| { | |
| "best_metric": 0.47425341606140137, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.1736111111111111, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008680555555555555, | |
| "grad_norm": 3.7586703300476074, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8273, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008680555555555555, | |
| "eval_loss": 2.105442762374878, | |
| "eval_runtime": 33.6901, | |
| "eval_samples_per_second": 57.584, | |
| "eval_steps_per_second": 14.396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001736111111111111, | |
| "grad_norm": 3.1674458980560303, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9926, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0026041666666666665, | |
| "grad_norm": 4.303656101226807, | |
| "learning_rate": 3e-05, | |
| "loss": 2.0866, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003472222222222222, | |
| "grad_norm": 3.611846923828125, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1624, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004340277777777778, | |
| "grad_norm": 3.0472545623779297, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9643, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005208333333333333, | |
| "grad_norm": 2.9491395950317383, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7744, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006076388888888889, | |
| "grad_norm": 3.180370569229126, | |
| "learning_rate": 7e-05, | |
| "loss": 1.6672, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006944444444444444, | |
| "grad_norm": 3.311208724975586, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5235, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0078125, | |
| "grad_norm": 3.2982378005981445, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3982, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008680555555555556, | |
| "grad_norm": 3.758650541305542, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3426, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009548611111111112, | |
| "grad_norm": 3.1775450706481934, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.214, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010416666666666666, | |
| "grad_norm": 2.8208556175231934, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.1415, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011284722222222222, | |
| "grad_norm": 2.4152212142944336, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.1385, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012152777777777778, | |
| "grad_norm": 2.2878611087799072, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.1721, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013020833333333334, | |
| "grad_norm": 1.8518415689468384, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.1229, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013888888888888888, | |
| "grad_norm": 1.716903805732727, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.066, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014756944444444444, | |
| "grad_norm": 1.7045224905014038, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.9593, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015625, | |
| "grad_norm": 1.8572195768356323, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.0787, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016493055555555556, | |
| "grad_norm": 1.4604061841964722, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.0051, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.017361111111111112, | |
| "grad_norm": 1.7314320802688599, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.0643, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018229166666666668, | |
| "grad_norm": 1.4772697687149048, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.0238, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019097222222222224, | |
| "grad_norm": 1.3212639093399048, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.877, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.019965277777777776, | |
| "grad_norm": 1.3424663543701172, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.9632, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.020833333333333332, | |
| "grad_norm": 1.2182601690292358, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.8376, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.021701388888888888, | |
| "grad_norm": 1.0654693841934204, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.7583, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022569444444444444, | |
| "grad_norm": 1.3452422618865967, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.9343, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0234375, | |
| "grad_norm": 1.2998955249786377, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.8537, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.024305555555555556, | |
| "grad_norm": 1.5102040767669678, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.8419, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.025173611111111112, | |
| "grad_norm": 1.1616286039352417, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.7627, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.026041666666666668, | |
| "grad_norm": 1.220555067062378, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.815, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.026909722222222224, | |
| "grad_norm": 1.2631940841674805, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.8008, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "grad_norm": 1.1802059412002563, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.7938, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.028645833333333332, | |
| "grad_norm": 1.2273606061935425, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.7889, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.029513888888888888, | |
| "grad_norm": 1.2379533052444458, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.7535, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.030381944444444444, | |
| "grad_norm": 1.180274248123169, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.7507, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03125, | |
| "grad_norm": 1.2396448850631714, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.7136, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03211805555555555, | |
| "grad_norm": 1.307834267616272, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.7206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03298611111111111, | |
| "grad_norm": 1.343642234802246, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.7286, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.033854166666666664, | |
| "grad_norm": 1.2396036386489868, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.6148, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.034722222222222224, | |
| "grad_norm": 1.1274713277816772, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.6235, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.035590277777777776, | |
| "grad_norm": 1.1663782596588135, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.5883, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.036458333333333336, | |
| "grad_norm": 1.2625908851623535, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.6196, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03732638888888889, | |
| "grad_norm": 1.2862653732299805, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.6243, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03819444444444445, | |
| "grad_norm": 1.5083249807357788, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.6284, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0390625, | |
| "grad_norm": 1.5108219385147095, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.5845, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03993055555555555, | |
| "grad_norm": 1.6352540254592896, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.7316, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04079861111111111, | |
| "grad_norm": 2.937321186065674, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.9716, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.041666666666666664, | |
| "grad_norm": 2.7645087242126465, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.9336, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.042534722222222224, | |
| "grad_norm": 2.979653835296631, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 1.0183, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.043402777777777776, | |
| "grad_norm": 3.2009198665618896, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.0273, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.043402777777777776, | |
| "eval_loss": 0.8885940313339233, | |
| "eval_runtime": 33.637, | |
| "eval_samples_per_second": 57.675, | |
| "eval_steps_per_second": 14.419, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.044270833333333336, | |
| "grad_norm": 6.456084251403809, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 1.8316, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04513888888888889, | |
| "grad_norm": 4.288782119750977, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 1.6296, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04600694444444445, | |
| "grad_norm": 3.24642014503479, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 1.414, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.046875, | |
| "grad_norm": 2.601104497909546, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 1.4343, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04774305555555555, | |
| "grad_norm": 1.8146635293960571, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 1.1515, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04861111111111111, | |
| "grad_norm": 1.755637764930725, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 1.0007, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.049479166666666664, | |
| "grad_norm": 1.7022700309753418, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.9395, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.050347222222222224, | |
| "grad_norm": 1.5965139865875244, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.8832, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.051215277777777776, | |
| "grad_norm": 1.5245304107666016, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.7738, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.052083333333333336, | |
| "grad_norm": 1.6449687480926514, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.7855, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05295138888888889, | |
| "grad_norm": 1.399305820465088, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.6629, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05381944444444445, | |
| "grad_norm": 1.4465663433074951, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.7728, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0546875, | |
| "grad_norm": 1.242693543434143, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.7214, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 1.3179938793182373, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.7382, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05642361111111111, | |
| "grad_norm": 1.2749793529510498, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.7738, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.057291666666666664, | |
| "grad_norm": 1.1451467275619507, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.6538, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.058159722222222224, | |
| "grad_norm": 1.1956616640090942, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.8066, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.059027777777777776, | |
| "grad_norm": 1.022029161453247, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.6577, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.059895833333333336, | |
| "grad_norm": 0.965019166469574, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.636, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.06076388888888889, | |
| "grad_norm": 0.9661323428153992, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.6429, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06163194444444445, | |
| "grad_norm": 0.9548866152763367, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.6221, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.8804452419281006, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.5963, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06336805555555555, | |
| "grad_norm": 0.8252166509628296, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.5927, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0642361111111111, | |
| "grad_norm": 0.8140515685081482, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.5707, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06510416666666667, | |
| "grad_norm": 0.8823627233505249, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.5738, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06597222222222222, | |
| "grad_norm": 0.9068223237991333, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.5964, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.06684027777777778, | |
| "grad_norm": 0.9282422661781311, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.5758, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.06770833333333333, | |
| "grad_norm": 0.923147976398468, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.5366, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0685763888888889, | |
| "grad_norm": 0.8402060270309448, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.5203, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.06944444444444445, | |
| "grad_norm": 0.9093599319458008, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.5539, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0703125, | |
| "grad_norm": 0.9284139275550842, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.5022, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.07118055555555555, | |
| "grad_norm": 0.8983213305473328, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.5395, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0720486111111111, | |
| "grad_norm": 0.9012270569801331, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.52, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.07291666666666667, | |
| "grad_norm": 1.0759103298187256, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.4413, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.07378472222222222, | |
| "grad_norm": 0.8890159726142883, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.4661, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.07465277777777778, | |
| "grad_norm": 0.9476726055145264, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.5134, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.07552083333333333, | |
| "grad_norm": 0.9966571927070618, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.4999, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0763888888888889, | |
| "grad_norm": 0.9323421716690063, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.4746, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.07725694444444445, | |
| "grad_norm": 1.0732293128967285, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.459, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.078125, | |
| "grad_norm": 0.9883078336715698, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.4358, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07899305555555555, | |
| "grad_norm": 1.0474294424057007, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.4618, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0798611111111111, | |
| "grad_norm": 0.9766831994056702, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.4572, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.08072916666666667, | |
| "grad_norm": 1.0797269344329834, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.525, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.08159722222222222, | |
| "grad_norm": 0.9671390056610107, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.4436, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.08246527777777778, | |
| "grad_norm": 1.0156289339065552, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.4855, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 1.0827502012252808, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.49, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.0842013888888889, | |
| "grad_norm": 1.5371901988983154, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.5909, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.08506944444444445, | |
| "grad_norm": 1.998530387878418, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.6505, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0859375, | |
| "grad_norm": 1.8727068901062012, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.6312, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.08680555555555555, | |
| "grad_norm": 2.3722784519195557, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.6095, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08680555555555555, | |
| "eval_loss": 0.688700795173645, | |
| "eval_runtime": 33.6831, | |
| "eval_samples_per_second": 57.596, | |
| "eval_steps_per_second": 14.399, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0876736111111111, | |
| "grad_norm": 5.118232250213623, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 1.4222, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.08854166666666667, | |
| "grad_norm": 3.706031084060669, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 1.2231, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.08940972222222222, | |
| "grad_norm": 3.153409719467163, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 1.1504, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.09027777777777778, | |
| "grad_norm": 2.429748773574829, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 1.0779, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.09114583333333333, | |
| "grad_norm": 2.1256322860717773, | |
| "learning_rate": 5e-05, | |
| "loss": 0.886, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.0920138888888889, | |
| "grad_norm": 1.98789644241333, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.7669, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.09288194444444445, | |
| "grad_norm": 1.5516505241394043, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 0.6996, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 1.5301878452301025, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.6199, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.09461805555555555, | |
| "grad_norm": 1.5088517665863037, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 0.6105, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.0954861111111111, | |
| "grad_norm": 1.4736902713775635, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.5944, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09635416666666667, | |
| "grad_norm": 1.251574158668518, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 0.6094, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.09722222222222222, | |
| "grad_norm": 1.304919958114624, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.627, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.09809027777777778, | |
| "grad_norm": 1.2010833024978638, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 0.6006, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.09895833333333333, | |
| "grad_norm": 1.1784776449203491, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.6402, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.0998263888888889, | |
| "grad_norm": 1.1817885637283325, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.5687, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.10069444444444445, | |
| "grad_norm": 0.9305168986320496, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.5628, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.1015625, | |
| "grad_norm": 0.9683446884155273, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 0.5664, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.10243055555555555, | |
| "grad_norm": 0.9450289607048035, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.538, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.1032986111111111, | |
| "grad_norm": 0.9733933210372925, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 0.5555, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "grad_norm": 0.7670676112174988, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.4893, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10503472222222222, | |
| "grad_norm": 0.8021773099899292, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 0.4855, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.10590277777777778, | |
| "grad_norm": 0.8285829424858093, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.4965, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.10677083333333333, | |
| "grad_norm": 0.7743699550628662, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 0.4728, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.1076388888888889, | |
| "grad_norm": 0.8068888783454895, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.4915, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.10850694444444445, | |
| "grad_norm": 0.9645229578018188, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.5565, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.109375, | |
| "grad_norm": 0.8263698816299438, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.5079, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.11024305555555555, | |
| "grad_norm": 0.8237981796264648, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 0.5212, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.8913101553916931, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.489, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.11197916666666667, | |
| "grad_norm": 0.7909724712371826, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 0.4411, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.11284722222222222, | |
| "grad_norm": 0.8449598550796509, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.4894, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11371527777777778, | |
| "grad_norm": 0.7651047110557556, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 0.4711, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.11458333333333333, | |
| "grad_norm": 0.731490433216095, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.4462, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.1154513888888889, | |
| "grad_norm": 0.7811890840530396, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 0.4137, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.11631944444444445, | |
| "grad_norm": 0.8106331825256348, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.432, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.1171875, | |
| "grad_norm": 0.7604708671569824, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.3917, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.11805555555555555, | |
| "grad_norm": 0.8251763582229614, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.4248, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.1189236111111111, | |
| "grad_norm": 0.788393497467041, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 0.3887, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.11979166666666667, | |
| "grad_norm": 0.8035151362419128, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.3985, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.12065972222222222, | |
| "grad_norm": 0.8012828230857849, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 0.4245, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.12152777777777778, | |
| "grad_norm": 0.8701144456863403, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.4004, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12239583333333333, | |
| "grad_norm": 0.8174064755439758, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 0.3884, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.1232638888888889, | |
| "grad_norm": 0.871465265750885, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.4317, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.12413194444444445, | |
| "grad_norm": 0.8454309105873108, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.4032, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.9313730001449585, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.4529, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.12586805555555555, | |
| "grad_norm": 1.333052396774292, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.5374, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.1267361111111111, | |
| "grad_norm": 1.2165260314941406, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.4878, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.12760416666666666, | |
| "grad_norm": 1.5397956371307373, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 0.5069, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.1284722222222222, | |
| "grad_norm": 1.6286752223968506, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.4962, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.1293402777777778, | |
| "grad_norm": 1.4014798402786255, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 0.4579, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.13020833333333334, | |
| "grad_norm": 1.5754759311676025, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.5774, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13020833333333334, | |
| "eval_loss": 0.5275475382804871, | |
| "eval_runtime": 33.7924, | |
| "eval_samples_per_second": 57.409, | |
| "eval_steps_per_second": 14.352, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1310763888888889, | |
| "grad_norm": 2.40449857711792, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 1.0037, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.13194444444444445, | |
| "grad_norm": 1.9176386594772339, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 0.9472, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.1328125, | |
| "grad_norm": 1.9148679971694946, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 0.8323, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.13368055555555555, | |
| "grad_norm": 1.8058258295059204, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.8515, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.1345486111111111, | |
| "grad_norm": 1.8391540050506592, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.7764, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.13541666666666666, | |
| "grad_norm": 1.7676095962524414, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.7057, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.1362847222222222, | |
| "grad_norm": 1.6236857175827026, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 0.5863, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.1371527777777778, | |
| "grad_norm": 1.507211685180664, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.566, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.13802083333333334, | |
| "grad_norm": 2.5461390018463135, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 0.591, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "grad_norm": 2.094942569732666, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.5695, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13975694444444445, | |
| "grad_norm": 1.6320278644561768, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 0.5514, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.140625, | |
| "grad_norm": 1.6330500841140747, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.516, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.14149305555555555, | |
| "grad_norm": 1.2982337474822998, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 0.4979, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.1423611111111111, | |
| "grad_norm": 1.1797913312911987, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.5412, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.14322916666666666, | |
| "grad_norm": 1.2599879503250122, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.5735, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.1440972222222222, | |
| "grad_norm": 1.167892336845398, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.4817, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.1449652777777778, | |
| "grad_norm": 0.9992820620536804, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 0.449, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.14583333333333334, | |
| "grad_norm": 0.9512782692909241, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.4629, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.1467013888888889, | |
| "grad_norm": 0.9919994473457336, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 0.4487, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.14756944444444445, | |
| "grad_norm": 0.9102839827537537, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.4748, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1484375, | |
| "grad_norm": 0.8750783205032349, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 0.4575, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.14930555555555555, | |
| "grad_norm": 0.8381144404411316, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.4604, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.1501736111111111, | |
| "grad_norm": 0.8436367511749268, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 0.4166, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.15104166666666666, | |
| "grad_norm": 0.830169677734375, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.4301, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.1519097222222222, | |
| "grad_norm": 0.8524389266967773, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.4448, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1527777777777778, | |
| "grad_norm": 0.9152529239654541, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 0.4638, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.15364583333333334, | |
| "grad_norm": 0.8847336173057556, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 0.4604, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.1545138888888889, | |
| "grad_norm": 0.8971191644668579, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 0.4751, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.15538194444444445, | |
| "grad_norm": 0.8379711508750916, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 0.4655, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 0.822320282459259, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.4227, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.15711805555555555, | |
| "grad_norm": 0.8396154642105103, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.4205, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.1579861111111111, | |
| "grad_norm": 0.8803654909133911, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.4138, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.15885416666666666, | |
| "grad_norm": 0.8425192832946777, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 0.4189, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.1597222222222222, | |
| "grad_norm": 0.801551342010498, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.3918, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.1605902777777778, | |
| "grad_norm": 0.8335273265838623, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.4153, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.16145833333333334, | |
| "grad_norm": 0.8369459509849548, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.396, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.1623263888888889, | |
| "grad_norm": 0.8201226592063904, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 0.3597, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.16319444444444445, | |
| "grad_norm": 0.8360642194747925, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.3973, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.1640625, | |
| "grad_norm": 0.888002872467041, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 0.3941, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.16493055555555555, | |
| "grad_norm": 0.8810456991195679, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.4305, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1657986111111111, | |
| "grad_norm": 0.8414878845214844, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 0.4195, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.9335379004478455, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.4141, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.1675347222222222, | |
| "grad_norm": 0.863761305809021, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 0.4181, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.1684027777777778, | |
| "grad_norm": 0.8671419024467468, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.4068, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.16927083333333334, | |
| "grad_norm": 0.9308309555053711, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.4263, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.1701388888888889, | |
| "grad_norm": 0.9095333814620972, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.4436, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.17100694444444445, | |
| "grad_norm": 0.9374375343322754, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 0.427, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.171875, | |
| "grad_norm": 1.117672324180603, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.4335, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.17274305555555555, | |
| "grad_norm": 1.2056872844696045, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 0.4124, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.1736111111111111, | |
| "grad_norm": 1.3249119520187378, | |
| "learning_rate": 0.0, | |
| "loss": 0.5252, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1736111111111111, | |
| "eval_loss": 0.47425341606140137, | |
| "eval_runtime": 33.7434, | |
| "eval_samples_per_second": 57.493, | |
| "eval_steps_per_second": 14.373, | |
| "step": 200 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.54569648635904e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |