| { | |
| "best_metric": 0.004985797218978405, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.43149946062567424, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004314994606256742, | |
| "grad_norm": 17.087665557861328, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8617, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004314994606256742, | |
| "eval_loss": 1.3578087091445923, | |
| "eval_runtime": 43.1351, | |
| "eval_samples_per_second": 9.041, | |
| "eval_steps_per_second": 2.272, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008629989212513484, | |
| "grad_norm": 18.310680389404297, | |
| "learning_rate": 2e-05, | |
| "loss": 2.15, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012944983818770227, | |
| "grad_norm": 11.765509605407715, | |
| "learning_rate": 3e-05, | |
| "loss": 1.918, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017259978425026967, | |
| "grad_norm": 10.882978439331055, | |
| "learning_rate": 4e-05, | |
| "loss": 1.534, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021574973031283712, | |
| "grad_norm": 10.474682807922363, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0628, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025889967637540454, | |
| "grad_norm": 7.007547855377197, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6529, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.030204962243797196, | |
| "grad_norm": 7.29658842086792, | |
| "learning_rate": 7e-05, | |
| "loss": 0.3454, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.034519956850053934, | |
| "grad_norm": 7.774313449859619, | |
| "learning_rate": 8e-05, | |
| "loss": 0.172, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.038834951456310676, | |
| "grad_norm": 11.443821907043457, | |
| "learning_rate": 9e-05, | |
| "loss": 0.1285, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.043149946062567425, | |
| "grad_norm": 3.870835542678833, | |
| "learning_rate": 0.0001, | |
| "loss": 0.105, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04746494066882417, | |
| "grad_norm": 1.3818610906600952, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.0662, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05177993527508091, | |
| "grad_norm": 0.9391865730285645, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.0341, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05609492988133765, | |
| "grad_norm": 1.3468683958053589, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.0455, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06040992448759439, | |
| "grad_norm": 1.2473664283752441, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.0308, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06472491909385113, | |
| "grad_norm": 0.7611331939697266, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.0273, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06903991370010787, | |
| "grad_norm": 0.6905964612960815, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.0319, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07335490830636461, | |
| "grad_norm": 0.4306313991546631, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.0312, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07766990291262135, | |
| "grad_norm": 0.8068592548370361, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.0349, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08198489751887811, | |
| "grad_norm": 1.119532823562622, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.0342, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08629989212513485, | |
| "grad_norm": 0.9314156770706177, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.0281, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09061488673139159, | |
| "grad_norm": 0.5867143273353577, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.0223, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09492988133764833, | |
| "grad_norm": 0.7694201469421387, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.0233, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09924487594390508, | |
| "grad_norm": 0.7751960754394531, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.0172, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10355987055016182, | |
| "grad_norm": 0.907068133354187, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0256, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10787486515641856, | |
| "grad_norm": 0.8207224011421204, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.0326, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1121898597626753, | |
| "grad_norm": 0.7676880359649658, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.0237, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11650485436893204, | |
| "grad_norm": 1.1785573959350586, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.0349, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12081984897518878, | |
| "grad_norm": 3.5154619216918945, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.0276, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12513484358144553, | |
| "grad_norm": 0.45314833521842957, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0196, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12944983818770225, | |
| "grad_norm": 1.771968126296997, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0488, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.133764832793959, | |
| "grad_norm": 0.781960666179657, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.0287, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13807982740021574, | |
| "grad_norm": 5.066781997680664, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.0237, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1423948220064725, | |
| "grad_norm": 1.486770749092102, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.0369, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.14670981661272922, | |
| "grad_norm": 0.8950640559196472, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.0209, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15102481121898598, | |
| "grad_norm": 1.024499535560608, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.0264, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1553398058252427, | |
| "grad_norm": 0.7848332524299622, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0324, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15965480043149946, | |
| "grad_norm": 0.42584487795829773, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.0179, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16396979503775622, | |
| "grad_norm": 0.4489155411720276, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.0241, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16828478964401294, | |
| "grad_norm": 0.8728815317153931, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.0219, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1725997842502697, | |
| "grad_norm": 1.0815844535827637, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.0389, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17691477885652643, | |
| "grad_norm": 0.3527948558330536, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.0188, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18122977346278318, | |
| "grad_norm": 0.5202154517173767, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0176, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1855447680690399, | |
| "grad_norm": 0.6290869116783142, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.0288, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18985976267529667, | |
| "grad_norm": 0.5054512619972229, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.018, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1941747572815534, | |
| "grad_norm": 0.5555866956710815, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.0173, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19848975188781015, | |
| "grad_norm": 0.9120898842811584, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.0316, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20280474649406688, | |
| "grad_norm": 0.43381747603416443, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.0195, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.20711974110032363, | |
| "grad_norm": 0.5131010413169861, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0214, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.21143473570658036, | |
| "grad_norm": 0.5879638195037842, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.0177, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21574973031283712, | |
| "grad_norm": 0.6071250438690186, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.0214, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21574973031283712, | |
| "eval_loss": 0.00678399158641696, | |
| "eval_runtime": 44.1541, | |
| "eval_samples_per_second": 8.833, | |
| "eval_steps_per_second": 2.219, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22006472491909385, | |
| "grad_norm": 1.976332187652588, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.0361, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2243797195253506, | |
| "grad_norm": 0.2932753264904022, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.0171, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.22869471413160733, | |
| "grad_norm": 0.31595897674560547, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.0195, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.23300970873786409, | |
| "grad_norm": 1.3101752996444702, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0292, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2373247033441208, | |
| "grad_norm": 0.7268949747085571, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.0143, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24163969795037757, | |
| "grad_norm": 4.275149822235107, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.0417, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2459546925566343, | |
| "grad_norm": 0.3323039710521698, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.0145, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.25026968716289105, | |
| "grad_norm": 0.3134349584579468, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.0159, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2545846817691478, | |
| "grad_norm": 1.0623679161071777, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.0273, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2588996763754045, | |
| "grad_norm": 1.1334818601608276, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.019, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2632146709816613, | |
| "grad_norm": 0.45052817463874817, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.0226, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.267529665587918, | |
| "grad_norm": 0.6137033104896545, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.0212, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.27184466019417475, | |
| "grad_norm": 0.7195796370506287, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.0213, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2761596548004315, | |
| "grad_norm": 0.5169023871421814, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.0222, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.28047464940668826, | |
| "grad_norm": 0.36940544843673706, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.0206, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.284789644012945, | |
| "grad_norm": 0.6449036598205566, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.0438, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2891046386192017, | |
| "grad_norm": 1.0550373792648315, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0297, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.29341963322545844, | |
| "grad_norm": 0.3580387830734253, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.0208, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2977346278317152, | |
| "grad_norm": 0.4854778051376343, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.0218, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.30204962243797195, | |
| "grad_norm": 0.4402463436126709, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.0157, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3063646170442287, | |
| "grad_norm": 0.3080613315105438, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.015, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3106796116504854, | |
| "grad_norm": 0.3834276497364044, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.0122, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3149946062567422, | |
| "grad_norm": 0.9351459741592407, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.0232, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3193096008629989, | |
| "grad_norm": 0.8108393549919128, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.0276, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.32362459546925565, | |
| "grad_norm": 0.43026992678642273, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.0136, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.32793959007551243, | |
| "grad_norm": 0.4602266550064087, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.0175, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.33225458468176916, | |
| "grad_norm": 11.124612808227539, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.0284, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3365695792880259, | |
| "grad_norm": 6.074794769287109, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.028, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3408845738942826, | |
| "grad_norm": 1.4700261354446411, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.0224, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.3451995685005394, | |
| "grad_norm": 17.13897132873535, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.0538, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.34951456310679613, | |
| "grad_norm": 0.4576086103916168, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.021, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.35382955771305286, | |
| "grad_norm": 0.3490538001060486, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.0213, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.3581445523193096, | |
| "grad_norm": 7.836808204650879, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.0245, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.36245954692556637, | |
| "grad_norm": 16.858186721801758, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.2472, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3667745415318231, | |
| "grad_norm": 13.203956604003906, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.0769, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3710895361380798, | |
| "grad_norm": 8.34621810913086, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.057, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.37540453074433655, | |
| "grad_norm": 0.9256253242492676, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.0226, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.37971952535059333, | |
| "grad_norm": 0.4759206473827362, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.0165, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.38403451995685006, | |
| "grad_norm": 0.8075918555259705, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.0152, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.3883495145631068, | |
| "grad_norm": 0.435330867767334, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.0122, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3926645091693635, | |
| "grad_norm": 0.4027554988861084, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.0163, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.3969795037756203, | |
| "grad_norm": 0.7867634296417236, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.0268, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.40129449838187703, | |
| "grad_norm": 0.49145984649658203, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.0255, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.40560949298813376, | |
| "grad_norm": 0.4385581612586975, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.0172, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.4099244875943905, | |
| "grad_norm": 0.42079663276672363, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.0172, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.41423948220064727, | |
| "grad_norm": 0.37281689047813416, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.0163, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.418554476806904, | |
| "grad_norm": 0.5622067451477051, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.0149, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.4228694714131607, | |
| "grad_norm": 0.7449488639831543, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.015, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.42718446601941745, | |
| "grad_norm": 0.26745229959487915, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.0088, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.43149946062567424, | |
| "grad_norm": 0.23704928159713745, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.0098, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.43149946062567424, | |
| "eval_loss": 0.004985797218978405, | |
| "eval_runtime": 44.1566, | |
| "eval_samples_per_second": 8.832, | |
| "eval_steps_per_second": 2.219, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5669428198414746e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |