| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2467308166790032, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002467308166790032, | |
| "grad_norm": 16.683284759521484, | |
| "learning_rate": 0.0, | |
| "loss": 2.5206, | |
| "num_input_tokens_seen": 262144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004934616333580064, | |
| "grad_norm": 19.499160766601562, | |
| "learning_rate": 1.0000000000000001e-07, | |
| "loss": 2.1037, | |
| "num_input_tokens_seen": 524288, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007401924500370096, | |
| "grad_norm": 15.584578514099121, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 2.1221, | |
| "num_input_tokens_seen": 786432, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009869232667160128, | |
| "grad_norm": 18.40481185913086, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 1.9157, | |
| "num_input_tokens_seen": 1048576, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001233654083395016, | |
| "grad_norm": 19.92998504638672, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 2.6474, | |
| "num_input_tokens_seen": 1310720, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014803849000740192, | |
| "grad_norm": 19.297449111938477, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 2.4133, | |
| "num_input_tokens_seen": 1572864, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017271157167530224, | |
| "grad_norm": 22.468198776245117, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 2.6828, | |
| "num_input_tokens_seen": 1835008, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0019738465334320256, | |
| "grad_norm": 17.352039337158203, | |
| "learning_rate": 7.000000000000001e-07, | |
| "loss": 2.3061, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0022205773501110288, | |
| "grad_norm": 12.8675537109375, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 2.0333, | |
| "num_input_tokens_seen": 2359296, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002467308166790032, | |
| "grad_norm": 14.969992637634277, | |
| "learning_rate": 9.000000000000001e-07, | |
| "loss": 2.5559, | |
| "num_input_tokens_seen": 2621440, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002714038983469035, | |
| "grad_norm": 15.295183181762695, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 2.557, | |
| "num_input_tokens_seen": 2883584, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0029607698001480384, | |
| "grad_norm": 10.054173469543457, | |
| "learning_rate": 1.1e-06, | |
| "loss": 2.1582, | |
| "num_input_tokens_seen": 3145728, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0032075006168270415, | |
| "grad_norm": 10.735544204711914, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 2.0169, | |
| "num_input_tokens_seen": 3407872, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0034542314335060447, | |
| "grad_norm": 11.899219512939453, | |
| "learning_rate": 1.3e-06, | |
| "loss": 2.4531, | |
| "num_input_tokens_seen": 3670016, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003700962250185048, | |
| "grad_norm": 13.826565742492676, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 2.3567, | |
| "num_input_tokens_seen": 3932160, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003947693066864051, | |
| "grad_norm": 6.6798224449157715, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.6159, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004194423883543055, | |
| "grad_norm": 8.633581161499023, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 2.4096, | |
| "num_input_tokens_seen": 4456448, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0044411547002220575, | |
| "grad_norm": 7.755622863769531, | |
| "learning_rate": 1.7000000000000002e-06, | |
| "loss": 2.2198, | |
| "num_input_tokens_seen": 4718592, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004687885516901061, | |
| "grad_norm": 7.24108362197876, | |
| "learning_rate": 1.8000000000000001e-06, | |
| "loss": 2.195, | |
| "num_input_tokens_seen": 4980736, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004934616333580064, | |
| "grad_norm": 5.231243133544922, | |
| "learning_rate": 1.9000000000000002e-06, | |
| "loss": 1.9149, | |
| "num_input_tokens_seen": 5242880, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0051813471502590676, | |
| "grad_norm": 15.724678993225098, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.4373, | |
| "num_input_tokens_seen": 5505024, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00542807796693807, | |
| "grad_norm": 4.023858547210693, | |
| "learning_rate": 2.1000000000000002e-06, | |
| "loss": 2.093, | |
| "num_input_tokens_seen": 5767168, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005674808783617074, | |
| "grad_norm": 3.049189329147339, | |
| "learning_rate": 2.2e-06, | |
| "loss": 2.3108, | |
| "num_input_tokens_seen": 6029312, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005921539600296077, | |
| "grad_norm": 4.3906354904174805, | |
| "learning_rate": 2.3000000000000004e-06, | |
| "loss": 2.0827, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00616827041697508, | |
| "grad_norm": 3.7468109130859375, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 2.312, | |
| "num_input_tokens_seen": 6553600, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006415001233654083, | |
| "grad_norm": 3.3470516204833984, | |
| "learning_rate": 2.5e-06, | |
| "loss": 2.5401, | |
| "num_input_tokens_seen": 6815744, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006661732050333087, | |
| "grad_norm": 2.9284937381744385, | |
| "learning_rate": 2.6e-06, | |
| "loss": 1.8949, | |
| "num_input_tokens_seen": 7077888, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0069084628670120895, | |
| "grad_norm": 3.228973388671875, | |
| "learning_rate": 2.7000000000000004e-06, | |
| "loss": 2.123, | |
| "num_input_tokens_seen": 7340032, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007155193683691093, | |
| "grad_norm": 2.123669385910034, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 2.0715, | |
| "num_input_tokens_seen": 7602176, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007401924500370096, | |
| "grad_norm": 2.808058977127075, | |
| "learning_rate": 2.9e-06, | |
| "loss": 1.9762, | |
| "num_input_tokens_seen": 7864320, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0076486553170490995, | |
| "grad_norm": 2.9628617763519287, | |
| "learning_rate": 3e-06, | |
| "loss": 2.4305, | |
| "num_input_tokens_seen": 8126464, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007895386133728102, | |
| "grad_norm": 2.185053586959839, | |
| "learning_rate": 3.1000000000000004e-06, | |
| "loss": 2.3956, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008142116950407105, | |
| "grad_norm": 1.7794125080108643, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 2.3345, | |
| "num_input_tokens_seen": 8650752, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00838884776708611, | |
| "grad_norm": 1.2772505283355713, | |
| "learning_rate": 3.3000000000000006e-06, | |
| "loss": 2.173, | |
| "num_input_tokens_seen": 8912896, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008635578583765112, | |
| "grad_norm": 1.7572567462921143, | |
| "learning_rate": 3.4000000000000005e-06, | |
| "loss": 2.2358, | |
| "num_input_tokens_seen": 9175040, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008882309400444115, | |
| "grad_norm": 4.534196853637695, | |
| "learning_rate": 3.5e-06, | |
| "loss": 1.7227, | |
| "num_input_tokens_seen": 9437184, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009129040217123118, | |
| "grad_norm": 1.3536083698272705, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 1.5496, | |
| "num_input_tokens_seen": 9699328, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009375771033802122, | |
| "grad_norm": 2.4008381366729736, | |
| "learning_rate": 3.7e-06, | |
| "loss": 2.3225, | |
| "num_input_tokens_seen": 9961472, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.009622501850481125, | |
| "grad_norm": 1.4890753030776978, | |
| "learning_rate": 3.8000000000000005e-06, | |
| "loss": 2.2718, | |
| "num_input_tokens_seen": 10223616, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009869232667160128, | |
| "grad_norm": 22.986099243164062, | |
| "learning_rate": 3.900000000000001e-06, | |
| "loss": 1.8245, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010115963483839132, | |
| "grad_norm": 3.394990921020508, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.991, | |
| "num_input_tokens_seen": 10747904, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010362694300518135, | |
| "grad_norm": 1.8627941608428955, | |
| "learning_rate": 4.1e-06, | |
| "loss": 2.2176, | |
| "num_input_tokens_seen": 11010048, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010609425117197138, | |
| "grad_norm": 9.628961563110352, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 2.1058, | |
| "num_input_tokens_seen": 11272192, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01085615593387614, | |
| "grad_norm": 1.0936553478240967, | |
| "learning_rate": 4.3e-06, | |
| "loss": 2.2169, | |
| "num_input_tokens_seen": 11534336, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011102886750555145, | |
| "grad_norm": 1.0321332216262817, | |
| "learning_rate": 4.4e-06, | |
| "loss": 1.7619, | |
| "num_input_tokens_seen": 11796480, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011349617567234148, | |
| "grad_norm": 19.57929039001465, | |
| "learning_rate": 4.5e-06, | |
| "loss": 2.0291, | |
| "num_input_tokens_seen": 12058624, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01159634838391315, | |
| "grad_norm": 1.3844197988510132, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 2.2314, | |
| "num_input_tokens_seen": 12320768, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.011843079200592153, | |
| "grad_norm": 0.850957453250885, | |
| "learning_rate": 4.7e-06, | |
| "loss": 1.8677, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012089810017271158, | |
| "grad_norm": 1.143416166305542, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.8022, | |
| "num_input_tokens_seen": 12845056, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01233654083395016, | |
| "grad_norm": 1.5641077756881714, | |
| "learning_rate": 4.9000000000000005e-06, | |
| "loss": 1.97, | |
| "num_input_tokens_seen": 13107200, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012583271650629163, | |
| "grad_norm": 1.3804495334625244, | |
| "learning_rate": 5e-06, | |
| "loss": 1.9272, | |
| "num_input_tokens_seen": 13369344, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.012830002467308166, | |
| "grad_norm": 1.558229684829712, | |
| "learning_rate": 5.1e-06, | |
| "loss": 2.062, | |
| "num_input_tokens_seen": 13631488, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.01307673328398717, | |
| "grad_norm": 11.860638618469238, | |
| "learning_rate": 5.2e-06, | |
| "loss": 2.3097, | |
| "num_input_tokens_seen": 13893632, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.013323464100666173, | |
| "grad_norm": 0.9336137175559998, | |
| "learning_rate": 5.300000000000001e-06, | |
| "loss": 1.8883, | |
| "num_input_tokens_seen": 14155776, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.013570194917345176, | |
| "grad_norm": 1.0054830312728882, | |
| "learning_rate": 5.400000000000001e-06, | |
| "loss": 2.1054, | |
| "num_input_tokens_seen": 14417920, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.013816925734024179, | |
| "grad_norm": 0.8040982484817505, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 1.704, | |
| "num_input_tokens_seen": 14680064, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.014063656550703183, | |
| "grad_norm": 0.8780809640884399, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 1.5234, | |
| "num_input_tokens_seen": 14942208, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.014310387367382186, | |
| "grad_norm": 1.0134830474853516, | |
| "learning_rate": 5.7e-06, | |
| "loss": 1.8635, | |
| "num_input_tokens_seen": 15204352, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.014557118184061189, | |
| "grad_norm": 1.2978655099868774, | |
| "learning_rate": 5.8e-06, | |
| "loss": 1.8941, | |
| "num_input_tokens_seen": 15466496, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.014803849000740192, | |
| "grad_norm": 1.0360183715820312, | |
| "learning_rate": 5.9e-06, | |
| "loss": 1.5408, | |
| "num_input_tokens_seen": 15728640, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.015050579817419196, | |
| "grad_norm": 1.1055400371551514, | |
| "learning_rate": 6e-06, | |
| "loss": 2.3942, | |
| "num_input_tokens_seen": 15990784, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.015297310634098199, | |
| "grad_norm": 0.677260160446167, | |
| "learning_rate": 6.1e-06, | |
| "loss": 2.2286, | |
| "num_input_tokens_seen": 16252928, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.015544041450777202, | |
| "grad_norm": 2.7347521781921387, | |
| "learning_rate": 6.200000000000001e-06, | |
| "loss": 1.5486, | |
| "num_input_tokens_seen": 16515072, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.015790772267456205, | |
| "grad_norm": 0.5401502847671509, | |
| "learning_rate": 6.300000000000001e-06, | |
| "loss": 2.0308, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.016037503084135207, | |
| "grad_norm": 1.037590503692627, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 1.4798, | |
| "num_input_tokens_seen": 17039360, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01628423390081421, | |
| "grad_norm": 0.6973419189453125, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 2.0788, | |
| "num_input_tokens_seen": 17301504, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.016530964717493216, | |
| "grad_norm": 0.8023918271064758, | |
| "learning_rate": 6.600000000000001e-06, | |
| "loss": 1.7997, | |
| "num_input_tokens_seen": 17563648, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.01677769553417222, | |
| "grad_norm": 0.6638779640197754, | |
| "learning_rate": 6.700000000000001e-06, | |
| "loss": 1.9026, | |
| "num_input_tokens_seen": 17825792, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.017024426350851222, | |
| "grad_norm": 0.6551264524459839, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 1.7984, | |
| "num_input_tokens_seen": 18087936, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.017271157167530225, | |
| "grad_norm": 1.490675687789917, | |
| "learning_rate": 6.9e-06, | |
| "loss": 1.7201, | |
| "num_input_tokens_seen": 18350080, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.017517887984209227, | |
| "grad_norm": 1.0823466777801514, | |
| "learning_rate": 7e-06, | |
| "loss": 1.7211, | |
| "num_input_tokens_seen": 18612224, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.01776461880088823, | |
| "grad_norm": 0.6104586124420166, | |
| "learning_rate": 7.100000000000001e-06, | |
| "loss": 1.1804, | |
| "num_input_tokens_seen": 18874368, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.018011349617567233, | |
| "grad_norm": 0.562042236328125, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 1.3951, | |
| "num_input_tokens_seen": 19136512, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.018258080434246236, | |
| "grad_norm": 0.7759392261505127, | |
| "learning_rate": 7.3e-06, | |
| "loss": 2.0176, | |
| "num_input_tokens_seen": 19398656, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.018504811250925242, | |
| "grad_norm": 1.0909373760223389, | |
| "learning_rate": 7.4e-06, | |
| "loss": 1.981, | |
| "num_input_tokens_seen": 19660800, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.018751542067604245, | |
| "grad_norm": 1.069872498512268, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.6917, | |
| "num_input_tokens_seen": 19922944, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.018998272884283247, | |
| "grad_norm": 0.7408702373504639, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 2.0653, | |
| "num_input_tokens_seen": 20185088, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.01924500370096225, | |
| "grad_norm": 2.0848100185394287, | |
| "learning_rate": 7.7e-06, | |
| "loss": 1.704, | |
| "num_input_tokens_seen": 20447232, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.019491734517641253, | |
| "grad_norm": 0.908286988735199, | |
| "learning_rate": 7.800000000000002e-06, | |
| "loss": 2.208, | |
| "num_input_tokens_seen": 20709376, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.019738465334320256, | |
| "grad_norm": 0.746882975101471, | |
| "learning_rate": 7.9e-06, | |
| "loss": 1.6077, | |
| "num_input_tokens_seen": 20971520, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01998519615099926, | |
| "grad_norm": 1.8665310144424438, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.0049, | |
| "num_input_tokens_seen": 21233664, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.020231926967678265, | |
| "grad_norm": 0.5606961846351624, | |
| "learning_rate": 8.1e-06, | |
| "loss": 2.0754, | |
| "num_input_tokens_seen": 21495808, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.020478657784357267, | |
| "grad_norm": 8.728538513183594, | |
| "learning_rate": 8.2e-06, | |
| "loss": 1.8255, | |
| "num_input_tokens_seen": 21757952, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.02072538860103627, | |
| "grad_norm": 1.3503004312515259, | |
| "learning_rate": 8.3e-06, | |
| "loss": 1.5528, | |
| "num_input_tokens_seen": 22020096, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.020972119417715273, | |
| "grad_norm": 0.989362895488739, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 2.1408, | |
| "num_input_tokens_seen": 22282240, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.021218850234394276, | |
| "grad_norm": 0.6346938610076904, | |
| "learning_rate": 8.5e-06, | |
| "loss": 2.0522, | |
| "num_input_tokens_seen": 22544384, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.02146558105107328, | |
| "grad_norm": 0.9276885390281677, | |
| "learning_rate": 8.6e-06, | |
| "loss": 2.0185, | |
| "num_input_tokens_seen": 22806528, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.02171231186775228, | |
| "grad_norm": 0.44476205110549927, | |
| "learning_rate": 8.700000000000001e-06, | |
| "loss": 2.1696, | |
| "num_input_tokens_seen": 23068672, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.021959042684431284, | |
| "grad_norm": 0.5806407332420349, | |
| "learning_rate": 8.8e-06, | |
| "loss": 2.0952, | |
| "num_input_tokens_seen": 23330816, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.02220577350111029, | |
| "grad_norm": 0.3519119620323181, | |
| "learning_rate": 8.900000000000001e-06, | |
| "loss": 1.5856, | |
| "num_input_tokens_seen": 23592960, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.022452504317789293, | |
| "grad_norm": 0.5435070991516113, | |
| "learning_rate": 9e-06, | |
| "loss": 1.5677, | |
| "num_input_tokens_seen": 23855104, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.022699235134468296, | |
| "grad_norm": 0.5541613101959229, | |
| "learning_rate": 9.100000000000001e-06, | |
| "loss": 2.0635, | |
| "num_input_tokens_seen": 24117248, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.0229459659511473, | |
| "grad_norm": 0.8948331475257874, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 1.386, | |
| "num_input_tokens_seen": 24379392, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0231926967678263, | |
| "grad_norm": 0.39605551958084106, | |
| "learning_rate": 9.3e-06, | |
| "loss": 1.3151, | |
| "num_input_tokens_seen": 24641536, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.023439427584505304, | |
| "grad_norm": 0.4620722234249115, | |
| "learning_rate": 9.4e-06, | |
| "loss": 1.5472, | |
| "num_input_tokens_seen": 24903680, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.023686158401184307, | |
| "grad_norm": 0.8512610197067261, | |
| "learning_rate": 9.5e-06, | |
| "loss": 1.918, | |
| "num_input_tokens_seen": 25165824, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.02393288921786331, | |
| "grad_norm": 1.0007725954055786, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 2.0203, | |
| "num_input_tokens_seen": 25427968, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.024179620034542316, | |
| "grad_norm": 0.558268129825592, | |
| "learning_rate": 9.7e-06, | |
| "loss": 1.7781, | |
| "num_input_tokens_seen": 25690112, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.02442635085122132, | |
| "grad_norm": 0.33053046464920044, | |
| "learning_rate": 9.800000000000001e-06, | |
| "loss": 1.9374, | |
| "num_input_tokens_seen": 25952256, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.02467308166790032, | |
| "grad_norm": 0.47462955117225647, | |
| "learning_rate": 9.9e-06, | |
| "loss": 1.7824, | |
| "num_input_tokens_seen": 26214400, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.024919812484579324, | |
| "grad_norm": 0.5819123983383179, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7157, | |
| "num_input_tokens_seen": 26476544, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.025166543301258327, | |
| "grad_norm": 0.4024888575077057, | |
| "learning_rate": 9.999969538288953e-06, | |
| "loss": 1.6603, | |
| "num_input_tokens_seen": 26738688, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.02541327411793733, | |
| "grad_norm": 0.4729028046131134, | |
| "learning_rate": 9.999878153526974e-06, | |
| "loss": 2.4554, | |
| "num_input_tokens_seen": 27000832, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.025660004934616332, | |
| "grad_norm": 0.6632626056671143, | |
| "learning_rate": 9.999725846827562e-06, | |
| "loss": 1.8782, | |
| "num_input_tokens_seen": 27262976, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.025906735751295335, | |
| "grad_norm": 1.9816948175430298, | |
| "learning_rate": 9.999512620046523e-06, | |
| "loss": 1.7047, | |
| "num_input_tokens_seen": 27525120, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02615346656797434, | |
| "grad_norm": 0.40769246220588684, | |
| "learning_rate": 9.999238475781957e-06, | |
| "loss": 1.6149, | |
| "num_input_tokens_seen": 27787264, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.026400197384653344, | |
| "grad_norm": 0.3405158221721649, | |
| "learning_rate": 9.998903417374228e-06, | |
| "loss": 2.0906, | |
| "num_input_tokens_seen": 28049408, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.026646928201332347, | |
| "grad_norm": 0.497395396232605, | |
| "learning_rate": 9.998507448905917e-06, | |
| "loss": 1.5876, | |
| "num_input_tokens_seen": 28311552, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.02689365901801135, | |
| "grad_norm": 0.4290633499622345, | |
| "learning_rate": 9.998050575201772e-06, | |
| "loss": 1.5216, | |
| "num_input_tokens_seen": 28573696, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.027140389834690352, | |
| "grad_norm": 0.3609262704849243, | |
| "learning_rate": 9.997532801828659e-06, | |
| "loss": 2.1408, | |
| "num_input_tokens_seen": 28835840, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.027387120651369355, | |
| "grad_norm": 0.6255217790603638, | |
| "learning_rate": 9.99695413509548e-06, | |
| "loss": 1.1463, | |
| "num_input_tokens_seen": 29097984, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.027633851468048358, | |
| "grad_norm": 0.6729506850242615, | |
| "learning_rate": 9.996314582053106e-06, | |
| "loss": 1.3884, | |
| "num_input_tokens_seen": 29360128, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.02788058228472736, | |
| "grad_norm": 0.3117102086544037, | |
| "learning_rate": 9.995614150494293e-06, | |
| "loss": 1.6354, | |
| "num_input_tokens_seen": 29622272, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.028127313101406367, | |
| "grad_norm": 0.7941350936889648, | |
| "learning_rate": 9.994852848953574e-06, | |
| "loss": 1.4103, | |
| "num_input_tokens_seen": 29884416, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.02837404391808537, | |
| "grad_norm": 0.552463710308075, | |
| "learning_rate": 9.994030686707171e-06, | |
| "loss": 1.4375, | |
| "num_input_tokens_seen": 30146560, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.028620774734764372, | |
| "grad_norm": 0.4415859878063202, | |
| "learning_rate": 9.993147673772869e-06, | |
| "loss": 1.554, | |
| "num_input_tokens_seen": 30408704, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.028867505551443375, | |
| "grad_norm": 0.3809610903263092, | |
| "learning_rate": 9.992203820909906e-06, | |
| "loss": 1.5911, | |
| "num_input_tokens_seen": 30670848, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.029114236368122378, | |
| "grad_norm": 0.3418121635913849, | |
| "learning_rate": 9.991199139618828e-06, | |
| "loss": 1.5202, | |
| "num_input_tokens_seen": 30932992, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.02936096718480138, | |
| "grad_norm": 0.4744432270526886, | |
| "learning_rate": 9.990133642141359e-06, | |
| "loss": 1.8556, | |
| "num_input_tokens_seen": 31195136, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.029607698001480384, | |
| "grad_norm": 0.5877406001091003, | |
| "learning_rate": 9.989007341460251e-06, | |
| "loss": 2.0399, | |
| "num_input_tokens_seen": 31457280, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02985442881815939, | |
| "grad_norm": 0.7880735397338867, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 1.7712, | |
| "num_input_tokens_seen": 31719424, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.030101159634838393, | |
| "grad_norm": 0.5546642541885376, | |
| "learning_rate": 9.98657238612229e-06, | |
| "loss": 1.6735, | |
| "num_input_tokens_seen": 31981568, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.030347890451517395, | |
| "grad_norm": 0.32245898246765137, | |
| "learning_rate": 9.985263761134602e-06, | |
| "loss": 1.7308, | |
| "num_input_tokens_seen": 32243712, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.030594621268196398, | |
| "grad_norm": 0.7740073204040527, | |
| "learning_rate": 9.983894392281237e-06, | |
| "loss": 1.4024, | |
| "num_input_tokens_seen": 32505856, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.0308413520848754, | |
| "grad_norm": 0.5259237885475159, | |
| "learning_rate": 9.982464296247523e-06, | |
| "loss": 1.8065, | |
| "num_input_tokens_seen": 32768000, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.031088082901554404, | |
| "grad_norm": 1.6967214345932007, | |
| "learning_rate": 9.980973490458728e-06, | |
| "loss": 1.787, | |
| "num_input_tokens_seen": 33030144, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.031334813718233406, | |
| "grad_norm": 0.3362340033054352, | |
| "learning_rate": 9.979421993079853e-06, | |
| "loss": 2.2669, | |
| "num_input_tokens_seen": 33292288, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.03158154453491241, | |
| "grad_norm": 0.49716174602508545, | |
| "learning_rate": 9.9778098230154e-06, | |
| "loss": 1.9467, | |
| "num_input_tokens_seen": 33554432, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.03182827535159141, | |
| "grad_norm": 0.31525981426239014, | |
| "learning_rate": 9.976136999909156e-06, | |
| "loss": 2.0196, | |
| "num_input_tokens_seen": 33816576, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.032075006168270415, | |
| "grad_norm": 0.4798625707626343, | |
| "learning_rate": 9.974403544143942e-06, | |
| "loss": 1.4132, | |
| "num_input_tokens_seen": 34078720, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03232173698494942, | |
| "grad_norm": 0.3842827081680298, | |
| "learning_rate": 9.972609476841368e-06, | |
| "loss": 1.4007, | |
| "num_input_tokens_seen": 34340864, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.03256846780162842, | |
| "grad_norm": 0.3742620348930359, | |
| "learning_rate": 9.970754819861577e-06, | |
| "loss": 1.8558, | |
| "num_input_tokens_seen": 34603008, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.03281519861830743, | |
| "grad_norm": 0.2592817544937134, | |
| "learning_rate": 9.968839595802982e-06, | |
| "loss": 1.8881, | |
| "num_input_tokens_seen": 34865152, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.03306192943498643, | |
| "grad_norm": 0.7180063128471375, | |
| "learning_rate": 9.966863828001982e-06, | |
| "loss": 1.4668, | |
| "num_input_tokens_seen": 35127296, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.033308660251665435, | |
| "grad_norm": 0.5548637509346008, | |
| "learning_rate": 9.964827540532685e-06, | |
| "loss": 1.9784, | |
| "num_input_tokens_seen": 35389440, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.03355539106834444, | |
| "grad_norm": 0.608799397945404, | |
| "learning_rate": 9.962730758206612e-06, | |
| "loss": 1.8939, | |
| "num_input_tokens_seen": 35651584, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.03380212188502344, | |
| "grad_norm": 0.34416207671165466, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 1.8515, | |
| "num_input_tokens_seen": 35913728, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.034048852701702444, | |
| "grad_norm": 0.37716981768608093, | |
| "learning_rate": 9.958355811915452e-06, | |
| "loss": 1.7956, | |
| "num_input_tokens_seen": 36175872, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.034295583518381446, | |
| "grad_norm": 0.4558100402355194, | |
| "learning_rate": 9.95607770125771e-06, | |
| "loss": 2.0922, | |
| "num_input_tokens_seen": 36438016, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.03454231433506045, | |
| "grad_norm": 0.9773036241531372, | |
| "learning_rate": 9.953739202357219e-06, | |
| "loss": 1.1874, | |
| "num_input_tokens_seen": 36700160, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03478904515173945, | |
| "grad_norm": 0.6007382869720459, | |
| "learning_rate": 9.951340343707852e-06, | |
| "loss": 1.6766, | |
| "num_input_tokens_seen": 36962304, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.035035775968418455, | |
| "grad_norm": 0.47525718808174133, | |
| "learning_rate": 9.948881154538946e-06, | |
| "loss": 1.4628, | |
| "num_input_tokens_seen": 37224448, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.03528250678509746, | |
| "grad_norm": 1.6111029386520386, | |
| "learning_rate": 9.946361664814942e-06, | |
| "loss": 1.6761, | |
| "num_input_tokens_seen": 37486592, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.03552923760177646, | |
| "grad_norm": 0.510202944278717, | |
| "learning_rate": 9.94378190523503e-06, | |
| "loss": 1.5761, | |
| "num_input_tokens_seen": 37748736, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.03577596841845546, | |
| "grad_norm": 0.3128513693809509, | |
| "learning_rate": 9.941141907232766e-06, | |
| "loss": 1.7816, | |
| "num_input_tokens_seen": 38010880, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.036022699235134466, | |
| "grad_norm": 0.5524406433105469, | |
| "learning_rate": 9.938441702975689e-06, | |
| "loss": 2.3617, | |
| "num_input_tokens_seen": 38273024, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.03626943005181347, | |
| "grad_norm": 0.28761568665504456, | |
| "learning_rate": 9.93568132536494e-06, | |
| "loss": 1.5824, | |
| "num_input_tokens_seen": 38535168, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.03651616086849247, | |
| "grad_norm": 0.3261396288871765, | |
| "learning_rate": 9.932860808034847e-06, | |
| "loss": 1.4992, | |
| "num_input_tokens_seen": 38797312, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.03676289168517148, | |
| "grad_norm": 1.7563891410827637, | |
| "learning_rate": 9.929980185352525e-06, | |
| "loss": 2.0062, | |
| "num_input_tokens_seen": 39059456, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.037009622501850484, | |
| "grad_norm": 0.3231620192527771, | |
| "learning_rate": 9.927039492417452e-06, | |
| "loss": 1.9814, | |
| "num_input_tokens_seen": 39321600, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.037256353318529487, | |
| "grad_norm": 0.5372762084007263, | |
| "learning_rate": 9.924038765061042e-06, | |
| "loss": 1.8328, | |
| "num_input_tokens_seen": 39583744, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.03750308413520849, | |
| "grad_norm": 0.5384396314620972, | |
| "learning_rate": 9.92097803984621e-06, | |
| "loss": 1.9721, | |
| "num_input_tokens_seen": 39845888, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.03774981495188749, | |
| "grad_norm": 0.3716285228729248, | |
| "learning_rate": 9.91785735406693e-06, | |
| "loss": 1.8848, | |
| "num_input_tokens_seen": 40108032, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.037996545768566495, | |
| "grad_norm": 0.3303345739841461, | |
| "learning_rate": 9.914676745747772e-06, | |
| "loss": 1.83, | |
| "num_input_tokens_seen": 40370176, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.0382432765852455, | |
| "grad_norm": 0.4025614559650421, | |
| "learning_rate": 9.911436253643445e-06, | |
| "loss": 1.9444, | |
| "num_input_tokens_seen": 40632320, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.0384900074019245, | |
| "grad_norm": 0.3882172107696533, | |
| "learning_rate": 9.908135917238321e-06, | |
| "loss": 1.7647, | |
| "num_input_tokens_seen": 40894464, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.0387367382186035, | |
| "grad_norm": 0.3332440257072449, | |
| "learning_rate": 9.904775776745959e-06, | |
| "loss": 1.5421, | |
| "num_input_tokens_seen": 41156608, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.038983469035282506, | |
| "grad_norm": 0.4627978205680847, | |
| "learning_rate": 9.901355873108611e-06, | |
| "loss": 1.6268, | |
| "num_input_tokens_seen": 41418752, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.03923019985196151, | |
| "grad_norm": 0.45848193764686584, | |
| "learning_rate": 9.89787624799672e-06, | |
| "loss": 1.8942, | |
| "num_input_tokens_seen": 41680896, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.03947693066864051, | |
| "grad_norm": 0.34131988883018494, | |
| "learning_rate": 9.894336943808426e-06, | |
| "loss": 1.8634, | |
| "num_input_tokens_seen": 41943040, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.039723661485319514, | |
| "grad_norm": 0.6125646233558655, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 1.7283, | |
| "num_input_tokens_seen": 42205184, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.03997039230199852, | |
| "grad_norm": 0.29789456725120544, | |
| "learning_rate": 9.887079471430481e-06, | |
| "loss": 2.0546, | |
| "num_input_tokens_seen": 42467328, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.04021712311867752, | |
| "grad_norm": 0.6001120209693909, | |
| "learning_rate": 9.883361391670841e-06, | |
| "loss": 1.9128, | |
| "num_input_tokens_seen": 42729472, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.04046385393535653, | |
| "grad_norm": 0.403012752532959, | |
| "learning_rate": 9.879583809693737e-06, | |
| "loss": 1.7995, | |
| "num_input_tokens_seen": 42991616, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.04071058475203553, | |
| "grad_norm": 0.4296472668647766, | |
| "learning_rate": 9.875746771527817e-06, | |
| "loss": 1.4867, | |
| "num_input_tokens_seen": 43253760, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.040957315568714535, | |
| "grad_norm": 0.40064001083374023, | |
| "learning_rate": 9.871850323926178e-06, | |
| "loss": 1.5266, | |
| "num_input_tokens_seen": 43515904, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.04120404638539354, | |
| "grad_norm": 0.43372851610183716, | |
| "learning_rate": 9.867894514365802e-06, | |
| "loss": 1.8959, | |
| "num_input_tokens_seen": 43778048, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.04145077720207254, | |
| "grad_norm": 0.2620079815387726, | |
| "learning_rate": 9.863879391046985e-06, | |
| "loss": 2.2592, | |
| "num_input_tokens_seen": 44040192, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.04169750801875154, | |
| "grad_norm": 0.5816200375556946, | |
| "learning_rate": 9.859805002892733e-06, | |
| "loss": 1.6409, | |
| "num_input_tokens_seen": 44302336, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.041944238835430546, | |
| "grad_norm": 0.24126295745372772, | |
| "learning_rate": 9.85567139954818e-06, | |
| "loss": 1.5916, | |
| "num_input_tokens_seen": 44564480, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.04219096965210955, | |
| "grad_norm": 0.44154781103134155, | |
| "learning_rate": 9.851478631379982e-06, | |
| "loss": 2.1419, | |
| "num_input_tokens_seen": 44826624, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.04243770046878855, | |
| "grad_norm": 0.3429047763347626, | |
| "learning_rate": 9.847226749475696e-06, | |
| "loss": 1.2978, | |
| "num_input_tokens_seen": 45088768, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.042684431285467554, | |
| "grad_norm": 0.4060891270637512, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 2.0514, | |
| "num_input_tokens_seen": 45350912, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.04293116210214656, | |
| "grad_norm": 3.0130326747894287, | |
| "learning_rate": 9.838545852409857e-06, | |
| "loss": 1.9413, | |
| "num_input_tokens_seen": 45613056, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.04317789291882556, | |
| "grad_norm": 0.3682909309864044, | |
| "learning_rate": 9.834116943022299e-06, | |
| "loss": 1.8323, | |
| "num_input_tokens_seen": 45875200, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.04342462373550456, | |
| "grad_norm": 0.317842960357666, | |
| "learning_rate": 9.829629131445342e-06, | |
| "loss": 1.6821, | |
| "num_input_tokens_seen": 46137344, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.043671354552183565, | |
| "grad_norm": 0.5329482555389404, | |
| "learning_rate": 9.825082472361558e-06, | |
| "loss": 2.0072, | |
| "num_input_tokens_seen": 46399488, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.04391808536886257, | |
| "grad_norm": 0.36978521943092346, | |
| "learning_rate": 9.82047702117055e-06, | |
| "loss": 2.1558, | |
| "num_input_tokens_seen": 46661632, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.04416481618554157, | |
| "grad_norm": 0.3222188949584961, | |
| "learning_rate": 9.815812833988292e-06, | |
| "loss": 2.1112, | |
| "num_input_tokens_seen": 46923776, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.04441154700222058, | |
| "grad_norm": 0.4519665539264679, | |
| "learning_rate": 9.811089967646427e-06, | |
| "loss": 1.9106, | |
| "num_input_tokens_seen": 47185920, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04465827781889958, | |
| "grad_norm": 0.2261379510164261, | |
| "learning_rate": 9.806308479691595e-06, | |
| "loss": 1.7543, | |
| "num_input_tokens_seen": 47448064, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.044905008635578586, | |
| "grad_norm": 0.4306648373603821, | |
| "learning_rate": 9.801468428384716e-06, | |
| "loss": 2.1505, | |
| "num_input_tokens_seen": 47710208, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.04515173945225759, | |
| "grad_norm": 0.34030383825302124, | |
| "learning_rate": 9.796569872700287e-06, | |
| "loss": 1.7867, | |
| "num_input_tokens_seen": 47972352, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.04539847026893659, | |
| "grad_norm": 0.29829004406929016, | |
| "learning_rate": 9.791612872325667e-06, | |
| "loss": 2.1088, | |
| "num_input_tokens_seen": 48234496, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.045645201085615594, | |
| "grad_norm": 0.5674875974655151, | |
| "learning_rate": 9.786597487660336e-06, | |
| "loss": 1.7166, | |
| "num_input_tokens_seen": 48496640, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.0458919319022946, | |
| "grad_norm": 1.0494624376296997, | |
| "learning_rate": 9.781523779815178e-06, | |
| "loss": 1.909, | |
| "num_input_tokens_seen": 48758784, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.0461386627189736, | |
| "grad_norm": 0.5063501596450806, | |
| "learning_rate": 9.776391810611719e-06, | |
| "loss": 2.0148, | |
| "num_input_tokens_seen": 49020928, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.0463853935356526, | |
| "grad_norm": 0.3112070560455322, | |
| "learning_rate": 9.771201642581384e-06, | |
| "loss": 1.6722, | |
| "num_input_tokens_seen": 49283072, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.046632124352331605, | |
| "grad_norm": 0.2980418801307678, | |
| "learning_rate": 9.765953338964736e-06, | |
| "loss": 1.9106, | |
| "num_input_tokens_seen": 49545216, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.04687885516901061, | |
| "grad_norm": 0.4022710919380188, | |
| "learning_rate": 9.760646963710694e-06, | |
| "loss": 1.8416, | |
| "num_input_tokens_seen": 49807360, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.04712558598568961, | |
| "grad_norm": 0.4678567051887512, | |
| "learning_rate": 9.755282581475769e-06, | |
| "loss": 1.3391, | |
| "num_input_tokens_seen": 50069504, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.047372316802368614, | |
| "grad_norm": 0.3067920506000519, | |
| "learning_rate": 9.749860257623262e-06, | |
| "loss": 1.817, | |
| "num_input_tokens_seen": 50331648, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 0.31706950068473816, | |
| "learning_rate": 9.744380058222483e-06, | |
| "loss": 1.5534, | |
| "num_input_tokens_seen": 50593792, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.04786577843572662, | |
| "grad_norm": 0.3867824673652649, | |
| "learning_rate": 9.73884205004793e-06, | |
| "loss": 1.8822, | |
| "num_input_tokens_seen": 50855936, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.04811250925240563, | |
| "grad_norm": 0.5505887866020203, | |
| "learning_rate": 9.733246300578482e-06, | |
| "loss": 1.5254, | |
| "num_input_tokens_seen": 51118080, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.04835924006908463, | |
| "grad_norm": 0.3414452075958252, | |
| "learning_rate": 9.727592877996585e-06, | |
| "loss": 1.8025, | |
| "num_input_tokens_seen": 51380224, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.048605970885763634, | |
| "grad_norm": 0.45754650235176086, | |
| "learning_rate": 9.721881851187406e-06, | |
| "loss": 2.2462, | |
| "num_input_tokens_seen": 51642368, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.04885270170244264, | |
| "grad_norm": 0.265245258808136, | |
| "learning_rate": 9.716113289738005e-06, | |
| "loss": 2.0391, | |
| "num_input_tokens_seen": 51904512, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.04909943251912164, | |
| "grad_norm": 0.3758782744407654, | |
| "learning_rate": 9.710287263936485e-06, | |
| "loss": 1.71, | |
| "num_input_tokens_seen": 52166656, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.04934616333580064, | |
| "grad_norm": 0.3058117926120758, | |
| "learning_rate": 9.704403844771128e-06, | |
| "loss": 1.5908, | |
| "num_input_tokens_seen": 52428800, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.049592894152479645, | |
| "grad_norm": 0.3393475413322449, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 1.4709, | |
| "num_input_tokens_seen": 52690944, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.04983962496915865, | |
| "grad_norm": 0.33585816621780396, | |
| "learning_rate": 9.69246511379778e-06, | |
| "loss": 1.5541, | |
| "num_input_tokens_seen": 52953088, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.05008635578583765, | |
| "grad_norm": 0.3068286180496216, | |
| "learning_rate": 9.68640994745946e-06, | |
| "loss": 2.0374, | |
| "num_input_tokens_seen": 53215232, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.050333086602516654, | |
| "grad_norm": 0.3098278045654297, | |
| "learning_rate": 9.680297678694867e-06, | |
| "loss": 1.9932, | |
| "num_input_tokens_seen": 53477376, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.050579817419195656, | |
| "grad_norm": 2.7050626277923584, | |
| "learning_rate": 9.674128381980073e-06, | |
| "loss": 1.3617, | |
| "num_input_tokens_seen": 53739520, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.05082654823587466, | |
| "grad_norm": 0.22176742553710938, | |
| "learning_rate": 9.667902132486009e-06, | |
| "loss": 1.8249, | |
| "num_input_tokens_seen": 54001664, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.05107327905255366, | |
| "grad_norm": 0.35358500480651855, | |
| "learning_rate": 9.661619006077562e-06, | |
| "loss": 1.8192, | |
| "num_input_tokens_seen": 54263808, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.051320009869232665, | |
| "grad_norm": 0.6246964335441589, | |
| "learning_rate": 9.655279079312643e-06, | |
| "loss": 1.6647, | |
| "num_input_tokens_seen": 54525952, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.05156674068591167, | |
| "grad_norm": 0.5339682102203369, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 1.9559, | |
| "num_input_tokens_seen": 54788096, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.05181347150259067, | |
| "grad_norm": 0.4896355867385864, | |
| "learning_rate": 9.642429134404568e-06, | |
| "loss": 1.1909, | |
| "num_input_tokens_seen": 55050240, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.05206020231926968, | |
| "grad_norm": 0.3802131414413452, | |
| "learning_rate": 9.635919272833938e-06, | |
| "loss": 2.1234, | |
| "num_input_tokens_seen": 55312384, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.05230693313594868, | |
| "grad_norm": 0.3870851695537567, | |
| "learning_rate": 9.629352924049975e-06, | |
| "loss": 1.5652, | |
| "num_input_tokens_seen": 55574528, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.052553663952627686, | |
| "grad_norm": 0.2589404881000519, | |
| "learning_rate": 9.622730168061568e-06, | |
| "loss": 1.5086, | |
| "num_input_tokens_seen": 55836672, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.05280039476930669, | |
| "grad_norm": 0.34146517515182495, | |
| "learning_rate": 9.616051085564905e-06, | |
| "loss": 1.3068, | |
| "num_input_tokens_seen": 56098816, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.05304712558598569, | |
| "grad_norm": 0.3951856195926666, | |
| "learning_rate": 9.609315757942504e-06, | |
| "loss": 1.4909, | |
| "num_input_tokens_seen": 56360960, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.053293856402664694, | |
| "grad_norm": 0.23125781118869781, | |
| "learning_rate": 9.602524267262202e-06, | |
| "loss": 1.6771, | |
| "num_input_tokens_seen": 56623104, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.0535405872193437, | |
| "grad_norm": 0.30795449018478394, | |
| "learning_rate": 9.595676696276173e-06, | |
| "loss": 1.7215, | |
| "num_input_tokens_seen": 56885248, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.0537873180360227, | |
| "grad_norm": 0.2819620370864868, | |
| "learning_rate": 9.588773128419907e-06, | |
| "loss": 1.3582, | |
| "num_input_tokens_seen": 57147392, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.0540340488527017, | |
| "grad_norm": 0.21246762573719025, | |
| "learning_rate": 9.581813647811199e-06, | |
| "loss": 1.6455, | |
| "num_input_tokens_seen": 57409536, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.054280779669380705, | |
| "grad_norm": 0.2589544355869293, | |
| "learning_rate": 9.574798339249124e-06, | |
| "loss": 1.6292, | |
| "num_input_tokens_seen": 57671680, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.05452751048605971, | |
| "grad_norm": 0.2522466778755188, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 1.8189, | |
| "num_input_tokens_seen": 57933824, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.05477424130273871, | |
| "grad_norm": 0.2954379618167877, | |
| "learning_rate": 9.560600580861366e-06, | |
| "loss": 1.774, | |
| "num_input_tokens_seen": 58195968, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.05502097211941771, | |
| "grad_norm": 0.3274562358856201, | |
| "learning_rate": 9.553418304030886e-06, | |
| "loss": 1.6534, | |
| "num_input_tokens_seen": 58458112, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.055267702936096716, | |
| "grad_norm": 0.37323611974716187, | |
| "learning_rate": 9.546180545235344e-06, | |
| "loss": 1.8863, | |
| "num_input_tokens_seen": 58720256, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.05551443375277572, | |
| "grad_norm": 0.28407496213912964, | |
| "learning_rate": 9.538887392664544e-06, | |
| "loss": 1.7969, | |
| "num_input_tokens_seen": 58982400, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.05576116456945472, | |
| "grad_norm": 0.25206607580184937, | |
| "learning_rate": 9.531538935183252e-06, | |
| "loss": 1.842, | |
| "num_input_tokens_seen": 59244544, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.05600789538613373, | |
| "grad_norm": 0.3008832037448883, | |
| "learning_rate": 9.524135262330098e-06, | |
| "loss": 2.0255, | |
| "num_input_tokens_seen": 59506688, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.056254626202812734, | |
| "grad_norm": 0.2403050661087036, | |
| "learning_rate": 9.516676464316505e-06, | |
| "loss": 1.3322, | |
| "num_input_tokens_seen": 59768832, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.05650135701949174, | |
| "grad_norm": 0.26147162914276123, | |
| "learning_rate": 9.50916263202557e-06, | |
| "loss": 1.8543, | |
| "num_input_tokens_seen": 60030976, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.05674808783617074, | |
| "grad_norm": 0.32931873202323914, | |
| "learning_rate": 9.501593857010968e-06, | |
| "loss": 1.9961, | |
| "num_input_tokens_seen": 60293120, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.05699481865284974, | |
| "grad_norm": 0.26853638887405396, | |
| "learning_rate": 9.493970231495836e-06, | |
| "loss": 1.6481, | |
| "num_input_tokens_seen": 60555264, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.057241549469528745, | |
| "grad_norm": 0.33695557713508606, | |
| "learning_rate": 9.486291848371642e-06, | |
| "loss": 1.6796, | |
| "num_input_tokens_seen": 60817408, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.05748828028620775, | |
| "grad_norm": 0.3412604331970215, | |
| "learning_rate": 9.478558801197065e-06, | |
| "loss": 1.4463, | |
| "num_input_tokens_seen": 61079552, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.05773501110288675, | |
| "grad_norm": 0.3287171423435211, | |
| "learning_rate": 9.470771184196842e-06, | |
| "loss": 1.8843, | |
| "num_input_tokens_seen": 61341696, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.05798174191956575, | |
| "grad_norm": 0.4994906187057495, | |
| "learning_rate": 9.46292909226063e-06, | |
| "loss": 1.6577, | |
| "num_input_tokens_seen": 61603840, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.058228472736244756, | |
| "grad_norm": 0.3780612647533417, | |
| "learning_rate": 9.45503262094184e-06, | |
| "loss": 1.8985, | |
| "num_input_tokens_seen": 61865984, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.05847520355292376, | |
| "grad_norm": 0.2917082607746124, | |
| "learning_rate": 9.44708186645649e-06, | |
| "loss": 1.6278, | |
| "num_input_tokens_seen": 62128128, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.05872193436960276, | |
| "grad_norm": 0.2749132812023163, | |
| "learning_rate": 9.439076925682006e-06, | |
| "loss": 2.1182, | |
| "num_input_tokens_seen": 62390272, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.058968665186281764, | |
| "grad_norm": 0.34079936146736145, | |
| "learning_rate": 9.431017896156074e-06, | |
| "loss": 1.7252, | |
| "num_input_tokens_seen": 62652416, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.05921539600296077, | |
| "grad_norm": 0.2402135133743286, | |
| "learning_rate": 9.42290487607542e-06, | |
| "loss": 1.8629, | |
| "num_input_tokens_seen": 62914560, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.05946212681963977, | |
| "grad_norm": 0.40557897090911865, | |
| "learning_rate": 9.414737964294636e-06, | |
| "loss": 1.4655, | |
| "num_input_tokens_seen": 63176704, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.05970885763631878, | |
| "grad_norm": 0.31378883123397827, | |
| "learning_rate": 9.406517260324962e-06, | |
| "loss": 1.3033, | |
| "num_input_tokens_seen": 63438848, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.05995558845299778, | |
| "grad_norm": 1.0957661867141724, | |
| "learning_rate": 9.398242864333084e-06, | |
| "loss": 1.6811, | |
| "num_input_tokens_seen": 63700992, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.060202319269676785, | |
| "grad_norm": 0.5017796158790588, | |
| "learning_rate": 9.389914877139903e-06, | |
| "loss": 1.7252, | |
| "num_input_tokens_seen": 63963136, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.06044905008635579, | |
| "grad_norm": 0.31879162788391113, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 1.6618, | |
| "num_input_tokens_seen": 64225280, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.06069578090303479, | |
| "grad_norm": 0.28952914476394653, | |
| "learning_rate": 9.37309853569698e-06, | |
| "loss": 1.449, | |
| "num_input_tokens_seen": 64487424, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.06094251171971379, | |
| "grad_norm": 0.2795778214931488, | |
| "learning_rate": 9.364610386349048e-06, | |
| "loss": 1.6841, | |
| "num_input_tokens_seen": 64749568, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.061189242536392796, | |
| "grad_norm": 0.2345486432313919, | |
| "learning_rate": 9.356069055600949e-06, | |
| "loss": 1.686, | |
| "num_input_tokens_seen": 65011712, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.0614359733530718, | |
| "grad_norm": 0.4272654056549072, | |
| "learning_rate": 9.347474647526095e-06, | |
| "loss": 1.5592, | |
| "num_input_tokens_seen": 65273856, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.0616827041697508, | |
| "grad_norm": 0.28724414110183716, | |
| "learning_rate": 9.338827266844643e-06, | |
| "loss": 1.6606, | |
| "num_input_tokens_seen": 65536000, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.061929434986429804, | |
| "grad_norm": 0.27960872650146484, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 1.5445, | |
| "num_input_tokens_seen": 65798144, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.06217616580310881, | |
| "grad_norm": 0.2837168872356415, | |
| "learning_rate": 9.321374009768525e-06, | |
| "loss": 1.4314, | |
| "num_input_tokens_seen": 66060288, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.06242289661978781, | |
| "grad_norm": 0.26491212844848633, | |
| "learning_rate": 9.312568346036288e-06, | |
| "loss": 1.3124, | |
| "num_input_tokens_seen": 66322432, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.06266962743646681, | |
| "grad_norm": 0.39029908180236816, | |
| "learning_rate": 9.30371013501972e-06, | |
| "loss": 1.6831, | |
| "num_input_tokens_seen": 66584576, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.06291635825314582, | |
| "grad_norm": 0.26802682876586914, | |
| "learning_rate": 9.294799484653323e-06, | |
| "loss": 1.7579, | |
| "num_input_tokens_seen": 66846720, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.06316308906982482, | |
| "grad_norm": 0.2546183168888092, | |
| "learning_rate": 9.285836503510562e-06, | |
| "loss": 1.6593, | |
| "num_input_tokens_seen": 67108864, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.06340981988650382, | |
| "grad_norm": 0.24312745034694672, | |
| "learning_rate": 9.276821300802535e-06, | |
| "loss": 2.0922, | |
| "num_input_tokens_seen": 67371008, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.06365655070318282, | |
| "grad_norm": 0.4153420925140381, | |
| "learning_rate": 9.267753986376638e-06, | |
| "loss": 1.5677, | |
| "num_input_tokens_seen": 67633152, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.06390328151986183, | |
| "grad_norm": 0.20946179330348969, | |
| "learning_rate": 9.25863467071524e-06, | |
| "loss": 1.8557, | |
| "num_input_tokens_seen": 67895296, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.06415001233654083, | |
| "grad_norm": 0.3546552360057831, | |
| "learning_rate": 9.24946346493432e-06, | |
| "loss": 1.6333, | |
| "num_input_tokens_seen": 68157440, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.06439674315321983, | |
| "grad_norm": 0.34967514872550964, | |
| "learning_rate": 9.24024048078213e-06, | |
| "loss": 2.1472, | |
| "num_input_tokens_seen": 68419584, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.06464347396989883, | |
| "grad_norm": 0.304616242647171, | |
| "learning_rate": 9.230965830637821e-06, | |
| "loss": 1.8176, | |
| "num_input_tokens_seen": 68681728, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.06489020478657784, | |
| "grad_norm": 0.23437748849391937, | |
| "learning_rate": 9.221639627510076e-06, | |
| "loss": 1.9167, | |
| "num_input_tokens_seen": 68943872, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.06513693560325684, | |
| "grad_norm": 0.26866498589515686, | |
| "learning_rate": 9.21226198503574e-06, | |
| "loss": 1.6385, | |
| "num_input_tokens_seen": 69206016, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.06538366641993584, | |
| "grad_norm": 0.278683066368103, | |
| "learning_rate": 9.202833017478421e-06, | |
| "loss": 1.7856, | |
| "num_input_tokens_seen": 69468160, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.06563039723661486, | |
| "grad_norm": 0.3804785907268524, | |
| "learning_rate": 9.193352839727122e-06, | |
| "loss": 1.7004, | |
| "num_input_tokens_seen": 69730304, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.06587712805329386, | |
| "grad_norm": 0.24755661189556122, | |
| "learning_rate": 9.18382156729481e-06, | |
| "loss": 1.7464, | |
| "num_input_tokens_seen": 69992448, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.06612385886997287, | |
| "grad_norm": 0.31840574741363525, | |
| "learning_rate": 9.174239316317034e-06, | |
| "loss": 1.4537, | |
| "num_input_tokens_seen": 70254592, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.06637058968665187, | |
| "grad_norm": 0.2087324857711792, | |
| "learning_rate": 9.164606203550498e-06, | |
| "loss": 1.8524, | |
| "num_input_tokens_seen": 70516736, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.06661732050333087, | |
| "grad_norm": 0.5688844919204712, | |
| "learning_rate": 9.154922346371641e-06, | |
| "loss": 1.868, | |
| "num_input_tokens_seen": 70778880, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.06686405132000987, | |
| "grad_norm": 0.28839144110679626, | |
| "learning_rate": 9.145187862775208e-06, | |
| "loss": 1.8603, | |
| "num_input_tokens_seen": 71041024, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.06711078213668888, | |
| "grad_norm": 0.3128485083580017, | |
| "learning_rate": 9.13540287137281e-06, | |
| "loss": 1.3797, | |
| "num_input_tokens_seen": 71303168, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.06735751295336788, | |
| "grad_norm": 0.3282206952571869, | |
| "learning_rate": 9.125567491391476e-06, | |
| "loss": 1.5653, | |
| "num_input_tokens_seen": 71565312, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.06760424377004688, | |
| "grad_norm": 0.4496432840824127, | |
| "learning_rate": 9.115681842672211e-06, | |
| "loss": 1.6801, | |
| "num_input_tokens_seen": 71827456, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.06785097458672588, | |
| "grad_norm": 0.32268252968788147, | |
| "learning_rate": 9.10574604566852e-06, | |
| "loss": 2.2858, | |
| "num_input_tokens_seen": 72089600, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.06809770540340489, | |
| "grad_norm": 0.2562284767627716, | |
| "learning_rate": 9.09576022144496e-06, | |
| "loss": 1.4747, | |
| "num_input_tokens_seen": 72351744, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.06834443622008389, | |
| "grad_norm": 0.23939964175224304, | |
| "learning_rate": 9.085724491675642e-06, | |
| "loss": 1.5631, | |
| "num_input_tokens_seen": 72613888, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.06859116703676289, | |
| "grad_norm": 0.4609747529029846, | |
| "learning_rate": 9.07563897864277e-06, | |
| "loss": 1.7264, | |
| "num_input_tokens_seen": 72876032, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.0688378978534419, | |
| "grad_norm": 0.3924141824245453, | |
| "learning_rate": 9.065503805235139e-06, | |
| "loss": 1.4072, | |
| "num_input_tokens_seen": 73138176, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.0690846286701209, | |
| "grad_norm": 0.29724472761154175, | |
| "learning_rate": 9.055319094946633e-06, | |
| "loss": 1.3118, | |
| "num_input_tokens_seen": 73400320, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.0693313594867999, | |
| "grad_norm": 0.4114074110984802, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 1.9738, | |
| "num_input_tokens_seen": 73662464, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.0695780903034789, | |
| "grad_norm": 0.23386453092098236, | |
| "learning_rate": 9.03480156071901e-06, | |
| "loss": 1.8462, | |
| "num_input_tokens_seen": 73924608, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.0698248211201579, | |
| "grad_norm": 0.22296760976314545, | |
| "learning_rate": 9.02446898677957e-06, | |
| "loss": 1.7928, | |
| "num_input_tokens_seen": 74186752, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.07007155193683691, | |
| "grad_norm": 0.2875213027000427, | |
| "learning_rate": 9.014087375955574e-06, | |
| "loss": 1.7923, | |
| "num_input_tokens_seen": 74448896, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.07031828275351591, | |
| "grad_norm": 0.19052010774612427, | |
| "learning_rate": 9.003656854743667e-06, | |
| "loss": 1.528, | |
| "num_input_tokens_seen": 74711040, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.07056501357019491, | |
| "grad_norm": 0.3048911392688751, | |
| "learning_rate": 8.993177550236464e-06, | |
| "loss": 1.831, | |
| "num_input_tokens_seen": 74973184, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.07081174438687392, | |
| "grad_norm": 0.17250804603099823, | |
| "learning_rate": 8.982649590120982e-06, | |
| "loss": 1.1951, | |
| "num_input_tokens_seen": 75235328, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.07105847520355292, | |
| "grad_norm": 0.3263763189315796, | |
| "learning_rate": 8.972073102677091e-06, | |
| "loss": 1.7192, | |
| "num_input_tokens_seen": 75497472, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.07130520602023192, | |
| "grad_norm": 0.3392772376537323, | |
| "learning_rate": 8.961448216775955e-06, | |
| "loss": 1.9796, | |
| "num_input_tokens_seen": 75759616, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.07155193683691093, | |
| "grad_norm": 0.3611414432525635, | |
| "learning_rate": 8.950775061878453e-06, | |
| "loss": 2.015, | |
| "num_input_tokens_seen": 76021760, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.07179866765358993, | |
| "grad_norm": 0.1821010261774063, | |
| "learning_rate": 8.94005376803361e-06, | |
| "loss": 1.3525, | |
| "num_input_tokens_seen": 76283904, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.07204539847026893, | |
| "grad_norm": 0.5545079112052917, | |
| "learning_rate": 8.92928446587701e-06, | |
| "loss": 1.6759, | |
| "num_input_tokens_seen": 76546048, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.07229212928694793, | |
| "grad_norm": 0.3202209174633026, | |
| "learning_rate": 8.9184672866292e-06, | |
| "loss": 1.4154, | |
| "num_input_tokens_seen": 76808192, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.07253886010362694, | |
| "grad_norm": 0.2715050280094147, | |
| "learning_rate": 8.907602362094094e-06, | |
| "loss": 1.6875, | |
| "num_input_tokens_seen": 77070336, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.07278559092030594, | |
| "grad_norm": 0.2807007133960724, | |
| "learning_rate": 8.896689824657371e-06, | |
| "loss": 1.7927, | |
| "num_input_tokens_seen": 77332480, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.07303232173698494, | |
| "grad_norm": 0.2917633354663849, | |
| "learning_rate": 8.885729807284855e-06, | |
| "loss": 1.5705, | |
| "num_input_tokens_seen": 77594624, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.07327905255366396, | |
| "grad_norm": 0.3167378604412079, | |
| "learning_rate": 8.874722443520898e-06, | |
| "loss": 1.9123, | |
| "num_input_tokens_seen": 77856768, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.07352578337034296, | |
| "grad_norm": 0.30874526500701904, | |
| "learning_rate": 8.863667867486756e-06, | |
| "loss": 1.7957, | |
| "num_input_tokens_seen": 78118912, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.07377251418702196, | |
| "grad_norm": 0.32000553607940674, | |
| "learning_rate": 8.852566213878947e-06, | |
| "loss": 1.9255, | |
| "num_input_tokens_seen": 78381056, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.07401924500370097, | |
| "grad_norm": 0.3279455602169037, | |
| "learning_rate": 8.841417617967618e-06, | |
| "loss": 1.8232, | |
| "num_input_tokens_seen": 78643200, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07426597582037997, | |
| "grad_norm": 0.2578760087490082, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 1.5326, | |
| "num_input_tokens_seen": 78905344, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.07451270663705897, | |
| "grad_norm": 0.21257418394088745, | |
| "learning_rate": 8.818980143173212e-06, | |
| "loss": 1.529, | |
| "num_input_tokens_seen": 79167488, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.07475943745373798, | |
| "grad_norm": 0.3379907011985779, | |
| "learning_rate": 8.807691537683685e-06, | |
| "loss": 1.6849, | |
| "num_input_tokens_seen": 79429632, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.07500616827041698, | |
| "grad_norm": 0.23352430760860443, | |
| "learning_rate": 8.796356536674404e-06, | |
| "loss": 1.5998, | |
| "num_input_tokens_seen": 79691776, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.07525289908709598, | |
| "grad_norm": 0.4021840989589691, | |
| "learning_rate": 8.784975278258783e-06, | |
| "loss": 1.7475, | |
| "num_input_tokens_seen": 79953920, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.07549962990377498, | |
| "grad_norm": 0.3122968375682831, | |
| "learning_rate": 8.773547901113862e-06, | |
| "loss": 1.8813, | |
| "num_input_tokens_seen": 80216064, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.07574636072045399, | |
| "grad_norm": 0.25700807571411133, | |
| "learning_rate": 8.762074544478622e-06, | |
| "loss": 2.0497, | |
| "num_input_tokens_seen": 80478208, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.07599309153713299, | |
| "grad_norm": 0.6370308995246887, | |
| "learning_rate": 8.750555348152299e-06, | |
| "loss": 1.6946, | |
| "num_input_tokens_seen": 80740352, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.07623982235381199, | |
| "grad_norm": 0.22553326189517975, | |
| "learning_rate": 8.73899045249266e-06, | |
| "loss": 1.902, | |
| "num_input_tokens_seen": 81002496, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.076486553170491, | |
| "grad_norm": 0.23086640238761902, | |
| "learning_rate": 8.727379998414311e-06, | |
| "loss": 1.629, | |
| "num_input_tokens_seen": 81264640, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.07673328398717, | |
| "grad_norm": 0.4032231271266937, | |
| "learning_rate": 8.715724127386971e-06, | |
| "loss": 1.805, | |
| "num_input_tokens_seen": 81526784, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.076980014803849, | |
| "grad_norm": 0.31547385454177856, | |
| "learning_rate": 8.70402298143375e-06, | |
| "loss": 1.6519, | |
| "num_input_tokens_seen": 81788928, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.077226745620528, | |
| "grad_norm": 0.2974226176738739, | |
| "learning_rate": 8.692276703129421e-06, | |
| "loss": 1.6291, | |
| "num_input_tokens_seen": 82051072, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.077473476437207, | |
| "grad_norm": 0.2320721596479416, | |
| "learning_rate": 8.680485435598674e-06, | |
| "loss": 1.5294, | |
| "num_input_tokens_seen": 82313216, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.07772020725388601, | |
| "grad_norm": 0.26393061876296997, | |
| "learning_rate": 8.668649322514382e-06, | |
| "loss": 1.6567, | |
| "num_input_tokens_seen": 82575360, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.07796693807056501, | |
| "grad_norm": 0.31006282567977905, | |
| "learning_rate": 8.656768508095853e-06, | |
| "loss": 1.3175, | |
| "num_input_tokens_seen": 82837504, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.07821366888724401, | |
| "grad_norm": 0.30799600481987, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 1.6641, | |
| "num_input_tokens_seen": 83099648, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.07846039970392302, | |
| "grad_norm": 0.2402356117963791, | |
| "learning_rate": 8.632873354854881e-06, | |
| "loss": 1.6, | |
| "num_input_tokens_seen": 83361792, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.07870713052060202, | |
| "grad_norm": 0.2880563735961914, | |
| "learning_rate": 8.620859307187339e-06, | |
| "loss": 1.3359, | |
| "num_input_tokens_seen": 83623936, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.07895386133728102, | |
| "grad_norm": 0.20638631284236908, | |
| "learning_rate": 8.608801140491811e-06, | |
| "loss": 1.3001, | |
| "num_input_tokens_seen": 83886080, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.07920059215396003, | |
| "grad_norm": 0.18959663808345795, | |
| "learning_rate": 8.596699001693257e-06, | |
| "loss": 1.862, | |
| "num_input_tokens_seen": 84148224, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.07944732297063903, | |
| "grad_norm": 0.24531440436840057, | |
| "learning_rate": 8.584553038252415e-06, | |
| "loss": 1.6415, | |
| "num_input_tokens_seen": 84410368, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.07969405378731803, | |
| "grad_norm": 0.2331283986568451, | |
| "learning_rate": 8.572363398164017e-06, | |
| "loss": 1.5621, | |
| "num_input_tokens_seen": 84672512, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.07994078460399703, | |
| "grad_norm": 0.19714899361133575, | |
| "learning_rate": 8.560130229954985e-06, | |
| "loss": 1.9105, | |
| "num_input_tokens_seen": 84934656, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.08018751542067604, | |
| "grad_norm": 0.37617865204811096, | |
| "learning_rate": 8.547853682682605e-06, | |
| "loss": 1.4315, | |
| "num_input_tokens_seen": 85196800, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.08043424623735504, | |
| "grad_norm": 0.38534656167030334, | |
| "learning_rate": 8.535533905932739e-06, | |
| "loss": 1.8205, | |
| "num_input_tokens_seen": 85458944, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.08068097705403404, | |
| "grad_norm": 0.3376696705818176, | |
| "learning_rate": 8.523171049817974e-06, | |
| "loss": 1.668, | |
| "num_input_tokens_seen": 85721088, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.08092770787071306, | |
| "grad_norm": 0.3171237111091614, | |
| "learning_rate": 8.510765264975813e-06, | |
| "loss": 1.474, | |
| "num_input_tokens_seen": 85983232, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.08117443868739206, | |
| "grad_norm": 0.40522676706314087, | |
| "learning_rate": 8.498316702566828e-06, | |
| "loss": 1.828, | |
| "num_input_tokens_seen": 86245376, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.08142116950407106, | |
| "grad_norm": 0.29329410195350647, | |
| "learning_rate": 8.485825514272824e-06, | |
| "loss": 1.5659, | |
| "num_input_tokens_seen": 86507520, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.08166790032075007, | |
| "grad_norm": 0.457561194896698, | |
| "learning_rate": 8.473291852294986e-06, | |
| "loss": 2.0202, | |
| "num_input_tokens_seen": 86769664, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.08191463113742907, | |
| "grad_norm": 0.3520510792732239, | |
| "learning_rate": 8.460715869352035e-06, | |
| "loss": 1.5418, | |
| "num_input_tokens_seen": 87031808, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.08216136195410807, | |
| "grad_norm": 0.24725475907325745, | |
| "learning_rate": 8.44809771867835e-06, | |
| "loss": 1.5912, | |
| "num_input_tokens_seen": 87293952, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.08240809277078708, | |
| "grad_norm": 0.27952858805656433, | |
| "learning_rate": 8.435437554022116e-06, | |
| "loss": 2.0136, | |
| "num_input_tokens_seen": 87556096, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.08265482358746608, | |
| "grad_norm": 0.3019633889198303, | |
| "learning_rate": 8.422735529643445e-06, | |
| "loss": 1.7385, | |
| "num_input_tokens_seen": 87818240, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.08290155440414508, | |
| "grad_norm": 0.27266594767570496, | |
| "learning_rate": 8.409991800312493e-06, | |
| "loss": 1.2272, | |
| "num_input_tokens_seen": 88080384, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.08314828522082408, | |
| "grad_norm": 0.23454353213310242, | |
| "learning_rate": 8.397206521307584e-06, | |
| "loss": 2.0053, | |
| "num_input_tokens_seen": 88342528, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.08339501603750309, | |
| "grad_norm": 0.4828662574291229, | |
| "learning_rate": 8.384379848413304e-06, | |
| "loss": 1.9389, | |
| "num_input_tokens_seen": 88604672, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.08364174685418209, | |
| "grad_norm": 0.3016226887702942, | |
| "learning_rate": 8.371511937918616e-06, | |
| "loss": 1.7783, | |
| "num_input_tokens_seen": 88866816, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.08388847767086109, | |
| "grad_norm": 0.2821120619773865, | |
| "learning_rate": 8.358602946614952e-06, | |
| "loss": 2.0129, | |
| "num_input_tokens_seen": 89128960, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.0841352084875401, | |
| "grad_norm": 0.26417189836502075, | |
| "learning_rate": 8.345653031794292e-06, | |
| "loss": 1.8609, | |
| "num_input_tokens_seen": 89391104, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.0843819393042191, | |
| "grad_norm": 0.22533980011940002, | |
| "learning_rate": 8.332662351247262e-06, | |
| "loss": 1.9865, | |
| "num_input_tokens_seen": 89653248, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.0846286701208981, | |
| "grad_norm": 0.21896155178546906, | |
| "learning_rate": 8.319631063261209e-06, | |
| "loss": 1.5262, | |
| "num_input_tokens_seen": 89915392, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.0848754009375771, | |
| "grad_norm": 0.3828951120376587, | |
| "learning_rate": 8.30655932661826e-06, | |
| "loss": 1.8122, | |
| "num_input_tokens_seen": 90177536, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.0851221317542561, | |
| "grad_norm": 0.2111983597278595, | |
| "learning_rate": 8.293447300593402e-06, | |
| "loss": 1.7962, | |
| "num_input_tokens_seen": 90439680, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.08536886257093511, | |
| "grad_norm": 0.34530311822891235, | |
| "learning_rate": 8.280295144952537e-06, | |
| "loss": 1.8614, | |
| "num_input_tokens_seen": 90701824, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.08561559338761411, | |
| "grad_norm": 0.3356333374977112, | |
| "learning_rate": 8.267103019950529e-06, | |
| "loss": 1.688, | |
| "num_input_tokens_seen": 90963968, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.08586232420429311, | |
| "grad_norm": 0.17506998777389526, | |
| "learning_rate": 8.253871086329255e-06, | |
| "loss": 1.1625, | |
| "num_input_tokens_seen": 91226112, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.08610905502097212, | |
| "grad_norm": 0.26492053270339966, | |
| "learning_rate": 8.240599505315656e-06, | |
| "loss": 1.8381, | |
| "num_input_tokens_seen": 91488256, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.08635578583765112, | |
| "grad_norm": 0.4436925947666168, | |
| "learning_rate": 8.227288438619754e-06, | |
| "loss": 1.2551, | |
| "num_input_tokens_seen": 91750400, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.08660251665433012, | |
| "grad_norm": 0.29770198464393616, | |
| "learning_rate": 8.213938048432697e-06, | |
| "loss": 2.0214, | |
| "num_input_tokens_seen": 92012544, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.08684924747100913, | |
| "grad_norm": 0.2671870291233063, | |
| "learning_rate": 8.200548497424779e-06, | |
| "loss": 1.8595, | |
| "num_input_tokens_seen": 92274688, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.08709597828768813, | |
| "grad_norm": 0.3322468101978302, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 1.8408, | |
| "num_input_tokens_seen": 92536832, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.08734270910436713, | |
| "grad_norm": 0.2707277834415436, | |
| "learning_rate": 8.173652566011339e-06, | |
| "loss": 1.8141, | |
| "num_input_tokens_seen": 92798976, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.08758943992104613, | |
| "grad_norm": 0.3420428931713104, | |
| "learning_rate": 8.160146513324256e-06, | |
| "loss": 1.7292, | |
| "num_input_tokens_seen": 93061120, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.08783617073772514, | |
| "grad_norm": 0.34296715259552, | |
| "learning_rate": 8.146601955249187e-06, | |
| "loss": 1.5302, | |
| "num_input_tokens_seen": 93323264, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.08808290155440414, | |
| "grad_norm": 0.2963867783546448, | |
| "learning_rate": 8.133019056822303e-06, | |
| "loss": 1.6297, | |
| "num_input_tokens_seen": 93585408, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.08832963237108314, | |
| "grad_norm": 0.2812798321247101, | |
| "learning_rate": 8.119397983546932e-06, | |
| "loss": 1.7256, | |
| "num_input_tokens_seen": 93847552, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.08857636318776216, | |
| "grad_norm": 0.20225989818572998, | |
| "learning_rate": 8.105738901391553e-06, | |
| "loss": 1.5714, | |
| "num_input_tokens_seen": 94109696, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.08882309400444116, | |
| "grad_norm": 0.3172900974750519, | |
| "learning_rate": 8.092041976787772e-06, | |
| "loss": 1.8771, | |
| "num_input_tokens_seen": 94371840, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.08906982482112016, | |
| "grad_norm": 0.2378884255886078, | |
| "learning_rate": 8.078307376628292e-06, | |
| "loss": 1.739, | |
| "num_input_tokens_seen": 94633984, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.08931655563779917, | |
| "grad_norm": 0.6169587969779968, | |
| "learning_rate": 8.064535268264883e-06, | |
| "loss": 1.5751, | |
| "num_input_tokens_seen": 94896128, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.08956328645447817, | |
| "grad_norm": 0.2723526060581207, | |
| "learning_rate": 8.05072581950634e-06, | |
| "loss": 1.3679, | |
| "num_input_tokens_seen": 95158272, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.08981001727115717, | |
| "grad_norm": 0.20204123854637146, | |
| "learning_rate": 8.036879198616434e-06, | |
| "loss": 1.3856, | |
| "num_input_tokens_seen": 95420416, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.09005674808783617, | |
| "grad_norm": 0.3206169009208679, | |
| "learning_rate": 8.022995574311876e-06, | |
| "loss": 1.8262, | |
| "num_input_tokens_seen": 95682560, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.09030347890451518, | |
| "grad_norm": 0.32242709398269653, | |
| "learning_rate": 8.009075115760243e-06, | |
| "loss": 1.7613, | |
| "num_input_tokens_seen": 95944704, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.09055020972119418, | |
| "grad_norm": 0.2581716477870941, | |
| "learning_rate": 7.99511799257793e-06, | |
| "loss": 1.1449, | |
| "num_input_tokens_seen": 96206848, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.09079694053787318, | |
| "grad_norm": 0.23341234028339386, | |
| "learning_rate": 7.981124374828079e-06, | |
| "loss": 1.7955, | |
| "num_input_tokens_seen": 96468992, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.09104367135455219, | |
| "grad_norm": 0.3861933648586273, | |
| "learning_rate": 7.967094433018508e-06, | |
| "loss": 1.6175, | |
| "num_input_tokens_seen": 96731136, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.09129040217123119, | |
| "grad_norm": 0.1654781550168991, | |
| "learning_rate": 7.953028338099628e-06, | |
| "loss": 1.7449, | |
| "num_input_tokens_seen": 96993280, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.09153713298791019, | |
| "grad_norm": 0.28304633498191833, | |
| "learning_rate": 7.938926261462366e-06, | |
| "loss": 1.74, | |
| "num_input_tokens_seen": 97255424, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.0917838638045892, | |
| "grad_norm": 0.4599458873271942, | |
| "learning_rate": 7.92478837493608e-06, | |
| "loss": 1.8308, | |
| "num_input_tokens_seen": 97517568, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.0920305946212682, | |
| "grad_norm": 0.2703869342803955, | |
| "learning_rate": 7.910614850786448e-06, | |
| "loss": 2.0039, | |
| "num_input_tokens_seen": 97779712, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.0922773254379472, | |
| "grad_norm": 0.4541519284248352, | |
| "learning_rate": 7.896405861713393e-06, | |
| "loss": 1.8527, | |
| "num_input_tokens_seen": 98041856, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.0925240562546262, | |
| "grad_norm": 0.32874220609664917, | |
| "learning_rate": 7.882161580848966e-06, | |
| "loss": 1.3467, | |
| "num_input_tokens_seen": 98304000, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.0927707870713052, | |
| "grad_norm": 0.39634859561920166, | |
| "learning_rate": 7.86788218175523e-06, | |
| "loss": 1.8598, | |
| "num_input_tokens_seen": 98566144, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.09301751788798421, | |
| "grad_norm": 0.222642183303833, | |
| "learning_rate": 7.85356783842216e-06, | |
| "loss": 1.9958, | |
| "num_input_tokens_seen": 98828288, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.09326424870466321, | |
| "grad_norm": 0.17015564441680908, | |
| "learning_rate": 7.839218725265507e-06, | |
| "loss": 1.4093, | |
| "num_input_tokens_seen": 99090432, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.09351097952134221, | |
| "grad_norm": 0.2415931075811386, | |
| "learning_rate": 7.82483501712469e-06, | |
| "loss": 1.6474, | |
| "num_input_tokens_seen": 99352576, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.09375771033802122, | |
| "grad_norm": 0.37360304594039917, | |
| "learning_rate": 7.810416889260653e-06, | |
| "loss": 1.6654, | |
| "num_input_tokens_seen": 99614720, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.09400444115470022, | |
| "grad_norm": 0.8946660161018372, | |
| "learning_rate": 7.795964517353734e-06, | |
| "loss": 2.0143, | |
| "num_input_tokens_seen": 99876864, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.09425117197137922, | |
| "grad_norm": 0.2802148759365082, | |
| "learning_rate": 7.781478077501526e-06, | |
| "loss": 1.8721, | |
| "num_input_tokens_seen": 100139008, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.09449790278805822, | |
| "grad_norm": 0.44011056423187256, | |
| "learning_rate": 7.76695774621672e-06, | |
| "loss": 1.9178, | |
| "num_input_tokens_seen": 100401152, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.09474463360473723, | |
| "grad_norm": 0.20782537758350372, | |
| "learning_rate": 7.752403700424978e-06, | |
| "loss": 2.0922, | |
| "num_input_tokens_seen": 100663296, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.09499136442141623, | |
| "grad_norm": 0.2332392930984497, | |
| "learning_rate": 7.737816117462752e-06, | |
| "loss": 1.332, | |
| "num_input_tokens_seen": 100925440, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 0.333558589220047, | |
| "learning_rate": 7.723195175075136e-06, | |
| "loss": 1.7392, | |
| "num_input_tokens_seen": 101187584, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.09548482605477424, | |
| "grad_norm": 0.48137280344963074, | |
| "learning_rate": 7.7085410514137e-06, | |
| "loss": 1.6437, | |
| "num_input_tokens_seen": 101449728, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.09573155687145324, | |
| "grad_norm": 1.1044962406158447, | |
| "learning_rate": 7.693853925034316e-06, | |
| "loss": 1.336, | |
| "num_input_tokens_seen": 101711872, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.09597828768813224, | |
| "grad_norm": 0.29922980070114136, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 1.7313, | |
| "num_input_tokens_seen": 101974016, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.09622501850481126, | |
| "grad_norm": 0.18246975541114807, | |
| "learning_rate": 7.66438138035365e-06, | |
| "loss": 1.6867, | |
| "num_input_tokens_seen": 102236160, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.09647174932149026, | |
| "grad_norm": 0.38045111298561096, | |
| "learning_rate": 7.649596321166024e-06, | |
| "loss": 1.8284, | |
| "num_input_tokens_seen": 102498304, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.09671848013816926, | |
| "grad_norm": 0.35603606700897217, | |
| "learning_rate": 7.634778977483389e-06, | |
| "loss": 1.6896, | |
| "num_input_tokens_seen": 102760448, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.09696521095484827, | |
| "grad_norm": 0.3689684569835663, | |
| "learning_rate": 7.619929529850397e-06, | |
| "loss": 1.8039, | |
| "num_input_tokens_seen": 103022592, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.09721194177152727, | |
| "grad_norm": 0.23540283739566803, | |
| "learning_rate": 7.605048159202884e-06, | |
| "loss": 1.5043, | |
| "num_input_tokens_seen": 103284736, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.09745867258820627, | |
| "grad_norm": 0.20255284011363983, | |
| "learning_rate": 7.590135046865652e-06, | |
| "loss": 1.7616, | |
| "num_input_tokens_seen": 103546880, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.09770540340488527, | |
| "grad_norm": 0.356922447681427, | |
| "learning_rate": 7.575190374550272e-06, | |
| "loss": 1.6655, | |
| "num_input_tokens_seen": 103809024, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.09795213422156428, | |
| "grad_norm": 0.227988600730896, | |
| "learning_rate": 7.560214324352858e-06, | |
| "loss": 1.8386, | |
| "num_input_tokens_seen": 104071168, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.09819886503824328, | |
| "grad_norm": 0.20468367636203766, | |
| "learning_rate": 7.545207078751858e-06, | |
| "loss": 1.7277, | |
| "num_input_tokens_seen": 104333312, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.09844559585492228, | |
| "grad_norm": 0.2872495651245117, | |
| "learning_rate": 7.530168820605819e-06, | |
| "loss": 1.5949, | |
| "num_input_tokens_seen": 104595456, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.09869232667160129, | |
| "grad_norm": 0.3156526982784271, | |
| "learning_rate": 7.515099733151177e-06, | |
| "loss": 1.7387, | |
| "num_input_tokens_seen": 104857600, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09893905748828029, | |
| "grad_norm": 0.22332081198692322, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.814, | |
| "num_input_tokens_seen": 105119744, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.09918578830495929, | |
| "grad_norm": 0.2750714421272278, | |
| "learning_rate": 7.484869805137778e-06, | |
| "loss": 1.7958, | |
| "num_input_tokens_seen": 105381888, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.0994325191216383, | |
| "grad_norm": 0.30154484510421753, | |
| "learning_rate": 7.469709332921155e-06, | |
| "loss": 1.7635, | |
| "num_input_tokens_seen": 105644032, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.0996792499383173, | |
| "grad_norm": 0.32109102606773376, | |
| "learning_rate": 7.454518768075705e-06, | |
| "loss": 2.0223, | |
| "num_input_tokens_seen": 105906176, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.0999259807549963, | |
| "grad_norm": 0.24551673233509064, | |
| "learning_rate": 7.4392982956936644e-06, | |
| "loss": 1.9326, | |
| "num_input_tokens_seen": 106168320, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.1001727115716753, | |
| "grad_norm": 0.15664780139923096, | |
| "learning_rate": 7.424048101231687e-06, | |
| "loss": 1.5685, | |
| "num_input_tokens_seen": 106430464, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.1004194423883543, | |
| "grad_norm": 0.32335466146469116, | |
| "learning_rate": 7.408768370508577e-06, | |
| "loss": 1.6535, | |
| "num_input_tokens_seen": 106692608, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.10066617320503331, | |
| "grad_norm": 0.2537672221660614, | |
| "learning_rate": 7.393459289703035e-06, | |
| "loss": 1.972, | |
| "num_input_tokens_seen": 106954752, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.10091290402171231, | |
| "grad_norm": 0.35351064801216125, | |
| "learning_rate": 7.378121045351378e-06, | |
| "loss": 1.7374, | |
| "num_input_tokens_seen": 107216896, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.10115963483839131, | |
| "grad_norm": 0.23979292809963226, | |
| "learning_rate": 7.362753824345271e-06, | |
| "loss": 1.4493, | |
| "num_input_tokens_seen": 107479040, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.10140636565507032, | |
| "grad_norm": 0.31650328636169434, | |
| "learning_rate": 7.347357813929455e-06, | |
| "loss": 1.4775, | |
| "num_input_tokens_seen": 107741184, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.10165309647174932, | |
| "grad_norm": 0.3928271234035492, | |
| "learning_rate": 7.3319332016994575e-06, | |
| "loss": 1.5661, | |
| "num_input_tokens_seen": 108003328, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.10189982728842832, | |
| "grad_norm": 0.23190626502037048, | |
| "learning_rate": 7.31648017559931e-06, | |
| "loss": 1.5938, | |
| "num_input_tokens_seen": 108265472, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.10214655810510732, | |
| "grad_norm": 0.3870755136013031, | |
| "learning_rate": 7.300998923919259e-06, | |
| "loss": 1.9648, | |
| "num_input_tokens_seen": 108527616, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.10239328892178633, | |
| "grad_norm": 0.2155226618051529, | |
| "learning_rate": 7.285489635293472e-06, | |
| "loss": 1.6274, | |
| "num_input_tokens_seen": 108789760, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.10264001973846533, | |
| "grad_norm": 0.4175530970096588, | |
| "learning_rate": 7.269952498697734e-06, | |
| "loss": 1.3114, | |
| "num_input_tokens_seen": 109051904, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.10288675055514433, | |
| "grad_norm": 0.2762328088283539, | |
| "learning_rate": 7.254387703447154e-06, | |
| "loss": 1.4719, | |
| "num_input_tokens_seen": 109314048, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.10313348137182334, | |
| "grad_norm": 0.3410496711730957, | |
| "learning_rate": 7.238795439193849e-06, | |
| "loss": 1.4193, | |
| "num_input_tokens_seen": 109576192, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.10338021218850234, | |
| "grad_norm": 0.25268110632896423, | |
| "learning_rate": 7.223175895924638e-06, | |
| "loss": 1.5439, | |
| "num_input_tokens_seen": 109838336, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.10362694300518134, | |
| "grad_norm": 0.23334471881389618, | |
| "learning_rate": 7.207529263958727e-06, | |
| "loss": 1.8237, | |
| "num_input_tokens_seen": 110100480, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.10387367382186036, | |
| "grad_norm": 0.2891489863395691, | |
| "learning_rate": 7.191855733945388e-06, | |
| "loss": 1.5014, | |
| "num_input_tokens_seen": 110362624, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.10412040463853936, | |
| "grad_norm": 0.21520870923995972, | |
| "learning_rate": 7.176155496861639e-06, | |
| "loss": 1.6988, | |
| "num_input_tokens_seen": 110624768, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.10436713545521836, | |
| "grad_norm": 0.6229656934738159, | |
| "learning_rate": 7.160428744009913e-06, | |
| "loss": 1.4534, | |
| "num_input_tokens_seen": 110886912, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.10461386627189737, | |
| "grad_norm": 0.2720300257205963, | |
| "learning_rate": 7.1446756670157306e-06, | |
| "loss": 1.88, | |
| "num_input_tokens_seen": 111149056, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.10486059708857637, | |
| "grad_norm": 0.37459537386894226, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 1.5503, | |
| "num_input_tokens_seen": 111411200, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.10510732790525537, | |
| "grad_norm": 0.1883237063884735, | |
| "learning_rate": 7.113091308703498e-06, | |
| "loss": 1.6568, | |
| "num_input_tokens_seen": 111673344, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.10535405872193437, | |
| "grad_norm": 0.2526542842388153, | |
| "learning_rate": 7.0972604122308865e-06, | |
| "loss": 1.9429, | |
| "num_input_tokens_seen": 111935488, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.10560078953861338, | |
| "grad_norm": 0.14260494709014893, | |
| "learning_rate": 7.081403961302007e-06, | |
| "loss": 1.5881, | |
| "num_input_tokens_seen": 112197632, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.10584752035529238, | |
| "grad_norm": 0.3512221574783325, | |
| "learning_rate": 7.06552214912271e-06, | |
| "loss": 1.6881, | |
| "num_input_tokens_seen": 112459776, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.10609425117197138, | |
| "grad_norm": 0.3587039113044739, | |
| "learning_rate": 7.049615169207864e-06, | |
| "loss": 1.9665, | |
| "num_input_tokens_seen": 112721920, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.10634098198865038, | |
| "grad_norm": 0.4645310044288635, | |
| "learning_rate": 7.033683215379002e-06, | |
| "loss": 1.667, | |
| "num_input_tokens_seen": 112984064, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.10658771280532939, | |
| "grad_norm": 0.1917354017496109, | |
| "learning_rate": 7.0177264817619514e-06, | |
| "loss": 1.2185, | |
| "num_input_tokens_seen": 113246208, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.10683444362200839, | |
| "grad_norm": 0.376539945602417, | |
| "learning_rate": 7.0017451627844765e-06, | |
| "loss": 1.4775, | |
| "num_input_tokens_seen": 113508352, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.1070811744386874, | |
| "grad_norm": 0.3137195408344269, | |
| "learning_rate": 6.985739453173903e-06, | |
| "loss": 1.9464, | |
| "num_input_tokens_seen": 113770496, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.1073279052553664, | |
| "grad_norm": 0.42510855197906494, | |
| "learning_rate": 6.9697095479547564e-06, | |
| "loss": 1.4709, | |
| "num_input_tokens_seen": 114032640, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.1075746360720454, | |
| "grad_norm": 0.3661745488643646, | |
| "learning_rate": 6.953655642446368e-06, | |
| "loss": 1.5647, | |
| "num_input_tokens_seen": 114294784, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.1078213668887244, | |
| "grad_norm": 0.3004036843776703, | |
| "learning_rate": 6.9375779322605154e-06, | |
| "loss": 1.5687, | |
| "num_input_tokens_seen": 114556928, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.1080680977054034, | |
| "grad_norm": 0.3142424523830414, | |
| "learning_rate": 6.921476613299018e-06, | |
| "loss": 1.8035, | |
| "num_input_tokens_seen": 114819072, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.10831482852208241, | |
| "grad_norm": 0.2967626452445984, | |
| "learning_rate": 6.905351881751372e-06, | |
| "loss": 1.789, | |
| "num_input_tokens_seen": 115081216, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.10856155933876141, | |
| "grad_norm": 0.23613819479942322, | |
| "learning_rate": 6.889203934092337e-06, | |
| "loss": 1.6938, | |
| "num_input_tokens_seen": 115343360, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.10880829015544041, | |
| "grad_norm": 0.3341924548149109, | |
| "learning_rate": 6.873032967079562e-06, | |
| "loss": 1.6346, | |
| "num_input_tokens_seen": 115605504, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.10905502097211942, | |
| "grad_norm": 0.17042715847492218, | |
| "learning_rate": 6.856839177751175e-06, | |
| "loss": 1.7458, | |
| "num_input_tokens_seen": 115867648, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.10930175178879842, | |
| "grad_norm": 0.25520455837249756, | |
| "learning_rate": 6.840622763423391e-06, | |
| "loss": 2.0416, | |
| "num_input_tokens_seen": 116129792, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.10954848260547742, | |
| "grad_norm": 0.28210514783859253, | |
| "learning_rate": 6.824383921688098e-06, | |
| "loss": 1.5153, | |
| "num_input_tokens_seen": 116391936, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.10979521342215642, | |
| "grad_norm": 0.31353867053985596, | |
| "learning_rate": 6.808122850410461e-06, | |
| "loss": 1.8329, | |
| "num_input_tokens_seen": 116654080, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.11004194423883543, | |
| "grad_norm": 0.35945144295692444, | |
| "learning_rate": 6.7918397477265e-06, | |
| "loss": 1.9674, | |
| "num_input_tokens_seen": 116916224, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.11028867505551443, | |
| "grad_norm": 0.1974448412656784, | |
| "learning_rate": 6.775534812040686e-06, | |
| "loss": 1.5327, | |
| "num_input_tokens_seen": 117178368, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.11053540587219343, | |
| "grad_norm": 0.22307898104190826, | |
| "learning_rate": 6.759208242023509e-06, | |
| "loss": 1.3609, | |
| "num_input_tokens_seen": 117440512, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.11078213668887243, | |
| "grad_norm": 0.2500917613506317, | |
| "learning_rate": 6.7428602366090764e-06, | |
| "loss": 1.5072, | |
| "num_input_tokens_seen": 117702656, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.11102886750555144, | |
| "grad_norm": 0.27835747599601746, | |
| "learning_rate": 6.7264909949926735e-06, | |
| "loss": 1.7833, | |
| "num_input_tokens_seen": 117964800, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.11127559832223044, | |
| "grad_norm": 0.3439980745315552, | |
| "learning_rate": 6.710100716628345e-06, | |
| "loss": 1.5402, | |
| "num_input_tokens_seen": 118226944, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.11152232913890944, | |
| "grad_norm": 0.22713187336921692, | |
| "learning_rate": 6.693689601226458e-06, | |
| "loss": 1.4622, | |
| "num_input_tokens_seen": 118489088, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.11176905995558846, | |
| "grad_norm": 0.4418184459209442, | |
| "learning_rate": 6.677257848751276e-06, | |
| "loss": 1.8627, | |
| "num_input_tokens_seen": 118751232, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.11201579077226746, | |
| "grad_norm": 0.192154660820961, | |
| "learning_rate": 6.6608056594185166e-06, | |
| "loss": 1.4465, | |
| "num_input_tokens_seen": 119013376, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.11226252158894647, | |
| "grad_norm": 0.15196916460990906, | |
| "learning_rate": 6.644333233692917e-06, | |
| "loss": 2.0922, | |
| "num_input_tokens_seen": 119275520, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.11250925240562547, | |
| "grad_norm": 0.3137149512767792, | |
| "learning_rate": 6.627840772285784e-06, | |
| "loss": 1.5899, | |
| "num_input_tokens_seen": 119537664, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.11275598322230447, | |
| "grad_norm": 0.26558390259742737, | |
| "learning_rate": 6.611328476152557e-06, | |
| "loss": 1.4563, | |
| "num_input_tokens_seen": 119799808, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.11300271403898347, | |
| "grad_norm": 0.20857472717761993, | |
| "learning_rate": 6.594796546490351e-06, | |
| "loss": 2.042, | |
| "num_input_tokens_seen": 120061952, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.11324944485566248, | |
| "grad_norm": 0.3639008700847626, | |
| "learning_rate": 6.578245184735513e-06, | |
| "loss": 1.7995, | |
| "num_input_tokens_seen": 120324096, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.11349617567234148, | |
| "grad_norm": 0.3296775221824646, | |
| "learning_rate": 6.561674592561164e-06, | |
| "loss": 1.6771, | |
| "num_input_tokens_seen": 120586240, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.11374290648902048, | |
| "grad_norm": 0.37127259373664856, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 1.941, | |
| "num_input_tokens_seen": 120848384, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.11398963730569948, | |
| "grad_norm": 0.24075454473495483, | |
| "learning_rate": 6.5284765248155295e-06, | |
| "loss": 1.5899, | |
| "num_input_tokens_seen": 121110528, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.11423636812237849, | |
| "grad_norm": 0.23995226621627808, | |
| "learning_rate": 6.5118494537522235e-06, | |
| "loss": 1.5628, | |
| "num_input_tokens_seen": 121372672, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.11448309893905749, | |
| "grad_norm": 0.31708386540412903, | |
| "learning_rate": 6.495203961280434e-06, | |
| "loss": 1.5741, | |
| "num_input_tokens_seen": 121634816, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.11472982975573649, | |
| "grad_norm": 0.33891844749450684, | |
| "learning_rate": 6.4785402502202345e-06, | |
| "loss": 1.8145, | |
| "num_input_tokens_seen": 121896960, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.1149765605724155, | |
| "grad_norm": 0.29311618208885193, | |
| "learning_rate": 6.461858523613684e-06, | |
| "loss": 1.4072, | |
| "num_input_tokens_seen": 122159104, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.1152232913890945, | |
| "grad_norm": 0.3098562955856323, | |
| "learning_rate": 6.445158984722358e-06, | |
| "loss": 1.4241, | |
| "num_input_tokens_seen": 122421248, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.1154700222057735, | |
| "grad_norm": 0.2898317277431488, | |
| "learning_rate": 6.428441837024868e-06, | |
| "loss": 1.9755, | |
| "num_input_tokens_seen": 122683392, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.1157167530224525, | |
| "grad_norm": 0.24661053717136383, | |
| "learning_rate": 6.411707284214384e-06, | |
| "loss": 1.9215, | |
| "num_input_tokens_seen": 122945536, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.1159634838391315, | |
| "grad_norm": 0.19443027675151825, | |
| "learning_rate": 6.3949555301961474e-06, | |
| "loss": 1.7465, | |
| "num_input_tokens_seen": 123207680, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.11621021465581051, | |
| "grad_norm": 0.3199927508831024, | |
| "learning_rate": 6.378186779084996e-06, | |
| "loss": 1.4374, | |
| "num_input_tokens_seen": 123469824, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.11645694547248951, | |
| "grad_norm": 0.21007393300533295, | |
| "learning_rate": 6.361401235202872e-06, | |
| "loss": 1.8806, | |
| "num_input_tokens_seen": 123731968, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.11670367628916851, | |
| "grad_norm": 0.3228000998497009, | |
| "learning_rate": 6.344599103076329e-06, | |
| "loss": 1.3583, | |
| "num_input_tokens_seen": 123994112, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.11695040710584752, | |
| "grad_norm": 0.4336913824081421, | |
| "learning_rate": 6.327780587434045e-06, | |
| "loss": 1.5847, | |
| "num_input_tokens_seen": 124256256, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.11719713792252652, | |
| "grad_norm": 0.28673404455184937, | |
| "learning_rate": 6.310945893204324e-06, | |
| "loss": 1.2474, | |
| "num_input_tokens_seen": 124518400, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.11744386873920552, | |
| "grad_norm": 0.22935543954372406, | |
| "learning_rate": 6.294095225512604e-06, | |
| "loss": 1.5185, | |
| "num_input_tokens_seen": 124780544, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.11769059955588453, | |
| "grad_norm": 0.22382254898548126, | |
| "learning_rate": 6.277228789678953e-06, | |
| "loss": 1.6705, | |
| "num_input_tokens_seen": 125042688, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.11793733037256353, | |
| "grad_norm": 0.5391249060630798, | |
| "learning_rate": 6.26034679121557e-06, | |
| "loss": 1.682, | |
| "num_input_tokens_seen": 125304832, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.11818406118924253, | |
| "grad_norm": 0.28263115882873535, | |
| "learning_rate": 6.243449435824276e-06, | |
| "loss": 2.1149, | |
| "num_input_tokens_seen": 125566976, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.11843079200592153, | |
| "grad_norm": 0.24054385721683502, | |
| "learning_rate": 6.2265369293940135e-06, | |
| "loss": 1.801, | |
| "num_input_tokens_seen": 125829120, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.11867752282260054, | |
| "grad_norm": 0.23487120866775513, | |
| "learning_rate": 6.209609477998339e-06, | |
| "loss": 1.6175, | |
| "num_input_tokens_seen": 126091264, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.11892425363927954, | |
| "grad_norm": 0.30739638209342957, | |
| "learning_rate": 6.192667287892905e-06, | |
| "loss": 1.9698, | |
| "num_input_tokens_seen": 126353408, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.11917098445595854, | |
| "grad_norm": 0.3312475085258484, | |
| "learning_rate": 6.17571056551295e-06, | |
| "loss": 2.1531, | |
| "num_input_tokens_seen": 126615552, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.11941771527263756, | |
| "grad_norm": 0.3214891254901886, | |
| "learning_rate": 6.158739517470786e-06, | |
| "loss": 1.7976, | |
| "num_input_tokens_seen": 126877696, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.11966444608931656, | |
| "grad_norm": 0.19428040087223053, | |
| "learning_rate": 6.141754350553279e-06, | |
| "loss": 1.5015, | |
| "num_input_tokens_seen": 127139840, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.11991117690599556, | |
| "grad_norm": 0.18812116980552673, | |
| "learning_rate": 6.124755271719326e-06, | |
| "loss": 1.2669, | |
| "num_input_tokens_seen": 127401984, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.12015790772267457, | |
| "grad_norm": 0.2792108654975891, | |
| "learning_rate": 6.107742488097338e-06, | |
| "loss": 1.6827, | |
| "num_input_tokens_seen": 127664128, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.12040463853935357, | |
| "grad_norm": 0.32973822951316833, | |
| "learning_rate": 6.090716206982714e-06, | |
| "loss": 1.4348, | |
| "num_input_tokens_seen": 127926272, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.12065136935603257, | |
| "grad_norm": 0.23311680555343628, | |
| "learning_rate": 6.073676635835317e-06, | |
| "loss": 1.7046, | |
| "num_input_tokens_seen": 128188416, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.12089810017271158, | |
| "grad_norm": 0.4876193106174469, | |
| "learning_rate": 6.056623982276945e-06, | |
| "loss": 0.9838, | |
| "num_input_tokens_seen": 128450560, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.12114483098939058, | |
| "grad_norm": 0.23447804152965546, | |
| "learning_rate": 6.039558454088796e-06, | |
| "loss": 1.5899, | |
| "num_input_tokens_seen": 128712704, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.12139156180606958, | |
| "grad_norm": 0.31559622287750244, | |
| "learning_rate": 6.022480259208951e-06, | |
| "loss": 1.8169, | |
| "num_input_tokens_seen": 128974848, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.12163829262274858, | |
| "grad_norm": 0.228166401386261, | |
| "learning_rate": 6.005389605729824e-06, | |
| "loss": 1.7, | |
| "num_input_tokens_seen": 129236992, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.12188502343942759, | |
| "grad_norm": 0.25788137316703796, | |
| "learning_rate": 5.988286701895631e-06, | |
| "loss": 1.8412, | |
| "num_input_tokens_seen": 129499136, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.12213175425610659, | |
| "grad_norm": 0.23868145048618317, | |
| "learning_rate": 5.97117175609986e-06, | |
| "loss": 1.4791, | |
| "num_input_tokens_seen": 129761280, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.12237848507278559, | |
| "grad_norm": 0.22958144545555115, | |
| "learning_rate": 5.954044976882725e-06, | |
| "loss": 1.6004, | |
| "num_input_tokens_seen": 130023424, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.1226252158894646, | |
| "grad_norm": 0.24195703864097595, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 1.8709, | |
| "num_input_tokens_seen": 130285568, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.1228719467061436, | |
| "grad_norm": 0.35294461250305176, | |
| "learning_rate": 5.919756753063601e-06, | |
| "loss": 1.8445, | |
| "num_input_tokens_seen": 130547712, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.1231186775228226, | |
| "grad_norm": 0.4138323664665222, | |
| "learning_rate": 5.902595726252801e-06, | |
| "loss": 1.9917, | |
| "num_input_tokens_seen": 130809856, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.1233654083395016, | |
| "grad_norm": 0.7690160870552063, | |
| "learning_rate": 5.885423701597918e-06, | |
| "loss": 2.0276, | |
| "num_input_tokens_seen": 131072000, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1236121391561806, | |
| "grad_norm": 0.28807610273361206, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 1.952, | |
| "num_input_tokens_seen": 131334144, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.12385886997285961, | |
| "grad_norm": 0.35294869542121887, | |
| "learning_rate": 5.851047495830163e-06, | |
| "loss": 1.5884, | |
| "num_input_tokens_seen": 131596288, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.12410560078953861, | |
| "grad_norm": 0.20024876296520233, | |
| "learning_rate": 5.8338437335805124e-06, | |
| "loss": 1.497, | |
| "num_input_tokens_seen": 131858432, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.12435233160621761, | |
| "grad_norm": 0.3332088887691498, | |
| "learning_rate": 5.816629811208112e-06, | |
| "loss": 1.8099, | |
| "num_input_tokens_seen": 132120576, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.12459906242289662, | |
| "grad_norm": 0.21323569118976593, | |
| "learning_rate": 5.799405938459175e-06, | |
| "loss": 2.0373, | |
| "num_input_tokens_seen": 132382720, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.12484579323957562, | |
| "grad_norm": 0.2117518186569214, | |
| "learning_rate": 5.782172325201155e-06, | |
| "loss": 1.8806, | |
| "num_input_tokens_seen": 132644864, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.12509252405625462, | |
| "grad_norm": 0.29583173990249634, | |
| "learning_rate": 5.764929181420191e-06, | |
| "loss": 1.7029, | |
| "num_input_tokens_seen": 132907008, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.12533925487293363, | |
| "grad_norm": 0.3036397695541382, | |
| "learning_rate": 5.747676717218549e-06, | |
| "loss": 1.6968, | |
| "num_input_tokens_seen": 133169152, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.12558598568961263, | |
| "grad_norm": 0.4999355971813202, | |
| "learning_rate": 5.730415142812059e-06, | |
| "loss": 1.9457, | |
| "num_input_tokens_seen": 133431296, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.12583271650629163, | |
| "grad_norm": 0.2996709942817688, | |
| "learning_rate": 5.7131446685275595e-06, | |
| "loss": 1.8654, | |
| "num_input_tokens_seen": 133693440, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.12607944732297063, | |
| "grad_norm": 0.3077060282230377, | |
| "learning_rate": 5.695865504800328e-06, | |
| "loss": 1.8855, | |
| "num_input_tokens_seen": 133955584, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.12632617813964964, | |
| "grad_norm": 0.29848551750183105, | |
| "learning_rate": 5.678577862171523e-06, | |
| "loss": 1.8403, | |
| "num_input_tokens_seen": 134217728, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.12657290895632864, | |
| "grad_norm": 0.3802272081375122, | |
| "learning_rate": 5.661281951285613e-06, | |
| "loss": 1.7932, | |
| "num_input_tokens_seen": 134479872, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.12681963977300764, | |
| "grad_norm": 0.2726668417453766, | |
| "learning_rate": 5.643977982887815e-06, | |
| "loss": 1.399, | |
| "num_input_tokens_seen": 134742016, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.12706637058968664, | |
| "grad_norm": 0.3101379871368408, | |
| "learning_rate": 5.626666167821522e-06, | |
| "loss": 1.917, | |
| "num_input_tokens_seen": 135004160, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.12731310140636565, | |
| "grad_norm": 0.1991398185491562, | |
| "learning_rate": 5.609346717025738e-06, | |
| "loss": 1.6612, | |
| "num_input_tokens_seen": 135266304, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.12755983222304465, | |
| "grad_norm": 0.2825518250465393, | |
| "learning_rate": 5.592019841532507e-06, | |
| "loss": 1.7776, | |
| "num_input_tokens_seen": 135528448, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.12780656303972365, | |
| "grad_norm": 0.21650439500808716, | |
| "learning_rate": 5.5746857524643335e-06, | |
| "loss": 1.5227, | |
| "num_input_tokens_seen": 135790592, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.12805329385640266, | |
| "grad_norm": 0.272237092256546, | |
| "learning_rate": 5.557344661031628e-06, | |
| "loss": 1.8114, | |
| "num_input_tokens_seen": 136052736, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.12830002467308166, | |
| "grad_norm": 0.3208904564380646, | |
| "learning_rate": 5.539996778530114e-06, | |
| "loss": 1.4108, | |
| "num_input_tokens_seen": 136314880, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.12854675548976066, | |
| "grad_norm": 0.21720334887504578, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 2.0095, | |
| "num_input_tokens_seen": 136577024, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.12879348630643966, | |
| "grad_norm": 0.3421568274497986, | |
| "learning_rate": 5.505281485914732e-06, | |
| "loss": 1.8559, | |
| "num_input_tokens_seen": 136839168, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.12904021712311867, | |
| "grad_norm": 0.2509710192680359, | |
| "learning_rate": 5.487914498795748e-06, | |
| "loss": 1.6357, | |
| "num_input_tokens_seen": 137101312, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.12928694793979767, | |
| "grad_norm": 0.19334466755390167, | |
| "learning_rate": 5.470541566592573e-06, | |
| "loss": 1.1662, | |
| "num_input_tokens_seen": 137363456, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.12953367875647667, | |
| "grad_norm": 0.22243958711624146, | |
| "learning_rate": 5.453162900988902e-06, | |
| "loss": 1.4116, | |
| "num_input_tokens_seen": 137625600, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.12978040957315568, | |
| "grad_norm": 0.37442705035209656, | |
| "learning_rate": 5.435778713738292e-06, | |
| "loss": 2.0153, | |
| "num_input_tokens_seen": 137887744, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.13002714038983468, | |
| "grad_norm": 0.24719154834747314, | |
| "learning_rate": 5.41838921666158e-06, | |
| "loss": 1.2343, | |
| "num_input_tokens_seen": 138149888, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.13027387120651368, | |
| "grad_norm": 0.313684344291687, | |
| "learning_rate": 5.400994621644294e-06, | |
| "loss": 1.83, | |
| "num_input_tokens_seen": 138412032, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.13052060202319268, | |
| "grad_norm": 0.3713296353816986, | |
| "learning_rate": 5.383595140634093e-06, | |
| "loss": 1.9503, | |
| "num_input_tokens_seen": 138674176, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.13076733283987169, | |
| "grad_norm": 0.2469317466020584, | |
| "learning_rate": 5.366190985638159e-06, | |
| "loss": 1.1653, | |
| "num_input_tokens_seen": 138936320, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.13101406365655072, | |
| "grad_norm": 0.3134791851043701, | |
| "learning_rate": 5.348782368720627e-06, | |
| "loss": 1.4074, | |
| "num_input_tokens_seen": 139198464, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.13126079447322972, | |
| "grad_norm": 0.2104741483926773, | |
| "learning_rate": 5.3313695020000026e-06, | |
| "loss": 1.9757, | |
| "num_input_tokens_seen": 139460608, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.13150752528990872, | |
| "grad_norm": 0.2387029379606247, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 1.6213, | |
| "num_input_tokens_seen": 139722752, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.13175425610658772, | |
| "grad_norm": 0.371168315410614, | |
| "learning_rate": 5.296531867879809e-06, | |
| "loss": 1.8211, | |
| "num_input_tokens_seen": 139984896, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.13200098692326673, | |
| "grad_norm": 0.4188603162765503, | |
| "learning_rate": 5.27910752496582e-06, | |
| "loss": 1.7739, | |
| "num_input_tokens_seen": 140247040, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.13224771773994573, | |
| "grad_norm": 0.38428500294685364, | |
| "learning_rate": 5.2616797812147205e-06, | |
| "loss": 1.8766, | |
| "num_input_tokens_seen": 140509184, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.13249444855662473, | |
| "grad_norm": 0.27660655975341797, | |
| "learning_rate": 5.244248848978067e-06, | |
| "loss": 1.7614, | |
| "num_input_tokens_seen": 140771328, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.13274117937330374, | |
| "grad_norm": 0.1527780443429947, | |
| "learning_rate": 5.226814940646268e-06, | |
| "loss": 1.2256, | |
| "num_input_tokens_seen": 141033472, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.13298791018998274, | |
| "grad_norm": 0.264778733253479, | |
| "learning_rate": 5.209378268645998e-06, | |
| "loss": 1.4941, | |
| "num_input_tokens_seen": 141295616, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.13323464100666174, | |
| "grad_norm": 0.3885688781738281, | |
| "learning_rate": 5.1919390454376e-06, | |
| "loss": 1.9089, | |
| "num_input_tokens_seen": 141557760, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.13348137182334074, | |
| "grad_norm": 0.2816999554634094, | |
| "learning_rate": 5.174497483512506e-06, | |
| "loss": 1.6554, | |
| "num_input_tokens_seen": 141819904, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.13372810264001975, | |
| "grad_norm": 0.2949479818344116, | |
| "learning_rate": 5.157053795390642e-06, | |
| "loss": 1.5687, | |
| "num_input_tokens_seen": 142082048, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.13397483345669875, | |
| "grad_norm": 0.1631646454334259, | |
| "learning_rate": 5.139608193617846e-06, | |
| "loss": 1.117, | |
| "num_input_tokens_seen": 142344192, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.13422156427337775, | |
| "grad_norm": 0.23090092837810516, | |
| "learning_rate": 5.1221608907632665e-06, | |
| "loss": 1.8237, | |
| "num_input_tokens_seen": 142606336, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.13446829509005676, | |
| "grad_norm": 0.20347069203853607, | |
| "learning_rate": 5.1047120994167855e-06, | |
| "loss": 1.7979, | |
| "num_input_tokens_seen": 142868480, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.13471502590673576, | |
| "grad_norm": 0.2656711935997009, | |
| "learning_rate": 5.087262032186418e-06, | |
| "loss": 1.8041, | |
| "num_input_tokens_seen": 143130624, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.13496175672341476, | |
| "grad_norm": 0.40291059017181396, | |
| "learning_rate": 5.069810901695727e-06, | |
| "loss": 1.9054, | |
| "num_input_tokens_seen": 143392768, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.13520848754009376, | |
| "grad_norm": 0.6440242528915405, | |
| "learning_rate": 5.05235892058123e-06, | |
| "loss": 1.5505, | |
| "num_input_tokens_seen": 143654912, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.13545521835677277, | |
| "grad_norm": 0.2078663855791092, | |
| "learning_rate": 5.034906301489808e-06, | |
| "loss": 1.6307, | |
| "num_input_tokens_seen": 143917056, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.13570194917345177, | |
| "grad_norm": 0.3324054777622223, | |
| "learning_rate": 5.0174532570761194e-06, | |
| "loss": 1.7519, | |
| "num_input_tokens_seen": 144179200, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.13594867999013077, | |
| "grad_norm": 0.20945605635643005, | |
| "learning_rate": 5e-06, | |
| "loss": 1.7034, | |
| "num_input_tokens_seen": 144441344, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.13619541080680977, | |
| "grad_norm": 0.3655446469783783, | |
| "learning_rate": 4.982546742923883e-06, | |
| "loss": 2.0479, | |
| "num_input_tokens_seen": 144703488, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.13644214162348878, | |
| "grad_norm": 0.3826795518398285, | |
| "learning_rate": 4.965093698510192e-06, | |
| "loss": 1.454, | |
| "num_input_tokens_seen": 144965632, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.13668887244016778, | |
| "grad_norm": 0.30656811594963074, | |
| "learning_rate": 4.9476410794187726e-06, | |
| "loss": 1.5023, | |
| "num_input_tokens_seen": 145227776, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.13693560325684678, | |
| "grad_norm": 0.23264142870903015, | |
| "learning_rate": 4.9301890983042744e-06, | |
| "loss": 1.4307, | |
| "num_input_tokens_seen": 145489920, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.13718233407352579, | |
| "grad_norm": 0.2861672341823578, | |
| "learning_rate": 4.9127379678135825e-06, | |
| "loss": 1.4308, | |
| "num_input_tokens_seen": 145752064, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.1374290648902048, | |
| "grad_norm": 0.31259533762931824, | |
| "learning_rate": 4.895287900583216e-06, | |
| "loss": 2.0955, | |
| "num_input_tokens_seen": 146014208, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.1376757957068838, | |
| "grad_norm": 0.33701300621032715, | |
| "learning_rate": 4.877839109236735e-06, | |
| "loss": 2.0646, | |
| "num_input_tokens_seen": 146276352, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.1379225265235628, | |
| "grad_norm": 0.23440125584602356, | |
| "learning_rate": 4.860391806382157e-06, | |
| "loss": 1.3577, | |
| "num_input_tokens_seen": 146538496, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.1381692573402418, | |
| "grad_norm": 0.39793065190315247, | |
| "learning_rate": 4.842946204609359e-06, | |
| "loss": 1.9013, | |
| "num_input_tokens_seen": 146800640, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.1384159881569208, | |
| "grad_norm": 0.3499162495136261, | |
| "learning_rate": 4.825502516487497e-06, | |
| "loss": 1.9023, | |
| "num_input_tokens_seen": 147062784, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.1386627189735998, | |
| "grad_norm": 0.28828251361846924, | |
| "learning_rate": 4.8080609545624004e-06, | |
| "loss": 1.446, | |
| "num_input_tokens_seen": 147324928, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.1389094497902788, | |
| "grad_norm": 0.3065829575061798, | |
| "learning_rate": 4.7906217313540035e-06, | |
| "loss": 2.0544, | |
| "num_input_tokens_seen": 147587072, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.1391561806069578, | |
| "grad_norm": 0.3566630780696869, | |
| "learning_rate": 4.7731850593537316e-06, | |
| "loss": 1.9503, | |
| "num_input_tokens_seen": 147849216, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.1394029114236368, | |
| "grad_norm": 0.2425328940153122, | |
| "learning_rate": 4.755751151021934e-06, | |
| "loss": 1.7033, | |
| "num_input_tokens_seen": 148111360, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.1396496422403158, | |
| "grad_norm": 0.2376437932252884, | |
| "learning_rate": 4.738320218785281e-06, | |
| "loss": 1.6898, | |
| "num_input_tokens_seen": 148373504, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.13989637305699482, | |
| "grad_norm": 0.19275647401809692, | |
| "learning_rate": 4.720892475034181e-06, | |
| "loss": 2.0209, | |
| "num_input_tokens_seen": 148635648, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.14014310387367382, | |
| "grad_norm": 0.3049376308917999, | |
| "learning_rate": 4.703468132120193e-06, | |
| "loss": 1.7352, | |
| "num_input_tokens_seen": 148897792, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.14038983469035282, | |
| "grad_norm": 0.24015147984027863, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 1.6749, | |
| "num_input_tokens_seen": 149159936, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.14063656550703182, | |
| "grad_norm": 0.3943753242492676, | |
| "learning_rate": 4.668630498000001e-06, | |
| "loss": 1.977, | |
| "num_input_tokens_seen": 149422080, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.14088329632371083, | |
| "grad_norm": 0.18447957932949066, | |
| "learning_rate": 4.651217631279374e-06, | |
| "loss": 1.8602, | |
| "num_input_tokens_seen": 149684224, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.14113002714038983, | |
| "grad_norm": 0.20968987047672272, | |
| "learning_rate": 4.6338090143618435e-06, | |
| "loss": 1.5058, | |
| "num_input_tokens_seen": 149946368, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.14137675795706883, | |
| "grad_norm": 0.27084267139434814, | |
| "learning_rate": 4.6164048593659076e-06, | |
| "loss": 1.8903, | |
| "num_input_tokens_seen": 150208512, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.14162348877374784, | |
| "grad_norm": 0.33901768922805786, | |
| "learning_rate": 4.5990053783557066e-06, | |
| "loss": 1.81, | |
| "num_input_tokens_seen": 150470656, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.14187021959042684, | |
| "grad_norm": 0.38979673385620117, | |
| "learning_rate": 4.581610783338424e-06, | |
| "loss": 2.0141, | |
| "num_input_tokens_seen": 150732800, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.14211695040710584, | |
| "grad_norm": 0.3750932216644287, | |
| "learning_rate": 4.564221286261709e-06, | |
| "loss": 1.6991, | |
| "num_input_tokens_seen": 150994944, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.14236368122378484, | |
| "grad_norm": 0.2790539264678955, | |
| "learning_rate": 4.546837099011101e-06, | |
| "loss": 1.5295, | |
| "num_input_tokens_seen": 151257088, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.14261041204046385, | |
| "grad_norm": 0.17121604084968567, | |
| "learning_rate": 4.529458433407429e-06, | |
| "loss": 1.3758, | |
| "num_input_tokens_seen": 151519232, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 1.2501734495162964, | |
| "learning_rate": 4.512085501204254e-06, | |
| "loss": 1.8476, | |
| "num_input_tokens_seen": 151781376, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.14310387367382185, | |
| "grad_norm": 0.22766587138175964, | |
| "learning_rate": 4.494718514085269e-06, | |
| "loss": 1.0005, | |
| "num_input_tokens_seen": 152043520, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.14335060449050085, | |
| "grad_norm": 0.46749159693717957, | |
| "learning_rate": 4.477357683661734e-06, | |
| "loss": 1.7644, | |
| "num_input_tokens_seen": 152305664, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.14359733530717986, | |
| "grad_norm": 0.5128108859062195, | |
| "learning_rate": 4.460003221469886e-06, | |
| "loss": 1.6494, | |
| "num_input_tokens_seen": 152567808, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.14384406612385886, | |
| "grad_norm": 0.35547828674316406, | |
| "learning_rate": 4.442655338968373e-06, | |
| "loss": 1.9043, | |
| "num_input_tokens_seen": 152829952, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.14409079694053786, | |
| "grad_norm": 0.2643188536167145, | |
| "learning_rate": 4.425314247535668e-06, | |
| "loss": 1.8414, | |
| "num_input_tokens_seen": 153092096, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.14433752775721687, | |
| "grad_norm": 0.36946919560432434, | |
| "learning_rate": 4.4079801584674955e-06, | |
| "loss": 1.6937, | |
| "num_input_tokens_seen": 153354240, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.14458425857389587, | |
| "grad_norm": 0.30119383335113525, | |
| "learning_rate": 4.390653282974264e-06, | |
| "loss": 1.6792, | |
| "num_input_tokens_seen": 153616384, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.14483098939057487, | |
| "grad_norm": 0.30609673261642456, | |
| "learning_rate": 4.373333832178478e-06, | |
| "loss": 1.7094, | |
| "num_input_tokens_seen": 153878528, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.14507772020725387, | |
| "grad_norm": 0.32530122995376587, | |
| "learning_rate": 4.356022017112187e-06, | |
| "loss": 1.9982, | |
| "num_input_tokens_seen": 154140672, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.14532445102393288, | |
| "grad_norm": 0.39551761746406555, | |
| "learning_rate": 4.3387180487143875e-06, | |
| "loss": 2.07, | |
| "num_input_tokens_seen": 154402816, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.14557118184061188, | |
| "grad_norm": 0.45149853825569153, | |
| "learning_rate": 4.321422137828479e-06, | |
| "loss": 1.4199, | |
| "num_input_tokens_seen": 154664960, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.14581791265729088, | |
| "grad_norm": 0.3984176814556122, | |
| "learning_rate": 4.304134495199675e-06, | |
| "loss": 1.5707, | |
| "num_input_tokens_seen": 154927104, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.14606464347396989, | |
| "grad_norm": 0.3942200839519501, | |
| "learning_rate": 4.286855331472442e-06, | |
| "loss": 1.6478, | |
| "num_input_tokens_seen": 155189248, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.14631137429064892, | |
| "grad_norm": 0.1897418200969696, | |
| "learning_rate": 4.269584857187942e-06, | |
| "loss": 1.4291, | |
| "num_input_tokens_seen": 155451392, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.14655810510732792, | |
| "grad_norm": 0.262803852558136, | |
| "learning_rate": 4.2523232827814534e-06, | |
| "loss": 1.2587, | |
| "num_input_tokens_seen": 155713536, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.14680483592400692, | |
| "grad_norm": 0.6395058631896973, | |
| "learning_rate": 4.23507081857981e-06, | |
| "loss": 1.3483, | |
| "num_input_tokens_seen": 155975680, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.14705156674068592, | |
| "grad_norm": 0.25592687726020813, | |
| "learning_rate": 4.217827674798845e-06, | |
| "loss": 1.615, | |
| "num_input_tokens_seen": 156237824, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.14729829755736493, | |
| "grad_norm": 0.22586092352867126, | |
| "learning_rate": 4.200594061540827e-06, | |
| "loss": 1.6813, | |
| "num_input_tokens_seen": 156499968, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.14754502837404393, | |
| "grad_norm": 0.2651527225971222, | |
| "learning_rate": 4.183370188791891e-06, | |
| "loss": 1.416, | |
| "num_input_tokens_seen": 156762112, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.14779175919072293, | |
| "grad_norm": 0.33769476413726807, | |
| "learning_rate": 4.166156266419489e-06, | |
| "loss": 1.7654, | |
| "num_input_tokens_seen": 157024256, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.14803849000740193, | |
| "grad_norm": 0.3942760229110718, | |
| "learning_rate": 4.148952504169839e-06, | |
| "loss": 1.666, | |
| "num_input_tokens_seen": 157286400, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.14828522082408094, | |
| "grad_norm": 0.315070241689682, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 1.6868, | |
| "num_input_tokens_seen": 157548544, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.14853195164075994, | |
| "grad_norm": 0.30992016196250916, | |
| "learning_rate": 4.114576298402085e-06, | |
| "loss": 1.2569, | |
| "num_input_tokens_seen": 157810688, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.14877868245743894, | |
| "grad_norm": 0.15681593120098114, | |
| "learning_rate": 4.0974042737472005e-06, | |
| "loss": 1.8132, | |
| "num_input_tokens_seen": 158072832, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.14902541327411795, | |
| "grad_norm": 0.3081078827381134, | |
| "learning_rate": 4.0802432469364e-06, | |
| "loss": 1.8482, | |
| "num_input_tokens_seen": 158334976, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.14927214409079695, | |
| "grad_norm": 0.2770363688468933, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 2.1245, | |
| "num_input_tokens_seen": 158597120, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.14951887490747595, | |
| "grad_norm": 0.22125285863876343, | |
| "learning_rate": 4.045955023117276e-06, | |
| "loss": 2.0896, | |
| "num_input_tokens_seen": 158859264, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.14976560572415495, | |
| "grad_norm": 0.2769063115119934, | |
| "learning_rate": 4.028828243900141e-06, | |
| "loss": 2.1542, | |
| "num_input_tokens_seen": 159121408, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.15001233654083396, | |
| "grad_norm": 0.26015493273735046, | |
| "learning_rate": 4.0117132981043695e-06, | |
| "loss": 1.6067, | |
| "num_input_tokens_seen": 159383552, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.15025906735751296, | |
| "grad_norm": 0.41176754236221313, | |
| "learning_rate": 3.994610394270178e-06, | |
| "loss": 1.942, | |
| "num_input_tokens_seen": 159645696, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.15050579817419196, | |
| "grad_norm": 0.2698221206665039, | |
| "learning_rate": 3.977519740791049e-06, | |
| "loss": 1.8544, | |
| "num_input_tokens_seen": 159907840, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.15075252899087097, | |
| "grad_norm": 0.21741293370723724, | |
| "learning_rate": 3.960441545911205e-06, | |
| "loss": 1.5599, | |
| "num_input_tokens_seen": 160169984, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.15099925980754997, | |
| "grad_norm": 0.3728959560394287, | |
| "learning_rate": 3.943376017723058e-06, | |
| "loss": 1.3439, | |
| "num_input_tokens_seen": 160432128, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.15124599062422897, | |
| "grad_norm": 0.36028945446014404, | |
| "learning_rate": 3.926323364164684e-06, | |
| "loss": 1.9217, | |
| "num_input_tokens_seen": 160694272, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.15149272144090797, | |
| "grad_norm": 0.24226897954940796, | |
| "learning_rate": 3.909283793017289e-06, | |
| "loss": 1.6554, | |
| "num_input_tokens_seen": 160956416, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.15173945225758698, | |
| "grad_norm": 0.41064637899398804, | |
| "learning_rate": 3.892257511902664e-06, | |
| "loss": 1.8607, | |
| "num_input_tokens_seen": 161218560, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.15198618307426598, | |
| "grad_norm": 0.2579009234905243, | |
| "learning_rate": 3.875244728280676e-06, | |
| "loss": 1.4227, | |
| "num_input_tokens_seen": 161480704, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.15223291389094498, | |
| "grad_norm": 0.26726585626602173, | |
| "learning_rate": 3.8582456494467214e-06, | |
| "loss": 1.5324, | |
| "num_input_tokens_seen": 161742848, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.15247964470762398, | |
| "grad_norm": 0.25933149456977844, | |
| "learning_rate": 3.841260482529215e-06, | |
| "loss": 1.7812, | |
| "num_input_tokens_seen": 162004992, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.152726375524303, | |
| "grad_norm": 0.4113217294216156, | |
| "learning_rate": 3.82428943448705e-06, | |
| "loss": 1.3672, | |
| "num_input_tokens_seen": 162267136, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.152973106340982, | |
| "grad_norm": 0.20348288118839264, | |
| "learning_rate": 3.8073327121070968e-06, | |
| "loss": 1.0549, | |
| "num_input_tokens_seen": 162529280, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.153219837157661, | |
| "grad_norm": 0.2775270640850067, | |
| "learning_rate": 3.790390522001662e-06, | |
| "loss": 1.5691, | |
| "num_input_tokens_seen": 162791424, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.15346656797434, | |
| "grad_norm": 0.2500717043876648, | |
| "learning_rate": 3.7734630706059873e-06, | |
| "loss": 1.2996, | |
| "num_input_tokens_seen": 163053568, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.153713298791019, | |
| "grad_norm": 0.4124068021774292, | |
| "learning_rate": 3.756550564175727e-06, | |
| "loss": 2.1117, | |
| "num_input_tokens_seen": 163315712, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.153960029607698, | |
| "grad_norm": 0.20559923350811005, | |
| "learning_rate": 3.7396532087844318e-06, | |
| "loss": 1.1094, | |
| "num_input_tokens_seen": 163577856, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.154206760424377, | |
| "grad_norm": 0.33458614349365234, | |
| "learning_rate": 3.7227712103210485e-06, | |
| "loss": 1.5924, | |
| "num_input_tokens_seen": 163840000, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.154453491241056, | |
| "grad_norm": 0.27552902698516846, | |
| "learning_rate": 3.705904774487396e-06, | |
| "loss": 1.7425, | |
| "num_input_tokens_seen": 164102144, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.154700222057735, | |
| "grad_norm": 0.2488897293806076, | |
| "learning_rate": 3.6890541067956775e-06, | |
| "loss": 2.0084, | |
| "num_input_tokens_seen": 164364288, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.154946952874414, | |
| "grad_norm": 0.3026079535484314, | |
| "learning_rate": 3.672219412565956e-06, | |
| "loss": 1.7328, | |
| "num_input_tokens_seen": 164626432, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.15519368369109302, | |
| "grad_norm": 0.3371894061565399, | |
| "learning_rate": 3.655400896923672e-06, | |
| "loss": 1.5856, | |
| "num_input_tokens_seen": 164888576, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.15544041450777202, | |
| "grad_norm": 0.3499716520309448, | |
| "learning_rate": 3.6385987647971287e-06, | |
| "loss": 1.4779, | |
| "num_input_tokens_seen": 165150720, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.15568714532445102, | |
| "grad_norm": 0.32119953632354736, | |
| "learning_rate": 3.6218132209150047e-06, | |
| "loss": 1.8302, | |
| "num_input_tokens_seen": 165412864, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.15593387614113002, | |
| "grad_norm": 0.240133598446846, | |
| "learning_rate": 3.6050444698038547e-06, | |
| "loss": 1.6325, | |
| "num_input_tokens_seen": 165675008, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.15618060695780903, | |
| "grad_norm": 0.25198155641555786, | |
| "learning_rate": 3.5882927157856175e-06, | |
| "loss": 2.0047, | |
| "num_input_tokens_seen": 165937152, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.15642733777448803, | |
| "grad_norm": 0.19772285223007202, | |
| "learning_rate": 3.571558162975133e-06, | |
| "loss": 1.7201, | |
| "num_input_tokens_seen": 166199296, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.15667406859116703, | |
| "grad_norm": 0.32129037380218506, | |
| "learning_rate": 3.5548410152776414e-06, | |
| "loss": 1.4001, | |
| "num_input_tokens_seen": 166461440, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.15692079940784603, | |
| "grad_norm": 0.41397202014923096, | |
| "learning_rate": 3.538141476386317e-06, | |
| "loss": 1.7114, | |
| "num_input_tokens_seen": 166723584, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.15716753022452504, | |
| "grad_norm": 0.3888271450996399, | |
| "learning_rate": 3.521459749779769e-06, | |
| "loss": 1.7102, | |
| "num_input_tokens_seen": 166985728, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.15741426104120404, | |
| "grad_norm": 0.3346923887729645, | |
| "learning_rate": 3.5047960387195673e-06, | |
| "loss": 1.7585, | |
| "num_input_tokens_seen": 167247872, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.15766099185788304, | |
| "grad_norm": 0.3371780216693878, | |
| "learning_rate": 3.488150546247778e-06, | |
| "loss": 1.532, | |
| "num_input_tokens_seen": 167510016, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.15790772267456205, | |
| "grad_norm": 0.3255195915699005, | |
| "learning_rate": 3.471523475184472e-06, | |
| "loss": 2.0643, | |
| "num_input_tokens_seen": 167772160, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.15815445349124105, | |
| "grad_norm": 0.3299016058444977, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 1.7138, | |
| "num_input_tokens_seen": 168034304, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.15840118430792005, | |
| "grad_norm": 0.4465411901473999, | |
| "learning_rate": 3.4383254074388373e-06, | |
| "loss": 1.4068, | |
| "num_input_tokens_seen": 168296448, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.15864791512459905, | |
| "grad_norm": 0.2777688801288605, | |
| "learning_rate": 3.4217548152644887e-06, | |
| "loss": 1.7274, | |
| "num_input_tokens_seen": 168558592, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.15889464594127806, | |
| "grad_norm": 0.3787316083908081, | |
| "learning_rate": 3.40520345350965e-06, | |
| "loss": 1.4899, | |
| "num_input_tokens_seen": 168820736, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.15914137675795706, | |
| "grad_norm": 0.19709822535514832, | |
| "learning_rate": 3.3886715238474454e-06, | |
| "loss": 1.138, | |
| "num_input_tokens_seen": 169082880, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.15938810757463606, | |
| "grad_norm": 0.5791448950767517, | |
| "learning_rate": 3.372159227714218e-06, | |
| "loss": 1.7617, | |
| "num_input_tokens_seen": 169345024, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.15963483839131506, | |
| "grad_norm": 0.2917760908603668, | |
| "learning_rate": 3.355666766307084e-06, | |
| "loss": 1.4254, | |
| "num_input_tokens_seen": 169607168, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.15988156920799407, | |
| "grad_norm": 0.2395298182964325, | |
| "learning_rate": 3.339194340581485e-06, | |
| "loss": 1.613, | |
| "num_input_tokens_seen": 169869312, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.16012830002467307, | |
| "grad_norm": 0.4135853946208954, | |
| "learning_rate": 3.322742151248726e-06, | |
| "loss": 1.7439, | |
| "num_input_tokens_seen": 170131456, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.16037503084135207, | |
| "grad_norm": 0.2076270878314972, | |
| "learning_rate": 3.3063103987735433e-06, | |
| "loss": 1.6445, | |
| "num_input_tokens_seen": 170393600, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.16062176165803108, | |
| "grad_norm": 0.3565100133419037, | |
| "learning_rate": 3.289899283371657e-06, | |
| "loss": 1.8746, | |
| "num_input_tokens_seen": 170655744, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.16086849247471008, | |
| "grad_norm": 0.15975721180438995, | |
| "learning_rate": 3.273509005007327e-06, | |
| "loss": 1.5286, | |
| "num_input_tokens_seen": 170917888, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.16111522329138908, | |
| "grad_norm": 0.378402441740036, | |
| "learning_rate": 3.2571397633909252e-06, | |
| "loss": 2.028, | |
| "num_input_tokens_seen": 171180032, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.16136195410806808, | |
| "grad_norm": 0.23541276156902313, | |
| "learning_rate": 3.2407917579764914e-06, | |
| "loss": 1.5504, | |
| "num_input_tokens_seen": 171442176, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.16160868492474711, | |
| "grad_norm": 0.20868459343910217, | |
| "learning_rate": 3.224465187959316e-06, | |
| "loss": 2.0618, | |
| "num_input_tokens_seen": 171704320, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.16185541574142612, | |
| "grad_norm": 0.258038192987442, | |
| "learning_rate": 3.2081602522734987e-06, | |
| "loss": 1.7872, | |
| "num_input_tokens_seen": 171966464, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.16210214655810512, | |
| "grad_norm": 0.4574372470378876, | |
| "learning_rate": 3.1918771495895395e-06, | |
| "loss": 1.6086, | |
| "num_input_tokens_seen": 172228608, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.16234887737478412, | |
| "grad_norm": 0.4050358533859253, | |
| "learning_rate": 3.1756160783119015e-06, | |
| "loss": 1.4888, | |
| "num_input_tokens_seen": 172490752, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.16259560819146313, | |
| "grad_norm": 0.26240259408950806, | |
| "learning_rate": 3.1593772365766107e-06, | |
| "loss": 1.7043, | |
| "num_input_tokens_seen": 172752896, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.16284233900814213, | |
| "grad_norm": 0.20817944407463074, | |
| "learning_rate": 3.1431608222488276e-06, | |
| "loss": 1.4598, | |
| "num_input_tokens_seen": 173015040, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.16308906982482113, | |
| "grad_norm": 0.44060733914375305, | |
| "learning_rate": 3.12696703292044e-06, | |
| "loss": 1.898, | |
| "num_input_tokens_seen": 173277184, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.16333580064150013, | |
| "grad_norm": 0.28915196657180786, | |
| "learning_rate": 3.110796065907665e-06, | |
| "loss": 1.2809, | |
| "num_input_tokens_seen": 173539328, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.16358253145817914, | |
| "grad_norm": 0.28369492292404175, | |
| "learning_rate": 3.09464811824863e-06, | |
| "loss": 1.8475, | |
| "num_input_tokens_seen": 173801472, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.16382926227485814, | |
| "grad_norm": 0.21826131641864777, | |
| "learning_rate": 3.078523386700982e-06, | |
| "loss": 1.7563, | |
| "num_input_tokens_seen": 174063616, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.16407599309153714, | |
| "grad_norm": 0.3093124330043793, | |
| "learning_rate": 3.0624220677394854e-06, | |
| "loss": 1.7989, | |
| "num_input_tokens_seen": 174325760, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.16432272390821615, | |
| "grad_norm": 0.23655392229557037, | |
| "learning_rate": 3.0463443575536324e-06, | |
| "loss": 1.1725, | |
| "num_input_tokens_seen": 174587904, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.16456945472489515, | |
| "grad_norm": 0.30597802996635437, | |
| "learning_rate": 3.030290452045245e-06, | |
| "loss": 1.5523, | |
| "num_input_tokens_seen": 174850048, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.16481618554157415, | |
| "grad_norm": 0.32336390018463135, | |
| "learning_rate": 3.0142605468260976e-06, | |
| "loss": 1.8207, | |
| "num_input_tokens_seen": 175112192, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.16506291635825315, | |
| "grad_norm": 0.33342787623405457, | |
| "learning_rate": 2.9982548372155264e-06, | |
| "loss": 1.4246, | |
| "num_input_tokens_seen": 175374336, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.16530964717493216, | |
| "grad_norm": 0.2869754433631897, | |
| "learning_rate": 2.98227351823805e-06, | |
| "loss": 1.287, | |
| "num_input_tokens_seen": 175636480, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.16555637799161116, | |
| "grad_norm": 0.29800844192504883, | |
| "learning_rate": 2.966316784621e-06, | |
| "loss": 1.8511, | |
| "num_input_tokens_seen": 175898624, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.16580310880829016, | |
| "grad_norm": 0.4779532551765442, | |
| "learning_rate": 2.9503848307921363e-06, | |
| "loss": 1.4982, | |
| "num_input_tokens_seen": 176160768, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.16604983962496916, | |
| "grad_norm": 0.1853656768798828, | |
| "learning_rate": 2.934477850877292e-06, | |
| "loss": 1.5068, | |
| "num_input_tokens_seen": 176422912, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.16629657044164817, | |
| "grad_norm": 0.24669089913368225, | |
| "learning_rate": 2.918596038697995e-06, | |
| "loss": 1.5875, | |
| "num_input_tokens_seen": 176685056, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.16654330125832717, | |
| "grad_norm": 0.32669490575790405, | |
| "learning_rate": 2.9027395877691143e-06, | |
| "loss": 1.1128, | |
| "num_input_tokens_seen": 176947200, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.16679003207500617, | |
| "grad_norm": 0.22396613657474518, | |
| "learning_rate": 2.886908691296504e-06, | |
| "loss": 1.3264, | |
| "num_input_tokens_seen": 177209344, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.16703676289168518, | |
| "grad_norm": 0.22605319321155548, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 1.9182, | |
| "num_input_tokens_seen": 177471488, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.16728349370836418, | |
| "grad_norm": 0.3146352171897888, | |
| "learning_rate": 2.8553243329842715e-06, | |
| "loss": 1.5042, | |
| "num_input_tokens_seen": 177733632, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.16753022452504318, | |
| "grad_norm": 0.32827454805374146, | |
| "learning_rate": 2.839571255990088e-06, | |
| "loss": 1.6748, | |
| "num_input_tokens_seen": 177995776, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.16777695534172218, | |
| "grad_norm": 0.19679811596870422, | |
| "learning_rate": 2.8238445031383634e-06, | |
| "loss": 1.485, | |
| "num_input_tokens_seen": 178257920, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.1680236861584012, | |
| "grad_norm": 0.2624945044517517, | |
| "learning_rate": 2.8081442660546126e-06, | |
| "loss": 1.6265, | |
| "num_input_tokens_seen": 178520064, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.1682704169750802, | |
| "grad_norm": 0.21925391256809235, | |
| "learning_rate": 2.7924707360412743e-06, | |
| "loss": 1.7237, | |
| "num_input_tokens_seen": 178782208, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.1685171477917592, | |
| "grad_norm": 0.5328143239021301, | |
| "learning_rate": 2.776824104075364e-06, | |
| "loss": 1.8024, | |
| "num_input_tokens_seen": 179044352, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.1687638786084382, | |
| "grad_norm": 0.383619099855423, | |
| "learning_rate": 2.761204560806152e-06, | |
| "loss": 1.5762, | |
| "num_input_tokens_seen": 179306496, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.1690106094251172, | |
| "grad_norm": 0.36523357033729553, | |
| "learning_rate": 2.7456122965528475e-06, | |
| "loss": 1.916, | |
| "num_input_tokens_seen": 179568640, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.1692573402417962, | |
| "grad_norm": 0.37342143058776855, | |
| "learning_rate": 2.7300475013022666e-06, | |
| "loss": 1.0616, | |
| "num_input_tokens_seen": 179830784, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.1695040710584752, | |
| "grad_norm": 0.3579748570919037, | |
| "learning_rate": 2.714510364706531e-06, | |
| "loss": 2.0594, | |
| "num_input_tokens_seen": 180092928, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.1697508018751542, | |
| "grad_norm": 0.3356163203716278, | |
| "learning_rate": 2.699001076080742e-06, | |
| "loss": 1.7452, | |
| "num_input_tokens_seen": 180355072, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.1699975326918332, | |
| "grad_norm": 0.26012998819351196, | |
| "learning_rate": 2.683519824400693e-06, | |
| "loss": 1.6249, | |
| "num_input_tokens_seen": 180617216, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.1702442635085122, | |
| "grad_norm": 0.45150065422058105, | |
| "learning_rate": 2.6680667983005446e-06, | |
| "loss": 1.4417, | |
| "num_input_tokens_seen": 180879360, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.17049099432519121, | |
| "grad_norm": 0.30424007773399353, | |
| "learning_rate": 2.6526421860705474e-06, | |
| "loss": 1.407, | |
| "num_input_tokens_seen": 181141504, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 0.17073772514187022, | |
| "grad_norm": 0.4288609027862549, | |
| "learning_rate": 2.637246175654731e-06, | |
| "loss": 1.565, | |
| "num_input_tokens_seen": 181403648, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.17098445595854922, | |
| "grad_norm": 0.2482622265815735, | |
| "learning_rate": 2.6218789546486235e-06, | |
| "loss": 1.8121, | |
| "num_input_tokens_seen": 181665792, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.17123118677522822, | |
| "grad_norm": 0.22211559116840363, | |
| "learning_rate": 2.6065407102969664e-06, | |
| "loss": 1.7575, | |
| "num_input_tokens_seen": 181927936, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.17147791759190723, | |
| "grad_norm": 0.1990126669406891, | |
| "learning_rate": 2.5912316294914232e-06, | |
| "loss": 1.7779, | |
| "num_input_tokens_seen": 182190080, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.17172464840858623, | |
| "grad_norm": 0.3231181800365448, | |
| "learning_rate": 2.5759518987683154e-06, | |
| "loss": 1.292, | |
| "num_input_tokens_seen": 182452224, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.17197137922526523, | |
| "grad_norm": 0.2569955587387085, | |
| "learning_rate": 2.560701704306336e-06, | |
| "loss": 1.6064, | |
| "num_input_tokens_seen": 182714368, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 0.17221811004194423, | |
| "grad_norm": 0.27727434039115906, | |
| "learning_rate": 2.545481231924296e-06, | |
| "loss": 1.7567, | |
| "num_input_tokens_seen": 182976512, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.17246484085862324, | |
| "grad_norm": 0.4798392057418823, | |
| "learning_rate": 2.5302906670788463e-06, | |
| "loss": 1.6045, | |
| "num_input_tokens_seen": 183238656, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.17271157167530224, | |
| "grad_norm": 0.21941442787647247, | |
| "learning_rate": 2.5151301948622235e-06, | |
| "loss": 1.5115, | |
| "num_input_tokens_seen": 183500800, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.17295830249198124, | |
| "grad_norm": 0.26305386424064636, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 1.2139, | |
| "num_input_tokens_seen": 183762944, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 0.17320503330866024, | |
| "grad_norm": 0.2462892383337021, | |
| "learning_rate": 2.484900266848825e-06, | |
| "loss": 1.5875, | |
| "num_input_tokens_seen": 184025088, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.17345176412533925, | |
| "grad_norm": 0.21067021787166595, | |
| "learning_rate": 2.469831179394182e-06, | |
| "loss": 1.3405, | |
| "num_input_tokens_seen": 184287232, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 0.17369849494201825, | |
| "grad_norm": 0.23109757900238037, | |
| "learning_rate": 2.4547929212481436e-06, | |
| "loss": 1.606, | |
| "num_input_tokens_seen": 184549376, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.17394522575869725, | |
| "grad_norm": 0.4015589654445648, | |
| "learning_rate": 2.4397856756471435e-06, | |
| "loss": 1.8624, | |
| "num_input_tokens_seen": 184811520, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.17419195657537626, | |
| "grad_norm": 0.3183045983314514, | |
| "learning_rate": 2.424809625449729e-06, | |
| "loss": 1.5761, | |
| "num_input_tokens_seen": 185073664, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.17443868739205526, | |
| "grad_norm": 0.3008684515953064, | |
| "learning_rate": 2.40986495313435e-06, | |
| "loss": 1.4587, | |
| "num_input_tokens_seen": 185335808, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.17468541820873426, | |
| "grad_norm": 0.24359382688999176, | |
| "learning_rate": 2.39495184079712e-06, | |
| "loss": 1.5966, | |
| "num_input_tokens_seen": 185597952, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.17493214902541326, | |
| "grad_norm": 0.3360385596752167, | |
| "learning_rate": 2.380070470149605e-06, | |
| "loss": 1.53, | |
| "num_input_tokens_seen": 185860096, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 0.17517887984209227, | |
| "grad_norm": 0.37896421551704407, | |
| "learning_rate": 2.3652210225166122e-06, | |
| "loss": 1.4273, | |
| "num_input_tokens_seen": 186122240, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.17542561065877127, | |
| "grad_norm": 0.22193817794322968, | |
| "learning_rate": 2.3504036788339763e-06, | |
| "loss": 1.4629, | |
| "num_input_tokens_seen": 186384384, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 0.17567234147545027, | |
| "grad_norm": 0.23270967602729797, | |
| "learning_rate": 2.3356186196463497e-06, | |
| "loss": 1.4425, | |
| "num_input_tokens_seen": 186646528, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.17591907229212927, | |
| "grad_norm": 0.2334495335817337, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 1.558, | |
| "num_input_tokens_seen": 186908672, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 0.17616580310880828, | |
| "grad_norm": 0.29328563809394836, | |
| "learning_rate": 2.3061460749656844e-06, | |
| "loss": 1.7001, | |
| "num_input_tokens_seen": 187170816, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.17641253392548728, | |
| "grad_norm": 0.3238964378833771, | |
| "learning_rate": 2.2914589485863015e-06, | |
| "loss": 1.7355, | |
| "num_input_tokens_seen": 187432960, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.17665926474216628, | |
| "grad_norm": 0.5925378799438477, | |
| "learning_rate": 2.2768048249248648e-06, | |
| "loss": 2.0788, | |
| "num_input_tokens_seen": 187695104, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.17690599555884529, | |
| "grad_norm": 0.24551017582416534, | |
| "learning_rate": 2.2621838825372496e-06, | |
| "loss": 1.6617, | |
| "num_input_tokens_seen": 187957248, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 0.17715272637552432, | |
| "grad_norm": 0.19846408069133759, | |
| "learning_rate": 2.2475962995750224e-06, | |
| "loss": 1.5413, | |
| "num_input_tokens_seen": 188219392, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.17739945719220332, | |
| "grad_norm": 0.2510528266429901, | |
| "learning_rate": 2.23304225378328e-06, | |
| "loss": 1.7186, | |
| "num_input_tokens_seen": 188481536, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 0.17764618800888232, | |
| "grad_norm": 0.2695014476776123, | |
| "learning_rate": 2.218521922498476e-06, | |
| "loss": 1.3308, | |
| "num_input_tokens_seen": 188743680, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.17789291882556132, | |
| "grad_norm": 0.3821446895599365, | |
| "learning_rate": 2.204035482646267e-06, | |
| "loss": 1.6929, | |
| "num_input_tokens_seen": 189005824, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.17813964964224033, | |
| "grad_norm": 0.3116302788257599, | |
| "learning_rate": 2.1895831107393485e-06, | |
| "loss": 1.5853, | |
| "num_input_tokens_seen": 189267968, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.17838638045891933, | |
| "grad_norm": 0.9760715961456299, | |
| "learning_rate": 2.175164982875311e-06, | |
| "loss": 1.4186, | |
| "num_input_tokens_seen": 189530112, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 0.17863311127559833, | |
| "grad_norm": 0.2930695414543152, | |
| "learning_rate": 2.1607812747344955e-06, | |
| "loss": 1.9299, | |
| "num_input_tokens_seen": 189792256, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.17887984209227734, | |
| "grad_norm": 0.27560484409332275, | |
| "learning_rate": 2.146432161577842e-06, | |
| "loss": 1.869, | |
| "num_input_tokens_seen": 190054400, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.17912657290895634, | |
| "grad_norm": 0.4233398735523224, | |
| "learning_rate": 2.132117818244771e-06, | |
| "loss": 1.8978, | |
| "num_input_tokens_seen": 190316544, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.17937330372563534, | |
| "grad_norm": 0.21294540166854858, | |
| "learning_rate": 2.1178384191510344e-06, | |
| "loss": 1.9182, | |
| "num_input_tokens_seen": 190578688, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 0.17962003454231434, | |
| "grad_norm": 0.3538358211517334, | |
| "learning_rate": 2.103594138286607e-06, | |
| "loss": 1.9857, | |
| "num_input_tokens_seen": 190840832, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.17986676535899335, | |
| "grad_norm": 0.34079834818840027, | |
| "learning_rate": 2.0893851492135536e-06, | |
| "loss": 1.6827, | |
| "num_input_tokens_seen": 191102976, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 0.18011349617567235, | |
| "grad_norm": 0.28942787647247314, | |
| "learning_rate": 2.075211625063923e-06, | |
| "loss": 1.5478, | |
| "num_input_tokens_seen": 191365120, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.18036022699235135, | |
| "grad_norm": 0.33003339171409607, | |
| "learning_rate": 2.061073738537635e-06, | |
| "loss": 1.6105, | |
| "num_input_tokens_seen": 191627264, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.18060695780903036, | |
| "grad_norm": 0.20433729887008667, | |
| "learning_rate": 2.046971661900373e-06, | |
| "loss": 1.8698, | |
| "num_input_tokens_seen": 191889408, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.18085368862570936, | |
| "grad_norm": 0.1890942007303238, | |
| "learning_rate": 2.0329055669814936e-06, | |
| "loss": 1.4596, | |
| "num_input_tokens_seen": 192151552, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 0.18110041944238836, | |
| "grad_norm": 0.34075161814689636, | |
| "learning_rate": 2.0188756251719204e-06, | |
| "loss": 1.5388, | |
| "num_input_tokens_seen": 192413696, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.18134715025906736, | |
| "grad_norm": 0.465636283159256, | |
| "learning_rate": 2.0048820074220716e-06, | |
| "loss": 1.6769, | |
| "num_input_tokens_seen": 192675840, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.18159388107574637, | |
| "grad_norm": 0.3639475405216217, | |
| "learning_rate": 1.990924884239758e-06, | |
| "loss": 1.4542, | |
| "num_input_tokens_seen": 192937984, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.18184061189242537, | |
| "grad_norm": 0.22438043355941772, | |
| "learning_rate": 1.977004425688126e-06, | |
| "loss": 1.7826, | |
| "num_input_tokens_seen": 193200128, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 0.18208734270910437, | |
| "grad_norm": 0.23819977045059204, | |
| "learning_rate": 1.9631208013835677e-06, | |
| "loss": 1.5294, | |
| "num_input_tokens_seen": 193462272, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.18233407352578337, | |
| "grad_norm": 0.16036422550678253, | |
| "learning_rate": 1.9492741804936623e-06, | |
| "loss": 1.3988, | |
| "num_input_tokens_seen": 193724416, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 0.18258080434246238, | |
| "grad_norm": 0.19281713664531708, | |
| "learning_rate": 1.9354647317351187e-06, | |
| "loss": 2.13, | |
| "num_input_tokens_seen": 193986560, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.18282753515914138, | |
| "grad_norm": 0.441250741481781, | |
| "learning_rate": 1.9216926233717087e-06, | |
| "loss": 2.1448, | |
| "num_input_tokens_seen": 194248704, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 0.18307426597582038, | |
| "grad_norm": 0.299956351518631, | |
| "learning_rate": 1.90795802321223e-06, | |
| "loss": 1.7517, | |
| "num_input_tokens_seen": 194510848, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.18332099679249939, | |
| "grad_norm": 0.2056249976158142, | |
| "learning_rate": 1.8942610986084487e-06, | |
| "loss": 1.2246, | |
| "num_input_tokens_seen": 194772992, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 0.1835677276091784, | |
| "grad_norm": 0.21236024796962738, | |
| "learning_rate": 1.8806020164530702e-06, | |
| "loss": 1.4881, | |
| "num_input_tokens_seen": 195035136, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.1838144584258574, | |
| "grad_norm": 0.2904950976371765, | |
| "learning_rate": 1.8669809431776991e-06, | |
| "loss": 1.6151, | |
| "num_input_tokens_seen": 195297280, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.1840611892425364, | |
| "grad_norm": 0.21807019412517548, | |
| "learning_rate": 1.8533980447508138e-06, | |
| "loss": 1.6726, | |
| "num_input_tokens_seen": 195559424, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.1843079200592154, | |
| "grad_norm": 0.23090478777885437, | |
| "learning_rate": 1.8398534866757455e-06, | |
| "loss": 1.7856, | |
| "num_input_tokens_seen": 195821568, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 0.1845546508758944, | |
| "grad_norm": 0.28993329405784607, | |
| "learning_rate": 1.8263474339886628e-06, | |
| "loss": 1.8773, | |
| "num_input_tokens_seen": 196083712, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.1848013816925734, | |
| "grad_norm": 0.3971545696258545, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 1.7139, | |
| "num_input_tokens_seen": 196345856, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.1850481125092524, | |
| "grad_norm": 0.19998975098133087, | |
| "learning_rate": 1.799451502575222e-06, | |
| "loss": 1.6208, | |
| "num_input_tokens_seen": 196608000, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.1852948433259314, | |
| "grad_norm": 0.293244868516922, | |
| "learning_rate": 1.7860619515673034e-06, | |
| "loss": 1.9268, | |
| "num_input_tokens_seen": 196870144, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 0.1855415741426104, | |
| "grad_norm": 0.3308587372303009, | |
| "learning_rate": 1.7727115613802465e-06, | |
| "loss": 1.9633, | |
| "num_input_tokens_seen": 197132288, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.1857883049592894, | |
| "grad_norm": 0.2106206715106964, | |
| "learning_rate": 1.7594004946843458e-06, | |
| "loss": 1.8514, | |
| "num_input_tokens_seen": 197394432, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 0.18603503577596842, | |
| "grad_norm": 0.3629756271839142, | |
| "learning_rate": 1.746128913670746e-06, | |
| "loss": 2.0288, | |
| "num_input_tokens_seen": 197656576, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.18628176659264742, | |
| "grad_norm": 0.2693224549293518, | |
| "learning_rate": 1.7328969800494727e-06, | |
| "loss": 1.7449, | |
| "num_input_tokens_seen": 197918720, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.18652849740932642, | |
| "grad_norm": 0.2536444365978241, | |
| "learning_rate": 1.7197048550474643e-06, | |
| "loss": 1.6386, | |
| "num_input_tokens_seen": 198180864, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.18677522822600542, | |
| "grad_norm": 0.19451206922531128, | |
| "learning_rate": 1.7065526994065973e-06, | |
| "loss": 1.6479, | |
| "num_input_tokens_seen": 198443008, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 0.18702195904268443, | |
| "grad_norm": 0.2774448096752167, | |
| "learning_rate": 1.6934406733817417e-06, | |
| "loss": 1.3525, | |
| "num_input_tokens_seen": 198705152, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.18726868985936343, | |
| "grad_norm": 0.4685295820236206, | |
| "learning_rate": 1.680368936738792e-06, | |
| "loss": 1.9418, | |
| "num_input_tokens_seen": 198967296, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 0.18751542067604243, | |
| "grad_norm": 0.2218584567308426, | |
| "learning_rate": 1.6673376487527382e-06, | |
| "loss": 1.376, | |
| "num_input_tokens_seen": 199229440, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.18776215149272144, | |
| "grad_norm": 0.356768935918808, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 1.865, | |
| "num_input_tokens_seen": 199491584, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 0.18800888230940044, | |
| "grad_norm": 0.2825476825237274, | |
| "learning_rate": 1.6413970533850498e-06, | |
| "loss": 1.6937, | |
| "num_input_tokens_seen": 199753728, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.18825561312607944, | |
| "grad_norm": 0.17668165266513824, | |
| "learning_rate": 1.6284880620813847e-06, | |
| "loss": 1.7994, | |
| "num_input_tokens_seen": 200015872, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.18850234394275844, | |
| "grad_norm": 0.18310214579105377, | |
| "learning_rate": 1.6156201515866971e-06, | |
| "loss": 1.5417, | |
| "num_input_tokens_seen": 200278016, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.18874907475943745, | |
| "grad_norm": 0.3639572262763977, | |
| "learning_rate": 1.6027934786924187e-06, | |
| "loss": 2.0172, | |
| "num_input_tokens_seen": 200540160, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.18899580557611645, | |
| "grad_norm": 0.22743955254554749, | |
| "learning_rate": 1.5900081996875083e-06, | |
| "loss": 1.453, | |
| "num_input_tokens_seen": 200802304, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.18924253639279545, | |
| "grad_norm": 0.2889941930770874, | |
| "learning_rate": 1.5772644703565564e-06, | |
| "loss": 1.5592, | |
| "num_input_tokens_seen": 201064448, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 0.18948926720947445, | |
| "grad_norm": 0.2820563018321991, | |
| "learning_rate": 1.5645624459778858e-06, | |
| "loss": 1.8922, | |
| "num_input_tokens_seen": 201326592, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.18973599802615346, | |
| "grad_norm": 0.1855258345603943, | |
| "learning_rate": 1.551902281321651e-06, | |
| "loss": 1.6053, | |
| "num_input_tokens_seen": 201588736, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 0.18998272884283246, | |
| "grad_norm": 0.18336619436740875, | |
| "learning_rate": 1.5392841306479667e-06, | |
| "loss": 1.5118, | |
| "num_input_tokens_seen": 201850880, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.19022945965951146, | |
| "grad_norm": 0.34779712557792664, | |
| "learning_rate": 1.5267081477050132e-06, | |
| "loss": 1.5625, | |
| "num_input_tokens_seen": 202113024, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 0.30039459466934204, | |
| "learning_rate": 1.514174485727178e-06, | |
| "loss": 1.5418, | |
| "num_input_tokens_seen": 202375168, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.19072292129286947, | |
| "grad_norm": 0.2960957884788513, | |
| "learning_rate": 1.5016832974331725e-06, | |
| "loss": 1.3917, | |
| "num_input_tokens_seen": 202637312, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 0.19096965210954847, | |
| "grad_norm": 0.2889593541622162, | |
| "learning_rate": 1.489234735024188e-06, | |
| "loss": 1.5424, | |
| "num_input_tokens_seen": 202899456, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.19121638292622747, | |
| "grad_norm": 0.2686896324157715, | |
| "learning_rate": 1.4768289501820265e-06, | |
| "loss": 1.6948, | |
| "num_input_tokens_seen": 203161600, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.19146311374290648, | |
| "grad_norm": 0.35694169998168945, | |
| "learning_rate": 1.4644660940672628e-06, | |
| "loss": 1.5278, | |
| "num_input_tokens_seen": 203423744, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.19170984455958548, | |
| "grad_norm": 0.2902432382106781, | |
| "learning_rate": 1.4521463173173966e-06, | |
| "loss": 1.643, | |
| "num_input_tokens_seen": 203685888, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.19195657537626448, | |
| "grad_norm": 0.45950496196746826, | |
| "learning_rate": 1.4398697700450181e-06, | |
| "loss": 1.2811, | |
| "num_input_tokens_seen": 203948032, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.19220330619294348, | |
| "grad_norm": 0.28215292096138, | |
| "learning_rate": 1.4276366018359845e-06, | |
| "loss": 1.968, | |
| "num_input_tokens_seen": 204210176, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 0.19245003700962252, | |
| "grad_norm": 0.26845288276672363, | |
| "learning_rate": 1.4154469617475864e-06, | |
| "loss": 1.9697, | |
| "num_input_tokens_seen": 204472320, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.19269676782630152, | |
| "grad_norm": 0.2510419189929962, | |
| "learning_rate": 1.4033009983067454e-06, | |
| "loss": 1.7787, | |
| "num_input_tokens_seen": 204734464, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 0.19294349864298052, | |
| "grad_norm": 0.39068034291267395, | |
| "learning_rate": 1.3911988595081894e-06, | |
| "loss": 1.8188, | |
| "num_input_tokens_seen": 204996608, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.19319022945965952, | |
| "grad_norm": 0.32934966683387756, | |
| "learning_rate": 1.3791406928126638e-06, | |
| "loss": 1.4715, | |
| "num_input_tokens_seen": 205258752, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 0.19343696027633853, | |
| "grad_norm": 0.4297356605529785, | |
| "learning_rate": 1.3671266451451209e-06, | |
| "loss": 2.0179, | |
| "num_input_tokens_seen": 205520896, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.19368369109301753, | |
| "grad_norm": 0.20103523135185242, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 1.5002, | |
| "num_input_tokens_seen": 205783040, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.19393042190969653, | |
| "grad_norm": 0.5125095248222351, | |
| "learning_rate": 1.3432314919041478e-06, | |
| "loss": 1.8507, | |
| "num_input_tokens_seen": 206045184, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.19417715272637553, | |
| "grad_norm": 0.3016910254955292, | |
| "learning_rate": 1.3313506774856177e-06, | |
| "loss": 1.3569, | |
| "num_input_tokens_seen": 206307328, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 0.19442388354305454, | |
| "grad_norm": 0.25727003812789917, | |
| "learning_rate": 1.3195145644013286e-06, | |
| "loss": 1.6336, | |
| "num_input_tokens_seen": 206569472, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.19467061435973354, | |
| "grad_norm": 0.25804463028907776, | |
| "learning_rate": 1.3077232968705805e-06, | |
| "loss": 1.5826, | |
| "num_input_tokens_seen": 206831616, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 0.19491734517641254, | |
| "grad_norm": 0.2707713842391968, | |
| "learning_rate": 1.2959770185662502e-06, | |
| "loss": 1.5577, | |
| "num_input_tokens_seen": 207093760, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.19516407599309155, | |
| "grad_norm": 0.22968651354312897, | |
| "learning_rate": 1.2842758726130283e-06, | |
| "loss": 1.5968, | |
| "num_input_tokens_seen": 207355904, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.19541080680977055, | |
| "grad_norm": 0.14831578731536865, | |
| "learning_rate": 1.2726200015856893e-06, | |
| "loss": 1.0922, | |
| "num_input_tokens_seen": 207618048, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.19565753762644955, | |
| "grad_norm": 0.405351847410202, | |
| "learning_rate": 1.2610095475073415e-06, | |
| "loss": 1.9769, | |
| "num_input_tokens_seen": 207880192, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 0.19590426844312855, | |
| "grad_norm": 0.37764203548431396, | |
| "learning_rate": 1.2494446518477022e-06, | |
| "loss": 1.6718, | |
| "num_input_tokens_seen": 208142336, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.19615099925980756, | |
| "grad_norm": 0.21938475966453552, | |
| "learning_rate": 1.2379254555213788e-06, | |
| "loss": 1.5984, | |
| "num_input_tokens_seen": 208404480, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.19639773007648656, | |
| "grad_norm": 0.260897159576416, | |
| "learning_rate": 1.22645209888614e-06, | |
| "loss": 1.3849, | |
| "num_input_tokens_seen": 208666624, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.19664446089316556, | |
| "grad_norm": 0.3183205723762512, | |
| "learning_rate": 1.2150247217412186e-06, | |
| "loss": 1.6641, | |
| "num_input_tokens_seen": 208928768, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 0.19689119170984457, | |
| "grad_norm": 0.25011545419692993, | |
| "learning_rate": 1.203643463325596e-06, | |
| "loss": 1.485, | |
| "num_input_tokens_seen": 209190912, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.19713792252652357, | |
| "grad_norm": 0.29727256298065186, | |
| "learning_rate": 1.1923084623163172e-06, | |
| "loss": 1.3779, | |
| "num_input_tokens_seen": 209453056, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 0.19738465334320257, | |
| "grad_norm": 0.3542685806751251, | |
| "learning_rate": 1.1810198568267906e-06, | |
| "loss": 1.2787, | |
| "num_input_tokens_seen": 209715200, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.19763138415988157, | |
| "grad_norm": 0.3065374791622162, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 1.3865, | |
| "num_input_tokens_seen": 209977344, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 0.19787811497656058, | |
| "grad_norm": 0.24071305990219116, | |
| "learning_rate": 1.1585823820323845e-06, | |
| "loss": 1.7097, | |
| "num_input_tokens_seen": 210239488, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 0.19812484579323958, | |
| "grad_norm": 0.30029404163360596, | |
| "learning_rate": 1.1474337861210543e-06, | |
| "loss": 1.6166, | |
| "num_input_tokens_seen": 210501632, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 0.19837157660991858, | |
| "grad_norm": 0.3482155501842499, | |
| "learning_rate": 1.136332132513245e-06, | |
| "loss": 1.4857, | |
| "num_input_tokens_seen": 210763776, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.19861830742659758, | |
| "grad_norm": 0.33486634492874146, | |
| "learning_rate": 1.1252775564791023e-06, | |
| "loss": 1.4237, | |
| "num_input_tokens_seen": 211025920, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.1988650382432766, | |
| "grad_norm": 0.3351602852344513, | |
| "learning_rate": 1.1142701927151456e-06, | |
| "loss": 1.8177, | |
| "num_input_tokens_seen": 211288064, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.1991117690599556, | |
| "grad_norm": 0.3947872221469879, | |
| "learning_rate": 1.1033101753426285e-06, | |
| "loss": 1.8403, | |
| "num_input_tokens_seen": 211550208, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 0.1993584998766346, | |
| "grad_norm": 0.35190752148628235, | |
| "learning_rate": 1.0923976379059059e-06, | |
| "loss": 1.6172, | |
| "num_input_tokens_seen": 211812352, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 0.1996052306933136, | |
| "grad_norm": 0.23227426409721375, | |
| "learning_rate": 1.0815327133708015e-06, | |
| "loss": 1.1447, | |
| "num_input_tokens_seen": 212074496, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 0.1998519615099926, | |
| "grad_norm": 0.30079352855682373, | |
| "learning_rate": 1.0707155341229902e-06, | |
| "loss": 1.9032, | |
| "num_input_tokens_seen": 212336640, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.2000986923266716, | |
| "grad_norm": 0.20834387838840485, | |
| "learning_rate": 1.0599462319663906e-06, | |
| "loss": 1.8074, | |
| "num_input_tokens_seen": 212598784, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 0.2003454231433506, | |
| "grad_norm": 0.43393853306770325, | |
| "learning_rate": 1.049224938121548e-06, | |
| "loss": 1.8503, | |
| "num_input_tokens_seen": 212860928, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.2005921539600296, | |
| "grad_norm": 0.31511902809143066, | |
| "learning_rate": 1.0385517832240472e-06, | |
| "loss": 1.512, | |
| "num_input_tokens_seen": 213123072, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 0.2008388847767086, | |
| "grad_norm": 0.17316994071006775, | |
| "learning_rate": 1.0279268973229089e-06, | |
| "loss": 1.5999, | |
| "num_input_tokens_seen": 213385216, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 0.2010856155933876, | |
| "grad_norm": 0.24697916209697723, | |
| "learning_rate": 1.0173504098790188e-06, | |
| "loss": 1.272, | |
| "num_input_tokens_seen": 213647360, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.20133234641006661, | |
| "grad_norm": 0.2564072906970978, | |
| "learning_rate": 1.006822449763537e-06, | |
| "loss": 2.1296, | |
| "num_input_tokens_seen": 213909504, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.20157907722674562, | |
| "grad_norm": 0.26823318004608154, | |
| "learning_rate": 9.963431452563331e-07, | |
| "loss": 1.9528, | |
| "num_input_tokens_seen": 214171648, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.20182580804342462, | |
| "grad_norm": 0.2205478847026825, | |
| "learning_rate": 9.859126240444284e-07, | |
| "loss": 1.4545, | |
| "num_input_tokens_seen": 214433792, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 0.20207253886010362, | |
| "grad_norm": 0.45528295636177063, | |
| "learning_rate": 9.7553101322043e-07, | |
| "loss": 1.9818, | |
| "num_input_tokens_seen": 214695936, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 0.20231926967678263, | |
| "grad_norm": 0.2815514802932739, | |
| "learning_rate": 9.651984392809916e-07, | |
| "loss": 1.6919, | |
| "num_input_tokens_seen": 214958080, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.20256600049346163, | |
| "grad_norm": 0.31144043803215027, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 1.7837, | |
| "num_input_tokens_seen": 215220224, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 0.20281273131014063, | |
| "grad_norm": 0.3299436569213867, | |
| "learning_rate": 9.446809050533679e-07, | |
| "loss": 2.0261, | |
| "num_input_tokens_seen": 215482368, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.20305946212681963, | |
| "grad_norm": 0.31391656398773193, | |
| "learning_rate": 9.344961947648624e-07, | |
| "loss": 1.7735, | |
| "num_input_tokens_seen": 215744512, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 0.20330619294349864, | |
| "grad_norm": 0.37549975514411926, | |
| "learning_rate": 9.243610213572285e-07, | |
| "loss": 1.9061, | |
| "num_input_tokens_seen": 216006656, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 0.20355292376017764, | |
| "grad_norm": 0.3471549451351166, | |
| "learning_rate": 9.142755083243577e-07, | |
| "loss": 1.0835, | |
| "num_input_tokens_seen": 216268800, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.20379965457685664, | |
| "grad_norm": 0.21472056210041046, | |
| "learning_rate": 9.042397785550405e-07, | |
| "loss": 1.487, | |
| "num_input_tokens_seen": 216530944, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.20404638539353565, | |
| "grad_norm": 0.3580244183540344, | |
| "learning_rate": 8.942539543314799e-07, | |
| "loss": 1.5566, | |
| "num_input_tokens_seen": 216793088, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 0.20429311621021465, | |
| "grad_norm": 0.771636962890625, | |
| "learning_rate": 8.843181573277904e-07, | |
| "loss": 1.4313, | |
| "num_input_tokens_seen": 217055232, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.20453984702689365, | |
| "grad_norm": 0.2665698230266571, | |
| "learning_rate": 8.744325086085248e-07, | |
| "loss": 1.5071, | |
| "num_input_tokens_seen": 217317376, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 0.20478657784357265, | |
| "grad_norm": 0.5237531065940857, | |
| "learning_rate": 8.645971286271903e-07, | |
| "loss": 1.7021, | |
| "num_input_tokens_seen": 217579520, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.20503330866025166, | |
| "grad_norm": 0.3260135054588318, | |
| "learning_rate": 8.54812137224792e-07, | |
| "loss": 1.5491, | |
| "num_input_tokens_seen": 217841664, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 0.20528003947693066, | |
| "grad_norm": 0.37850940227508545, | |
| "learning_rate": 8.450776536283594e-07, | |
| "loss": 1.9982, | |
| "num_input_tokens_seen": 218103808, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.20552677029360966, | |
| "grad_norm": 0.3043404221534729, | |
| "learning_rate": 8.353937964495029e-07, | |
| "loss": 1.6239, | |
| "num_input_tokens_seen": 218365952, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 0.20577350111028866, | |
| "grad_norm": 0.2891063988208771, | |
| "learning_rate": 8.25760683682968e-07, | |
| "loss": 1.4132, | |
| "num_input_tokens_seen": 218628096, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.20602023192696767, | |
| "grad_norm": 0.2345696985721588, | |
| "learning_rate": 8.161784327051919e-07, | |
| "loss": 1.6094, | |
| "num_input_tokens_seen": 218890240, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.20626696274364667, | |
| "grad_norm": 0.3723156750202179, | |
| "learning_rate": 8.066471602728804e-07, | |
| "loss": 1.6819, | |
| "num_input_tokens_seen": 219152384, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 0.20651369356032567, | |
| "grad_norm": 0.44934532046318054, | |
| "learning_rate": 7.971669825215789e-07, | |
| "loss": 1.6014, | |
| "num_input_tokens_seen": 219414528, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 0.20676042437700468, | |
| "grad_norm": 0.25686654448509216, | |
| "learning_rate": 7.877380149642628e-07, | |
| "loss": 1.8622, | |
| "num_input_tokens_seen": 219676672, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 0.20700715519368368, | |
| "grad_norm": 0.3707871735095978, | |
| "learning_rate": 7.783603724899258e-07, | |
| "loss": 1.5101, | |
| "num_input_tokens_seen": 219938816, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 0.20725388601036268, | |
| "grad_norm": 0.4154548943042755, | |
| "learning_rate": 7.690341693621805e-07, | |
| "loss": 1.7454, | |
| "num_input_tokens_seen": 220200960, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.20750061682704168, | |
| "grad_norm": 0.3507881462574005, | |
| "learning_rate": 7.597595192178702e-07, | |
| "loss": 1.5214, | |
| "num_input_tokens_seen": 220463104, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 0.20774734764372071, | |
| "grad_norm": 0.32315999269485474, | |
| "learning_rate": 7.505365350656813e-07, | |
| "loss": 1.8847, | |
| "num_input_tokens_seen": 220725248, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 0.20799407846039972, | |
| "grad_norm": 0.2104586958885193, | |
| "learning_rate": 7.413653292847617e-07, | |
| "loss": 1.3325, | |
| "num_input_tokens_seen": 220987392, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 0.20824080927707872, | |
| "grad_norm": 0.2483946830034256, | |
| "learning_rate": 7.322460136233622e-07, | |
| "loss": 1.4646, | |
| "num_input_tokens_seen": 221249536, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 0.20848754009375772, | |
| "grad_norm": 0.3510516285896301, | |
| "learning_rate": 7.23178699197467e-07, | |
| "loss": 1.8601, | |
| "num_input_tokens_seen": 221511680, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.20873427091043673, | |
| "grad_norm": 0.22424964606761932, | |
| "learning_rate": 7.141634964894389e-07, | |
| "loss": 1.422, | |
| "num_input_tokens_seen": 221773824, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.20898100172711573, | |
| "grad_norm": 0.36059847474098206, | |
| "learning_rate": 7.052005153466779e-07, | |
| "loss": 1.2802, | |
| "num_input_tokens_seen": 222035968, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 0.20922773254379473, | |
| "grad_norm": 0.29703643918037415, | |
| "learning_rate": 6.962898649802824e-07, | |
| "loss": 1.9207, | |
| "num_input_tokens_seen": 222298112, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 0.20947446336047373, | |
| "grad_norm": 0.3677685856819153, | |
| "learning_rate": 6.874316539637127e-07, | |
| "loss": 1.5452, | |
| "num_input_tokens_seen": 222560256, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 0.20972119417715274, | |
| "grad_norm": 0.6440513730049133, | |
| "learning_rate": 6.786259902314768e-07, | |
| "loss": 1.4732, | |
| "num_input_tokens_seen": 222822400, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.20996792499383174, | |
| "grad_norm": 0.2577255070209503, | |
| "learning_rate": 6.698729810778065e-07, | |
| "loss": 1.7592, | |
| "num_input_tokens_seen": 223084544, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 0.21021465581051074, | |
| "grad_norm": 0.287110835313797, | |
| "learning_rate": 6.611727331553585e-07, | |
| "loss": 2.0263, | |
| "num_input_tokens_seen": 223346688, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.21046138662718974, | |
| "grad_norm": 0.2498570680618286, | |
| "learning_rate": 6.52525352473905e-07, | |
| "loss": 1.7688, | |
| "num_input_tokens_seen": 223608832, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 0.21070811744386875, | |
| "grad_norm": 0.36089619994163513, | |
| "learning_rate": 6.439309443990532e-07, | |
| "loss": 2.0014, | |
| "num_input_tokens_seen": 223870976, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.21095484826054775, | |
| "grad_norm": 1.3907390832901, | |
| "learning_rate": 6.353896136509524e-07, | |
| "loss": 1.8, | |
| "num_input_tokens_seen": 224133120, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.21120157907722675, | |
| "grad_norm": 0.2767269015312195, | |
| "learning_rate": 6.269014643030214e-07, | |
| "loss": 1.4085, | |
| "num_input_tokens_seen": 224395264, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 0.21144830989390576, | |
| "grad_norm": 0.20977024734020233, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 1.8731, | |
| "num_input_tokens_seen": 224657408, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 0.21169504071058476, | |
| "grad_norm": 0.2735670804977417, | |
| "learning_rate": 6.100851228600974e-07, | |
| "loss": 1.7069, | |
| "num_input_tokens_seen": 224919552, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.21194177152726376, | |
| "grad_norm": 0.3599633574485779, | |
| "learning_rate": 6.017571356669183e-07, | |
| "loss": 1.6557, | |
| "num_input_tokens_seen": 225181696, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 0.21218850234394276, | |
| "grad_norm": 0.25999823212623596, | |
| "learning_rate": 5.934827396750392e-07, | |
| "loss": 1.2838, | |
| "num_input_tokens_seen": 225443840, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.21243523316062177, | |
| "grad_norm": 0.33764758706092834, | |
| "learning_rate": 5.852620357053651e-07, | |
| "loss": 1.955, | |
| "num_input_tokens_seen": 225705984, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 0.21268196397730077, | |
| "grad_norm": 0.15850548446178436, | |
| "learning_rate": 5.770951239245803e-07, | |
| "loss": 1.1359, | |
| "num_input_tokens_seen": 225968128, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 0.21292869479397977, | |
| "grad_norm": 0.3201885223388672, | |
| "learning_rate": 5.689821038439264e-07, | |
| "loss": 1.7928, | |
| "num_input_tokens_seen": 226230272, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 0.21317542561065878, | |
| "grad_norm": 0.25651001930236816, | |
| "learning_rate": 5.609230743179939e-07, | |
| "loss": 1.7624, | |
| "num_input_tokens_seen": 226492416, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.21342215642733778, | |
| "grad_norm": 0.2685423493385315, | |
| "learning_rate": 5.529181335435124e-07, | |
| "loss": 1.747, | |
| "num_input_tokens_seen": 226754560, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.21366888724401678, | |
| "grad_norm": 0.24144497513771057, | |
| "learning_rate": 5.449673790581611e-07, | |
| "loss": 1.2972, | |
| "num_input_tokens_seen": 227016704, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 0.21391561806069578, | |
| "grad_norm": 0.2833223342895508, | |
| "learning_rate": 5.370709077393721e-07, | |
| "loss": 1.5515, | |
| "num_input_tokens_seen": 227278848, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 0.2141623488773748, | |
| "grad_norm": 0.5597326159477234, | |
| "learning_rate": 5.292288158031595e-07, | |
| "loss": 1.2957, | |
| "num_input_tokens_seen": 227540992, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.2144090796940538, | |
| "grad_norm": 0.2911970913410187, | |
| "learning_rate": 5.214411988029355e-07, | |
| "loss": 1.5322, | |
| "num_input_tokens_seen": 227803136, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 0.2146558105107328, | |
| "grad_norm": 0.27730849385261536, | |
| "learning_rate": 5.137081516283582e-07, | |
| "loss": 2.0445, | |
| "num_input_tokens_seen": 228065280, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.2149025413274118, | |
| "grad_norm": 0.23569044470787048, | |
| "learning_rate": 5.06029768504166e-07, | |
| "loss": 1.4844, | |
| "num_input_tokens_seen": 228327424, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 0.2151492721440908, | |
| "grad_norm": 0.34393903613090515, | |
| "learning_rate": 4.984061429890324e-07, | |
| "loss": 1.7995, | |
| "num_input_tokens_seen": 228589568, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 0.2153960029607698, | |
| "grad_norm": 0.3047172725200653, | |
| "learning_rate": 4.908373679744316e-07, | |
| "loss": 1.9499, | |
| "num_input_tokens_seen": 228851712, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 0.2156427337774488, | |
| "grad_norm": 0.3547765612602234, | |
| "learning_rate": 4.833235356834959e-07, | |
| "loss": 1.2096, | |
| "num_input_tokens_seen": 229113856, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 0.2158894645941278, | |
| "grad_norm": 0.28206881880760193, | |
| "learning_rate": 4.758647376699033e-07, | |
| "loss": 1.8047, | |
| "num_input_tokens_seen": 229376000, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.2161361954108068, | |
| "grad_norm": 0.37405312061309814, | |
| "learning_rate": 4.6846106481675035e-07, | |
| "loss": 1.967, | |
| "num_input_tokens_seen": 229638144, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.2163829262274858, | |
| "grad_norm": 0.28268763422966003, | |
| "learning_rate": 4.6111260733545714e-07, | |
| "loss": 1.413, | |
| "num_input_tokens_seen": 229900288, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 0.21662965704416481, | |
| "grad_norm": 0.33675679564476013, | |
| "learning_rate": 4.538194547646574e-07, | |
| "loss": 1.8347, | |
| "num_input_tokens_seen": 230162432, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 0.21687638786084382, | |
| "grad_norm": 0.29510554671287537, | |
| "learning_rate": 4.4658169596911493e-07, | |
| "loss": 1.7789, | |
| "num_input_tokens_seen": 230424576, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 0.21712311867752282, | |
| "grad_norm": 0.22556479275226593, | |
| "learning_rate": 4.3939941913863525e-07, | |
| "loss": 1.4442, | |
| "num_input_tokens_seen": 230686720, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.21736984949420182, | |
| "grad_norm": 0.25110024213790894, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 1.8965, | |
| "num_input_tokens_seen": 230948864, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 0.21761658031088082, | |
| "grad_norm": 0.28704214096069336, | |
| "learning_rate": 4.2520166075087635e-07, | |
| "loss": 1.2111, | |
| "num_input_tokens_seen": 231211008, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.21786331112755983, | |
| "grad_norm": 0.3127775490283966, | |
| "learning_rate": 4.1818635218880186e-07, | |
| "loss": 1.5499, | |
| "num_input_tokens_seen": 231473152, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 0.21811004194423883, | |
| "grad_norm": 0.14734895527362823, | |
| "learning_rate": 4.112268715800943e-07, | |
| "loss": 1.2497, | |
| "num_input_tokens_seen": 231735296, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.21835677276091783, | |
| "grad_norm": 0.29640600085258484, | |
| "learning_rate": 4.043233037238281e-07, | |
| "loss": 1.7869, | |
| "num_input_tokens_seen": 231997440, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.21860350357759684, | |
| "grad_norm": 0.2300645112991333, | |
| "learning_rate": 3.9747573273779816e-07, | |
| "loss": 2.0367, | |
| "num_input_tokens_seen": 232259584, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 0.21885023439427584, | |
| "grad_norm": 0.22962304949760437, | |
| "learning_rate": 3.90684242057498e-07, | |
| "loss": 1.5592, | |
| "num_input_tokens_seen": 232521728, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 0.21909696521095484, | |
| "grad_norm": 0.2504030466079712, | |
| "learning_rate": 3.8394891443509554e-07, | |
| "loss": 1.6542, | |
| "num_input_tokens_seen": 232783872, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.21934369602763384, | |
| "grad_norm": 0.2758059799671173, | |
| "learning_rate": 3.772698319384349e-07, | |
| "loss": 1.8074, | |
| "num_input_tokens_seen": 233046016, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 0.21959042684431285, | |
| "grad_norm": 0.1838909238576889, | |
| "learning_rate": 3.7064707595002636e-07, | |
| "loss": 1.418, | |
| "num_input_tokens_seen": 233308160, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.21983715766099185, | |
| "grad_norm": 0.23375551402568817, | |
| "learning_rate": 3.6408072716606346e-07, | |
| "loss": 1.3544, | |
| "num_input_tokens_seen": 233570304, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 0.22008388847767085, | |
| "grad_norm": 0.26496320962905884, | |
| "learning_rate": 3.575708655954324e-07, | |
| "loss": 1.2265, | |
| "num_input_tokens_seen": 233832448, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 0.22033061929434986, | |
| "grad_norm": 0.19440144300460815, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 1.3137, | |
| "num_input_tokens_seen": 234094592, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 0.22057735011102886, | |
| "grad_norm": 0.33545535802841187, | |
| "learning_rate": 3.4472092068735917e-07, | |
| "loss": 1.8718, | |
| "num_input_tokens_seen": 234356736, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.22082408092770786, | |
| "grad_norm": 0.2817319631576538, | |
| "learning_rate": 3.3838099392243915e-07, | |
| "loss": 1.5016, | |
| "num_input_tokens_seen": 234618880, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.22107081174438686, | |
| "grad_norm": 0.2984430193901062, | |
| "learning_rate": 3.320978675139919e-07, | |
| "loss": 1.779, | |
| "num_input_tokens_seen": 234881024, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.22131754256106587, | |
| "grad_norm": 0.23902887105941772, | |
| "learning_rate": 3.258716180199278e-07, | |
| "loss": 1.3892, | |
| "num_input_tokens_seen": 235143168, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 0.22156427337774487, | |
| "grad_norm": 0.20809443295001984, | |
| "learning_rate": 3.1970232130513365e-07, | |
| "loss": 1.8955, | |
| "num_input_tokens_seen": 235405312, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 0.22181100419442387, | |
| "grad_norm": 0.6240611672401428, | |
| "learning_rate": 3.135900525405428e-07, | |
| "loss": 1.4981, | |
| "num_input_tokens_seen": 235667456, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 0.22205773501110287, | |
| "grad_norm": 0.24363017082214355, | |
| "learning_rate": 3.0753488620222037e-07, | |
| "loss": 1.8729, | |
| "num_input_tokens_seen": 235929600, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.22230446582778188, | |
| "grad_norm": 0.27527663111686707, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 2.0414, | |
| "num_input_tokens_seen": 236191744, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 0.22255119664446088, | |
| "grad_norm": 0.2439730167388916, | |
| "learning_rate": 2.9559615522887275e-07, | |
| "loss": 1.706, | |
| "num_input_tokens_seen": 236453888, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 0.22279792746113988, | |
| "grad_norm": 0.25705206394195557, | |
| "learning_rate": 2.8971273606351656e-07, | |
| "loss": 2.0021, | |
| "num_input_tokens_seen": 236716032, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.22304465827781889, | |
| "grad_norm": 0.34864532947540283, | |
| "learning_rate": 2.838867102619952e-07, | |
| "loss": 1.7085, | |
| "num_input_tokens_seen": 236978176, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 0.22329138909449792, | |
| "grad_norm": 0.4523051083087921, | |
| "learning_rate": 2.7811814881259503e-07, | |
| "loss": 1.4751, | |
| "num_input_tokens_seen": 237240320, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.22353811991117692, | |
| "grad_norm": 0.33270108699798584, | |
| "learning_rate": 2.724071220034158e-07, | |
| "loss": 1.9118, | |
| "num_input_tokens_seen": 237502464, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 0.22378485072785592, | |
| "grad_norm": 0.35357242822647095, | |
| "learning_rate": 2.6675369942151864e-07, | |
| "loss": 1.8829, | |
| "num_input_tokens_seen": 237764608, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 0.22403158154453492, | |
| "grad_norm": 0.38699132204055786, | |
| "learning_rate": 2.611579499520722e-07, | |
| "loss": 1.6583, | |
| "num_input_tokens_seen": 238026752, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 0.22427831236121393, | |
| "grad_norm": 0.37224283814430237, | |
| "learning_rate": 2.556199417775174e-07, | |
| "loss": 1.3216, | |
| "num_input_tokens_seen": 238288896, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 0.22452504317789293, | |
| "grad_norm": 0.32813823223114014, | |
| "learning_rate": 2.5013974237673824e-07, | |
| "loss": 2.0885, | |
| "num_input_tokens_seen": 238551040, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.22477177399457193, | |
| "grad_norm": 0.3540266752243042, | |
| "learning_rate": 2.447174185242324e-07, | |
| "loss": 1.6199, | |
| "num_input_tokens_seen": 238813184, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 0.22501850481125094, | |
| "grad_norm": 0.22869907319545746, | |
| "learning_rate": 2.3935303628930705e-07, | |
| "loss": 2.0078, | |
| "num_input_tokens_seen": 239075328, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 0.22526523562792994, | |
| "grad_norm": 0.31733882427215576, | |
| "learning_rate": 2.3404666103526542e-07, | |
| "loss": 1.334, | |
| "num_input_tokens_seen": 239337472, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 0.22551196644460894, | |
| "grad_norm": 0.27598369121551514, | |
| "learning_rate": 2.287983574186159e-07, | |
| "loss": 1.3499, | |
| "num_input_tokens_seen": 239599616, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 0.22575869726128794, | |
| "grad_norm": 0.1539166122674942, | |
| "learning_rate": 2.2360818938828189e-07, | |
| "loss": 1.4926, | |
| "num_input_tokens_seen": 239861760, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.22600542807796695, | |
| "grad_norm": 0.2620428800582886, | |
| "learning_rate": 2.1847622018482283e-07, | |
| "loss": 1.8938, | |
| "num_input_tokens_seen": 240123904, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 0.22625215889464595, | |
| "grad_norm": 0.36652788519859314, | |
| "learning_rate": 2.134025123396638e-07, | |
| "loss": 1.3867, | |
| "num_input_tokens_seen": 240386048, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 0.22649888971132495, | |
| "grad_norm": 0.306090384721756, | |
| "learning_rate": 2.083871276743338e-07, | |
| "loss": 1.5576, | |
| "num_input_tokens_seen": 240648192, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 0.22674562052800395, | |
| "grad_norm": 0.31827080249786377, | |
| "learning_rate": 2.0343012729971244e-07, | |
| "loss": 1.8278, | |
| "num_input_tokens_seen": 240910336, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 0.22699235134468296, | |
| "grad_norm": 0.3130633533000946, | |
| "learning_rate": 1.9853157161528468e-07, | |
| "loss": 1.999, | |
| "num_input_tokens_seen": 241172480, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.22723908216136196, | |
| "grad_norm": 0.2340356707572937, | |
| "learning_rate": 1.9369152030840553e-07, | |
| "loss": 2.1723, | |
| "num_input_tokens_seen": 241434624, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 0.22748581297804096, | |
| "grad_norm": 0.4273170530796051, | |
| "learning_rate": 1.8891003235357307e-07, | |
| "loss": 1.7863, | |
| "num_input_tokens_seen": 241696768, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 0.22773254379471997, | |
| "grad_norm": 0.2784411907196045, | |
| "learning_rate": 1.841871660117095e-07, | |
| "loss": 1.7997, | |
| "num_input_tokens_seen": 241958912, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 0.22797927461139897, | |
| "grad_norm": 0.27668172121047974, | |
| "learning_rate": 1.7952297882945e-07, | |
| "loss": 1.7699, | |
| "num_input_tokens_seen": 242221056, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.22822600542807797, | |
| "grad_norm": 0.27039194107055664, | |
| "learning_rate": 1.7491752763844294e-07, | |
| "loss": 1.7443, | |
| "num_input_tokens_seen": 242483200, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.22847273624475697, | |
| "grad_norm": 0.24253779649734497, | |
| "learning_rate": 1.7037086855465902e-07, | |
| "loss": 1.4137, | |
| "num_input_tokens_seen": 242745344, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 0.22871946706143598, | |
| "grad_norm": 0.262689471244812, | |
| "learning_rate": 1.6588305697770313e-07, | |
| "loss": 1.5132, | |
| "num_input_tokens_seen": 243007488, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 0.22896619787811498, | |
| "grad_norm": 0.21166115999221802, | |
| "learning_rate": 1.6145414759014433e-07, | |
| "loss": 1.3376, | |
| "num_input_tokens_seen": 243269632, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 0.22921292869479398, | |
| "grad_norm": 0.27536365389823914, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 1.8721, | |
| "num_input_tokens_seen": 243531776, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 0.22945965951147299, | |
| "grad_norm": 0.3286449611186981, | |
| "learning_rate": 1.5277325052430569e-07, | |
| "loss": 2.1457, | |
| "num_input_tokens_seen": 243793920, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.229706390328152, | |
| "grad_norm": 0.2047201246023178, | |
| "learning_rate": 1.4852136862001766e-07, | |
| "loss": 1.4811, | |
| "num_input_tokens_seen": 244056064, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 0.229953121144831, | |
| "grad_norm": 0.22693318128585815, | |
| "learning_rate": 1.4432860045182019e-07, | |
| "loss": 1.9241, | |
| "num_input_tokens_seen": 244318208, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 0.23019985196151, | |
| "grad_norm": 0.583653450012207, | |
| "learning_rate": 1.4019499710726913e-07, | |
| "loss": 1.9567, | |
| "num_input_tokens_seen": 244580352, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 0.230446582778189, | |
| "grad_norm": 0.3117119073867798, | |
| "learning_rate": 1.3612060895301759e-07, | |
| "loss": 1.6888, | |
| "num_input_tokens_seen": 244842496, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 0.230693313594868, | |
| "grad_norm": 0.26275816559791565, | |
| "learning_rate": 1.3210548563419857e-07, | |
| "loss": 1.7499, | |
| "num_input_tokens_seen": 245104640, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.230940044411547, | |
| "grad_norm": 0.18302679061889648, | |
| "learning_rate": 1.2814967607382433e-07, | |
| "loss": 1.1345, | |
| "num_input_tokens_seen": 245366784, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.231186775228226, | |
| "grad_norm": 0.2012418955564499, | |
| "learning_rate": 1.2425322847218368e-07, | |
| "loss": 1.8273, | |
| "num_input_tokens_seen": 245628928, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 0.231433506044905, | |
| "grad_norm": 0.23460544645786285, | |
| "learning_rate": 1.2041619030626283e-07, | |
| "loss": 1.8274, | |
| "num_input_tokens_seen": 245891072, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.231680236861584, | |
| "grad_norm": 0.4306367337703705, | |
| "learning_rate": 1.166386083291604e-07, | |
| "loss": 1.6486, | |
| "num_input_tokens_seen": 246153216, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 0.231926967678263, | |
| "grad_norm": 0.2089300900697708, | |
| "learning_rate": 1.1292052856952063e-07, | |
| "loss": 1.3933, | |
| "num_input_tokens_seen": 246415360, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.23217369849494202, | |
| "grad_norm": 0.23853234946727753, | |
| "learning_rate": 1.0926199633097156e-07, | |
| "loss": 1.4156, | |
| "num_input_tokens_seen": 246677504, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 0.23242042931162102, | |
| "grad_norm": 0.24944059550762177, | |
| "learning_rate": 1.0566305619157502e-07, | |
| "loss": 1.7874, | |
| "num_input_tokens_seen": 246939648, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 0.23266716012830002, | |
| "grad_norm": 0.1825234442949295, | |
| "learning_rate": 1.0212375200327973e-07, | |
| "loss": 1.3472, | |
| "num_input_tokens_seen": 247201792, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 0.23291389094497902, | |
| "grad_norm": 0.3297896981239319, | |
| "learning_rate": 9.864412689139124e-08, | |
| "loss": 1.6156, | |
| "num_input_tokens_seen": 247463936, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 0.23316062176165803, | |
| "grad_norm": 0.30966678261756897, | |
| "learning_rate": 9.522422325404234e-08, | |
| "loss": 1.7015, | |
| "num_input_tokens_seen": 247726080, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.23340735257833703, | |
| "grad_norm": 0.2826879024505615, | |
| "learning_rate": 9.186408276168012e-08, | |
| "loss": 1.757, | |
| "num_input_tokens_seen": 247988224, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.23365408339501603, | |
| "grad_norm": 0.43711355328559875, | |
| "learning_rate": 8.856374635655696e-08, | |
| "loss": 1.8845, | |
| "num_input_tokens_seen": 248250368, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 0.23390081421169504, | |
| "grad_norm": 0.16611160337924957, | |
| "learning_rate": 8.53232542522292e-08, | |
| "loss": 1.5545, | |
| "num_input_tokens_seen": 248512512, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 0.23414754502837404, | |
| "grad_norm": 0.25117266178131104, | |
| "learning_rate": 8.214264593307097e-08, | |
| "loss": 1.5059, | |
| "num_input_tokens_seen": 248774656, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 0.23439427584505304, | |
| "grad_norm": 0.31824541091918945, | |
| "learning_rate": 7.90219601537906e-08, | |
| "loss": 1.937, | |
| "num_input_tokens_seen": 249036800, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.23464100666173204, | |
| "grad_norm": 0.3191492259502411, | |
| "learning_rate": 7.59612349389599e-08, | |
| "loss": 1.9477, | |
| "num_input_tokens_seen": 249298944, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 0.23488773747841105, | |
| "grad_norm": 0.15992209315299988, | |
| "learning_rate": 7.296050758254958e-08, | |
| "loss": 1.7433, | |
| "num_input_tokens_seen": 249561088, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.23513446829509005, | |
| "grad_norm": 0.27538275718688965, | |
| "learning_rate": 7.001981464747565e-08, | |
| "loss": 1.8585, | |
| "num_input_tokens_seen": 249823232, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 0.23538119911176905, | |
| "grad_norm": 0.35428425669670105, | |
| "learning_rate": 6.713919196515317e-08, | |
| "loss": 1.8342, | |
| "num_input_tokens_seen": 250085376, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 0.23562792992844805, | |
| "grad_norm": 0.3533397912979126, | |
| "learning_rate": 6.431867463506047e-08, | |
| "loss": 1.6695, | |
| "num_input_tokens_seen": 250347520, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.23587466074512706, | |
| "grad_norm": 0.32426542043685913, | |
| "learning_rate": 6.15582970243117e-08, | |
| "loss": 2.0652, | |
| "num_input_tokens_seen": 250609664, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 0.23612139156180606, | |
| "grad_norm": 0.22531364858150482, | |
| "learning_rate": 5.8858092767236084e-08, | |
| "loss": 1.7251, | |
| "num_input_tokens_seen": 250871808, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 0.23636812237848506, | |
| "grad_norm": 0.2263481318950653, | |
| "learning_rate": 5.621809476497098e-08, | |
| "loss": 1.1222, | |
| "num_input_tokens_seen": 251133952, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 0.23661485319516407, | |
| "grad_norm": 0.30886295437812805, | |
| "learning_rate": 5.363833518505834e-08, | |
| "loss": 1.8128, | |
| "num_input_tokens_seen": 251396096, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 0.23686158401184307, | |
| "grad_norm": 0.3169589936733246, | |
| "learning_rate": 5.111884546105506e-08, | |
| "loss": 1.9473, | |
| "num_input_tokens_seen": 251658240, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.23710831482852207, | |
| "grad_norm": 0.1736677587032318, | |
| "learning_rate": 4.865965629214819e-08, | |
| "loss": 1.4546, | |
| "num_input_tokens_seen": 251920384, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 0.23735504564520107, | |
| "grad_norm": 0.23293748497962952, | |
| "learning_rate": 4.626079764278202e-08, | |
| "loss": 1.2854, | |
| "num_input_tokens_seen": 252182528, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 0.23760177646188008, | |
| "grad_norm": 0.3253999352455139, | |
| "learning_rate": 4.392229874229159e-08, | |
| "loss": 1.5582, | |
| "num_input_tokens_seen": 252444672, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 0.23784850727855908, | |
| "grad_norm": 0.35785549879074097, | |
| "learning_rate": 4.164418808454806e-08, | |
| "loss": 1.9794, | |
| "num_input_tokens_seen": 252706816, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 0.22039461135864258, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 1.288, | |
| "num_input_tokens_seen": 252968960, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.23834196891191708, | |
| "grad_norm": 0.24973900616168976, | |
| "learning_rate": 3.726924179339009e-08, | |
| "loss": 1.3325, | |
| "num_input_tokens_seen": 253231104, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.23858869972859612, | |
| "grad_norm": 0.3697846531867981, | |
| "learning_rate": 3.517245946731529e-08, | |
| "loss": 1.75, | |
| "num_input_tokens_seen": 253493248, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 0.23883543054527512, | |
| "grad_norm": 0.3277115225791931, | |
| "learning_rate": 3.313617199801777e-08, | |
| "loss": 1.598, | |
| "num_input_tokens_seen": 253755392, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 0.23908216136195412, | |
| "grad_norm": 0.3776665925979614, | |
| "learning_rate": 3.1160404197018155e-08, | |
| "loss": 1.5441, | |
| "num_input_tokens_seen": 254017536, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 0.23932889217863312, | |
| "grad_norm": 0.27291175723075867, | |
| "learning_rate": 2.9245180138423033e-08, | |
| "loss": 1.4075, | |
| "num_input_tokens_seen": 254279680, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.23957562299531213, | |
| "grad_norm": 0.3305472135543823, | |
| "learning_rate": 2.7390523158633552e-08, | |
| "loss": 2.0716, | |
| "num_input_tokens_seen": 254541824, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 0.23982235381199113, | |
| "grad_norm": 0.21496239304542542, | |
| "learning_rate": 2.5596455856058966e-08, | |
| "loss": 1.2715, | |
| "num_input_tokens_seen": 254803968, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.24006908462867013, | |
| "grad_norm": 0.3123878538608551, | |
| "learning_rate": 2.386300009084408e-08, | |
| "loss": 1.6762, | |
| "num_input_tokens_seen": 255066112, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 0.24031581544534913, | |
| "grad_norm": 0.24841855466365814, | |
| "learning_rate": 2.219017698460002e-08, | |
| "loss": 1.7913, | |
| "num_input_tokens_seen": 255328256, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 0.24056254626202814, | |
| "grad_norm": 0.33678221702575684, | |
| "learning_rate": 2.057800692014833e-08, | |
| "loss": 1.5478, | |
| "num_input_tokens_seen": 255590400, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.24080927707870714, | |
| "grad_norm": 0.20863652229309082, | |
| "learning_rate": 1.9026509541272276e-08, | |
| "loss": 1.7592, | |
| "num_input_tokens_seen": 255852544, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 0.24105600789538614, | |
| "grad_norm": 0.2960647642612457, | |
| "learning_rate": 1.753570375247815e-08, | |
| "loss": 1.3895, | |
| "num_input_tokens_seen": 256114688, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 0.24130273871206515, | |
| "grad_norm": 0.2581060230731964, | |
| "learning_rate": 1.610560771876435e-08, | |
| "loss": 1.9954, | |
| "num_input_tokens_seen": 256376832, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 0.24154946952874415, | |
| "grad_norm": 0.25385424494743347, | |
| "learning_rate": 1.4736238865398766e-08, | |
| "loss": 1.7407, | |
| "num_input_tokens_seen": 256638976, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 0.24179620034542315, | |
| "grad_norm": 0.13977891206741333, | |
| "learning_rate": 1.3427613877709523e-08, | |
| "loss": 1.3923, | |
| "num_input_tokens_seen": 256901120, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.24204293116210215, | |
| "grad_norm": 0.26059940457344055, | |
| "learning_rate": 1.2179748700879013e-08, | |
| "loss": 1.7049, | |
| "num_input_tokens_seen": 257163264, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 0.24228966197878116, | |
| "grad_norm": 0.23644216358661652, | |
| "learning_rate": 1.0992658539750179e-08, | |
| "loss": 1.8183, | |
| "num_input_tokens_seen": 257425408, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 0.24253639279546016, | |
| "grad_norm": 0.39895159006118774, | |
| "learning_rate": 9.866357858642206e-09, | |
| "loss": 1.2922, | |
| "num_input_tokens_seen": 257687552, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 0.24278312361213916, | |
| "grad_norm": 0.32731232047080994, | |
| "learning_rate": 8.800860381173448e-09, | |
| "loss": 1.5821, | |
| "num_input_tokens_seen": 257949696, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 0.24302985442881817, | |
| "grad_norm": 0.36111322045326233, | |
| "learning_rate": 7.796179090094891e-09, | |
| "loss": 1.7553, | |
| "num_input_tokens_seen": 258211840, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.24327658524549717, | |
| "grad_norm": 0.3253917992115021, | |
| "learning_rate": 6.852326227130835e-09, | |
| "loss": 1.3174, | |
| "num_input_tokens_seen": 258473984, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 0.24352331606217617, | |
| "grad_norm": 0.2258145809173584, | |
| "learning_rate": 5.969313292830126e-09, | |
| "loss": 1.6489, | |
| "num_input_tokens_seen": 258736128, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 0.24377004687885517, | |
| "grad_norm": 0.16833138465881348, | |
| "learning_rate": 5.147151046426824e-09, | |
| "loss": 1.2464, | |
| "num_input_tokens_seen": 258998272, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.24401677769553418, | |
| "grad_norm": 0.45908233523368835, | |
| "learning_rate": 4.385849505708084e-09, | |
| "loss": 1.7759, | |
| "num_input_tokens_seen": 259260416, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 0.24426350851221318, | |
| "grad_norm": 0.16207066178321838, | |
| "learning_rate": 3.685417946894254e-09, | |
| "loss": 1.3764, | |
| "num_input_tokens_seen": 259522560, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.24451023932889218, | |
| "grad_norm": 0.21899637579917908, | |
| "learning_rate": 3.0458649045211897e-09, | |
| "loss": 1.9428, | |
| "num_input_tokens_seen": 259784704, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 0.24475697014557118, | |
| "grad_norm": 0.3863295018672943, | |
| "learning_rate": 2.4671981713420003e-09, | |
| "loss": 1.942, | |
| "num_input_tokens_seen": 260046848, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 0.2450037009622502, | |
| "grad_norm": 0.2451121211051941, | |
| "learning_rate": 1.9494247982282386e-09, | |
| "loss": 1.4942, | |
| "num_input_tokens_seen": 260308992, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 0.2452504317789292, | |
| "grad_norm": 0.3088672161102295, | |
| "learning_rate": 1.4925510940844157e-09, | |
| "loss": 2.1903, | |
| "num_input_tokens_seen": 260571136, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.2454971625956082, | |
| "grad_norm": 0.32511118054389954, | |
| "learning_rate": 1.096582625772502e-09, | |
| "loss": 1.7177, | |
| "num_input_tokens_seen": 260833280, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.2457438934122872, | |
| "grad_norm": 0.23251359164714813, | |
| "learning_rate": 7.615242180436521e-10, | |
| "loss": 1.2304, | |
| "num_input_tokens_seen": 261095424, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 0.2459906242289662, | |
| "grad_norm": 0.46146008372306824, | |
| "learning_rate": 4.87379953478806e-10, | |
| "loss": 1.1382, | |
| "num_input_tokens_seen": 261357568, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 0.2462373550456452, | |
| "grad_norm": 0.2049003392457962, | |
| "learning_rate": 2.741531724392843e-10, | |
| "loss": 1.3837, | |
| "num_input_tokens_seen": 261619712, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 0.2464840858623242, | |
| "grad_norm": 0.3614410161972046, | |
| "learning_rate": 1.2184647302626585e-10, | |
| "loss": 1.9884, | |
| "num_input_tokens_seen": 261881856, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 0.2467308166790032, | |
| "grad_norm": 0.3488081097602844, | |
| "learning_rate": 3.0461711048035415e-11, | |
| "loss": 1.8701, | |
| "num_input_tokens_seen": 262144000, | |
| "step": 1000 | |
| } | |
| ], | |
| "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": 484794433536000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |