pbe-lora
/
gcp_models
/lora-logo_fix_full_deepseek7b_ds33i_lr_0.0002_alpha_512_r_512
/checkpoint-624
/trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9807692307692308, | |
| "eval_steps": 78, | |
| "global_step": 624, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.9576937530625236, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 2.3642923831939697, | |
| "eval_runtime": 31.3026, | |
| "eval_samples_per_second": 50.667, | |
| "eval_steps_per_second": 0.799, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.016756435109279, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3822, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.7558182317986264, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2765, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.4623363957636424, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0812, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.134156633277105, | |
| "learning_rate": 5e-05, | |
| "loss": 1.798, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.7690432787697787, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3743, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.886611999270118, | |
| "learning_rate": 7e-05, | |
| "loss": 1.2698, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.7973710180632572, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9957, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.6695485757123936, | |
| "learning_rate": 9e-05, | |
| "loss": 0.8504, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.5684386784655082, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7259, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.4504348217072197, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 0.7077, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.36339319206682963, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6921, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.3224158197143531, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 0.5797, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.21382937684980174, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5724, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.18630690263851857, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.5883, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.18338477639373002, | |
| "learning_rate": 0.00016, | |
| "loss": 0.5608, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.17973298036275828, | |
| "learning_rate": 0.00017, | |
| "loss": 0.5204, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.14677483054602705, | |
| "learning_rate": 0.00018, | |
| "loss": 0.5816, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.20527755486363392, | |
| "learning_rate": 0.00019, | |
| "loss": 0.5549, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.22469508152984974, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5259, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.13963615923703887, | |
| "learning_rate": 0.00019999941186316965, | |
| "loss": 0.5415, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.2487915230723844, | |
| "learning_rate": 0.0001999976474595967, | |
| "loss": 0.5296, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.15679778398631403, | |
| "learning_rate": 0.00019999470681003533, | |
| "loss": 0.5308, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.16274363749163362, | |
| "learning_rate": 0.00019999058994907564, | |
| "loss": 0.5488, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.11548554800287134, | |
| "learning_rate": 0.00019998529692514318, | |
| "loss": 0.523, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.1926387691379014, | |
| "learning_rate": 0.00019997882780049847, | |
| "loss": 0.5395, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.11478363802679677, | |
| "learning_rate": 0.00019997118265123597, | |
| "loss": 0.4966, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.12922130001001353, | |
| "learning_rate": 0.0001999623615672837, | |
| "loss": 0.495, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.154649765536972, | |
| "learning_rate": 0.00019995236465240166, | |
| "loss": 0.5528, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.1102239917890927, | |
| "learning_rate": 0.00019994119202418098, | |
| "loss": 0.5, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.12057481213954827, | |
| "learning_rate": 0.00019992884381404228, | |
| "loss": 0.5044, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.11845756760213995, | |
| "learning_rate": 0.00019991532016723439, | |
| "loss": 0.5072, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.1016045171681305, | |
| "learning_rate": 0.0001999006212428323, | |
| "loss": 0.5199, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.10165821205500736, | |
| "learning_rate": 0.00019988474721373568, | |
| "loss": 0.5061, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.09725718978705772, | |
| "learning_rate": 0.00019986769826666652, | |
| "loss": 0.5058, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.10013953937644998, | |
| "learning_rate": 0.00019984947460216707, | |
| "loss": 0.4662, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.09585472186577305, | |
| "learning_rate": 0.00019983007643459755, | |
| "loss": 0.5209, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.12160225588940578, | |
| "learning_rate": 0.00019980950399213344, | |
| "loss": 0.4799, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.08783461057350635, | |
| "learning_rate": 0.00019978775751676298, | |
| "loss": 0.4601, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.09361279898761421, | |
| "learning_rate": 0.00019976483726428422, | |
| "loss": 0.4839, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.10246186756638315, | |
| "learning_rate": 0.0001997407435043021, | |
| "loss": 0.4829, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.08699899980810057, | |
| "learning_rate": 0.0001997154765202251, | |
| "loss": 0.4858, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.0872056094840794, | |
| "learning_rate": 0.0001996890366092622, | |
| "loss": 0.4994, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.10404734980212342, | |
| "learning_rate": 0.00019966142408241901, | |
| "loss": 0.4821, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.10271882693772645, | |
| "learning_rate": 0.00019963263926449444, | |
| "loss": 0.5136, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.09615809933833842, | |
| "learning_rate": 0.00019960268249407675, | |
| "loss": 0.4806, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.10324244169737243, | |
| "learning_rate": 0.0001995715541235395, | |
| "loss": 0.5178, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.09144153708576061, | |
| "learning_rate": 0.00019953925451903756, | |
| "loss": 0.4906, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.08917919344270175, | |
| "learning_rate": 0.0001995057840605026, | |
| "loss": 0.4854, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.09554449870725211, | |
| "learning_rate": 0.0001994711431416389, | |
| "loss": 0.4939, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.09115002372736682, | |
| "learning_rate": 0.00019943533216991842, | |
| "loss": 0.4955, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.08353991501841487, | |
| "learning_rate": 0.00019939835156657616, | |
| "loss": 0.4942, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.10546903256978929, | |
| "learning_rate": 0.00019936020176660523, | |
| "loss": 0.5566, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.08497316721885892, | |
| "learning_rate": 0.00019932088321875172, | |
| "loss": 0.445, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.07851980705890292, | |
| "learning_rate": 0.0001992803963855093, | |
| "loss": 0.4611, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.08361298203943864, | |
| "learning_rate": 0.00019923874174311394, | |
| "loss": 0.4303, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.0841263746061434, | |
| "learning_rate": 0.00019919591978153825, | |
| "loss": 0.4946, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.0780879111467538, | |
| "learning_rate": 0.0001991519310044857, | |
| "loss": 0.4689, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.08732617645014529, | |
| "learning_rate": 0.00019910677592938457, | |
| "loss": 0.4918, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.08908129146664355, | |
| "learning_rate": 0.00019906045508738228, | |
| "loss": 0.4989, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.07378157682196985, | |
| "learning_rate": 0.00019901296902333858, | |
| "loss": 0.4405, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.08388050997830931, | |
| "learning_rate": 0.0001989643182958196, | |
| "loss": 0.4921, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.08494891432391286, | |
| "learning_rate": 0.00019891450347709098, | |
| "loss": 0.4749, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.08652999220189139, | |
| "learning_rate": 0.00019886352515311134, | |
| "loss": 0.5102, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.0758488450712337, | |
| "learning_rate": 0.00019881138392352529, | |
| "loss": 0.485, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.0807458785920033, | |
| "learning_rate": 0.0001987580804016563, | |
| "loss": 0.4539, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.0904952507784973, | |
| "learning_rate": 0.00019870361521449978, | |
| "loss": 0.5093, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.07874392972836033, | |
| "learning_rate": 0.00019864798900271532, | |
| "loss": 0.4985, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.08074850253327294, | |
| "learning_rate": 0.0001985912024206194, | |
| "loss": 0.4857, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.07702553592964846, | |
| "learning_rate": 0.0001985332561361776, | |
| "loss": 0.4848, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.07538964191843366, | |
| "learning_rate": 0.00019847415083099686, | |
| "loss": 0.463, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.07455910267208772, | |
| "learning_rate": 0.00019841388720031727, | |
| "loss": 0.4607, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.07568421209759528, | |
| "learning_rate": 0.00019835246595300405, | |
| "loss": 0.469, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.08283925051757123, | |
| "learning_rate": 0.00019828988781153917, | |
| "loss": 0.4798, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.07197018105379838, | |
| "learning_rate": 0.0001982261535120128, | |
| "loss": 0.4495, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.07588357960118751, | |
| "learning_rate": 0.00019816126380411476, | |
| "loss": 0.4933, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.07762197438469468, | |
| "learning_rate": 0.00019809521945112559, | |
| "loss": 0.4338, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.07429965528466595, | |
| "learning_rate": 0.00019802802122990758, | |
| "loss": 0.463, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.47018665075302124, | |
| "eval_runtime": 31.4457, | |
| "eval_samples_per_second": 50.436, | |
| "eval_steps_per_second": 0.795, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.07607844932261384, | |
| "learning_rate": 0.00019795966993089574, | |
| "loss": 0.4543, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.081174945094011, | |
| "learning_rate": 0.00019789016635808837, | |
| "loss": 0.4915, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.07915337361027842, | |
| "learning_rate": 0.0001978195113290377, | |
| "loss": 0.474, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.0783187074092481, | |
| "learning_rate": 0.00019774770567484022, | |
| "loss": 0.4481, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.07880715046238167, | |
| "learning_rate": 0.00019767475024012697, | |
| "loss": 0.4341, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.0806976838276348, | |
| "learning_rate": 0.00019760064588305345, | |
| "loss": 0.4641, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.08758634506990264, | |
| "learning_rate": 0.00019752539347528972, | |
| "loss": 0.4768, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.08753532277842584, | |
| "learning_rate": 0.00019744899390201006, | |
| "loss": 0.4505, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.09777683442661952, | |
| "learning_rate": 0.00019737144806188247, | |
| "loss": 0.4938, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.10475365288705184, | |
| "learning_rate": 0.0001972927568670583, | |
| "loss": 0.4692, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.07697624292561879, | |
| "learning_rate": 0.00019721292124316131, | |
| "loss": 0.4646, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.0889139209733116, | |
| "learning_rate": 0.00019713194212927696, | |
| "loss": 0.4469, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.09311930282978383, | |
| "learning_rate": 0.00019704982047794115, | |
| "loss": 0.5151, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.08434147654476686, | |
| "learning_rate": 0.00019696655725512933, | |
| "loss": 0.4588, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.08609043947490852, | |
| "learning_rate": 0.0001968821534402448, | |
| "loss": 0.4506, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.08017126052043291, | |
| "learning_rate": 0.00019679661002610743, | |
| "loss": 0.4475, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.08937103886262696, | |
| "learning_rate": 0.00019670992801894185, | |
| "loss": 0.4323, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.08243440718087472, | |
| "learning_rate": 0.00019662210843836574, | |
| "loss": 0.4682, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.0822028482677556, | |
| "learning_rate": 0.00019653315231737758, | |
| "loss": 0.4632, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.08768647113231792, | |
| "learning_rate": 0.0001964430607023449, | |
| "loss": 0.4763, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.08310160386974857, | |
| "learning_rate": 0.00019635183465299157, | |
| "loss": 0.4738, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.08524529510828038, | |
| "learning_rate": 0.00019625947524238563, | |
| "loss": 0.5143, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.07981231231973578, | |
| "learning_rate": 0.00019616598355692643, | |
| "loss": 0.4595, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.07385816946714303, | |
| "learning_rate": 0.00019607136069633212, | |
| "loss": 0.4757, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.08330603210697045, | |
| "learning_rate": 0.00019597560777362644, | |
| "loss": 0.4642, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.07210743188564775, | |
| "learning_rate": 0.0001958787259151258, | |
| "loss": 0.453, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.07134818865047196, | |
| "learning_rate": 0.00019578071626042602, | |
| "loss": 0.3932, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.07922767957981888, | |
| "learning_rate": 0.00019568157996238884, | |
| "loss": 0.4912, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.08771064927922, | |
| "learning_rate": 0.00019558131818712838, | |
| "loss": 0.47, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.07855314418750606, | |
| "learning_rate": 0.0001954799321139975, | |
| "loss": 0.449, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.08846173699063252, | |
| "learning_rate": 0.00019537742293557396, | |
| "loss": 0.5129, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.08236891075291973, | |
| "learning_rate": 0.00019527379185764612, | |
| "loss": 0.4965, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.07795835842381585, | |
| "learning_rate": 0.0001951690400991991, | |
| "loss": 0.4558, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.08344617544927467, | |
| "learning_rate": 0.00019506316889240027, | |
| "loss": 0.4316, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.07540899421075185, | |
| "learning_rate": 0.0001949561794825847, | |
| "loss": 0.4509, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.07189761355465896, | |
| "learning_rate": 0.00019484807312824067, | |
| "loss": 0.4261, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.08219409571224609, | |
| "learning_rate": 0.0001947388511009947, | |
| "loss": 0.4259, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.07937686601645606, | |
| "learning_rate": 0.0001946285146855968, | |
| "loss": 0.466, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.08615291754393793, | |
| "learning_rate": 0.00019451706517990513, | |
| "loss": 0.4553, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.08779783383935659, | |
| "learning_rate": 0.0001944045038948709, | |
| "loss": 0.4468, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.08147943900072253, | |
| "learning_rate": 0.00019429083215452276, | |
| "loss": 0.4561, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.09099776866425152, | |
| "learning_rate": 0.00019417605129595157, | |
| "loss": 0.5018, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.08424197379690702, | |
| "learning_rate": 0.0001940601626692943, | |
| "loss": 0.4526, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.07866217295326207, | |
| "learning_rate": 0.0001939431676377183, | |
| "loss": 0.4321, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.08138284265704941, | |
| "learning_rate": 0.00019382506757740532, | |
| "loss": 0.4392, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.08763203993333732, | |
| "learning_rate": 0.0001937058638775353, | |
| "loss": 0.4718, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.07676395750806715, | |
| "learning_rate": 0.00019358555794027, | |
| "loss": 0.4303, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.08899095845003774, | |
| "learning_rate": 0.00019346415118073632, | |
| "loss": 0.4688, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.08985241039663144, | |
| "learning_rate": 0.00019334164502701016, | |
| "loss": 0.4502, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.08864463459153939, | |
| "learning_rate": 0.00019321804092009906, | |
| "loss": 0.4596, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.08426846372338173, | |
| "learning_rate": 0.0001930933403139256, | |
| "loss": 0.4321, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.07954390493054744, | |
| "learning_rate": 0.00019296754467531014, | |
| "loss": 0.4258, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.07712555497675415, | |
| "learning_rate": 0.00019284065548395363, | |
| "loss": 0.4458, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.09826199538529941, | |
| "learning_rate": 0.00019271267423242024, | |
| "loss": 0.4739, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.07937324926086349, | |
| "learning_rate": 0.00019258360242611973, | |
| "loss": 0.3958, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.09276594332492127, | |
| "learning_rate": 0.00019245344158328972, | |
| "loss": 0.4454, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.09469314851059352, | |
| "learning_rate": 0.00019232219323497797, | |
| "loss": 0.5012, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.08080639785303419, | |
| "learning_rate": 0.0001921898589250242, | |
| "loss": 0.4258, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.08107763850205266, | |
| "learning_rate": 0.00019205644021004202, | |
| "loss": 0.4365, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.09645480193078979, | |
| "learning_rate": 0.0001919219386594007, | |
| "loss": 0.4445, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.0984618243938996, | |
| "learning_rate": 0.0001917863558552065, | |
| "loss": 0.4519, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.08810102921338284, | |
| "learning_rate": 0.00019164969339228422, | |
| "loss": 0.4275, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.07209850008164273, | |
| "learning_rate": 0.0001915119528781585, | |
| "loss": 0.446, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.08534362535649169, | |
| "learning_rate": 0.00019137313593303463, | |
| "loss": 0.419, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.07931386455567475, | |
| "learning_rate": 0.00019123324418977982, | |
| "loss": 0.4683, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.07920091476694083, | |
| "learning_rate": 0.00019109227929390378, | |
| "loss": 0.4641, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.0945926732709944, | |
| "learning_rate": 0.0001909502429035395, | |
| "loss": 0.4951, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.083724504222346, | |
| "learning_rate": 0.00019080713668942356, | |
| "loss": 0.4515, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.08650794676325269, | |
| "learning_rate": 0.00019066296233487672, | |
| "loss": 0.5212, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.07550774418373392, | |
| "learning_rate": 0.00019051772153578389, | |
| "loss": 0.4982, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.07958449304767184, | |
| "learning_rate": 0.00019037141600057437, | |
| "loss": 0.4438, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.07907660997330491, | |
| "learning_rate": 0.00019022404745020163, | |
| "loss": 0.4446, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.08403460530824067, | |
| "learning_rate": 0.0001900756176181231, | |
| "loss": 0.4954, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.07121713811670598, | |
| "learning_rate": 0.00018992612825027976, | |
| "loss": 0.4107, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.08888402716413658, | |
| "learning_rate": 0.00018977558110507578, | |
| "loss": 0.4647, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.07729783862955082, | |
| "learning_rate": 0.0001896239779533575, | |
| "loss": 0.4229, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.08006550817418195, | |
| "learning_rate": 0.00018947132057839285, | |
| "loss": 0.4561, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.06984953321391904, | |
| "learning_rate": 0.00018931761077585035, | |
| "loss": 0.4169, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.444174200296402, | |
| "eval_runtime": 31.4712, | |
| "eval_samples_per_second": 50.395, | |
| "eval_steps_per_second": 0.794, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.08018469116289545, | |
| "learning_rate": 0.00018916285035377794, | |
| "loss": 0.4503, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.07472127890764482, | |
| "learning_rate": 0.00018900704113258165, | |
| "loss": 0.3947, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.0821581012984107, | |
| "learning_rate": 0.00018885018494500436, | |
| "loss": 0.4651, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.07947038098348047, | |
| "learning_rate": 0.00018869228363610404, | |
| "loss": 0.4341, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.08140775754652937, | |
| "learning_rate": 0.00018853333906323225, | |
| "loss": 0.4415, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.08765931951958895, | |
| "learning_rate": 0.00018837335309601213, | |
| "loss": 0.4357, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.08442880892691382, | |
| "learning_rate": 0.0001882123276163164, | |
| "loss": 0.4609, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.09715434319124053, | |
| "learning_rate": 0.00018805026451824546, | |
| "loss": 0.4562, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.09347382736349209, | |
| "learning_rate": 0.0001878871657081048, | |
| "loss": 0.4737, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.09710819476140052, | |
| "learning_rate": 0.00018772303310438275, | |
| "loss": 0.4093, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.07891824166135025, | |
| "learning_rate": 0.00018755786863772792, | |
| "loss": 0.4532, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.0844025513913066, | |
| "learning_rate": 0.00018739167425092644, | |
| "loss": 0.446, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.09240034775723983, | |
| "learning_rate": 0.00018722445189887907, | |
| "loss": 0.4527, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.07973241323378466, | |
| "learning_rate": 0.00018705620354857833, | |
| "loss": 0.409, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.0762520514861058, | |
| "learning_rate": 0.00018688693117908521, | |
| "loss": 0.4785, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.08262985236128, | |
| "learning_rate": 0.00018671663678150607, | |
| "loss": 0.4314, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.081932544928875, | |
| "learning_rate": 0.00018654532235896898, | |
| "loss": 0.4347, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.0954889996650435, | |
| "learning_rate": 0.0001863729899266004, | |
| "loss": 0.4523, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.0933844173634654, | |
| "learning_rate": 0.00018619964151150137, | |
| "loss": 0.4385, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.08100659598302466, | |
| "learning_rate": 0.0001860252791527236, | |
| "loss": 0.443, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.08402731540674666, | |
| "learning_rate": 0.0001858499049012456, | |
| "loss": 0.4488, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.0847646100119722, | |
| "learning_rate": 0.00018567352081994852, | |
| "loss": 0.4452, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.07907581204553846, | |
| "learning_rate": 0.00018549612898359182, | |
| "loss": 0.451, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.08637033720756092, | |
| "learning_rate": 0.00018531773147878895, | |
| "loss": 0.4425, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.07860781076008888, | |
| "learning_rate": 0.0001851383304039828, | |
| "loss": 0.4223, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.09230920690158759, | |
| "learning_rate": 0.0001849579278694209, | |
| "loss": 0.4305, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.0741895536668344, | |
| "learning_rate": 0.0001847765259971308, | |
| "loss": 0.4202, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.07790747997729928, | |
| "learning_rate": 0.00018459412692089494, | |
| "loss": 0.4416, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.08468534726841428, | |
| "learning_rate": 0.0001844107327862256, | |
| "loss": 0.4544, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.09269533885564803, | |
| "learning_rate": 0.0001842263457503397, | |
| "loss": 0.4579, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.07202556081323952, | |
| "learning_rate": 0.00018404096798213334, | |
| "loss": 0.4232, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.08525241804626488, | |
| "learning_rate": 0.00018385460166215638, | |
| "loss": 0.4141, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.08924354777300852, | |
| "learning_rate": 0.00018366724898258676, | |
| "loss": 0.4529, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.08099522477717064, | |
| "learning_rate": 0.00018347891214720477, | |
| "loss": 0.4703, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.08207966306854911, | |
| "learning_rate": 0.0001832895933713669, | |
| "loss": 0.4221, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.08833974423720233, | |
| "learning_rate": 0.00018309929488198012, | |
| "loss": 0.47, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.0825533317998992, | |
| "learning_rate": 0.0001829080189174754, | |
| "loss": 0.4427, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.08037569999241694, | |
| "learning_rate": 0.00018271576772778154, | |
| "loss": 0.4419, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.08639200811474251, | |
| "learning_rate": 0.00018252254357429862, | |
| "loss": 0.4246, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.07267641895058494, | |
| "learning_rate": 0.00018232834872987147, | |
| "loss": 0.3956, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.08610579960197104, | |
| "learning_rate": 0.00018213318547876298, | |
| "loss": 0.4414, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.09186840821155946, | |
| "learning_rate": 0.00018193705611662696, | |
| "loss": 0.4177, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.08706736973820678, | |
| "learning_rate": 0.00018173996295048147, | |
| "loss": 0.4789, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.07334594688469492, | |
| "learning_rate": 0.0001815419082986815, | |
| "loss": 0.4271, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.08342217915939124, | |
| "learning_rate": 0.00018134289449089184, | |
| "loss": 0.4307, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.09389735105911007, | |
| "learning_rate": 0.00018114292386805936, | |
| "loss": 0.5084, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.09006740885148933, | |
| "learning_rate": 0.0001809419987823859, | |
| "loss": 0.4056, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.07121816467150913, | |
| "learning_rate": 0.00018074012159730032, | |
| "loss": 0.4277, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.08235101026308798, | |
| "learning_rate": 0.00018053729468743077, | |
| "loss": 0.3862, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.0847711800807384, | |
| "learning_rate": 0.00018033352043857675, | |
| "loss": 0.4318, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.08426668159343044, | |
| "learning_rate": 0.0001801288012476811, | |
| "loss": 0.4086, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.08251689590670132, | |
| "learning_rate": 0.00017992313952280172, | |
| "loss": 0.4286, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.07765075868537137, | |
| "learning_rate": 0.00017971653768308332, | |
| "loss": 0.438, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.07334563579113847, | |
| "learning_rate": 0.00017950899815872892, | |
| "loss": 0.4018, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.08055566369309557, | |
| "learning_rate": 0.0001793005233909713, | |
| "loss": 0.4234, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.07958008993094648, | |
| "learning_rate": 0.00017909111583204422, | |
| "loss": 0.44, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.09280699072968741, | |
| "learning_rate": 0.0001788807779451536, | |
| "loss": 0.4227, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.07693169121037356, | |
| "learning_rate": 0.0001786695122044487, | |
| "loss": 0.4478, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.07950835942157759, | |
| "learning_rate": 0.00017845732109499275, | |
| "loss": 0.4127, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.0825838707194437, | |
| "learning_rate": 0.0001782442071127338, | |
| "loss": 0.3989, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.0820192714301344, | |
| "learning_rate": 0.00017803017276447558, | |
| "loss": 0.4117, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.08266323600913242, | |
| "learning_rate": 0.0001778152205678477, | |
| "loss": 0.4115, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.09014685440524756, | |
| "learning_rate": 0.00017759935305127628, | |
| "loss": 0.4213, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.08003172169631632, | |
| "learning_rate": 0.00017738257275395404, | |
| "loss": 0.4492, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.08382716268554129, | |
| "learning_rate": 0.0001771648822258105, | |
| "loss": 0.4239, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.08458564896753232, | |
| "learning_rate": 0.00017694628402748202, | |
| "loss": 0.422, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.09196661919825705, | |
| "learning_rate": 0.00017672678073028163, | |
| "loss": 0.471, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.07698737002145145, | |
| "learning_rate": 0.0001765063749161688, | |
| "loss": 0.4132, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.07467731807448537, | |
| "learning_rate": 0.00017628506917771906, | |
| "loss": 0.479, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.08077943554506183, | |
| "learning_rate": 0.00017606286611809353, | |
| "loss": 0.4248, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.06992980003731436, | |
| "learning_rate": 0.0001758397683510083, | |
| "loss": 0.4315, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.08372536073946843, | |
| "learning_rate": 0.00017561577850070355, | |
| "loss": 0.4449, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.07728684058389318, | |
| "learning_rate": 0.00017539089920191298, | |
| "loss": 0.4102, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.07595500885479803, | |
| "learning_rate": 0.00017516513309983253, | |
| "loss": 0.4138, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.08896190709649075, | |
| "learning_rate": 0.0001749384828500894, | |
| "loss": 0.461, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.07539184697796432, | |
| "learning_rate": 0.00017471095111871074, | |
| "loss": 0.4117, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.08363633341284239, | |
| "learning_rate": 0.00017448254058209244, | |
| "loss": 0.4711, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.08326685819573444, | |
| "learning_rate": 0.0001742532539269674, | |
| "loss": 0.4411, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.4278123378753662, | |
| "eval_runtime": 31.4949, | |
| "eval_samples_per_second": 50.357, | |
| "eval_steps_per_second": 0.794, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.07732973043941553, | |
| "learning_rate": 0.00017402309385037423, | |
| "loss": 0.4379, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.0774523597417446, | |
| "learning_rate": 0.00017379206305962526, | |
| "loss": 0.447, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.08401116509418527, | |
| "learning_rate": 0.0001735601642722748, | |
| "loss": 0.4567, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.07735698013628362, | |
| "learning_rate": 0.00017332740021608722, | |
| "loss": 0.4197, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.07680567518283475, | |
| "learning_rate": 0.00017309377362900486, | |
| "loss": 0.4098, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.08122692422363423, | |
| "learning_rate": 0.00017285928725911562, | |
| "loss": 0.4149, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.08681701750052026, | |
| "learning_rate": 0.00017262394386462101, | |
| "loss": 0.4695, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.07626703932302029, | |
| "learning_rate": 0.00017238774621380337, | |
| "loss": 0.4493, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.07783076190751023, | |
| "learning_rate": 0.0001721506970849934, | |
| "loss": 0.4519, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.07851126371673435, | |
| "learning_rate": 0.00017191279926653761, | |
| "loss": 0.4646, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.07985898889121004, | |
| "learning_rate": 0.00017167405555676535, | |
| "loss": 0.4265, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.0782899694335972, | |
| "learning_rate": 0.00017143446876395602, | |
| "loss": 0.4414, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.0804512588231197, | |
| "learning_rate": 0.00017119404170630594, | |
| "loss": 0.4404, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.07731729751082467, | |
| "learning_rate": 0.00017095277721189528, | |
| "loss": 0.4417, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.07168689530432704, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.4382, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.07902533484598116, | |
| "learning_rate": 0.00017046774727433222, | |
| "loss": 0.4088, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.08232481685887245, | |
| "learning_rate": 0.00017022398753645916, | |
| "loss": 0.3865, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.08632426307204455, | |
| "learning_rate": 0.00016997940177231722, | |
| "loss": 0.4382, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.07388797256773258, | |
| "learning_rate": 0.0001697339928589043, | |
| "loss": 0.3799, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.08898666754826341, | |
| "learning_rate": 0.00016948776368290084, | |
| "loss": 0.4228, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.07930751762003878, | |
| "learning_rate": 0.00016924071714063575, | |
| "loss": 0.4405, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.08451897393194631, | |
| "learning_rate": 0.00016899285613805246, | |
| "loss": 0.4201, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.07509156290441986, | |
| "learning_rate": 0.00016874418359067464, | |
| "loss": 0.4236, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.07423524924140647, | |
| "learning_rate": 0.00016849470242357196, | |
| "loss": 0.4207, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.09131652369207922, | |
| "learning_rate": 0.00016824441557132568, | |
| "loss": 0.4244, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.07200307125773978, | |
| "learning_rate": 0.00016799332597799413, | |
| "loss": 0.3969, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.08850588028575115, | |
| "learning_rate": 0.00016774143659707808, | |
| "loss": 0.4083, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.08952226340711347, | |
| "learning_rate": 0.00016748875039148593, | |
| "loss": 0.4044, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.07625949844917335, | |
| "learning_rate": 0.000167235270333499, | |
| "loss": 0.4374, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.08512481964665687, | |
| "learning_rate": 0.0001669809994047364, | |
| "loss": 0.4179, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.08624448187165956, | |
| "learning_rate": 0.00016672594059612017, | |
| "loss": 0.4061, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.08247703101102852, | |
| "learning_rate": 0.0001664700969078398, | |
| "loss": 0.4499, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.07862715865198186, | |
| "learning_rate": 0.00016621347134931729, | |
| "loss": 0.4077, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.07218201414128739, | |
| "learning_rate": 0.00016595606693917142, | |
| "loss": 0.4434, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.07572789587568578, | |
| "learning_rate": 0.00016569788670518253, | |
| "loss": 0.4311, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.0834144142579703, | |
| "learning_rate": 0.00016543893368425666, | |
| "loss": 0.4366, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.08935819944784767, | |
| "learning_rate": 0.00016517921092239, | |
| "loss": 0.5029, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.07069431389655506, | |
| "learning_rate": 0.00016491872147463306, | |
| "loss": 0.4222, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.07615580144655403, | |
| "learning_rate": 0.00016465746840505448, | |
| "loss": 0.4575, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.07585167832031271, | |
| "learning_rate": 0.00016439545478670543, | |
| "loss": 0.4108, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.07823962802576302, | |
| "learning_rate": 0.000164132683701583, | |
| "loss": 0.4073, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.0739491453502392, | |
| "learning_rate": 0.00016386915824059427, | |
| "loss": 0.3972, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.08405357936143208, | |
| "learning_rate": 0.00016360488150351984, | |
| "loss": 0.4515, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.07695511244129288, | |
| "learning_rate": 0.00016333985659897735, | |
| "loss": 0.4279, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.06470217776094543, | |
| "learning_rate": 0.00016307408664438495, | |
| "loss": 0.4116, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.07308502501504789, | |
| "learning_rate": 0.00016280757476592466, | |
| "loss": 0.4341, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.06951503390440086, | |
| "learning_rate": 0.0001625403240985054, | |
| "loss": 0.4487, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.0692451278626476, | |
| "learning_rate": 0.0001622723377857265, | |
| "loss": 0.3826, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.07045628495573776, | |
| "learning_rate": 0.0001620036189798403, | |
| "loss": 0.4205, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.0817507962133775, | |
| "learning_rate": 0.00016173417084171536, | |
| "loss": 0.4058, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.08274224378072262, | |
| "learning_rate": 0.00016146399654079914, | |
| "loss": 0.4158, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.08104189231717747, | |
| "learning_rate": 0.00016119309925508078, | |
| "loss": 0.4582, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.07690391237677474, | |
| "learning_rate": 0.00016092148217105372, | |
| "loss": 0.4225, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.07890029013664841, | |
| "learning_rate": 0.0001606491484836782, | |
| "loss": 0.3967, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.0731319870015359, | |
| "learning_rate": 0.00016037610139634358, | |
| "loss": 0.4572, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.07566883804698676, | |
| "learning_rate": 0.00016010234412083086, | |
| "loss": 0.4124, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.07670361507960137, | |
| "learning_rate": 0.0001598278798772748, | |
| "loss": 0.4405, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.07969549982736794, | |
| "learning_rate": 0.00015955271189412598, | |
| "loss": 0.4223, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.08620664325730339, | |
| "learning_rate": 0.0001592768434081129, | |
| "loss": 0.4107, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.07814855518482838, | |
| "learning_rate": 0.00015900027766420393, | |
| "loss": 0.4256, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.07265880949372827, | |
| "learning_rate": 0.00015872301791556903, | |
| "loss": 0.3877, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.07164568406361997, | |
| "learning_rate": 0.00015844506742354164, | |
| "loss": 0.433, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.08097386064452165, | |
| "learning_rate": 0.00015816642945758012, | |
| "loss": 0.4352, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.07039809315446639, | |
| "learning_rate": 0.00015788710729522953, | |
| "loss": 0.4151, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.07923887250236342, | |
| "learning_rate": 0.00015760710422208288, | |
| "loss": 0.3972, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.08013977027306368, | |
| "learning_rate": 0.00015732642353174259, | |
| "loss": 0.4095, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.07082003627582258, | |
| "learning_rate": 0.00015704506852578165, | |
| "loss": 0.3764, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.07635025387900074, | |
| "learning_rate": 0.0001567630425137049, | |
| "loss": 0.4163, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.08691670113747935, | |
| "learning_rate": 0.00015648034881291003, | |
| "loss": 0.3652, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.07557246139809001, | |
| "learning_rate": 0.00015619699074864864, | |
| "loss": 0.3532, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.07500478833529528, | |
| "learning_rate": 0.00015591297165398692, | |
| "loss": 0.4134, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.07338624139290303, | |
| "learning_rate": 0.00015562829486976673, | |
| "loss": 0.3828, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.0694479071810134, | |
| "learning_rate": 0.0001553429637445661, | |
| "loss": 0.3887, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.0776950089538383, | |
| "learning_rate": 0.00015505698163465986, | |
| "loss": 0.4357, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.08048431664884834, | |
| "learning_rate": 0.00015477035190398025, | |
| "loss": 0.432, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.07227807968656443, | |
| "learning_rate": 0.00015448307792407734, | |
| "loss": 0.4162, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.07990637247600575, | |
| "learning_rate": 0.00015419516307407926, | |
| "loss": 0.4125, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.08651130022810746, | |
| "learning_rate": 0.00015390661074065256, | |
| "loss": 0.4635, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4184270203113556, | |
| "eval_runtime": 31.4969, | |
| "eval_samples_per_second": 50.354, | |
| "eval_steps_per_second": 0.794, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.07760795024261388, | |
| "learning_rate": 0.00015361742431796235, | |
| "loss": 0.4102, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.07500083036261085, | |
| "learning_rate": 0.00015332760720763232, | |
| "loss": 0.3701, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.06959027667343202, | |
| "learning_rate": 0.00015303716281870483, | |
| "loss": 0.3699, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.07739035786714127, | |
| "learning_rate": 0.00015274609456760073, | |
| "loss": 0.3901, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.0706332460743926, | |
| "learning_rate": 0.00015245440587807917, | |
| "loss": 0.4052, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.07768457365355498, | |
| "learning_rate": 0.00015216210018119733, | |
| "loss": 0.4184, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.07667200337121889, | |
| "learning_rate": 0.00015186918091527024, | |
| "loss": 0.3588, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.07623901525993244, | |
| "learning_rate": 0.00015157565152583002, | |
| "loss": 0.404, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.07702050587257582, | |
| "learning_rate": 0.00015128151546558554, | |
| "loss": 0.4079, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.0804479276929052, | |
| "learning_rate": 0.0001509867761943818, | |
| "loss": 0.4053, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.0866043648806226, | |
| "learning_rate": 0.00015069143717915927, | |
| "loss": 0.3595, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.08793180613547621, | |
| "learning_rate": 0.00015039550189391298, | |
| "loss": 0.4132, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.07242208696332281, | |
| "learning_rate": 0.0001500989738196517, | |
| "loss": 0.3624, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.07985557474189871, | |
| "learning_rate": 0.0001498018564443571, | |
| "loss": 0.3848, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.07296248114979226, | |
| "learning_rate": 0.0001495041532629426, | |
| "loss": 0.4096, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.07254961312475611, | |
| "learning_rate": 0.0001492058677772123, | |
| "loss": 0.3755, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.07435543248681963, | |
| "learning_rate": 0.00014890700349581986, | |
| "loss": 0.3561, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.07837798166763452, | |
| "learning_rate": 0.000148607563934227, | |
| "loss": 0.3998, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.08540052388847688, | |
| "learning_rate": 0.0001483075526146625, | |
| "loss": 0.4036, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.07942069397955749, | |
| "learning_rate": 0.00014800697306608044, | |
| "loss": 0.4043, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.07852405614327404, | |
| "learning_rate": 0.00014770582882411888, | |
| "loss": 0.3981, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.07765405089566957, | |
| "learning_rate": 0.00014740412343105828, | |
| "loss": 0.3397, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.08348696642060623, | |
| "learning_rate": 0.00014710186043577966, | |
| "loss": 0.3993, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.07822840523042333, | |
| "learning_rate": 0.00014679904339372302, | |
| "loss": 0.399, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.08365550912732765, | |
| "learning_rate": 0.00014649567586684547, | |
| "loss": 0.3926, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.07057745999260892, | |
| "learning_rate": 0.00014619176142357935, | |
| "loss": 0.3847, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.08297051826126539, | |
| "learning_rate": 0.00014588730363879014, | |
| "loss": 0.3857, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.07927914689055876, | |
| "learning_rate": 0.0001455823060937347, | |
| "loss": 0.4004, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.0867049401688423, | |
| "learning_rate": 0.00014527677237601865, | |
| "loss": 0.4438, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.07834997566686215, | |
| "learning_rate": 0.00014497070607955476, | |
| "loss": 0.383, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.07921580318560457, | |
| "learning_rate": 0.00014466411080452018, | |
| "loss": 0.4004, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.07564152502069386, | |
| "learning_rate": 0.00014435699015731448, | |
| "loss": 0.3911, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.0808116993432974, | |
| "learning_rate": 0.00014404934775051682, | |
| "loss": 0.3868, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.08277929771799022, | |
| "learning_rate": 0.00014374118720284388, | |
| "loss": 0.3955, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.07849962595775353, | |
| "learning_rate": 0.00014343251213910698, | |
| "loss": 0.4138, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.08786512640781652, | |
| "learning_rate": 0.00014312332619016965, | |
| "loss": 0.3943, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.08663821916619512, | |
| "learning_rate": 0.00014281363299290466, | |
| "loss": 0.4326, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.08465615501394959, | |
| "learning_rate": 0.0001425034361901516, | |
| "loss": 0.3817, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.0833629193039595, | |
| "learning_rate": 0.00014219273943067375, | |
| "loss": 0.3704, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.08340772894173044, | |
| "learning_rate": 0.00014188154636911524, | |
| "loss": 0.402, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.0753248263596041, | |
| "learning_rate": 0.00014156986066595807, | |
| "loss": 0.4042, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.0829371123195246, | |
| "learning_rate": 0.0001412576859874791, | |
| "loss": 0.3817, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.07464042823718454, | |
| "learning_rate": 0.00014094502600570688, | |
| "loss": 0.3969, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.09122968517792625, | |
| "learning_rate": 0.00014063188439837832, | |
| "loss": 0.4261, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.07863348055715408, | |
| "learning_rate": 0.00014031826484889578, | |
| "loss": 0.3933, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.07943831687450215, | |
| "learning_rate": 0.0001400041710462833, | |
| "loss": 0.3961, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.08419392469783887, | |
| "learning_rate": 0.00013968960668514372, | |
| "loss": 0.4033, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.07877945367133823, | |
| "learning_rate": 0.0001393745754656146, | |
| "loss": 0.3577, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.07986223671673909, | |
| "learning_rate": 0.00013905908109332525, | |
| "loss": 0.3759, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.07612977637397003, | |
| "learning_rate": 0.00013874312727935292, | |
| "loss": 0.3711, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.07999126154235789, | |
| "learning_rate": 0.00013842671774017906, | |
| "loss": 0.4057, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.08473947589738894, | |
| "learning_rate": 0.00013810985619764572, | |
| "loss": 0.3988, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.08875451962957616, | |
| "learning_rate": 0.0001377925463789118, | |
| "loss": 0.4147, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.079655956238025, | |
| "learning_rate": 0.00013747479201640914, | |
| "loss": 0.3989, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.08242768475092853, | |
| "learning_rate": 0.00013715659684779855, | |
| "loss": 0.4054, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.0781491659459016, | |
| "learning_rate": 0.00013683796461592604, | |
| "loss": 0.4458, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.07598114894664264, | |
| "learning_rate": 0.00013651889906877865, | |
| "loss": 0.3911, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.07670234017641822, | |
| "learning_rate": 0.00013619940395944027, | |
| "loss": 0.3898, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.07860175338477762, | |
| "learning_rate": 0.00013587948304604781, | |
| "loss": 0.3915, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.08334552842056786, | |
| "learning_rate": 0.00013555914009174663, | |
| "loss": 0.4044, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.07848806656728508, | |
| "learning_rate": 0.00013523837886464664, | |
| "loss": 0.3758, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.08364496288919489, | |
| "learning_rate": 0.00013491720313777756, | |
| "loss": 0.4156, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.08394772816799491, | |
| "learning_rate": 0.00013459561668904496, | |
| "loss": 0.4068, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.0864713947166038, | |
| "learning_rate": 0.00013427362330118543, | |
| "loss": 0.4072, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.08002433773127675, | |
| "learning_rate": 0.00013395122676172248, | |
| "loss": 0.3708, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.08236433988274829, | |
| "learning_rate": 0.0001336284308629216, | |
| "loss": 0.3878, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.0868877092334235, | |
| "learning_rate": 0.00013330523940174602, | |
| "loss": 0.3994, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.0815198545760725, | |
| "learning_rate": 0.00013298165617981172, | |
| "loss": 0.4142, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.07484707453139179, | |
| "learning_rate": 0.00013265768500334287, | |
| "loss": 0.3731, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.0794758829177575, | |
| "learning_rate": 0.00013233332968312715, | |
| "loss": 0.3775, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.09378925137578271, | |
| "learning_rate": 0.00013200859403447073, | |
| "loss": 0.4095, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.08078187681707542, | |
| "learning_rate": 0.0001316834818771535, | |
| "loss": 0.3848, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.07864643961418008, | |
| "learning_rate": 0.00013135799703538418, | |
| "loss": 0.3886, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.0805707525757092, | |
| "learning_rate": 0.00013103214333775521, | |
| "loss": 0.3888, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.08245000788485915, | |
| "learning_rate": 0.00013070592461719778, | |
| "loss": 0.4132, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.07866135306204902, | |
| "learning_rate": 0.00013037934471093682, | |
| "loss": 0.3981, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.0762509064395761, | |
| "learning_rate": 0.00013005240746044572, | |
| "loss": 0.3955, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.07249815363012721, | |
| "learning_rate": 0.00012972511671140125, | |
| "loss": 0.3626, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.4133565425872803, | |
| "eval_runtime": 31.5259, | |
| "eval_samples_per_second": 50.308, | |
| "eval_steps_per_second": 0.793, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.07447636591818245, | |
| "learning_rate": 0.0001293974763136383, | |
| "loss": 0.4022, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.07905695092853075, | |
| "learning_rate": 0.00012906949012110456, | |
| "loss": 0.4035, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.07325378961858443, | |
| "learning_rate": 0.0001287411619918152, | |
| "loss": 0.4045, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.07306244730070513, | |
| "learning_rate": 0.00012841249578780757, | |
| "loss": 0.3953, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.0805980331304115, | |
| "learning_rate": 0.00012808349537509563, | |
| "loss": 0.3823, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.08229744669326565, | |
| "learning_rate": 0.00012775416462362457, | |
| "loss": 0.371, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.07530542770296608, | |
| "learning_rate": 0.00012742450740722532, | |
| "loss": 0.3574, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.07743523802851904, | |
| "learning_rate": 0.00012709452760356884, | |
| "loss": 0.3614, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.08169294031775218, | |
| "learning_rate": 0.00012676422909412068, | |
| "loss": 0.4086, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.08069592093841153, | |
| "learning_rate": 0.00012643361576409516, | |
| "loss": 0.3769, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.07504167901203086, | |
| "learning_rate": 0.00012610269150240986, | |
| "loss": 0.4055, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.08350635209003442, | |
| "learning_rate": 0.00012577146020163968, | |
| "loss": 0.3864, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.07891619414281131, | |
| "learning_rate": 0.00012543992575797115, | |
| "loss": 0.4063, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.07415769914540568, | |
| "learning_rate": 0.00012510809207115666, | |
| "loss": 0.3716, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.0755092242652122, | |
| "learning_rate": 0.0001247759630444684, | |
| "loss": 0.3691, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.08024381151209611, | |
| "learning_rate": 0.00012444354258465268, | |
| "loss": 0.4106, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.08090035844250885, | |
| "learning_rate": 0.00012411083460188378, | |
| "loss": 0.4184, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.07776820546479746, | |
| "learning_rate": 0.00012377784300971807, | |
| "loss": 0.3606, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.07772136068905951, | |
| "learning_rate": 0.00012344457172504795, | |
| "loss": 0.3955, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.08071512021898622, | |
| "learning_rate": 0.0001231110246680558, | |
| "loss": 0.4257, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.07902285109418822, | |
| "learning_rate": 0.00012277720576216771, | |
| "loss": 0.3707, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.0709988454471743, | |
| "learning_rate": 0.00012244311893400763, | |
| "loss": 0.3341, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.077554128009626, | |
| "learning_rate": 0.00012210876811335087, | |
| "loss": 0.3993, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.07657330750558217, | |
| "learning_rate": 0.00012177415723307808, | |
| "loss": 0.3827, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.07827776040695841, | |
| "learning_rate": 0.00012143929022912894, | |
| "loss": 0.3627, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.0740345029436297, | |
| "learning_rate": 0.00012110417104045575, | |
| "loss": 0.3557, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.08549600954967101, | |
| "learning_rate": 0.00012076880360897736, | |
| "loss": 0.3682, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.07901141834734705, | |
| "learning_rate": 0.00012043319187953241, | |
| "loss": 0.3937, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.08120922500580939, | |
| "learning_rate": 0.00012009733979983337, | |
| "loss": 0.4023, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.07676937741717564, | |
| "learning_rate": 0.00011976125132041974, | |
| "loss": 0.3883, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.08145129881614924, | |
| "learning_rate": 0.00011942493039461184, | |
| "loss": 0.3876, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.07926723121096249, | |
| "learning_rate": 0.00011908838097846404, | |
| "loss": 0.3558, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.0809613287674327, | |
| "learning_rate": 0.0001187516070307186, | |
| "loss": 0.397, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.07954552358424609, | |
| "learning_rate": 0.00011841461251275867, | |
| "loss": 0.4052, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.07405170980250532, | |
| "learning_rate": 0.00011807740138856202, | |
| "loss": 0.3828, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.08521172352756448, | |
| "learning_rate": 0.00011773997762465429, | |
| "loss": 0.3883, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.07756062443249918, | |
| "learning_rate": 0.00011740234519006236, | |
| "loss": 0.3851, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.07980640763358252, | |
| "learning_rate": 0.0001170645080562676, | |
| "loss": 0.3941, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.09311924282141737, | |
| "learning_rate": 0.00011672647019715925, | |
| "loss": 0.4297, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.08822570082752848, | |
| "learning_rate": 0.00011638823558898762, | |
| "loss": 0.4127, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.08240686433611583, | |
| "learning_rate": 0.00011604980821031726, | |
| "loss": 0.384, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.08146116870793536, | |
| "learning_rate": 0.00011571119204198037, | |
| "loss": 0.3496, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.0790970883458089, | |
| "learning_rate": 0.00011537239106702969, | |
| "loss": 0.3684, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.0788954504336981, | |
| "learning_rate": 0.00011503340927069189, | |
| "loss": 0.3739, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.08021117125120701, | |
| "learning_rate": 0.0001146942506403205, | |
| "loss": 0.3544, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.07458926561485639, | |
| "learning_rate": 0.00011435491916534919, | |
| "loss": 0.3661, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.07758204916491954, | |
| "learning_rate": 0.00011401541883724474, | |
| "loss": 0.4001, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.0830475207327915, | |
| "learning_rate": 0.00011367575364946006, | |
| "loss": 0.3982, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.09271760063339704, | |
| "learning_rate": 0.00011333592759738729, | |
| "loss": 0.3823, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.07694651943262981, | |
| "learning_rate": 0.00011299594467831078, | |
| "loss": 0.4144, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.07788384291336206, | |
| "learning_rate": 0.00011265580889136007, | |
| "loss": 0.3858, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.08030421335332905, | |
| "learning_rate": 0.00011231552423746283, | |
| "loss": 0.3985, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.08325727227633425, | |
| "learning_rate": 0.00011197509471929779, | |
| "loss": 0.3666, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.07398668511660214, | |
| "learning_rate": 0.00011163452434124773, | |
| "loss": 0.3753, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.06977442653302289, | |
| "learning_rate": 0.0001112938171093523, | |
| "loss": 0.349, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.07654587312110067, | |
| "learning_rate": 0.00011095297703126093, | |
| "loss": 0.3642, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.09580311611958295, | |
| "learning_rate": 0.00011061200811618564, | |
| "loss": 0.4154, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.07509915904710483, | |
| "learning_rate": 0.00011027091437485404, | |
| "loss": 0.3411, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.08424016623153631, | |
| "learning_rate": 0.00010992969981946191, | |
| "loss": 0.4267, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.08608407016778004, | |
| "learning_rate": 0.00010958836846362621, | |
| "loss": 0.3944, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.08500940759924136, | |
| "learning_rate": 0.0001092469243223378, | |
| "loss": 0.3813, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.08045340329183402, | |
| "learning_rate": 0.00010890537141191417, | |
| "loss": 0.4101, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.08160668584828902, | |
| "learning_rate": 0.00010856371374995222, | |
| "loss": 0.4185, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.09122696966387649, | |
| "learning_rate": 0.00010822195535528106, | |
| "loss": 0.3965, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.07523917491848117, | |
| "learning_rate": 0.00010788010024791464, | |
| "loss": 0.3867, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.08187275857077707, | |
| "learning_rate": 0.00010753815244900458, | |
| "loss": 0.3651, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.07481860262974419, | |
| "learning_rate": 0.00010719611598079278, | |
| "loss": 0.3919, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.08213083716264738, | |
| "learning_rate": 0.00010685399486656406, | |
| "loss": 0.4088, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.07864566100598501, | |
| "learning_rate": 0.00010651179313059905, | |
| "loss": 0.385, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.06867707201915998, | |
| "learning_rate": 0.00010616951479812658, | |
| "loss": 0.3356, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.07752703169783293, | |
| "learning_rate": 0.00010582716389527658, | |
| "loss": 0.4016, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.08060511901628008, | |
| "learning_rate": 0.00010548474444903247, | |
| "loss": 0.3874, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.07725392144012032, | |
| "learning_rate": 0.0001051422604871841, | |
| "loss": 0.3953, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.07590291638786788, | |
| "learning_rate": 0.00010479971603828, | |
| "loss": 0.3685, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.08098405610120554, | |
| "learning_rate": 0.00010445711513158038, | |
| "loss": 0.4145, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.07792529270619988, | |
| "learning_rate": 0.00010411446179700943, | |
| "loss": 0.3879, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.07803877303978403, | |
| "learning_rate": 0.00010377176006510812, | |
| "loss": 0.4113, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.08254478846798866, | |
| "learning_rate": 0.00010342901396698659, | |
| "loss": 0.3622, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 0.40739139914512634, | |
| "eval_runtime": 31.5046, | |
| "eval_samples_per_second": 50.342, | |
| "eval_steps_per_second": 0.794, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.0861752861641254, | |
| "learning_rate": 0.00010308622753427692, | |
| "loss": 0.4153, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.08060738937219403, | |
| "learning_rate": 0.00010274340479908568, | |
| "loss": 0.3621, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.07455871544807684, | |
| "learning_rate": 0.0001024005497939464, | |
| "loss": 0.4044, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.07273274312303991, | |
| "learning_rate": 0.00010205766655177215, | |
| "loss": 0.3615, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.07557122903096708, | |
| "learning_rate": 0.00010171475910580824, | |
| "loss": 0.4087, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.07157984309995921, | |
| "learning_rate": 0.00010137183148958463, | |
| "loss": 0.3528, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.08189268272946562, | |
| "learning_rate": 0.00010102888773686852, | |
| "loss": 0.4107, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.0683151135884821, | |
| "learning_rate": 0.00010068593188161697, | |
| "loss": 0.3759, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.07153236662079392, | |
| "learning_rate": 0.00010034296795792937, | |
| "loss": 0.372, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.07338442025524573, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3418, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.07441870206852327, | |
| "learning_rate": 9.965703204207066e-05, | |
| "loss": 0.3687, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.0771105649193471, | |
| "learning_rate": 9.931406811838308e-05, | |
| "loss": 0.3522, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.07380948664015868, | |
| "learning_rate": 9.89711122631315e-05, | |
| "loss": 0.3609, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.08280755739037238, | |
| "learning_rate": 9.862816851041541e-05, | |
| "loss": 0.4113, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.08375223924539885, | |
| "learning_rate": 9.828524089419179e-05, | |
| "loss": 0.3699, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.08575384879702211, | |
| "learning_rate": 9.79423334482279e-05, | |
| "loss": 0.3661, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.08727666140464903, | |
| "learning_rate": 9.759945020605363e-05, | |
| "loss": 0.3715, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.08037894721613417, | |
| "learning_rate": 9.725659520091433e-05, | |
| "loss": 0.3893, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.07913116207392096, | |
| "learning_rate": 9.691377246572309e-05, | |
| "loss": 0.3864, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.08537848951324671, | |
| "learning_rate": 9.657098603301346e-05, | |
| "loss": 0.4407, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.07586746645084512, | |
| "learning_rate": 9.622823993489193e-05, | |
| "loss": 0.3843, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.08030491789417263, | |
| "learning_rate": 9.588553820299056e-05, | |
| "loss": 0.3646, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.07594015259093277, | |
| "learning_rate": 9.554288486841963e-05, | |
| "loss": 0.3635, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.08698031761165553, | |
| "learning_rate": 9.520028396172003e-05, | |
| "loss": 0.3938, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.08044005224836778, | |
| "learning_rate": 9.485773951281595e-05, | |
| "loss": 0.3786, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.0797861113193457, | |
| "learning_rate": 9.451525555096753e-05, | |
| "loss": 0.4071, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.07778511619729672, | |
| "learning_rate": 9.417283610472344e-05, | |
| "loss": 0.3803, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.08213674482933962, | |
| "learning_rate": 9.383048520187344e-05, | |
| "loss": 0.4265, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.07129154135692377, | |
| "learning_rate": 9.348820686940099e-05, | |
| "loss": 0.3372, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.07918362128766454, | |
| "learning_rate": 9.314600513343595e-05, | |
| "loss": 0.3904, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.07944741698853969, | |
| "learning_rate": 9.280388401920724e-05, | |
| "loss": 0.3791, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.077951468026884, | |
| "learning_rate": 9.246184755099545e-05, | |
| "loss": 0.3669, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.07699666002038329, | |
| "learning_rate": 9.211989975208538e-05, | |
| "loss": 0.3766, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.0758416555720215, | |
| "learning_rate": 9.177804464471898e-05, | |
| "loss": 0.3448, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 0.07745843786630063, | |
| "learning_rate": 9.143628625004779e-05, | |
| "loss": 0.3858, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.08217970720485462, | |
| "learning_rate": 9.109462858808586e-05, | |
| "loss": 0.3714, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.07395704142635354, | |
| "learning_rate": 9.075307567766222e-05, | |
| "loss": 0.3595, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.08320606902559918, | |
| "learning_rate": 9.041163153637381e-05, | |
| "loss": 0.4228, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.07751422791855053, | |
| "learning_rate": 9.00703001805381e-05, | |
| "loss": 0.3788, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.08130776009738187, | |
| "learning_rate": 8.972908562514598e-05, | |
| "loss": 0.3873, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.07606729027827926, | |
| "learning_rate": 8.93879918838144e-05, | |
| "loss": 0.3786, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.07164819932685276, | |
| "learning_rate": 8.904702296873912e-05, | |
| "loss": 0.3735, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.07729914588013745, | |
| "learning_rate": 8.870618289064776e-05, | |
| "loss": 0.3769, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.07563987823012108, | |
| "learning_rate": 8.836547565875227e-05, | |
| "loss": 0.3813, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 0.07922886095003479, | |
| "learning_rate": 8.802490528070223e-05, | |
| "loss": 0.3876, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.07359087278326075, | |
| "learning_rate": 8.76844757625372e-05, | |
| "loss": 0.3863, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.07421124570955039, | |
| "learning_rate": 8.734419110863996e-05, | |
| "loss": 0.3644, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.07599801309887802, | |
| "learning_rate": 8.70040553216892e-05, | |
| "loss": 0.3814, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.07888590295402388, | |
| "learning_rate": 8.666407240261272e-05, | |
| "loss": 0.3922, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.07700289203794641, | |
| "learning_rate": 8.632424635053997e-05, | |
| "loss": 0.3822, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 0.08587536136701782, | |
| "learning_rate": 8.598458116275531e-05, | |
| "loss": 0.3701, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.07524177119282785, | |
| "learning_rate": 8.564508083465079e-05, | |
| "loss": 0.3481, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.08074691952835882, | |
| "learning_rate": 8.530574935967952e-05, | |
| "loss": 0.3947, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.08251247714437773, | |
| "learning_rate": 8.496659072930813e-05, | |
| "loss": 0.3553, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.08246787559310244, | |
| "learning_rate": 8.462760893297033e-05, | |
| "loss": 0.3939, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.07337917868000356, | |
| "learning_rate": 8.428880795801965e-05, | |
| "loss": 0.3511, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 0.07646424474761701, | |
| "learning_rate": 8.395019178968274e-05, | |
| "loss": 0.3921, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.07685580162645157, | |
| "learning_rate": 8.36117644110124e-05, | |
| "loss": 0.3846, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.07114478103274646, | |
| "learning_rate": 8.327352980284076e-05, | |
| "loss": 0.3859, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 0.07462868914838419, | |
| "learning_rate": 8.293549194373243e-05, | |
| "loss": 0.3992, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.07791967530814532, | |
| "learning_rate": 8.259765480993766e-05, | |
| "loss": 0.3763, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.07414048548103445, | |
| "learning_rate": 8.226002237534572e-05, | |
| "loss": 0.3583, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.06937165079323315, | |
| "learning_rate": 8.192259861143801e-05, | |
| "loss": 0.3466, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.07303961077692538, | |
| "learning_rate": 8.158538748724139e-05, | |
| "loss": 0.3709, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.0790163481856328, | |
| "learning_rate": 8.124839296928144e-05, | |
| "loss": 0.3716, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 0.0801577404880072, | |
| "learning_rate": 8.091161902153595e-05, | |
| "loss": 0.4057, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.08035241810403845, | |
| "learning_rate": 8.057506960538819e-05, | |
| "loss": 0.3626, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.07532381558885316, | |
| "learning_rate": 8.023874867958027e-05, | |
| "loss": 0.3963, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.0814266145635628, | |
| "learning_rate": 7.990266020016667e-05, | |
| "loss": 0.3957, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.0862574311610671, | |
| "learning_rate": 7.95668081204676e-05, | |
| "loss": 0.4086, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.08320602145548657, | |
| "learning_rate": 7.923119639102268e-05, | |
| "loss": 0.3467, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.07036534614923647, | |
| "learning_rate": 7.889582895954427e-05, | |
| "loss": 0.3441, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 0.07551665506917347, | |
| "learning_rate": 7.85607097708711e-05, | |
| "loss": 0.3576, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.07576595562532126, | |
| "learning_rate": 7.822584276692191e-05, | |
| "loss": 0.3871, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.08167019073704809, | |
| "learning_rate": 7.789123188664914e-05, | |
| "loss": 0.4268, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.07923353923818714, | |
| "learning_rate": 7.755688106599241e-05, | |
| "loss": 0.4139, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.0751700699535381, | |
| "learning_rate": 7.722279423783231e-05, | |
| "loss": 0.3832, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.07740449362403487, | |
| "learning_rate": 7.688897533194424e-05, | |
| "loss": 0.3903, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.40031635761260986, | |
| "eval_runtime": 31.5013, | |
| "eval_samples_per_second": 50.347, | |
| "eval_steps_per_second": 0.794, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 0.0753926468365596, | |
| "learning_rate": 7.655542827495204e-05, | |
| "loss": 0.3861, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.0765452404420019, | |
| "learning_rate": 7.622215699028196e-05, | |
| "loss": 0.4013, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.07304309807157051, | |
| "learning_rate": 7.588916539811626e-05, | |
| "loss": 0.3522, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 0.07761435516519116, | |
| "learning_rate": 7.555645741534736e-05, | |
| "loss": 0.3849, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.07534622864164545, | |
| "learning_rate": 7.52240369555316e-05, | |
| "loss": 0.3453, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.07566234536455298, | |
| "learning_rate": 7.489190792884338e-05, | |
| "loss": 0.3811, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.07796684887294057, | |
| "learning_rate": 7.456007424202886e-05, | |
| "loss": 0.3816, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.07939927859969524, | |
| "learning_rate": 7.422853979836034e-05, | |
| "loss": 0.383, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.07858039926471795, | |
| "learning_rate": 7.389730849759017e-05, | |
| "loss": 0.3548, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.08709857407566311, | |
| "learning_rate": 7.356638423590485e-05, | |
| "loss": 0.3979, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.07713700765129777, | |
| "learning_rate": 7.323577090587935e-05, | |
| "loss": 0.3338, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.07638291321426217, | |
| "learning_rate": 7.290547239643117e-05, | |
| "loss": 0.369, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.0810045523880091, | |
| "learning_rate": 7.257549259277472e-05, | |
| "loss": 0.3735, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.07174415210201111, | |
| "learning_rate": 7.224583537637544e-05, | |
| "loss": 0.3568, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.07833604321691894, | |
| "learning_rate": 7.19165046249044e-05, | |
| "loss": 0.403, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 0.07296247157648875, | |
| "learning_rate": 7.158750421219244e-05, | |
| "loss": 0.367, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.06941929360097275, | |
| "learning_rate": 7.125883800818482e-05, | |
| "loss": 0.3494, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.07863938745183933, | |
| "learning_rate": 7.093050987889547e-05, | |
| "loss": 0.4009, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.07714414282808234, | |
| "learning_rate": 7.06025236863617e-05, | |
| "loss": 0.3771, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.07185026603624924, | |
| "learning_rate": 7.027488328859876e-05, | |
| "loss": 0.3755, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.07286891232090549, | |
| "learning_rate": 6.994759253955431e-05, | |
| "loss": 0.3569, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.0761553092206952, | |
| "learning_rate": 6.96206552890632e-05, | |
| "loss": 0.3754, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 0.07503382570698697, | |
| "learning_rate": 6.929407538280222e-05, | |
| "loss": 0.3812, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.08128387153215556, | |
| "learning_rate": 6.896785666224481e-05, | |
| "loss": 0.3984, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.07916631520762145, | |
| "learning_rate": 6.864200296461584e-05, | |
| "loss": 0.3921, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 0.08127958052701541, | |
| "learning_rate": 6.831651812284652e-05, | |
| "loss": 0.3892, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.0813173238661542, | |
| "learning_rate": 6.799140596552928e-05, | |
| "loss": 0.3592, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.0775910249032601, | |
| "learning_rate": 6.766667031687286e-05, | |
| "loss": 0.3751, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.07968426877838305, | |
| "learning_rate": 6.734231499665717e-05, | |
| "loss": 0.3925, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.07910046458954106, | |
| "learning_rate": 6.701834382018832e-05, | |
| "loss": 0.3995, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.07754633698823493, | |
| "learning_rate": 6.669476059825401e-05, | |
| "loss": 0.4047, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.07193870312921681, | |
| "learning_rate": 6.637156913707839e-05, | |
| "loss": 0.319, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.07242747817024907, | |
| "learning_rate": 6.604877323827755e-05, | |
| "loss": 0.3471, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.07424958429296438, | |
| "learning_rate": 6.572637669881458e-05, | |
| "loss": 0.3593, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.0748457928908322, | |
| "learning_rate": 6.540438331095509e-05, | |
| "loss": 0.3898, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.07738661216581003, | |
| "learning_rate": 6.508279686222243e-05, | |
| "loss": 0.3605, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.07844744837219766, | |
| "learning_rate": 6.47616211353534e-05, | |
| "loss": 0.3724, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 0.0838617355349577, | |
| "learning_rate": 6.444085990825338e-05, | |
| "loss": 0.3575, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.08205622905796599, | |
| "learning_rate": 6.412051695395225e-05, | |
| "loss": 0.3771, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.07571568577769608, | |
| "learning_rate": 6.380059604055974e-05, | |
| "loss": 0.3749, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 0.07974094837676436, | |
| "learning_rate": 6.34811009312214e-05, | |
| "loss": 0.4128, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.0791063012952443, | |
| "learning_rate": 6.316203538407397e-05, | |
| "loss": 0.3801, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.07430747651477144, | |
| "learning_rate": 6.284340315220146e-05, | |
| "loss": 0.357, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.07299391948552236, | |
| "learning_rate": 6.252520798359092e-05, | |
| "loss": 0.3312, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.07769253661565559, | |
| "learning_rate": 6.22074536210882e-05, | |
| "loss": 0.3829, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.07366174690959486, | |
| "learning_rate": 6.18901438023543e-05, | |
| "loss": 0.3401, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.08390773003798377, | |
| "learning_rate": 6.157328225982097e-05, | |
| "loss": 0.4356, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 0.07698300587520791, | |
| "learning_rate": 6.125687272064713e-05, | |
| "loss": 0.3704, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.07673890630827201, | |
| "learning_rate": 6.0940918906674726e-05, | |
| "loss": 0.3748, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.08003154714235751, | |
| "learning_rate": 6.0625424534385425e-05, | |
| "loss": 0.3882, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.07380881788709838, | |
| "learning_rate": 6.031039331485631e-05, | |
| "loss": 0.3858, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.07590814319305429, | |
| "learning_rate": 5.9995828953716695e-05, | |
| "loss": 0.3231, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.07665854652804305, | |
| "learning_rate": 5.9681735151104265e-05, | |
| "loss": 0.3803, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 0.0740586109186508, | |
| "learning_rate": 5.936811560162169e-05, | |
| "loss": 0.3913, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.07034245488734069, | |
| "learning_rate": 5.905497399429316e-05, | |
| "loss": 0.3414, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.07089519782322849, | |
| "learning_rate": 5.87423140125209e-05, | |
| "loss": 0.3383, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.07570770556387404, | |
| "learning_rate": 5.8430139334041966e-05, | |
| "loss": 0.4171, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.07279724711891891, | |
| "learning_rate": 5.811845363088477e-05, | |
| "loss": 0.3944, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.07349384624259331, | |
| "learning_rate": 5.780726056932629e-05, | |
| "loss": 0.3433, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.07288506225996622, | |
| "learning_rate": 5.749656380984844e-05, | |
| "loss": 0.3577, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.0781730206249498, | |
| "learning_rate": 5.718636700709537e-05, | |
| "loss": 0.3987, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.07288596629518923, | |
| "learning_rate": 5.687667380983037e-05, | |
| "loss": 0.3654, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 0.07652737726620985, | |
| "learning_rate": 5.656748786089303e-05, | |
| "loss": 0.3724, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.07500088313695388, | |
| "learning_rate": 5.625881279715615e-05, | |
| "loss": 0.3348, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.07961888163877841, | |
| "learning_rate": 5.59506522494832e-05, | |
| "loss": 0.3819, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.07660615744321793, | |
| "learning_rate": 5.5643009842685554e-05, | |
| "loss": 0.3439, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.0797276678480634, | |
| "learning_rate": 5.5335889195479785e-05, | |
| "loss": 0.365, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.0732611981197724, | |
| "learning_rate": 5.502929392044528e-05, | |
| "loss": 0.3528, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 0.0785303715242327, | |
| "learning_rate": 5.472322762398139e-05, | |
| "loss": 0.3818, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.08251705391680844, | |
| "learning_rate": 5.4417693906265365e-05, | |
| "loss": 0.3806, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.08454732130870848, | |
| "learning_rate": 5.411269636120984e-05, | |
| "loss": 0.4001, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.07768228381369272, | |
| "learning_rate": 5.380823857642069e-05, | |
| "loss": 0.3899, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.07497176157800585, | |
| "learning_rate": 5.350432413315455e-05, | |
| "loss": 0.3327, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.08034807155890702, | |
| "learning_rate": 5.3200956606277006e-05, | |
| "loss": 0.3792, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.08799556189760001, | |
| "learning_rate": 5.289813956422036e-05, | |
| "loss": 0.3565, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 0.0754987027227741, | |
| "learning_rate": 5.259587656894174e-05, | |
| "loss": 0.3574, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.08311898696454592, | |
| "learning_rate": 5.2294171175881125e-05, | |
| "loss": 0.4112, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.0830498252463038, | |
| "learning_rate": 5.199302693391959e-05, | |
| "loss": 0.3737, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.39541947841644287, | |
| "eval_runtime": 31.4984, | |
| "eval_samples_per_second": 50.352, | |
| "eval_steps_per_second": 0.794, | |
| "step": 624 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 936, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 312, | |
| "total_flos": 3.41954773545019e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |