| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9683794466403162, | |
| "eval_steps": 16, | |
| "global_step": 126, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.17573034763336182, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0307, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.0314464569091797, | |
| "eval_runtime": 589.9959, | |
| "eval_samples_per_second": 0.351, | |
| "eval_steps_per_second": 0.351, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.1727771908044815, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1265, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.2174711972475052, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0362, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.15978679060935974, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1557, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.1518234759569168, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9664, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.1279090940952301, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9584, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.14364583790302277, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0269, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.18047624826431274, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9699, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.1313191056251526, | |
| "learning_rate": 0.00018, | |
| "loss": 1.93, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.14072288572788239, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9375, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.13216689229011536, | |
| "learning_rate": 0.00019999871623526481, | |
| "loss": 2.0861, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.12376871705055237, | |
| "learning_rate": 0.00019999486497402038, | |
| "loss": 2.0024, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.11119924485683441, | |
| "learning_rate": 0.00019998844631514886, | |
| "loss": 2.0243, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.11198648810386658, | |
| "learning_rate": 0.00019997946042345127, | |
| "loss": 1.9499, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.11798805743455887, | |
| "learning_rate": 0.00019996790752964305, | |
| "loss": 2.0469, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.12525062263011932, | |
| "learning_rate": 0.00019995378793034814, | |
| "loss": 2.0982, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.9930143356323242, | |
| "eval_runtime": 587.3154, | |
| "eval_samples_per_second": 0.352, | |
| "eval_steps_per_second": 0.352, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.1235467791557312, | |
| "learning_rate": 0.00019993710198809136, | |
| "loss": 2.0232, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.10296319425106049, | |
| "learning_rate": 0.00019991785013128923, | |
| "loss": 1.996, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.10613357275724411, | |
| "learning_rate": 0.00019989603285423889, | |
| "loss": 2.0909, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.1147119328379631, | |
| "learning_rate": 0.00019987165071710527, | |
| "loss": 1.9893, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.1092303916811943, | |
| "learning_rate": 0.00019984470434590703, | |
| "loss": 1.9745, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.13837751746177673, | |
| "learning_rate": 0.0001998151944325001, | |
| "loss": 2.0544, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.12572677433490753, | |
| "learning_rate": 0.00019978312173456027, | |
| "loss": 1.9235, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.11084165424108505, | |
| "learning_rate": 0.00019974848707556345, | |
| "loss": 2.0651, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.10701000690460205, | |
| "learning_rate": 0.00019971129134476473, | |
| "loss": 1.9667, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.1185716763138771, | |
| "learning_rate": 0.00019967153549717553, | |
| "loss": 1.9993, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.14391109347343445, | |
| "learning_rate": 0.0001996292205535389, | |
| "loss": 2.0942, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.11472482979297638, | |
| "learning_rate": 0.00019958434760030346, | |
| "loss": 2.0754, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.09692487865686417, | |
| "learning_rate": 0.00019953691778959557, | |
| "loss": 2.0101, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.10973215848207474, | |
| "learning_rate": 0.00019948693233918952, | |
| "loss": 2.0088, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.10801681876182556, | |
| "learning_rate": 0.00019943439253247656, | |
| "loss": 2.0177, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.11581862717866898, | |
| "learning_rate": 0.00019937929971843165, | |
| "loss": 1.8967, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.9818447828292847, | |
| "eval_runtime": 587.0079, | |
| "eval_samples_per_second": 0.353, | |
| "eval_steps_per_second": 0.353, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.11895039677619934, | |
| "learning_rate": 0.0001993216553115791, | |
| "loss": 1.9273, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.12135493755340576, | |
| "learning_rate": 0.00019926146079195594, | |
| "loss": 2.0167, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.1046937108039856, | |
| "learning_rate": 0.0001991987177050743, | |
| "loss": 2.0068, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.11556221544742584, | |
| "learning_rate": 0.00019913342766188138, | |
| "loss": 2.157, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.10031617432832718, | |
| "learning_rate": 0.00019906559233871828, | |
| "loss": 2.0234, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.11878479272127151, | |
| "learning_rate": 0.0001989952134772769, | |
| "loss": 1.9956, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.10510522127151489, | |
| "learning_rate": 0.00019892229288455532, | |
| "loss": 2.1002, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.09501214325428009, | |
| "learning_rate": 0.00019884683243281116, | |
| "loss": 1.8809, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.09750509262084961, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 2.1677, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.10707078874111176, | |
| "learning_rate": 0.00019868829976729443, | |
| "loss": 1.9349, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.11763511598110199, | |
| "learning_rate": 0.00019860523162389476, | |
| "loss": 2.0093, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.09981624782085419, | |
| "learning_rate": 0.00019851963176211387, | |
| "loss": 2.003, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.10791173577308655, | |
| "learning_rate": 0.00019843150237975344, | |
| "loss": 2.0147, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.10654355585575104, | |
| "learning_rate": 0.00019834084573956128, | |
| "loss": 2.0423, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.11113700270652771, | |
| "learning_rate": 0.00019824766416917338, | |
| "loss": 1.9396, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.11194361746311188, | |
| "learning_rate": 0.00019815196006105402, | |
| "loss": 1.9726, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.9757568836212158, | |
| "eval_runtime": 586.7896, | |
| "eval_samples_per_second": 0.353, | |
| "eval_steps_per_second": 0.353, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.10718481242656708, | |
| "learning_rate": 0.0001980537358724344, | |
| "loss": 1.974, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.1139945313334465, | |
| "learning_rate": 0.00019795299412524945, | |
| "loss": 2.0978, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.11229316890239716, | |
| "learning_rate": 0.0001978497374060733, | |
| "loss": 2.0419, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.10654540359973907, | |
| "learning_rate": 0.00019774396836605255, | |
| "loss": 1.9337, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.09649579972028732, | |
| "learning_rate": 0.00019763568972083856, | |
| "loss": 2.0043, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.10226842761039734, | |
| "learning_rate": 0.00019752490425051743, | |
| "loss": 1.9678, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.10110396891832352, | |
| "learning_rate": 0.0001974116147995387, | |
| "loss": 2.0006, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.10171829164028168, | |
| "learning_rate": 0.0001972958242766425, | |
| "loss": 1.9753, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.1117730587720871, | |
| "learning_rate": 0.0001971775356547846, | |
| "loss": 1.9982, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.15865837037563324, | |
| "learning_rate": 0.00019705675197106016, | |
| "loss": 2.0222, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.10181812196969986, | |
| "learning_rate": 0.00019693347632662595, | |
| "loss": 2.0899, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.13255544006824493, | |
| "learning_rate": 0.00019680771188662044, | |
| "loss": 2.0191, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.8338626623153687, | |
| "learning_rate": 0.0001966794618800827, | |
| "loss": 2.0432, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.11790451407432556, | |
| "learning_rate": 0.00019654872959986937, | |
| "loss": 2.0005, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.12201216071844101, | |
| "learning_rate": 0.00019641551840257035, | |
| "loss": 1.9949, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.10102586448192596, | |
| "learning_rate": 0.00019627983170842234, | |
| "loss": 2.0108, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.9710921049118042, | |
| "eval_runtime": 588.7491, | |
| "eval_samples_per_second": 0.352, | |
| "eval_steps_per_second": 0.352, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.14357174932956696, | |
| "learning_rate": 0.00019614167300122126, | |
| "loss": 1.7736, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.0991039052605629, | |
| "learning_rate": 0.0001960010458282326, | |
| "loss": 1.9889, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.10566934943199158, | |
| "learning_rate": 0.00019585795380010044, | |
| "loss": 1.8411, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.12068266421556473, | |
| "learning_rate": 0.0001957124005907548, | |
| "loss": 1.9175, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.10454852879047394, | |
| "learning_rate": 0.00019556438993731726, | |
| "loss": 1.9158, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.11026794463396072, | |
| "learning_rate": 0.00019541392564000488, | |
| "loss": 1.9053, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.11682567000389099, | |
| "learning_rate": 0.00019526101156203295, | |
| "loss": 1.9778, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.11718857288360596, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.9957, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.11099609732627869, | |
| "learning_rate": 0.00019494784983136425, | |
| "loss": 1.8909, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.11991846561431885, | |
| "learning_rate": 0.00019478761021918728, | |
| "loss": 1.9644, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.12009608745574951, | |
| "learning_rate": 0.0001946249369071837, | |
| "loss": 2.0168, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.1274980902671814, | |
| "learning_rate": 0.00019445983407203872, | |
| "loss": 1.7852, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.12307930737733841, | |
| "learning_rate": 0.00019429230595281632, | |
| "loss": 1.9185, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.1239650622010231, | |
| "learning_rate": 0.00019412235685085035, | |
| "loss": 1.9912, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.12378279119729996, | |
| "learning_rate": 0.00019394999112963402, | |
| "loss": 1.8249, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.1403149962425232, | |
| "learning_rate": 0.00019377521321470805, | |
| "loss": 2.01, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 1.9759098291397095, | |
| "eval_runtime": 587.469, | |
| "eval_samples_per_second": 0.352, | |
| "eval_steps_per_second": 0.352, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.12876343727111816, | |
| "learning_rate": 0.00019359802759354695, | |
| "loss": 1.9961, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.1330948770046234, | |
| "learning_rate": 0.00019341843881544372, | |
| "loss": 1.9642, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.13431289792060852, | |
| "learning_rate": 0.00019323645149139319, | |
| "loss": 1.9867, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.13692668080329895, | |
| "learning_rate": 0.00019305207029397348, | |
| "loss": 1.9685, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.13141922652721405, | |
| "learning_rate": 0.00019286529995722623, | |
| "loss": 1.9022, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.13360707461833954, | |
| "learning_rate": 0.00019267614527653488, | |
| "loss": 1.9811, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.1410575956106186, | |
| "learning_rate": 0.00019248461110850157, | |
| "loss": 2.0276, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.1281205415725708, | |
| "learning_rate": 0.00019229070237082252, | |
| "loss": 1.8166, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.31853872537612915, | |
| "learning_rate": 0.0001920944240421617, | |
| "loss": 1.9699, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.1361798644065857, | |
| "learning_rate": 0.00019189578116202307, | |
| "loss": 1.9419, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.1369122415781021, | |
| "learning_rate": 0.0001916947788306211, | |
| "loss": 2.0005, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.14621175825595856, | |
| "learning_rate": 0.0001914914222087499, | |
| "loss": 1.904, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.1483631581068039, | |
| "learning_rate": 0.0001912857165176507, | |
| "loss": 1.9783, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.15535128116607666, | |
| "learning_rate": 0.00019107766703887764, | |
| "loss": 1.9242, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.1497003585100174, | |
| "learning_rate": 0.0001908672791141625, | |
| "loss": 1.9094, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.14517174661159515, | |
| "learning_rate": 0.00019065455814527718, | |
| "loss": 2.0594, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 1.977068305015564, | |
| "eval_runtime": 587.2535, | |
| "eval_samples_per_second": 0.352, | |
| "eval_steps_per_second": 0.352, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.149668887257576, | |
| "learning_rate": 0.0001904395095938953, | |
| "loss": 1.8582, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.14095304906368256, | |
| "learning_rate": 0.00019022213898145176, | |
| "loss": 1.8937, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.14488399028778076, | |
| "learning_rate": 0.00019000245188900111, | |
| "loss": 1.8799, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.1409035623073578, | |
| "learning_rate": 0.00018978045395707418, | |
| "loss": 1.9641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.15016290545463562, | |
| "learning_rate": 0.0001895561508855333, | |
| "loss": 1.9878, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.14171820878982544, | |
| "learning_rate": 0.00018932954843342591, | |
| "loss": 1.9328, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.1357404738664627, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 1.9264, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.13309913873672485, | |
| "learning_rate": 0.00018886946871873856, | |
| "loss": 1.9505, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.13994307816028595, | |
| "learning_rate": 0.00018863600326884082, | |
| "loss": 2.0543, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.147433340549469, | |
| "learning_rate": 0.00018840026206343784, | |
| "loss": 2.0231, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.13546781241893768, | |
| "learning_rate": 0.00018816225115525454, | |
| "loss": 1.8892, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.13406571745872498, | |
| "learning_rate": 0.0001879219766552911, | |
| "loss": 1.8828, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.14394783973693848, | |
| "learning_rate": 0.00018767944473266614, | |
| "loss": 1.938, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.1423158198595047, | |
| "learning_rate": 0.00018743466161445823, | |
| "loss": 1.8268, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.2636297345161438, | |
| "learning_rate": 0.00018718763358554607, | |
| "loss": 1.8625, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.14624255895614624, | |
| "learning_rate": 0.0001869383669884471, | |
| "loss": 1.9392, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.9756392240524292, | |
| "eval_runtime": 587.7368, | |
| "eval_samples_per_second": 0.352, | |
| "eval_steps_per_second": 0.352, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.14748816192150116, | |
| "learning_rate": 0.0001866868682231547, | |
| "loss": 1.9757, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.16464634239673615, | |
| "learning_rate": 0.00018643314374697378, | |
| "loss": 1.96, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.1459386795759201, | |
| "learning_rate": 0.00018617720007435497, | |
| "loss": 1.9337, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.1428644359111786, | |
| "learning_rate": 0.00018591904377672757, | |
| "loss": 1.7804, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.14610743522644043, | |
| "learning_rate": 0.00018565868148233053, | |
| "loss": 1.9056, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.14204370975494385, | |
| "learning_rate": 0.00018539611987604258, | |
| "loss": 1.97, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.14234338700771332, | |
| "learning_rate": 0.00018513136569921023, | |
| "loss": 1.9025, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.1486772745847702, | |
| "learning_rate": 0.00018486442574947511, | |
| "loss": 1.9135, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.1450343132019043, | |
| "learning_rate": 0.000184595306880599, | |
| "loss": 1.8578, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.140796959400177, | |
| "learning_rate": 0.00018432401600228823, | |
| "loss": 1.9178, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.14083623886108398, | |
| "learning_rate": 0.00018405056008001603, | |
| "loss": 1.7776, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.1653621792793274, | |
| "learning_rate": 0.00018377494613484378, | |
| "loss": 1.8844, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.156838059425354, | |
| "learning_rate": 0.00018349718124324076, | |
| "loss": 1.9659, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.14624595642089844, | |
| "learning_rate": 0.0001832172725369024, | |
| "loss": 1.9813, | |
| "step": 126 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 630, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 63, | |
| "total_flos": 7.12910688623788e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |