| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 2352, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_entropy": 0.7441253011463252, |
| "eval_loss": 2.4717867374420166, |
| "eval_mean_token_accuracy": 0.6263054841347323, |
| "eval_num_tokens": 0.0, |
| "eval_runtime": 44.5378, |
| "eval_samples_per_second": 23.463, |
| "eval_steps_per_second": 5.883, |
| "step": 0 |
| }, |
| { |
| "entropy": 0.7895201802253723, |
| "epoch": 0.004251700680272109, |
| "grad_norm": 0.8038196563720703, |
| "learning_rate": 9.961734693877551e-05, |
| "loss": 2.4038867950439453, |
| "mean_token_accuracy": 0.6224425852298736, |
| "num_tokens": 9328.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.8704251646995544, |
| "epoch": 0.008503401360544218, |
| "grad_norm": 0.7324869632720947, |
| "learning_rate": 9.91921768707483e-05, |
| "loss": 1.9501838684082031, |
| "mean_token_accuracy": 0.6429464161396027, |
| "num_tokens": 19473.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.0007735908031463, |
| "epoch": 0.012755102040816327, |
| "grad_norm": 1.2104312181472778, |
| "learning_rate": 9.876700680272109e-05, |
| "loss": 1.489585781097412, |
| "mean_token_accuracy": 0.6886208653450012, |
| "num_tokens": 29449.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.2490371704101562, |
| "epoch": 0.017006802721088437, |
| "grad_norm": 0.35242822766304016, |
| "learning_rate": 9.834183673469389e-05, |
| "loss": 1.4031854629516602, |
| "mean_token_accuracy": 0.6893938302993774, |
| "num_tokens": 38885.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.156481719017029, |
| "epoch": 0.021258503401360544, |
| "grad_norm": 0.29233095049858093, |
| "learning_rate": 9.791666666666667e-05, |
| "loss": 1.13862886428833, |
| "mean_token_accuracy": 0.7356042921543121, |
| "num_tokens": 49658.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.0561675131320953, |
| "epoch": 0.025510204081632654, |
| "grad_norm": 0.44513002038002014, |
| "learning_rate": 9.749149659863947e-05, |
| "loss": 1.1001633644104003, |
| "mean_token_accuracy": 0.7346036016941071, |
| "num_tokens": 60560.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.0129335343837738, |
| "epoch": 0.02976190476190476, |
| "grad_norm": 0.35273969173431396, |
| "learning_rate": 9.706632653061225e-05, |
| "loss": 1.0496091842651367, |
| "mean_token_accuracy": 0.7338723540306091, |
| "num_tokens": 73767.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.9904452860355377, |
| "epoch": 0.034013605442176874, |
| "grad_norm": 0.20354461669921875, |
| "learning_rate": 9.664115646258503e-05, |
| "loss": 0.9870148658752441, |
| "mean_token_accuracy": 0.7565846800804138, |
| "num_tokens": 85087.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.9738265931606293, |
| "epoch": 0.03826530612244898, |
| "grad_norm": 0.45790979266166687, |
| "learning_rate": 9.621598639455783e-05, |
| "loss": 0.9613595008850098, |
| "mean_token_accuracy": 0.7610337018966675, |
| "num_tokens": 95022.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.9440798819065094, |
| "epoch": 0.04251700680272109, |
| "grad_norm": 0.35626640915870667, |
| "learning_rate": 9.579081632653061e-05, |
| "loss": 0.9162805557250977, |
| "mean_token_accuracy": 0.7618738412857056, |
| "num_tokens": 106825.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.9322093605995179, |
| "epoch": 0.0467687074829932, |
| "grad_norm": 0.41860198974609375, |
| "learning_rate": 9.536564625850341e-05, |
| "loss": 0.9208142280578613, |
| "mean_token_accuracy": 0.7668713092803955, |
| "num_tokens": 117627.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.8814590692520141, |
| "epoch": 0.05102040816326531, |
| "grad_norm": 0.5872869491577148, |
| "learning_rate": 9.494047619047619e-05, |
| "loss": 0.8783014297485352, |
| "mean_token_accuracy": 0.7709871232509613, |
| "num_tokens": 129618.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.86140576004982, |
| "epoch": 0.055272108843537414, |
| "grad_norm": 0.4151027798652649, |
| "learning_rate": 9.451530612244899e-05, |
| "loss": 0.8385090827941895, |
| "mean_token_accuracy": 0.7878557801246643, |
| "num_tokens": 140476.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.7823852598667145, |
| "epoch": 0.05952380952380952, |
| "grad_norm": 0.6097142696380615, |
| "learning_rate": 9.409013605442177e-05, |
| "loss": 0.7834642887115478, |
| "mean_token_accuracy": 0.7922966778278351, |
| "num_tokens": 152252.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.8885609090328217, |
| "epoch": 0.06377551020408163, |
| "grad_norm": 0.3831205368041992, |
| "learning_rate": 9.366496598639456e-05, |
| "loss": 0.9057139396667481, |
| "mean_token_accuracy": 0.7586827576160431, |
| "num_tokens": 162998.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.8506790935993195, |
| "epoch": 0.06802721088435375, |
| "grad_norm": 0.4612574279308319, |
| "learning_rate": 9.323979591836735e-05, |
| "loss": 0.8219076156616211, |
| "mean_token_accuracy": 0.7892741382122039, |
| "num_tokens": 173248.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.85696662068367, |
| "epoch": 0.07227891156462585, |
| "grad_norm": 0.6407354474067688, |
| "learning_rate": 9.281462585034014e-05, |
| "loss": 0.8771568298339844, |
| "mean_token_accuracy": 0.7746504783630371, |
| "num_tokens": 183540.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.8503131151199341, |
| "epoch": 0.07653061224489796, |
| "grad_norm": 0.4775673449039459, |
| "learning_rate": 9.238945578231293e-05, |
| "loss": 0.7829782962799072, |
| "mean_token_accuracy": 0.7903713524341583, |
| "num_tokens": 194744.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.7273110747337341, |
| "epoch": 0.08078231292517007, |
| "grad_norm": 0.28129827976226807, |
| "learning_rate": 9.196428571428572e-05, |
| "loss": 0.7294204235076904, |
| "mean_token_accuracy": 0.8032773494720459, |
| "num_tokens": 207174.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.7966374695301056, |
| "epoch": 0.08503401360544217, |
| "grad_norm": 0.4943501651287079, |
| "learning_rate": 9.153911564625851e-05, |
| "loss": 0.8117904663085938, |
| "mean_token_accuracy": 0.7718977212905884, |
| "num_tokens": 217341.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.7621297895908355, |
| "epoch": 0.08928571428571429, |
| "grad_norm": 0.7795273661613464, |
| "learning_rate": 9.11139455782313e-05, |
| "loss": 0.7390175819396972, |
| "mean_token_accuracy": 0.7991273105144501, |
| "num_tokens": 227481.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.7846836626529694, |
| "epoch": 0.0935374149659864, |
| "grad_norm": 0.5696049928665161, |
| "learning_rate": 9.068877551020408e-05, |
| "loss": 0.7595390796661377, |
| "mean_token_accuracy": 0.788711428642273, |
| "num_tokens": 237612.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.7737141489982605, |
| "epoch": 0.0977891156462585, |
| "grad_norm": 0.5130123496055603, |
| "learning_rate": 9.026360544217687e-05, |
| "loss": 0.7576333522796631, |
| "mean_token_accuracy": 0.7758967220783234, |
| "num_tokens": 248218.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.6375986337661743, |
| "epoch": 0.10204081632653061, |
| "grad_norm": 0.8193577527999878, |
| "learning_rate": 8.983843537414967e-05, |
| "loss": 0.6211213111877442, |
| "mean_token_accuracy": 0.8208125472068787, |
| "num_tokens": 258441.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.6664006829261779, |
| "epoch": 0.10629251700680271, |
| "grad_norm": 0.6085699796676636, |
| "learning_rate": 8.941326530612245e-05, |
| "loss": 0.694005823135376, |
| "mean_token_accuracy": 0.8076555073261261, |
| "num_tokens": 268684.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.7731355726718903, |
| "epoch": 0.11054421768707483, |
| "grad_norm": 0.669662356376648, |
| "learning_rate": 8.898809523809524e-05, |
| "loss": 0.7673550605773926, |
| "mean_token_accuracy": 0.7881227731704712, |
| "num_tokens": 279434.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.6918620884418487, |
| "epoch": 0.11479591836734694, |
| "grad_norm": 0.41331204771995544, |
| "learning_rate": 8.856292517006803e-05, |
| "loss": 0.6603828430175781, |
| "mean_token_accuracy": 0.7999509751796723, |
| "num_tokens": 292081.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.6284413754940033, |
| "epoch": 0.11904761904761904, |
| "grad_norm": 0.5364882946014404, |
| "learning_rate": 8.813775510204082e-05, |
| "loss": 0.6319595813751221, |
| "mean_token_accuracy": 0.8188855946063995, |
| "num_tokens": 302835.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.7235157012939453, |
| "epoch": 0.12329931972789115, |
| "grad_norm": 0.6309073567390442, |
| "learning_rate": 8.77125850340136e-05, |
| "loss": 0.7478713512420654, |
| "mean_token_accuracy": 0.7892998337745667, |
| "num_tokens": 312703.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.6613646924495697, |
| "epoch": 0.12755102040816327, |
| "grad_norm": 0.6847456693649292, |
| "learning_rate": 8.72874149659864e-05, |
| "loss": 0.6457613945007324, |
| "mean_token_accuracy": 0.8177429616451264, |
| "num_tokens": 322433.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.6452407896518707, |
| "epoch": 0.13180272108843538, |
| "grad_norm": 0.846867561340332, |
| "learning_rate": 8.68622448979592e-05, |
| "loss": 0.646483039855957, |
| "mean_token_accuracy": 0.8097379863262176, |
| "num_tokens": 333425.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.6624458074569702, |
| "epoch": 0.1360544217687075, |
| "grad_norm": 0.5457995533943176, |
| "learning_rate": 8.643707482993198e-05, |
| "loss": 0.6448498249053956, |
| "mean_token_accuracy": 0.8157779753208161, |
| "num_tokens": 345275.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.653342092037201, |
| "epoch": 0.14030612244897958, |
| "grad_norm": 0.5937319397926331, |
| "learning_rate": 8.601190476190477e-05, |
| "loss": 0.657109546661377, |
| "mean_token_accuracy": 0.7984300255775452, |
| "num_tokens": 355488.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.7131676137447357, |
| "epoch": 0.1445578231292517, |
| "grad_norm": 0.8101398944854736, |
| "learning_rate": 8.558673469387756e-05, |
| "loss": 0.7153036594390869, |
| "mean_token_accuracy": 0.7985480785369873, |
| "num_tokens": 366696.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.708580482006073, |
| "epoch": 0.1488095238095238, |
| "grad_norm": 0.6513782143592834, |
| "learning_rate": 8.516156462585034e-05, |
| "loss": 0.7102705001831054, |
| "mean_token_accuracy": 0.8050340950489044, |
| "num_tokens": 378108.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.6968572676181793, |
| "epoch": 0.15306122448979592, |
| "grad_norm": 0.9672437310218811, |
| "learning_rate": 8.473639455782312e-05, |
| "loss": 0.6984944820404053, |
| "mean_token_accuracy": 0.8096450090408325, |
| "num_tokens": 387247.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.6053666353225708, |
| "epoch": 0.15731292517006804, |
| "grad_norm": 0.7467218637466431, |
| "learning_rate": 8.431122448979592e-05, |
| "loss": 0.6112328052520752, |
| "mean_token_accuracy": 0.8201241433620453, |
| "num_tokens": 398723.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.6494611740112305, |
| "epoch": 0.16156462585034015, |
| "grad_norm": 0.7286034822463989, |
| "learning_rate": 8.388605442176872e-05, |
| "loss": 0.6477136135101318, |
| "mean_token_accuracy": 0.8122058808803558, |
| "num_tokens": 409886.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.6897552013397217, |
| "epoch": 0.16581632653061223, |
| "grad_norm": 0.6391761898994446, |
| "learning_rate": 8.34608843537415e-05, |
| "loss": 0.6935544013977051, |
| "mean_token_accuracy": 0.7966985881328583, |
| "num_tokens": 422738.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.6955088675022125, |
| "epoch": 0.17006802721088435, |
| "grad_norm": 0.5648608803749084, |
| "learning_rate": 8.30357142857143e-05, |
| "loss": 0.715025520324707, |
| "mean_token_accuracy": 0.7990479111671448, |
| "num_tokens": 431499.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.657172217965126, |
| "epoch": 0.17431972789115646, |
| "grad_norm": 0.5713154077529907, |
| "learning_rate": 8.261054421768708e-05, |
| "loss": 0.6249523162841797, |
| "mean_token_accuracy": 0.8170171797275543, |
| "num_tokens": 441604.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.614434689283371, |
| "epoch": 0.17857142857142858, |
| "grad_norm": 0.5609672665596008, |
| "learning_rate": 8.218537414965986e-05, |
| "loss": 0.6232338428497315, |
| "mean_token_accuracy": 0.8169759333133697, |
| "num_tokens": 452819.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.6596544206142425, |
| "epoch": 0.1828231292517007, |
| "grad_norm": 0.8918700218200684, |
| "learning_rate": 8.176020408163265e-05, |
| "loss": 0.6472682952880859, |
| "mean_token_accuracy": 0.8114864528179169, |
| "num_tokens": 463985.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.5568734735250473, |
| "epoch": 0.1870748299319728, |
| "grad_norm": 0.6551166772842407, |
| "learning_rate": 8.133503401360544e-05, |
| "loss": 0.5621543407440186, |
| "mean_token_accuracy": 0.8313680768013001, |
| "num_tokens": 473644.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.6327908158302307, |
| "epoch": 0.1913265306122449, |
| "grad_norm": 0.7210569977760315, |
| "learning_rate": 8.090986394557824e-05, |
| "loss": 0.6351128101348877, |
| "mean_token_accuracy": 0.8192271828651428, |
| "num_tokens": 483952.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.6680390477180481, |
| "epoch": 0.195578231292517, |
| "grad_norm": 0.8066325783729553, |
| "learning_rate": 8.048469387755102e-05, |
| "loss": 0.6428803920745849, |
| "mean_token_accuracy": 0.8096719264984131, |
| "num_tokens": 495728.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.5830813407897949, |
| "epoch": 0.19982993197278912, |
| "grad_norm": 0.6207858324050903, |
| "learning_rate": 8.005952380952382e-05, |
| "loss": 0.5903921604156495, |
| "mean_token_accuracy": 0.832057636976242, |
| "num_tokens": 506225.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.6163366287946701, |
| "epoch": 0.20408163265306123, |
| "grad_norm": 0.27546176314353943, |
| "learning_rate": 7.96343537414966e-05, |
| "loss": 0.6205612182617187, |
| "mean_token_accuracy": 0.8090631544589997, |
| "num_tokens": 518289.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.5763369917869567, |
| "epoch": 0.20833333333333334, |
| "grad_norm": 0.5931833982467651, |
| "learning_rate": 7.920918367346939e-05, |
| "loss": 0.5674782752990722, |
| "mean_token_accuracy": 0.8279130697250366, |
| "num_tokens": 531099.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.6561572968959808, |
| "epoch": 0.21258503401360543, |
| "grad_norm": 0.7970412373542786, |
| "learning_rate": 7.878401360544218e-05, |
| "loss": 0.6701024055480957, |
| "mean_token_accuracy": 0.8162985026836396, |
| "num_tokens": 539953.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.5853851974010468, |
| "epoch": 0.21683673469387754, |
| "grad_norm": 0.74663907289505, |
| "learning_rate": 7.835884353741498e-05, |
| "loss": 0.5840775966644287, |
| "mean_token_accuracy": 0.830883127450943, |
| "num_tokens": 550283.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.6775606602430344, |
| "epoch": 0.22108843537414966, |
| "grad_norm": 0.5372825860977173, |
| "learning_rate": 7.793367346938776e-05, |
| "loss": 0.6854439735412597, |
| "mean_token_accuracy": 0.7958937227725983, |
| "num_tokens": 561951.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.6704744577407837, |
| "epoch": 0.22534013605442177, |
| "grad_norm": 0.7710736393928528, |
| "learning_rate": 7.750850340136054e-05, |
| "loss": 0.6726304054260254, |
| "mean_token_accuracy": 0.8020202696323395, |
| "num_tokens": 572509.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.635757040977478, |
| "epoch": 0.22959183673469388, |
| "grad_norm": 0.620157778263092, |
| "learning_rate": 7.708333333333334e-05, |
| "loss": 0.6136677742004395, |
| "mean_token_accuracy": 0.8304697453975678, |
| "num_tokens": 583522.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.6270190805196763, |
| "epoch": 0.233843537414966, |
| "grad_norm": 0.3838287889957428, |
| "learning_rate": 7.665816326530612e-05, |
| "loss": 0.6416101455688477, |
| "mean_token_accuracy": 0.8076549887657165, |
| "num_tokens": 595086.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.6419758051633835, |
| "epoch": 0.23809523809523808, |
| "grad_norm": 0.6037173867225647, |
| "learning_rate": 7.623299319727891e-05, |
| "loss": 0.6315017223358155, |
| "mean_token_accuracy": 0.8098805785179138, |
| "num_tokens": 606510.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.5769951343536377, |
| "epoch": 0.2423469387755102, |
| "grad_norm": 1.013440489768982, |
| "learning_rate": 7.58078231292517e-05, |
| "loss": 0.5704180717468261, |
| "mean_token_accuracy": 0.8303274273872375, |
| "num_tokens": 617019.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.6124611109495163, |
| "epoch": 0.2465986394557823, |
| "grad_norm": 0.7080560326576233, |
| "learning_rate": 7.53826530612245e-05, |
| "loss": 0.621029281616211, |
| "mean_token_accuracy": 0.8226043820381165, |
| "num_tokens": 627658.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.6244533747434616, |
| "epoch": 0.2508503401360544, |
| "grad_norm": 0.7130760550498962, |
| "learning_rate": 7.495748299319728e-05, |
| "loss": 0.6250315189361573, |
| "mean_token_accuracy": 0.812971156835556, |
| "num_tokens": 636966.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.61286960542202, |
| "epoch": 0.25510204081632654, |
| "grad_norm": 0.5573196411132812, |
| "learning_rate": 7.453231292517007e-05, |
| "loss": 0.6197751045227051, |
| "mean_token_accuracy": 0.8135783731937408, |
| "num_tokens": 648475.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.6105983853340149, |
| "epoch": 0.2593537414965986, |
| "grad_norm": 0.8304420113563538, |
| "learning_rate": 7.410714285714286e-05, |
| "loss": 0.6049539566040039, |
| "mean_token_accuracy": 0.8161618828773498, |
| "num_tokens": 660048.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.6327467203140259, |
| "epoch": 0.26360544217687076, |
| "grad_norm": 0.6550470590591431, |
| "learning_rate": 7.368197278911565e-05, |
| "loss": 0.6316221237182618, |
| "mean_token_accuracy": 0.8131963431835174, |
| "num_tokens": 671505.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.6295043647289276, |
| "epoch": 0.26785714285714285, |
| "grad_norm": 0.6002435088157654, |
| "learning_rate": 7.325680272108843e-05, |
| "loss": 0.6159311771392822, |
| "mean_token_accuracy": 0.8182806372642517, |
| "num_tokens": 681911.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.5830861747264862, |
| "epoch": 0.272108843537415, |
| "grad_norm": 0.7070937752723694, |
| "learning_rate": 7.283163265306123e-05, |
| "loss": 0.5752198219299316, |
| "mean_token_accuracy": 0.8236642122268677, |
| "num_tokens": 691175.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.6063521772623062, |
| "epoch": 0.2763605442176871, |
| "grad_norm": 0.70107501745224, |
| "learning_rate": 7.240646258503402e-05, |
| "loss": 0.6175377845764161, |
| "mean_token_accuracy": 0.8269807457923889, |
| "num_tokens": 701381.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.6279960155487061, |
| "epoch": 0.28061224489795916, |
| "grad_norm": 0.7800400257110596, |
| "learning_rate": 7.19812925170068e-05, |
| "loss": 0.6200803756713867, |
| "mean_token_accuracy": 0.8243706822395325, |
| "num_tokens": 711160.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.6208126276731492, |
| "epoch": 0.2848639455782313, |
| "grad_norm": 0.5167033076286316, |
| "learning_rate": 7.155612244897959e-05, |
| "loss": 0.6058928012847901, |
| "mean_token_accuracy": 0.825822365283966, |
| "num_tokens": 721555.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.609162974357605, |
| "epoch": 0.2891156462585034, |
| "grad_norm": 0.8961696624755859, |
| "learning_rate": 7.113095238095239e-05, |
| "loss": 0.6239143371582031, |
| "mean_token_accuracy": 0.8218865990638733, |
| "num_tokens": 731723.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.6567182302474975, |
| "epoch": 0.29336734693877553, |
| "grad_norm": 0.3495732247829437, |
| "learning_rate": 7.070578231292517e-05, |
| "loss": 0.6583582878112793, |
| "mean_token_accuracy": 0.8035318732261658, |
| "num_tokens": 745338.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.5773716390132904, |
| "epoch": 0.2976190476190476, |
| "grad_norm": 0.7330310344696045, |
| "learning_rate": 7.028061224489795e-05, |
| "loss": 0.5598068237304688, |
| "mean_token_accuracy": 0.8329594731330872, |
| "num_tokens": 755761.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.6005543798208237, |
| "epoch": 0.3018707482993197, |
| "grad_norm": 1.0653876066207886, |
| "learning_rate": 6.985544217687075e-05, |
| "loss": 0.6206864356994629, |
| "mean_token_accuracy": 0.8177128791809082, |
| "num_tokens": 765987.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.62425377368927, |
| "epoch": 0.30612244897959184, |
| "grad_norm": 0.8440945148468018, |
| "learning_rate": 6.943027210884355e-05, |
| "loss": 0.6362304210662841, |
| "mean_token_accuracy": 0.8133590519428253, |
| "num_tokens": 776707.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.6137575387954712, |
| "epoch": 0.31037414965986393, |
| "grad_norm": 0.8290141224861145, |
| "learning_rate": 6.900510204081633e-05, |
| "loss": 0.602045726776123, |
| "mean_token_accuracy": 0.8269721269607544, |
| "num_tokens": 785808.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.6052783876657486, |
| "epoch": 0.31462585034013607, |
| "grad_norm": 0.6991459131240845, |
| "learning_rate": 6.857993197278913e-05, |
| "loss": 0.6025216579437256, |
| "mean_token_accuracy": 0.8308734178543091, |
| "num_tokens": 795902.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.6147994667291641, |
| "epoch": 0.31887755102040816, |
| "grad_norm": 0.7895340323448181, |
| "learning_rate": 6.815476190476191e-05, |
| "loss": 0.6181727409362793, |
| "mean_token_accuracy": 0.8263129591941833, |
| "num_tokens": 805319.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.6230242431163788, |
| "epoch": 0.3231292517006803, |
| "grad_norm": 0.7686090469360352, |
| "learning_rate": 6.772959183673469e-05, |
| "loss": 0.620832872390747, |
| "mean_token_accuracy": 0.809659230709076, |
| "num_tokens": 817027.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.5874412208795547, |
| "epoch": 0.3273809523809524, |
| "grad_norm": 0.9315619468688965, |
| "learning_rate": 6.730442176870749e-05, |
| "loss": 0.5822995185852051, |
| "mean_token_accuracy": 0.8226828098297119, |
| "num_tokens": 830032.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.5659277379512787, |
| "epoch": 0.33163265306122447, |
| "grad_norm": 0.8107892870903015, |
| "learning_rate": 6.687925170068029e-05, |
| "loss": 0.5684999465942383, |
| "mean_token_accuracy": 0.8392240762710571, |
| "num_tokens": 840386.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.5930269837379456, |
| "epoch": 0.3358843537414966, |
| "grad_norm": 0.7134554386138916, |
| "learning_rate": 6.645408163265307e-05, |
| "loss": 0.5747966766357422, |
| "mean_token_accuracy": 0.827442079782486, |
| "num_tokens": 851076.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.6496313869953155, |
| "epoch": 0.3401360544217687, |
| "grad_norm": 0.87777179479599, |
| "learning_rate": 6.602891156462585e-05, |
| "loss": 0.6809831142425538, |
| "mean_token_accuracy": 0.785821259021759, |
| "num_tokens": 862678.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.5907361328601837, |
| "epoch": 0.34438775510204084, |
| "grad_norm": 0.711604118347168, |
| "learning_rate": 6.560374149659865e-05, |
| "loss": 0.5807193756103516, |
| "mean_token_accuracy": 0.8352659344673157, |
| "num_tokens": 873136.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 0.5893878310918808, |
| "epoch": 0.3486394557823129, |
| "grad_norm": 0.6100995540618896, |
| "learning_rate": 6.517857142857143e-05, |
| "loss": 0.5770053863525391, |
| "mean_token_accuracy": 0.8248592674732208, |
| "num_tokens": 884688.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 0.5606941819190979, |
| "epoch": 0.352891156462585, |
| "grad_norm": 0.6781875491142273, |
| "learning_rate": 6.475340136054421e-05, |
| "loss": 0.5801912784576416, |
| "mean_token_accuracy": 0.8323125898838043, |
| "num_tokens": 896185.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 0.5933171272277832, |
| "epoch": 0.35714285714285715, |
| "grad_norm": 0.5787054300308228, |
| "learning_rate": 6.432823129251701e-05, |
| "loss": 0.5779991149902344, |
| "mean_token_accuracy": 0.8351444482803345, |
| "num_tokens": 906197.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 0.5471704989671707, |
| "epoch": 0.36139455782312924, |
| "grad_norm": 1.0463767051696777, |
| "learning_rate": 6.390306122448981e-05, |
| "loss": 0.5410798549652099, |
| "mean_token_accuracy": 0.8452448129653931, |
| "num_tokens": 915927.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 0.537025648355484, |
| "epoch": 0.3656462585034014, |
| "grad_norm": 0.725310742855072, |
| "learning_rate": 6.347789115646259e-05, |
| "loss": 0.5336166381835937, |
| "mean_token_accuracy": 0.8406780958175659, |
| "num_tokens": 925972.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 0.6086225181818008, |
| "epoch": 0.36989795918367346, |
| "grad_norm": 0.6319683194160461, |
| "learning_rate": 6.305272108843537e-05, |
| "loss": 0.6223300933837891, |
| "mean_token_accuracy": 0.8144682884216309, |
| "num_tokens": 938614.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 0.6386535853147507, |
| "epoch": 0.3741496598639456, |
| "grad_norm": 0.9547185897827148, |
| "learning_rate": 6.262755102040817e-05, |
| "loss": 0.636644697189331, |
| "mean_token_accuracy": 0.8114496529102325, |
| "num_tokens": 951270.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 0.5482926398515702, |
| "epoch": 0.3784013605442177, |
| "grad_norm": 0.8478467464447021, |
| "learning_rate": 6.220238095238095e-05, |
| "loss": 0.5229831218719483, |
| "mean_token_accuracy": 0.8450385332107544, |
| "num_tokens": 962007.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 0.5352211892604828, |
| "epoch": 0.3826530612244898, |
| "grad_norm": 1.1555845737457275, |
| "learning_rate": 6.177721088435374e-05, |
| "loss": 0.5529211044311524, |
| "mean_token_accuracy": 0.8393910169601441, |
| "num_tokens": 971221.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 0.6504414319992066, |
| "epoch": 0.3869047619047619, |
| "grad_norm": 0.6787072420120239, |
| "learning_rate": 6.135204081632653e-05, |
| "loss": 0.6610816478729248, |
| "mean_token_accuracy": 0.7907391488552094, |
| "num_tokens": 982564.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 0.5921294629573822, |
| "epoch": 0.391156462585034, |
| "grad_norm": 0.7555624842643738, |
| "learning_rate": 6.092687074829932e-05, |
| "loss": 0.5777195930480957, |
| "mean_token_accuracy": 0.8236903607845306, |
| "num_tokens": 992309.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 0.578193974494934, |
| "epoch": 0.39540816326530615, |
| "grad_norm": 0.5832639336585999, |
| "learning_rate": 6.050170068027211e-05, |
| "loss": 0.5782378196716309, |
| "mean_token_accuracy": 0.825832200050354, |
| "num_tokens": 1004082.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 0.5312168657779693, |
| "epoch": 0.39965986394557823, |
| "grad_norm": 0.6483455300331116, |
| "learning_rate": 6.0076530612244896e-05, |
| "loss": 0.5226385593414307, |
| "mean_token_accuracy": 0.837943822145462, |
| "num_tokens": 1014018.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 0.5291696071624756, |
| "epoch": 0.4039115646258503, |
| "grad_norm": 0.8548340797424316, |
| "learning_rate": 5.965136054421769e-05, |
| "loss": 0.5349358558654785, |
| "mean_token_accuracy": 0.8440997183322907, |
| "num_tokens": 1024546.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 0.5704925835132599, |
| "epoch": 0.40816326530612246, |
| "grad_norm": 0.7204116582870483, |
| "learning_rate": 5.922619047619048e-05, |
| "loss": 0.5723382472991944, |
| "mean_token_accuracy": 0.8350829958915711, |
| "num_tokens": 1035324.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 0.5551350146532059, |
| "epoch": 0.41241496598639454, |
| "grad_norm": 0.8478047251701355, |
| "learning_rate": 5.8801020408163266e-05, |
| "loss": 0.5603343963623046, |
| "mean_token_accuracy": 0.8310107290744781, |
| "num_tokens": 1045459.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 0.5924204260110855, |
| "epoch": 0.4166666666666667, |
| "grad_norm": 1.0831539630889893, |
| "learning_rate": 5.837585034013606e-05, |
| "loss": 0.5897612571716309, |
| "mean_token_accuracy": 0.8289736449718476, |
| "num_tokens": 1054399.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 0.6486367821693421, |
| "epoch": 0.42091836734693877, |
| "grad_norm": 0.7564862966537476, |
| "learning_rate": 5.7950680272108846e-05, |
| "loss": 0.6640692234039307, |
| "mean_token_accuracy": 0.8002952694892883, |
| "num_tokens": 1068567.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 0.5693342804908752, |
| "epoch": 0.42517006802721086, |
| "grad_norm": 0.9830188751220703, |
| "learning_rate": 5.7525510204081636e-05, |
| "loss": 0.5391183853149414, |
| "mean_token_accuracy": 0.8396909654140472, |
| "num_tokens": 1079595.0, |
| "step": 1000 |
| }, |
| { |
| "entropy": 0.6238065242767334, |
| "epoch": 0.429421768707483, |
| "grad_norm": 0.8739970326423645, |
| "learning_rate": 5.710034013605442e-05, |
| "loss": 0.6429170608520508, |
| "mean_token_accuracy": 0.816579920053482, |
| "num_tokens": 1090254.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 0.650809234380722, |
| "epoch": 0.4336734693877551, |
| "grad_norm": 0.6658247113227844, |
| "learning_rate": 5.6675170068027215e-05, |
| "loss": 0.633099365234375, |
| "mean_token_accuracy": 0.8052545428276062, |
| "num_tokens": 1100320.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 0.6291825830936432, |
| "epoch": 0.4379251700680272, |
| "grad_norm": 0.7465150356292725, |
| "learning_rate": 5.6250000000000005e-05, |
| "loss": 0.6484538078308105, |
| "mean_token_accuracy": 0.8210124790668487, |
| "num_tokens": 1109938.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 0.6182401776313782, |
| "epoch": 0.4421768707482993, |
| "grad_norm": 0.720923125743866, |
| "learning_rate": 5.582482993197279e-05, |
| "loss": 0.6223091602325439, |
| "mean_token_accuracy": 0.8170465350151062, |
| "num_tokens": 1121480.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 0.6288217008113861, |
| "epoch": 0.44642857142857145, |
| "grad_norm": 0.8048785328865051, |
| "learning_rate": 5.5399659863945585e-05, |
| "loss": 0.6142692565917969, |
| "mean_token_accuracy": 0.8101728081703186, |
| "num_tokens": 1134615.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 0.5737671077251434, |
| "epoch": 0.45068027210884354, |
| "grad_norm": 1.0010799169540405, |
| "learning_rate": 5.497448979591837e-05, |
| "loss": 0.578005313873291, |
| "mean_token_accuracy": 0.8241186082363129, |
| "num_tokens": 1148059.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 0.6049871623516083, |
| "epoch": 0.4549319727891156, |
| "grad_norm": 0.7644203901290894, |
| "learning_rate": 5.454931972789116e-05, |
| "loss": 0.6036805152893067, |
| "mean_token_accuracy": 0.8251873433589936, |
| "num_tokens": 1159077.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 0.5016378700733185, |
| "epoch": 0.45918367346938777, |
| "grad_norm": 0.8055089116096497, |
| "learning_rate": 5.412414965986394e-05, |
| "loss": 0.47589454650878904, |
| "mean_token_accuracy": 0.852514261007309, |
| "num_tokens": 1170338.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 0.5905508637428284, |
| "epoch": 0.46343537414965985, |
| "grad_norm": 0.8147892355918884, |
| "learning_rate": 5.369897959183674e-05, |
| "loss": 0.6135655403137207, |
| "mean_token_accuracy": 0.8159750401973724, |
| "num_tokens": 1181967.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 0.5504540711641311, |
| "epoch": 0.467687074829932, |
| "grad_norm": 0.7014718055725098, |
| "learning_rate": 5.327380952380953e-05, |
| "loss": 0.5393699169158935, |
| "mean_token_accuracy": 0.8400495707988739, |
| "num_tokens": 1191911.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 0.5911126136779785, |
| "epoch": 0.4719387755102041, |
| "grad_norm": 0.8102626800537109, |
| "learning_rate": 5.284863945578231e-05, |
| "loss": 0.5901049137115478, |
| "mean_token_accuracy": 0.8300528645515441, |
| "num_tokens": 1201620.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 0.5760516464710236, |
| "epoch": 0.47619047619047616, |
| "grad_norm": 0.5337172150611877, |
| "learning_rate": 5.242346938775511e-05, |
| "loss": 0.6015921115875245, |
| "mean_token_accuracy": 0.8279711067676544, |
| "num_tokens": 1212976.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 0.6197247624397277, |
| "epoch": 0.4804421768707483, |
| "grad_norm": 0.6187336444854736, |
| "learning_rate": 5.19982993197279e-05, |
| "loss": 0.5980201244354248, |
| "mean_token_accuracy": 0.8173838019371032, |
| "num_tokens": 1224500.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 0.5247576057910919, |
| "epoch": 0.4846938775510204, |
| "grad_norm": 0.38675031065940857, |
| "learning_rate": 5.157312925170068e-05, |
| "loss": 0.5128117084503174, |
| "mean_token_accuracy": 0.8427697956562042, |
| "num_tokens": 1236056.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 0.5545101583003997, |
| "epoch": 0.48894557823129253, |
| "grad_norm": 0.8362757563591003, |
| "learning_rate": 5.114795918367348e-05, |
| "loss": 0.5881862163543701, |
| "mean_token_accuracy": 0.8283910691738129, |
| "num_tokens": 1246454.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 0.5925249218940735, |
| "epoch": 0.4931972789115646, |
| "grad_norm": 0.6821584105491638, |
| "learning_rate": 5.072278911564626e-05, |
| "loss": 0.5613045215606689, |
| "mean_token_accuracy": 0.8208597123622894, |
| "num_tokens": 1258943.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 0.5415159404277802, |
| "epoch": 0.49744897959183676, |
| "grad_norm": 0.6268453001976013, |
| "learning_rate": 5.029761904761905e-05, |
| "loss": 0.5331630706787109, |
| "mean_token_accuracy": 0.8364126265048981, |
| "num_tokens": 1272811.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 0.5170255899429321, |
| "epoch": 0.5017006802721088, |
| "grad_norm": 0.9418641924858093, |
| "learning_rate": 4.987244897959184e-05, |
| "loss": 0.5485562324523926, |
| "mean_token_accuracy": 0.8380054891109466, |
| "num_tokens": 1284235.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 0.5575446605682373, |
| "epoch": 0.5059523809523809, |
| "grad_norm": 0.6781197190284729, |
| "learning_rate": 4.944727891156462e-05, |
| "loss": 0.5431806564331054, |
| "mean_token_accuracy": 0.8374831795692443, |
| "num_tokens": 1293691.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 0.5571623414754867, |
| "epoch": 0.5102040816326531, |
| "grad_norm": 0.6811428666114807, |
| "learning_rate": 4.902210884353742e-05, |
| "loss": 0.571410083770752, |
| "mean_token_accuracy": 0.8248052895069122, |
| "num_tokens": 1304900.0, |
| "step": 1200 |
| }, |
| { |
| "entropy": 0.6219375789165497, |
| "epoch": 0.5144557823129252, |
| "grad_norm": 0.8971446752548218, |
| "learning_rate": 4.859693877551021e-05, |
| "loss": 0.6108813285827637, |
| "mean_token_accuracy": 0.8282350063323974, |
| "num_tokens": 1315658.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 0.5790914714336395, |
| "epoch": 0.5187074829931972, |
| "grad_norm": 0.8718211054801941, |
| "learning_rate": 4.817176870748299e-05, |
| "loss": 0.5702257633209229, |
| "mean_token_accuracy": 0.8363608837127685, |
| "num_tokens": 1325007.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 0.553312674164772, |
| "epoch": 0.5229591836734694, |
| "grad_norm": 0.6368089914321899, |
| "learning_rate": 4.774659863945579e-05, |
| "loss": 0.5468079566955566, |
| "mean_token_accuracy": 0.8384977638721466, |
| "num_tokens": 1334178.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 0.5654692828655243, |
| "epoch": 0.5272108843537415, |
| "grad_norm": 0.28180381655693054, |
| "learning_rate": 4.732142857142857e-05, |
| "loss": 0.5865198135375976, |
| "mean_token_accuracy": 0.8254834353923798, |
| "num_tokens": 1346386.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 0.605426836013794, |
| "epoch": 0.5314625850340136, |
| "grad_norm": 0.7490566372871399, |
| "learning_rate": 4.689625850340136e-05, |
| "loss": 0.5977043628692627, |
| "mean_token_accuracy": 0.8090501189231872, |
| "num_tokens": 1355782.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 0.6523470669984818, |
| "epoch": 0.5357142857142857, |
| "grad_norm": 0.8416953086853027, |
| "learning_rate": 4.647108843537415e-05, |
| "loss": 0.6364702224731446, |
| "mean_token_accuracy": 0.8065241694450378, |
| "num_tokens": 1367425.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 0.6016772747039795, |
| "epoch": 0.5399659863945578, |
| "grad_norm": 0.723196804523468, |
| "learning_rate": 4.604591836734694e-05, |
| "loss": 0.5914052486419678, |
| "mean_token_accuracy": 0.8149433314800263, |
| "num_tokens": 1379306.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 0.538858824968338, |
| "epoch": 0.54421768707483, |
| "grad_norm": 0.7268431186676025, |
| "learning_rate": 4.562074829931973e-05, |
| "loss": 0.5699212074279785, |
| "mean_token_accuracy": 0.8373402774333953, |
| "num_tokens": 1388943.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 0.5116531759500503, |
| "epoch": 0.548469387755102, |
| "grad_norm": 0.6881728172302246, |
| "learning_rate": 4.5195578231292515e-05, |
| "loss": 0.501812219619751, |
| "mean_token_accuracy": 0.8508045136928558, |
| "num_tokens": 1398890.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 0.5898961424827576, |
| "epoch": 0.5527210884353742, |
| "grad_norm": 0.9265963435173035, |
| "learning_rate": 4.477040816326531e-05, |
| "loss": 0.5903323650360107, |
| "mean_token_accuracy": 0.8182829022407532, |
| "num_tokens": 1412402.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 0.5762919217348099, |
| "epoch": 0.5569727891156463, |
| "grad_norm": 0.6862229108810425, |
| "learning_rate": 4.4345238095238095e-05, |
| "loss": 0.5722722053527832, |
| "mean_token_accuracy": 0.8374342918395996, |
| "num_tokens": 1425081.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 0.5345231264829635, |
| "epoch": 0.5612244897959183, |
| "grad_norm": 0.7506856322288513, |
| "learning_rate": 4.3920068027210885e-05, |
| "loss": 0.5166549205780029, |
| "mean_token_accuracy": 0.8448654294013977, |
| "num_tokens": 1436487.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 0.5727064400911331, |
| "epoch": 0.5654761904761905, |
| "grad_norm": 0.7576751708984375, |
| "learning_rate": 4.3494897959183675e-05, |
| "loss": 0.5965213298797607, |
| "mean_token_accuracy": 0.8292974472045899, |
| "num_tokens": 1447115.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 0.6086050748825074, |
| "epoch": 0.5697278911564626, |
| "grad_norm": 1.0944355726242065, |
| "learning_rate": 4.3069727891156465e-05, |
| "loss": 0.6146334648132324, |
| "mean_token_accuracy": 0.8208171963691712, |
| "num_tokens": 1458109.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 0.548018091917038, |
| "epoch": 0.5739795918367347, |
| "grad_norm": 0.7556106448173523, |
| "learning_rate": 4.2644557823129255e-05, |
| "loss": 0.5399428367614746, |
| "mean_token_accuracy": 0.8316729366779327, |
| "num_tokens": 1468353.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 0.57362260222435, |
| "epoch": 0.5782312925170068, |
| "grad_norm": 0.958890974521637, |
| "learning_rate": 4.2219387755102045e-05, |
| "loss": 0.5638460159301758, |
| "mean_token_accuracy": 0.8328832030296326, |
| "num_tokens": 1478064.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 0.4699955850839615, |
| "epoch": 0.5824829931972789, |
| "grad_norm": 0.951663613319397, |
| "learning_rate": 4.1794217687074834e-05, |
| "loss": 0.4790843963623047, |
| "mean_token_accuracy": 0.8547844409942627, |
| "num_tokens": 1488401.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 0.5664187341928482, |
| "epoch": 0.5867346938775511, |
| "grad_norm": 0.8573746085166931, |
| "learning_rate": 4.136904761904762e-05, |
| "loss": 0.6015422821044922, |
| "mean_token_accuracy": 0.8200101733207703, |
| "num_tokens": 1498757.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 0.5411120235919953, |
| "epoch": 0.5909863945578231, |
| "grad_norm": 0.738762617111206, |
| "learning_rate": 4.094387755102041e-05, |
| "loss": 0.49553709030151366, |
| "mean_token_accuracy": 0.8463812232017517, |
| "num_tokens": 1509252.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 0.5284088224172592, |
| "epoch": 0.5952380952380952, |
| "grad_norm": 0.9987853765487671, |
| "learning_rate": 4.0518707482993204e-05, |
| "loss": 0.521688985824585, |
| "mean_token_accuracy": 0.8317105531692505, |
| "num_tokens": 1521575.0, |
| "step": 1400 |
| }, |
| { |
| "entropy": 0.5420585960149765, |
| "epoch": 0.5994897959183674, |
| "grad_norm": 0.5594030022621155, |
| "learning_rate": 4.009353741496599e-05, |
| "loss": 0.5624300003051758, |
| "mean_token_accuracy": 0.8328603029251098, |
| "num_tokens": 1533858.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 0.6201832562685012, |
| "epoch": 0.6037414965986394, |
| "grad_norm": 0.9479369521141052, |
| "learning_rate": 3.966836734693878e-05, |
| "loss": 0.5940685749053956, |
| "mean_token_accuracy": 0.8293437898159027, |
| "num_tokens": 1544902.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 0.6230043023824692, |
| "epoch": 0.6079931972789115, |
| "grad_norm": 0.8622655868530273, |
| "learning_rate": 3.924319727891157e-05, |
| "loss": 0.631603193283081, |
| "mean_token_accuracy": 0.8104620337486267, |
| "num_tokens": 1555779.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 0.5547834306955337, |
| "epoch": 0.6122448979591837, |
| "grad_norm": 0.8286665678024292, |
| "learning_rate": 3.881802721088436e-05, |
| "loss": 0.555398416519165, |
| "mean_token_accuracy": 0.8266190946102142, |
| "num_tokens": 1568157.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 0.5555658012628555, |
| "epoch": 0.6164965986394558, |
| "grad_norm": 1.2064694166183472, |
| "learning_rate": 3.839285714285715e-05, |
| "loss": 0.5589458465576171, |
| "mean_token_accuracy": 0.8308910727500916, |
| "num_tokens": 1578660.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 0.5215276837348938, |
| "epoch": 0.6207482993197279, |
| "grad_norm": 1.134692668914795, |
| "learning_rate": 3.796768707482993e-05, |
| "loss": 0.5223335266113281, |
| "mean_token_accuracy": 0.8505008935928344, |
| "num_tokens": 1588221.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 0.5241445243358612, |
| "epoch": 0.625, |
| "grad_norm": 0.32119959592819214, |
| "learning_rate": 3.7542517006802727e-05, |
| "loss": 0.5141430377960206, |
| "mean_token_accuracy": 0.8423964560031891, |
| "num_tokens": 1600810.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 0.5927034109830857, |
| "epoch": 0.6292517006802721, |
| "grad_norm": 0.8377068042755127, |
| "learning_rate": 3.711734693877551e-05, |
| "loss": 0.5961884975433349, |
| "mean_token_accuracy": 0.8162056863307953, |
| "num_tokens": 1611543.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 0.5436273574829101, |
| "epoch": 0.6335034013605442, |
| "grad_norm": 1.032684087753296, |
| "learning_rate": 3.66921768707483e-05, |
| "loss": 0.534994649887085, |
| "mean_token_accuracy": 0.8348295450210571, |
| "num_tokens": 1623564.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 0.5652735084295273, |
| "epoch": 0.6377551020408163, |
| "grad_norm": 0.9198411107063293, |
| "learning_rate": 3.626700680272109e-05, |
| "loss": 0.56695556640625, |
| "mean_token_accuracy": 0.8294547438621521, |
| "num_tokens": 1634706.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 0.5435687988996506, |
| "epoch": 0.6420068027210885, |
| "grad_norm": 1.0693076848983765, |
| "learning_rate": 3.584183673469388e-05, |
| "loss": 0.5479542255401612, |
| "mean_token_accuracy": 0.831254106760025, |
| "num_tokens": 1646948.0, |
| "step": 1510 |
| }, |
| { |
| "entropy": 0.5947155982255936, |
| "epoch": 0.6462585034013606, |
| "grad_norm": 0.8154687285423279, |
| "learning_rate": 3.541666666666667e-05, |
| "loss": 0.5963615417480469, |
| "mean_token_accuracy": 0.8205921828746796, |
| "num_tokens": 1659463.0, |
| "step": 1520 |
| }, |
| { |
| "entropy": 0.5729703456163406, |
| "epoch": 0.6505102040816326, |
| "grad_norm": 0.9937994480133057, |
| "learning_rate": 3.499149659863946e-05, |
| "loss": 0.5724692344665527, |
| "mean_token_accuracy": 0.8275785386562348, |
| "num_tokens": 1669020.0, |
| "step": 1530 |
| }, |
| { |
| "entropy": 0.5577893137931824, |
| "epoch": 0.6547619047619048, |
| "grad_norm": 0.9926438331604004, |
| "learning_rate": 3.456632653061225e-05, |
| "loss": 0.5496519088745118, |
| "mean_token_accuracy": 0.8388534963130951, |
| "num_tokens": 1679086.0, |
| "step": 1540 |
| }, |
| { |
| "entropy": 0.5564258128404618, |
| "epoch": 0.6590136054421769, |
| "grad_norm": 0.6609563827514648, |
| "learning_rate": 3.414115646258503e-05, |
| "loss": 0.5487947940826416, |
| "mean_token_accuracy": 0.835220330953598, |
| "num_tokens": 1688728.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 0.5531272172927857, |
| "epoch": 0.6632653061224489, |
| "grad_norm": 0.8581554293632507, |
| "learning_rate": 3.371598639455782e-05, |
| "loss": 0.5585684776306152, |
| "mean_token_accuracy": 0.8341455698013306, |
| "num_tokens": 1700307.0, |
| "step": 1560 |
| }, |
| { |
| "entropy": 0.5576629728078842, |
| "epoch": 0.6675170068027211, |
| "grad_norm": 1.0460259914398193, |
| "learning_rate": 3.329081632653062e-05, |
| "loss": 0.5379378318786621, |
| "mean_token_accuracy": 0.8366690516471863, |
| "num_tokens": 1710339.0, |
| "step": 1570 |
| }, |
| { |
| "entropy": 0.5780779421329498, |
| "epoch": 0.6717687074829932, |
| "grad_norm": 0.8212461471557617, |
| "learning_rate": 3.28656462585034e-05, |
| "loss": 0.5949641704559326, |
| "mean_token_accuracy": 0.8214079976081848, |
| "num_tokens": 1721506.0, |
| "step": 1580 |
| }, |
| { |
| "entropy": 0.5216499924659729, |
| "epoch": 0.6760204081632653, |
| "grad_norm": 0.8629688620567322, |
| "learning_rate": 3.244047619047619e-05, |
| "loss": 0.5170677661895752, |
| "mean_token_accuracy": 0.8427080929279327, |
| "num_tokens": 1732208.0, |
| "step": 1590 |
| }, |
| { |
| "entropy": 0.49583795964717864, |
| "epoch": 0.6802721088435374, |
| "grad_norm": 1.0993518829345703, |
| "learning_rate": 3.201530612244898e-05, |
| "loss": 0.5001798152923584, |
| "mean_token_accuracy": 0.8505501627922059, |
| "num_tokens": 1743050.0, |
| "step": 1600 |
| }, |
| { |
| "entropy": 0.5788540303707123, |
| "epoch": 0.6845238095238095, |
| "grad_norm": 0.7463700175285339, |
| "learning_rate": 3.159013605442177e-05, |
| "loss": 0.5734623432159424, |
| "mean_token_accuracy": 0.820825070142746, |
| "num_tokens": 1756862.0, |
| "step": 1610 |
| }, |
| { |
| "entropy": 0.5762177228927612, |
| "epoch": 0.6887755102040817, |
| "grad_norm": 0.9257715344429016, |
| "learning_rate": 3.116496598639456e-05, |
| "loss": 0.5818124294281006, |
| "mean_token_accuracy": 0.8196542203426361, |
| "num_tokens": 1768627.0, |
| "step": 1620 |
| }, |
| { |
| "entropy": 0.5790290325880051, |
| "epoch": 0.6930272108843537, |
| "grad_norm": 0.7693411707878113, |
| "learning_rate": 3.073979591836735e-05, |
| "loss": 0.5630362033843994, |
| "mean_token_accuracy": 0.8297848999500275, |
| "num_tokens": 1778631.0, |
| "step": 1630 |
| }, |
| { |
| "entropy": 0.5448883175849915, |
| "epoch": 0.6972789115646258, |
| "grad_norm": 0.8125811219215393, |
| "learning_rate": 3.0314625850340138e-05, |
| "loss": 0.5536840438842774, |
| "mean_token_accuracy": 0.8345063030719757, |
| "num_tokens": 1790461.0, |
| "step": 1640 |
| }, |
| { |
| "entropy": 0.6271291971206665, |
| "epoch": 0.701530612244898, |
| "grad_norm": 0.7942107915878296, |
| "learning_rate": 2.9889455782312924e-05, |
| "loss": 0.6389796257019043, |
| "mean_token_accuracy": 0.810248178243637, |
| "num_tokens": 1800913.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 0.5628238677978515, |
| "epoch": 0.70578231292517, |
| "grad_norm": 0.6301717162132263, |
| "learning_rate": 2.9464285714285718e-05, |
| "loss": 0.5345774173736573, |
| "mean_token_accuracy": 0.8370151519775391, |
| "num_tokens": 1811886.0, |
| "step": 1660 |
| }, |
| { |
| "entropy": 0.48286513090133665, |
| "epoch": 0.7100340136054422, |
| "grad_norm": 1.233020544052124, |
| "learning_rate": 2.9039115646258504e-05, |
| "loss": 0.5052211284637451, |
| "mean_token_accuracy": 0.8479276895523071, |
| "num_tokens": 1821468.0, |
| "step": 1670 |
| }, |
| { |
| "entropy": 0.6830842137336731, |
| "epoch": 0.7142857142857143, |
| "grad_norm": 1.1565057039260864, |
| "learning_rate": 2.8613945578231294e-05, |
| "loss": 0.7028451442718506, |
| "mean_token_accuracy": 0.7885268032550812, |
| "num_tokens": 1830341.0, |
| "step": 1680 |
| }, |
| { |
| "entropy": 0.6287564933300018, |
| "epoch": 0.7185374149659864, |
| "grad_norm": 0.5923300385475159, |
| "learning_rate": 2.8188775510204084e-05, |
| "loss": 0.6260773658752441, |
| "mean_token_accuracy": 0.80694420337677, |
| "num_tokens": 1840794.0, |
| "step": 1690 |
| }, |
| { |
| "entropy": 0.5761405915021897, |
| "epoch": 0.7227891156462585, |
| "grad_norm": 0.813294529914856, |
| "learning_rate": 2.776360544217687e-05, |
| "loss": 0.5476944923400879, |
| "mean_token_accuracy": 0.8244221389293671, |
| "num_tokens": 1851534.0, |
| "step": 1700 |
| }, |
| { |
| "entropy": 0.5528579622507095, |
| "epoch": 0.7270408163265306, |
| "grad_norm": 0.9476060271263123, |
| "learning_rate": 2.7338435374149664e-05, |
| "loss": 0.5636507987976074, |
| "mean_token_accuracy": 0.8234051108360291, |
| "num_tokens": 1863352.0, |
| "step": 1710 |
| }, |
| { |
| "entropy": 0.5006043136119842, |
| "epoch": 0.7312925170068028, |
| "grad_norm": 0.9661667943000793, |
| "learning_rate": 2.6913265306122447e-05, |
| "loss": 0.4998173236846924, |
| "mean_token_accuracy": 0.8556727051734925, |
| "num_tokens": 1873010.0, |
| "step": 1720 |
| }, |
| { |
| "entropy": 0.5668102502822876, |
| "epoch": 0.7355442176870748, |
| "grad_norm": 0.9204102754592896, |
| "learning_rate": 2.648809523809524e-05, |
| "loss": 0.5956824779510498, |
| "mean_token_accuracy": 0.8302618801593781, |
| "num_tokens": 1882296.0, |
| "step": 1730 |
| }, |
| { |
| "entropy": 0.5725611984729767, |
| "epoch": 0.7397959183673469, |
| "grad_norm": 0.9404184222221375, |
| "learning_rate": 2.606292517006803e-05, |
| "loss": 0.5676938056945801, |
| "mean_token_accuracy": 0.8323635518550873, |
| "num_tokens": 1894428.0, |
| "step": 1740 |
| }, |
| { |
| "entropy": 0.606747168302536, |
| "epoch": 0.7440476190476191, |
| "grad_norm": 0.8424393534660339, |
| "learning_rate": 2.5637755102040816e-05, |
| "loss": 0.5834713935852051, |
| "mean_token_accuracy": 0.8257153987884521, |
| "num_tokens": 1904617.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 0.5970776557922364, |
| "epoch": 0.7482993197278912, |
| "grad_norm": 1.1546332836151123, |
| "learning_rate": 2.521258503401361e-05, |
| "loss": 0.5974382877349853, |
| "mean_token_accuracy": 0.8301580667495727, |
| "num_tokens": 1914950.0, |
| "step": 1760 |
| }, |
| { |
| "entropy": 0.5316449493169785, |
| "epoch": 0.7525510204081632, |
| "grad_norm": 1.3904755115509033, |
| "learning_rate": 2.4787414965986396e-05, |
| "loss": 0.527727460861206, |
| "mean_token_accuracy": 0.8430564641952515, |
| "num_tokens": 1924291.0, |
| "step": 1770 |
| }, |
| { |
| "entropy": 0.5104436665773392, |
| "epoch": 0.7568027210884354, |
| "grad_norm": 0.9666491150856018, |
| "learning_rate": 2.4362244897959186e-05, |
| "loss": 0.5042972564697266, |
| "mean_token_accuracy": 0.841067123413086, |
| "num_tokens": 1935889.0, |
| "step": 1780 |
| }, |
| { |
| "entropy": 0.5277058184146881, |
| "epoch": 0.7610544217687075, |
| "grad_norm": 1.3077667951583862, |
| "learning_rate": 2.3937074829931973e-05, |
| "loss": 0.5233573913574219, |
| "mean_token_accuracy": 0.8365782618522644, |
| "num_tokens": 1946417.0, |
| "step": 1790 |
| }, |
| { |
| "entropy": 0.5900924652814865, |
| "epoch": 0.7653061224489796, |
| "grad_norm": 1.129841923713684, |
| "learning_rate": 2.3511904761904762e-05, |
| "loss": 0.6162432193756103, |
| "mean_token_accuracy": 0.8183229088783264, |
| "num_tokens": 1958665.0, |
| "step": 1800 |
| }, |
| { |
| "entropy": 0.5582915276288987, |
| "epoch": 0.7695578231292517, |
| "grad_norm": 1.0439772605895996, |
| "learning_rate": 2.3086734693877552e-05, |
| "loss": 0.5462551593780518, |
| "mean_token_accuracy": 0.8470064103603363, |
| "num_tokens": 1967612.0, |
| "step": 1810 |
| }, |
| { |
| "entropy": 0.5408319383859634, |
| "epoch": 0.7738095238095238, |
| "grad_norm": 0.9232698082923889, |
| "learning_rate": 2.266156462585034e-05, |
| "loss": 0.5256539344787597, |
| "mean_token_accuracy": 0.8365410387516021, |
| "num_tokens": 1977989.0, |
| "step": 1820 |
| }, |
| { |
| "entropy": 0.5403281807899475, |
| "epoch": 0.7780612244897959, |
| "grad_norm": 1.0451940298080444, |
| "learning_rate": 2.2236394557823132e-05, |
| "loss": 0.5474090576171875, |
| "mean_token_accuracy": 0.834468537569046, |
| "num_tokens": 1990698.0, |
| "step": 1830 |
| }, |
| { |
| "entropy": 0.5493248134851456, |
| "epoch": 0.782312925170068, |
| "grad_norm": 0.774145245552063, |
| "learning_rate": 2.181122448979592e-05, |
| "loss": 0.554120397567749, |
| "mean_token_accuracy": 0.8225033700466156, |
| "num_tokens": 2001822.0, |
| "step": 1840 |
| }, |
| { |
| "entropy": 0.5199731826782227, |
| "epoch": 0.7865646258503401, |
| "grad_norm": 1.0582787990570068, |
| "learning_rate": 2.138605442176871e-05, |
| "loss": 0.5166659355163574, |
| "mean_token_accuracy": 0.8476324081420898, |
| "num_tokens": 2012779.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 0.504674881696701, |
| "epoch": 0.7908163265306123, |
| "grad_norm": 0.8114542961120605, |
| "learning_rate": 2.09608843537415e-05, |
| "loss": 0.5136760711669922, |
| "mean_token_accuracy": 0.8496062397956848, |
| "num_tokens": 2023065.0, |
| "step": 1860 |
| }, |
| { |
| "entropy": 0.5434481918811798, |
| "epoch": 0.7950680272108843, |
| "grad_norm": 0.9178285002708435, |
| "learning_rate": 2.0535714285714285e-05, |
| "loss": 0.5489007472991944, |
| "mean_token_accuracy": 0.8227114081382751, |
| "num_tokens": 2037557.0, |
| "step": 1870 |
| }, |
| { |
| "entropy": 0.5326362639665604, |
| "epoch": 0.7993197278911565, |
| "grad_norm": 0.7624576091766357, |
| "learning_rate": 2.0110544217687075e-05, |
| "loss": 0.5364444732666016, |
| "mean_token_accuracy": 0.8336756289005279, |
| "num_tokens": 2048539.0, |
| "step": 1880 |
| }, |
| { |
| "entropy": 0.5348059087991714, |
| "epoch": 0.8035714285714286, |
| "grad_norm": 0.6548311710357666, |
| "learning_rate": 1.9685374149659865e-05, |
| "loss": 0.5343772411346436, |
| "mean_token_accuracy": 0.8385817587375641, |
| "num_tokens": 2059612.0, |
| "step": 1890 |
| }, |
| { |
| "entropy": 0.5933915734291076, |
| "epoch": 0.8078231292517006, |
| "grad_norm": 1.13102126121521, |
| "learning_rate": 1.9260204081632655e-05, |
| "loss": 0.6000364780426025, |
| "mean_token_accuracy": 0.8166829824447632, |
| "num_tokens": 2070418.0, |
| "step": 1900 |
| }, |
| { |
| "entropy": 0.606149223446846, |
| "epoch": 0.8120748299319728, |
| "grad_norm": 1.6694409847259521, |
| "learning_rate": 1.8835034013605444e-05, |
| "loss": 0.6033652782440185, |
| "mean_token_accuracy": 0.8095532536506653, |
| "num_tokens": 2082806.0, |
| "step": 1910 |
| }, |
| { |
| "entropy": 0.6159947037696838, |
| "epoch": 0.8163265306122449, |
| "grad_norm": 0.7934441566467285, |
| "learning_rate": 1.840986394557823e-05, |
| "loss": 0.6037148475646973, |
| "mean_token_accuracy": 0.8110804080963134, |
| "num_tokens": 2095279.0, |
| "step": 1920 |
| }, |
| { |
| "entropy": 0.587390485405922, |
| "epoch": 0.8205782312925171, |
| "grad_norm": 0.8202760219573975, |
| "learning_rate": 1.798469387755102e-05, |
| "loss": 0.586046838760376, |
| "mean_token_accuracy": 0.8243176221847535, |
| "num_tokens": 2105372.0, |
| "step": 1930 |
| }, |
| { |
| "entropy": 0.5912446022033692, |
| "epoch": 0.8248299319727891, |
| "grad_norm": 1.623152256011963, |
| "learning_rate": 1.755952380952381e-05, |
| "loss": 0.596843671798706, |
| "mean_token_accuracy": 0.8153438031673431, |
| "num_tokens": 2114729.0, |
| "step": 1940 |
| }, |
| { |
| "entropy": 0.5157216489315033, |
| "epoch": 0.8290816326530612, |
| "grad_norm": 0.9215971827507019, |
| "learning_rate": 1.71343537414966e-05, |
| "loss": 0.5145907402038574, |
| "mean_token_accuracy": 0.8426204800605774, |
| "num_tokens": 2125290.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 0.5829062938690186, |
| "epoch": 0.8333333333333334, |
| "grad_norm": 1.193843126296997, |
| "learning_rate": 1.670918367346939e-05, |
| "loss": 0.5695863723754883, |
| "mean_token_accuracy": 0.8192765057086945, |
| "num_tokens": 2136344.0, |
| "step": 1960 |
| }, |
| { |
| "entropy": 0.4996066093444824, |
| "epoch": 0.8375850340136054, |
| "grad_norm": 0.8927513360977173, |
| "learning_rate": 1.6284013605442177e-05, |
| "loss": 0.4900965213775635, |
| "mean_token_accuracy": 0.8509392082691193, |
| "num_tokens": 2146080.0, |
| "step": 1970 |
| }, |
| { |
| "entropy": 0.5360583394765854, |
| "epoch": 0.8418367346938775, |
| "grad_norm": 1.058348536491394, |
| "learning_rate": 1.5858843537414967e-05, |
| "loss": 0.5512252807617187, |
| "mean_token_accuracy": 0.8354442238807678, |
| "num_tokens": 2156011.0, |
| "step": 1980 |
| }, |
| { |
| "entropy": 0.6012335926294327, |
| "epoch": 0.8460884353741497, |
| "grad_norm": 0.7904354333877563, |
| "learning_rate": 1.5433673469387753e-05, |
| "loss": 0.6157900333404541, |
| "mean_token_accuracy": 0.8187953770160675, |
| "num_tokens": 2167057.0, |
| "step": 1990 |
| }, |
| { |
| "entropy": 0.6478571712970733, |
| "epoch": 0.8503401360544217, |
| "grad_norm": 1.0595366954803467, |
| "learning_rate": 1.5008503401360543e-05, |
| "loss": 0.6455856323242187, |
| "mean_token_accuracy": 0.7955973386764527, |
| "num_tokens": 2178418.0, |
| "step": 2000 |
| }, |
| { |
| "entropy": 0.5748985707759857, |
| "epoch": 0.8545918367346939, |
| "grad_norm": 1.1120526790618896, |
| "learning_rate": 1.4583333333333335e-05, |
| "loss": 0.5637976646423339, |
| "mean_token_accuracy": 0.8272497594356537, |
| "num_tokens": 2189919.0, |
| "step": 2010 |
| }, |
| { |
| "entropy": 0.5793386727571488, |
| "epoch": 0.858843537414966, |
| "grad_norm": 0.9996525645256042, |
| "learning_rate": 1.4158163265306123e-05, |
| "loss": 0.5585187911987305, |
| "mean_token_accuracy": 0.8226561129093171, |
| "num_tokens": 2202449.0, |
| "step": 2020 |
| }, |
| { |
| "entropy": 0.48502568900585175, |
| "epoch": 0.8630952380952381, |
| "grad_norm": 0.8485120534896851, |
| "learning_rate": 1.3732993197278913e-05, |
| "loss": 0.4754936218261719, |
| "mean_token_accuracy": 0.8551179468631744, |
| "num_tokens": 2212256.0, |
| "step": 2030 |
| }, |
| { |
| "entropy": 0.5177913874387741, |
| "epoch": 0.8673469387755102, |
| "grad_norm": 1.0269567966461182, |
| "learning_rate": 1.3307823129251701e-05, |
| "loss": 0.5295746326446533, |
| "mean_token_accuracy": 0.8426526129245758, |
| "num_tokens": 2222079.0, |
| "step": 2040 |
| }, |
| { |
| "entropy": 0.5418720453977585, |
| "epoch": 0.8715986394557823, |
| "grad_norm": 1.1140215396881104, |
| "learning_rate": 1.288265306122449e-05, |
| "loss": 0.5403457164764405, |
| "mean_token_accuracy": 0.8360271990299225, |
| "num_tokens": 2233010.0, |
| "step": 2050 |
| }, |
| { |
| "entropy": 0.5022894471883774, |
| "epoch": 0.8758503401360545, |
| "grad_norm": 0.9412987232208252, |
| "learning_rate": 1.245748299319728e-05, |
| "loss": 0.5068081855773926, |
| "mean_token_accuracy": 0.8397215008735657, |
| "num_tokens": 2242876.0, |
| "step": 2060 |
| }, |
| { |
| "entropy": 0.559627965092659, |
| "epoch": 0.8801020408163265, |
| "grad_norm": 1.1703239679336548, |
| "learning_rate": 1.2032312925170067e-05, |
| "loss": 0.5765266418457031, |
| "mean_token_accuracy": 0.8238355994224549, |
| "num_tokens": 2253375.0, |
| "step": 2070 |
| }, |
| { |
| "entropy": 0.5473792344331742, |
| "epoch": 0.8843537414965986, |
| "grad_norm": 1.2103474140167236, |
| "learning_rate": 1.1607142857142857e-05, |
| "loss": 0.5515032768249511, |
| "mean_token_accuracy": 0.8346924901008606, |
| "num_tokens": 2265217.0, |
| "step": 2080 |
| }, |
| { |
| "entropy": 0.5150429278612136, |
| "epoch": 0.8886054421768708, |
| "grad_norm": 0.8060351014137268, |
| "learning_rate": 1.1181972789115647e-05, |
| "loss": 0.5019734859466553, |
| "mean_token_accuracy": 0.8517545342445374, |
| "num_tokens": 2276492.0, |
| "step": 2090 |
| }, |
| { |
| "entropy": 0.5388852089643479, |
| "epoch": 0.8928571428571429, |
| "grad_norm": 1.129920244216919, |
| "learning_rate": 1.0756802721088435e-05, |
| "loss": 0.5413199424743652, |
| "mean_token_accuracy": 0.8384690225124359, |
| "num_tokens": 2286622.0, |
| "step": 2100 |
| }, |
| { |
| "entropy": 0.5830584645271302, |
| "epoch": 0.8971088435374149, |
| "grad_norm": 1.0372401475906372, |
| "learning_rate": 1.0331632653061225e-05, |
| "loss": 0.5750691890716553, |
| "mean_token_accuracy": 0.8245911538600922, |
| "num_tokens": 2298062.0, |
| "step": 2110 |
| }, |
| { |
| "entropy": 0.5636593252420425, |
| "epoch": 0.9013605442176871, |
| "grad_norm": 0.7910812497138977, |
| "learning_rate": 9.906462585034014e-06, |
| "loss": 0.568049955368042, |
| "mean_token_accuracy": 0.8189381241798401, |
| "num_tokens": 2310002.0, |
| "step": 2120 |
| }, |
| { |
| "entropy": 0.5329378515481948, |
| "epoch": 0.9056122448979592, |
| "grad_norm": 0.780502438545227, |
| "learning_rate": 9.481292517006803e-06, |
| "loss": 0.5344277381896972, |
| "mean_token_accuracy": 0.8355330467224121, |
| "num_tokens": 2321286.0, |
| "step": 2130 |
| }, |
| { |
| "entropy": 0.5965909093618393, |
| "epoch": 0.9098639455782312, |
| "grad_norm": 1.108359694480896, |
| "learning_rate": 9.056122448979593e-06, |
| "loss": 0.6025591373443604, |
| "mean_token_accuracy": 0.8153828561306, |
| "num_tokens": 2334075.0, |
| "step": 2140 |
| }, |
| { |
| "entropy": 0.551003360748291, |
| "epoch": 0.9141156462585034, |
| "grad_norm": 0.9165040850639343, |
| "learning_rate": 8.630952380952381e-06, |
| "loss": 0.5357895851135254, |
| "mean_token_accuracy": 0.8391867280006409, |
| "num_tokens": 2343342.0, |
| "step": 2150 |
| }, |
| { |
| "entropy": 0.6025931894779205, |
| "epoch": 0.9183673469387755, |
| "grad_norm": 0.9292078018188477, |
| "learning_rate": 8.20578231292517e-06, |
| "loss": 0.6112618923187256, |
| "mean_token_accuracy": 0.8223409533500672, |
| "num_tokens": 2353860.0, |
| "step": 2160 |
| }, |
| { |
| "entropy": 0.5607409834861755, |
| "epoch": 0.9226190476190477, |
| "grad_norm": 0.8626019358634949, |
| "learning_rate": 7.78061224489796e-06, |
| "loss": 0.5666313648223877, |
| "mean_token_accuracy": 0.8334515213966369, |
| "num_tokens": 2364432.0, |
| "step": 2170 |
| }, |
| { |
| "entropy": 0.6042696863412857, |
| "epoch": 0.9268707482993197, |
| "grad_norm": 1.1293621063232422, |
| "learning_rate": 7.355442176870749e-06, |
| "loss": 0.6011404037475586, |
| "mean_token_accuracy": 0.8190859973430633, |
| "num_tokens": 2374475.0, |
| "step": 2180 |
| }, |
| { |
| "entropy": 0.5735134840011596, |
| "epoch": 0.9311224489795918, |
| "grad_norm": 0.9066168069839478, |
| "learning_rate": 6.930272108843537e-06, |
| "loss": 0.5751115798950195, |
| "mean_token_accuracy": 0.825209504365921, |
| "num_tokens": 2386447.0, |
| "step": 2190 |
| }, |
| { |
| "entropy": 0.5244353115558624, |
| "epoch": 0.935374149659864, |
| "grad_norm": 1.072506308555603, |
| "learning_rate": 6.505102040816327e-06, |
| "loss": 0.5103401660919189, |
| "mean_token_accuracy": 0.8505155682563782, |
| "num_tokens": 2396159.0, |
| "step": 2200 |
| }, |
| { |
| "entropy": 0.5949863910675048, |
| "epoch": 0.939625850340136, |
| "grad_norm": 0.6773778200149536, |
| "learning_rate": 6.079931972789116e-06, |
| "loss": 0.5959713459014893, |
| "mean_token_accuracy": 0.8145836770534516, |
| "num_tokens": 2406947.0, |
| "step": 2210 |
| }, |
| { |
| "entropy": 0.551213338971138, |
| "epoch": 0.9438775510204082, |
| "grad_norm": 0.6725026369094849, |
| "learning_rate": 5.654761904761905e-06, |
| "loss": 0.5293383121490478, |
| "mean_token_accuracy": 0.8271439135074615, |
| "num_tokens": 2419071.0, |
| "step": 2220 |
| }, |
| { |
| "entropy": 0.5137664794921875, |
| "epoch": 0.9481292517006803, |
| "grad_norm": 0.8478580117225647, |
| "learning_rate": 5.229591836734695e-06, |
| "loss": 0.5074201583862304, |
| "mean_token_accuracy": 0.842332798242569, |
| "num_tokens": 2430620.0, |
| "step": 2230 |
| }, |
| { |
| "entropy": 0.5922556847333909, |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.3467719554901123, |
| "learning_rate": 4.804421768707483e-06, |
| "loss": 0.5839669227600097, |
| "mean_token_accuracy": 0.811210173368454, |
| "num_tokens": 2444057.0, |
| "step": 2240 |
| }, |
| { |
| "entropy": 0.5484513103961944, |
| "epoch": 0.9566326530612245, |
| "grad_norm": 0.760888397693634, |
| "learning_rate": 4.379251700680272e-06, |
| "loss": 0.5440735340118408, |
| "mean_token_accuracy": 0.8317016720771789, |
| "num_tokens": 2454080.0, |
| "step": 2250 |
| }, |
| { |
| "entropy": 0.5103359013795853, |
| "epoch": 0.9608843537414966, |
| "grad_norm": 0.9869306683540344, |
| "learning_rate": 3.954081632653062e-06, |
| "loss": 0.5173935890197754, |
| "mean_token_accuracy": 0.845134687423706, |
| "num_tokens": 2463311.0, |
| "step": 2260 |
| }, |
| { |
| "entropy": 0.5766151458024978, |
| "epoch": 0.9651360544217688, |
| "grad_norm": 1.1104836463928223, |
| "learning_rate": 3.5289115646258504e-06, |
| "loss": 0.5886892318725586, |
| "mean_token_accuracy": 0.8289117157459259, |
| "num_tokens": 2475264.0, |
| "step": 2270 |
| }, |
| { |
| "entropy": 0.5101310968399048, |
| "epoch": 0.9693877551020408, |
| "grad_norm": 3.386535406112671, |
| "learning_rate": 3.1037414965986395e-06, |
| "loss": 0.5177210807800293, |
| "mean_token_accuracy": 0.8472946226596832, |
| "num_tokens": 2484532.0, |
| "step": 2280 |
| }, |
| { |
| "entropy": 0.5026126235723496, |
| "epoch": 0.9736394557823129, |
| "grad_norm": 0.9637086987495422, |
| "learning_rate": 2.6785714285714285e-06, |
| "loss": 0.49527649879455565, |
| "mean_token_accuracy": 0.85142502784729, |
| "num_tokens": 2494982.0, |
| "step": 2290 |
| }, |
| { |
| "entropy": 0.5845519959926605, |
| "epoch": 0.9778911564625851, |
| "grad_norm": 0.9303038120269775, |
| "learning_rate": 2.253401360544218e-06, |
| "loss": 0.568077802658081, |
| "mean_token_accuracy": 0.8299287617206573, |
| "num_tokens": 2505785.0, |
| "step": 2300 |
| }, |
| { |
| "entropy": 0.5489324152469635, |
| "epoch": 0.9821428571428571, |
| "grad_norm": 1.0844236612319946, |
| "learning_rate": 1.8282312925170068e-06, |
| "loss": 0.5580832481384277, |
| "mean_token_accuracy": 0.8412139117717743, |
| "num_tokens": 2514540.0, |
| "step": 2310 |
| }, |
| { |
| "entropy": 0.5149367898702621, |
| "epoch": 0.9863945578231292, |
| "grad_norm": 1.0444934368133545, |
| "learning_rate": 1.403061224489796e-06, |
| "loss": 0.5115521907806396, |
| "mean_token_accuracy": 0.8455105900764466, |
| "num_tokens": 2525422.0, |
| "step": 2320 |
| }, |
| { |
| "entropy": 0.5144448757171631, |
| "epoch": 0.9906462585034014, |
| "grad_norm": 0.7299341559410095, |
| "learning_rate": 9.778911564625851e-07, |
| "loss": 0.5067722797393799, |
| "mean_token_accuracy": 0.8519455373287201, |
| "num_tokens": 2535049.0, |
| "step": 2330 |
| }, |
| { |
| "entropy": 0.5480362325906754, |
| "epoch": 0.9948979591836735, |
| "grad_norm": 1.154684066772461, |
| "learning_rate": 5.527210884353742e-07, |
| "loss": 0.5571912288665771, |
| "mean_token_accuracy": 0.8421735644340516, |
| "num_tokens": 2544974.0, |
| "step": 2340 |
| }, |
| { |
| "entropy": 0.5128873139619827, |
| "epoch": 0.9991496598639455, |
| "grad_norm": 0.5887725949287415, |
| "learning_rate": 1.2755102040816326e-07, |
| "loss": 0.5141651153564453, |
| "mean_token_accuracy": 0.8440634250640869, |
| "num_tokens": 2555761.0, |
| "step": 2350 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_entropy": 0.5433352808005937, |
| "eval_loss": 0.5373454689979553, |
| "eval_mean_token_accuracy": 0.8366637416468322, |
| "eval_num_tokens": 2558089.0, |
| "eval_runtime": 35.2529, |
| "eval_samples_per_second": 29.643, |
| "eval_steps_per_second": 7.432, |
| "step": 2352 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2352, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.921285046068777e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
