| { | |
| "best_metric": 0.32453402876853943, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.12849341471249598, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00128493414712496, | |
| "grad_norm": 0.2153976410627365, | |
| "learning_rate": 1.6666666666666668e-07, | |
| "loss": 0.2219, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00128493414712496, | |
| "eval_loss": 0.5323071479797363, | |
| "eval_runtime": 104.1803, | |
| "eval_samples_per_second": 12.584, | |
| "eval_steps_per_second": 1.574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00256986829424992, | |
| "grad_norm": 0.30113792419433594, | |
| "learning_rate": 3.3333333333333335e-07, | |
| "loss": 0.2754, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038548024413748794, | |
| "grad_norm": 0.34443554282188416, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.2138, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00513973658849984, | |
| "grad_norm": 0.39076605439186096, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 0.2594, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006424670735624799, | |
| "grad_norm": 0.4116816818714142, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 0.2973, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007709604882749759, | |
| "grad_norm": 0.47579216957092285, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.3334, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008994539029874718, | |
| "grad_norm": 0.4625336229801178, | |
| "learning_rate": 1.1666666666666668e-06, | |
| "loss": 0.378, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01027947317699968, | |
| "grad_norm": 0.49837028980255127, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.3781, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011564407324124639, | |
| "grad_norm": 0.6171607971191406, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.4556, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012849341471249599, | |
| "grad_norm": 0.5609787106513977, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.3851, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014134275618374558, | |
| "grad_norm": 0.5493508577346802, | |
| "learning_rate": 1.8333333333333333e-06, | |
| "loss": 0.361, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015419209765499518, | |
| "grad_norm": 0.6691854000091553, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.3836, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016704143912624477, | |
| "grad_norm": 0.6240688562393188, | |
| "learning_rate": 2.166666666666667e-06, | |
| "loss": 0.4312, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017989078059749437, | |
| "grad_norm": 0.7265613675117493, | |
| "learning_rate": 2.3333333333333336e-06, | |
| "loss": 0.402, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019274012206874396, | |
| "grad_norm": 0.7323911190032959, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.4389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02055894635399936, | |
| "grad_norm": 0.7426925301551819, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.391, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02184388050112432, | |
| "grad_norm": 0.8133726716041565, | |
| "learning_rate": 2.8333333333333335e-06, | |
| "loss": 0.4516, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023128814648249278, | |
| "grad_norm": 0.7418370842933655, | |
| "learning_rate": 3e-06, | |
| "loss": 0.394, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024413748795374238, | |
| "grad_norm": 0.7176808714866638, | |
| "learning_rate": 3.1666666666666667e-06, | |
| "loss": 0.3914, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025698682942499197, | |
| "grad_norm": 0.7384213805198669, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.492, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026983617089624157, | |
| "grad_norm": 0.8748512268066406, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.4822, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028268551236749116, | |
| "grad_norm": 0.9340311884880066, | |
| "learning_rate": 3.6666666666666666e-06, | |
| "loss": 0.4356, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029553485383874076, | |
| "grad_norm": 0.760717511177063, | |
| "learning_rate": 3.833333333333334e-06, | |
| "loss": 0.3861, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030838419530999035, | |
| "grad_norm": 0.8021165728569031, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.3977, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.032123353678123995, | |
| "grad_norm": 0.8144139051437378, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.4304, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033408287825248954, | |
| "grad_norm": 0.7808437347412109, | |
| "learning_rate": 4.333333333333334e-06, | |
| "loss": 0.4361, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.034693221972373914, | |
| "grad_norm": 1.1297154426574707, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.5637, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03597815611949887, | |
| "grad_norm": 0.9760102033615112, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 0.4492, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03726309026662383, | |
| "grad_norm": 0.9299658536911011, | |
| "learning_rate": 4.833333333333333e-06, | |
| "loss": 0.3935, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03854802441374879, | |
| "grad_norm": 0.998177170753479, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4626, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03983295856087375, | |
| "grad_norm": 1.0855931043624878, | |
| "learning_rate": 4.997482666353287e-06, | |
| "loss": 0.3724, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04111789270799872, | |
| "grad_norm": 1.125369668006897, | |
| "learning_rate": 4.989935734988098e-06, | |
| "loss": 0.4277, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04240282685512368, | |
| "grad_norm": 1.185484528541565, | |
| "learning_rate": 4.977374404419838e-06, | |
| "loss": 0.5637, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04368776100224864, | |
| "grad_norm": 1.4676731824874878, | |
| "learning_rate": 4.959823971496575e-06, | |
| "loss": 0.4642, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0449726951493736, | |
| "grad_norm": 1.6404002904891968, | |
| "learning_rate": 4.937319780454559e-06, | |
| "loss": 0.5588, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.046257629296498556, | |
| "grad_norm": 1.335082769393921, | |
| "learning_rate": 4.909907151739634e-06, | |
| "loss": 0.4545, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.047542563443623516, | |
| "grad_norm": 1.3332980871200562, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.4349, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.048827497590748475, | |
| "grad_norm": 1.369439959526062, | |
| "learning_rate": 4.8405871765993435e-06, | |
| "loss": 0.4278, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.050112431737873435, | |
| "grad_norm": 1.502086877822876, | |
| "learning_rate": 4.7988194313786275e-06, | |
| "loss": 0.5379, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.051397365884998394, | |
| "grad_norm": 1.5149955749511719, | |
| "learning_rate": 4.752422169756048e-06, | |
| "loss": 0.4262, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.052682300032123354, | |
| "grad_norm": 1.4554944038391113, | |
| "learning_rate": 4.701488829641845e-06, | |
| "loss": 0.5276, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05396723417924831, | |
| "grad_norm": 1.277449369430542, | |
| "learning_rate": 4.646121984004666e-06, | |
| "loss": 0.4139, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05525216832637327, | |
| "grad_norm": 1.4300509691238403, | |
| "learning_rate": 4.586433134303257e-06, | |
| "loss": 0.5761, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05653710247349823, | |
| "grad_norm": 1.1660631895065308, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.4325, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05782203662062319, | |
| "grad_norm": 1.6382452249526978, | |
| "learning_rate": 4.454578706170075e-06, | |
| "loss": 0.4775, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05910697076774815, | |
| "grad_norm": 1.5593774318695068, | |
| "learning_rate": 4.382678665009028e-06, | |
| "loss": 0.373, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06039190491487311, | |
| "grad_norm": 1.3182231187820435, | |
| "learning_rate": 4.3069871595684795e-06, | |
| "loss": 0.3875, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06167683906199807, | |
| "grad_norm": 1.720353364944458, | |
| "learning_rate": 4.227656622467162e-06, | |
| "loss": 0.5628, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06296177320912304, | |
| "grad_norm": 1.7283390760421753, | |
| "learning_rate": 4.144846814849282e-06, | |
| "loss": 0.4885, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06424670735624799, | |
| "grad_norm": 2.8064615726470947, | |
| "learning_rate": 4.058724504646834e-06, | |
| "loss": 0.7336, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06424670735624799, | |
| "eval_loss": 0.34164541959762573, | |
| "eval_runtime": 105.4694, | |
| "eval_samples_per_second": 12.43, | |
| "eval_steps_per_second": 1.555, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06553164150337296, | |
| "grad_norm": 0.26072192192077637, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.1646, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.06681657565049791, | |
| "grad_norm": 0.3280903398990631, | |
| "learning_rate": 3.8772424536302565e-06, | |
| "loss": 0.2271, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.06810150979762288, | |
| "grad_norm": 0.34677988290786743, | |
| "learning_rate": 3.782248193514766e-06, | |
| "loss": 0.2508, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.06938644394474783, | |
| "grad_norm": 0.4058302044868469, | |
| "learning_rate": 3.684671656182497e-06, | |
| "loss": 0.2262, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0706713780918728, | |
| "grad_norm": 0.38339221477508545, | |
| "learning_rate": 3.5847093477938955e-06, | |
| "loss": 0.2467, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07195631223899775, | |
| "grad_norm": 0.4589427411556244, | |
| "learning_rate": 3.4825625791348093e-06, | |
| "loss": 0.2348, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.07324124638612271, | |
| "grad_norm": 0.5955134034156799, | |
| "learning_rate": 3.3784370602033572e-06, | |
| "loss": 0.3195, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07452618053324767, | |
| "grad_norm": 0.492436021566391, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.2931, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.07581111468037263, | |
| "grad_norm": 0.5189871191978455, | |
| "learning_rate": 3.165092113916688e-06, | |
| "loss": 0.273, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.07709604882749758, | |
| "grad_norm": 0.5466316938400269, | |
| "learning_rate": 3.056302334890786e-06, | |
| "loss": 0.3282, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07838098297462255, | |
| "grad_norm": 0.6036167144775391, | |
| "learning_rate": 2.946392236996592e-06, | |
| "loss": 0.2782, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0796659171217475, | |
| "grad_norm": 0.600953221321106, | |
| "learning_rate": 2.835583164544139e-06, | |
| "loss": 0.2846, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.08095085126887247, | |
| "grad_norm": 0.6118208765983582, | |
| "learning_rate": 2.724098272258584e-06, | |
| "loss": 0.298, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.08223578541599744, | |
| "grad_norm": 0.5902886986732483, | |
| "learning_rate": 2.6121620758762877e-06, | |
| "loss": 0.3588, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.08352071956312239, | |
| "grad_norm": 0.5028055906295776, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.2523, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.08480565371024736, | |
| "grad_norm": 0.6613095998764038, | |
| "learning_rate": 2.3878379241237136e-06, | |
| "loss": 0.2476, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.08609058785737231, | |
| "grad_norm": 0.5534865260124207, | |
| "learning_rate": 2.2759017277414165e-06, | |
| "loss": 0.2462, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.08737552200449727, | |
| "grad_norm": 0.7256202697753906, | |
| "learning_rate": 2.1644168354558623e-06, | |
| "loss": 0.3748, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.08866045615162223, | |
| "grad_norm": 0.7539519667625427, | |
| "learning_rate": 2.053607763003409e-06, | |
| "loss": 0.3342, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0899453902987472, | |
| "grad_norm": 0.6876543760299683, | |
| "learning_rate": 1.9436976651092143e-06, | |
| "loss": 0.2865, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09123032444587215, | |
| "grad_norm": 0.7085744738578796, | |
| "learning_rate": 1.8349078860833125e-06, | |
| "loss": 0.2928, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.09251525859299711, | |
| "grad_norm": 0.6572118997573853, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.2248, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09380019274012207, | |
| "grad_norm": 0.6709907054901123, | |
| "learning_rate": 1.6215629397966432e-06, | |
| "loss": 0.3372, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.09508512688724703, | |
| "grad_norm": 0.7788072824478149, | |
| "learning_rate": 1.5174374208651913e-06, | |
| "loss": 0.3332, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.09637006103437198, | |
| "grad_norm": 0.7085012793540955, | |
| "learning_rate": 1.415290652206105e-06, | |
| "loss": 0.2757, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09765499518149695, | |
| "grad_norm": 0.8017731308937073, | |
| "learning_rate": 1.3153283438175036e-06, | |
| "loss": 0.3319, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0989399293286219, | |
| "grad_norm": 0.7940526604652405, | |
| "learning_rate": 1.217751806485235e-06, | |
| "loss": 0.3149, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.10022486347574687, | |
| "grad_norm": 0.8877953290939331, | |
| "learning_rate": 1.122757546369744e-06, | |
| "loss": 0.3214, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.10150979762287182, | |
| "grad_norm": 0.9085245728492737, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.3384, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.10279473176999679, | |
| "grad_norm": 0.7721331715583801, | |
| "learning_rate": 9.412754953531664e-07, | |
| "loss": 0.263, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10407966591712174, | |
| "grad_norm": 1.0416125059127808, | |
| "learning_rate": 8.551531851507186e-07, | |
| "loss": 0.4007, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.10536460006424671, | |
| "grad_norm": 0.8873374462127686, | |
| "learning_rate": 7.723433775328385e-07, | |
| "loss": 0.3045, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.10664953421137166, | |
| "grad_norm": 0.8218931555747986, | |
| "learning_rate": 6.930128404315214e-07, | |
| "loss": 0.2967, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.10793446835849663, | |
| "grad_norm": 0.9357181191444397, | |
| "learning_rate": 6.17321334990973e-07, | |
| "loss": 0.3382, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1092194025056216, | |
| "grad_norm": 1.129144549369812, | |
| "learning_rate": 5.454212938299256e-07, | |
| "loss": 0.3723, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.11050433665274655, | |
| "grad_norm": 0.9294447302818298, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.3518, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.11178927079987151, | |
| "grad_norm": 1.224295735359192, | |
| "learning_rate": 4.1356686569674344e-07, | |
| "loss": 0.4988, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.11307420494699646, | |
| "grad_norm": 1.0254179239273071, | |
| "learning_rate": 3.538780159953348e-07, | |
| "loss": 0.3184, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.11435913909412143, | |
| "grad_norm": 1.141256332397461, | |
| "learning_rate": 2.98511170358155e-07, | |
| "loss": 0.3678, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.11564407324124638, | |
| "grad_norm": 1.2963924407958984, | |
| "learning_rate": 2.4757783024395244e-07, | |
| "loss": 0.432, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11692900738837135, | |
| "grad_norm": 1.0066637992858887, | |
| "learning_rate": 2.0118056862137358e-07, | |
| "loss": 0.3393, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.1182139415354963, | |
| "grad_norm": 1.2111726999282837, | |
| "learning_rate": 1.59412823400657e-07, | |
| "loss": 0.4263, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.11949887568262127, | |
| "grad_norm": 1.2096489667892456, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.3961, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.12078380982974622, | |
| "grad_norm": 1.258070468902588, | |
| "learning_rate": 9.00928482603669e-08, | |
| "loss": 0.4429, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.12206874397687119, | |
| "grad_norm": 1.3796954154968262, | |
| "learning_rate": 6.268021954544095e-08, | |
| "loss": 0.3849, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.12335367812399614, | |
| "grad_norm": 1.115661382675171, | |
| "learning_rate": 4.017602850342584e-08, | |
| "loss": 0.2734, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.12463861227112111, | |
| "grad_norm": 1.1489228010177612, | |
| "learning_rate": 2.262559558016325e-08, | |
| "loss": 0.3193, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.12592354641824607, | |
| "grad_norm": 1.5417214632034302, | |
| "learning_rate": 1.006426501190233e-08, | |
| "loss": 0.4079, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.127208480565371, | |
| "grad_norm": 1.401361346244812, | |
| "learning_rate": 2.5173336467135266e-09, | |
| "loss": 0.3922, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.12849341471249598, | |
| "grad_norm": 2.738529920578003, | |
| "learning_rate": 0.0, | |
| "loss": 0.7924, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12849341471249598, | |
| "eval_loss": 0.32453402876853943, | |
| "eval_runtime": 105.3757, | |
| "eval_samples_per_second": 12.441, | |
| "eval_steps_per_second": 1.556, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5273699984801792e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |