| { |
| "best_global_step": 3000, |
| "best_metric": 0.43371766805648804, |
| "best_model_checkpoint": "/scratch/gk_checkpoint_lora_v2/checkpoint-3000", |
| "epoch": 2.956475824092932, |
| "eval_steps": 200, |
| "global_step": 9800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.0372698324173688, |
| "epoch": 0.015086369465188203, |
| "grad_norm": 0.4944687783718109, |
| "learning_rate": 3.266666666666667e-05, |
| "loss": 2.1209957885742186, |
| "mean_token_accuracy": 0.6639667785167694, |
| "num_tokens": 213967.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.4767542722821236, |
| "epoch": 0.030172738930376405, |
| "grad_norm": 0.29953643679618835, |
| "learning_rate": 6.6e-05, |
| "loss": 0.5209395980834961, |
| "mean_token_accuracy": 0.9028549310564995, |
| "num_tokens": 426365.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.46151453502476214, |
| "epoch": 0.04525910839556461, |
| "grad_norm": 0.3118787109851837, |
| "learning_rate": 9.933333333333334e-05, |
| "loss": 0.508198356628418, |
| "mean_token_accuracy": 0.9032981966435909, |
| "num_tokens": 642837.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.4455497920885682, |
| "epoch": 0.06034547786075281, |
| "grad_norm": 0.3013271391391754, |
| "learning_rate": 9.999382532513122e-05, |
| "loss": 0.48826019287109373, |
| "mean_token_accuracy": 0.907553653717041, |
| "num_tokens": 856475.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.06034547786075281, |
| "eval_entropy": 0.4689600637588114, |
| "eval_loss": 0.4816349446773529, |
| "eval_mean_token_accuracy": 0.8987587762934696, |
| "eval_num_tokens": 856475.0, |
| "eval_runtime": 37.5206, |
| "eval_samples_per_second": 57.728, |
| "eval_steps_per_second": 7.223, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.44372758489102127, |
| "epoch": 0.075431847325941, |
| "grad_norm": 0.31373220682144165, |
| "learning_rate": 9.997479627263544e-05, |
| "loss": 0.4843710327148438, |
| "mean_token_accuracy": 0.9082412907481193, |
| "num_tokens": 1069370.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.4475720078870654, |
| "epoch": 0.09051821679112922, |
| "grad_norm": 0.27380964159965515, |
| "learning_rate": 9.994291516446573e-05, |
| "loss": 0.491109733581543, |
| "mean_token_accuracy": 0.9055162121355533, |
| "num_tokens": 1286132.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.4463552813604474, |
| "epoch": 0.10560458625631741, |
| "grad_norm": 0.2614763677120209, |
| "learning_rate": 9.989819019951048e-05, |
| "loss": 0.4837772369384766, |
| "mean_token_accuracy": 0.9081570096313953, |
| "num_tokens": 1500851.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.41013720393180847, |
| "epoch": 0.12069095572150562, |
| "grad_norm": 0.4836612045764923, |
| "learning_rate": 9.984063287972232e-05, |
| "loss": 0.44385364532470706, |
| "mean_token_accuracy": 0.9148843766748905, |
| "num_tokens": 1708807.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.12069095572150562, |
| "eval_entropy": 0.4811463643044123, |
| "eval_loss": 0.4747391641139984, |
| "eval_mean_token_accuracy": 0.8997697566268189, |
| "eval_num_tokens": 1708807.0, |
| "eval_runtime": 37.1123, |
| "eval_samples_per_second": 58.363, |
| "eval_steps_per_second": 7.302, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.42200190499424933, |
| "epoch": 0.13577732518669383, |
| "grad_norm": 0.19339531660079956, |
| "learning_rate": 9.977025800716017e-05, |
| "loss": 0.45712459564208985, |
| "mean_token_accuracy": 0.9106362241506577, |
| "num_tokens": 1923184.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.43271509755402804, |
| "epoch": 0.150863694651882, |
| "grad_norm": 0.299110472202301, |
| "learning_rate": 9.968708368018253e-05, |
| "loss": 0.4724855422973633, |
| "mean_token_accuracy": 0.9078708891570568, |
| "num_tokens": 2139609.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.43638833791017534, |
| "epoch": 0.16595006411707022, |
| "grad_norm": 0.2539425492286682, |
| "learning_rate": 9.959113128879322e-05, |
| "loss": 0.4785395050048828, |
| "mean_token_accuracy": 0.907249256670475, |
| "num_tokens": 2358080.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.43115664307028057, |
| "epoch": 0.18103643358225843, |
| "grad_norm": 0.2542003393173218, |
| "learning_rate": 9.948242550914035e-05, |
| "loss": 0.4740608215332031, |
| "mean_token_accuracy": 0.9089943794906139, |
| "num_tokens": 2574667.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.18103643358225843, |
| "eval_entropy": 0.45346878287537074, |
| "eval_loss": 0.46328845620155334, |
| "eval_mean_token_accuracy": 0.9025413253210568, |
| "eval_num_tokens": 2574667.0, |
| "eval_runtime": 37.1254, |
| "eval_samples_per_second": 58.343, |
| "eval_steps_per_second": 7.3, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.4420048241317272, |
| "epoch": 0.19612280304744664, |
| "grad_norm": 0.26832085847854614, |
| "learning_rate": 9.936099429717045e-05, |
| "loss": 0.486652717590332, |
| "mean_token_accuracy": 0.9074076810479164, |
| "num_tokens": 2790489.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.4269510039314628, |
| "epoch": 0.21120917251263482, |
| "grad_norm": 0.20635050535202026, |
| "learning_rate": 9.922686888143897e-05, |
| "loss": 0.4619187927246094, |
| "mean_token_accuracy": 0.910810690075159, |
| "num_tokens": 3003881.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.42016164746135476, |
| "epoch": 0.22629554197782303, |
| "grad_norm": 0.2643264830112457, |
| "learning_rate": 9.908008375507924e-05, |
| "loss": 0.46344844818115233, |
| "mean_token_accuracy": 0.9113752076029777, |
| "num_tokens": 3218446.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.3974369211867452, |
| "epoch": 0.24138191144301124, |
| "grad_norm": 0.19392798840999603, |
| "learning_rate": 9.89206766669318e-05, |
| "loss": 0.42646697998046873, |
| "mean_token_accuracy": 0.9165593402087688, |
| "num_tokens": 3428256.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.24138191144301124, |
| "eval_entropy": 0.43642714537157784, |
| "eval_loss": 0.46031010150909424, |
| "eval_mean_token_accuracy": 0.9025695645061366, |
| "eval_num_tokens": 3428256.0, |
| "eval_runtime": 37.1078, |
| "eval_samples_per_second": 58.37, |
| "eval_steps_per_second": 7.303, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.4217161551490426, |
| "epoch": 0.25646828090819945, |
| "grad_norm": 0.21452021598815918, |
| "learning_rate": 9.874868861183658e-05, |
| "loss": 0.4612973022460938, |
| "mean_token_accuracy": 0.9114794608950615, |
| "num_tokens": 3642529.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 0.41439461953938006, |
| "epoch": 0.27155465037338766, |
| "grad_norm": 0.25079163908958435, |
| "learning_rate": 9.856416382009006e-05, |
| "loss": 0.4494070053100586, |
| "mean_token_accuracy": 0.9127840812504292, |
| "num_tokens": 3855962.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 0.4270974922552705, |
| "epoch": 0.2866410198385759, |
| "grad_norm": 0.20817860960960388, |
| "learning_rate": 9.836714974607077e-05, |
| "loss": 0.46105358123779294, |
| "mean_token_accuracy": 0.9099104046821594, |
| "num_tokens": 4069157.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 0.400859787017107, |
| "epoch": 0.301727389303764, |
| "grad_norm": 0.20943191647529602, |
| "learning_rate": 9.815769705603521e-05, |
| "loss": 0.4289055633544922, |
| "mean_token_accuracy": 0.9167061321437359, |
| "num_tokens": 4278743.0, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.301727389303764, |
| "eval_entropy": 0.44312036031946483, |
| "eval_loss": 0.4571220278739929, |
| "eval_mean_token_accuracy": 0.9029428505809545, |
| "eval_num_tokens": 4278743.0, |
| "eval_runtime": 37.0803, |
| "eval_samples_per_second": 58.414, |
| "eval_steps_per_second": 7.308, |
| "step": 1000 |
| }, |
| { |
| "entropy": 0.4052092955261469, |
| "epoch": 0.31681375876895224, |
| "grad_norm": 0.21670734882354736, |
| "learning_rate": 9.793585961508811e-05, |
| "loss": 0.44187084197998044, |
| "mean_token_accuracy": 0.9138142390549183, |
| "num_tokens": 4495120.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 0.3885428298264742, |
| "epoch": 0.33190012823414045, |
| "grad_norm": 0.2656344771385193, |
| "learning_rate": 9.770169447332977e-05, |
| "loss": 0.42026878356933595, |
| "mean_token_accuracy": 0.9171342994272709, |
| "num_tokens": 4707664.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 0.41116086438298227, |
| "epoch": 0.34698649769932866, |
| "grad_norm": 0.25747165083885193, |
| "learning_rate": 9.745526185118458e-05, |
| "loss": 0.44418087005615237, |
| "mean_token_accuracy": 0.9133055797219276, |
| "num_tokens": 4921515.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 0.40833847373723986, |
| "epoch": 0.36207286716451687, |
| "grad_norm": 0.22326916456222534, |
| "learning_rate": 9.719662512391396e-05, |
| "loss": 0.4394912338256836, |
| "mean_token_accuracy": 0.9140990000963211, |
| "num_tokens": 5133998.0, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.36207286716451687, |
| "eval_entropy": 0.44459747828240764, |
| "eval_loss": 0.4540960192680359, |
| "eval_mean_token_accuracy": 0.9033675605080664, |
| "eval_num_tokens": 5133998.0, |
| "eval_runtime": 37.1014, |
| "eval_samples_per_second": 58.381, |
| "eval_steps_per_second": 7.304, |
| "step": 1200 |
| }, |
| { |
| "entropy": 0.39192866910248997, |
| "epoch": 0.3771592366297051, |
| "grad_norm": 0.20642907917499542, |
| "learning_rate": 9.692585080531822e-05, |
| "loss": 0.42892616271972656, |
| "mean_token_accuracy": 0.9165673214197159, |
| "num_tokens": 5348047.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 0.40107650008052587, |
| "epoch": 0.3922456060948933, |
| "grad_norm": 0.2515887916088104, |
| "learning_rate": 9.664300853063104e-05, |
| "loss": 0.4329941558837891, |
| "mean_token_accuracy": 0.9152751086652279, |
| "num_tokens": 5562125.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 0.3964537301659584, |
| "epoch": 0.4073319755600815, |
| "grad_norm": 0.20992055535316467, |
| "learning_rate": 9.63481710386114e-05, |
| "loss": 0.4275414276123047, |
| "mean_token_accuracy": 0.9168652257323265, |
| "num_tokens": 5773685.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 0.39044841077178716, |
| "epoch": 0.42241834502526965, |
| "grad_norm": 0.30388110876083374, |
| "learning_rate": 9.604141415283728e-05, |
| "loss": 0.42324817657470704, |
| "mean_token_accuracy": 0.9169075645506382, |
| "num_tokens": 5986601.0, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.42241834502526965, |
| "eval_entropy": 0.4361799991658693, |
| "eval_loss": 0.45172417163848877, |
| "eval_mean_token_accuracy": 0.9033232137725802, |
| "eval_num_tokens": 5986601.0, |
| "eval_runtime": 37.1897, |
| "eval_samples_per_second": 58.242, |
| "eval_steps_per_second": 7.287, |
| "step": 1400 |
| }, |
| { |
| "entropy": 0.4137679870799184, |
| "epoch": 0.43750471449045786, |
| "grad_norm": 0.23755542933940887, |
| "learning_rate": 9.572281676220608e-05, |
| "loss": 0.4478377532958984, |
| "mean_token_accuracy": 0.911891212016344, |
| "num_tokens": 6203048.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 0.41279098089784383, |
| "epoch": 0.45259108395564607, |
| "grad_norm": 0.21780936419963837, |
| "learning_rate": 9.539246080064659e-05, |
| "loss": 0.45262195587158205, |
| "mean_token_accuracy": 0.9123758906126023, |
| "num_tokens": 6419624.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 0.41412957072257994, |
| "epoch": 0.4676774534208343, |
| "grad_norm": 0.2430579662322998, |
| "learning_rate": 9.505043122604818e-05, |
| "loss": 0.45246307373046873, |
| "mean_token_accuracy": 0.9122441673278808, |
| "num_tokens": 6633965.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 0.3798889485746622, |
| "epoch": 0.4827638228860225, |
| "grad_norm": 0.28653672337532043, |
| "learning_rate": 9.469681599841192e-05, |
| "loss": 0.41427810668945314, |
| "mean_token_accuracy": 0.9184439463913441, |
| "num_tokens": 6847358.0, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.4827638228860225, |
| "eval_entropy": 0.43242653594025826, |
| "eval_loss": 0.4488651752471924, |
| "eval_mean_token_accuracy": 0.9040581949082688, |
| "eval_num_tokens": 6847358.0, |
| "eval_runtime": 37.1595, |
| "eval_samples_per_second": 58.289, |
| "eval_steps_per_second": 7.293, |
| "step": 1600 |
| }, |
| { |
| "entropy": 0.38126184083521364, |
| "epoch": 0.4978501923512107, |
| "grad_norm": 0.2068091183900833, |
| "learning_rate": 9.433170605722996e-05, |
| "loss": 0.40500320434570314, |
| "mean_token_accuracy": 0.9181749866902829, |
| "num_tokens": 7062005.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 0.38879580337554215, |
| "epoch": 0.5129365618163989, |
| "grad_norm": 0.19908899068832397, |
| "learning_rate": 9.395519529809848e-05, |
| "loss": 0.41957916259765626, |
| "mean_token_accuracy": 0.9183010324835778, |
| "num_tokens": 7272082.0, |
| "step": 1700 |
| }, |
| { |
| "entropy": 0.3867104376107454, |
| "epoch": 0.5280229312815871, |
| "grad_norm": 0.21681655943393707, |
| "learning_rate": 9.356738054857057e-05, |
| "loss": 0.41496986389160156, |
| "mean_token_accuracy": 0.9176018598675728, |
| "num_tokens": 7484751.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 0.3900348538905382, |
| "epoch": 0.5431093007467753, |
| "grad_norm": 0.23264895379543304, |
| "learning_rate": 9.316836154325494e-05, |
| "loss": 0.4201799774169922, |
| "mean_token_accuracy": 0.9161376728117466, |
| "num_tokens": 7699385.0, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.5431093007467753, |
| "eval_entropy": 0.4371595958941977, |
| "eval_loss": 0.44555598497390747, |
| "eval_mean_token_accuracy": 0.9047388078101887, |
| "eval_num_tokens": 7699385.0, |
| "eval_runtime": 37.2391, |
| "eval_samples_per_second": 58.165, |
| "eval_steps_per_second": 7.277, |
| "step": 1800 |
| }, |
| { |
| "entropy": 0.38737339399755, |
| "epoch": 0.5581956702119635, |
| "grad_norm": 0.21236486732959747, |
| "learning_rate": 9.275824089816716e-05, |
| "loss": 0.4186508941650391, |
| "mean_token_accuracy": 0.9184837466478348, |
| "num_tokens": 7912846.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 0.38791515786200764, |
| "epoch": 0.5732820396771517, |
| "grad_norm": 0.22874821722507477, |
| "learning_rate": 9.233712408433972e-05, |
| "loss": 0.42144878387451173, |
| "mean_token_accuracy": 0.9170675221085548, |
| "num_tokens": 8126645.0, |
| "step": 1900 |
| }, |
| { |
| "entropy": 0.3831383780390024, |
| "epoch": 0.5883684091423399, |
| "grad_norm": 0.3072109818458557, |
| "learning_rate": 9.190511940069813e-05, |
| "loss": 0.407428092956543, |
| "mean_token_accuracy": 0.9184182004630566, |
| "num_tokens": 8341447.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 0.38130090072751044, |
| "epoch": 0.603454778607528, |
| "grad_norm": 0.2783527374267578, |
| "learning_rate": 9.146233794620944e-05, |
| "loss": 0.41518512725830076, |
| "mean_token_accuracy": 0.9192077203094959, |
| "num_tokens": 8553915.0, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.603454778607528, |
| "eval_entropy": 0.41359548831557874, |
| "eval_loss": 0.4426310062408447, |
| "eval_mean_token_accuracy": 0.9062746316744392, |
| "eval_num_tokens": 8553915.0, |
| "eval_runtime": 37.0772, |
| "eval_samples_per_second": 58.419, |
| "eval_steps_per_second": 7.309, |
| "step": 2000 |
| }, |
| { |
| "entropy": 0.40945424281060694, |
| "epoch": 0.6185411480727163, |
| "grad_norm": 0.2751815915107727, |
| "learning_rate": 9.100889359131093e-05, |
| "loss": 0.44279281616210936, |
| "mean_token_accuracy": 0.9126340833306312, |
| "num_tokens": 8773030.0, |
| "step": 2050 |
| }, |
| { |
| "entropy": 0.37910934548825026, |
| "epoch": 0.6336275175379045, |
| "grad_norm": 0.24518635869026184, |
| "learning_rate": 9.054490294862594e-05, |
| "loss": 0.41019065856933595, |
| "mean_token_accuracy": 0.9180504800379277, |
| "num_tokens": 8987621.0, |
| "step": 2100 |
| }, |
| { |
| "entropy": 0.38141273133456705, |
| "epoch": 0.6487138870030927, |
| "grad_norm": 0.2637041211128235, |
| "learning_rate": 9.00704853429745e-05, |
| "loss": 0.41344562530517576, |
| "mean_token_accuracy": 0.9188940741121769, |
| "num_tokens": 9202085.0, |
| "step": 2150 |
| }, |
| { |
| "entropy": 0.37150444712489844, |
| "epoch": 0.6638002564682809, |
| "grad_norm": 0.23061881959438324, |
| "learning_rate": 8.958576278068655e-05, |
| "loss": 0.4002714157104492, |
| "mean_token_accuracy": 0.9211013509333134, |
| "num_tokens": 9414528.0, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.6638002564682809, |
| "eval_entropy": 0.4198416776652706, |
| "eval_loss": 0.44056928157806396, |
| "eval_mean_token_accuracy": 0.9060557997094749, |
| "eval_num_tokens": 9414528.0, |
| "eval_runtime": 37.0429, |
| "eval_samples_per_second": 58.473, |
| "eval_steps_per_second": 7.316, |
| "step": 2200 |
| }, |
| { |
| "entropy": 0.3824780482426286, |
| "epoch": 0.6788866259334692, |
| "grad_norm": 0.29528528451919556, |
| "learning_rate": 8.909085991822532e-05, |
| "loss": 0.4100413513183594, |
| "mean_token_accuracy": 0.9181285245716572, |
| "num_tokens": 9631160.0, |
| "step": 2250 |
| }, |
| { |
| "entropy": 0.37036353170871733, |
| "epoch": 0.6939729953986573, |
| "grad_norm": 0.2833597958087921, |
| "learning_rate": 8.858590403012954e-05, |
| "loss": 0.39582439422607424, |
| "mean_token_accuracy": 0.9203065976500511, |
| "num_tokens": 9844323.0, |
| "step": 2300 |
| }, |
| { |
| "entropy": 0.377471005320549, |
| "epoch": 0.7090593648638455, |
| "grad_norm": 0.2559050917625427, |
| "learning_rate": 8.807102497628199e-05, |
| "loss": 0.4039160919189453, |
| "mean_token_accuracy": 0.9185835334658623, |
| "num_tokens": 10060066.0, |
| "step": 2350 |
| }, |
| { |
| "entropy": 0.38689912386238573, |
| "epoch": 0.7241457343290337, |
| "grad_norm": 0.3571145236492157, |
| "learning_rate": 8.754635516851342e-05, |
| "loss": 0.41998291015625, |
| "mean_token_accuracy": 0.9171991994976998, |
| "num_tokens": 10275374.0, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.7241457343290337, |
| "eval_entropy": 0.4061841280148038, |
| "eval_loss": 0.4392658472061157, |
| "eval_mean_token_accuracy": 0.9060493254573583, |
| "eval_num_tokens": 10275374.0, |
| "eval_runtime": 37.185, |
| "eval_samples_per_second": 58.249, |
| "eval_steps_per_second": 7.288, |
| "step": 2400 |
| }, |
| { |
| "entropy": 0.3773344187065959, |
| "epoch": 0.7392321037942219, |
| "grad_norm": 0.23827174305915833, |
| "learning_rate": 8.701202953655006e-05, |
| "loss": 0.4055968475341797, |
| "mean_token_accuracy": 0.9189482787251473, |
| "num_tokens": 10495301.0, |
| "step": 2450 |
| }, |
| { |
| "entropy": 0.3638977843523026, |
| "epoch": 0.7543184732594101, |
| "grad_norm": 0.247745543718338, |
| "learning_rate": 8.646818549331366e-05, |
| "loss": 0.38891139984130857, |
| "mean_token_accuracy": 0.9226090031862259, |
| "num_tokens": 10706938.0, |
| "step": 2500 |
| }, |
| { |
| "entropy": 0.358336652033031, |
| "epoch": 0.7694048427245983, |
| "grad_norm": 0.24292156100273132, |
| "learning_rate": 8.591496289958292e-05, |
| "loss": 0.3846548461914063, |
| "mean_token_accuracy": 0.923456951379776, |
| "num_tokens": 10918302.0, |
| "step": 2550 |
| }, |
| { |
| "entropy": 0.37086400829255584, |
| "epoch": 0.7844912121897866, |
| "grad_norm": 0.2979118525981903, |
| "learning_rate": 8.535250402802536e-05, |
| "loss": 0.39662261962890627, |
| "mean_token_accuracy": 0.9212297305464745, |
| "num_tokens": 11131056.0, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.7844912121897866, |
| "eval_entropy": 0.4161290250361186, |
| "eval_loss": 0.43674495816230774, |
| "eval_mean_token_accuracy": 0.9060781219788583, |
| "eval_num_tokens": 11131056.0, |
| "eval_runtime": 37.0488, |
| "eval_samples_per_second": 58.463, |
| "eval_steps_per_second": 7.315, |
| "step": 2600 |
| }, |
| { |
| "entropy": 0.36887906536459925, |
| "epoch": 0.7995775816549747, |
| "grad_norm": 0.25673073530197144, |
| "learning_rate": 8.478095352660897e-05, |
| "loss": 0.3948686218261719, |
| "mean_token_accuracy": 0.9204315200448037, |
| "num_tokens": 11345648.0, |
| "step": 2650 |
| }, |
| { |
| "entropy": 0.36981521353125574, |
| "epoch": 0.814663951120163, |
| "grad_norm": 0.2649747133255005, |
| "learning_rate": 8.4200458381403e-05, |
| "loss": 0.3937848663330078, |
| "mean_token_accuracy": 0.9218536545336247, |
| "num_tokens": 11559009.0, |
| "step": 2700 |
| }, |
| { |
| "entropy": 0.37904939975589513, |
| "epoch": 0.8297503205853511, |
| "grad_norm": 0.20989011228084564, |
| "learning_rate": 8.361116787877736e-05, |
| "loss": 0.4084677505493164, |
| "mean_token_accuracy": 0.9188165719807148, |
| "num_tokens": 11776255.0, |
| "step": 2750 |
| }, |
| { |
| "entropy": 0.3781035339459777, |
| "epoch": 0.8448366900505393, |
| "grad_norm": 0.2979874908924103, |
| "learning_rate": 8.301323356701069e-05, |
| "loss": 0.40767410278320315, |
| "mean_token_accuracy": 0.9183482979238033, |
| "num_tokens": 11994830.0, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.8448366900505393, |
| "eval_entropy": 0.3918299580962016, |
| "eval_loss": 0.43606311082839966, |
| "eval_mean_token_accuracy": 0.9074829088805786, |
| "eval_num_tokens": 11994830.0, |
| "eval_runtime": 37.1502, |
| "eval_samples_per_second": 58.304, |
| "eval_steps_per_second": 7.295, |
| "step": 2800 |
| }, |
| { |
| "entropy": 0.3669764836877584, |
| "epoch": 0.8599230595157276, |
| "grad_norm": 0.3718933165073395, |
| "learning_rate": 8.240680921731639e-05, |
| "loss": 0.39511192321777344, |
| "mean_token_accuracy": 0.9215331043303013, |
| "num_tokens": 12210990.0, |
| "step": 2850 |
| }, |
| { |
| "entropy": 0.36516126081347466, |
| "epoch": 0.8750094289809157, |
| "grad_norm": 0.2584734559059143, |
| "learning_rate": 8.179205078429728e-05, |
| "loss": 0.3858111572265625, |
| "mean_token_accuracy": 0.9223315984010696, |
| "num_tokens": 12425768.0, |
| "step": 2900 |
| }, |
| { |
| "entropy": 0.36489626977592704, |
| "epoch": 0.890095798446104, |
| "grad_norm": 0.260593980550766, |
| "learning_rate": 8.116911636583866e-05, |
| "loss": 0.3904818344116211, |
| "mean_token_accuracy": 0.921723841279745, |
| "num_tokens": 12644047.0, |
| "step": 2950 |
| }, |
| { |
| "entropy": 0.35986222576349974, |
| "epoch": 0.9051821679112921, |
| "grad_norm": 0.2872949540615082, |
| "learning_rate": 8.053816616245007e-05, |
| "loss": 0.3802699661254883, |
| "mean_token_accuracy": 0.922919643521309, |
| "num_tokens": 12858612.0, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.9051821679112921, |
| "eval_entropy": 0.39114147694128465, |
| "eval_loss": 0.43371766805648804, |
| "eval_mean_token_accuracy": 0.9085190791045608, |
| "eval_num_tokens": 12858612.0, |
| "eval_runtime": 37.1981, |
| "eval_samples_per_second": 58.229, |
| "eval_steps_per_second": 7.285, |
| "step": 3000 |
| }, |
| { |
| "entropy": 0.3628548865020275, |
| "epoch": 0.9202685373764804, |
| "grad_norm": 0.3397461771965027, |
| "learning_rate": 7.989936243606644e-05, |
| "loss": 0.38797500610351565, |
| "mean_token_accuracy": 0.9223182892799378, |
| "num_tokens": 13074583.0, |
| "step": 3050 |
| }, |
| { |
| "entropy": 0.3658443212881684, |
| "epoch": 0.9353549068416686, |
| "grad_norm": 0.21586942672729492, |
| "learning_rate": 7.925286946831907e-05, |
| "loss": 0.38840934753417966, |
| "mean_token_accuracy": 0.920469640493393, |
| "num_tokens": 13290531.0, |
| "step": 3100 |
| }, |
| { |
| "entropy": 0.3434870146587491, |
| "epoch": 0.9504412763068567, |
| "grad_norm": 0.4203721582889557, |
| "learning_rate": 7.859885351828722e-05, |
| "loss": 0.3654581832885742, |
| "mean_token_accuracy": 0.9264674150943756, |
| "num_tokens": 13501774.0, |
| "step": 3150 |
| }, |
| { |
| "entropy": 0.3622769057378173, |
| "epoch": 0.965527645772045, |
| "grad_norm": 0.4923344850540161, |
| "learning_rate": 7.793748277974116e-05, |
| "loss": 0.38648658752441406, |
| "mean_token_accuracy": 0.9216807208955288, |
| "num_tokens": 13719293.0, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.965527645772045, |
| "eval_entropy": 0.38819593988441453, |
| "eval_loss": 0.43394002318382263, |
| "eval_mean_token_accuracy": 0.9077828526496887, |
| "eval_num_tokens": 13719293.0, |
| "eval_runtime": 37.2602, |
| "eval_samples_per_second": 58.132, |
| "eval_steps_per_second": 7.273, |
| "step": 3200 |
| }, |
| { |
| "entropy": 0.35784762669354675, |
| "epoch": 0.9806140152372331, |
| "grad_norm": 0.295482873916626, |
| "learning_rate": 7.72689273378875e-05, |
| "loss": 0.3751881790161133, |
| "mean_token_accuracy": 0.9235683201253414, |
| "num_tokens": 13933952.0, |
| "step": 3250 |
| }, |
| { |
| "entropy": 0.35060869861394167, |
| "epoch": 0.9957003847024214, |
| "grad_norm": 0.3346746265888214, |
| "learning_rate": 7.659335912562849e-05, |
| "loss": 0.3715841293334961, |
| "mean_token_accuracy": 0.9249463096261025, |
| "num_tokens": 14146736.0, |
| "step": 3300 |
| }, |
| { |
| "entropy": 0.33144386649736896, |
| "epoch": 1.0105604586256318, |
| "grad_norm": 0.42002174258232117, |
| "learning_rate": 7.591095187934571e-05, |
| "loss": 0.3447689437866211, |
| "mean_token_accuracy": 0.9282537361389489, |
| "num_tokens": 14363628.0, |
| "step": 3350 |
| }, |
| { |
| "entropy": 0.29580484244972466, |
| "epoch": 1.02564682809082, |
| "grad_norm": 0.267696350812912, |
| "learning_rate": 7.522188109422025e-05, |
| "loss": 0.30982461929321287, |
| "mean_token_accuracy": 0.9349895706772804, |
| "num_tokens": 14577748.0, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.02564682809082, |
| "eval_entropy": 0.3474461413452546, |
| "eval_loss": 0.4461125433444977, |
| "eval_mean_token_accuracy": 0.9071816351140997, |
| "eval_num_tokens": 14577748.0, |
| "eval_runtime": 37.1626, |
| "eval_samples_per_second": 58.284, |
| "eval_steps_per_second": 7.292, |
| "step": 3400 |
| }, |
| { |
| "entropy": 0.30122795451432466, |
| "epoch": 1.0407331975560081, |
| "grad_norm": 0.2817290127277374, |
| "learning_rate": 7.452632397910045e-05, |
| "loss": 0.3127718353271484, |
| "mean_token_accuracy": 0.93441466614604, |
| "num_tokens": 14792632.0, |
| "step": 3450 |
| }, |
| { |
| "entropy": 0.2921810976602137, |
| "epoch": 1.0558195670211963, |
| "grad_norm": 0.3158903419971466, |
| "learning_rate": 7.3824459410929e-05, |
| "loss": 0.3033764839172363, |
| "mean_token_accuracy": 0.9362939922511577, |
| "num_tokens": 15005289.0, |
| "step": 3500 |
| }, |
| { |
| "entropy": 0.30137234527617696, |
| "epoch": 1.0709059364863847, |
| "grad_norm": 0.363569974899292, |
| "learning_rate": 7.311646788874093e-05, |
| "loss": 0.3192999267578125, |
| "mean_token_accuracy": 0.9330788172781468, |
| "num_tokens": 15221117.0, |
| "step": 3550 |
| }, |
| { |
| "entropy": 0.2979462206363678, |
| "epoch": 1.0859923059515728, |
| "grad_norm": 0.33784833550453186, |
| "learning_rate": 7.240253148724472e-05, |
| "loss": 0.3097235298156738, |
| "mean_token_accuracy": 0.935227975398302, |
| "num_tokens": 15433103.0, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.0859923059515728, |
| "eval_entropy": 0.33927392830378017, |
| "eval_loss": 0.44939693808555603, |
| "eval_mean_token_accuracy": 0.9080607321429517, |
| "eval_num_tokens": 15433103.0, |
| "eval_runtime": 37.0789, |
| "eval_samples_per_second": 58.416, |
| "eval_steps_per_second": 7.309, |
| "step": 3600 |
| }, |
| { |
| "entropy": 0.2955490641668439, |
| "epoch": 1.101078675416761, |
| "grad_norm": 0.26954564452171326, |
| "learning_rate": 7.168283380999781e-05, |
| "loss": 0.308115234375, |
| "mean_token_accuracy": 0.9356962423026561, |
| "num_tokens": 15647397.0, |
| "step": 3650 |
| }, |
| { |
| "entropy": 0.3024994757771492, |
| "epoch": 1.1161650448819491, |
| "grad_norm": 0.34243258833885193, |
| "learning_rate": 7.095755994218929e-05, |
| "loss": 0.3163371467590332, |
| "mean_token_accuracy": 0.933635587990284, |
| "num_tokens": 15862307.0, |
| "step": 3700 |
| }, |
| { |
| "entropy": 0.28693753194063903, |
| "epoch": 1.1312514143471373, |
| "grad_norm": 0.3753094971179962, |
| "learning_rate": 7.022689640304127e-05, |
| "loss": 0.30058185577392577, |
| "mean_token_accuracy": 0.9367860886454582, |
| "num_tokens": 16077573.0, |
| "step": 3750 |
| }, |
| { |
| "entropy": 0.2817346750572324, |
| "epoch": 1.1463377838123257, |
| "grad_norm": 0.36651188135147095, |
| "learning_rate": 6.949103109784174e-05, |
| "loss": 0.29092519760131835, |
| "mean_token_accuracy": 0.9392722348868847, |
| "num_tokens": 16287755.0, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.1463377838123257, |
| "eval_entropy": 0.3268261263181363, |
| "eval_loss": 0.45524126291275024, |
| "eval_mean_token_accuracy": 0.9080498321909746, |
| "eval_num_tokens": 16287755.0, |
| "eval_runtime": 37.2707, |
| "eval_samples_per_second": 58.115, |
| "eval_steps_per_second": 7.271, |
| "step": 3800 |
| }, |
| { |
| "entropy": 0.2927645993977785, |
| "epoch": 1.1614241532775138, |
| "grad_norm": 0.32257115840911865, |
| "learning_rate": 6.875015326962071e-05, |
| "loss": 0.3056098175048828, |
| "mean_token_accuracy": 0.9361269493401051, |
| "num_tokens": 16500869.0, |
| "step": 3850 |
| }, |
| { |
| "entropy": 0.2784220616333187, |
| "epoch": 1.176510522742702, |
| "grad_norm": 0.3277973234653473, |
| "learning_rate": 6.800445345048247e-05, |
| "loss": 0.2863511276245117, |
| "mean_token_accuracy": 0.9394664193689823, |
| "num_tokens": 16714052.0, |
| "step": 3900 |
| }, |
| { |
| "entropy": 0.28824312970042226, |
| "epoch": 1.1915968922078901, |
| "grad_norm": 0.45423227548599243, |
| "learning_rate": 6.725412341260632e-05, |
| "loss": 0.30036584854125975, |
| "mean_token_accuracy": 0.9367516180872917, |
| "num_tokens": 16929433.0, |
| "step": 3950 |
| }, |
| { |
| "entropy": 0.3048727669939399, |
| "epoch": 1.2066832616730783, |
| "grad_norm": 0.4174216091632843, |
| "learning_rate": 6.649935611892839e-05, |
| "loss": 0.3221250534057617, |
| "mean_token_accuracy": 0.9329589973390102, |
| "num_tokens": 17149131.0, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.2066832616730783, |
| "eval_entropy": 0.3393887681439794, |
| "eval_loss": 0.44970703125, |
| "eval_mean_token_accuracy": 0.907502448866728, |
| "eval_num_tokens": 17149131.0, |
| "eval_runtime": 37.1753, |
| "eval_samples_per_second": 58.265, |
| "eval_steps_per_second": 7.29, |
| "step": 4000 |
| }, |
| { |
| "entropy": 0.2786213347688317, |
| "epoch": 1.2217696311382666, |
| "grad_norm": 0.37704846262931824, |
| "learning_rate": 6.574034567351717e-05, |
| "loss": 0.28641138076782224, |
| "mean_token_accuracy": 0.9393399634957313, |
| "num_tokens": 17362785.0, |
| "step": 4050 |
| }, |
| { |
| "entropy": 0.2889704497903585, |
| "epoch": 1.2368560006034548, |
| "grad_norm": 0.3806622624397278, |
| "learning_rate": 6.49772872716557e-05, |
| "loss": 0.30537261962890627, |
| "mean_token_accuracy": 0.9361220151185989, |
| "num_tokens": 17578670.0, |
| "step": 4100 |
| }, |
| { |
| "entropy": 0.29292779937386515, |
| "epoch": 1.251942370068643, |
| "grad_norm": 0.3169683814048767, |
| "learning_rate": 6.421037714964293e-05, |
| "loss": 0.30579683303833005, |
| "mean_token_accuracy": 0.9352342364192009, |
| "num_tokens": 17802008.0, |
| "step": 4150 |
| }, |
| { |
| "entropy": 0.28012287182733414, |
| "epoch": 1.267028739533831, |
| "grad_norm": 0.2556808888912201, |
| "learning_rate": 6.343981253432761e-05, |
| "loss": 0.2942901611328125, |
| "mean_token_accuracy": 0.93847431153059, |
| "num_tokens": 18015619.0, |
| "step": 4200 |
| }, |
| { |
| "epoch": 1.267028739533831, |
| "eval_entropy": 0.3326790584354383, |
| "eval_loss": 0.45203062891960144, |
| "eval_mean_token_accuracy": 0.9082723077372871, |
| "eval_num_tokens": 18015619.0, |
| "eval_runtime": 37.2103, |
| "eval_samples_per_second": 58.21, |
| "eval_steps_per_second": 7.283, |
| "step": 4200 |
| }, |
| { |
| "entropy": 0.2790189484320581, |
| "epoch": 1.2821151089990193, |
| "grad_norm": 0.3167658746242523, |
| "learning_rate": 6.266579159238723e-05, |
| "loss": 0.2901947212219238, |
| "mean_token_accuracy": 0.9385272514820099, |
| "num_tokens": 18231214.0, |
| "step": 4250 |
| }, |
| { |
| "entropy": 0.28492060406133535, |
| "epoch": 1.2972014784642076, |
| "grad_norm": 0.3428349792957306, |
| "learning_rate": 6.188851337936541e-05, |
| "loss": 0.2975013542175293, |
| "mean_token_accuracy": 0.9384494511783124, |
| "num_tokens": 18443602.0, |
| "step": 4300 |
| }, |
| { |
| "entropy": 0.28728573814034464, |
| "epoch": 1.3122878479293958, |
| "grad_norm": 0.3879326581954956, |
| "learning_rate": 6.110817778848062e-05, |
| "loss": 0.2947955894470215, |
| "mean_token_accuracy": 0.9376472027599811, |
| "num_tokens": 18658957.0, |
| "step": 4350 |
| }, |
| { |
| "entropy": 0.27078360263258217, |
| "epoch": 1.327374217394584, |
| "grad_norm": 0.45004045963287354, |
| "learning_rate": 6.032498549921939e-05, |
| "loss": 0.28305835723876954, |
| "mean_token_accuracy": 0.9406134666502476, |
| "num_tokens": 18870053.0, |
| "step": 4400 |
| }, |
| { |
| "epoch": 1.327374217394584, |
| "eval_entropy": 0.3294620155958232, |
| "eval_loss": 0.4543997049331665, |
| "eval_mean_token_accuracy": 0.9081211842294109, |
| "eval_num_tokens": 18870053.0, |
| "eval_runtime": 37.2524, |
| "eval_samples_per_second": 58.144, |
| "eval_steps_per_second": 7.275, |
| "step": 4400 |
| }, |
| { |
| "entropy": 0.2799815020523965, |
| "epoch": 1.3424605868597723, |
| "grad_norm": 0.44520097970962524, |
| "learning_rate": 5.953913792572761e-05, |
| "loss": 0.28622047424316405, |
| "mean_token_accuracy": 0.9398869612812996, |
| "num_tokens": 19083502.0, |
| "step": 4450 |
| }, |
| { |
| "entropy": 0.28538848023861646, |
| "epoch": 1.3575469563249605, |
| "grad_norm": 0.376067578792572, |
| "learning_rate": 5.8750837165012516e-05, |
| "loss": 0.29442657470703126, |
| "mean_token_accuracy": 0.9369049946963787, |
| "num_tokens": 19301474.0, |
| "step": 4500 |
| }, |
| { |
| "entropy": 0.2700873460620642, |
| "epoch": 1.3726333257901486, |
| "grad_norm": 0.3803156316280365, |
| "learning_rate": 5.79602859449694e-05, |
| "loss": 0.2789628601074219, |
| "mean_token_accuracy": 0.9409016688168049, |
| "num_tokens": 19513118.0, |
| "step": 4550 |
| }, |
| { |
| "entropy": 0.2818992605619133, |
| "epoch": 1.3877196952553368, |
| "grad_norm": 0.3878261148929596, |
| "learning_rate": 5.716768757224583e-05, |
| "loss": 0.291706428527832, |
| "mean_token_accuracy": 0.9382703882455826, |
| "num_tokens": 19729704.0, |
| "step": 4600 |
| }, |
| { |
| "epoch": 1.3877196952553368, |
| "eval_entropy": 0.3223673155551907, |
| "eval_loss": 0.4583451747894287, |
| "eval_mean_token_accuracy": 0.9085318800268138, |
| "eval_num_tokens": 19729704.0, |
| "eval_runtime": 37.2126, |
| "eval_samples_per_second": 58.206, |
| "eval_steps_per_second": 7.282, |
| "step": 4600 |
| }, |
| { |
| "entropy": 0.2773911802843213, |
| "epoch": 1.402806064720525, |
| "grad_norm": 0.4441978931427002, |
| "learning_rate": 5.637324587995714e-05, |
| "loss": 0.28889572143554687, |
| "mean_token_accuracy": 0.9393369700014591, |
| "num_tokens": 19941579.0, |
| "step": 4650 |
| }, |
| { |
| "entropy": 0.2760587067343295, |
| "epoch": 1.4178924341857133, |
| "grad_norm": 0.31453457474708557, |
| "learning_rate": 5.557716517526656e-05, |
| "loss": 0.2823097038269043, |
| "mean_token_accuracy": 0.9404082801938057, |
| "num_tokens": 20152481.0, |
| "step": 4700 |
| }, |
| { |
| "entropy": 0.2687125858291984, |
| "epoch": 1.4329788036509015, |
| "grad_norm": 0.4302677810192108, |
| "learning_rate": 5.4779650186843335e-05, |
| "loss": 0.28021940231323245, |
| "mean_token_accuracy": 0.9412896266579628, |
| "num_tokens": 20364280.0, |
| "step": 4750 |
| }, |
| { |
| "entropy": 0.28299310375005005, |
| "epoch": 1.4480651731160896, |
| "grad_norm": 0.4275122582912445, |
| "learning_rate": 5.3980906012212575e-05, |
| "loss": 0.29417877197265624, |
| "mean_token_accuracy": 0.9380144135653973, |
| "num_tokens": 20579080.0, |
| "step": 4800 |
| }, |
| { |
| "epoch": 1.4480651731160896, |
| "eval_entropy": 0.3136782179899321, |
| "eval_loss": 0.4654751420021057, |
| "eval_mean_token_accuracy": 0.9077895956725652, |
| "eval_num_tokens": 20579080.0, |
| "eval_runtime": 37.1335, |
| "eval_samples_per_second": 58.33, |
| "eval_steps_per_second": 7.298, |
| "step": 4800 |
| }, |
| { |
| "entropy": 0.26981769694015384, |
| "epoch": 1.4631515425812778, |
| "grad_norm": 0.3479642868041992, |
| "learning_rate": 5.318113806501009e-05, |
| "loss": 0.2793255615234375, |
| "mean_token_accuracy": 0.940917958021164, |
| "num_tokens": 20794818.0, |
| "step": 4850 |
| }, |
| { |
| "entropy": 0.27721120171248914, |
| "epoch": 1.478237912046466, |
| "grad_norm": 0.36213237047195435, |
| "learning_rate": 5.238055202215606e-05, |
| "loss": 0.2876263427734375, |
| "mean_token_accuracy": 0.9395251777768135, |
| "num_tokens": 21007893.0, |
| "step": 4900 |
| }, |
| { |
| "entropy": 0.2697361321747303, |
| "epoch": 1.4933242815116543, |
| "grad_norm": 0.3829312324523926, |
| "learning_rate": 5.157935377096091e-05, |
| "loss": 0.2791532325744629, |
| "mean_token_accuracy": 0.9417897801101208, |
| "num_tokens": 21221698.0, |
| "step": 4950 |
| }, |
| { |
| "entropy": 0.26987188443541527, |
| "epoch": 1.5084106509768425, |
| "grad_norm": 0.5338497757911682, |
| "learning_rate": 5.077774935617715e-05, |
| "loss": 0.2768931770324707, |
| "mean_token_accuracy": 0.9414016118645668, |
| "num_tokens": 21434912.0, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.5084106509768425, |
| "eval_entropy": 0.31743444043221947, |
| "eval_loss": 0.46169763803482056, |
| "eval_mean_token_accuracy": 0.9076986282074143, |
| "eval_num_tokens": 21434912.0, |
| "eval_runtime": 37.2102, |
| "eval_samples_per_second": 58.21, |
| "eval_steps_per_second": 7.283, |
| "step": 5000 |
| }, |
| { |
| "entropy": 0.27476332798600195, |
| "epoch": 1.5234970204420306, |
| "grad_norm": 0.3199191987514496, |
| "learning_rate": 4.997594492701074e-05, |
| "loss": 0.2819905471801758, |
| "mean_token_accuracy": 0.9403638400137424, |
| "num_tokens": 21650284.0, |
| "step": 5050 |
| }, |
| { |
| "entropy": 0.2720643111690879, |
| "epoch": 1.538583389907219, |
| "grad_norm": 0.49105435609817505, |
| "learning_rate": 4.917414668410541e-05, |
| "loss": 0.28312482833862307, |
| "mean_token_accuracy": 0.9400044956803322, |
| "num_tokens": 21864950.0, |
| "step": 5100 |
| }, |
| { |
| "entropy": 0.2742350418306887, |
| "epoch": 1.553669759372407, |
| "grad_norm": 0.3570726215839386, |
| "learning_rate": 4.837256082651398e-05, |
| "loss": 0.2866826057434082, |
| "mean_token_accuracy": 0.940371020436287, |
| "num_tokens": 22081595.0, |
| "step": 5150 |
| }, |
| { |
| "entropy": 0.26034254603087903, |
| "epoch": 1.5687561288375953, |
| "grad_norm": 0.37878358364105225, |
| "learning_rate": 4.757139349867003e-05, |
| "loss": 0.26901472091674805, |
| "mean_token_accuracy": 0.943619585186243, |
| "num_tokens": 22293286.0, |
| "step": 5200 |
| }, |
| { |
| "epoch": 1.5687561288375953, |
| "eval_entropy": 0.3216313538021267, |
| "eval_loss": 0.45686572790145874, |
| "eval_mean_token_accuracy": 0.908281669625497, |
| "eval_num_tokens": 22293286.0, |
| "eval_runtime": 37.2587, |
| "eval_samples_per_second": 58.134, |
| "eval_steps_per_second": 7.273, |
| "step": 5200 |
| }, |
| { |
| "entropy": 0.25965558482334017, |
| "epoch": 1.5838424983027835, |
| "grad_norm": 0.5104638338088989, |
| "learning_rate": 4.677085073737347e-05, |
| "loss": 0.2651633071899414, |
| "mean_token_accuracy": 0.943703119456768, |
| "num_tokens": 22507183.0, |
| "step": 5250 |
| }, |
| { |
| "entropy": 0.2634627244435251, |
| "epoch": 1.5989288677679716, |
| "grad_norm": 0.39737868309020996, |
| "learning_rate": 4.5971138418804024e-05, |
| "loss": 0.2716307067871094, |
| "mean_token_accuracy": 0.9426473924517631, |
| "num_tokens": 22719425.0, |
| "step": 5300 |
| }, |
| { |
| "entropy": 0.26387994691729544, |
| "epoch": 1.61401523723316, |
| "grad_norm": 0.3169187605381012, |
| "learning_rate": 4.517246220557577e-05, |
| "loss": 0.2690562057495117, |
| "mean_token_accuracy": 0.9435765042901039, |
| "num_tokens": 22935863.0, |
| "step": 5350 |
| }, |
| { |
| "entropy": 0.2732780100405216, |
| "epoch": 1.629101606698348, |
| "grad_norm": 0.5206496715545654, |
| "learning_rate": 4.437502749384686e-05, |
| "loss": 0.28528207778930664, |
| "mean_token_accuracy": 0.9399016280472279, |
| "num_tokens": 23150285.0, |
| "step": 5400 |
| }, |
| { |
| "epoch": 1.629101606698348, |
| "eval_entropy": 0.3117673156776111, |
| "eval_loss": 0.4644741117954254, |
| "eval_mean_token_accuracy": 0.9071205707053857, |
| "eval_num_tokens": 23150285.0, |
| "eval_runtime": 37.233, |
| "eval_samples_per_second": 58.174, |
| "eval_steps_per_second": 7.278, |
| "step": 5400 |
| }, |
| { |
| "entropy": 0.25959222281351685, |
| "epoch": 1.6441879761635363, |
| "grad_norm": 0.37161391973495483, |
| "learning_rate": 4.357903936049758e-05, |
| "loss": 0.26540708541870117, |
| "mean_token_accuracy": 0.9441601178050041, |
| "num_tokens": 23361061.0, |
| "step": 5450 |
| }, |
| { |
| "entropy": 0.258843588642776, |
| "epoch": 1.6592743456287244, |
| "grad_norm": 0.3901636302471161, |
| "learning_rate": 4.278470251039052e-05, |
| "loss": 0.2657164001464844, |
| "mean_token_accuracy": 0.9435085739195347, |
| "num_tokens": 23576068.0, |
| "step": 5500 |
| }, |
| { |
| "entropy": 0.2609032719023526, |
| "epoch": 1.6743607150939126, |
| "grad_norm": 0.3928777873516083, |
| "learning_rate": 4.199222122372658e-05, |
| "loss": 0.2640374183654785, |
| "mean_token_accuracy": 0.9443163026869297, |
| "num_tokens": 23787002.0, |
| "step": 5550 |
| }, |
| { |
| "entropy": 0.2564471643790603, |
| "epoch": 1.689447084559101, |
| "grad_norm": 0.3459172546863556, |
| "learning_rate": 4.1201799303509984e-05, |
| "loss": 0.2629901695251465, |
| "mean_token_accuracy": 0.9437471415102482, |
| "num_tokens": 23997298.0, |
| "step": 5600 |
| }, |
| { |
| "epoch": 1.689447084559101, |
| "eval_entropy": 0.30813075843992266, |
| "eval_loss": 0.46801915764808655, |
| "eval_mean_token_accuracy": 0.9075211451502304, |
| "eval_num_tokens": 23997298.0, |
| "eval_runtime": 37.1802, |
| "eval_samples_per_second": 58.257, |
| "eval_steps_per_second": 7.289, |
| "step": 5600 |
| }, |
| { |
| "entropy": 0.26069454461336133, |
| "epoch": 1.704533454024289, |
| "grad_norm": 0.4609261453151703, |
| "learning_rate": 4.041364002313619e-05, |
| "loss": 0.26864715576171877, |
| "mean_token_accuracy": 0.9432297512888909, |
| "num_tokens": 24213258.0, |
| "step": 5650 |
| }, |
| { |
| "entropy": 0.26323398426175115, |
| "epoch": 1.7196198234894773, |
| "grad_norm": 0.4566548764705658, |
| "learning_rate": 3.962794607411584e-05, |
| "loss": 0.2684891510009766, |
| "mean_token_accuracy": 0.9431661969423294, |
| "num_tokens": 24429089.0, |
| "step": 5700 |
| }, |
| { |
| "entropy": 0.26415870275348424, |
| "epoch": 1.7347061929546654, |
| "grad_norm": 0.454801082611084, |
| "learning_rate": 3.8844919513948486e-05, |
| "loss": 0.2741558265686035, |
| "mean_token_accuracy": 0.9412616415321827, |
| "num_tokens": 24646888.0, |
| "step": 5750 |
| }, |
| { |
| "entropy": 0.25849502749741077, |
| "epoch": 1.7497925624198536, |
| "grad_norm": 0.47254759073257446, |
| "learning_rate": 3.80647617141593e-05, |
| "loss": 0.26054887771606444, |
| "mean_token_accuracy": 0.94430311486125, |
| "num_tokens": 24861569.0, |
| "step": 5800 |
| }, |
| { |
| "epoch": 1.7497925624198536, |
| "eval_entropy": 0.29998021306146994, |
| "eval_loss": 0.47340917587280273, |
| "eval_mean_token_accuracy": 0.9083721395788158, |
| "eval_num_tokens": 24861569.0, |
| "eval_runtime": 37.3662, |
| "eval_samples_per_second": 57.967, |
| "eval_steps_per_second": 7.253, |
| "step": 5800 |
| }, |
| { |
| "entropy": 0.2529403425566852, |
| "epoch": 1.764878931885042, |
| "grad_norm": 0.45025748014450073, |
| "learning_rate": 3.7287673308512186e-05, |
| "loss": 0.26045492172241214, |
| "mean_token_accuracy": 0.9441630898416042, |
| "num_tokens": 25079317.0, |
| "step": 5850 |
| }, |
| { |
| "entropy": 0.2550449293479323, |
| "epoch": 1.7799653013502301, |
| "grad_norm": 0.4205138087272644, |
| "learning_rate": 3.65138541414127e-05, |
| "loss": 0.26142183303833005, |
| "mean_token_accuracy": 0.9442940099537372, |
| "num_tokens": 25293828.0, |
| "step": 5900 |
| }, |
| { |
| "entropy": 0.26166333435103295, |
| "epoch": 1.7950516708154183, |
| "grad_norm": 0.32279399037361145, |
| "learning_rate": 3.5743503216513875e-05, |
| "loss": 0.27175371170043944, |
| "mean_token_accuracy": 0.9426822887361049, |
| "num_tokens": 25509857.0, |
| "step": 5950 |
| }, |
| { |
| "entropy": 0.2534090391360223, |
| "epoch": 1.8101380402806064, |
| "grad_norm": 0.4058147370815277, |
| "learning_rate": 3.4976818645538266e-05, |
| "loss": 0.2650087547302246, |
| "mean_token_accuracy": 0.9448564203083515, |
| "num_tokens": 25722906.0, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.8101380402806064, |
| "eval_entropy": 0.3064177740379013, |
| "eval_loss": 0.4730622470378876, |
| "eval_mean_token_accuracy": 0.9072717905484442, |
| "eval_num_tokens": 25722906.0, |
| "eval_runtime": 37.3208, |
| "eval_samples_per_second": 58.037, |
| "eval_steps_per_second": 7.261, |
| "step": 6000 |
| }, |
| { |
| "entropy": 0.2568224469386041, |
| "epoch": 1.8252244097457946, |
| "grad_norm": 0.7752001285552979, |
| "learning_rate": 3.42139975973295e-05, |
| "loss": 0.26035600662231445, |
| "mean_token_accuracy": 0.9453255115449428, |
| "num_tokens": 25934089.0, |
| "step": 6050 |
| }, |
| { |
| "entropy": 0.25038454053923487, |
| "epoch": 1.840310779210983, |
| "grad_norm": 0.657081127166748, |
| "learning_rate": 3.3455236247146124e-05, |
| "loss": 0.25294511795043945, |
| "mean_token_accuracy": 0.9468451295793057, |
| "num_tokens": 26145757.0, |
| "step": 6100 |
| }, |
| { |
| "entropy": 0.25195862116292117, |
| "epoch": 1.8553971486761711, |
| "grad_norm": 0.4311438202857971, |
| "learning_rate": 3.270072972621116e-05, |
| "loss": 0.2561396598815918, |
| "mean_token_accuracy": 0.945042757242918, |
| "num_tokens": 26363126.0, |
| "step": 6150 |
| }, |
| { |
| "entropy": 0.24140722384676339, |
| "epoch": 1.8704835181413593, |
| "grad_norm": 0.3511962592601776, |
| "learning_rate": 3.1950672071529976e-05, |
| "loss": 0.2441703224182129, |
| "mean_token_accuracy": 0.9480637626349926, |
| "num_tokens": 26570762.0, |
| "step": 6200 |
| }, |
| { |
| "epoch": 1.8704835181413593, |
| "eval_entropy": 0.29495117315726965, |
| "eval_loss": 0.4819435179233551, |
| "eval_mean_token_accuracy": 0.9071202113179703, |
| "eval_num_tokens": 26570762.0, |
| "eval_runtime": 37.2485, |
| "eval_samples_per_second": 58.15, |
| "eval_steps_per_second": 7.275, |
| "step": 6200 |
| }, |
| { |
| "entropy": 0.25350754015147686, |
| "epoch": 1.8855698876065476, |
| "grad_norm": 0.4511338472366333, |
| "learning_rate": 3.1205256175989706e-05, |
| "loss": 0.2587089538574219, |
| "mean_token_accuracy": 0.9447831605374813, |
| "num_tokens": 26786633.0, |
| "step": 6250 |
| }, |
| { |
| "entropy": 0.24989185376092793, |
| "epoch": 1.9006562570717356, |
| "grad_norm": 0.6432870030403137, |
| "learning_rate": 3.046467373875282e-05, |
| "loss": 0.2545445251464844, |
| "mean_token_accuracy": 0.9456490239501, |
| "num_tokens": 26999534.0, |
| "step": 6300 |
| }, |
| { |
| "entropy": 0.2594654941000044, |
| "epoch": 1.915742626536924, |
| "grad_norm": 0.3382566273212433, |
| "learning_rate": 2.9729115215957664e-05, |
| "loss": 0.26606035232543945, |
| "mean_token_accuracy": 0.9442368443310261, |
| "num_tokens": 27215468.0, |
| "step": 6350 |
| }, |
| { |
| "entropy": 0.2511021154373884, |
| "epoch": 1.930828996002112, |
| "grad_norm": 0.5591769814491272, |
| "learning_rate": 2.8998769771738833e-05, |
| "loss": 0.25475397109985354, |
| "mean_token_accuracy": 0.9452549339830876, |
| "num_tokens": 27431751.0, |
| "step": 6400 |
| }, |
| { |
| "epoch": 1.930828996002112, |
| "eval_entropy": 0.2883295046777303, |
| "eval_loss": 0.4905667006969452, |
| "eval_mean_token_accuracy": 0.9074331280050243, |
| "eval_num_tokens": 27431751.0, |
| "eval_runtime": 37.2686, |
| "eval_samples_per_second": 58.119, |
| "eval_steps_per_second": 7.272, |
| "step": 6400 |
| }, |
| { |
| "entropy": 0.24450184650719164, |
| "epoch": 1.9459153654673003, |
| "grad_norm": 0.4845283031463623, |
| "learning_rate": 2.8273825229579558e-05, |
| "loss": 0.2493889808654785, |
| "mean_token_accuracy": 0.9475250770151615, |
| "num_tokens": 27643957.0, |
| "step": 6450 |
| }, |
| { |
| "entropy": 0.25026212429627775, |
| "epoch": 1.9610017349324886, |
| "grad_norm": 0.4210788309574127, |
| "learning_rate": 2.7554468024009082e-05, |
| "loss": 0.25582372665405273, |
| "mean_token_accuracy": 0.9451599711179733, |
| "num_tokens": 27862796.0, |
| "step": 6500 |
| }, |
| { |
| "entropy": 0.2594556957855821, |
| "epoch": 1.9760881043976766, |
| "grad_norm": 0.42034855484962463, |
| "learning_rate": 2.6840883152657075e-05, |
| "loss": 0.2614474105834961, |
| "mean_token_accuracy": 0.9446786725521088, |
| "num_tokens": 28080081.0, |
| "step": 6550 |
| }, |
| { |
| "entropy": 0.2424509571492672, |
| "epoch": 1.991174473862865, |
| "grad_norm": 0.5637903213500977, |
| "learning_rate": 2.6133254128677766e-05, |
| "loss": 0.24372596740722657, |
| "mean_token_accuracy": 0.9479729002714157, |
| "num_tokens": 28291753.0, |
| "step": 6600 |
| }, |
| { |
| "epoch": 1.991174473862865, |
| "eval_entropy": 0.2895552223458941, |
| "eval_loss": 0.48857003450393677, |
| "eval_mean_token_accuracy": 0.9079141579430922, |
| "eval_num_tokens": 28291753.0, |
| "eval_runtime": 37.2416, |
| "eval_samples_per_second": 58.161, |
| "eval_steps_per_second": 7.277, |
| "step": 6600 |
| }, |
| { |
| "entropy": 0.24137189186315247, |
| "epoch": 2.0060345477860753, |
| "grad_norm": 0.4415420591831207, |
| "learning_rate": 2.5431762933555627e-05, |
| "loss": 0.23770923614501954, |
| "mean_token_accuracy": 0.9500614218602931, |
| "num_tokens": 28501531.0, |
| "step": 6650 |
| }, |
| { |
| "entropy": 0.20573811857029795, |
| "epoch": 2.0211209172512636, |
| "grad_norm": 0.5171937942504883, |
| "learning_rate": 2.473658997030514e-05, |
| "loss": 0.19352760314941406, |
| "mean_token_accuracy": 0.9575251358747482, |
| "num_tokens": 28718312.0, |
| "step": 6700 |
| }, |
| { |
| "entropy": 0.20038287844508887, |
| "epoch": 2.0362072867164516, |
| "grad_norm": 0.42165201902389526, |
| "learning_rate": 2.404791401707633e-05, |
| "loss": 0.18894313812255858, |
| "mean_token_accuracy": 0.9588627055287361, |
| "num_tokens": 28934285.0, |
| "step": 6750 |
| }, |
| { |
| "entropy": 0.19508995985612274, |
| "epoch": 2.05129365618164, |
| "grad_norm": 0.35577845573425293, |
| "learning_rate": 2.3365912181178313e-05, |
| "loss": 0.1867695426940918, |
| "mean_token_accuracy": 0.9598716080188752, |
| "num_tokens": 29145157.0, |
| "step": 6800 |
| }, |
| { |
| "epoch": 2.05129365618164, |
| "eval_entropy": 0.2568544143350362, |
| "eval_loss": 0.5305211544036865, |
| "eval_mean_token_accuracy": 0.9064581629534929, |
| "eval_num_tokens": 29145157.0, |
| "eval_runtime": 37.1895, |
| "eval_samples_per_second": 58.242, |
| "eval_steps_per_second": 7.287, |
| "step": 6800 |
| }, |
| { |
| "entropy": 0.2055508348532021, |
| "epoch": 2.066380025646828, |
| "grad_norm": 0.42946624755859375, |
| "learning_rate": 2.269075985353254e-05, |
| "loss": 0.1946415138244629, |
| "mean_token_accuracy": 0.9576617389917373, |
| "num_tokens": 29362502.0, |
| "step": 6850 |
| }, |
| { |
| "entropy": 0.19851462194696068, |
| "epoch": 2.0814663951120163, |
| "grad_norm": 0.4784873127937317, |
| "learning_rate": 2.20226306635672e-05, |
| "loss": 0.1882442855834961, |
| "mean_token_accuracy": 0.958879132270813, |
| "num_tokens": 29577964.0, |
| "step": 6900 |
| }, |
| { |
| "entropy": 0.20270802198909224, |
| "epoch": 2.0965527645772046, |
| "grad_norm": 0.5308135151863098, |
| "learning_rate": 2.1361696434564993e-05, |
| "loss": 0.1924464225769043, |
| "mean_token_accuracy": 0.9582864837348462, |
| "num_tokens": 29792051.0, |
| "step": 6950 |
| }, |
| { |
| "entropy": 0.19360160086303949, |
| "epoch": 2.1116391340423926, |
| "grad_norm": 0.3992004990577698, |
| "learning_rate": 2.070812713947513e-05, |
| "loss": 0.18389596939086914, |
| "mean_token_accuracy": 0.9606801150739193, |
| "num_tokens": 30010593.0, |
| "step": 7000 |
| }, |
| { |
| "epoch": 2.1116391340423926, |
| "eval_entropy": 0.2496587313794122, |
| "eval_loss": 0.5409784317016602, |
| "eval_mean_token_accuracy": 0.9062512767710809, |
| "eval_num_tokens": 30010593.0, |
| "eval_runtime": 37.2073, |
| "eval_samples_per_second": 58.214, |
| "eval_steps_per_second": 7.284, |
| "step": 7000 |
| }, |
| { |
| "entropy": 0.19243362288922072, |
| "epoch": 2.126725503507581, |
| "grad_norm": 0.485505610704422, |
| "learning_rate": 2.006209085720122e-05, |
| "loss": 0.18137836456298828, |
| "mean_token_accuracy": 0.9603879378736019, |
| "num_tokens": 30224235.0, |
| "step": 7050 |
| }, |
| { |
| "entropy": 0.1971529097482562, |
| "epoch": 2.1418118729727693, |
| "grad_norm": 0.3532182276248932, |
| "learning_rate": 1.9423753729376388e-05, |
| "loss": 0.1862693214416504, |
| "mean_token_accuracy": 0.959182897657156, |
| "num_tokens": 30438574.0, |
| "step": 7100 |
| }, |
| { |
| "entropy": 0.19837678778916598, |
| "epoch": 2.1568982424379572, |
| "grad_norm": 0.5558100342750549, |
| "learning_rate": 1.8793279917636448e-05, |
| "loss": 0.1895616340637207, |
| "mean_token_accuracy": 0.958885507285595, |
| "num_tokens": 30654293.0, |
| "step": 7150 |
| }, |
| { |
| "entropy": 0.19329896425828338, |
| "epoch": 2.1719846119031456, |
| "grad_norm": 0.4981042146682739, |
| "learning_rate": 1.817083156140237e-05, |
| "loss": 0.18090120315551758, |
| "mean_token_accuracy": 0.9607469955086708, |
| "num_tokens": 30865232.0, |
| "step": 7200 |
| }, |
| { |
| "epoch": 2.1719846119031456, |
| "eval_entropy": 0.2497983215534819, |
| "eval_loss": 0.5419089198112488, |
| "eval_mean_token_accuracy": 0.9055907944031747, |
| "eval_num_tokens": 30865232.0, |
| "eval_runtime": 37.1887, |
| "eval_samples_per_second": 58.243, |
| "eval_steps_per_second": 7.287, |
| "step": 7200 |
| }, |
| { |
| "entropy": 0.19074429869651793, |
| "epoch": 2.1870709813683336, |
| "grad_norm": 0.5064796209335327, |
| "learning_rate": 1.7556568736182667e-05, |
| "loss": 0.18279983520507812, |
| "mean_token_accuracy": 0.9610813467204571, |
| "num_tokens": 31074859.0, |
| "step": 7250 |
| }, |
| { |
| "entropy": 0.18915067540481686, |
| "epoch": 2.202157350833522, |
| "grad_norm": 0.462493360042572, |
| "learning_rate": 1.6950649412406777e-05, |
| "loss": 0.18141572952270507, |
| "mean_token_accuracy": 0.9607113988697529, |
| "num_tokens": 31285366.0, |
| "step": 7300 |
| }, |
| { |
| "entropy": 0.19164147678762675, |
| "epoch": 2.2172437202987103, |
| "grad_norm": 0.44526222348213196, |
| "learning_rate": 1.63532294147997e-05, |
| "loss": 0.1814894676208496, |
| "mean_token_accuracy": 0.9610688266158104, |
| "num_tokens": 31497431.0, |
| "step": 7350 |
| }, |
| { |
| "entropy": 0.19515870379284025, |
| "epoch": 2.2323300897638982, |
| "grad_norm": 0.5659943222999573, |
| "learning_rate": 1.5764462382308254e-05, |
| "loss": 0.18695903778076173, |
| "mean_token_accuracy": 0.9594297151267529, |
| "num_tokens": 31711142.0, |
| "step": 7400 |
| }, |
| { |
| "epoch": 2.2323300897638982, |
| "eval_entropy": 0.24821185405843812, |
| "eval_loss": 0.5459219217300415, |
| "eval_mean_token_accuracy": 0.9052295550649017, |
| "eval_num_tokens": 31711142.0, |
| "eval_runtime": 37.1776, |
| "eval_samples_per_second": 58.261, |
| "eval_steps_per_second": 7.289, |
| "step": 7400 |
| }, |
| { |
| "entropy": 0.19548690050840378, |
| "epoch": 2.2474164592290866, |
| "grad_norm": 0.498912513256073, |
| "learning_rate": 1.5184499728589846e-05, |
| "loss": 0.18344196319580078, |
| "mean_token_accuracy": 0.9600871665775776, |
| "num_tokens": 31923379.0, |
| "step": 7450 |
| }, |
| { |
| "entropy": 0.19262660641223192, |
| "epoch": 2.2625028286942745, |
| "grad_norm": 0.41678550839424133, |
| "learning_rate": 1.4613490603073194e-05, |
| "loss": 0.18303531646728516, |
| "mean_token_accuracy": 0.9605987747013569, |
| "num_tokens": 32135266.0, |
| "step": 7500 |
| }, |
| { |
| "entropy": 0.19937248670496047, |
| "epoch": 2.277589198159463, |
| "grad_norm": 0.6035925149917603, |
| "learning_rate": 1.4051581852601492e-05, |
| "loss": 0.18883104324340821, |
| "mean_token_accuracy": 0.9591751427948475, |
| "num_tokens": 32351854.0, |
| "step": 7550 |
| }, |
| { |
| "entropy": 0.19550999199971555, |
| "epoch": 2.2926755676246513, |
| "grad_norm": 0.4360465705394745, |
| "learning_rate": 1.3498917983667658e-05, |
| "loss": 0.18691642761230468, |
| "mean_token_accuracy": 0.9598778022825718, |
| "num_tokens": 32567025.0, |
| "step": 7600 |
| }, |
| { |
| "epoch": 2.2926755676246513, |
| "eval_entropy": 0.24827074039576238, |
| "eval_loss": 0.5438116192817688, |
| "eval_mean_token_accuracy": 0.9056458268658262, |
| "eval_num_tokens": 32567025.0, |
| "eval_runtime": 37.13, |
| "eval_samples_per_second": 58.336, |
| "eval_steps_per_second": 7.299, |
| "step": 7600 |
| }, |
| { |
| "entropy": 0.19866504015401007, |
| "epoch": 2.3077619370898392, |
| "grad_norm": 0.4768233299255371, |
| "learning_rate": 1.2955641125251555e-05, |
| "loss": 0.18666345596313477, |
| "mean_token_accuracy": 0.9592089447379112, |
| "num_tokens": 32781090.0, |
| "step": 7650 |
| }, |
| { |
| "entropy": 0.19146794026717542, |
| "epoch": 2.3228483065550276, |
| "grad_norm": 0.392702579498291, |
| "learning_rate": 1.2421890992268542e-05, |
| "loss": 0.18030118942260742, |
| "mean_token_accuracy": 0.9610011300444603, |
| "num_tokens": 32993619.0, |
| "step": 7700 |
| }, |
| { |
| "entropy": 0.19083258060738445, |
| "epoch": 2.3379346760202155, |
| "grad_norm": 0.5067113637924194, |
| "learning_rate": 1.189780484963885e-05, |
| "loss": 0.17912176132202148, |
| "mean_token_accuracy": 0.9609163939952851, |
| "num_tokens": 33207287.0, |
| "step": 7750 |
| }, |
| { |
| "entropy": 0.19270094383507966, |
| "epoch": 2.353021045485404, |
| "grad_norm": 0.3395691215991974, |
| "learning_rate": 1.138351747698711e-05, |
| "loss": 0.18421865463256837, |
| "mean_token_accuracy": 0.9601799823343754, |
| "num_tokens": 33423228.0, |
| "step": 7800 |
| }, |
| { |
| "epoch": 2.353021045485404, |
| "eval_entropy": 0.2481674429895253, |
| "eval_loss": 0.547441840171814, |
| "eval_mean_token_accuracy": 0.9053705822937603, |
| "eval_num_tokens": 33423228.0, |
| "eval_runtime": 37.2459, |
| "eval_samples_per_second": 58.154, |
| "eval_steps_per_second": 7.276, |
| "step": 7800 |
| }, |
| { |
| "entropy": 0.1889958502538502, |
| "epoch": 2.3681074149505923, |
| "grad_norm": 0.4847002327442169, |
| "learning_rate": 1.0879161133981014e-05, |
| "loss": 0.17589187622070312, |
| "mean_token_accuracy": 0.9615845668315888, |
| "num_tokens": 33638871.0, |
| "step": 7850 |
| }, |
| { |
| "entropy": 0.18853790896944703, |
| "epoch": 2.3831937844157802, |
| "grad_norm": 0.5678646564483643, |
| "learning_rate": 1.0384865526317861e-05, |
| "loss": 0.1777634620666504, |
| "mean_token_accuracy": 0.961886543482542, |
| "num_tokens": 33852577.0, |
| "step": 7900 |
| }, |
| { |
| "entropy": 0.19151988808065654, |
| "epoch": 2.3982801538809686, |
| "grad_norm": 0.4446047246456146, |
| "learning_rate": 9.900757772368175e-06, |
| "loss": 0.17955810546875, |
| "mean_token_accuracy": 0.9614880438148975, |
| "num_tokens": 34065599.0, |
| "step": 7950 |
| }, |
| { |
| "entropy": 0.19300217579118908, |
| "epoch": 2.4133665233461565, |
| "grad_norm": 0.5685653686523438, |
| "learning_rate": 9.426962370484533e-06, |
| "loss": 0.18160755157470704, |
| "mean_token_accuracy": 0.9607279069721699, |
| "num_tokens": 34280453.0, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.4133665233461565, |
| "eval_entropy": 0.24335849892719205, |
| "eval_loss": 0.5554639101028442, |
| "eval_mean_token_accuracy": 0.905630389702716, |
| "eval_num_tokens": 34280453.0, |
| "eval_runtime": 37.2491, |
| "eval_samples_per_second": 58.149, |
| "eval_steps_per_second": 7.275, |
| "step": 8000 |
| }, |
| { |
| "entropy": 0.18967346624471249, |
| "epoch": 2.428452892811345, |
| "grad_norm": 0.5121133923530579, |
| "learning_rate": 8.963601166984225e-06, |
| "loss": 0.1821819305419922, |
| "mean_token_accuracy": 0.9610455152392388, |
| "num_tokens": 34494654.0, |
| "step": 8050 |
| }, |
| { |
| "entropy": 0.18874711729586124, |
| "epoch": 2.4435392622765333, |
| "grad_norm": 0.6657042503356934, |
| "learning_rate": 8.510793324813937e-06, |
| "loss": 0.17630435943603515, |
| "mean_token_accuracy": 0.9615484464168549, |
| "num_tokens": 34704277.0, |
| "step": 8100 |
| }, |
| { |
| "entropy": 0.19604809990152716, |
| "epoch": 2.458625631741721, |
| "grad_norm": 0.6367285847663879, |
| "learning_rate": 8.068655292904559e-06, |
| "loss": 0.1849921989440918, |
| "mean_token_accuracy": 0.9597983421385288, |
| "num_tokens": 34918987.0, |
| "step": 8150 |
| }, |
| { |
| "entropy": 0.19020996399223805, |
| "epoch": 2.4737120012069096, |
| "grad_norm": 0.40266647934913635, |
| "learning_rate": 7.63730077622392e-06, |
| "loss": 0.18030958175659179, |
| "mean_token_accuracy": 0.9618312911689282, |
| "num_tokens": 35128250.0, |
| "step": 8200 |
| }, |
| { |
| "epoch": 2.4737120012069096, |
| "eval_entropy": 0.24456536362971767, |
| "eval_loss": 0.5537819266319275, |
| "eval_mean_token_accuracy": 0.905363669254683, |
| "eval_num_tokens": 35128250.0, |
| "eval_runtime": 37.3206, |
| "eval_samples_per_second": 58.038, |
| "eval_steps_per_second": 7.261, |
| "step": 8200 |
| }, |
| { |
| "entropy": 0.1947929921839386, |
| "epoch": 2.4887983706720975, |
| "grad_norm": 0.5730997323989868, |
| "learning_rate": 7.216840706535133e-06, |
| "loss": 0.1838933753967285, |
| "mean_token_accuracy": 0.9602823905646801, |
| "num_tokens": 35344354.0, |
| "step": 8250 |
| }, |
| { |
| "entropy": 0.1937092263624072, |
| "epoch": 2.503884740137286, |
| "grad_norm": 0.48286330699920654, |
| "learning_rate": 6.807383213868318e-06, |
| "loss": 0.1827998924255371, |
| "mean_token_accuracy": 0.9602498579025268, |
| "num_tokens": 35559731.0, |
| "step": 8300 |
| }, |
| { |
| "entropy": 0.18829923996701836, |
| "epoch": 2.5189711096024743, |
| "grad_norm": 0.5280757546424866, |
| "learning_rate": 6.4090335987126e-06, |
| "loss": 0.17718358993530273, |
| "mean_token_accuracy": 0.9615453231334686, |
| "num_tokens": 35772707.0, |
| "step": 8350 |
| }, |
| { |
| "entropy": 0.19396818530745805, |
| "epoch": 2.534057479067662, |
| "grad_norm": 0.4934554100036621, |
| "learning_rate": 6.021894304935943e-06, |
| "loss": 0.18351167678833008, |
| "mean_token_accuracy": 0.9603780242800712, |
| "num_tokens": 35987178.0, |
| "step": 8400 |
| }, |
| { |
| "epoch": 2.534057479067662, |
| "eval_entropy": 0.2449101031761328, |
| "eval_loss": 0.5524511337280273, |
| "eval_mean_token_accuracy": 0.9050956489415186, |
| "eval_num_tokens": 35987178.0, |
| "eval_runtime": 37.2719, |
| "eval_samples_per_second": 58.113, |
| "eval_steps_per_second": 7.271, |
| "step": 8400 |
| }, |
| { |
| "entropy": 0.18812250457704066, |
| "epoch": 2.5491438485328506, |
| "grad_norm": 0.5735852718353271, |
| "learning_rate": 5.646064893439623e-06, |
| "loss": 0.17783910751342774, |
| "mean_token_accuracy": 0.9615232966840267, |
| "num_tokens": 36200263.0, |
| "step": 8450 |
| }, |
| { |
| "entropy": 0.18926897779107094, |
| "epoch": 2.5642302179980385, |
| "grad_norm": 0.5568459033966064, |
| "learning_rate": 5.281642016554017e-06, |
| "loss": 0.1792352867126465, |
| "mean_token_accuracy": 0.9616803368926048, |
| "num_tokens": 36411968.0, |
| "step": 8500 |
| }, |
| { |
| "entropy": 0.19124026644974948, |
| "epoch": 2.579316587463227, |
| "grad_norm": 0.5221688151359558, |
| "learning_rate": 4.928719393182507e-06, |
| "loss": 0.17745084762573243, |
| "mean_token_accuracy": 0.9616039192676544, |
| "num_tokens": 36626784.0, |
| "step": 8550 |
| }, |
| { |
| "entropy": 0.19215355191379785, |
| "epoch": 2.5944029569284153, |
| "grad_norm": 0.36854663491249084, |
| "learning_rate": 4.5873877846996594e-06, |
| "loss": 0.18093048095703124, |
| "mean_token_accuracy": 0.9610362699627877, |
| "num_tokens": 36839614.0, |
| "step": 8600 |
| }, |
| { |
| "epoch": 2.5944029569284153, |
| "eval_entropy": 0.24483193833779585, |
| "eval_loss": 0.5536935925483704, |
| "eval_mean_token_accuracy": 0.9050766867465199, |
| "eval_num_tokens": 36839614.0, |
| "eval_runtime": 37.2832, |
| "eval_samples_per_second": 58.096, |
| "eval_steps_per_second": 7.269, |
| "step": 8600 |
| }, |
| { |
| "entropy": 0.19345266066491604, |
| "epoch": 2.6094893263936036, |
| "grad_norm": 0.36760082840919495, |
| "learning_rate": 4.257734971610106e-06, |
| "loss": 0.18040838241577148, |
| "mean_token_accuracy": 0.9611816507577896, |
| "num_tokens": 37053142.0, |
| "step": 8650 |
| }, |
| { |
| "entropy": 0.188013746580109, |
| "epoch": 2.6245756958587916, |
| "grad_norm": 0.5213715434074402, |
| "learning_rate": 3.93984573097394e-06, |
| "loss": 0.17426759719848633, |
| "mean_token_accuracy": 0.962059508562088, |
| "num_tokens": 37267777.0, |
| "step": 8700 |
| }, |
| { |
| "entropy": 0.1918721451703459, |
| "epoch": 2.6396620653239795, |
| "grad_norm": 0.5748514533042908, |
| "learning_rate": 3.633801814604554e-06, |
| "loss": 0.1796425437927246, |
| "mean_token_accuracy": 0.9613311864435673, |
| "num_tokens": 37485508.0, |
| "step": 8750 |
| }, |
| { |
| "entropy": 0.18769024461507797, |
| "epoch": 2.654748434789168, |
| "grad_norm": 0.37133195996284485, |
| "learning_rate": 3.339681928044436e-06, |
| "loss": 0.17722646713256837, |
| "mean_token_accuracy": 0.9621489056944847, |
| "num_tokens": 37694053.0, |
| "step": 8800 |
| }, |
| { |
| "epoch": 2.654748434789168, |
| "eval_entropy": 0.24254771412738574, |
| "eval_loss": 0.558121383190155, |
| "eval_mean_token_accuracy": 0.905118876497684, |
| "eval_num_tokens": 37694053.0, |
| "eval_runtime": 37.2089, |
| "eval_samples_per_second": 58.212, |
| "eval_steps_per_second": 7.283, |
| "step": 8800 |
| }, |
| { |
| "entropy": 0.18984992211684584, |
| "epoch": 2.6698348042543563, |
| "grad_norm": 0.43609800934791565, |
| "learning_rate": 3.057561710324447e-06, |
| "loss": 0.17845310211181642, |
| "mean_token_accuracy": 0.9613586132228374, |
| "num_tokens": 37906133.0, |
| "step": 8850 |
| }, |
| { |
| "entropy": 0.1950311391800642, |
| "epoch": 2.6849211737195446, |
| "grad_norm": 0.45412150025367737, |
| "learning_rate": 2.787513714511636e-06, |
| "loss": 0.18089279174804687, |
| "mean_token_accuracy": 0.9608308251202107, |
| "num_tokens": 38121697.0, |
| "step": 8900 |
| }, |
| { |
| "entropy": 0.18615621831268073, |
| "epoch": 2.7000075431847326, |
| "grad_norm": 0.6591213345527649, |
| "learning_rate": 2.52960738905072e-06, |
| "loss": 0.17349456787109374, |
| "mean_token_accuracy": 0.9623284694552422, |
| "num_tokens": 38339277.0, |
| "step": 8950 |
| }, |
| { |
| "entropy": 0.18828014567494392, |
| "epoch": 2.715093912649921, |
| "grad_norm": 0.47049465775489807, |
| "learning_rate": 2.2839090599040046e-06, |
| "loss": 0.17837800979614257, |
| "mean_token_accuracy": 0.9619372922182083, |
| "num_tokens": 38551183.0, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.715093912649921, |
| "eval_entropy": 0.24229726709452942, |
| "eval_loss": 0.5592358708381653, |
| "eval_mean_token_accuracy": 0.905019719882205, |
| "eval_num_tokens": 38551183.0, |
| "eval_runtime": 37.1765, |
| "eval_samples_per_second": 58.263, |
| "eval_steps_per_second": 7.29, |
| "step": 9000 |
| }, |
| { |
| "entropy": 0.18336616074666381, |
| "epoch": 2.730180282115109, |
| "grad_norm": 0.3691662549972534, |
| "learning_rate": 2.0504819134942734e-06, |
| "loss": 0.17197175979614257, |
| "mean_token_accuracy": 0.9629626546800136, |
| "num_tokens": 38763413.0, |
| "step": 9050 |
| }, |
| { |
| "entropy": 0.18445612547919155, |
| "epoch": 2.7452666515802973, |
| "grad_norm": 0.5340840816497803, |
| "learning_rate": 1.8293859804550506e-06, |
| "loss": 0.17212907791137697, |
| "mean_token_accuracy": 0.9631160937249661, |
| "num_tokens": 38979256.0, |
| "step": 9100 |
| }, |
| { |
| "entropy": 0.18713438665494322, |
| "epoch": 2.7603530210454856, |
| "grad_norm": 0.5069661736488342, |
| "learning_rate": 1.620678120192537e-06, |
| "loss": 0.1732018280029297, |
| "mean_token_accuracy": 0.9624787227809429, |
| "num_tokens": 39194699.0, |
| "step": 9150 |
| }, |
| { |
| "entropy": 0.19093556420877575, |
| "epoch": 2.7754393905106736, |
| "grad_norm": 0.3724497854709625, |
| "learning_rate": 1.424412006263004e-06, |
| "loss": 0.17719757080078125, |
| "mean_token_accuracy": 0.9616392150521278, |
| "num_tokens": 39405056.0, |
| "step": 9200 |
| }, |
| { |
| "epoch": 2.7754393905106736, |
| "eval_entropy": 0.2416494778216545, |
| "eval_loss": 0.5602814555168152, |
| "eval_mean_token_accuracy": 0.9050707438775094, |
| "eval_num_tokens": 39405056.0, |
| "eval_runtime": 37.0527, |
| "eval_samples_per_second": 58.457, |
| "eval_steps_per_second": 7.314, |
| "step": 9200 |
| }, |
| { |
| "entropy": 0.18624798154458402, |
| "epoch": 2.790525759975862, |
| "grad_norm": 0.5416818857192993, |
| "learning_rate": 1.24063811256952e-06, |
| "loss": 0.17536975860595702, |
| "mean_token_accuracy": 0.9625106258690357, |
| "num_tokens": 39620602.0, |
| "step": 9250 |
| }, |
| { |
| "entropy": 0.18864918448030948, |
| "epoch": 2.80561212944105, |
| "grad_norm": 0.7557387351989746, |
| "learning_rate": 1.0694037003815493e-06, |
| "loss": 0.1763162422180176, |
| "mean_token_accuracy": 0.9617964868247509, |
| "num_tokens": 39838171.0, |
| "step": 9300 |
| }, |
| { |
| "entropy": 0.19156487157568336, |
| "epoch": 2.8206984989062382, |
| "grad_norm": 0.5030518174171448, |
| "learning_rate": 9.107528061807425e-07, |
| "loss": 0.17927934646606444, |
| "mean_token_accuracy": 0.9610569317638874, |
| "num_tokens": 40055765.0, |
| "step": 9350 |
| }, |
| { |
| "entropy": 0.19062289187684656, |
| "epoch": 2.8357848683714266, |
| "grad_norm": 0.3872191905975342, |
| "learning_rate": 7.64726230336027e-07, |
| "loss": 0.1788728141784668, |
| "mean_token_accuracy": 0.9610781705379486, |
| "num_tokens": 40273169.0, |
| "step": 9400 |
| }, |
| { |
| "epoch": 2.8357848683714266, |
| "eval_entropy": 0.2424020753190526, |
| "eval_loss": 0.5598563551902771, |
| "eval_mean_token_accuracy": 0.905123386435843, |
| "eval_num_tokens": 40273169.0, |
| "eval_runtime": 37.2998, |
| "eval_samples_per_second": 58.07, |
| "eval_steps_per_second": 7.265, |
| "step": 9400 |
| }, |
| { |
| "entropy": 0.19168663132935762, |
| "epoch": 2.8508712378366146, |
| "grad_norm": 0.38919326663017273, |
| "learning_rate": 6.313615266109463e-07, |
| "loss": 0.17518898010253905, |
| "mean_token_accuracy": 0.9616159409284591, |
| "num_tokens": 40493623.0, |
| "step": 9450 |
| }, |
| { |
| "entropy": 0.1842949813697487, |
| "epoch": 2.865957607301803, |
| "grad_norm": 0.4381106197834015, |
| "learning_rate": 5.106929925059456e-07, |
| "loss": 0.17125751495361327, |
| "mean_token_accuracy": 0.9631977449357509, |
| "num_tokens": 40706058.0, |
| "step": 9500 |
| }, |
| { |
| "entropy": 0.18345711720176042, |
| "epoch": 2.881043976766991, |
| "grad_norm": 0.625280499458313, |
| "learning_rate": 4.027516604380388e-07, |
| "loss": 0.17233373641967772, |
| "mean_token_accuracy": 0.9627382136881352, |
| "num_tokens": 40919257.0, |
| "step": 9550 |
| }, |
| { |
| "entropy": 0.19293911349028348, |
| "epoch": 2.8961303462321792, |
| "grad_norm": 0.5119889974594116, |
| "learning_rate": 3.075652897602033e-07, |
| "loss": 0.18010311126708983, |
| "mean_token_accuracy": 0.960850502550602, |
| "num_tokens": 41135038.0, |
| "step": 9600 |
| }, |
| { |
| "epoch": 2.8961303462321792, |
| "eval_entropy": 0.242256640535659, |
| "eval_loss": 0.5602179169654846, |
| "eval_mean_token_accuracy": 0.9051620641317755, |
| "eval_num_tokens": 41135038.0, |
| "eval_runtime": 37.3372, |
| "eval_samples_per_second": 58.012, |
| "eval_steps_per_second": 7.258, |
| "step": 9600 |
| }, |
| { |
| "entropy": 0.1843437609449029, |
| "epoch": 2.9112167156973676, |
| "grad_norm": 0.5234854221343994, |
| "learning_rate": 2.2515835962245157e-07, |
| "loss": 0.16681966781616211, |
| "mean_token_accuracy": 0.9633826872706414, |
| "num_tokens": 41350531.0, |
| "step": 9650 |
| }, |
| { |
| "entropy": 0.18940109137445688, |
| "epoch": 2.9263030851625556, |
| "grad_norm": 0.5936132073402405, |
| "learning_rate": 1.5555206267655055e-07, |
| "loss": 0.17372846603393555, |
| "mean_token_accuracy": 0.9623673681914806, |
| "num_tokens": 41568124.0, |
| "step": 9700 |
| }, |
| { |
| "entropy": 0.18825361583381892, |
| "epoch": 2.941389454627744, |
| "grad_norm": 0.43561285734176636, |
| "learning_rate": 9.876429962585309e-08, |
| "loss": 0.17482643127441405, |
| "mean_token_accuracy": 0.962187256962061, |
| "num_tokens": 41784922.0, |
| "step": 9750 |
| }, |
| { |
| "entropy": 0.19123295756056904, |
| "epoch": 2.956475824092932, |
| "grad_norm": 0.45098307728767395, |
| "learning_rate": 5.4809674621797425e-08, |
| "loss": 0.1720089340209961, |
| "mean_token_accuracy": 0.9617229135334492, |
| "num_tokens": 42005066.0, |
| "step": 9800 |
| }, |
| { |
| "epoch": 2.956475824092932, |
| "eval_entropy": 0.2421166613917949, |
| "eval_loss": 0.5603178143501282, |
| "eval_mean_token_accuracy": 0.9051976802164338, |
| "eval_num_tokens": 42005066.0, |
| "eval_runtime": 37.2727, |
| "eval_samples_per_second": 58.112, |
| "eval_steps_per_second": 7.271, |
| "step": 9800 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 9945, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.278959418863923e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
