| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.44145873320537427, |
| "eval_steps": 500, |
| "global_step": 460, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0047984644913627635, |
| "grad_norm": 32.591251373291016, |
| "learning_rate": 8.401166180758017e-06, |
| "loss": 1.152, |
| "mean_token_accuracy": 0.730931556224823, |
| "num_tokens": 799294.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.009596928982725527, |
| "grad_norm": 3.1753504276275635, |
| "learning_rate": 1.8902623906705538e-05, |
| "loss": 0.5765, |
| "mean_token_accuracy": 0.8255371809005737, |
| "num_tokens": 1589820.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.014395393474088292, |
| "grad_norm": 2.811250686645508, |
| "learning_rate": 2.9404081632653062e-05, |
| "loss": 0.4173, |
| "mean_token_accuracy": 0.8512514710426331, |
| "num_tokens": 2378183.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.019193857965451054, |
| "grad_norm": 2.1911630630493164, |
| "learning_rate": 3.990553935860058e-05, |
| "loss": 0.3916, |
| "mean_token_accuracy": 0.8533002972602844, |
| "num_tokens": 3183115.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02399232245681382, |
| "grad_norm": 3.374872922897339, |
| "learning_rate": 5.0406997084548104e-05, |
| "loss": 0.3496, |
| "mean_token_accuracy": 0.8802085399627686, |
| "num_tokens": 3991639.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.028790786948176585, |
| "grad_norm": 2.2735555171966553, |
| "learning_rate": 6.090845481049563e-05, |
| "loss": 0.3253, |
| "mean_token_accuracy": 0.8847130298614502, |
| "num_tokens": 4786386.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03358925143953935, |
| "grad_norm": 1.5320895910263062, |
| "learning_rate": 7.140991253644314e-05, |
| "loss": 0.2999, |
| "mean_token_accuracy": 0.8903302311897278, |
| "num_tokens": 5575841.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.03838771593090211, |
| "grad_norm": 2.4821479320526123, |
| "learning_rate": 7.350805771429152e-05, |
| "loss": 0.3198, |
| "mean_token_accuracy": 0.8918884038925171, |
| "num_tokens": 6351291.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.04318618042226487, |
| "grad_norm": 1.3984349966049194, |
| "learning_rate": 7.349933866980902e-05, |
| "loss": 0.2805, |
| "mean_token_accuracy": 0.8992334485054017, |
| "num_tokens": 7127815.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.04798464491362764, |
| "grad_norm": 0.9826128482818604, |
| "learning_rate": 7.348391492008383e-05, |
| "loss": 0.2894, |
| "mean_token_accuracy": 0.8915998458862304, |
| "num_tokens": 7928844.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.052783109404990404, |
| "grad_norm": 1.3426622152328491, |
| "learning_rate": 7.34617902179726e-05, |
| "loss": 0.2652, |
| "mean_token_accuracy": 0.9018174767494201, |
| "num_tokens": 8725094.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.05758157389635317, |
| "grad_norm": 0.9711771607398987, |
| "learning_rate": 7.343296994678593e-05, |
| "loss": 0.2739, |
| "mean_token_accuracy": 0.8992493629455567, |
| "num_tokens": 9521312.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06238003838771593, |
| "grad_norm": 0.986544132232666, |
| "learning_rate": 7.339746111897856e-05, |
| "loss": 0.2652, |
| "mean_token_accuracy": 0.8993094563484192, |
| "num_tokens": 10328920.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.0671785028790787, |
| "grad_norm": 1.0141630172729492, |
| "learning_rate": 7.335527237444306e-05, |
| "loss": 0.2582, |
| "mean_token_accuracy": 0.9018368721008301, |
| "num_tokens": 11129367.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.07197696737044146, |
| "grad_norm": 1.9091362953186035, |
| "learning_rate": 7.330641397840763e-05, |
| "loss": 0.2532, |
| "mean_token_accuracy": 0.9050414323806762, |
| "num_tokens": 11925943.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.07677543186180422, |
| "grad_norm": 0.6851639747619629, |
| "learning_rate": 7.32508978189384e-05, |
| "loss": 0.2463, |
| "mean_token_accuracy": 0.9032415986061096, |
| "num_tokens": 12715832.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.08157389635316699, |
| "grad_norm": 0.9245691299438477, |
| "learning_rate": 7.318873740404686e-05, |
| "loss": 0.2409, |
| "mean_token_accuracy": 0.9095496535301208, |
| "num_tokens": 13512930.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.08637236084452975, |
| "grad_norm": 1.114152431488037, |
| "learning_rate": 7.311994785840315e-05, |
| "loss": 0.236, |
| "mean_token_accuracy": 0.9103517293930053, |
| "num_tokens": 14310763.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.09117082533589252, |
| "grad_norm": 0.6443946361541748, |
| "learning_rate": 7.304454591965593e-05, |
| "loss": 0.2337, |
| "mean_token_accuracy": 0.9106445193290711, |
| "num_tokens": 15077828.0, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.09596928982725528, |
| "grad_norm": 0.8331279158592224, |
| "learning_rate": 7.296254993435989e-05, |
| "loss": 0.2407, |
| "mean_token_accuracy": 0.9029403924942017, |
| "num_tokens": 15876828.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.10076775431861804, |
| "grad_norm": 1.4841084480285645, |
| "learning_rate": 7.287397985351168e-05, |
| "loss": 0.245, |
| "mean_token_accuracy": 0.9005821108818054, |
| "num_tokens": 16684191.0, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.10556621880998081, |
| "grad_norm": 0.5702885985374451, |
| "learning_rate": 7.27788572276955e-05, |
| "loss": 0.2268, |
| "mean_token_accuracy": 0.905585777759552, |
| "num_tokens": 17499344.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.11036468330134357, |
| "grad_norm": 0.6955417990684509, |
| "learning_rate": 7.267720520183951e-05, |
| "loss": 0.228, |
| "mean_token_accuracy": 0.9089990615844726, |
| "num_tokens": 18311988.0, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.11516314779270634, |
| "grad_norm": 0.8562710881233215, |
| "learning_rate": 7.256904850958429e-05, |
| "loss": 0.2313, |
| "mean_token_accuracy": 0.9063257932662964, |
| "num_tokens": 19117619.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.1199616122840691, |
| "grad_norm": 0.5443550944328308, |
| "learning_rate": 7.245441346726467e-05, |
| "loss": 0.2237, |
| "mean_token_accuracy": 0.9092974305152893, |
| "num_tokens": 19905936.0, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.12476007677543186, |
| "grad_norm": 0.6315863728523254, |
| "learning_rate": 7.233332796750656e-05, |
| "loss": 0.2152, |
| "mean_token_accuracy": 0.9135099887847901, |
| "num_tokens": 20687613.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.1295585412667946, |
| "grad_norm": 0.9352563619613647, |
| "learning_rate": 7.220582147244025e-05, |
| "loss": 0.217, |
| "mean_token_accuracy": 0.9076200485229492, |
| "num_tokens": 21492115.0, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.1343570057581574, |
| "grad_norm": 0.8867104649543762, |
| "learning_rate": 7.207192500653172e-05, |
| "loss": 0.2312, |
| "mean_token_accuracy": 0.9056767225265503, |
| "num_tokens": 22272734.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.13915547024952016, |
| "grad_norm": 0.6146453022956848, |
| "learning_rate": 7.193167114903386e-05, |
| "loss": 0.2261, |
| "mean_token_accuracy": 0.905716347694397, |
| "num_tokens": 23051480.0, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.14395393474088292, |
| "grad_norm": 1.0299674272537231, |
| "learning_rate": 7.178509402605946e-05, |
| "loss": 0.2346, |
| "mean_token_accuracy": 0.9057998061180115, |
| "num_tokens": 23843143.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.14875239923224567, |
| "grad_norm": 0.810525119304657, |
| "learning_rate": 7.16322293022777e-05, |
| "loss": 0.2307, |
| "mean_token_accuracy": 0.9111165881156922, |
| "num_tokens": 24637524.0, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.15355086372360843, |
| "grad_norm": 0.4699096977710724, |
| "learning_rate": 7.147311417223636e-05, |
| "loss": 0.2297, |
| "mean_token_accuracy": 0.9072130799293519, |
| "num_tokens": 25434785.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.15834932821497122, |
| "grad_norm": 0.8143472671508789, |
| "learning_rate": 7.130778735131171e-05, |
| "loss": 0.2186, |
| "mean_token_accuracy": 0.9113067984580994, |
| "num_tokens": 26236980.0, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.16314779270633398, |
| "grad_norm": 0.5336032509803772, |
| "learning_rate": 7.113628906628854e-05, |
| "loss": 0.2186, |
| "mean_token_accuracy": 0.9100312232971192, |
| "num_tokens": 27022193.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.16794625719769674, |
| "grad_norm": 0.5377821922302246, |
| "learning_rate": 7.095866104557217e-05, |
| "loss": 0.2136, |
| "mean_token_accuracy": 0.9070743322372437, |
| "num_tokens": 27814657.0, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.1727447216890595, |
| "grad_norm": 0.4592677354812622, |
| "learning_rate": 7.077494650903529e-05, |
| "loss": 0.2115, |
| "mean_token_accuracy": 0.909694254398346, |
| "num_tokens": 28609492.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.17754318618042225, |
| "grad_norm": 0.9938281178474426, |
| "learning_rate": 7.058519015750186e-05, |
| "loss": 0.2187, |
| "mean_token_accuracy": 0.9073381423950195, |
| "num_tokens": 29402462.0, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.18234165067178504, |
| "grad_norm": 0.5051109194755554, |
| "learning_rate": 7.038943816187062e-05, |
| "loss": 0.2174, |
| "mean_token_accuracy": 0.9115898251533509, |
| "num_tokens": 30207426.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.1871401151631478, |
| "grad_norm": 0.6154143214225769, |
| "learning_rate": 7.018773815188091e-05, |
| "loss": 0.2008, |
| "mean_token_accuracy": 0.9124987602233887, |
| "num_tokens": 30985559.0, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.19193857965451055, |
| "grad_norm": 0.6422397494316101, |
| "learning_rate": 6.998013920452367e-05, |
| "loss": 0.2071, |
| "mean_token_accuracy": 0.9167937636375427, |
| "num_tokens": 31763312.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1967370441458733, |
| "grad_norm": 0.5240011215209961, |
| "learning_rate": 6.976669183210004e-05, |
| "loss": 0.2196, |
| "mean_token_accuracy": 0.9105538129806519, |
| "num_tokens": 32546702.0, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.20153550863723607, |
| "grad_norm": 0.48978161811828613, |
| "learning_rate": 6.954744796993096e-05, |
| "loss": 0.2165, |
| "mean_token_accuracy": 0.9121721982955933, |
| "num_tokens": 33362696.0, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.20633397312859886, |
| "grad_norm": 0.6336808204650879, |
| "learning_rate": 6.932246096372041e-05, |
| "loss": 0.2257, |
| "mean_token_accuracy": 0.9081306457519531, |
| "num_tokens": 34162694.0, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.21113243761996162, |
| "grad_norm": 0.47279420495033264, |
| "learning_rate": 6.909178555657557e-05, |
| "loss": 0.2116, |
| "mean_token_accuracy": 0.9091696262359619, |
| "num_tokens": 34949786.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.21593090211132437, |
| "grad_norm": 0.5637255907058716, |
| "learning_rate": 6.885547787568674e-05, |
| "loss": 0.209, |
| "mean_token_accuracy": 0.9129250407218933, |
| "num_tokens": 35750169.0, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.22072936660268713, |
| "grad_norm": 1.205546498298645, |
| "learning_rate": 6.861359541867084e-05, |
| "loss": 0.2012, |
| "mean_token_accuracy": 0.9175987482070923, |
| "num_tokens": 36542344.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.2255278310940499, |
| "grad_norm": 0.8636100888252258, |
| "learning_rate": 6.836619703958119e-05, |
| "loss": 0.2041, |
| "mean_token_accuracy": 0.9169086694717408, |
| "num_tokens": 37351148.0, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.23032629558541268, |
| "grad_norm": 0.6066936254501343, |
| "learning_rate": 6.811334293458733e-05, |
| "loss": 0.1971, |
| "mean_token_accuracy": 0.9161781072616577, |
| "num_tokens": 38114955.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.23512476007677544, |
| "grad_norm": 0.5045466423034668, |
| "learning_rate": 6.78550946273283e-05, |
| "loss": 0.1991, |
| "mean_token_accuracy": 0.9162214040756226, |
| "num_tokens": 38908489.0, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.2399232245681382, |
| "grad_norm": 0.4524458646774292, |
| "learning_rate": 6.759151495394289e-05, |
| "loss": 0.2079, |
| "mean_token_accuracy": 0.9115633845329285, |
| "num_tokens": 39711511.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.24472168905950095, |
| "grad_norm": 0.3954505920410156, |
| "learning_rate": 6.732266804778059e-05, |
| "loss": 0.2071, |
| "mean_token_accuracy": 0.9117343664169312, |
| "num_tokens": 40499386.0, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.2495201535508637, |
| "grad_norm": 0.8436290621757507, |
| "learning_rate": 6.704861932379685e-05, |
| "loss": 0.2021, |
| "mean_token_accuracy": 0.9147255301475525, |
| "num_tokens": 41305685.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.2543186180422265, |
| "grad_norm": 0.47678083181381226, |
| "learning_rate": 6.676943546263647e-05, |
| "loss": 0.2084, |
| "mean_token_accuracy": 0.9162402510643005, |
| "num_tokens": 42099299.0, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.2591170825335892, |
| "grad_norm": 0.6068950295448303, |
| "learning_rate": 6.648518439440924e-05, |
| "loss": 0.2101, |
| "mean_token_accuracy": 0.9077034235000611, |
| "num_tokens": 42916607.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.263915547024952, |
| "grad_norm": 0.49654993414878845, |
| "learning_rate": 6.619593528216123e-05, |
| "loss": 0.2048, |
| "mean_token_accuracy": 0.9157393455505372, |
| "num_tokens": 43714272.0, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.2687140115163148, |
| "grad_norm": 0.7558993697166443, |
| "learning_rate": 6.590175850504635e-05, |
| "loss": 0.2071, |
| "mean_token_accuracy": 0.9156303167343139, |
| "num_tokens": 44506596.0, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.27351247600767753, |
| "grad_norm": 0.4323616623878479, |
| "learning_rate": 6.560272564120192e-05, |
| "loss": 0.1981, |
| "mean_token_accuracy": 0.9156986951828003, |
| "num_tokens": 45282564.0, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.2783109404990403, |
| "grad_norm": 0.3599900007247925, |
| "learning_rate": 6.52989094503325e-05, |
| "loss": 0.2077, |
| "mean_token_accuracy": 0.9143546223640442, |
| "num_tokens": 46098513.0, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.28310940499040305, |
| "grad_norm": 0.33340930938720703, |
| "learning_rate": 6.499038385600624e-05, |
| "loss": 0.1938, |
| "mean_token_accuracy": 0.9212781906127929, |
| "num_tokens": 46887829.0, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.28790786948176583, |
| "grad_norm": 0.306796133518219, |
| "learning_rate": 6.467722392766801e-05, |
| "loss": 0.1959, |
| "mean_token_accuracy": 0.9193766951560974, |
| "num_tokens": 47691699.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.2927063339731286, |
| "grad_norm": 0.3488706648349762, |
| "learning_rate": 6.435950586237382e-05, |
| "loss": 0.2066, |
| "mean_token_accuracy": 0.9102665543556213, |
| "num_tokens": 48486193.0, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.29750479846449135, |
| "grad_norm": 0.5964604020118713, |
| "learning_rate": 6.403730696625067e-05, |
| "loss": 0.1893, |
| "mean_token_accuracy": 0.9162996411323547, |
| "num_tokens": 49288543.0, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.30230326295585414, |
| "grad_norm": 0.3607555627822876, |
| "learning_rate": 6.371070563568684e-05, |
| "loss": 0.1923, |
| "mean_token_accuracy": 0.9159826397895813, |
| "num_tokens": 50087277.0, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.30710172744721687, |
| "grad_norm": 0.5310798287391663, |
| "learning_rate": 6.337978133825659e-05, |
| "loss": 0.1871, |
| "mean_token_accuracy": 0.9196419477462768, |
| "num_tokens": 50868001.0, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.31190019193857965, |
| "grad_norm": 0.5248069167137146, |
| "learning_rate": 6.304461459338445e-05, |
| "loss": 0.2029, |
| "mean_token_accuracy": 0.9152723550796509, |
| "num_tokens": 51662419.0, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.31669865642994244, |
| "grad_norm": 0.3722710907459259, |
| "learning_rate": 6.270528695275349e-05, |
| "loss": 0.201, |
| "mean_token_accuracy": 0.91062912940979, |
| "num_tokens": 52446100.0, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.32149712092130517, |
| "grad_norm": 0.36808404326438904, |
| "learning_rate": 6.236188098046236e-05, |
| "loss": 0.2001, |
| "mean_token_accuracy": 0.9152203679084778, |
| "num_tokens": 53244169.0, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.32629558541266795, |
| "grad_norm": 0.25250986218452454, |
| "learning_rate": 6.201448023293617e-05, |
| "loss": 0.2013, |
| "mean_token_accuracy": 0.911141550540924, |
| "num_tokens": 54040490.0, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.3310940499040307, |
| "grad_norm": 0.31841546297073364, |
| "learning_rate": 6.166316923859576e-05, |
| "loss": 0.2054, |
| "mean_token_accuracy": 0.9115605592727661, |
| "num_tokens": 54866178.0, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.33589251439539347, |
| "grad_norm": 26.990447998046875, |
| "learning_rate": 6.130803347729047e-05, |
| "loss": 0.1908, |
| "mean_token_accuracy": 0.9202599406242371, |
| "num_tokens": 55653730.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.34069097888675626, |
| "grad_norm": 0.30666667222976685, |
| "learning_rate": 6.094915935949953e-05, |
| "loss": 0.1885, |
| "mean_token_accuracy": 0.9189923286437989, |
| "num_tokens": 56444777.0, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.345489443378119, |
| "grad_norm": 0.4795357882976532, |
| "learning_rate": 6.0586634205306915e-05, |
| "loss": 0.1956, |
| "mean_token_accuracy": 0.9183237552642822, |
| "num_tokens": 57253377.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.3502879078694818, |
| "grad_norm": 0.23285166919231415, |
| "learning_rate": 6.022054622315494e-05, |
| "loss": 0.1871, |
| "mean_token_accuracy": 0.9199147820472717, |
| "num_tokens": 58042662.0, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.3550863723608445, |
| "grad_norm": 0.4314901530742645, |
| "learning_rate": 5.9850984488381596e-05, |
| "loss": 0.1962, |
| "mean_token_accuracy": 0.9169607877731323, |
| "num_tokens": 58831799.0, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.3598848368522073, |
| "grad_norm": 0.3640917241573334, |
| "learning_rate": 5.94780389215471e-05, |
| "loss": 0.1933, |
| "mean_token_accuracy": 0.9174081683158875, |
| "num_tokens": 59645117.0, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.3646833013435701, |
| "grad_norm": 0.2740689516067505, |
| "learning_rate": 5.910180026655467e-05, |
| "loss": 0.1907, |
| "mean_token_accuracy": 0.9203463912010192, |
| "num_tokens": 60430338.0, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.3694817658349328, |
| "grad_norm": 0.2786269783973694, |
| "learning_rate": 5.872236006857106e-05, |
| "loss": 0.185, |
| "mean_token_accuracy": 0.9187370657920837, |
| "num_tokens": 61209084.0, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.3742802303262956, |
| "grad_norm": 0.24551868438720703, |
| "learning_rate": 5.833981065175203e-05, |
| "loss": 0.1857, |
| "mean_token_accuracy": 0.9178588390350342, |
| "num_tokens": 62007757.0, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.3790786948176583, |
| "grad_norm": 0.6173501014709473, |
| "learning_rate": 5.7954245096778384e-05, |
| "loss": 0.189, |
| "mean_token_accuracy": 0.9154422998428344, |
| "num_tokens": 62797095.0, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.3838771593090211, |
| "grad_norm": 0.22034378349781036, |
| "learning_rate": 5.756575721820784e-05, |
| "loss": 0.2012, |
| "mean_token_accuracy": 0.909715449810028, |
| "num_tokens": 63594142.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.3886756238003839, |
| "grad_norm": 0.39530545473098755, |
| "learning_rate": 5.717444154164841e-05, |
| "loss": 0.1912, |
| "mean_token_accuracy": 0.9185901284217834, |
| "num_tokens": 64395013.0, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.3934740882917466, |
| "grad_norm": 0.5130671262741089, |
| "learning_rate": 5.678039328075872e-05, |
| "loss": 0.2055, |
| "mean_token_accuracy": 0.9089265704154968, |
| "num_tokens": 65183834.0, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.3982725527831094, |
| "grad_norm": 0.25764885544776917, |
| "learning_rate": 5.638370831408094e-05, |
| "loss": 0.201, |
| "mean_token_accuracy": 0.9145246505737304, |
| "num_tokens": 65971151.0, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.40307101727447214, |
| "grad_norm": 1.2055509090423584, |
| "learning_rate": 5.5984483161711884e-05, |
| "loss": 0.2015, |
| "mean_token_accuracy": 0.9111255884170533, |
| "num_tokens": 66785774.0, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.40786948176583493, |
| "grad_norm": 0.25073662400245667, |
| "learning_rate": 5.5582814961818154e-05, |
| "loss": 0.1953, |
| "mean_token_accuracy": 0.9116534113883972, |
| "num_tokens": 67574032.0, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.4126679462571977, |
| "grad_norm": 0.46643003821372986, |
| "learning_rate": 5.5178801447000696e-05, |
| "loss": 0.2133, |
| "mean_token_accuracy": 0.9100813388824462, |
| "num_tokens": 68372777.0, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.41746641074856045, |
| "grad_norm": 0.20133262872695923, |
| "learning_rate": 5.4772540920514845e-05, |
| "loss": 0.1939, |
| "mean_token_accuracy": 0.916495680809021, |
| "num_tokens": 69170895.0, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.42226487523992323, |
| "grad_norm": 0.23032309114933014, |
| "learning_rate": 5.4364132232351584e-05, |
| "loss": 0.2009, |
| "mean_token_accuracy": 0.9147676229476929, |
| "num_tokens": 69973680.0, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.42706333973128596, |
| "grad_norm": 0.33535414934158325, |
| "learning_rate": 5.395367475518553e-05, |
| "loss": 0.1898, |
| "mean_token_accuracy": 0.9177168607711792, |
| "num_tokens": 70753938.0, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.43186180422264875, |
| "grad_norm": 0.41969069838523865, |
| "learning_rate": 5.3541268360196046e-05, |
| "loss": 0.1918, |
| "mean_token_accuracy": 0.91667799949646, |
| "num_tokens": 71546158.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.43666026871401153, |
| "grad_norm": 0.20039504766464233, |
| "learning_rate": 5.3127013392766776e-05, |
| "loss": 0.1955, |
| "mean_token_accuracy": 0.9168407678604126, |
| "num_tokens": 72367912.0, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.44145873320537427, |
| "grad_norm": 0.2675475776195526, |
| "learning_rate": 5.271101064807009e-05, |
| "loss": 0.1944, |
| "mean_token_accuracy": 0.9160084128379822, |
| "num_tokens": 73158030.0, |
| "step": 460 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1042, |
| "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": 2.2135909642812785e+18, |
| "train_batch_size": 24, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
