| { | |
| "best_metric": 0.030804481357336044, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 1.3490725126475547, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006745362563237774, | |
| "grad_norm": 1.2400175333023071, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4484, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006745362563237774, | |
| "eval_loss": 2.4732091426849365, | |
| "eval_runtime": 4.2133, | |
| "eval_samples_per_second": 59.336, | |
| "eval_steps_per_second": 14.953, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013490725126475547, | |
| "grad_norm": 1.746989130973816, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02023608768971332, | |
| "grad_norm": 1.7150555849075317, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5039, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.026981450252951095, | |
| "grad_norm": 1.9112859964370728, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3835, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03372681281618887, | |
| "grad_norm": 1.8590703010559082, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4084, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04047217537942664, | |
| "grad_norm": 1.994749903678894, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3308, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.047217537942664416, | |
| "grad_norm": 1.9599947929382324, | |
| "learning_rate": 7e-05, | |
| "loss": 2.2064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05396290050590219, | |
| "grad_norm": 1.8283764123916626, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1668, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06070826306913996, | |
| "grad_norm": 1.8431702852249146, | |
| "learning_rate": 9e-05, | |
| "loss": 1.8207, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06745362563237774, | |
| "grad_norm": 1.7513902187347412, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07419898819561552, | |
| "grad_norm": 1.5856826305389404, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.336, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08094435075885328, | |
| "grad_norm": 1.5326967239379883, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.0208, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08768971332209106, | |
| "grad_norm": 1.4028621912002563, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.8476, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09443507588532883, | |
| "grad_norm": 1.4114820957183838, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.7371, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10118043844856661, | |
| "grad_norm": 1.2082682847976685, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.6626, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10792580101180438, | |
| "grad_norm": 1.1544679403305054, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.3939, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11467116357504216, | |
| "grad_norm": 0.9324457049369812, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.2523, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12141652613827993, | |
| "grad_norm": 0.8373090028762817, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.2021, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1281618887015177, | |
| "grad_norm": 0.6018897891044617, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.1238, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13490725126475547, | |
| "grad_norm": 0.7867188453674316, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14165261382799327, | |
| "grad_norm": 0.7352498173713684, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.0723, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14839797639123103, | |
| "grad_norm": 0.8991091847419739, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.1772, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1551433389544688, | |
| "grad_norm": 1.035231590270996, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.2832, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16188870151770657, | |
| "grad_norm": 0.9051530957221985, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.064, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16863406408094436, | |
| "grad_norm": 0.7188823223114014, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.0517, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17537942664418213, | |
| "grad_norm": 0.46549901366233826, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.1109, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1821247892074199, | |
| "grad_norm": 0.5394489169120789, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.1084, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.18887015177065766, | |
| "grad_norm": 0.41629818081855774, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.026, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19561551433389546, | |
| "grad_norm": 0.18275360763072968, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.01, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20236087689713322, | |
| "grad_norm": 0.2997238337993622, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0147, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.209106239460371, | |
| "grad_norm": 0.34996435046195984, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.0727, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.21585160202360876, | |
| "grad_norm": 0.11553355306386948, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.007, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22259696458684655, | |
| "grad_norm": 0.6371837258338928, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.2365, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.22934232715008432, | |
| "grad_norm": 0.24877570569515228, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.0127, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23608768971332209, | |
| "grad_norm": 0.9486711621284485, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.2689, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24283305227655985, | |
| "grad_norm": 0.5964698195457458, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.1425, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24957841483979765, | |
| "grad_norm": 0.9327266812324524, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.3979, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2563237774030354, | |
| "grad_norm": 2.276948928833008, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.5783, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2630691399662732, | |
| "grad_norm": 3.357478618621826, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.6218, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.26981450252951095, | |
| "grad_norm": 1.1287559270858765, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.1638, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2765598650927487, | |
| "grad_norm": 0.7897985577583313, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.1114, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.28330522765598654, | |
| "grad_norm": 0.35362014174461365, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0645, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2900505902192243, | |
| "grad_norm": 0.3299892246723175, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.0734, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.29679595278246207, | |
| "grad_norm": 0.20617251098155975, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.062, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.30354131534569984, | |
| "grad_norm": 0.2516458332538605, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.0756, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3102866779089376, | |
| "grad_norm": 0.18184010684490204, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.0274, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.31703204047217537, | |
| "grad_norm": 0.6161956191062927, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.0782, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.32377740303541314, | |
| "grad_norm": 0.3464246094226837, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0492, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3305227655986509, | |
| "grad_norm": 0.3543274700641632, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.0431, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3372681281618887, | |
| "grad_norm": 0.35507461428642273, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.0615, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3372681281618887, | |
| "eval_loss": 0.12481166422367096, | |
| "eval_runtime": 4.1844, | |
| "eval_samples_per_second": 59.746, | |
| "eval_steps_per_second": 15.056, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3440134907251265, | |
| "grad_norm": 0.6176913976669312, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.0584, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.35075885328836426, | |
| "grad_norm": 0.4576355218887329, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.1297, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.357504215851602, | |
| "grad_norm": 0.2627366781234741, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.0278, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3642495784148398, | |
| "grad_norm": 0.21006304025650024, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0249, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.37099494097807756, | |
| "grad_norm": 0.2625662684440613, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.0567, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3777403035413153, | |
| "grad_norm": 0.13903094828128815, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.0153, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3844856661045531, | |
| "grad_norm": 0.3335474729537964, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.0406, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3912310286677909, | |
| "grad_norm": 0.5261087417602539, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.0645, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.3979763912310287, | |
| "grad_norm": 0.3396313786506653, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.1187, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.40472175379426645, | |
| "grad_norm": 0.12215958535671234, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.0332, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4114671163575042, | |
| "grad_norm": 0.12980970740318298, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.0362, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.418212478920742, | |
| "grad_norm": 0.14014245569705963, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.0355, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.42495784148397975, | |
| "grad_norm": 0.10224577784538269, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.0225, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4317032040472175, | |
| "grad_norm": 0.05420713126659393, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.0064, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.43844856661045534, | |
| "grad_norm": 0.09725449979305267, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.0272, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4451939291736931, | |
| "grad_norm": 0.061895571649074554, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0067, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.45193929173693087, | |
| "grad_norm": 0.16127723455429077, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0247, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.45868465430016864, | |
| "grad_norm": 0.10433106869459152, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.0232, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4654300168634064, | |
| "grad_norm": 0.1770942360162735, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.0648, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.47217537942664417, | |
| "grad_norm": 0.05089578032493591, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.0047, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.47892074198988194, | |
| "grad_norm": 0.04429392144083977, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.0046, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4856661045531197, | |
| "grad_norm": 0.03947385400533676, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0036, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4924114671163575, | |
| "grad_norm": 0.3026740849018097, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.0643, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4991568296795953, | |
| "grad_norm": 0.5699010491371155, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.1916, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5059021922428331, | |
| "grad_norm": 1.258675456047058, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.7678, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5126475548060708, | |
| "grad_norm": 0.7247858047485352, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.3692, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5193929173693086, | |
| "grad_norm": 0.3413718640804291, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.0726, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5261382799325464, | |
| "grad_norm": 0.33681803941726685, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.0958, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5328836424957841, | |
| "grad_norm": 0.056699346750974655, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.0044, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.5396290050590219, | |
| "grad_norm": 0.19200845062732697, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.0148, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5463743676222597, | |
| "grad_norm": 0.10613183677196503, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.0073, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5531197301854974, | |
| "grad_norm": 0.11156696826219559, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.0175, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5598650927487352, | |
| "grad_norm": 0.09746899455785751, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.0076, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5666104553119731, | |
| "grad_norm": 0.07079606503248215, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.0055, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5733558178752108, | |
| "grad_norm": 0.16447293758392334, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.0498, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5801011804384486, | |
| "grad_norm": 0.09365685284137726, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0065, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5868465430016864, | |
| "grad_norm": 0.13086366653442383, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.0084, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5935919055649241, | |
| "grad_norm": 0.08966828882694244, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.0074, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.6003372681281619, | |
| "grad_norm": 0.08384972810745239, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.0057, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.6070826306913997, | |
| "grad_norm": 0.06855591386556625, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0049, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6138279932546374, | |
| "grad_norm": 0.05239510163664818, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.0035, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6205733558178752, | |
| "grad_norm": 0.06461122632026672, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.0142, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.627318718381113, | |
| "grad_norm": 0.053655944764614105, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.0038, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6340640809443507, | |
| "grad_norm": 0.04611735790967941, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.0032, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6408094435075885, | |
| "grad_norm": 0.03549090772867203, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.0023, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6475548060708263, | |
| "grad_norm": 0.07244165986776352, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0028, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.654300168634064, | |
| "grad_norm": 0.1616162806749344, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.0267, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6610455311973018, | |
| "grad_norm": 0.29952797293663025, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.0434, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6677908937605397, | |
| "grad_norm": 0.028047610074281693, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.002, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6745362563237775, | |
| "grad_norm": 0.07022430747747421, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.0128, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6745362563237775, | |
| "eval_loss": 0.047212474048137665, | |
| "eval_runtime": 4.1679, | |
| "eval_samples_per_second": 59.982, | |
| "eval_steps_per_second": 15.116, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6812816188870152, | |
| "grad_norm": 0.17502517998218536, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 0.0105, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.688026981450253, | |
| "grad_norm": 0.09536734968423843, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.0182, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6947723440134908, | |
| "grad_norm": 0.18720607459545135, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 0.0244, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.7015177065767285, | |
| "grad_norm": 0.10460835695266724, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.0161, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.7082630691399663, | |
| "grad_norm": 0.04144510254263878, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0021, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.715008431703204, | |
| "grad_norm": 0.27221187949180603, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.0207, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.7217537942664418, | |
| "grad_norm": 0.07747731357812881, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 0.0038, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.7284991568296796, | |
| "grad_norm": 0.2026963233947754, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.0358, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7352445193929174, | |
| "grad_norm": 0.10932726413011551, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 0.0203, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.7419898819561551, | |
| "grad_norm": 0.07752896845340729, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.0033, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7487352445193929, | |
| "grad_norm": 0.5522063970565796, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.1557, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7554806070826307, | |
| "grad_norm": 0.8922995924949646, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.4962, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7622259696458684, | |
| "grad_norm": 0.747218668460846, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 0.2185, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.7689713322091062, | |
| "grad_norm": 0.19041088223457336, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.0152, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.7757166947723441, | |
| "grad_norm": 0.4229462444782257, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.0618, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7824620573355818, | |
| "grad_norm": 0.30456361174583435, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.0824, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7892074198988196, | |
| "grad_norm": 0.2638731300830841, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.0391, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.7959527824620574, | |
| "grad_norm": 0.12386748194694519, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.0198, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.8026981450252951, | |
| "grad_norm": 0.13967956602573395, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.0204, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.8094435075885329, | |
| "grad_norm": 0.13475240767002106, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.0054, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8161888701517707, | |
| "grad_norm": 0.21277835965156555, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.0224, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.8229342327150084, | |
| "grad_norm": 0.21421295404434204, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.0088, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.8296795952782462, | |
| "grad_norm": 0.22496074438095093, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.0233, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.836424957841484, | |
| "grad_norm": 0.24452394247055054, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0363, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8431703204047217, | |
| "grad_norm": 0.1874397248029709, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.0108, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8499156829679595, | |
| "grad_norm": 0.09923595935106277, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.0044, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8566610455311973, | |
| "grad_norm": 0.08702019602060318, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.0038, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.863406408094435, | |
| "grad_norm": 0.1192399188876152, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.0059, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8701517706576728, | |
| "grad_norm": 0.055553749203681946, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.0026, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.8768971332209107, | |
| "grad_norm": 0.055112626403570175, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.0025, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8836424957841484, | |
| "grad_norm": 0.032335035502910614, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.0014, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.8903878583473862, | |
| "grad_norm": 0.14078502357006073, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.0137, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.897133220910624, | |
| "grad_norm": 0.04515624791383743, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.0028, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.9038785834738617, | |
| "grad_norm": 0.06440647691488266, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.0059, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.9106239460370995, | |
| "grad_norm": 0.24568696320056915, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.0066, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.9173693086003373, | |
| "grad_norm": 0.03420849144458771, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.0017, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.924114671163575, | |
| "grad_norm": 0.03081429935991764, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.0013, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.9308600337268128, | |
| "grad_norm": 0.017709970474243164, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.0008, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.9376053962900506, | |
| "grad_norm": 0.036176182329654694, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.0016, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.9443507588532883, | |
| "grad_norm": 0.024693654850125313, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.0012, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9510961214165261, | |
| "grad_norm": 0.17358708381652832, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.0156, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.9578414839797639, | |
| "grad_norm": 0.1224161759018898, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.0162, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9645868465430016, | |
| "grad_norm": 0.10097432136535645, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0128, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.9713322091062394, | |
| "grad_norm": 0.1563689410686493, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.0154, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9780775716694773, | |
| "grad_norm": 0.34062257409095764, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.049, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.984822934232715, | |
| "grad_norm": 0.11708389222621918, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.0171, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.9915682967959528, | |
| "grad_norm": 0.131124809384346, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.0188, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.9983136593591906, | |
| "grad_norm": 0.48198604583740234, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.0995, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.0050590219224282, | |
| "grad_norm": 0.4684287905693054, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.2564, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.0118043844856661, | |
| "grad_norm": 0.6373432874679565, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.2716, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0118043844856661, | |
| "eval_loss": 0.0355226956307888, | |
| "eval_runtime": 4.1722, | |
| "eval_samples_per_second": 59.921, | |
| "eval_steps_per_second": 15.1, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0185497470489038, | |
| "grad_norm": 0.3283449113368988, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 0.0724, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.0252951096121417, | |
| "grad_norm": 0.13863329589366913, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.0232, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.0320404721753795, | |
| "grad_norm": 0.21840208768844604, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.0189, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.0387858347386172, | |
| "grad_norm": 0.14212460815906525, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.0182, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.045531197301855, | |
| "grad_norm": 0.21400751173496246, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.0124, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.0522765598650927, | |
| "grad_norm": 0.006335023324936628, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.0003, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.0590219224283306, | |
| "grad_norm": 0.044015780091285706, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 0.0012, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.0657672849915683, | |
| "grad_norm": 0.019701050594449043, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.0009, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.0725126475548061, | |
| "grad_norm": 0.018881501629948616, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.0007, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.0792580101180438, | |
| "grad_norm": 0.24259497225284576, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.0272, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0860033726812817, | |
| "grad_norm": 0.0803951844573021, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 0.0116, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.0927487352445193, | |
| "grad_norm": 0.138003408908844, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0214, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.0994940978077572, | |
| "grad_norm": 0.1587391346693039, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 0.0123, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.1062394603709949, | |
| "grad_norm": 0.09421160817146301, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.0186, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.1129848229342327, | |
| "grad_norm": 0.05252014100551605, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.0019, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.1197301854974704, | |
| "grad_norm": 0.061075758188962936, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.0022, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.1264755480607083, | |
| "grad_norm": 0.1525970995426178, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.0243, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.1332209106239461, | |
| "grad_norm": 0.08765783160924911, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.0028, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.1399662731871838, | |
| "grad_norm": 0.05461001396179199, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.0018, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.1467116357504217, | |
| "grad_norm": 0.031027011573314667, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.0012, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1534569983136593, | |
| "grad_norm": 0.11484523862600327, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.0131, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.1602023608768972, | |
| "grad_norm": 0.10547629743814468, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.0035, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.1669477234401349, | |
| "grad_norm": 0.07820610702037811, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.0087, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.1736930860033727, | |
| "grad_norm": 0.13314871490001678, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.0086, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.1804384485666104, | |
| "grad_norm": 0.0992496982216835, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.0035, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.1871838111298483, | |
| "grad_norm": 0.07356826961040497, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.0026, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.193929173693086, | |
| "grad_norm": 0.11367491632699966, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.0038, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.2006745362563238, | |
| "grad_norm": 0.17552682757377625, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.006, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.2074198988195615, | |
| "grad_norm": 0.18896107375621796, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.0089, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.2141652613827993, | |
| "grad_norm": 0.1438591331243515, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.0095, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.220910623946037, | |
| "grad_norm": 0.11014795303344727, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0036, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.2276559865092749, | |
| "grad_norm": 0.20106233656406403, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.007, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.2344013490725128, | |
| "grad_norm": 0.13474810123443604, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.0216, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.2411467116357504, | |
| "grad_norm": 0.12335095554590225, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.0044, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.2478920741989883, | |
| "grad_norm": 0.13575774431228638, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.0114, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.254637436762226, | |
| "grad_norm": 0.490744024515152, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.2586, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.2613827993254638, | |
| "grad_norm": 0.36557716131210327, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.0905, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.2681281618887015, | |
| "grad_norm": 0.17767265439033508, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.0353, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.2748735244519394, | |
| "grad_norm": 0.056860972195863724, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.0127, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.281618887015177, | |
| "grad_norm": 0.2886894643306732, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.0757, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.2883642495784149, | |
| "grad_norm": 0.013288192451000214, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.0006, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.2951096121416525, | |
| "grad_norm": 0.2898249626159668, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.0343, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.3018549747048904, | |
| "grad_norm": 0.010432682000100613, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.0004, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.3086003372681283, | |
| "grad_norm": 0.16382138431072235, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.0074, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.315345699831366, | |
| "grad_norm": 0.11828618496656418, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.0156, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.3220910623946036, | |
| "grad_norm": 0.03025907278060913, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.001, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.3288364249578415, | |
| "grad_norm": 0.018650656566023827, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.0007, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.3355817875210794, | |
| "grad_norm": 0.01551801897585392, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.0006, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.342327150084317, | |
| "grad_norm": 0.024330761283636093, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.0009, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.3490725126475547, | |
| "grad_norm": 0.052249450236558914, | |
| "learning_rate": 0.0, | |
| "loss": 0.0048, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.3490725126475547, | |
| "eval_loss": 0.030804481357336044, | |
| "eval_runtime": 4.1742, | |
| "eval_samples_per_second": 59.892, | |
| "eval_steps_per_second": 15.093, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.373561255559168e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |