376e-05, | |
| "loss": 1.2839, | |
| "num_input_tokens_seen": 158597120, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.13630229419703105, | |
| "grad_norm": 0.44184988737106323, | |
| "learning_rate": 4.045955023117276e-05, | |
| "loss": 1.3822, | |
| "num_input_tokens_seen": 158859264, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.1365272154745839, | |
| "grad_norm": 0.45626702904701233, | |
| "learning_rate": 4.028828243900141e-05, | |
| "loss": 1.4369, | |
| "num_input_tokens_seen": 159121408, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.2623542547225952, | |
| "learning_rate": 4.0117132981043693e-05, | |
| "loss": 1.2356, | |
| "num_input_tokens_seen": 159383552, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.1369770580296896, | |
| "grad_norm": 0.2714481055736542, | |
| "learning_rate": 3.9946103942701777e-05, | |
| "loss": 1.4336, | |
| "num_input_tokens_seen": 159645696, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.13720197930724246, | |
| "grad_norm": 0.4344947934150696, | |
| "learning_rate": 3.9775197407910485e-05, | |
| "loss": 1.3214, | |
| "num_input_tokens_seen": 159907840, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.13742690058479531, | |
| "grad_norm": 0.3765691816806793, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 1.3965, | |
| "num_input_tokens_seen": 160169984, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.13765182186234817, | |
| "grad_norm": 0.8579828143119812, | |
| "learning_rate": 3.943376017723057e-05, | |
| "loss": 1.4656, | |
| "num_input_tokens_seen": 160432128, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.13787674313990103, | |
| "grad_norm": 0.2760258913040161, | |
| "learning_rate": 3.926323364164684e-05, | |
| "loss": 1.7707, | |
| "num_input_tokens_seen": 160694272, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.1381016644174539, | |
| "grad_norm": 0.28735071420669556, | |
| "learning_rate": 3.9092837930172884e-05, | |
| "loss": 1.3462, | |
| "num_input_tokens_seen": 160956416, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.13832658569500675, | |
| "grad_norm": 0.26882848143577576, | |
| "learning_rate": 3.892257511902664e-05, | |
| "loss": 1.3798, | |
| "num_input_tokens_seen": 161218560, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.1385515069725596, | |
| "grad_norm": 0.7233993411064148, | |
| "learning_rate": 3.875244728280676e-05, | |
| "loss": 1.0232, | |
| "num_input_tokens_seen": 161480704, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.13877642825011247, | |
| "grad_norm": 0.3466539978981018, | |
| "learning_rate": 3.858245649446721e-05, | |
| "loss": 1.3842, | |
| "num_input_tokens_seen": 161742848, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.13900134952766532, | |
| "grad_norm": 0.24579237401485443, | |
| "learning_rate": 3.841260482529214e-05, | |
| "loss": 1.1613, | |
| "num_input_tokens_seen": 162004992, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.13922627080521818, | |
| "grad_norm": 0.2630798816680908, | |
| "learning_rate": 3.82428943448705e-05, | |
| "loss": 1.3372, | |
| "num_input_tokens_seen": 162267136, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.13945119208277104, | |
| "grad_norm": 0.27555617690086365, | |
| "learning_rate": 3.807332712107097e-05, | |
| "loss": 0.8722, | |
| "num_input_tokens_seen": 162529280, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.1396761133603239, | |
| "grad_norm": 0.8287885785102844, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.4182, | |
| "num_input_tokens_seen": 162791424, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.13990103463787673, | |
| "grad_norm": 0.28893017768859863, | |
| "learning_rate": 3.773463070605987e-05, | |
| "loss": 1.267, | |
| "num_input_tokens_seen": 163053568, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.1401259559154296, | |
| "grad_norm": 0.28053274750709534, | |
| "learning_rate": 3.756550564175727e-05, | |
| "loss": 1.3201, | |
| "num_input_tokens_seen": 163315712, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 0.25568142533302307, | |
| "learning_rate": 3.739653208784432e-05, | |
| "loss": 1.3894, | |
| "num_input_tokens_seen": 163577856, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.1405757984705353, | |
| "grad_norm": 0.3981480896472931, | |
| "learning_rate": 3.7227712103210486e-05, | |
| "loss": 1.3398, | |
| "num_input_tokens_seen": 163840000, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.14080071974808817, | |
| "grad_norm": 0.31518107652664185, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8814, | |
| "num_input_tokens_seen": 164102144, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.14102564102564102, | |
| "grad_norm": 1.6972969770431519, | |
| "learning_rate": 3.6890541067956776e-05, | |
| "loss": 1.6809, | |
| "num_input_tokens_seen": 164364288, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.14125056230319388, | |
| "grad_norm": 0.2689877152442932, | |
| "learning_rate": 3.6722194125659556e-05, | |
| "loss": 1.412, | |
| "num_input_tokens_seen": 164626432, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.14147548358074674, | |
| "grad_norm": 0.22733396291732788, | |
| "learning_rate": 3.655400896923672e-05, | |
| "loss": 1.2612, | |
| "num_input_tokens_seen": 164888576, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.1417004048582996, | |
| "grad_norm": 0.206431582570076, | |
| "learning_rate": 3.6385987647971285e-05, | |
| "loss": 1.1172, | |
| "num_input_tokens_seen": 165150720, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.14192532613585246, | |
| "grad_norm": 0.42070865631103516, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 1.642, | |
| "num_input_tokens_seen": 165412864, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.14215024741340532, | |
| "grad_norm": 0.3252650499343872, | |
| "learning_rate": 3.605044469803854e-05, | |
| "loss": 1.6878, | |
| "num_input_tokens_seen": 165675008, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.14237516869095818, | |
| "grad_norm": 0.24793250858783722, | |
| "learning_rate": 3.588292715785617e-05, | |
| "loss": 1.5085, | |
| "num_input_tokens_seen": 165937152, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.14260008996851103, | |
| "grad_norm": 0.2541254162788391, | |
| "learning_rate": 3.5715581629751326e-05, | |
| "loss": 1.0216, | |
| "num_input_tokens_seen": 166199296, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.14282501124606387, | |
| "grad_norm": 0.41134512424468994, | |
| "learning_rate": 3.554841015277641e-05, | |
| "loss": 1.6166, | |
| "num_input_tokens_seen": 166461440, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.14304993252361672, | |
| "grad_norm": 0.311408668756485, | |
| "learning_rate": 3.5381414763863166e-05, | |
| "loss": 1.1436, | |
| "num_input_tokens_seen": 166723584, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.14327485380116958, | |
| "grad_norm": 0.29306137561798096, | |
| "learning_rate": 3.5214597497797684e-05, | |
| "loss": 1.8737, | |
| "num_input_tokens_seen": 166985728, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.14349977507872244, | |
| "grad_norm": 0.6098542213439941, | |
| "learning_rate": 3.504796038719567e-05, | |
| "loss": 1.6415, | |
| "num_input_tokens_seen": 167247872, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.1437246963562753, | |
| "grad_norm": 0.26231542229652405, | |
| "learning_rate": 3.488150546247778e-05, | |
| "loss": 1.5265, | |
| "num_input_tokens_seen": 167510016, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.14394961763382816, | |
| "grad_norm": 0.3009147346019745, | |
| "learning_rate": 3.471523475184472e-05, | |
| "loss": 1.3886, | |
| "num_input_tokens_seen": 167772160, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.14417453891138102, | |
| "grad_norm": 0.31200405955314636, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.5625, | |
| "num_input_tokens_seen": 168034304, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.14439946018893388, | |
| "grad_norm": 0.3186989724636078, | |
| "learning_rate": 3.438325407438837e-05, | |
| "loss": 1.2634, | |
| "num_input_tokens_seen": 168296448, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.14462438146648673, | |
| "grad_norm": 0.28268516063690186, | |
| "learning_rate": 3.4217548152644885e-05, | |
| "loss": 1.0662, | |
| "num_input_tokens_seen": 168558592, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.1448493027440396, | |
| "grad_norm": 0.3295919597148895, | |
| "learning_rate": 3.40520345350965e-05, | |
| "loss": 1.787, | |
| "num_input_tokens_seen": 168820736, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.14507422402159245, | |
| "grad_norm": 0.47454962134361267, | |
| "learning_rate": 3.388671523847445e-05, | |
| "loss": 1.6098, | |
| "num_input_tokens_seen": 169082880, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.1452991452991453, | |
| "grad_norm": 0.37780699133872986, | |
| "learning_rate": 3.372159227714218e-05, | |
| "loss": 1.5719, | |
| "num_input_tokens_seen": 169345024, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.14552406657669817, | |
| "grad_norm": 0.39475154876708984, | |
| "learning_rate": 3.355666766307084e-05, | |
| "loss": 2.0794, | |
| "num_input_tokens_seen": 169607168, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.145748987854251, | |
| "grad_norm": 0.5949121713638306, | |
| "learning_rate": 3.339194340581485e-05, | |
| "loss": 1.1768, | |
| "num_input_tokens_seen": 169869312, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.14597390913180386, | |
| "grad_norm": 0.33387547731399536, | |
| "learning_rate": 3.322742151248725e-05, | |
| "loss": 1.5277, | |
| "num_input_tokens_seen": 170131456, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.14619883040935672, | |
| "grad_norm": 0.2769029140472412, | |
| "learning_rate": 3.3063103987735433e-05, | |
| "loss": 1.5336, | |
| "num_input_tokens_seen": 170393600, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.14642375168690958, | |
| "grad_norm": 0.2560354471206665, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 1.1709, | |
| "num_input_tokens_seen": 170655744, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.14664867296446243, | |
| "grad_norm": 0.4691326916217804, | |
| "learning_rate": 3.273509005007327e-05, | |
| "loss": 1.4694, | |
| "num_input_tokens_seen": 170917888, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.1468735942420153, | |
| "grad_norm": 0.2512299716472626, | |
| "learning_rate": 3.257139763390925e-05, | |
| "loss": 1.4209, | |
| "num_input_tokens_seen": 171180032, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.14709851551956815, | |
| "grad_norm": 0.36664241552352905, | |
| "learning_rate": 3.240791757976491e-05, | |
| "loss": 1.6359, | |
| "num_input_tokens_seen": 171442176, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.147323436797121, | |
| "grad_norm": 1.0399090051651, | |
| "learning_rate": 3.224465187959316e-05, | |
| "loss": 1.8301, | |
| "num_input_tokens_seen": 171704320, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.14754835807467387, | |
| "grad_norm": 0.38111740350723267, | |
| "learning_rate": 3.2081602522734986e-05, | |
| "loss": 2.0391, | |
| "num_input_tokens_seen": 171966464, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.14777327935222673, | |
| "grad_norm": 0.2596481740474701, | |
| "learning_rate": 3.1918771495895396e-05, | |
| "loss": 1.0399, | |
| "num_input_tokens_seen": 172228608, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.14799820062977959, | |
| "grad_norm": 0.24174773693084717, | |
| "learning_rate": 3.1756160783119016e-05, | |
| "loss": 1.0012, | |
| "num_input_tokens_seen": 172490752, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.14822312190733244, | |
| "grad_norm": 0.39571988582611084, | |
| "learning_rate": 3.1593772365766105e-05, | |
| "loss": 1.9274, | |
| "num_input_tokens_seen": 172752896, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.1484480431848853, | |
| "grad_norm": 0.2537073493003845, | |
| "learning_rate": 3.1431608222488275e-05, | |
| "loss": 1.1829, | |
| "num_input_tokens_seen": 173015040, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.14867296446243813, | |
| "grad_norm": 0.30034080147743225, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.5033, | |
| "num_input_tokens_seen": 173277184, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.148897885739991, | |
| "grad_norm": 0.46739694476127625, | |
| "learning_rate": 3.110796065907665e-05, | |
| "loss": 2.1391, | |
| "num_input_tokens_seen": 173539328, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.14912280701754385, | |
| "grad_norm": 0.2857431471347809, | |
| "learning_rate": 3.09464811824863e-05, | |
| "loss": 1.794, | |
| "num_input_tokens_seen": 173801472, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.1493477282950967, | |
| "grad_norm": 0.2435784935951233, | |
| "learning_rate": 3.078523386700982e-05, | |
| "loss": 1.3756, | |
| "num_input_tokens_seen": 174063616, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.14957264957264957, | |
| "grad_norm": 0.31536754965782166, | |
| "learning_rate": 3.062422067739485e-05, | |
| "loss": 1.7282, | |
| "num_input_tokens_seen": 174325760, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.14979757085020243, | |
| "grad_norm": 0.34157782793045044, | |
| "learning_rate": 3.046344357553632e-05, | |
| "loss": 1.6728, | |
| "num_input_tokens_seen": 174587904, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.15002249212775529, | |
| "grad_norm": 0.2535393238067627, | |
| "learning_rate": 3.0302904520452447e-05, | |
| "loss": 1.5404, | |
| "num_input_tokens_seen": 174850048, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.15024741340530814, | |
| "grad_norm": 0.40980955958366394, | |
| "learning_rate": 3.0142605468260978e-05, | |
| "loss": 1.3846, | |
| "num_input_tokens_seen": 175112192, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.150472334682861, | |
| "grad_norm": 0.28387653827667236, | |
| "learning_rate": 2.9982548372155263e-05, | |
| "loss": 1.5931, | |
| "num_input_tokens_seen": 175374336, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.15069725596041386, | |
| "grad_norm": 0.257438600063324, | |
| "learning_rate": 2.9822735182380496e-05, | |
| "loss": 1.2416, | |
| "num_input_tokens_seen": 175636480, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.15092217723796672, | |
| "grad_norm": 0.3665998578071594, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 1.0135, | |
| "num_input_tokens_seen": 175898624, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.15114709851551958, | |
| "grad_norm": 0.32949748635292053, | |
| "learning_rate": 2.950384830792136e-05, | |
| "loss": 1.6333, | |
| "num_input_tokens_seen": 176160768, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.15137201979307244, | |
| "grad_norm": 0.26206234097480774, | |
| "learning_rate": 2.934477850877292e-05, | |
| "loss": 1.581, | |
| "num_input_tokens_seen": 176422912, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.15159694107062527, | |
| "grad_norm": 0.24233995378017426, | |
| "learning_rate": 2.918596038697995e-05, | |
| "loss": 1.556, | |
| "num_input_tokens_seen": 176685056, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.15182186234817813, | |
| "grad_norm": 0.3522930145263672, | |
| "learning_rate": 2.9027395877691144e-05, | |
| "loss": 1.3463, | |
| "num_input_tokens_seen": 176947200, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.15204678362573099, | |
| "grad_norm": 0.25320544838905334, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 1.6151, | |
| "num_input_tokens_seen": 177209344, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.15227170490328384, | |
| "grad_norm": 0.3068138062953949, | |
| "learning_rate": 2.8711035421746367e-05, | |
| "loss": 1.5924, | |
| "num_input_tokens_seen": 177471488, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.1524966261808367, | |
| "grad_norm": 0.9334062337875366, | |
| "learning_rate": 2.8553243329842714e-05, | |
| "loss": 1.3416, | |
| "num_input_tokens_seen": 177733632, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.15272154745838956, | |
| "grad_norm": 0.34283843636512756, | |
| "learning_rate": 2.8395712559900877e-05, | |
| "loss": 1.313, | |
| "num_input_tokens_seen": 177995776, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.15294646873594242, | |
| "grad_norm": 0.36047711968421936, | |
| "learning_rate": 2.823844503138363e-05, | |
| "loss": 1.283, | |
| "num_input_tokens_seen": 178257920, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.15317139001349528, | |
| "grad_norm": 0.47825443744659424, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.3074, | |
| "num_input_tokens_seen": 178520064, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.15339631129104814, | |
| "grad_norm": 0.26862478256225586, | |
| "learning_rate": 2.7924707360412746e-05, | |
| "loss": 1.4357, | |
| "num_input_tokens_seen": 178782208, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.153621232568601, | |
| "grad_norm": 0.6874963641166687, | |
| "learning_rate": 2.776824104075364e-05, | |
| "loss": 1.9579, | |
| "num_input_tokens_seen": 179044352, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 0.32274290919303894, | |
| "learning_rate": 2.761204560806152e-05, | |
| "loss": 1.1533, | |
| "num_input_tokens_seen": 179306496, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.1540710751237067, | |
| "grad_norm": 0.5013816952705383, | |
| "learning_rate": 2.7456122965528475e-05, | |
| "loss": 2.2852, | |
| "num_input_tokens_seen": 179568640, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.15429599640125957, | |
| "grad_norm": 0.23807933926582336, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.9529, | |
| "num_input_tokens_seen": 179830784, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.1545209176788124, | |
| "grad_norm": 0.39833179116249084, | |
| "learning_rate": 2.7145103647065308e-05, | |
| "loss": 1.4946, | |
| "num_input_tokens_seen": 180092928, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.15474583895636526, | |
| "grad_norm": 0.2603168487548828, | |
| "learning_rate": 2.699001076080742e-05, | |
| "loss": 1.1422, | |
| "num_input_tokens_seen": 180355072, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.15497076023391812, | |
| "grad_norm": 0.2643228769302368, | |
| "learning_rate": 2.6835198244006927e-05, | |
| "loss": 1.402, | |
| "num_input_tokens_seen": 180617216, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.15519568151147098, | |
| "grad_norm": 0.3902268409729004, | |
| "learning_rate": 2.668066798300545e-05, | |
| "loss": 1.3769, | |
| "num_input_tokens_seen": 180879360, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.15542060278902384, | |
| "grad_norm": 0.22581857442855835, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.8756, | |
| "num_input_tokens_seen": 181141504, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 0.1556455240665767, | |
| "grad_norm": 0.2835070490837097, | |
| "learning_rate": 2.6372461756547306e-05, | |
| "loss": 1.6248, | |
| "num_input_tokens_seen": 181403648, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.15587044534412955, | |
| "grad_norm": 0.3780955374240875, | |
| "learning_rate": 2.6218789546486234e-05, | |
| "loss": 1.7845, | |
| "num_input_tokens_seen": 181665792, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.1560953666216824, | |
| "grad_norm": 0.2619756758213043, | |
| "learning_rate": 2.6065407102969664e-05, | |
| "loss": 1.6579, | |
| "num_input_tokens_seen": 181927936, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.15632028789923527, | |
| "grad_norm": 0.27253520488739014, | |
| "learning_rate": 2.591231629491423e-05, | |
| "loss": 1.732, | |
| "num_input_tokens_seen": 182190080, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.15654520917678813, | |
| "grad_norm": 0.5601329207420349, | |
| "learning_rate": 2.575951898768315e-05, | |
| "loss": 1.2634, | |
| "num_input_tokens_seen": 182452224, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.156770130454341, | |
| "grad_norm": 0.19660979509353638, | |
| "learning_rate": 2.560701704306336e-05, | |
| "loss": 1.0427, | |
| "num_input_tokens_seen": 182714368, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 0.15699505173189385, | |
| "grad_norm": 0.38262882828712463, | |
| "learning_rate": 2.545481231924296e-05, | |
| "loss": 1.6951, | |
| "num_input_tokens_seen": 182976512, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.1572199730094467, | |
| "grad_norm": 0.25855690240859985, | |
| "learning_rate": 2.5302906670788462e-05, | |
| "loss": 1.2998, | |
| "num_input_tokens_seen": 183238656, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.15744489428699954, | |
| "grad_norm": 0.3618425726890564, | |
| "learning_rate": 2.5151301948622237e-05, | |
| "loss": 1.4474, | |
| "num_input_tokens_seen": 183500800, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.1576698155645524, | |
| "grad_norm": 0.2380896806716919, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1, | |
| "num_input_tokens_seen": 183762944, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 0.27352097630500793, | |
| "learning_rate": 2.4849002668488245e-05, | |
| "loss": 1.2378, | |
| "num_input_tokens_seen": 184025088, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.1581196581196581, | |
| "grad_norm": 0.241080641746521, | |
| "learning_rate": 2.469831179394182e-05, | |
| "loss": 1.6727, | |
| "num_input_tokens_seen": 184287232, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 0.15834457939721097, | |
| "grad_norm": 0.5239187479019165, | |
| "learning_rate": 2.4547929212481435e-05, | |
| "loss": 1.0828, | |
| "num_input_tokens_seen": 184549376, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.15856950067476383, | |
| "grad_norm": 0.21369491517543793, | |
| "learning_rate": 2.4397856756471432e-05, | |
| "loss": 0.8688, | |
| "num_input_tokens_seen": 184811520, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.1587944219523167, | |
| "grad_norm": 0.3311217427253723, | |
| "learning_rate": 2.4248096254497288e-05, | |
| "loss": 1.04, | |
| "num_input_tokens_seen": 185073664, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.15901934322986955, | |
| "grad_norm": 0.6069524884223938, | |
| "learning_rate": 2.4098649531343497e-05, | |
| "loss": 1.3251, | |
| "num_input_tokens_seen": 185335808, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.1592442645074224, | |
| "grad_norm": 0.3160417377948761, | |
| "learning_rate": 2.39495184079712e-05, | |
| "loss": 1.514, | |
| "num_input_tokens_seen": 185597952, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.15946918578497526, | |
| "grad_norm": 0.34821102023124695, | |
| "learning_rate": 2.3800704701496053e-05, | |
| "loss": 1.3157, | |
| "num_input_tokens_seen": 185860096, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 0.15969410706252812, | |
| "grad_norm": 0.37680163979530334, | |
| "learning_rate": 2.3652210225166122e-05, | |
| "loss": 1.7779, | |
| "num_input_tokens_seen": 186122240, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.15991902834008098, | |
| "grad_norm": 0.6597973108291626, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 1.0905, | |
| "num_input_tokens_seen": 186384384, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 0.16014394961763384, | |
| "grad_norm": 0.2757372260093689, | |
| "learning_rate": 2.33561861964635e-05, | |
| "loss": 1.3679, | |
| "num_input_tokens_seen": 186646528, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.16036887089518667, | |
| "grad_norm": 0.2820758819580078, | |
| "learning_rate": 2.3208660251050158e-05, | |
| "loss": 1.9283, | |
| "num_input_tokens_seen": 186908672, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 0.16059379217273953, | |
| "grad_norm": 0.2349315583705902, | |
| "learning_rate": 2.3061460749656844e-05, | |
| "loss": 1.0785, | |
| "num_input_tokens_seen": 187170816, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.1608187134502924, | |
| "grad_norm": 0.4976591169834137, | |
| "learning_rate": 2.2914589485863014e-05, | |
| "loss": 2.0155, | |
| "num_input_tokens_seen": 187432960, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.16104363472784525, | |
| "grad_norm": 0.2699415683746338, | |
| "learning_rate": 2.2768048249248648e-05, | |
| "loss": 1.485, | |
| "num_input_tokens_seen": 187695104, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.1612685560053981, | |
| "grad_norm": 0.33777254819869995, | |
| "learning_rate": 2.2621838825372493e-05, | |
| "loss": 1.2485, | |
| "num_input_tokens_seen": 187957248, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 0.16149347728295096, | |
| "grad_norm": 0.27162325382232666, | |
| "learning_rate": 2.247596299575022e-05, | |
| "loss": 1.7082, | |
| "num_input_tokens_seen": 188219392, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.16171839856050382, | |
| "grad_norm": 0.5944697856903076, | |
| "learning_rate": 2.23304225378328e-05, | |
| "loss": 1.4907, | |
| "num_input_tokens_seen": 188481536, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 0.16194331983805668, | |
| "grad_norm": 0.5989211201667786, | |
| "learning_rate": 2.218521922498476e-05, | |
| "loss": 1.4793, | |
| "num_input_tokens_seen": 188743680, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.16216824111560954, | |
| "grad_norm": 0.33278682827949524, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.9338, | |
| "num_input_tokens_seen": 189005824, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.1623931623931624, | |
| "grad_norm": 0.21896512806415558, | |
| "learning_rate": 2.1895831107393484e-05, | |
| "loss": 0.9001, | |
| "num_input_tokens_seen": 189267968, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.16261808367071526, | |
| "grad_norm": 0.37337714433670044, | |
| "learning_rate": 2.1751649828753106e-05, | |
| "loss": 1.8342, | |
| "num_input_tokens_seen": 189530112, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 0.16284300494826812, | |
| "grad_norm": 0.36519575119018555, | |
| "learning_rate": 2.160781274734495e-05, | |
| "loss": 1.9973, | |
| "num_input_tokens_seen": 189792256, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.16306792622582097, | |
| "grad_norm": 0.3658199608325958, | |
| "learning_rate": 2.1464321615778422e-05, | |
| "loss": 1.4951, | |
| "num_input_tokens_seen": 190054400, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.1632928475033738, | |
| "grad_norm": 0.5318383574485779, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 1.8081, | |
| "num_input_tokens_seen": 190316544, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.16351776878092666, | |
| "grad_norm": 0.4171576499938965, | |
| "learning_rate": 2.117838419151034e-05, | |
| "loss": 1.2466, | |
| "num_input_tokens_seen": 190578688, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 0.16374269005847952, | |
| "grad_norm": 0.2993619441986084, | |
| "learning_rate": 2.103594138286607e-05, | |
| "loss": 1.3636, | |
| "num_input_tokens_seen": 190840832, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.16396761133603238, | |
| "grad_norm": 0.31914806365966797, | |
| "learning_rate": 2.0893851492135537e-05, | |
| "loss": 1.4931, | |
| "num_input_tokens_seen": 191102976, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 0.16419253261358524, | |
| "grad_norm": 0.4262048006057739, | |
| "learning_rate": 2.0752116250639225e-05, | |
| "loss": 1.607, | |
| "num_input_tokens_seen": 191365120, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.1644174538911381, | |
| "grad_norm": 0.2858421504497528, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.5553, | |
| "num_input_tokens_seen": 191627264, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.16464237516869096, | |
| "grad_norm": 0.24495238065719604, | |
| "learning_rate": 2.0469716619003725e-05, | |
| "loss": 1.4652, | |
| "num_input_tokens_seen": 191889408, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.16486729644624382, | |
| "grad_norm": 0.3603944480419159, | |
| "learning_rate": 2.0329055669814934e-05, | |
| "loss": 1.5141, | |
| "num_input_tokens_seen": 192151552, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 0.16509221772379667, | |
| "grad_norm": 0.2774426341056824, | |
| "learning_rate": 2.0188756251719203e-05, | |
| "loss": 1.5936, | |
| "num_input_tokens_seen": 192413696, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.16531713900134953, | |
| "grad_norm": 0.3978561460971832, | |
| "learning_rate": 2.0048820074220715e-05, | |
| "loss": 1.6921, | |
| "num_input_tokens_seen": 192675840, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.1655420602789024, | |
| "grad_norm": 0.39905136823654175, | |
| "learning_rate": 1.9909248842397584e-05, | |
| "loss": 1.6292, | |
| "num_input_tokens_seen": 192937984, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.16576698155645525, | |
| "grad_norm": 0.24895912408828735, | |
| "learning_rate": 1.977004425688126e-05, | |
| "loss": 1.4281, | |
| "num_input_tokens_seen": 193200128, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 0.1659919028340081, | |
| "grad_norm": 0.3778083920478821, | |
| "learning_rate": 1.9631208013835678e-05, | |
| "loss": 1.4312, | |
| "num_input_tokens_seen": 193462272, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.16621682411156094, | |
| "grad_norm": 0.8549690246582031, | |
| "learning_rate": 1.9492741804936622e-05, | |
| "loss": 1.5366, | |
| "num_input_tokens_seen": 193724416, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 0.1664417453891138, | |
| "grad_norm": 0.2696658670902252, | |
| "learning_rate": 1.9354647317351188e-05, | |
| "loss": 1.452, | |
| "num_input_tokens_seen": 193986560, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.24030734598636627, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.6674, | |
| "num_input_tokens_seen": 194248704, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 0.16689158794421952, | |
| "grad_norm": 0.2628820538520813, | |
| "learning_rate": 1.9079580232122303e-05, | |
| "loss": 1.8918, | |
| "num_input_tokens_seen": 194510848, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.16711650922177237, | |
| "grad_norm": 0.3136844038963318, | |
| "learning_rate": 1.8942610986084486e-05, | |
| "loss": 1.1222, | |
| "num_input_tokens_seen": 194772992, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 0.16734143049932523, | |
| "grad_norm": 0.27816563844680786, | |
| "learning_rate": 1.8806020164530702e-05, | |
| "loss": 1.7347, | |
| "num_input_tokens_seen": 195035136, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.1675663517768781, | |
| "grad_norm": 0.3501325845718384, | |
| "learning_rate": 1.866980943177699e-05, | |
| "loss": 1.9938, | |
| "num_input_tokens_seen": 195297280, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.16779127305443095, | |
| "grad_norm": 0.32793718576431274, | |
| "learning_rate": 1.8533980447508137e-05, | |
| "loss": 1.5852, | |
| "num_input_tokens_seen": 195559424, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.1680161943319838, | |
| "grad_norm": 0.26959773898124695, | |
| "learning_rate": 1.8398534866757454e-05, | |
| "loss": 1.4583, | |
| "num_input_tokens_seen": 195821568, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 0.16824111560953667, | |
| "grad_norm": 0.29915785789489746, | |
| "learning_rate": 1.8263474339886628e-05, | |
| "loss": 1.7142, | |
| "num_input_tokens_seen": 196083712, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.16846603688708953, | |
| "grad_norm": 0.37239888310432434, | |
| "learning_rate": 1.8128800512565513e-05, | |
| "loss": 1.6461, | |
| "num_input_tokens_seen": 196345856, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.16869095816464239, | |
| "grad_norm": 0.31688031554222107, | |
| "learning_rate": 1.7994515025752217e-05, | |
| "loss": 1.4778, | |
| "num_input_tokens_seen": 196608000, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.16891587944219524, | |
| "grad_norm": 0.32182300090789795, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.5883, | |
| "num_input_tokens_seen": 196870144, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 0.16914080071974807, | |
| "grad_norm": 0.2562112808227539, | |
| "learning_rate": 1.7727115613802465e-05, | |
| "loss": 1.409, | |
| "num_input_tokens_seen": 197132288, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.16936572199730093, | |
| "grad_norm": 0.501336932182312, | |
| "learning_rate": 1.7594004946843456e-05, | |
| "loss": 1.5277, | |
| "num_input_tokens_seen": 197394432, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 0.1695906432748538, | |
| "grad_norm": 0.2757022976875305, | |
| "learning_rate": 1.746128913670746e-05, | |
| "loss": 1.2632, | |
| "num_input_tokens_seen": 197656576, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.16981556455240665, | |
| "grad_norm": 0.2268674522638321, | |
| "learning_rate": 1.7328969800494726e-05, | |
| "loss": 1.2268, | |
| "num_input_tokens_seen": 197918720, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.1700404858299595, | |
| "grad_norm": 0.3350222706794739, | |
| "learning_rate": 1.7197048550474643e-05, | |
| "loss": 1.7233, | |
| "num_input_tokens_seen": 198180864, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.17026540710751237, | |
| "grad_norm": 0.3129500150680542, | |
| "learning_rate": 1.7065526994065973e-05, | |
| "loss": 1.1204, | |
| "num_input_tokens_seen": 198443008, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 0.17049032838506523, | |
| "grad_norm": 0.295625776052475, | |
| "learning_rate": 1.6934406733817414e-05, | |
| "loss": 0.8985, | |
| "num_input_tokens_seen": 198705152, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.17071524966261808, | |
| "grad_norm": 0.26125019788742065, | |
| "learning_rate": 1.680368936738792e-05, | |
| "loss": 1.0675, | |
| "num_input_tokens_seen": 198967296, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 0.2649379074573517, | |
| "learning_rate": 1.667337648752738e-05, | |
| "loss": 1.4381, | |
| "num_input_tokens_seen": 199229440, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.1711650922177238, | |
| "grad_norm": 0.24367214739322662, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.4375, | |
| "num_input_tokens_seen": 199491584, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 0.17139001349527666, | |
| "grad_norm": 0.4118271470069885, | |
| "learning_rate": 1.6413970533850498e-05, | |
| "loss": 1.8085, | |
| "num_input_tokens_seen": 199753728, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.17161493477282952, | |
| "grad_norm": 0.24232937395572662, | |
| "learning_rate": 1.6284880620813848e-05, | |
| "loss": 0.9696, | |
| "num_input_tokens_seen": 200015872, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.17183985605038238, | |
| "grad_norm": 0.2732202708721161, | |
| "learning_rate": 1.615620151586697e-05, | |
| "loss": 1.8716, | |
| "num_input_tokens_seen": 200278016, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.1720647773279352, | |
| "grad_norm": 0.3352683186531067, | |
| "learning_rate": 1.602793478692419e-05, | |
| "loss": 1.9496, | |
| "num_input_tokens_seen": 200540160, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.17228969860548807, | |
| "grad_norm": 0.35812363028526306, | |
| "learning_rate": 1.5900081996875083e-05, | |
| "loss": 1.3767, | |
| "num_input_tokens_seen": 200802304, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.17251461988304093, | |
| "grad_norm": 0.24810630083084106, | |
| "learning_rate": 1.5772644703565565e-05, | |
| "loss": 1.4532, | |
| "num_input_tokens_seen": 201064448, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 0.17273954116059378, | |
| "grad_norm": 0.2576179504394531, | |
| "learning_rate": 1.5645624459778856e-05, | |
| "loss": 1.1053, | |
| "num_input_tokens_seen": 201326592, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.17296446243814664, | |
| "grad_norm": 0.45622938871383667, | |
| "learning_rate": 1.551902281321651e-05, | |
| "loss": 1.6785, | |
| "num_input_tokens_seen": 201588736, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 0.1731893837156995, | |
| "grad_norm": 0.35794106125831604, | |
| "learning_rate": 1.5392841306479666e-05, | |
| "loss": 1.004, | |
| "num_input_tokens_seen": 201850880, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.17341430499325236, | |
| "grad_norm": 0.34276673197746277, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 1.2476, | |
| "num_input_tokens_seen": 202113024, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 0.17363922627080522, | |
| "grad_norm": 0.318548321723938, | |
| "learning_rate": 1.5141744857271778e-05, | |
| "loss": 1.6177, | |
| "num_input_tokens_seen": 202375168, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.17386414754835808, | |
| "grad_norm": 0.2709994316101074, | |
| "learning_rate": 1.5016832974331724e-05, | |
| "loss": 1.4153, | |
| "num_input_tokens_seen": 202637312, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 0.17408906882591094, | |
| "grad_norm": 0.23188814520835876, | |
| "learning_rate": 1.4892347350241881e-05, | |
| "loss": 1.1132, | |
| "num_input_tokens_seen": 202899456, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.1743139901034638, | |
| "grad_norm": 0.23023724555969238, | |
| "learning_rate": 1.4768289501820265e-05, | |
| "loss": 1.0796, | |
| "num_input_tokens_seen": 203161600, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.17453891138101665, | |
| "grad_norm": 0.23310570418834686, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9287, | |
| "num_input_tokens_seen": 203423744, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.1747638326585695, | |
| "grad_norm": 0.47127315402030945, | |
| "learning_rate": 1.4521463173173965e-05, | |
| "loss": 1.7062, | |
| "num_input_tokens_seen": 203685888, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.17498875393612237, | |
| "grad_norm": 0.2425903081893921, | |
| "learning_rate": 1.439869770045018e-05, | |
| "loss": 1.509, | |
| "num_input_tokens_seen": 203948032, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.1752136752136752, | |
| "grad_norm": 0.29599592089653015, | |
| "learning_rate": 1.4276366018359844e-05, | |
| "loss": 1.4202, | |
| "num_input_tokens_seen": 204210176, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 0.4893275499343872, | |
| "learning_rate": 1.4154469617475863e-05, | |
| "loss": 1.2288, | |
| "num_input_tokens_seen": 204472320, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.17566351776878092, | |
| "grad_norm": 0.6782318353652954, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.5115, | |
| "num_input_tokens_seen": 204734464, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 0.17588843904633378, | |
| "grad_norm": 0.359073668718338, | |
| "learning_rate": 1.3911988595081893e-05, | |
| "loss": 2.0383, | |
| "num_input_tokens_seen": 204996608, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.17611336032388664, | |
| "grad_norm": 0.35052844882011414, | |
| "learning_rate": 1.3791406928126638e-05, | |
| "loss": 1.364, | |
| "num_input_tokens_seen": 205258752, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 0.1763382816014395, | |
| "grad_norm": 0.3411898910999298, | |
| "learning_rate": 1.367126645145121e-05, | |
| "loss": 1.9237, | |
| "num_input_tokens_seen": 205520896, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.17656320287899235, | |
| "grad_norm": 0.28995242714881897, | |
| "learning_rate": 1.3551568628929434e-05, | |
| "loss": 1.9925, | |
| "num_input_tokens_seen": 205783040, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.1767881241565452, | |
| "grad_norm": 0.2879210412502289, | |
| "learning_rate": 1.3432314919041478e-05, | |
| "loss": 1.4678, | |
| "num_input_tokens_seen": 206045184, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.17701304543409807, | |
| "grad_norm": 0.6357771158218384, | |
| "learning_rate": 1.3313506774856177e-05, | |
| "loss": 1.8581, | |
| "num_input_tokens_seen": 206307328, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 0.17723796671165093, | |
| "grad_norm": 0.2830122113227844, | |
| "learning_rate": 1.3195145644013285e-05, | |
| "loss": 1.3386, | |
| "num_input_tokens_seen": 206569472, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.1774628879892038, | |
| "grad_norm": 0.486817866563797, | |
| "learning_rate": 1.3077232968705805e-05, | |
| "loss": 1.3974, | |
| "num_input_tokens_seen": 206831616, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 0.17768780926675665, | |
| "grad_norm": 0.27353304624557495, | |
| "learning_rate": 1.29597701856625e-05, | |
| "loss": 1.7853, | |
| "num_input_tokens_seen": 207093760, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.1779127305443095, | |
| "grad_norm": 0.2737731337547302, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 1.5908, | |
| "num_input_tokens_seen": 207355904, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.17813765182186234, | |
| "grad_norm": 0.28885483741760254, | |
| "learning_rate": 1.2726200015856892e-05, | |
| "loss": 1.3893, | |
| "num_input_tokens_seen": 207618048, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.1783625730994152, | |
| "grad_norm": 0.3733929991722107, | |
| "learning_rate": 1.2610095475073414e-05, | |
| "loss": 1.5299, | |
| "num_input_tokens_seen": 207880192, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 0.17858749437696805, | |
| "grad_norm": 0.27227166295051575, | |
| "learning_rate": 1.2494446518477022e-05, | |
| "loss": 1.3791, | |
| "num_input_tokens_seen": 208142336, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.1788124156545209, | |
| "grad_norm": 0.41097357869148254, | |
| "learning_rate": 1.2379254555213788e-05, | |
| "loss": 0.7853, | |
| "num_input_tokens_seen": 208404480, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.17903733693207377, | |
| "grad_norm": 0.4259317219257355, | |
| "learning_rate": 1.22645209888614e-05, | |
| "loss": 1.1717, | |
| "num_input_tokens_seen": 208666624, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.17926225820962663, | |
| "grad_norm": 0.2950097918510437, | |
| "learning_rate": 1.2150247217412186e-05, | |
| "loss": 1.7082, | |
| "num_input_tokens_seen": 208928768, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 0.1794871794871795, | |
| "grad_norm": 0.2869075834751129, | |
| "learning_rate": 1.203643463325596e-05, | |
| "loss": 1.7419, | |
| "num_input_tokens_seen": 209190912, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.17971210076473235, | |
| "grad_norm": 0.41858625411987305, | |
| "learning_rate": 1.1923084623163172e-05, | |
| "loss": 1.5839, | |
| "num_input_tokens_seen": 209453056, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 0.1799370220422852, | |
| "grad_norm": 0.22646434605121613, | |
| "learning_rate": 1.1810198568267905e-05, | |
| "loss": 1.3877, | |
| "num_input_tokens_seen": 209715200, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.18016194331983806, | |
| "grad_norm": 0.25302788615226746, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.417, | |
| "num_input_tokens_seen": 209977344, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 0.18038686459739092, | |
| "grad_norm": 0.269723117351532, | |
| "learning_rate": 1.1585823820323843e-05, | |
| "loss": 1.3995, | |
| "num_input_tokens_seen": 210239488, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 0.18061178587494378, | |
| "grad_norm": 0.32225891947746277, | |
| "learning_rate": 1.1474337861210543e-05, | |
| "loss": 1.5246, | |
| "num_input_tokens_seen": 210501632, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 0.18083670715249664, | |
| "grad_norm": 0.2819434702396393, | |
| "learning_rate": 1.1363321325132447e-05, | |
| "loss": 1.6224, | |
| "num_input_tokens_seen": 210763776, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.18106162843004947, | |
| "grad_norm": 0.21161556243896484, | |
| "learning_rate": 1.1252775564791024e-05, | |
| "loss": 0.8181, | |
| "num_input_tokens_seen": 211025920, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.18128654970760233, | |
| "grad_norm": 0.2685690224170685, | |
| "learning_rate": 1.1142701927151456e-05, | |
| "loss": 0.9464, | |
| "num_input_tokens_seen": 211288064, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.1815114709851552, | |
| "grad_norm": 0.4813108742237091, | |
| "learning_rate": 1.1033101753426283e-05, | |
| "loss": 1.6346, | |
| "num_input_tokens_seen": 211550208, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 0.18173639226270805, | |
| "grad_norm": 0.3357571065425873, | |
| "learning_rate": 1.0923976379059058e-05, | |
| "loss": 1.8358, | |
| "num_input_tokens_seen": 211812352, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 0.1819613135402609, | |
| "grad_norm": 0.2748908996582031, | |
| "learning_rate": 1.0815327133708015e-05, | |
| "loss": 1.6321, | |
| "num_input_tokens_seen": 212074496, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 0.18218623481781376, | |
| "grad_norm": 0.32630112767219543, | |
| "learning_rate": 1.0707155341229901e-05, | |
| "loss": 1.17, | |
| "num_input_tokens_seen": 212336640, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.18241115609536662, | |
| "grad_norm": 0.29258018732070923, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 1.0201, | |
| "num_input_tokens_seen": 212598784, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 0.18263607737291948, | |
| "grad_norm": 0.2514300048351288, | |
| "learning_rate": 1.049224938121548e-05, | |
| "loss": 0.9086, | |
| "num_input_tokens_seen": 212860928, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.18286099865047234, | |
| "grad_norm": 0.30031341314315796, | |
| "learning_rate": 1.0385517832240471e-05, | |
| "loss": 0.7005, | |
| "num_input_tokens_seen": 213123072, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 0.1830859199280252, | |
| "grad_norm": 0.38122648000717163, | |
| "learning_rate": 1.0279268973229089e-05, | |
| "loss": 0.9653, | |
| "num_input_tokens_seen": 213385216, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 0.18331084120557806, | |
| "grad_norm": 0.319106787443161, | |
| "learning_rate": 1.0173504098790187e-05, | |
| "loss": 1.1675, | |
| "num_input_tokens_seen": 213647360, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.18353576248313092, | |
| "grad_norm": 0.2643660008907318, | |
| "learning_rate": 1.006822449763537e-05, | |
| "loss": 1.5398, | |
| "num_input_tokens_seen": 213909504, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.18376068376068377, | |
| "grad_norm": 0.2221175879240036, | |
| "learning_rate": 9.963431452563332e-06, | |
| "loss": 1.2352, | |
| "num_input_tokens_seen": 214171648, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.1839856050382366, | |
| "grad_norm": 0.636135458946228, | |
| "learning_rate": 9.859126240444283e-06, | |
| "loss": 1.3639, | |
| "num_input_tokens_seen": 214433792, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 0.27148714661598206, | |
| "learning_rate": 9.755310132204298e-06, | |
| "loss": 1.2762, | |
| "num_input_tokens_seen": 214695936, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 0.18443544759334232, | |
| "grad_norm": 0.2437310367822647, | |
| "learning_rate": 9.651984392809914e-06, | |
| "loss": 2.0397, | |
| "num_input_tokens_seen": 214958080, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.18466036887089518, | |
| "grad_norm": 0.2802148461341858, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.5733, | |
| "num_input_tokens_seen": 215220224, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 0.18488529014844804, | |
| "grad_norm": 0.39606234431266785, | |
| "learning_rate": 9.446809050533678e-06, | |
| "loss": 1.2963, | |
| "num_input_tokens_seen": 215482368, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.1851102114260009, | |
| "grad_norm": 0.4500436782836914, | |
| "learning_rate": 9.344961947648623e-06, | |
| "loss": 1.9574, | |
| "num_input_tokens_seen": 215744512, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 0.18533513270355376, | |
| "grad_norm": 0.3091246783733368, | |
| "learning_rate": 9.243610213572285e-06, | |
| "loss": 1.5413, | |
| "num_input_tokens_seen": 216006656, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 0.18556005398110662, | |
| "grad_norm": 0.2845333516597748, | |
| "learning_rate": 9.142755083243576e-06, | |
| "loss": 2.1405, | |
| "num_input_tokens_seen": 216268800, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.18578497525865947, | |
| "grad_norm": 0.47833433747291565, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 2.0458, | |
| "num_input_tokens_seen": 216530944, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.18600989653621233, | |
| "grad_norm": 0.2986997067928314, | |
| "learning_rate": 8.9425395433148e-06, | |
| "loss": 1.3242, | |
| "num_input_tokens_seen": 216793088, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 0.1862348178137652, | |
| "grad_norm": 0.2789519131183624, | |
| "learning_rate": 8.843181573277902e-06, | |
| "loss": 1.8162, | |
| "num_input_tokens_seen": 217055232, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.18645973909131805, | |
| "grad_norm": 0.3428088128566742, | |
| "learning_rate": 8.744325086085248e-06, | |
| "loss": 1.5293, | |
| "num_input_tokens_seen": 217317376, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 0.1866846603688709, | |
| "grad_norm": 0.37942934036254883, | |
| "learning_rate": 8.645971286271904e-06, | |
| "loss": 1.3963, | |
| "num_input_tokens_seen": 217579520, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.18690958164642374, | |
| "grad_norm": 0.257756769657135, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 1.4567, | |
| "num_input_tokens_seen": 217841664, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 0.1871345029239766, | |
| "grad_norm": 0.2964596748352051, | |
| "learning_rate": 8.450776536283594e-06, | |
| "loss": 1.4137, | |
| "num_input_tokens_seen": 218103808, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.18735942420152946, | |
| "grad_norm": 0.3498225510120392, | |
| "learning_rate": 8.353937964495029e-06, | |
| "loss": 1.8612, | |
| "num_input_tokens_seen": 218365952, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 0.18758434547908232, | |
| "grad_norm": 3.0258142948150635, | |
| "learning_rate": 8.257606836829678e-06, | |
| "loss": 1.6101, | |
| "num_input_tokens_seen": 218628096, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.18780926675663517, | |
| "grad_norm": 0.2801116108894348, | |
| "learning_rate": 8.16178432705192e-06, | |
| "loss": 0.9278, | |
| "num_input_tokens_seen": 218890240, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.18803418803418803, | |
| "grad_norm": 0.3314686119556427, | |
| "learning_rate": 8.066471602728803e-06, | |
| "loss": 1.9387, | |
| "num_input_tokens_seen": 219152384, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 0.1882591093117409, | |
| "grad_norm": 0.348878413438797, | |
| "learning_rate": 7.971669825215788e-06, | |
| "loss": 1.322, | |
| "num_input_tokens_seen": 219414528, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 0.18848403058929375, | |
| "grad_norm": 0.24432994425296783, | |
| "learning_rate": 7.877380149642626e-06, | |
| "loss": 1.3546, | |
| "num_input_tokens_seen": 219676672, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 0.1887089518668466, | |
| "grad_norm": 0.320366770029068, | |
| "learning_rate": 7.783603724899257e-06, | |
| "loss": 1.5225, | |
| "num_input_tokens_seen": 219938816, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 0.18893387314439947, | |
| "grad_norm": 0.2689548432826996, | |
| "learning_rate": 7.690341693621805e-06, | |
| "loss": 1.5467, | |
| "num_input_tokens_seen": 220200960, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.18915879442195233, | |
| "grad_norm": 0.2117762565612793, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.0383, | |
| "num_input_tokens_seen": 220463104, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 0.18938371569950518, | |
| "grad_norm": 0.26459306478500366, | |
| "learning_rate": 7.505365350656812e-06, | |
| "loss": 1.8679, | |
| "num_input_tokens_seen": 220725248, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 0.18960863697705804, | |
| "grad_norm": 0.28376010060310364, | |
| "learning_rate": 7.413653292847617e-06, | |
| "loss": 1.6637, | |
| "num_input_tokens_seen": 220987392, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 0.18983355825461087, | |
| "grad_norm": 0.3108251392841339, | |
| "learning_rate": 7.322460136233622e-06, | |
| "loss": 2.0003, | |
| "num_input_tokens_seen": 221249536, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 0.19005847953216373, | |
| "grad_norm": 0.3655540645122528, | |
| "learning_rate": 7.2317869919746705e-06, | |
| "loss": 1.499, | |
| "num_input_tokens_seen": 221511680, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.1902834008097166, | |
| "grad_norm": 1.4836020469665527, | |
| "learning_rate": 7.1416349648943894e-06, | |
| "loss": 1.6247, | |
| "num_input_tokens_seen": 221773824, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.19050832208726945, | |
| "grad_norm": 1.6627871990203857, | |
| "learning_rate": 7.052005153466779e-06, | |
| "loss": 1.7312, | |
| "num_input_tokens_seen": 222035968, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 0.1907332433648223, | |
| "grad_norm": 0.2904163897037506, | |
| "learning_rate": 6.962898649802823e-06, | |
| "loss": 1.4695, | |
| "num_input_tokens_seen": 222298112, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 0.19095816464237517, | |
| "grad_norm": 0.3054295480251312, | |
| "learning_rate": 6.874316539637127e-06, | |
| "loss": 1.5799, | |
| "num_input_tokens_seen": 222560256, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 0.19118308591992803, | |
| "grad_norm": 0.269171804189682, | |
| "learning_rate": 6.786259902314768e-06, | |
| "loss": 1.3127, | |
| "num_input_tokens_seen": 222822400, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.19140800719748088, | |
| "grad_norm": 0.29726889729499817, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.7892, | |
| "num_input_tokens_seen": 223084544, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 0.19163292847503374, | |
| "grad_norm": 0.3201026916503906, | |
| "learning_rate": 6.611727331553586e-06, | |
| "loss": 1.3596, | |
| "num_input_tokens_seen": 223346688, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.1918578497525866, | |
| "grad_norm": 0.3100236654281616, | |
| "learning_rate": 6.52525352473905e-06, | |
| "loss": 1.1841, | |
| "num_input_tokens_seen": 223608832, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 0.19208277103013946, | |
| "grad_norm": 0.428475946187973, | |
| "learning_rate": 6.439309443990532e-06, | |
| "loss": 2.2884, | |
| "num_input_tokens_seen": 223870976, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 0.28759607672691345, | |
| "learning_rate": 6.353896136509524e-06, | |
| "loss": 1.6141, | |
| "num_input_tokens_seen": 224133120, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.19253261358524518, | |
| "grad_norm": 0.23132166266441345, | |
| "learning_rate": 6.269014643030213e-06, | |
| "loss": 0.8094, | |
| "num_input_tokens_seen": 224395264, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 0.192757534862798, | |
| "grad_norm": 0.2636610269546509, | |
| "learning_rate": 6.184665997806832e-06, | |
| "loss": 1.4375, | |
| "num_input_tokens_seen": 224657408, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 0.19298245614035087, | |
| "grad_norm": 0.24574293196201324, | |
| "learning_rate": 6.100851228600973e-06, | |
| "loss": 1.0708, | |
| "num_input_tokens_seen": 224919552, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.19320737741790373, | |
| "grad_norm": 0.22492122650146484, | |
| "learning_rate": 6.017571356669183e-06, | |
| "loss": 1.2114, | |
| "num_input_tokens_seen": 225181696, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 0.19343229869545658, | |
| "grad_norm": 0.3934623897075653, | |
| "learning_rate": 5.934827396750392e-06, | |
| "loss": 2.2453, | |
| "num_input_tokens_seen": 225443840, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.19365721997300944, | |
| "grad_norm": 0.2976413667201996, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.529, | |
| "num_input_tokens_seen": 225705984, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 0.1938821412505623, | |
| "grad_norm": 0.2744722068309784, | |
| "learning_rate": 5.770951239245803e-06, | |
| "loss": 1.1937, | |
| "num_input_tokens_seen": 225968128, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 0.19410706252811516, | |
| "grad_norm": 0.2966805100440979, | |
| "learning_rate": 5.689821038439263e-06, | |
| "loss": 1.6629, | |
| "num_input_tokens_seen": 226230272, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 0.19433198380566802, | |
| "grad_norm": 0.2719520926475525, | |
| "learning_rate": 5.6092307431799384e-06, | |
| "loss": 1.2716, | |
| "num_input_tokens_seen": 226492416, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.19455690508322088, | |
| "grad_norm": 0.2147417515516281, | |
| "learning_rate": 5.529181335435124e-06, | |
| "loss": 0.9605, | |
| "num_input_tokens_seen": 226754560, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.19478182636077374, | |
| "grad_norm": 0.3258356750011444, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 1.8107, | |
| "num_input_tokens_seen": 227016704, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 0.1950067476383266, | |
| "grad_norm": 0.27222108840942383, | |
| "learning_rate": 5.370709077393721e-06, | |
| "loss": 1.3168, | |
| "num_input_tokens_seen": 227278848, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 0.19523166891587945, | |
| "grad_norm": 0.2095833271741867, | |
| "learning_rate": 5.292288158031594e-06, | |
| "loss": 1.3649, | |
| "num_input_tokens_seen": 227540992, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.1954565901934323, | |
| "grad_norm": 0.31206318736076355, | |
| "learning_rate": 5.214411988029355e-06, | |
| "loss": 1.3449, | |
| "num_input_tokens_seen": 227803136, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 0.19568151147098514, | |
| "grad_norm": 0.3639450669288635, | |
| "learning_rate": 5.137081516283581e-06, | |
| "loss": 1.6845, | |
| "num_input_tokens_seen": 228065280, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.195906432748538, | |
| "grad_norm": 0.2893346846103668, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 1.2223, | |
| "num_input_tokens_seen": 228327424, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 0.19613135402609086, | |
| "grad_norm": 0.21746279299259186, | |
| "learning_rate": 4.984061429890324e-06, | |
| "loss": 1.1666, | |
| "num_input_tokens_seen": 228589568, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 0.19635627530364372, | |
| "grad_norm": 0.26073527336120605, | |
| "learning_rate": 4.908373679744316e-06, | |
| "loss": 1.7673, | |
| "num_input_tokens_seen": 228851712, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 0.19658119658119658, | |
| "grad_norm": 0.5019742250442505, | |
| "learning_rate": 4.833235356834959e-06, | |
| "loss": 0.8521, | |
| "num_input_tokens_seen": 229113856, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 0.19680611785874944, | |
| "grad_norm": 0.3473358750343323, | |
| "learning_rate": 4.758647376699032e-06, | |
| "loss": 1.3868, | |
| "num_input_tokens_seen": 229376000, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.1970310391363023, | |
| "grad_norm": 0.32887259125709534, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 1.5076, | |
| "num_input_tokens_seen": 229638144, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.19725596041385515, | |
| "grad_norm": 1.0063308477401733, | |
| "learning_rate": 4.611126073354571e-06, | |
| "loss": 1.422, | |
| "num_input_tokens_seen": 229900288, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 0.197480881691408, | |
| "grad_norm": 0.21128523349761963, | |
| "learning_rate": 4.538194547646574e-06, | |
| "loss": 1.4598, | |
| "num_input_tokens_seen": 230162432, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 0.19770580296896087, | |
| "grad_norm": 0.28047022223472595, | |
| "learning_rate": 4.465816959691149e-06, | |
| "loss": 1.0795, | |
| "num_input_tokens_seen": 230424576, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 0.19793072424651373, | |
| "grad_norm": 0.38452693819999695, | |
| "learning_rate": 4.3939941913863525e-06, | |
| "loss": 1.6362, | |
| "num_input_tokens_seen": 230686720, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.1981556455240666, | |
| "grad_norm": 0.27827146649360657, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.4264, | |
| "num_input_tokens_seen": 230948864, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 0.19838056680161945, | |
| "grad_norm": 0.2739766836166382, | |
| "learning_rate": 4.2520166075087635e-06, | |
| "loss": 1.2018, | |
| "num_input_tokens_seen": 231211008, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.19860548807917228, | |
| "grad_norm": 0.21906918287277222, | |
| "learning_rate": 4.181863521888019e-06, | |
| "loss": 0.8336, | |
| "num_input_tokens_seen": 231473152, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 0.19883040935672514, | |
| "grad_norm": 0.4255640208721161, | |
| "learning_rate": 4.112268715800943e-06, | |
| "loss": 1.2028, | |
| "num_input_tokens_seen": 231735296, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.199055330634278, | |
| "grad_norm": 0.24651283025741577, | |
| "learning_rate": 4.043233037238281e-06, | |
| "loss": 1.2193, | |
| "num_input_tokens_seen": 231997440, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.19928025191183085, | |
| "grad_norm": 0.7165899872779846, | |
| "learning_rate": 3.974757327377981e-06, | |
| "loss": 1.5189, | |
| "num_input_tokens_seen": 232259584, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 0.1995051731893837, | |
| "grad_norm": 0.30502429604530334, | |
| "learning_rate": 3.90684242057498e-06, | |
| "loss": 1.6756, | |
| "num_input_tokens_seen": 232521728, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 0.19973009446693657, | |
| "grad_norm": 0.3749113380908966, | |
| "learning_rate": 3.839489144350955e-06, | |
| "loss": 1.5954, | |
| "num_input_tokens_seen": 232783872, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.19995501574448943, | |
| "grad_norm": 0.29872778058052063, | |
| "learning_rate": 3.772698319384349e-06, | |
| "loss": 0.999, | |
| "num_input_tokens_seen": 233046016, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 0.2001799370220423, | |
| "grad_norm": 0.47089534997940063, | |
| "learning_rate": 3.7064707595002635e-06, | |
| "loss": 1.6206, | |
| "num_input_tokens_seen": 233308160, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.20040485829959515, | |
| "grad_norm": 0.4469537138938904, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 1.3996, | |
| "num_input_tokens_seen": 233570304, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 0.200629779577148, | |
| "grad_norm": 0.283834308385849, | |
| "learning_rate": 3.575708655954324e-06, | |
| "loss": 1.3198, | |
| "num_input_tokens_seen": 233832448, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 0.20085470085470086, | |
| "grad_norm": 0.4261209964752197, | |
| "learning_rate": 3.511175705587433e-06, | |
| "loss": 1.1136, | |
| "num_input_tokens_seen": 234094592, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 0.20107962213225372, | |
| "grad_norm": 0.2869652211666107, | |
| "learning_rate": 3.4472092068735916e-06, | |
| "loss": 1.0926, | |
| "num_input_tokens_seen": 234356736, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.20130454340980658, | |
| "grad_norm": 0.18117663264274597, | |
| "learning_rate": 3.3838099392243916e-06, | |
| "loss": 0.9276, | |
| "num_input_tokens_seen": 234618880, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.2015294646873594, | |
| "grad_norm": 0.49210941791534424, | |
| "learning_rate": 3.3209786751399187e-06, | |
| "loss": 1.5335, | |
| "num_input_tokens_seen": 234881024, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.20175438596491227, | |
| "grad_norm": 0.35008394718170166, | |
| "learning_rate": 3.258716180199278e-06, | |
| "loss": 1.8602, | |
| "num_input_tokens_seen": 235143168, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 0.20197930724246513, | |
| "grad_norm": 0.4784037470817566, | |
| "learning_rate": 3.197023213051337e-06, | |
| "loss": 1.5308, | |
| "num_input_tokens_seen": 235405312, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 0.202204228520018, | |
| "grad_norm": 0.2999178171157837, | |
| "learning_rate": 3.1359005254054273e-06, | |
| "loss": 1.5131, | |
| "num_input_tokens_seen": 235667456, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 0.20242914979757085, | |
| "grad_norm": 0.3838978707790375, | |
| "learning_rate": 3.0753488620222037e-06, | |
| "loss": 1.6273, | |
| "num_input_tokens_seen": 235929600, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2026540710751237, | |
| "grad_norm": 0.30641281604766846, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.7154, | |
| "num_input_tokens_seen": 236191744, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 0.20287899235267656, | |
| "grad_norm": 0.379870742559433, | |
| "learning_rate": 2.9559615522887273e-06, | |
| "loss": 1.8713, | |
| "num_input_tokens_seen": 236453888, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 0.20310391363022942, | |
| "grad_norm": 0.31836485862731934, | |
| "learning_rate": 2.8971273606351658e-06, | |
| "loss": 1.4777, | |
| "num_input_tokens_seen": 236716032, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.20332883490778228, | |
| "grad_norm": 0.2330200970172882, | |
| "learning_rate": 2.8388671026199522e-06, | |
| "loss": 1.17, | |
| "num_input_tokens_seen": 236978176, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 0.20355375618533514, | |
| "grad_norm": 0.2553198039531708, | |
| "learning_rate": 2.7811814881259503e-06, | |
| "loss": 0.7473, | |
| "num_input_tokens_seen": 237240320, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.203778677462888, | |
| "grad_norm": 0.2429661601781845, | |
| "learning_rate": 2.724071220034158e-06, | |
| "loss": 1.6603, | |
| "num_input_tokens_seen": 237502464, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 0.20400359874044086, | |
| "grad_norm": 0.23130248486995697, | |
| "learning_rate": 2.667536994215186e-06, | |
| "loss": 1.1438, | |
| "num_input_tokens_seen": 237764608, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 0.20422852001799371, | |
| "grad_norm": 0.4475621283054352, | |
| "learning_rate": 2.611579499520722e-06, | |
| "loss": 1.3467, | |
| "num_input_tokens_seen": 238026752, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 0.20445344129554655, | |
| "grad_norm": 0.4158174991607666, | |
| "learning_rate": 2.5561994177751737e-06, | |
| "loss": 1.9419, | |
| "num_input_tokens_seen": 238288896, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 0.2046783625730994, | |
| "grad_norm": 0.3838602602481842, | |
| "learning_rate": 2.501397423767382e-06, | |
| "loss": 1.4355, | |
| "num_input_tokens_seen": 238551040, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.20490328385065226, | |
| "grad_norm": 0.28037744760513306, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.4613, | |
| "num_input_tokens_seen": 238813184, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.370734304189682, | |
| "learning_rate": 2.3935303628930707e-06, | |
| "loss": 1.5199, | |
| "num_input_tokens_seen": 239075328, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 0.20535312640575798, | |
| "grad_norm": 0.38821879029273987, | |
| "learning_rate": 2.340466610352654e-06, | |
| "loss": 1.5737, | |
| "num_input_tokens_seen": 239337472, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 0.20557804768331084, | |
| "grad_norm": 0.2714470624923706, | |
| "learning_rate": 2.2879835741861586e-06, | |
| "loss": 1.9517, | |
| "num_input_tokens_seen": 239599616, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 0.2058029689608637, | |
| "grad_norm": 0.2324371039867401, | |
| "learning_rate": 2.2360818938828187e-06, | |
| "loss": 1.3721, | |
| "num_input_tokens_seen": 239861760, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.20602789023841656, | |
| "grad_norm": 0.27908140420913696, | |
| "learning_rate": 2.1847622018482283e-06, | |
| "loss": 1.8328, | |
| "num_input_tokens_seen": 240123904, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 0.20625281151596941, | |
| "grad_norm": 0.28744250535964966, | |
| "learning_rate": 2.134025123396638e-06, | |
| "loss": 1.7052, | |
| "num_input_tokens_seen": 240386048, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 0.20647773279352227, | |
| "grad_norm": 0.28908395767211914, | |
| "learning_rate": 2.0838712767433375e-06, | |
| "loss": 1.5337, | |
| "num_input_tokens_seen": 240648192, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 0.20670265407107513, | |
| "grad_norm": 0.3027624189853668, | |
| "learning_rate": 2.0343012729971243e-06, | |
| "loss": 1.5177, | |
| "num_input_tokens_seen": 240910336, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 0.206927575348628, | |
| "grad_norm": 0.22034700214862823, | |
| "learning_rate": 1.985315716152847e-06, | |
| "loss": 0.9706, | |
| "num_input_tokens_seen": 241172480, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.20715249662618085, | |
| "grad_norm": 0.2736298739910126, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.5079, | |
| "num_input_tokens_seen": 241434624, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 0.20737741790373368, | |
| "grad_norm": 0.39781084656715393, | |
| "learning_rate": 1.8891003235357308e-06, | |
| "loss": 1.5232, | |
| "num_input_tokens_seen": 241696768, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 0.20760233918128654, | |
| "grad_norm": 0.3146691620349884, | |
| "learning_rate": 1.841871660117095e-06, | |
| "loss": 1.32, | |
| "num_input_tokens_seen": 241958912, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 0.2078272604588394, | |
| "grad_norm": 0.34817108511924744, | |
| "learning_rate": 1.7952297882945003e-06, | |
| "loss": 1.1133, | |
| "num_input_tokens_seen": 242221056, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.20805218173639226, | |
| "grad_norm": 0.4052412211894989, | |
| "learning_rate": 1.7491752763844293e-06, | |
| "loss": 1.3553, | |
| "num_input_tokens_seen": 242483200, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.20827710301394511, | |
| "grad_norm": 0.28856000304222107, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.3245, | |
| "num_input_tokens_seen": 242745344, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 0.20850202429149797, | |
| "grad_norm": 0.2518732249736786, | |
| "learning_rate": 1.6588305697770313e-06, | |
| "loss": 1.2752, | |
| "num_input_tokens_seen": 243007488, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 0.20872694556905083, | |
| "grad_norm": 0.2444835901260376, | |
| "learning_rate": 1.6145414759014431e-06, | |
| "loss": 1.1666, | |
| "num_input_tokens_seen": 243269632, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 0.2089518668466037, | |
| "grad_norm": 0.23631195724010468, | |
| "learning_rate": 1.5708419435684462e-06, | |
| "loss": 1.2224, | |
| "num_input_tokens_seen": 243531776, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 0.20917678812415655, | |
| "grad_norm": 2.2602646350860596, | |
| "learning_rate": 1.5277325052430568e-06, | |
| "loss": 1.954, | |
| "num_input_tokens_seen": 243793920, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.2094017094017094, | |
| "grad_norm": 0.31157422065734863, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 1.781, | |
| "num_input_tokens_seen": 244056064, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 0.20962663067926227, | |
| "grad_norm": 0.3314647078514099, | |
| "learning_rate": 1.4432860045182017e-06, | |
| "loss": 2.0094, | |
| "num_input_tokens_seen": 244318208, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 0.20985155195681512, | |
| "grad_norm": 0.2697344422340393, | |
| "learning_rate": 1.4019499710726913e-06, | |
| "loss": 1.1265, | |
| "num_input_tokens_seen": 244580352, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 0.21007647323436798, | |
| "grad_norm": 0.7156555652618408, | |
| "learning_rate": 1.3612060895301759e-06, | |
| "loss": 1.3521, | |
| "num_input_tokens_seen": 244842496, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 0.21030139451192081, | |
| "grad_norm": 0.20836858451366425, | |
| "learning_rate": 1.3210548563419856e-06, | |
| "loss": 0.9915, | |
| "num_input_tokens_seen": 245104640, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.47020024061203003, | |
| "learning_rate": 1.2814967607382432e-06, | |
| "loss": 1.2631, | |
| "num_input_tokens_seen": 245366784, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.21075123706702653, | |
| "grad_norm": 0.5516555905342102, | |
| "learning_rate": 1.2425322847218368e-06, | |
| "loss": 1.318, | |
| "num_input_tokens_seen": 245628928, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 0.2109761583445794, | |
| "grad_norm": 0.2941971719264984, | |
| "learning_rate": 1.2041619030626284e-06, | |
| "loss": 1.2588, | |
| "num_input_tokens_seen": 245891072, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.21120107962213225, | |
| "grad_norm": 0.3142881691455841, | |
| "learning_rate": 1.166386083291604e-06, | |
| "loss": 1.5491, | |
| "num_input_tokens_seen": 246153216, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 0.2114260008996851, | |
| "grad_norm": 0.33687466382980347, | |
| "learning_rate": 1.1292052856952062e-06, | |
| "loss": 1.7112, | |
| "num_input_tokens_seen": 246415360, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.21165092217723797, | |
| "grad_norm": 0.23561953008174896, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.3672, | |
| "num_input_tokens_seen": 246677504, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 0.21187584345479082, | |
| "grad_norm": 0.24282871186733246, | |
| "learning_rate": 1.0566305619157502e-06, | |
| "loss": 1.5446, | |
| "num_input_tokens_seen": 246939648, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 0.21210076473234368, | |
| "grad_norm": 0.3530779778957367, | |
| "learning_rate": 1.0212375200327973e-06, | |
| "loss": 1.623, | |
| "num_input_tokens_seen": 247201792, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 0.21232568600989654, | |
| "grad_norm": 0.2710437774658203, | |
| "learning_rate": 9.864412689139123e-07, | |
| "loss": 1.0911, | |
| "num_input_tokens_seen": 247463936, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 0.2125506072874494, | |
| "grad_norm": 0.3001916706562042, | |
| "learning_rate": 9.522422325404235e-07, | |
| "loss": 2.0527, | |
| "num_input_tokens_seen": 247726080, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.21277552856500226, | |
| "grad_norm": 0.5507198572158813, | |
| "learning_rate": 9.186408276168013e-07, | |
| "loss": 1.3133, | |
| "num_input_tokens_seen": 247988224, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.21300044984255512, | |
| "grad_norm": 0.4351663887500763, | |
| "learning_rate": 8.856374635655695e-07, | |
| "loss": 1.5783, | |
| "num_input_tokens_seen": 248250368, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 0.21322537112010798, | |
| "grad_norm": 0.352603942155838, | |
| "learning_rate": 8.53232542522292e-07, | |
| "loss": 1.1274, | |
| "num_input_tokens_seen": 248512512, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 0.2134502923976608, | |
| "grad_norm": 0.25265082716941833, | |
| "learning_rate": 8.214264593307098e-07, | |
| "loss": 0.9922, | |
| "num_input_tokens_seen": 248774656, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 0.21367521367521367, | |
| "grad_norm": 0.27736958861351013, | |
| "learning_rate": 7.90219601537906e-07, | |
| "loss": 1.0984, | |
| "num_input_tokens_seen": 249036800, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.21390013495276652, | |
| "grad_norm": 0.22481057047843933, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.6848, | |
| "num_input_tokens_seen": 249298944, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 0.21412505623031938, | |
| "grad_norm": 0.514091432094574, | |
| "learning_rate": 7.296050758254957e-07, | |
| "loss": 1.6769, | |
| "num_input_tokens_seen": 249561088, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.21434997750787224, | |
| "grad_norm": 0.39093077182769775, | |
| "learning_rate": 7.001981464747565e-07, | |
| "loss": 1.7747, | |
| "num_input_tokens_seen": 249823232, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 0.2145748987854251, | |
| "grad_norm": 0.3265654444694519, | |
| "learning_rate": 6.713919196515317e-07, | |
| "loss": 1.3205, | |
| "num_input_tokens_seen": 250085376, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 0.21479982006297796, | |
| "grad_norm": 0.25656867027282715, | |
| "learning_rate": 6.431867463506048e-07, | |
| "loss": 1.0319, | |
| "num_input_tokens_seen": 250347520, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.21502474134053082, | |
| "grad_norm": 0.31202375888824463, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 1.5286, | |
| "num_input_tokens_seen": 250609664, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 0.21524966261808368, | |
| "grad_norm": 0.2782678008079529, | |
| "learning_rate": 5.885809276723608e-07, | |
| "loss": 1.8345, | |
| "num_input_tokens_seen": 250871808, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 0.21547458389563653, | |
| "grad_norm": 0.2971605062484741, | |
| "learning_rate": 5.621809476497098e-07, | |
| "loss": 1.0085, | |
| "num_input_tokens_seen": 251133952, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 0.2156995051731894, | |
| "grad_norm": 0.2913457751274109, | |
| "learning_rate": 5.363833518505834e-07, | |
| "loss": 1.1763, | |
| "num_input_tokens_seen": 251396096, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 0.21592442645074225, | |
| "grad_norm": 0.38938575983047485, | |
| "learning_rate": 5.111884546105506e-07, | |
| "loss": 1.1027, | |
| "num_input_tokens_seen": 251658240, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.2161493477282951, | |
| "grad_norm": 0.22164541482925415, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.7649, | |
| "num_input_tokens_seen": 251920384, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 0.21637426900584794, | |
| "grad_norm": 0.47079649567604065, | |
| "learning_rate": 4.6260797642782014e-07, | |
| "loss": 1.5604, | |
| "num_input_tokens_seen": 252182528, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 0.2165991902834008, | |
| "grad_norm": 0.27684617042541504, | |
| "learning_rate": 4.392229874229159e-07, | |
| "loss": 1.3192, | |
| "num_input_tokens_seen": 252444672, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 0.21682411156095366, | |
| "grad_norm": 0.7537292838096619, | |
| "learning_rate": 4.1644188084548063e-07, | |
| "loss": 1.6492, | |
| "num_input_tokens_seen": 252706816, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 0.21704903283850652, | |
| "grad_norm": 0.26928630471229553, | |
| "learning_rate": 3.9426493427611177e-07, | |
| "loss": 1.325, | |
| "num_input_tokens_seen": 252968960, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.21727395411605938, | |
| "grad_norm": 0.2575208842754364, | |
| "learning_rate": 3.7269241793390085e-07, | |
| "loss": 1.5905, | |
| "num_input_tokens_seen": 253231104, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.21749887539361223, | |
| "grad_norm": 0.23125195503234863, | |
| "learning_rate": 3.517245946731529e-07, | |
| "loss": 1.2487, | |
| "num_input_tokens_seen": 253493248, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 0.2177237966711651, | |
| "grad_norm": 0.3252660036087036, | |
| "learning_rate": 3.3136171998017775e-07, | |
| "loss": 1.4039, | |
| "num_input_tokens_seen": 253755392, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 0.21794871794871795, | |
| "grad_norm": 0.25830793380737305, | |
| "learning_rate": 3.1160404197018154e-07, | |
| "loss": 1.2268, | |
| "num_input_tokens_seen": 254017536, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 0.2181736392262708, | |
| "grad_norm": 0.25022169947624207, | |
| "learning_rate": 2.924518013842303e-07, | |
| "loss": 1.4004, | |
| "num_input_tokens_seen": 254279680, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.21839856050382367, | |
| "grad_norm": 0.2369910031557083, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 1.3025, | |
| "num_input_tokens_seen": 254541824, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 0.21862348178137653, | |
| "grad_norm": 0.28356534242630005, | |
| "learning_rate": 2.5596455856058963e-07, | |
| "loss": 1.8499, | |
| "num_input_tokens_seen": 254803968, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.21884840305892939, | |
| "grad_norm": 0.27577951550483704, | |
| "learning_rate": 2.386300009084408e-07, | |
| "loss": 0.9913, | |
| "num_input_tokens_seen": 255066112, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 0.21907332433648224, | |
| "grad_norm": 0.6673069000244141, | |
| "learning_rate": 2.219017698460002e-07, | |
| "loss": 1.4078, | |
| "num_input_tokens_seen": 255328256, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 0.21929824561403508, | |
| "grad_norm": 0.27162426710128784, | |
| "learning_rate": 2.057800692014833e-07, | |
| "loss": 1.8649, | |
| "num_input_tokens_seen": 255590400, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.21952316689158793, | |
| "grad_norm": 0.46019431948661804, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 1.4329, | |
| "num_input_tokens_seen": 255852544, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 0.2197480881691408, | |
| "grad_norm": 0.28555309772491455, | |
| "learning_rate": 1.753570375247815e-07, | |
| "loss": 1.6036, | |
| "num_input_tokens_seen": 256114688, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 0.21997300944669365, | |
| "grad_norm": 0.3448443114757538, | |
| "learning_rate": 1.6105607718764347e-07, | |
| "loss": 1.2266, | |
| "num_input_tokens_seen": 256376832, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 0.2201979307242465, | |
| "grad_norm": 0.32888004183769226, | |
| "learning_rate": 1.4736238865398765e-07, | |
| "loss": 1.4776, | |
| "num_input_tokens_seen": 256638976, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 0.22042285200179937, | |
| "grad_norm": 0.4627322256565094, | |
| "learning_rate": 1.342761387770952e-07, | |
| "loss": 1.3864, | |
| "num_input_tokens_seen": 256901120, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.22064777327935223, | |
| "grad_norm": 0.3258611559867859, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.3963, | |
| "num_input_tokens_seen": 257163264, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 0.22087269455690509, | |
| "grad_norm": 0.47918933629989624, | |
| "learning_rate": 1.0992658539750178e-07, | |
| "loss": 1.6036, | |
| "num_input_tokens_seen": 257425408, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 0.22109761583445794, | |
| "grad_norm": 0.22977593541145325, | |
| "learning_rate": 9.866357858642205e-08, | |
| "loss": 1.4893, | |
| "num_input_tokens_seen": 257687552, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 0.2213225371120108, | |
| "grad_norm": 0.28588688373565674, | |
| "learning_rate": 8.800860381173448e-08, | |
| "loss": 1.9434, | |
| "num_input_tokens_seen": 257949696, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 0.22154745838956366, | |
| "grad_norm": 0.25447309017181396, | |
| "learning_rate": 7.796179090094891e-08, | |
| "loss": 1.3682, | |
| "num_input_tokens_seen": 258211840, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.22177237966711652, | |
| "grad_norm": 0.2756679058074951, | |
| "learning_rate": 6.852326227130834e-08, | |
| "loss": 1.2565, | |
| "num_input_tokens_seen": 258473984, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 0.22199730094466938, | |
| "grad_norm": 0.40191200375556946, | |
| "learning_rate": 5.969313292830125e-08, | |
| "loss": 1.8224, | |
| "num_input_tokens_seen": 258736128, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.36071062088012695, | |
| "learning_rate": 5.1471510464268236e-08, | |
| "loss": 1.7145, | |
| "num_input_tokens_seen": 258998272, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.22244714349977507, | |
| "grad_norm": 0.24019958078861237, | |
| "learning_rate": 4.385849505708084e-08, | |
| "loss": 1.6252, | |
| "num_input_tokens_seen": 259260416, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 0.22267206477732793, | |
| "grad_norm": 0.3141970932483673, | |
| "learning_rate": 3.685417946894254e-08, | |
| "loss": 1.1591, | |
| "num_input_tokens_seen": 259522560, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.22289698605488079, | |
| "grad_norm": 0.2234763503074646, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 1.467, | |
| "num_input_tokens_seen": 259784704, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 0.22312190733243364, | |
| "grad_norm": 0.45924562215805054, | |
| "learning_rate": 2.467198171342e-08, | |
| "loss": 1.3947, | |
| "num_input_tokens_seen": 260046848, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 0.2233468286099865, | |
| "grad_norm": 0.30663082003593445, | |
| "learning_rate": 1.949424798228239e-08, | |
| "loss": 0.8988, | |
| "num_input_tokens_seen": 260308992, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 0.22357174988753936, | |
| "grad_norm": 0.3375454545021057, | |
| "learning_rate": 1.4925510940844156e-08, | |
| "loss": 1.8355, | |
| "num_input_tokens_seen": 260571136, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.22379667116509222, | |
| "grad_norm": 0.28863683342933655, | |
| "learning_rate": 1.096582625772502e-08, | |
| "loss": 1.0786, | |
| "num_input_tokens_seen": 260833280, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.22402159244264508, | |
| "grad_norm": 0.3245282471179962, | |
| "learning_rate": 7.615242180436522e-09, | |
| "loss": 1.0296, | |
| "num_input_tokens_seen": 261095424, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 0.22424651372019794, | |
| "grad_norm": 0.3670142590999603, | |
| "learning_rate": 4.873799534788059e-09, | |
| "loss": 1.6158, | |
| "num_input_tokens_seen": 261357568, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 0.2244714349977508, | |
| "grad_norm": 0.22898231446743011, | |
| "learning_rate": 2.741531724392843e-09, | |
| "loss": 1.0204, | |
| "num_input_tokens_seen": 261619712, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 0.22469635627530365, | |
| "grad_norm": 0.28812992572784424, | |
| "learning_rate": 1.2184647302626583e-09, | |
| "loss": 1.9515, | |
| "num_input_tokens_seen": 261881856, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 0.2249212775528565, | |
| "grad_norm": 0.2852112948894501, | |
| "learning_rate": 3.0461711048035415e-10, | |
| "loss": 2.1085, | |
| "num_input_tokens_seen": 262144000, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2249212775528565, | |
| "num_input_tokens_seen": 262144000, | |
| "step": 1000, | |
| "total_flos": 5.715019849269248e+18, | |
| "train_loss": 1.4907063425183296, | |
| "train_runtime": 24201.9893, | |
| "train_samples_per_second": 0.331, | |
| "train_steps_per_second": 0.041 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 262144000, | |
| "num_train_epochs": 1, | |
| "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": 5.715019849269248e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |