| { | |
| "best_metric": 1.20897376537323, | |
| "best_model_checkpoint": "model_training/reprover_err/checkpoints-random-09-08-18-00/checkpoint-250", | |
| "epoch": 7.302231237322515, | |
| "eval_steps": 25, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08113590263691683, | |
| "grad_norm": 23.601030349731445, | |
| "learning_rate": 5.102040816326531e-05, | |
| "loss": 12.5644, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16227180527383367, | |
| "grad_norm": 10.2500638961792, | |
| "learning_rate": 0.00010204081632653062, | |
| "loss": 7.6824, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2434077079107505, | |
| "grad_norm": 0.5588569641113281, | |
| "learning_rate": 0.00015306122448979594, | |
| "loss": 4.0204, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32454361054766734, | |
| "grad_norm": 0.23660239577293396, | |
| "learning_rate": 0.00020408163265306123, | |
| "loss": 3.6085, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4056795131845842, | |
| "grad_norm": 0.249436616897583, | |
| "learning_rate": 0.00025510204081632655, | |
| "loss": 3.5044, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4056795131845842, | |
| "eval_loss": 3.385061025619507, | |
| "eval_runtime": 98.6159, | |
| "eval_samples_per_second": 10.14, | |
| "eval_steps_per_second": 0.639, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.486815415821501, | |
| "grad_norm": 1.356109857559204, | |
| "learning_rate": 0.0003061224489795919, | |
| "loss": 3.4346, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5679513184584178, | |
| "grad_norm": 1.5906275510787964, | |
| "learning_rate": 0.00035714285714285714, | |
| "loss": 2.5708, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6490872210953347, | |
| "grad_norm": 0.7469751834869385, | |
| "learning_rate": 0.00040816326530612246, | |
| "loss": 1.9541, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7302231237322515, | |
| "grad_norm": 0.46847933530807495, | |
| "learning_rate": 0.0004591836734693878, | |
| "loss": 1.7316, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8113590263691683, | |
| "grad_norm": 0.7208541035652161, | |
| "learning_rate": 0.0004999935985425297, | |
| "loss": 1.6138, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8113590263691683, | |
| "eval_loss": 1.387947678565979, | |
| "eval_runtime": 98.6024, | |
| "eval_samples_per_second": 10.142, | |
| "eval_steps_per_second": 0.639, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8924949290060852, | |
| "grad_norm": 0.31425440311431885, | |
| "learning_rate": 0.0004997695819512612, | |
| "loss": 1.5905, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.973630831643002, | |
| "grad_norm": 0.4940365254878998, | |
| "learning_rate": 0.0004992258202402822, | |
| "loss": 1.5013, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.054766734279919, | |
| "grad_norm": 0.3743211328983307, | |
| "learning_rate": 0.0004983630095117843, | |
| "loss": 1.4282, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.1359026369168357, | |
| "grad_norm": 0.46512871980667114, | |
| "learning_rate": 0.0004971822543018662, | |
| "loss": 1.386, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2170385395537526, | |
| "grad_norm": 0.2764676511287689, | |
| "learning_rate": 0.0004956850661665511, | |
| "loss": 1.4375, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2170385395537526, | |
| "eval_loss": 1.2822275161743164, | |
| "eval_runtime": 98.6288, | |
| "eval_samples_per_second": 10.139, | |
| "eval_steps_per_second": 0.639, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2981744421906694, | |
| "grad_norm": 0.2621470093727112, | |
| "learning_rate": 0.0004938733617467517, | |
| "loss": 1.4209, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 0.14090226590633392, | |
| "learning_rate": 0.0004917494603146632, | |
| "loss": 1.3766, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.460446247464503, | |
| "grad_norm": 0.11969256401062012, | |
| "learning_rate": 0.0004893160808047222, | |
| "loss": 1.3755, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.5415821501014197, | |
| "grad_norm": 0.18346261978149414, | |
| "learning_rate": 0.00048657633833293557, | |
| "loss": 1.4168, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.6227180527383367, | |
| "grad_norm": 0.3624500036239624, | |
| "learning_rate": 0.0004835337402090316, | |
| "loss": 1.3587, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6227180527383367, | |
| "eval_loss": 1.2857593297958374, | |
| "eval_runtime": 98.6659, | |
| "eval_samples_per_second": 10.135, | |
| "eval_steps_per_second": 0.639, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.7038539553752536, | |
| "grad_norm": 0.5834723114967346, | |
| "learning_rate": 0.0004801921814465414, | |
| "loss": 1.3857, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7849898580121704, | |
| "grad_norm": 0.37480711936950684, | |
| "learning_rate": 0.00047655593977655674, | |
| "loss": 1.3745, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.866125760649087, | |
| "grad_norm": 0.31830307841300964, | |
| "learning_rate": 0.0004726296701715489, | |
| "loss": 1.3517, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.947261663286004, | |
| "grad_norm": 0.14451760053634644, | |
| "learning_rate": 0.00046841839888625623, | |
| "loss": 1.3346, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.028397565922921, | |
| "grad_norm": 0.22967207431793213, | |
| "learning_rate": 0.0004639275170232734, | |
| "loss": 1.3735, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.028397565922921, | |
| "eval_loss": 1.2710317373275757, | |
| "eval_runtime": 98.685, | |
| "eval_samples_per_second": 10.133, | |
| "eval_steps_per_second": 0.638, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.109533468559838, | |
| "grad_norm": 0.16856279969215393, | |
| "learning_rate": 0.0004591627736315743, | |
| "loss": 1.3417, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.1906693711967544, | |
| "grad_norm": 0.2670596241950989, | |
| "learning_rate": 0.0004541302683468084, | |
| "loss": 1.3135, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.2718052738336714, | |
| "grad_norm": 0.8827645778656006, | |
| "learning_rate": 0.0004488364435827881, | |
| "loss": 1.3399, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.3872511088848114, | |
| "learning_rate": 0.00044328807628416644, | |
| "loss": 1.3888, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.4340770791075053, | |
| "grad_norm": 0.5543010234832764, | |
| "learning_rate": 0.0004374922692508611, | |
| "loss": 1.3678, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4340770791075053, | |
| "eval_loss": 1.283129096031189, | |
| "eval_runtime": 98.6825, | |
| "eval_samples_per_second": 10.134, | |
| "eval_steps_per_second": 0.638, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.5152129817444218, | |
| "grad_norm": 0.3389835059642792, | |
| "learning_rate": 0.0004314564420453311, | |
| "loss": 1.3614, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.5963488843813387, | |
| "grad_norm": 0.38079357147216797, | |
| "learning_rate": 0.0004251883214943475, | |
| "loss": 1.342, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.6774847870182557, | |
| "grad_norm": 0.23523402214050293, | |
| "learning_rate": 0.0004186959317974155, | |
| "loss": 1.3378, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": 0.18377311527729034, | |
| "learning_rate": 0.00041198758425451266, | |
| "loss": 1.3272, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.839756592292089, | |
| "grad_norm": 0.4048319458961487, | |
| "learning_rate": 0.00040507186662629185, | |
| "loss": 1.3431, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.839756592292089, | |
| "eval_loss": 1.252098798751831, | |
| "eval_runtime": 98.7407, | |
| "eval_samples_per_second": 10.128, | |
| "eval_steps_per_second": 0.638, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.920892494929006, | |
| "grad_norm": 1.1706334352493286, | |
| "learning_rate": 0.0003979576321403705, | |
| "loss": 1.3111, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.002028397565923, | |
| "grad_norm": 0.3772040903568268, | |
| "learning_rate": 0.0003906539881577793, | |
| "loss": 1.3515, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.08316430020284, | |
| "grad_norm": 0.4847799241542816, | |
| "learning_rate": 0.0003831702845140801, | |
| "loss": 1.3442, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.1643002028397564, | |
| "grad_norm": 0.35955315828323364, | |
| "learning_rate": 0.00037551610155007613, | |
| "loss": 1.338, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.2454361054766734, | |
| "grad_norm": 0.30124932527542114, | |
| "learning_rate": 0.00036770123784744027, | |
| "loss": 1.3001, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.2454361054766734, | |
| "eval_loss": 1.2483381032943726, | |
| "eval_runtime": 98.609, | |
| "eval_samples_per_second": 10.141, | |
| "eval_steps_per_second": 0.639, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.3265720081135903, | |
| "grad_norm": 0.4706196188926697, | |
| "learning_rate": 0.00035973569768495855, | |
| "loss": 1.3099, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.4077079107505073, | |
| "grad_norm": 0.4052978754043579, | |
| "learning_rate": 0.0003516296782314491, | |
| "loss": 1.2863, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.4888438133874238, | |
| "grad_norm": 0.4775325655937195, | |
| "learning_rate": 0.00034339355649175095, | |
| "loss": 1.3306, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.5699797160243407, | |
| "grad_norm": 0.2688348591327667, | |
| "learning_rate": 0.00033503787602249364, | |
| "loss": 1.2971, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.6511156186612577, | |
| "grad_norm": 0.16574963927268982, | |
| "learning_rate": 0.00032657333343465356, | |
| "loss": 1.2761, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.6511156186612577, | |
| "eval_loss": 1.2276986837387085, | |
| "eval_runtime": 98.6417, | |
| "eval_samples_per_second": 10.138, | |
| "eval_steps_per_second": 0.639, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.732251521298174, | |
| "grad_norm": 0.16287527978420258, | |
| "learning_rate": 0.0003180107647001769, | |
| "loss": 1.2611, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.813387423935091, | |
| "grad_norm": 0.12902116775512695, | |
| "learning_rate": 0.0003093611312801979, | |
| "loss": 1.2933, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.894523326572008, | |
| "grad_norm": 0.19913575053215027, | |
| "learning_rate": 0.00030063550609261025, | |
| "loss": 1.2926, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.975659229208925, | |
| "grad_norm": 0.39822715520858765, | |
| "learning_rate": 0.000291845059336957, | |
| "loss": 1.3097, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 4.056795131845842, | |
| "grad_norm": 0.5150278806686401, | |
| "learning_rate": 0.0002830010441947834, | |
| "loss": 1.2907, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.056795131845842, | |
| "eval_loss": 1.20897376537323, | |
| "eval_runtime": 98.62, | |
| "eval_samples_per_second": 10.14, | |
| "eval_steps_per_second": 0.639, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.137931034482759, | |
| "grad_norm": 0.3091956675052643, | |
| "learning_rate": 0.00027411478242376017, | |
| "loss": 1.2904, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 4.219066937119676, | |
| "grad_norm": 0.2656278908252716, | |
| "learning_rate": 0.00026519764986401774, | |
| "loss": 1.2999, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.300202839756592, | |
| "grad_norm": 0.1790953278541565, | |
| "learning_rate": 0.000256261061875247, | |
| "loss": 1.2549, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.381338742393509, | |
| "grad_norm": 0.15690313279628754, | |
| "learning_rate": 0.0002473164587232079, | |
| "loss": 1.3, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.462474645030426, | |
| "grad_norm": 0.12892165780067444, | |
| "learning_rate": 0.0002383752909343547, | |
| "loss": 1.2946, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.462474645030426, | |
| "eval_loss": 1.2234361171722412, | |
| "eval_runtime": 98.5999, | |
| "eval_samples_per_second": 10.142, | |
| "eval_steps_per_second": 0.639, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.543610547667343, | |
| "grad_norm": 0.136368989944458, | |
| "learning_rate": 0.0002294490046373259, | |
| "loss": 1.2971, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.62474645030426, | |
| "grad_norm": 0.07033926248550415, | |
| "learning_rate": 0.00022054902691006405, | |
| "loss": 1.2991, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.08667398989200592, | |
| "learning_rate": 0.00021168675115132315, | |
| "loss": 1.291, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.787018255578094, | |
| "grad_norm": 0.08972382545471191, | |
| "learning_rate": 0.00020287352249529153, | |
| "loss": 1.3007, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.8681541582150105, | |
| "grad_norm": 0.1722905933856964, | |
| "learning_rate": 0.00019412062328800044, | |
| "loss": 1.2729, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.8681541582150105, | |
| "eval_loss": 1.2213460206985474, | |
| "eval_runtime": 98.5784, | |
| "eval_samples_per_second": 10.144, | |
| "eval_steps_per_second": 0.639, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.9492900608519275, | |
| "grad_norm": 0.10548505187034607, | |
| "learning_rate": 0.000185439258644112, | |
| "loss": 1.2854, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 5.0304259634888435, | |
| "grad_norm": 0.08486346155405045, | |
| "learning_rate": 0.00017684054210257517, | |
| "loss": 1.236, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.1115618661257605, | |
| "grad_norm": 0.10991238802671432, | |
| "learning_rate": 0.00016833548139951395, | |
| "loss": 1.2712, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 5.192697768762677, | |
| "grad_norm": 0.06149250268936157, | |
| "learning_rate": 0.0001599349643765599, | |
| "loss": 1.2807, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.273833671399594, | |
| "grad_norm": 0.17640946805477142, | |
| "learning_rate": 0.0001516497450426686, | |
| "loss": 1.3158, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.273833671399594, | |
| "eval_loss": 1.2180273532867432, | |
| "eval_runtime": 98.5761, | |
| "eval_samples_per_second": 10.144, | |
| "eval_steps_per_second": 0.639, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.354969574036511, | |
| "grad_norm": 0.46290215849876404, | |
| "learning_rate": 0.00014349042980726362, | |
| "loss": 1.2482, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.436105476673428, | |
| "grad_norm": 0.16729195415973663, | |
| "learning_rate": 0.0001354674639023318, | |
| "loss": 1.2903, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.517241379310345, | |
| "grad_norm": 0.24489770829677582, | |
| "learning_rate": 0.00012759111801085066, | |
| "loss": 1.2757, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.598377281947261, | |
| "grad_norm": 0.23532100021839142, | |
| "learning_rate": 0.00011987147511866788, | |
| "loss": 1.2928, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 5.679513184584178, | |
| "grad_norm": 0.07568836212158203, | |
| "learning_rate": 0.00011231841760666186, | |
| "loss": 1.2722, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.679513184584178, | |
| "eval_loss": 1.2159314155578613, | |
| "eval_runtime": 98.5804, | |
| "eval_samples_per_second": 10.144, | |
| "eval_steps_per_second": 0.639, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.760649087221095, | |
| "grad_norm": 0.07196550071239471, | |
| "learning_rate": 0.0001049416145997094, | |
| "loss": 1.2969, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 5.841784989858012, | |
| "grad_norm": 0.0853937566280365, | |
| "learning_rate": 9.775050958865584e-05, | |
| "loss": 1.306, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.922920892494929, | |
| "grad_norm": 0.05001223087310791, | |
| "learning_rate": 9.075430834113152e-05, | |
| "loss": 1.2304, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 6.004056795131846, | |
| "grad_norm": 0.058833617717027664, | |
| "learning_rate": 8.396196711669335e-05, | |
| "loss": 1.2746, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.085192697768763, | |
| "grad_norm": 0.07061880826950073, | |
| "learning_rate": 7.738218120137671e-05, | |
| "loss": 1.2522, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.085192697768763, | |
| "eval_loss": 1.2192745208740234, | |
| "eval_runtime": 98.5743, | |
| "eval_samples_per_second": 10.145, | |
| "eval_steps_per_second": 0.639, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.16632860040568, | |
| "grad_norm": 0.06949684768915176, | |
| "learning_rate": 7.102337377633394e-05, | |
| "loss": 1.2678, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.247464503042596, | |
| "grad_norm": 0.08404209464788437, | |
| "learning_rate": 6.489368513481228e-05, | |
| "loss": 1.2792, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 6.328600405679513, | |
| "grad_norm": 0.08185689151287079, | |
| "learning_rate": 5.9000962261273136e-05, | |
| "loss": 1.2779, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.40973630831643, | |
| "grad_norm": 0.04312283918261528, | |
| "learning_rate": 5.3352748785993164e-05, | |
| "loss": 1.3018, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 6.490872210953347, | |
| "grad_norm": 0.07406298071146011, | |
| "learning_rate": 4.795627532800806e-05, | |
| "loss": 1.2636, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.490872210953347, | |
| "eval_loss": 1.2143380641937256, | |
| "eval_runtime": 98.6065, | |
| "eval_samples_per_second": 10.141, | |
| "eval_steps_per_second": 0.639, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.572008113590264, | |
| "grad_norm": 0.043406181037425995, | |
| "learning_rate": 4.281845023876074e-05, | |
| "loss": 1.2578, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 6.653144016227181, | |
| "grad_norm": 0.07357024401426315, | |
| "learning_rate": 3.794585075830329e-05, | |
| "loss": 1.2472, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.734279918864098, | |
| "grad_norm": 0.05774565041065216, | |
| "learning_rate": 3.334471459537497e-05, | |
| "loss": 1.3082, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 6.8154158215010145, | |
| "grad_norm": 0.054679855704307556, | |
| "learning_rate": 2.902093194213526e-05, | |
| "loss": 1.2782, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.896551724137931, | |
| "grad_norm": 0.050430841743946075, | |
| "learning_rate": 2.4980037933772488e-05, | |
| "loss": 1.3043, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.896551724137931, | |
| "eval_loss": 1.2151918411254883, | |
| "eval_runtime": 98.562, | |
| "eval_samples_per_second": 10.146, | |
| "eval_steps_per_second": 0.639, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.9776876267748476, | |
| "grad_norm": 0.041136015206575394, | |
| "learning_rate": 2.122720556264357e-05, | |
| "loss": 1.2673, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": 0.03708193823695183, | |
| "learning_rate": 1.776723905601438e-05, | |
| "loss": 1.2496, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 7.139959432048681, | |
| "grad_norm": 0.055347807705402374, | |
| "learning_rate": 1.4604567725877926e-05, | |
| "loss": 1.2835, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.221095334685598, | |
| "grad_norm": 0.040714431554079056, | |
| "learning_rate": 1.1743240298725116e-05, | |
| "loss": 1.3163, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 7.302231237322515, | |
| "grad_norm": 0.03776278346776962, | |
| "learning_rate": 9.18691973252539e-06, | |
| "loss": 1.2647, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.302231237322515, | |
| "eval_loss": 1.2177557945251465, | |
| "eval_runtime": 98.5774, | |
| "eval_samples_per_second": 10.144, | |
| "eval_steps_per_second": 0.639, | |
| "step": 450 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 488, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.7034254328345395e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |