| { | |
| "best_metric": 2.4403305053710938, | |
| "best_model_checkpoint": "QaagiFilter5/checkpoint-5660", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 5660, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.044169611307420496, | |
| "grad_norm": 172.7814178466797, | |
| "learning_rate": 1.678445229681979e-06, | |
| "loss": 26.1479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08833922261484099, | |
| "grad_norm": 166.59046936035156, | |
| "learning_rate": 3.886925795053004e-06, | |
| "loss": 23.212, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13250883392226148, | |
| "grad_norm": 128.4106903076172, | |
| "learning_rate": 6.095406360424029e-06, | |
| "loss": 18.6127, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.17667844522968199, | |
| "grad_norm": 92.6707534790039, | |
| "learning_rate": 8.303886925795053e-06, | |
| "loss": 11.4991, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22084805653710246, | |
| "grad_norm": 27.35597801208496, | |
| "learning_rate": 1.0512367491166077e-05, | |
| "loss": 7.0239, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.26501766784452296, | |
| "grad_norm": 71.67853546142578, | |
| "learning_rate": 1.2720848056537101e-05, | |
| "loss": 5.5043, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.30918727915194344, | |
| "grad_norm": 37.85909652709961, | |
| "learning_rate": 1.4929328621908128e-05, | |
| "loss": 4.803, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.35335689045936397, | |
| "grad_norm": 73.24124908447266, | |
| "learning_rate": 1.7137809187279152e-05, | |
| "loss": 4.7082, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.39752650176678445, | |
| "grad_norm": 67.75065612792969, | |
| "learning_rate": 1.9346289752650175e-05, | |
| "loss": 4.2305, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.4416961130742049, | |
| "grad_norm": 38.89707565307617, | |
| "learning_rate": 2.1554770318021204e-05, | |
| "loss": 3.3087, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.48586572438162545, | |
| "grad_norm": 46.586524963378906, | |
| "learning_rate": 2.3763250883392226e-05, | |
| "loss": 4.019, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5300353356890459, | |
| "grad_norm": 41.0096435546875, | |
| "learning_rate": 2.5971731448763255e-05, | |
| "loss": 3.8054, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5742049469964664, | |
| "grad_norm": 73.49757385253906, | |
| "learning_rate": 2.8180212014134277e-05, | |
| "loss": 3.6329, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.6183745583038869, | |
| "grad_norm": 62.597286224365234, | |
| "learning_rate": 3.03886925795053e-05, | |
| "loss": 3.6779, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6625441696113075, | |
| "grad_norm": 35.01760482788086, | |
| "learning_rate": 3.2597173144876325e-05, | |
| "loss": 3.808, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.7067137809187279, | |
| "grad_norm": 33.265625, | |
| "learning_rate": 3.480565371024735e-05, | |
| "loss": 3.2528, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7508833922261484, | |
| "grad_norm": 41.54469299316406, | |
| "learning_rate": 3.7014134275618377e-05, | |
| "loss": 3.3373, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.7950530035335689, | |
| "grad_norm": 59.207889556884766, | |
| "learning_rate": 3.9222614840989406e-05, | |
| "loss": 2.716, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8392226148409894, | |
| "grad_norm": 37.75099182128906, | |
| "learning_rate": 4.143109540636043e-05, | |
| "loss": 3.174, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.8833922261484098, | |
| "grad_norm": 44.53806686401367, | |
| "learning_rate": 4.363957597173145e-05, | |
| "loss": 3.6122, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9275618374558304, | |
| "grad_norm": 36.89043426513672, | |
| "learning_rate": 4.584805653710247e-05, | |
| "loss": 3.0317, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.9717314487632509, | |
| "grad_norm": 75.27375030517578, | |
| "learning_rate": 4.8056537102473495e-05, | |
| "loss": 2.3758, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_explained_variance": 0.5094610452651978, | |
| "eval_loss": 3.465508222579956, | |
| "eval_mae": 1.3762876987457275, | |
| "eval_mse": 3.4517085552215576, | |
| "eval_r2": 0.4398180842399597, | |
| "eval_rmse": 1.8578773736953735, | |
| "eval_runtime": 1.0216, | |
| "eval_samples_per_second": 2215.123, | |
| "eval_steps_per_second": 69.498, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.0159010600706713, | |
| "grad_norm": 26.423126220703125, | |
| "learning_rate": 4.997055359246172e-05, | |
| "loss": 2.7841, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.0600706713780919, | |
| "grad_norm": 69.90520477294922, | |
| "learning_rate": 4.9725166862976055e-05, | |
| "loss": 2.1612, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.1042402826855124, | |
| "grad_norm": 33.07378387451172, | |
| "learning_rate": 4.9479780133490385e-05, | |
| "loss": 2.48, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.1484098939929328, | |
| "grad_norm": 17.648529052734375, | |
| "learning_rate": 4.9234393404004716e-05, | |
| "loss": 2.0749, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.1925795053003534, | |
| "grad_norm": 53.43230438232422, | |
| "learning_rate": 4.8989006674519046e-05, | |
| "loss": 2.1101, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.2367491166077738, | |
| "grad_norm": 35.27627944946289, | |
| "learning_rate": 4.8743619945033376e-05, | |
| "loss": 2.2126, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.2809187279151943, | |
| "grad_norm": 50.328914642333984, | |
| "learning_rate": 4.8498233215547706e-05, | |
| "loss": 2.0551, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.325088339222615, | |
| "grad_norm": 52.285911560058594, | |
| "learning_rate": 4.8252846486062036e-05, | |
| "loss": 1.9554, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.3692579505300353, | |
| "grad_norm": 43.46308135986328, | |
| "learning_rate": 4.8007459756576366e-05, | |
| "loss": 2.3065, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.4134275618374559, | |
| "grad_norm": 50.10768508911133, | |
| "learning_rate": 4.7762073027090696e-05, | |
| "loss": 2.2778, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.4575971731448762, | |
| "grad_norm": 32.7845344543457, | |
| "learning_rate": 4.7516686297605026e-05, | |
| "loss": 2.0533, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.5017667844522968, | |
| "grad_norm": 24.879047393798828, | |
| "learning_rate": 4.7271299568119356e-05, | |
| "loss": 2.1411, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.5459363957597172, | |
| "grad_norm": 44.34259796142578, | |
| "learning_rate": 4.702591283863369e-05, | |
| "loss": 2.2567, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.5901060070671378, | |
| "grad_norm": 59.14316940307617, | |
| "learning_rate": 4.6780526109148023e-05, | |
| "loss": 1.8269, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.6342756183745584, | |
| "grad_norm": 41.258827209472656, | |
| "learning_rate": 4.6535139379662354e-05, | |
| "loss": 2.0853, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.6784452296819787, | |
| "grad_norm": 22.546058654785156, | |
| "learning_rate": 4.6289752650176684e-05, | |
| "loss": 2.1658, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.7226148409893993, | |
| "grad_norm": 52.796470642089844, | |
| "learning_rate": 4.6044365920691014e-05, | |
| "loss": 2.367, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.76678445229682, | |
| "grad_norm": 29.541540145874023, | |
| "learning_rate": 4.5798979191205344e-05, | |
| "loss": 2.1246, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.8109540636042403, | |
| "grad_norm": 40.63389587402344, | |
| "learning_rate": 4.5553592461719674e-05, | |
| "loss": 2.0685, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.8551236749116606, | |
| "grad_norm": 34.64159393310547, | |
| "learning_rate": 4.5308205732234004e-05, | |
| "loss": 2.1979, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.8992932862190812, | |
| "grad_norm": 27.459083557128906, | |
| "learning_rate": 4.5062819002748334e-05, | |
| "loss": 1.9735, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.9434628975265018, | |
| "grad_norm": 25.363712310791016, | |
| "learning_rate": 4.4817432273262664e-05, | |
| "loss": 2.0339, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.9876325088339222, | |
| "grad_norm": 45.697757720947266, | |
| "learning_rate": 4.4572045543776994e-05, | |
| "loss": 1.967, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_explained_variance": 0.5648437142372131, | |
| "eval_loss": 3.2432901859283447, | |
| "eval_mae": 1.3005132675170898, | |
| "eval_mse": 3.227083444595337, | |
| "eval_r2": 0.4762727618217468, | |
| "eval_rmse": 1.7964085340499878, | |
| "eval_runtime": 1.0461, | |
| "eval_samples_per_second": 2163.35, | |
| "eval_steps_per_second": 67.874, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 2.0318021201413425, | |
| "grad_norm": 44.7116813659668, | |
| "learning_rate": 4.4326658814291324e-05, | |
| "loss": 1.2539, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.0759717314487633, | |
| "grad_norm": 25.487625122070312, | |
| "learning_rate": 4.408127208480566e-05, | |
| "loss": 1.1147, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.1201413427561837, | |
| "grad_norm": 27.024295806884766, | |
| "learning_rate": 4.383588535531999e-05, | |
| "loss": 0.8406, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.164310954063604, | |
| "grad_norm": 21.068811416625977, | |
| "learning_rate": 4.359049862583432e-05, | |
| "loss": 1.0608, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.208480565371025, | |
| "grad_norm": 17.862035751342773, | |
| "learning_rate": 4.334511189634865e-05, | |
| "loss": 1.1741, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.2526501766784452, | |
| "grad_norm": 44.87358856201172, | |
| "learning_rate": 4.3099725166862975e-05, | |
| "loss": 0.8678, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.2968197879858656, | |
| "grad_norm": 28.953048706054688, | |
| "learning_rate": 4.2854338437377305e-05, | |
| "loss": 0.8326, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.340989399293286, | |
| "grad_norm": 32.61209487915039, | |
| "learning_rate": 4.2608951707891635e-05, | |
| "loss": 0.9226, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.385159010600707, | |
| "grad_norm": 24.571086883544922, | |
| "learning_rate": 4.2363564978405965e-05, | |
| "loss": 0.8819, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.429328621908127, | |
| "grad_norm": 23.368595123291016, | |
| "learning_rate": 4.2118178248920295e-05, | |
| "loss": 0.8845, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 2.4734982332155475, | |
| "grad_norm": 35.36629867553711, | |
| "learning_rate": 4.1872791519434626e-05, | |
| "loss": 1.0751, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.5176678445229683, | |
| "grad_norm": 15.506020545959473, | |
| "learning_rate": 4.162740478994896e-05, | |
| "loss": 0.933, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 2.5618374558303887, | |
| "grad_norm": 40.057884216308594, | |
| "learning_rate": 4.138201806046329e-05, | |
| "loss": 0.9503, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.606007067137809, | |
| "grad_norm": 20.372051239013672, | |
| "learning_rate": 4.113663133097762e-05, | |
| "loss": 0.8741, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 2.65017667844523, | |
| "grad_norm": 10.090834617614746, | |
| "learning_rate": 4.089124460149195e-05, | |
| "loss": 0.9391, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.6943462897526502, | |
| "grad_norm": 14.696582794189453, | |
| "learning_rate": 4.064585787200628e-05, | |
| "loss": 0.9666, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 2.7385159010600706, | |
| "grad_norm": 31.863920211791992, | |
| "learning_rate": 4.040047114252061e-05, | |
| "loss": 1.0567, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.7826855123674914, | |
| "grad_norm": 36.8994255065918, | |
| "learning_rate": 4.015508441303494e-05, | |
| "loss": 1.0003, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 2.8268551236749118, | |
| "grad_norm": 21.43227195739746, | |
| "learning_rate": 3.990969768354927e-05, | |
| "loss": 1.0532, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.871024734982332, | |
| "grad_norm": 35.63019561767578, | |
| "learning_rate": 3.96643109540636e-05, | |
| "loss": 0.8816, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 2.9151943462897525, | |
| "grad_norm": 9.274225234985352, | |
| "learning_rate": 3.941892422457793e-05, | |
| "loss": 1.0889, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.9593639575971733, | |
| "grad_norm": 22.54602813720703, | |
| "learning_rate": 3.9173537495092263e-05, | |
| "loss": 0.9442, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_explained_variance": 0.5853231549263, | |
| "eval_loss": 2.897214651107788, | |
| "eval_mae": 1.210811972618103, | |
| "eval_mse": 2.8827266693115234, | |
| "eval_r2": 0.5321588516235352, | |
| "eval_rmse": 1.6978594064712524, | |
| "eval_runtime": 1.0405, | |
| "eval_samples_per_second": 2174.844, | |
| "eval_steps_per_second": 68.234, | |
| "step": 1698 | |
| }, | |
| { | |
| "epoch": 3.0035335689045937, | |
| "grad_norm": 20.036935806274414, | |
| "learning_rate": 3.8928150765606594e-05, | |
| "loss": 0.9184, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.047703180212014, | |
| "grad_norm": 34.86088180541992, | |
| "learning_rate": 3.868276403612093e-05, | |
| "loss": 0.5967, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 3.091872791519435, | |
| "grad_norm": 19.049938201904297, | |
| "learning_rate": 3.843737730663526e-05, | |
| "loss": 0.5294, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 3.136042402826855, | |
| "grad_norm": 12.164793014526367, | |
| "learning_rate": 3.819199057714959e-05, | |
| "loss": 0.6298, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 3.1802120141342756, | |
| "grad_norm": 34.6705207824707, | |
| "learning_rate": 3.794660384766392e-05, | |
| "loss": 0.6278, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.224381625441696, | |
| "grad_norm": 14.351198196411133, | |
| "learning_rate": 3.770121711817825e-05, | |
| "loss": 0.5648, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 3.2685512367491167, | |
| "grad_norm": 30.73033905029297, | |
| "learning_rate": 3.745583038869258e-05, | |
| "loss": 0.6436, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 3.312720848056537, | |
| "grad_norm": 22.45409393310547, | |
| "learning_rate": 3.721044365920691e-05, | |
| "loss": 0.6032, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 3.3568904593639575, | |
| "grad_norm": 12.688070297241211, | |
| "learning_rate": 3.696505692972124e-05, | |
| "loss": 0.6173, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.4010600706713783, | |
| "grad_norm": 21.9694766998291, | |
| "learning_rate": 3.671967020023557e-05, | |
| "loss": 0.515, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 3.4452296819787986, | |
| "grad_norm": 11.734025001525879, | |
| "learning_rate": 3.64742834707499e-05, | |
| "loss": 0.5558, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.489399293286219, | |
| "grad_norm": 22.58125877380371, | |
| "learning_rate": 3.622889674126423e-05, | |
| "loss": 0.5682, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 3.53356890459364, | |
| "grad_norm": 19.323246002197266, | |
| "learning_rate": 3.598351001177857e-05, | |
| "loss": 0.5542, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.57773851590106, | |
| "grad_norm": 18.396697998046875, | |
| "learning_rate": 3.57381232822929e-05, | |
| "loss": 0.6233, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 3.6219081272084805, | |
| "grad_norm": 29.500776290893555, | |
| "learning_rate": 3.549273655280723e-05, | |
| "loss": 0.6947, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 3.666077738515901, | |
| "grad_norm": 14.776251792907715, | |
| "learning_rate": 3.524734982332156e-05, | |
| "loss": 0.5729, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 3.7102473498233217, | |
| "grad_norm": 30.837646484375, | |
| "learning_rate": 3.500196309383589e-05, | |
| "loss": 0.669, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.754416961130742, | |
| "grad_norm": 22.036334991455078, | |
| "learning_rate": 3.475657636435022e-05, | |
| "loss": 0.5365, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 3.7985865724381624, | |
| "grad_norm": 7.9163079261779785, | |
| "learning_rate": 3.451118963486455e-05, | |
| "loss": 0.548, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 3.842756183745583, | |
| "grad_norm": 27.34328842163086, | |
| "learning_rate": 3.426580290537888e-05, | |
| "loss": 0.5585, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 3.8869257950530036, | |
| "grad_norm": 20.00174903869629, | |
| "learning_rate": 3.402041617589321e-05, | |
| "loss": 0.6514, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.931095406360424, | |
| "grad_norm": 15.843454360961914, | |
| "learning_rate": 3.377502944640754e-05, | |
| "loss": 0.6258, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 3.9752650176678443, | |
| "grad_norm": 31.284502029418945, | |
| "learning_rate": 3.352964271692187e-05, | |
| "loss": 0.5995, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_explained_variance": 0.6056773662567139, | |
| "eval_loss": 2.727660655975342, | |
| "eval_mae": 1.1792982816696167, | |
| "eval_mse": 2.715883255004883, | |
| "eval_r2": 0.5592360496520996, | |
| "eval_rmse": 1.6479936838150024, | |
| "eval_runtime": 1.0286, | |
| "eval_samples_per_second": 2200.076, | |
| "eval_steps_per_second": 69.026, | |
| "step": 2264 | |
| }, | |
| { | |
| "epoch": 4.019434628975265, | |
| "grad_norm": 15.487521171569824, | |
| "learning_rate": 3.32842559874362e-05, | |
| "loss": 0.5058, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 4.063604240282685, | |
| "grad_norm": 8.639957427978516, | |
| "learning_rate": 3.3038869257950536e-05, | |
| "loss": 0.4803, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 4.107773851590106, | |
| "grad_norm": 7.802794456481934, | |
| "learning_rate": 3.2793482528464867e-05, | |
| "loss": 0.351, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 4.151943462897527, | |
| "grad_norm": 10.31377124786377, | |
| "learning_rate": 3.25480957989792e-05, | |
| "loss": 0.453, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 4.196113074204947, | |
| "grad_norm": 18.428464889526367, | |
| "learning_rate": 3.230270906949353e-05, | |
| "loss": 0.4612, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 4.240282685512367, | |
| "grad_norm": 15.8595609664917, | |
| "learning_rate": 3.205732234000786e-05, | |
| "loss": 0.3915, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.284452296819788, | |
| "grad_norm": 17.2500057220459, | |
| "learning_rate": 3.181193561052219e-05, | |
| "loss": 0.3635, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 4.328621908127208, | |
| "grad_norm": 13.921929359436035, | |
| "learning_rate": 3.156654888103652e-05, | |
| "loss": 0.3373, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 4.372791519434629, | |
| "grad_norm": 14.69737434387207, | |
| "learning_rate": 3.132116215155085e-05, | |
| "loss": 0.4055, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 4.41696113074205, | |
| "grad_norm": 23.352657318115234, | |
| "learning_rate": 3.107577542206518e-05, | |
| "loss": 0.4435, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.46113074204947, | |
| "grad_norm": 10.377140045166016, | |
| "learning_rate": 3.083038869257951e-05, | |
| "loss": 0.3323, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 4.5053003533568905, | |
| "grad_norm": 9.900633811950684, | |
| "learning_rate": 3.058500196309384e-05, | |
| "loss": 0.3799, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 4.549469964664311, | |
| "grad_norm": 11.127573013305664, | |
| "learning_rate": 3.0339615233608164e-05, | |
| "loss": 0.3736, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 4.593639575971731, | |
| "grad_norm": 16.36042594909668, | |
| "learning_rate": 3.0094228504122494e-05, | |
| "loss": 0.4345, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.637809187279152, | |
| "grad_norm": 25.30819320678711, | |
| "learning_rate": 2.9848841774636828e-05, | |
| "loss": 0.3901, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 4.681978798586572, | |
| "grad_norm": 23.80220603942871, | |
| "learning_rate": 2.9603455045151158e-05, | |
| "loss": 0.4355, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 4.726148409893993, | |
| "grad_norm": 11.138365745544434, | |
| "learning_rate": 2.9358068315665488e-05, | |
| "loss": 0.3541, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 4.770318021201414, | |
| "grad_norm": 20.883947372436523, | |
| "learning_rate": 2.9112681586179818e-05, | |
| "loss": 0.3744, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.814487632508834, | |
| "grad_norm": 8.56249713897705, | |
| "learning_rate": 2.8867294856694148e-05, | |
| "loss": 0.3599, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 4.858657243816254, | |
| "grad_norm": 20.723438262939453, | |
| "learning_rate": 2.862190812720848e-05, | |
| "loss": 0.4961, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 4.902826855123675, | |
| "grad_norm": 10.906144142150879, | |
| "learning_rate": 2.8376521397722812e-05, | |
| "loss": 0.3921, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 4.946996466431095, | |
| "grad_norm": 10.464198112487793, | |
| "learning_rate": 2.8131134668237142e-05, | |
| "loss": 0.3569, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.991166077738516, | |
| "grad_norm": 60.609703063964844, | |
| "learning_rate": 2.7885747938751472e-05, | |
| "loss": 0.4576, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_explained_variance": 0.6176950931549072, | |
| "eval_loss": 2.477543830871582, | |
| "eval_mae": 1.134692907333374, | |
| "eval_mse": 2.467003345489502, | |
| "eval_r2": 0.5996270179748535, | |
| "eval_rmse": 1.5706697702407837, | |
| "eval_runtime": 1.0254, | |
| "eval_samples_per_second": 2206.885, | |
| "eval_steps_per_second": 69.239, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 5.035335689045937, | |
| "grad_norm": 15.79285717010498, | |
| "learning_rate": 2.7640361209265802e-05, | |
| "loss": 0.3458, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 5.079505300353357, | |
| "grad_norm": 9.123896598815918, | |
| "learning_rate": 2.7394974479780132e-05, | |
| "loss": 0.2756, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 5.123674911660777, | |
| "grad_norm": 10.223502159118652, | |
| "learning_rate": 2.7149587750294462e-05, | |
| "loss": 0.2661, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 5.167844522968198, | |
| "grad_norm": 15.297872543334961, | |
| "learning_rate": 2.6904201020808796e-05, | |
| "loss": 0.2333, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 5.212014134275618, | |
| "grad_norm": 6.982729911804199, | |
| "learning_rate": 2.6658814291323126e-05, | |
| "loss": 0.2596, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 5.256183745583039, | |
| "grad_norm": 14.569358825683594, | |
| "learning_rate": 2.6413427561837456e-05, | |
| "loss": 0.2551, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 5.30035335689046, | |
| "grad_norm": 10.034513473510742, | |
| "learning_rate": 2.6168040832351786e-05, | |
| "loss": 0.2628, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.34452296819788, | |
| "grad_norm": 10.558284759521484, | |
| "learning_rate": 2.5922654102866116e-05, | |
| "loss": 0.2863, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 5.3886925795053005, | |
| "grad_norm": 16.27973747253418, | |
| "learning_rate": 2.5677267373380446e-05, | |
| "loss": 0.2675, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 5.432862190812721, | |
| "grad_norm": 14.27253532409668, | |
| "learning_rate": 2.543188064389478e-05, | |
| "loss": 0.283, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 5.477031802120141, | |
| "grad_norm": 19.350168228149414, | |
| "learning_rate": 2.518649391440911e-05, | |
| "loss": 0.3148, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 5.521201413427562, | |
| "grad_norm": 8.544435501098633, | |
| "learning_rate": 2.494110718492344e-05, | |
| "loss": 0.2565, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 5.565371024734983, | |
| "grad_norm": 17.02871322631836, | |
| "learning_rate": 2.469572045543777e-05, | |
| "loss": 0.3099, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 5.609540636042403, | |
| "grad_norm": 10.150726318359375, | |
| "learning_rate": 2.44503337259521e-05, | |
| "loss": 0.2532, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 5.6537102473498235, | |
| "grad_norm": 14.919329643249512, | |
| "learning_rate": 2.420494699646643e-05, | |
| "loss": 0.2592, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.6978798586572434, | |
| "grad_norm": 10.145200729370117, | |
| "learning_rate": 2.3959560266980764e-05, | |
| "loss": 0.2884, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 5.742049469964664, | |
| "grad_norm": 26.694957733154297, | |
| "learning_rate": 2.3714173537495094e-05, | |
| "loss": 0.3092, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 5.786219081272085, | |
| "grad_norm": 9.009997367858887, | |
| "learning_rate": 2.3468786808009424e-05, | |
| "loss": 0.2768, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 5.830388692579505, | |
| "grad_norm": 14.945252418518066, | |
| "learning_rate": 2.3223400078523754e-05, | |
| "loss": 0.3033, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.874558303886926, | |
| "grad_norm": 22.651411056518555, | |
| "learning_rate": 2.2978013349038084e-05, | |
| "loss": 0.302, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 5.918727915194347, | |
| "grad_norm": 35.13420867919922, | |
| "learning_rate": 2.2732626619552418e-05, | |
| "loss": 0.2968, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 5.9628975265017665, | |
| "grad_norm": 8.667001724243164, | |
| "learning_rate": 2.2487239890066748e-05, | |
| "loss": 0.2591, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_explained_variance": 0.6250333786010742, | |
| "eval_loss": 2.4686992168426514, | |
| "eval_mae": 1.1278386116027832, | |
| "eval_mse": 2.4570138454437256, | |
| "eval_r2": 0.6012482643127441, | |
| "eval_rmse": 1.5674865245819092, | |
| "eval_runtime": 1.0575, | |
| "eval_samples_per_second": 2139.964, | |
| "eval_steps_per_second": 67.14, | |
| "step": 3396 | |
| }, | |
| { | |
| "epoch": 6.007067137809187, | |
| "grad_norm": 7.289055824279785, | |
| "learning_rate": 2.2241853160581078e-05, | |
| "loss": 0.2845, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 6.051236749116608, | |
| "grad_norm": 9.033802032470703, | |
| "learning_rate": 2.1996466431095408e-05, | |
| "loss": 0.2348, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 6.095406360424028, | |
| "grad_norm": 8.453237533569336, | |
| "learning_rate": 2.175107970160974e-05, | |
| "loss": 0.1626, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 6.139575971731449, | |
| "grad_norm": 12.62721061706543, | |
| "learning_rate": 2.150569297212407e-05, | |
| "loss": 0.1882, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 6.18374558303887, | |
| "grad_norm": 4.496434688568115, | |
| "learning_rate": 2.1260306242638402e-05, | |
| "loss": 0.2002, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.22791519434629, | |
| "grad_norm": 10.905092239379883, | |
| "learning_rate": 2.1014919513152732e-05, | |
| "loss": 0.1872, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 6.27208480565371, | |
| "grad_norm": 6.897697448730469, | |
| "learning_rate": 2.076953278366706e-05, | |
| "loss": 0.1842, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 6.316254416961131, | |
| "grad_norm": 18.04530906677246, | |
| "learning_rate": 2.052414605418139e-05, | |
| "loss": 0.1848, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 6.360424028268551, | |
| "grad_norm": 28.663089752197266, | |
| "learning_rate": 2.027875932469572e-05, | |
| "loss": 0.2338, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 6.404593639575972, | |
| "grad_norm": 7.388453960418701, | |
| "learning_rate": 2.0033372595210052e-05, | |
| "loss": 0.1731, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 6.448763250883392, | |
| "grad_norm": 8.80778694152832, | |
| "learning_rate": 1.9787985865724383e-05, | |
| "loss": 0.1948, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 6.492932862190813, | |
| "grad_norm": 15.45908260345459, | |
| "learning_rate": 1.9542599136238713e-05, | |
| "loss": 0.2057, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 6.5371024734982335, | |
| "grad_norm": 9.21857738494873, | |
| "learning_rate": 1.9297212406753043e-05, | |
| "loss": 0.2214, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 6.581272084805653, | |
| "grad_norm": 9.719182968139648, | |
| "learning_rate": 1.9051825677267373e-05, | |
| "loss": 0.1998, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 6.625441696113074, | |
| "grad_norm": 7.005542278289795, | |
| "learning_rate": 1.8806438947781703e-05, | |
| "loss": 0.1841, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 6.669611307420495, | |
| "grad_norm": 7.91580867767334, | |
| "learning_rate": 1.8561052218296036e-05, | |
| "loss": 0.1772, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 6.713780918727915, | |
| "grad_norm": 11.724370002746582, | |
| "learning_rate": 1.8315665488810367e-05, | |
| "loss": 0.1448, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 6.757950530035336, | |
| "grad_norm": 17.918067932128906, | |
| "learning_rate": 1.8070278759324697e-05, | |
| "loss": 0.2006, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 6.8021201413427566, | |
| "grad_norm": 11.593217849731445, | |
| "learning_rate": 1.7824892029839027e-05, | |
| "loss": 0.2018, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 6.8462897526501765, | |
| "grad_norm": 12.630243301391602, | |
| "learning_rate": 1.7579505300353357e-05, | |
| "loss": 0.1784, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 6.890459363957597, | |
| "grad_norm": 7.918076992034912, | |
| "learning_rate": 1.7334118570867687e-05, | |
| "loss": 0.1864, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 6.934628975265017, | |
| "grad_norm": 9.690032005310059, | |
| "learning_rate": 1.708873184138202e-05, | |
| "loss": 0.225, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 6.978798586572438, | |
| "grad_norm": 19.622501373291016, | |
| "learning_rate": 1.684334511189635e-05, | |
| "loss": 0.1898, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_explained_variance": 0.6274623870849609, | |
| "eval_loss": 2.4948439598083496, | |
| "eval_mae": 1.140474796295166, | |
| "eval_mse": 2.484145164489746, | |
| "eval_r2": 0.5968450903892517, | |
| "eval_rmse": 1.5761171579360962, | |
| "eval_runtime": 1.0544, | |
| "eval_samples_per_second": 2146.215, | |
| "eval_steps_per_second": 67.336, | |
| "step": 3962 | |
| }, | |
| { | |
| "epoch": 7.022968197879859, | |
| "grad_norm": 6.990258693695068, | |
| "learning_rate": 1.659795838241068e-05, | |
| "loss": 0.1784, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 7.067137809187279, | |
| "grad_norm": 5.022929668426514, | |
| "learning_rate": 1.635257165292501e-05, | |
| "loss": 0.1471, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.1113074204946995, | |
| "grad_norm": 6.776317119598389, | |
| "learning_rate": 1.610718492343934e-05, | |
| "loss": 0.1333, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 7.15547703180212, | |
| "grad_norm": 13.689594268798828, | |
| "learning_rate": 1.586179819395367e-05, | |
| "loss": 0.1339, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 7.19964664310954, | |
| "grad_norm": 6.960967063903809, | |
| "learning_rate": 1.5616411464468005e-05, | |
| "loss": 0.1278, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 7.243816254416961, | |
| "grad_norm": 9.860389709472656, | |
| "learning_rate": 1.5371024734982335e-05, | |
| "loss": 0.1419, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 7.287985865724382, | |
| "grad_norm": 12.38211727142334, | |
| "learning_rate": 1.5125638005496665e-05, | |
| "loss": 0.154, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 7.332155477031802, | |
| "grad_norm": 5.641261577606201, | |
| "learning_rate": 1.4880251276010995e-05, | |
| "loss": 0.1556, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 7.376325088339223, | |
| "grad_norm": 12.16318416595459, | |
| "learning_rate": 1.4634864546525327e-05, | |
| "loss": 0.1574, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 7.420494699646643, | |
| "grad_norm": 6.69941520690918, | |
| "learning_rate": 1.4389477817039653e-05, | |
| "loss": 0.1461, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 7.464664310954063, | |
| "grad_norm": 6.084545612335205, | |
| "learning_rate": 1.4144091087553985e-05, | |
| "loss": 0.1448, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 7.508833922261484, | |
| "grad_norm": 10.190794944763184, | |
| "learning_rate": 1.3898704358068315e-05, | |
| "loss": 0.1739, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 7.553003533568905, | |
| "grad_norm": 5.71160364151001, | |
| "learning_rate": 1.3653317628582645e-05, | |
| "loss": 0.1162, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 7.597173144876325, | |
| "grad_norm": 7.204683303833008, | |
| "learning_rate": 1.3407930899096977e-05, | |
| "loss": 0.1351, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 7.641342756183746, | |
| "grad_norm": 11.425016403198242, | |
| "learning_rate": 1.3162544169611307e-05, | |
| "loss": 0.1327, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 7.685512367491166, | |
| "grad_norm": 5.907583713531494, | |
| "learning_rate": 1.2917157440125637e-05, | |
| "loss": 0.1308, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 7.729681978798586, | |
| "grad_norm": 7.888271808624268, | |
| "learning_rate": 1.267177071063997e-05, | |
| "loss": 0.1427, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 7.773851590106007, | |
| "grad_norm": 5.342504024505615, | |
| "learning_rate": 1.24263839811543e-05, | |
| "loss": 0.1437, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 7.818021201413428, | |
| "grad_norm": 4.982570171356201, | |
| "learning_rate": 1.218099725166863e-05, | |
| "loss": 0.1237, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 7.862190812720848, | |
| "grad_norm": 3.8644771575927734, | |
| "learning_rate": 1.1935610522182961e-05, | |
| "loss": 0.1225, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 7.906360424028269, | |
| "grad_norm": 3.926877498626709, | |
| "learning_rate": 1.1690223792697291e-05, | |
| "loss": 0.1262, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 7.950530035335689, | |
| "grad_norm": 6.653122425079346, | |
| "learning_rate": 1.1444837063211621e-05, | |
| "loss": 0.1333, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 7.9946996466431095, | |
| "grad_norm": 7.844146251678467, | |
| "learning_rate": 1.1199450333725953e-05, | |
| "loss": 0.1308, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_explained_variance": 0.6261004209518433, | |
| "eval_loss": 2.495262622833252, | |
| "eval_mae": 1.1328405141830444, | |
| "eval_mse": 2.48473858833313, | |
| "eval_r2": 0.5967487692832947, | |
| "eval_rmse": 1.5763053894042969, | |
| "eval_runtime": 1.0666, | |
| "eval_samples_per_second": 2121.718, | |
| "eval_steps_per_second": 66.567, | |
| "step": 4528 | |
| }, | |
| { | |
| "epoch": 8.03886925795053, | |
| "grad_norm": 24.181594848632812, | |
| "learning_rate": 1.0954063604240283e-05, | |
| "loss": 0.1091, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 8.083038869257951, | |
| "grad_norm": 3.6817755699157715, | |
| "learning_rate": 1.0708676874754613e-05, | |
| "loss": 0.1275, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 8.12720848056537, | |
| "grad_norm": 3.9178013801574707, | |
| "learning_rate": 1.0463290145268945e-05, | |
| "loss": 0.0956, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 8.171378091872791, | |
| "grad_norm": 4.021216869354248, | |
| "learning_rate": 1.0217903415783275e-05, | |
| "loss": 0.103, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 8.215547703180212, | |
| "grad_norm": 11.239612579345703, | |
| "learning_rate": 9.972516686297605e-06, | |
| "loss": 0.0989, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 8.259717314487633, | |
| "grad_norm": 5.062624931335449, | |
| "learning_rate": 9.727129956811937e-06, | |
| "loss": 0.0998, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 8.303886925795053, | |
| "grad_norm": 4.972472190856934, | |
| "learning_rate": 9.481743227326266e-06, | |
| "loss": 0.0991, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 8.348056537102474, | |
| "grad_norm": 4.167801380157471, | |
| "learning_rate": 9.236356497840597e-06, | |
| "loss": 0.1016, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 8.392226148409893, | |
| "grad_norm": 4.731273651123047, | |
| "learning_rate": 8.990969768354928e-06, | |
| "loss": 0.1025, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 8.436395759717314, | |
| "grad_norm": 5.190533638000488, | |
| "learning_rate": 8.745583038869258e-06, | |
| "loss": 0.1012, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 8.480565371024735, | |
| "grad_norm": 7.925145149230957, | |
| "learning_rate": 8.50019630938359e-06, | |
| "loss": 0.1126, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 8.524734982332156, | |
| "grad_norm": 6.021143913269043, | |
| "learning_rate": 8.25480957989792e-06, | |
| "loss": 0.0804, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 8.568904593639576, | |
| "grad_norm": 4.904351711273193, | |
| "learning_rate": 8.00942285041225e-06, | |
| "loss": 0.0984, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 8.613074204946997, | |
| "grad_norm": 5.331979274749756, | |
| "learning_rate": 7.764036120926581e-06, | |
| "loss": 0.1087, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 8.657243816254416, | |
| "grad_norm": 7.438701629638672, | |
| "learning_rate": 7.518649391440912e-06, | |
| "loss": 0.11, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 8.701413427561837, | |
| "grad_norm": 5.5875420570373535, | |
| "learning_rate": 7.2732626619552425e-06, | |
| "loss": 0.1211, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 8.745583038869258, | |
| "grad_norm": 5.041488170623779, | |
| "learning_rate": 7.027875932469573e-06, | |
| "loss": 0.0783, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 8.789752650176679, | |
| "grad_norm": 3.2430458068847656, | |
| "learning_rate": 6.782489202983904e-06, | |
| "loss": 0.0982, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 8.8339222614841, | |
| "grad_norm": 4.588315010070801, | |
| "learning_rate": 6.5371024734982345e-06, | |
| "loss": 0.1137, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 8.878091872791519, | |
| "grad_norm": 5.235021114349365, | |
| "learning_rate": 6.291715744012564e-06, | |
| "loss": 0.097, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 8.92226148409894, | |
| "grad_norm": 4.683666229248047, | |
| "learning_rate": 6.046329014526895e-06, | |
| "loss": 0.0836, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 8.96643109540636, | |
| "grad_norm": 3.5004100799560547, | |
| "learning_rate": 5.800942285041226e-06, | |
| "loss": 0.0884, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_explained_variance": 0.6279962062835693, | |
| "eval_loss": 2.4493231773376465, | |
| "eval_mae": 1.1165964603424072, | |
| "eval_mse": 2.43858003616333, | |
| "eval_r2": 0.6042398810386658, | |
| "eval_rmse": 1.5615953207015991, | |
| "eval_runtime": 1.0409, | |
| "eval_samples_per_second": 2174.145, | |
| "eval_steps_per_second": 68.212, | |
| "step": 5094 | |
| }, | |
| { | |
| "epoch": 9.010600706713781, | |
| "grad_norm": 6.5793352127075195, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0868, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 9.054770318021202, | |
| "grad_norm": 2.6503169536590576, | |
| "learning_rate": 5.310168826069886e-06, | |
| "loss": 0.0657, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 9.098939929328623, | |
| "grad_norm": 2.9820001125335693, | |
| "learning_rate": 5.064782096584217e-06, | |
| "loss": 0.0699, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 9.143109540636042, | |
| "grad_norm": 3.706174373626709, | |
| "learning_rate": 4.819395367098548e-06, | |
| "loss": 0.0811, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 9.187279151943462, | |
| "grad_norm": 2.652496099472046, | |
| "learning_rate": 4.574008637612878e-06, | |
| "loss": 0.0658, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 9.231448763250883, | |
| "grad_norm": 4.267024040222168, | |
| "learning_rate": 4.328621908127209e-06, | |
| "loss": 0.0706, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 9.275618374558304, | |
| "grad_norm": 2.936169147491455, | |
| "learning_rate": 4.08323517864154e-06, | |
| "loss": 0.0661, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 9.319787985865725, | |
| "grad_norm": 3.2708146572113037, | |
| "learning_rate": 3.83784844915587e-06, | |
| "loss": 0.0829, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 9.363957597173146, | |
| "grad_norm": 5.624586582183838, | |
| "learning_rate": 3.5924617196702e-06, | |
| "loss": 0.0847, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 9.408127208480565, | |
| "grad_norm": 6.347949981689453, | |
| "learning_rate": 3.347074990184531e-06, | |
| "loss": 0.081, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 9.452296819787986, | |
| "grad_norm": 3.8003103733062744, | |
| "learning_rate": 3.1016882606988615e-06, | |
| "loss": 0.0657, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 9.496466431095406, | |
| "grad_norm": 3.1843507289886475, | |
| "learning_rate": 2.8563015312131925e-06, | |
| "loss": 0.0613, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 9.540636042402827, | |
| "grad_norm": 4.932063579559326, | |
| "learning_rate": 2.6109148017275226e-06, | |
| "loss": 0.0743, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 9.584805653710248, | |
| "grad_norm": 7.54895544052124, | |
| "learning_rate": 2.365528072241853e-06, | |
| "loss": 0.0683, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 9.628975265017669, | |
| "grad_norm": 5.509974956512451, | |
| "learning_rate": 2.120141342756184e-06, | |
| "loss": 0.0736, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 9.673144876325088, | |
| "grad_norm": 4.273847579956055, | |
| "learning_rate": 1.8747546132705144e-06, | |
| "loss": 0.0618, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 9.717314487632509, | |
| "grad_norm": 7.0803303718566895, | |
| "learning_rate": 1.629367883784845e-06, | |
| "loss": 0.0691, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 9.76148409893993, | |
| "grad_norm": 6.049960613250732, | |
| "learning_rate": 1.3839811542991755e-06, | |
| "loss": 0.0995, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 9.80565371024735, | |
| "grad_norm": 3.8500442504882812, | |
| "learning_rate": 1.1385944248135062e-06, | |
| "loss": 0.0732, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 9.849823321554771, | |
| "grad_norm": 4.026426792144775, | |
| "learning_rate": 8.932076953278367e-07, | |
| "loss": 0.0706, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 9.89399293286219, | |
| "grad_norm": 2.691366195678711, | |
| "learning_rate": 6.478209658421673e-07, | |
| "loss": 0.0807, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 9.93816254416961, | |
| "grad_norm": 4.666661262512207, | |
| "learning_rate": 4.024342363564979e-07, | |
| "loss": 0.0701, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 9.982332155477032, | |
| "grad_norm": 3.5465140342712402, | |
| "learning_rate": 1.5704750687082843e-07, | |
| "loss": 0.0763, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_explained_variance": 0.631534218788147, | |
| "eval_loss": 2.4403305053710938, | |
| "eval_mae": 1.1220409870147705, | |
| "eval_mse": 2.4293971061706543, | |
| "eval_r2": 0.6057301759719849, | |
| "eval_rmse": 1.5586522817611694, | |
| "eval_runtime": 0.9929, | |
| "eval_samples_per_second": 2279.266, | |
| "eval_steps_per_second": 71.51, | |
| "step": 5660 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5660, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5956780739788800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |