| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 312, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.4476254880428314, |
| "epoch": 0.009685230024213076, |
| "grad_norm": 1.3588989973068237, |
| "learning_rate": 0.0, |
| "loss": 2.2350821495056152, |
| "mean_token_accuracy": 0.5031501688063145, |
| "num_tokens": 96574.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.4007079899311066, |
| "epoch": 0.01937046004842615, |
| "grad_norm": 1.2849924564361572, |
| "learning_rate": 3.125e-06, |
| "loss": 2.14509654045105, |
| "mean_token_accuracy": 0.5205462127923965, |
| "num_tokens": 191520.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.4708476215600967, |
| "epoch": 0.029055690072639227, |
| "grad_norm": 1.2314231395721436, |
| "learning_rate": 6.25e-06, |
| "loss": 2.158306121826172, |
| "mean_token_accuracy": 0.5159582570195198, |
| "num_tokens": 287631.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.5651142746210098, |
| "epoch": 0.0387409200968523, |
| "grad_norm": 0.9785442352294922, |
| "learning_rate": 9.375000000000001e-06, |
| "loss": 2.0755105018615723, |
| "mean_token_accuracy": 0.5181002020835876, |
| "num_tokens": 384739.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.579958975315094, |
| "epoch": 0.048426150121065374, |
| "grad_norm": 0.7276659607887268, |
| "learning_rate": 1.25e-05, |
| "loss": 1.930289626121521, |
| "mean_token_accuracy": 0.5408441498875618, |
| "num_tokens": 481674.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.8359138667583466, |
| "epoch": 0.05811138014527845, |
| "grad_norm": 0.5072433352470398, |
| "learning_rate": 1.5625e-05, |
| "loss": 1.9374589920043945, |
| "mean_token_accuracy": 0.5299954265356064, |
| "num_tokens": 576090.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.8671298921108246, |
| "epoch": 0.06779661016949153, |
| "grad_norm": 0.44714638590812683, |
| "learning_rate": 1.8750000000000002e-05, |
| "loss": 1.8663867712020874, |
| "mean_token_accuracy": 0.5436736792325974, |
| "num_tokens": 673951.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.933446392416954, |
| "epoch": 0.0774818401937046, |
| "grad_norm": 0.5136867761611938, |
| "learning_rate": 2.1875e-05, |
| "loss": 1.7743638753890991, |
| "mean_token_accuracy": 0.5584963485598564, |
| "num_tokens": 771899.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 1.9850385338068008, |
| "epoch": 0.08716707021791767, |
| "grad_norm": 0.5442814826965332, |
| "learning_rate": 2.5e-05, |
| "loss": 1.7758773565292358, |
| "mean_token_accuracy": 0.5573008134961128, |
| "num_tokens": 868206.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 1.9424707889556885, |
| "epoch": 0.09685230024213075, |
| "grad_norm": 0.5084043741226196, |
| "learning_rate": 2.8125000000000003e-05, |
| "loss": 1.7394293546676636, |
| "mean_token_accuracy": 0.5608929991722107, |
| "num_tokens": 964219.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.8063177168369293, |
| "epoch": 0.10653753026634383, |
| "grad_norm": 0.3967217206954956, |
| "learning_rate": 3.125e-05, |
| "loss": 1.6807222366333008, |
| "mean_token_accuracy": 0.5679514929652214, |
| "num_tokens": 1062125.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 1.638314574956894, |
| "epoch": 0.1162227602905569, |
| "grad_norm": 0.5107802152633667, |
| "learning_rate": 3.4375e-05, |
| "loss": 1.6123173236846924, |
| "mean_token_accuracy": 0.583977460861206, |
| "num_tokens": 1159319.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 1.5576547533273697, |
| "epoch": 0.12590799031476999, |
| "grad_norm": 0.3253207802772522, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.6140292882919312, |
| "mean_token_accuracy": 0.5774664506316185, |
| "num_tokens": 1256881.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 1.4602049440145493, |
| "epoch": 0.13559322033898305, |
| "grad_norm": 0.3317743241786957, |
| "learning_rate": 4.0625000000000005e-05, |
| "loss": 1.5576837062835693, |
| "mean_token_accuracy": 0.586665965616703, |
| "num_tokens": 1351620.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 1.4226532131433487, |
| "epoch": 0.14527845036319612, |
| "grad_norm": 0.2991933524608612, |
| "learning_rate": 4.375e-05, |
| "loss": 1.5325368642807007, |
| "mean_token_accuracy": 0.5934261903166771, |
| "num_tokens": 1449026.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 1.453083336353302, |
| "epoch": 0.1549636803874092, |
| "grad_norm": 0.26260727643966675, |
| "learning_rate": 4.6875e-05, |
| "loss": 1.5117604732513428, |
| "mean_token_accuracy": 0.5941561385989189, |
| "num_tokens": 1546355.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 1.4769755005836487, |
| "epoch": 0.16464891041162227, |
| "grad_norm": 0.24356529116630554, |
| "learning_rate": 5e-05, |
| "loss": 1.5000947713851929, |
| "mean_token_accuracy": 0.5963850915431976, |
| "num_tokens": 1644308.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 1.4608993381261826, |
| "epoch": 0.17433414043583534, |
| "grad_norm": 0.27541783452033997, |
| "learning_rate": 4.999859193643945e-05, |
| "loss": 1.4296932220458984, |
| "mean_token_accuracy": 0.6135347038507462, |
| "num_tokens": 1741625.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 1.4715198874473572, |
| "epoch": 0.18401937046004843, |
| "grad_norm": 0.24254612624645233, |
| "learning_rate": 4.999436790436924e-05, |
| "loss": 1.4109866619110107, |
| "mean_token_accuracy": 0.6162872388958931, |
| "num_tokens": 1839077.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 1.4909484386444092, |
| "epoch": 0.1937046004842615, |
| "grad_norm": 0.24249622225761414, |
| "learning_rate": 4.9987328379605816e-05, |
| "loss": 1.4181320667266846, |
| "mean_token_accuracy": 0.6092976555228233, |
| "num_tokens": 1936754.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.468568578362465, |
| "epoch": 0.2033898305084746, |
| "grad_norm": 0.21892383694648743, |
| "learning_rate": 4.9977474155117045e-05, |
| "loss": 1.4207193851470947, |
| "mean_token_accuracy": 0.6143926084041595, |
| "num_tokens": 2034049.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 1.4144536703824997, |
| "epoch": 0.21307506053268765, |
| "grad_norm": 0.24802649021148682, |
| "learning_rate": 4.9964806340932865e-05, |
| "loss": 1.3823838233947754, |
| "mean_token_accuracy": 0.6196955218911171, |
| "num_tokens": 2131193.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 1.4027946889400482, |
| "epoch": 0.22276029055690072, |
| "grad_norm": 0.2114405333995819, |
| "learning_rate": 4.9949326364020314e-05, |
| "loss": 1.3788299560546875, |
| "mean_token_accuracy": 0.6205098181962967, |
| "num_tokens": 2228554.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 1.3630587011575699, |
| "epoch": 0.2324455205811138, |
| "grad_norm": 0.18567043542861938, |
| "learning_rate": 4.993103596812268e-05, |
| "loss": 1.3441742658615112, |
| "mean_token_accuracy": 0.6255069524049759, |
| "num_tokens": 2325761.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 1.3504581600427628, |
| "epoch": 0.24213075060532688, |
| "grad_norm": 0.18140752613544464, |
| "learning_rate": 4.9909937213563165e-05, |
| "loss": 1.3367418050765991, |
| "mean_token_accuracy": 0.6294924318790436, |
| "num_tokens": 2420230.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.3556479513645172, |
| "epoch": 0.25181598062953997, |
| "grad_norm": 0.19952309131622314, |
| "learning_rate": 4.988603247701277e-05, |
| "loss": 1.329459547996521, |
| "mean_token_accuracy": 0.6290309652686119, |
| "num_tokens": 2515756.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 1.3174784928560257, |
| "epoch": 0.26150121065375304, |
| "grad_norm": 0.2040238082408905, |
| "learning_rate": 4.985932445122257e-05, |
| "loss": 1.3146334886550903, |
| "mean_token_accuracy": 0.6350805461406708, |
| "num_tokens": 2611239.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 1.337596833705902, |
| "epoch": 0.2711864406779661, |
| "grad_norm": 0.1924348771572113, |
| "learning_rate": 4.982981614472039e-05, |
| "loss": 1.325057864189148, |
| "mean_token_accuracy": 0.6268098577857018, |
| "num_tokens": 2708463.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 1.295740321278572, |
| "epoch": 0.28087167070217917, |
| "grad_norm": 0.18018221855163574, |
| "learning_rate": 4.979751088147192e-05, |
| "loss": 1.2943141460418701, |
| "mean_token_accuracy": 0.6371493935585022, |
| "num_tokens": 2806105.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 1.2824859917163849, |
| "epoch": 0.29055690072639223, |
| "grad_norm": 0.1904715597629547, |
| "learning_rate": 4.97624123005063e-05, |
| "loss": 1.282959222793579, |
| "mean_token_accuracy": 0.6380399465560913, |
| "num_tokens": 2903815.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.274334877729416, |
| "epoch": 0.30024213075060535, |
| "grad_norm": 0.17454974353313446, |
| "learning_rate": 4.972452435550614e-05, |
| "loss": 1.2828162908554077, |
| "mean_token_accuracy": 0.6363882124423981, |
| "num_tokens": 3000656.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 1.298419788479805, |
| "epoch": 0.3099273607748184, |
| "grad_norm": 0.16989658772945404, |
| "learning_rate": 4.968385131436222e-05, |
| "loss": 1.283800482749939, |
| "mean_token_accuracy": 0.6383039951324463, |
| "num_tokens": 3098537.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 1.3138496726751328, |
| "epoch": 0.3196125907990315, |
| "grad_norm": 0.1963842809200287, |
| "learning_rate": 4.9640397758692715e-05, |
| "loss": 1.287667989730835, |
| "mean_token_accuracy": 0.6366405189037323, |
| "num_tokens": 3195923.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 1.316459745168686, |
| "epoch": 0.32929782082324455, |
| "grad_norm": 0.17209197580814362, |
| "learning_rate": 4.9594168583327094e-05, |
| "loss": 1.2872288227081299, |
| "mean_token_accuracy": 0.6377927586436272, |
| "num_tokens": 3293424.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 1.2688211798667908, |
| "epoch": 0.3389830508474576, |
| "grad_norm": 0.1710345298051834, |
| "learning_rate": 4.954516899575473e-05, |
| "loss": 1.2326550483703613, |
| "mean_token_accuracy": 0.6454800367355347, |
| "num_tokens": 3390314.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 1.275676041841507, |
| "epoch": 0.3486682808716707, |
| "grad_norm": 0.16850367188453674, |
| "learning_rate": 4.949340451553833e-05, |
| "loss": 1.2480475902557373, |
| "mean_token_accuracy": 0.644576296210289, |
| "num_tokens": 3485697.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 1.2488422840833664, |
| "epoch": 0.3583535108958838, |
| "grad_norm": 0.17575675249099731, |
| "learning_rate": 4.943888097369216e-05, |
| "loss": 1.2449251413345337, |
| "mean_token_accuracy": 0.6482485681772232, |
| "num_tokens": 3583116.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 1.20504991710186, |
| "epoch": 0.36803874092009686, |
| "grad_norm": 0.16634824872016907, |
| "learning_rate": 4.938160451202521e-05, |
| "loss": 1.210385799407959, |
| "mean_token_accuracy": 0.6547724008560181, |
| "num_tokens": 3678517.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 1.236429587006569, |
| "epoch": 0.37772397094430993, |
| "grad_norm": 0.15360407531261444, |
| "learning_rate": 4.9321581582449365e-05, |
| "loss": 1.2314069271087646, |
| "mean_token_accuracy": 0.6504408493638039, |
| "num_tokens": 3775690.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 1.2558289468288422, |
| "epoch": 0.387409200968523, |
| "grad_norm": 0.1626509577035904, |
| "learning_rate": 4.9258818946252624e-05, |
| "loss": 1.253812551498413, |
| "mean_token_accuracy": 0.6433829963207245, |
| "num_tokens": 3873239.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.2188849300146103, |
| "epoch": 0.39709443099273606, |
| "grad_norm": 0.16926692426204681, |
| "learning_rate": 4.9193323673337476e-05, |
| "loss": 1.2143971920013428, |
| "mean_token_accuracy": 0.6519596204161644, |
| "num_tokens": 3970507.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 1.2296934127807617, |
| "epoch": 0.4067796610169492, |
| "grad_norm": 0.17094968259334564, |
| "learning_rate": 4.912510314142448e-05, |
| "loss": 1.2195372581481934, |
| "mean_token_accuracy": 0.6513471901416779, |
| "num_tokens": 4067145.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 1.2168416231870651, |
| "epoch": 0.41646489104116224, |
| "grad_norm": 0.15936042368412018, |
| "learning_rate": 4.9054165035221236e-05, |
| "loss": 1.2123249769210815, |
| "mean_token_accuracy": 0.6524514406919479, |
| "num_tokens": 4165113.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 1.1896271854639053, |
| "epoch": 0.4261501210653753, |
| "grad_norm": 0.15422837436199188, |
| "learning_rate": 4.898051734555676e-05, |
| "loss": 1.1957529783248901, |
| "mean_token_accuracy": 0.6586505621671677, |
| "num_tokens": 4262663.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 1.2026645243167877, |
| "epoch": 0.4358353510895884, |
| "grad_norm": 0.16097040474414825, |
| "learning_rate": 4.890416836848127e-05, |
| "loss": 1.1992558240890503, |
| "mean_token_accuracy": 0.6544606015086174, |
| "num_tokens": 4359900.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 1.1843629777431488, |
| "epoch": 0.44552058111380144, |
| "grad_norm": 0.1597595363855362, |
| "learning_rate": 4.88251267043318e-05, |
| "loss": 1.1683578491210938, |
| "mean_token_accuracy": 0.6638541519641876, |
| "num_tokens": 4456985.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 1.1679482907056808, |
| "epoch": 0.4552058111380145, |
| "grad_norm": 0.15203599631786346, |
| "learning_rate": 4.87434012567633e-05, |
| "loss": 1.1561784744262695, |
| "mean_token_accuracy": 0.6650881245732307, |
| "num_tokens": 4554634.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 1.2105818390846252, |
| "epoch": 0.4648910411622276, |
| "grad_norm": 0.15597011148929596, |
| "learning_rate": 4.865900123174574e-05, |
| "loss": 1.1950294971466064, |
| "mean_token_accuracy": 0.6544563546776772, |
| "num_tokens": 4652249.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 1.2046389728784561, |
| "epoch": 0.4745762711864407, |
| "grad_norm": 0.15933600068092346, |
| "learning_rate": 4.857193613652711e-05, |
| "loss": 1.183128833770752, |
| "mean_token_accuracy": 0.6564416959881783, |
| "num_tokens": 4748832.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 1.2113090008497238, |
| "epoch": 0.48426150121065376, |
| "grad_norm": 0.15904678404331207, |
| "learning_rate": 4.848221577856243e-05, |
| "loss": 1.1915383338928223, |
| "mean_token_accuracy": 0.6567506939172745, |
| "num_tokens": 4845986.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.1754019558429718, |
| "epoch": 0.4939467312348668, |
| "grad_norm": 0.15548165142536163, |
| "learning_rate": 4.838985026440905e-05, |
| "loss": 1.1645618677139282, |
| "mean_token_accuracy": 0.6654537692666054, |
| "num_tokens": 4942777.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 1.1717564463615417, |
| "epoch": 0.5036319612590799, |
| "grad_norm": 0.16495537757873535, |
| "learning_rate": 4.829484999858815e-05, |
| "loss": 1.1674176454544067, |
| "mean_token_accuracy": 0.659358873963356, |
| "num_tokens": 5040326.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 1.1637324541807175, |
| "epoch": 0.513317191283293, |
| "grad_norm": 0.16075873374938965, |
| "learning_rate": 4.819722568241274e-05, |
| "loss": 1.1621849536895752, |
| "mean_token_accuracy": 0.663130484521389, |
| "num_tokens": 5137838.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 1.1703068912029266, |
| "epoch": 0.5230024213075061, |
| "grad_norm": 0.16048873960971832, |
| "learning_rate": 4.8096988312782174e-05, |
| "loss": 1.1667448282241821, |
| "mean_token_accuracy": 0.6606730446219444, |
| "num_tokens": 5234578.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 1.1869463622570038, |
| "epoch": 0.5326876513317191, |
| "grad_norm": 0.1574316769838333, |
| "learning_rate": 4.799414918094347e-05, |
| "loss": 1.1867117881774902, |
| "mean_token_accuracy": 0.6562071144580841, |
| "num_tokens": 5332439.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 1.1833796501159668, |
| "epoch": 0.5423728813559322, |
| "grad_norm": 0.1627049446105957, |
| "learning_rate": 4.788871987121937e-05, |
| "loss": 1.1771697998046875, |
| "mean_token_accuracy": 0.6603464111685753, |
| "num_tokens": 5430102.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 1.1720363795757294, |
| "epoch": 0.5520581113801453, |
| "grad_norm": 0.30378302931785583, |
| "learning_rate": 4.77807122597034e-05, |
| "loss": 1.1528563499450684, |
| "mean_token_accuracy": 0.6617102548480034, |
| "num_tokens": 5528264.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 1.1582888960838318, |
| "epoch": 0.5617433414043583, |
| "grad_norm": 0.1613432615995407, |
| "learning_rate": 4.767013851292212e-05, |
| "loss": 1.1482983827590942, |
| "mean_token_accuracy": 0.6675111055374146, |
| "num_tokens": 5625491.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 1.1704413145780563, |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.15665417909622192, |
| "learning_rate": 4.755701108646463e-05, |
| "loss": 1.1476081609725952, |
| "mean_token_accuracy": 0.6660670340061188, |
| "num_tokens": 5723563.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 1.1684788465499878, |
| "epoch": 0.5811138014527845, |
| "grad_norm": 0.1587826907634735, |
| "learning_rate": 4.744134272357948e-05, |
| "loss": 1.15497624874115, |
| "mean_token_accuracy": 0.662791483104229, |
| "num_tokens": 5821106.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.1705324202775955, |
| "epoch": 0.5907990314769975, |
| "grad_norm": 0.1650344729423523, |
| "learning_rate": 4.732314645373921e-05, |
| "loss": 1.168868899345398, |
| "mean_token_accuracy": 0.659059427678585, |
| "num_tokens": 5918772.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 1.1340993344783783, |
| "epoch": 0.6004842615012107, |
| "grad_norm": 0.15585103631019592, |
| "learning_rate": 4.7202435591172676e-05, |
| "loss": 1.1181915998458862, |
| "mean_token_accuracy": 0.6716931834816933, |
| "num_tokens": 6016758.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 1.1135689467191696, |
| "epoch": 0.6101694915254238, |
| "grad_norm": 0.15927211940288544, |
| "learning_rate": 4.7079223733365237e-05, |
| "loss": 1.1100869178771973, |
| "mean_token_accuracy": 0.6781439930200577, |
| "num_tokens": 6113210.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 1.1656545102596283, |
| "epoch": 0.6198547215496368, |
| "grad_norm": 0.1585935652256012, |
| "learning_rate": 4.6953524759527054e-05, |
| "loss": 1.1522451639175415, |
| "mean_token_accuracy": 0.664880745112896, |
| "num_tokens": 6210272.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 1.1241111010313034, |
| "epoch": 0.6295399515738499, |
| "grad_norm": 0.15607106685638428, |
| "learning_rate": 4.6825352829029705e-05, |
| "loss": 1.1200485229492188, |
| "mean_token_accuracy": 0.671033151447773, |
| "num_tokens": 6307273.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 1.135048821568489, |
| "epoch": 0.639225181598063, |
| "grad_norm": 0.1598539501428604, |
| "learning_rate": 4.6694722379811185e-05, |
| "loss": 1.1302683353424072, |
| "mean_token_accuracy": 0.6700672060251236, |
| "num_tokens": 6404865.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 1.1544559001922607, |
| "epoch": 0.648910411622276, |
| "grad_norm": 0.16644105315208435, |
| "learning_rate": 4.656164812674951e-05, |
| "loss": 1.1450002193450928, |
| "mean_token_accuracy": 0.6640813648700714, |
| "num_tokens": 6501650.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 1.132233053445816, |
| "epoch": 0.6585956416464891, |
| "grad_norm": 0.16045193374156952, |
| "learning_rate": 4.642614506000523e-05, |
| "loss": 1.121936559677124, |
| "mean_token_accuracy": 0.6716863736510277, |
| "num_tokens": 6599028.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 1.1332774758338928, |
| "epoch": 0.6682808716707022, |
| "grad_norm": 0.16355212032794952, |
| "learning_rate": 4.628822844333278e-05, |
| "loss": 1.1154568195343018, |
| "mean_token_accuracy": 0.6706111207604408, |
| "num_tokens": 6695913.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 1.117134228348732, |
| "epoch": 0.6779661016949152, |
| "grad_norm": 0.1609818935394287, |
| "learning_rate": 4.614791381236115e-05, |
| "loss": 1.108933925628662, |
| "mean_token_accuracy": 0.6739098057150841, |
| "num_tokens": 6793755.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.123718187212944, |
| "epoch": 0.6876513317191283, |
| "grad_norm": 0.16711370646953583, |
| "learning_rate": 4.6005216972843864e-05, |
| "loss": 1.1205769777297974, |
| "mean_token_accuracy": 0.6695492789149284, |
| "num_tokens": 6889869.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 1.1330177187919617, |
| "epoch": 0.6973365617433414, |
| "grad_norm": 0.15766654908657074, |
| "learning_rate": 4.5860153998878494e-05, |
| "loss": 1.136279582977295, |
| "mean_token_accuracy": 0.6664912849664688, |
| "num_tokens": 6987242.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 1.1289773285388947, |
| "epoch": 0.7070217917675545, |
| "grad_norm": 0.167424738407135, |
| "learning_rate": 4.571274123109606e-05, |
| "loss": 1.1257307529449463, |
| "mean_token_accuracy": 0.6683443114161491, |
| "num_tokens": 7083683.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 1.1089464724063873, |
| "epoch": 0.7167070217917676, |
| "grad_norm": 0.29150310158729553, |
| "learning_rate": 4.5562995274820284e-05, |
| "loss": 1.0986303091049194, |
| "mean_token_accuracy": 0.6785000637173653, |
| "num_tokens": 7180007.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 1.1168130189180374, |
| "epoch": 0.7263922518159807, |
| "grad_norm": 0.1623908281326294, |
| "learning_rate": 4.541093299819714e-05, |
| "loss": 1.1109479665756226, |
| "mean_token_accuracy": 0.6751653999090195, |
| "num_tokens": 7276880.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 1.1238265335559845, |
| "epoch": 0.7360774818401937, |
| "grad_norm": 0.16212861239910126, |
| "learning_rate": 4.5256571530294664e-05, |
| "loss": 1.104738473892212, |
| "mean_token_accuracy": 0.6755917444825172, |
| "num_tokens": 7374051.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 1.1079749763011932, |
| "epoch": 0.7457627118644068, |
| "grad_norm": 0.15648601949214935, |
| "learning_rate": 4.5099928259173516e-05, |
| "loss": 1.1000884771347046, |
| "mean_token_accuracy": 0.6749309673905373, |
| "num_tokens": 7471906.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 1.12865149974823, |
| "epoch": 0.7554479418886199, |
| "grad_norm": 0.15941032767295837, |
| "learning_rate": 4.4941020829928245e-05, |
| "loss": 1.1193838119506836, |
| "mean_token_accuracy": 0.6708522811532021, |
| "num_tokens": 7569981.0, |
| "step": 78 |
| }, |
| { |
| "entropy": 1.1111949235200882, |
| "epoch": 0.7651331719128329, |
| "grad_norm": 0.16523951292037964, |
| "learning_rate": 4.477986714269972e-05, |
| "loss": 1.1221985816955566, |
| "mean_token_accuracy": 0.6717454493045807, |
| "num_tokens": 7663566.0, |
| "step": 79 |
| }, |
| { |
| "entropy": 1.100884273648262, |
| "epoch": 0.774818401937046, |
| "grad_norm": 0.16432514786720276, |
| "learning_rate": 4.4616485350658685e-05, |
| "loss": 1.104296088218689, |
| "mean_token_accuracy": 0.6767150536179543, |
| "num_tokens": 7761120.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.1229810565710068, |
| "epoch": 0.784503631961259, |
| "grad_norm": 0.17101751267910004, |
| "learning_rate": 4.445089385796099e-05, |
| "loss": 1.1202152967453003, |
| "mean_token_accuracy": 0.6708082109689713, |
| "num_tokens": 7859307.0, |
| "step": 81 |
| }, |
| { |
| "entropy": 1.134630709886551, |
| "epoch": 0.7941888619854721, |
| "grad_norm": 0.1734648197889328, |
| "learning_rate": 4.4283111317674374e-05, |
| "loss": 1.1201170682907104, |
| "mean_token_accuracy": 0.6716241240501404, |
| "num_tokens": 7956863.0, |
| "step": 82 |
| }, |
| { |
| "entropy": 1.1259192377328873, |
| "epoch": 0.8038740920096852, |
| "grad_norm": 0.16475871205329895, |
| "learning_rate": 4.4113156629677316e-05, |
| "loss": 1.1068096160888672, |
| "mean_token_accuracy": 0.674552284181118, |
| "num_tokens": 8053100.0, |
| "step": 83 |
| }, |
| { |
| "entropy": 1.0983240008354187, |
| "epoch": 0.8135593220338984, |
| "grad_norm": 0.17292368412017822, |
| "learning_rate": 4.394104893853007e-05, |
| "loss": 1.0763158798217773, |
| "mean_token_accuracy": 0.6806622296571732, |
| "num_tokens": 8151004.0, |
| "step": 84 |
| }, |
| { |
| "entropy": 1.1288987547159195, |
| "epoch": 0.8232445520581114, |
| "grad_norm": 0.16203227639198303, |
| "learning_rate": 4.3766807631318106e-05, |
| "loss": 1.1195769309997559, |
| "mean_token_accuracy": 0.671344555914402, |
| "num_tokens": 8248668.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 1.1410782486200333, |
| "epoch": 0.8329297820823245, |
| "grad_norm": 0.16533830761909485, |
| "learning_rate": 4.359045233546827e-05, |
| "loss": 1.1256823539733887, |
| "mean_token_accuracy": 0.6698467060923576, |
| "num_tokens": 8345497.0, |
| "step": 86 |
| }, |
| { |
| "entropy": 1.0999096632003784, |
| "epoch": 0.8426150121065376, |
| "grad_norm": 0.17075778543949127, |
| "learning_rate": 4.341200291653781e-05, |
| "loss": 1.0872827768325806, |
| "mean_token_accuracy": 0.6762653961777687, |
| "num_tokens": 8443405.0, |
| "step": 87 |
| }, |
| { |
| "entropy": 1.0918122231960297, |
| "epoch": 0.8523002421307506, |
| "grad_norm": 0.1702580451965332, |
| "learning_rate": 4.323147947597666e-05, |
| "loss": 1.0806095600128174, |
| "mean_token_accuracy": 0.6800353080034256, |
| "num_tokens": 8540868.0, |
| "step": 88 |
| }, |
| { |
| "entropy": 1.0941280871629715, |
| "epoch": 0.8619854721549637, |
| "grad_norm": 0.16791851818561554, |
| "learning_rate": 4.3048902348863116e-05, |
| "loss": 1.0981943607330322, |
| "mean_token_accuracy": 0.6758224442601204, |
| "num_tokens": 8638186.0, |
| "step": 89 |
| }, |
| { |
| "entropy": 1.0951679199934006, |
| "epoch": 0.8716707021791767, |
| "grad_norm": 0.1697986125946045, |
| "learning_rate": 4.2864292101613136e-05, |
| "loss": 1.0987718105316162, |
| "mean_token_accuracy": 0.6747072339057922, |
| "num_tokens": 8735354.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.1223643571138382, |
| "epoch": 0.8813559322033898, |
| "grad_norm": 0.2108999490737915, |
| "learning_rate": 4.267766952966369e-05, |
| "loss": 1.1219862699508667, |
| "mean_token_accuracy": 0.6695899069309235, |
| "num_tokens": 8832051.0, |
| "step": 91 |
| }, |
| { |
| "entropy": 1.1099307239055634, |
| "epoch": 0.8910411622276029, |
| "grad_norm": 0.18003661930561066, |
| "learning_rate": 4.248905565513023e-05, |
| "loss": 1.0990370512008667, |
| "mean_token_accuracy": 0.6750800833106041, |
| "num_tokens": 8929471.0, |
| "step": 92 |
| }, |
| { |
| "entropy": 1.1097175031900406, |
| "epoch": 0.9007263922518159, |
| "grad_norm": 0.18473289906978607, |
| "learning_rate": 4.229847172443866e-05, |
| "loss": 1.0890154838562012, |
| "mean_token_accuracy": 0.6764732897281647, |
| "num_tokens": 9026545.0, |
| "step": 93 |
| }, |
| { |
| "entropy": 1.1048423945903778, |
| "epoch": 0.910411622276029, |
| "grad_norm": 0.17208412289619446, |
| "learning_rate": 4.210593920593201e-05, |
| "loss": 1.1022264957427979, |
| "mean_token_accuracy": 0.6741294264793396, |
| "num_tokens": 9124261.0, |
| "step": 94 |
| }, |
| { |
| "entropy": 1.0943758487701416, |
| "epoch": 0.9200968523002422, |
| "grad_norm": 0.18163490295410156, |
| "learning_rate": 4.191147978745218e-05, |
| "loss": 1.0901988744735718, |
| "mean_token_accuracy": 0.6788006126880646, |
| "num_tokens": 9220673.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 1.1178465783596039, |
| "epoch": 0.9297820823244553, |
| "grad_norm": 0.1731623411178589, |
| "learning_rate": 4.171511537389684e-05, |
| "loss": 1.1111767292022705, |
| "mean_token_accuracy": 0.6736986339092255, |
| "num_tokens": 9318321.0, |
| "step": 96 |
| }, |
| { |
| "entropy": 1.0975633561611176, |
| "epoch": 0.9394673123486683, |
| "grad_norm": 0.18208175897598267, |
| "learning_rate": 4.151686808475204e-05, |
| "loss": 1.0915802717208862, |
| "mean_token_accuracy": 0.6765245422720909, |
| "num_tokens": 9415394.0, |
| "step": 97 |
| }, |
| { |
| "entropy": 1.114044964313507, |
| "epoch": 0.9491525423728814, |
| "grad_norm": 0.17058847844600677, |
| "learning_rate": 4.131676025160047e-05, |
| "loss": 1.1074469089508057, |
| "mean_token_accuracy": 0.6720306798815727, |
| "num_tokens": 9512880.0, |
| "step": 98 |
| }, |
| { |
| "entropy": 1.07672019302845, |
| "epoch": 0.9588377723970944, |
| "grad_norm": 0.18478929996490479, |
| "learning_rate": 4.111481441560598e-05, |
| "loss": 1.0674448013305664, |
| "mean_token_accuracy": 0.6838654279708862, |
| "num_tokens": 9606053.0, |
| "step": 99 |
| }, |
| { |
| "entropy": 1.0935327857732773, |
| "epoch": 0.9685230024213075, |
| "grad_norm": 0.17510797083377838, |
| "learning_rate": 4.091105332497439e-05, |
| "loss": 1.0954351425170898, |
| "mean_token_accuracy": 0.6775561571121216, |
| "num_tokens": 9702569.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.0855822414159775, |
| "epoch": 0.9782082324455206, |
| "grad_norm": 0.18510136008262634, |
| "learning_rate": 4.070549993239106e-05, |
| "loss": 1.0844038724899292, |
| "mean_token_accuracy": 0.681103028357029, |
| "num_tokens": 9799976.0, |
| "step": 101 |
| }, |
| { |
| "entropy": 1.1072624325752258, |
| "epoch": 0.9878934624697336, |
| "grad_norm": 0.2109905481338501, |
| "learning_rate": 4.049817739243532e-05, |
| "loss": 1.1046338081359863, |
| "mean_token_accuracy": 0.6760703399777412, |
| "num_tokens": 9895575.0, |
| "step": 102 |
| }, |
| { |
| "entropy": 1.0761565268039703, |
| "epoch": 0.9975786924939467, |
| "grad_norm": 0.18559105694293976, |
| "learning_rate": 4.028910905897229e-05, |
| "loss": 1.0674762725830078, |
| "mean_token_accuracy": 0.6826195642352104, |
| "num_tokens": 9992394.0, |
| "step": 103 |
| }, |
| { |
| "entropy": 1.1065305471420288, |
| "epoch": 1.0, |
| "grad_norm": 0.3376278877258301, |
| "learning_rate": 4.007831848252211e-05, |
| "loss": 1.09256911277771, |
| "mean_token_accuracy": 0.678756445646286, |
| "num_tokens": 10016415.0, |
| "step": 104 |
| }, |
| { |
| "entropy": 1.1107248812913895, |
| "epoch": 1.0096852300242132, |
| "grad_norm": 0.1708710938692093, |
| "learning_rate": 3.986582940760717e-05, |
| "loss": 1.0717049837112427, |
| "mean_token_accuracy": 0.6800583377480507, |
| "num_tokens": 10113793.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 1.0776572525501251, |
| "epoch": 1.0193704600484261, |
| "grad_norm": 0.17748922109603882, |
| "learning_rate": 3.965166577007733e-05, |
| "loss": 1.0392060279846191, |
| "mean_token_accuracy": 0.6892436370253563, |
| "num_tokens": 10211074.0, |
| "step": 106 |
| }, |
| { |
| "entropy": 1.0571173429489136, |
| "epoch": 1.0290556900726393, |
| "grad_norm": 0.18791398406028748, |
| "learning_rate": 3.94358516944137e-05, |
| "loss": 1.038546085357666, |
| "mean_token_accuracy": 0.6879089176654816, |
| "num_tokens": 10307987.0, |
| "step": 107 |
| }, |
| { |
| "entropy": 1.0400206819176674, |
| "epoch": 1.0387409200968523, |
| "grad_norm": 0.16869165003299713, |
| "learning_rate": 3.9218411491011176e-05, |
| "loss": 1.0324063301086426, |
| "mean_token_accuracy": 0.6877342015504837, |
| "num_tokens": 10405148.0, |
| "step": 108 |
| }, |
| { |
| "entropy": 1.0476296544075012, |
| "epoch": 1.0484261501210654, |
| "grad_norm": 0.18576034903526306, |
| "learning_rate": 3.899936965343989e-05, |
| "loss": 1.0663259029388428, |
| "mean_token_accuracy": 0.6821715012192726, |
| "num_tokens": 10502344.0, |
| "step": 109 |
| }, |
| { |
| "entropy": 0.9960673823952675, |
| "epoch": 1.0581113801452784, |
| "grad_norm": 0.17832568287849426, |
| "learning_rate": 3.877875085568623e-05, |
| "loss": 1.0000097751617432, |
| "mean_token_accuracy": 0.6989128738641739, |
| "num_tokens": 10599599.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 1.0352009981870651, |
| "epoch": 1.0677966101694916, |
| "grad_norm": 0.17328514158725739, |
| "learning_rate": 3.8556579949373384e-05, |
| "loss": 1.0506186485290527, |
| "mean_token_accuracy": 0.6840933337807655, |
| "num_tokens": 10694645.0, |
| "step": 111 |
| }, |
| { |
| "entropy": 1.0331084430217743, |
| "epoch": 1.0774818401937045, |
| "grad_norm": 0.18105825781822205, |
| "learning_rate": 3.833288196096194e-05, |
| "loss": 1.0261142253875732, |
| "mean_token_accuracy": 0.6913967728614807, |
| "num_tokens": 10790067.0, |
| "step": 112 |
| }, |
| { |
| "entropy": 1.0757844671607018, |
| "epoch": 1.0871670702179177, |
| "grad_norm": 0.1806410551071167, |
| "learning_rate": 3.8107682088930794e-05, |
| "loss": 1.0621310472488403, |
| "mean_token_accuracy": 0.6843468695878983, |
| "num_tokens": 10885655.0, |
| "step": 113 |
| }, |
| { |
| "entropy": 1.0726244300603867, |
| "epoch": 1.0968523002421307, |
| "grad_norm": 0.17602035403251648, |
| "learning_rate": 3.7881005700938635e-05, |
| "loss": 1.0586791038513184, |
| "mean_token_accuracy": 0.6825271546840668, |
| "num_tokens": 10983568.0, |
| "step": 114 |
| }, |
| { |
| "entropy": 1.0513464957475662, |
| "epoch": 1.1065375302663438, |
| "grad_norm": 0.1740947663784027, |
| "learning_rate": 3.7652878330966415e-05, |
| "loss": 1.035830020904541, |
| "mean_token_accuracy": 0.6891666278243065, |
| "num_tokens": 11081209.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 1.0637426376342773, |
| "epoch": 1.116222760290557, |
| "grad_norm": 0.1756405085325241, |
| "learning_rate": 3.742332567644107e-05, |
| "loss": 1.0529723167419434, |
| "mean_token_accuracy": 0.6864708811044693, |
| "num_tokens": 11178554.0, |
| "step": 116 |
| }, |
| { |
| "entropy": 1.032620556652546, |
| "epoch": 1.12590799031477, |
| "grad_norm": 0.1746027022600174, |
| "learning_rate": 3.719237359534087e-05, |
| "loss": 1.0131734609603882, |
| "mean_token_accuracy": 0.6930168569087982, |
| "num_tokens": 11275773.0, |
| "step": 117 |
| }, |
| { |
| "entropy": 1.0357091426849365, |
| "epoch": 1.1355932203389831, |
| "grad_norm": 0.17611640691757202, |
| "learning_rate": 3.6960048103282566e-05, |
| "loss": 1.0305650234222412, |
| "mean_token_accuracy": 0.6928873062133789, |
| "num_tokens": 11372312.0, |
| "step": 118 |
| }, |
| { |
| "entropy": 1.0247548967599869, |
| "epoch": 1.145278450363196, |
| "grad_norm": 0.16733205318450928, |
| "learning_rate": 3.672637537059093e-05, |
| "loss": 1.0267465114593506, |
| "mean_token_accuracy": 0.6941879317164421, |
| "num_tokens": 11469895.0, |
| "step": 119 |
| }, |
| { |
| "entropy": 1.0328287035226822, |
| "epoch": 1.1549636803874093, |
| "grad_norm": 0.17758148908615112, |
| "learning_rate": 3.6491381719350756e-05, |
| "loss": 1.038550853729248, |
| "mean_token_accuracy": 0.687534786760807, |
| "num_tokens": 11567819.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 1.0606635063886642, |
| "epoch": 1.1646489104116222, |
| "grad_norm": 0.18219131231307983, |
| "learning_rate": 3.6255093620441834e-05, |
| "loss": 1.0544192790985107, |
| "mean_token_accuracy": 0.6846267804503441, |
| "num_tokens": 11665799.0, |
| "step": 121 |
| }, |
| { |
| "entropy": 1.0355539470911026, |
| "epoch": 1.1743341404358354, |
| "grad_norm": 0.18732059001922607, |
| "learning_rate": 3.6017537690557115e-05, |
| "loss": 1.0224016904830933, |
| "mean_token_accuracy": 0.6915983185172081, |
| "num_tokens": 11762356.0, |
| "step": 122 |
| }, |
| { |
| "entropy": 1.085768237709999, |
| "epoch": 1.1840193704600483, |
| "grad_norm": 0.20525461435317993, |
| "learning_rate": 3.577874068920446e-05, |
| "loss": 1.057420253753662, |
| "mean_token_accuracy": 0.6817465797066689, |
| "num_tokens": 11857832.0, |
| "step": 123 |
| }, |
| { |
| "entropy": 1.024247646331787, |
| "epoch": 1.1937046004842615, |
| "grad_norm": 0.17486801743507385, |
| "learning_rate": 3.553872951569236e-05, |
| "loss": 1.007400393486023, |
| "mean_token_accuracy": 0.6967773362994194, |
| "num_tokens": 11953563.0, |
| "step": 124 |
| }, |
| { |
| "entropy": 1.0304122641682625, |
| "epoch": 1.2033898305084745, |
| "grad_norm": 0.17227725684642792, |
| "learning_rate": 3.529753120609982e-05, |
| "loss": 1.0166981220245361, |
| "mean_token_accuracy": 0.6900071352720261, |
| "num_tokens": 12051630.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 1.0403276681900024, |
| "epoch": 1.2130750605326877, |
| "grad_norm": 0.17845618724822998, |
| "learning_rate": 3.505517293023088e-05, |
| "loss": 1.0411816835403442, |
| "mean_token_accuracy": 0.6878266781568527, |
| "num_tokens": 12149525.0, |
| "step": 126 |
| }, |
| { |
| "entropy": 1.0372891202569008, |
| "epoch": 1.2227602905569008, |
| "grad_norm": 0.17896883189678192, |
| "learning_rate": 3.481168198855409e-05, |
| "loss": 1.0509088039398193, |
| "mean_token_accuracy": 0.6861589029431343, |
| "num_tokens": 12246944.0, |
| "step": 127 |
| }, |
| { |
| "entropy": 1.0567465275526047, |
| "epoch": 1.2324455205811138, |
| "grad_norm": 0.1735103726387024, |
| "learning_rate": 3.456708580912725e-05, |
| "loss": 1.048382043838501, |
| "mean_token_accuracy": 0.6845468729734421, |
| "num_tokens": 12343964.0, |
| "step": 128 |
| }, |
| { |
| "entropy": 1.044258013367653, |
| "epoch": 1.242130750605327, |
| "grad_norm": 0.179740771651268, |
| "learning_rate": 3.432141194450772e-05, |
| "loss": 1.0318509340286255, |
| "mean_token_accuracy": 0.6892603412270546, |
| "num_tokens": 12441245.0, |
| "step": 129 |
| }, |
| { |
| "entropy": 1.0394302904605865, |
| "epoch": 1.25181598062954, |
| "grad_norm": 0.18108829855918884, |
| "learning_rate": 3.407468806864883e-05, |
| "loss": 1.0396722555160522, |
| "mean_token_accuracy": 0.6859570071101189, |
| "num_tokens": 12538938.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 1.0346315652132034, |
| "epoch": 1.261501210653753, |
| "grad_norm": 0.16831137239933014, |
| "learning_rate": 3.382694197378252e-05, |
| "loss": 1.0301259756088257, |
| "mean_token_accuracy": 0.6876077353954315, |
| "num_tokens": 12636750.0, |
| "step": 131 |
| }, |
| { |
| "entropy": 1.0501351803541183, |
| "epoch": 1.271186440677966, |
| "grad_norm": 0.18215049803256989, |
| "learning_rate": 3.357820156728867e-05, |
| "loss": 1.0379700660705566, |
| "mean_token_accuracy": 0.6864259541034698, |
| "num_tokens": 12732510.0, |
| "step": 132 |
| }, |
| { |
| "entropy": 1.056677907705307, |
| "epoch": 1.2808716707021792, |
| "grad_norm": 0.17387507855892181, |
| "learning_rate": 3.332849486855144e-05, |
| "loss": 1.0349537134170532, |
| "mean_token_accuracy": 0.6882437765598297, |
| "num_tokens": 12828202.0, |
| "step": 133 |
| }, |
| { |
| "entropy": 1.0694306939840317, |
| "epoch": 1.2905569007263922, |
| "grad_norm": 0.18142169713974, |
| "learning_rate": 3.307785000580313e-05, |
| "loss": 1.0491408109664917, |
| "mean_token_accuracy": 0.6856276169419289, |
| "num_tokens": 12924452.0, |
| "step": 134 |
| }, |
| { |
| "entropy": 1.0445284843444824, |
| "epoch": 1.3002421307506054, |
| "grad_norm": 0.17338253557682037, |
| "learning_rate": 3.282629521295556e-05, |
| "loss": 1.0387568473815918, |
| "mean_token_accuracy": 0.6878345832228661, |
| "num_tokens": 13021226.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 1.03611271828413, |
| "epoch": 1.3099273607748185, |
| "grad_norm": 0.17574281990528107, |
| "learning_rate": 3.257385882641971e-05, |
| "loss": 1.032334566116333, |
| "mean_token_accuracy": 0.6887728422880173, |
| "num_tokens": 13117072.0, |
| "step": 136 |
| }, |
| { |
| "entropy": 1.0164377763867378, |
| "epoch": 1.3196125907990315, |
| "grad_norm": 0.17293879389762878, |
| "learning_rate": 3.232056928191376e-05, |
| "loss": 1.0038666725158691, |
| "mean_token_accuracy": 0.6958679780364037, |
| "num_tokens": 13214927.0, |
| "step": 137 |
| }, |
| { |
| "entropy": 1.02716813236475, |
| "epoch": 1.3292978208232444, |
| "grad_norm": 0.1768789142370224, |
| "learning_rate": 3.2066455111259945e-05, |
| "loss": 1.0230392217636108, |
| "mean_token_accuracy": 0.6910659521818161, |
| "num_tokens": 13312250.0, |
| "step": 138 |
| }, |
| { |
| "entropy": 1.0242123305797577, |
| "epoch": 1.3389830508474576, |
| "grad_norm": 0.18655547499656677, |
| "learning_rate": 3.1811544939170575e-05, |
| "loss": 1.027778148651123, |
| "mean_token_accuracy": 0.6896005198359489, |
| "num_tokens": 13409125.0, |
| "step": 139 |
| }, |
| { |
| "entropy": 1.0247902870178223, |
| "epoch": 1.3486682808716708, |
| "grad_norm": 0.1732546091079712, |
| "learning_rate": 3.155586748002362e-05, |
| "loss": 1.0247126817703247, |
| "mean_token_accuracy": 0.6925645992159843, |
| "num_tokens": 13505714.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 1.0391114205121994, |
| "epoch": 1.3583535108958837, |
| "grad_norm": 0.1730506271123886, |
| "learning_rate": 3.1299451534628135e-05, |
| "loss": 1.0413163900375366, |
| "mean_token_accuracy": 0.6873403564095497, |
| "num_tokens": 13603282.0, |
| "step": 141 |
| }, |
| { |
| "entropy": 1.0580826699733734, |
| "epoch": 1.368038740920097, |
| "grad_norm": 0.17985138297080994, |
| "learning_rate": 3.1042325986980064e-05, |
| "loss": 1.048020362854004, |
| "mean_token_accuracy": 0.6840562298893929, |
| "num_tokens": 13699120.0, |
| "step": 142 |
| }, |
| { |
| "entropy": 1.034823827445507, |
| "epoch": 1.3777239709443099, |
| "grad_norm": 0.1742866039276123, |
| "learning_rate": 3.0784519801008546e-05, |
| "loss": 1.019952416419983, |
| "mean_token_accuracy": 0.6919118836522102, |
| "num_tokens": 13796639.0, |
| "step": 143 |
| }, |
| { |
| "entropy": 1.034243457019329, |
| "epoch": 1.387409200968523, |
| "grad_norm": 0.18104857206344604, |
| "learning_rate": 3.0526062017313254e-05, |
| "loss": 1.0257322788238525, |
| "mean_token_accuracy": 0.693074606359005, |
| "num_tokens": 13893968.0, |
| "step": 144 |
| }, |
| { |
| "entropy": 1.0477502346038818, |
| "epoch": 1.397094430992736, |
| "grad_norm": 0.17592455446720123, |
| "learning_rate": 3.0266981749893157e-05, |
| "loss": 1.0342764854431152, |
| "mean_token_accuracy": 0.6866420730948448, |
| "num_tokens": 13990892.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 1.0479690209031105, |
| "epoch": 1.4067796610169492, |
| "grad_norm": 0.1820760816335678, |
| "learning_rate": 3.0007308182866985e-05, |
| "loss": 1.0341622829437256, |
| "mean_token_accuracy": 0.687219500541687, |
| "num_tokens": 14087344.0, |
| "step": 146 |
| }, |
| { |
| "entropy": 1.0348835960030556, |
| "epoch": 1.4164648910411621, |
| "grad_norm": 0.1742199808359146, |
| "learning_rate": 2.974707056718571e-05, |
| "loss": 1.0271401405334473, |
| "mean_token_accuracy": 0.6896429732441902, |
| "num_tokens": 14185593.0, |
| "step": 147 |
| }, |
| { |
| "entropy": 1.0333365574479103, |
| "epoch": 1.4261501210653753, |
| "grad_norm": 0.177699476480484, |
| "learning_rate": 2.9486298217337637e-05, |
| "loss": 1.0313661098480225, |
| "mean_token_accuracy": 0.6886806860566139, |
| "num_tokens": 14283694.0, |
| "step": 148 |
| }, |
| { |
| "entropy": 1.0181496515870094, |
| "epoch": 1.4358353510895885, |
| "grad_norm": 0.17134729027748108, |
| "learning_rate": 2.9225020508046232e-05, |
| "loss": 1.009653091430664, |
| "mean_token_accuracy": 0.6931144669651985, |
| "num_tokens": 14380604.0, |
| "step": 149 |
| }, |
| { |
| "entropy": 1.038355827331543, |
| "epoch": 1.4455205811138014, |
| "grad_norm": 0.1845579445362091, |
| "learning_rate": 2.8963266870961226e-05, |
| "loss": 1.0307377576828003, |
| "mean_token_accuracy": 0.6884006261825562, |
| "num_tokens": 14478185.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 1.0334223732352257, |
| "epoch": 1.4552058111380144, |
| "grad_norm": 0.24978552758693695, |
| "learning_rate": 2.8701066791343288e-05, |
| "loss": 1.0366319417953491, |
| "mean_token_accuracy": 0.6860118135809898, |
| "num_tokens": 14575277.0, |
| "step": 151 |
| }, |
| { |
| "entropy": 1.0341607704758644, |
| "epoch": 1.4648910411622276, |
| "grad_norm": 0.17872564494609833, |
| "learning_rate": 2.8438449804742628e-05, |
| "loss": 1.0180070400238037, |
| "mean_token_accuracy": 0.6917398646473885, |
| "num_tokens": 14672534.0, |
| "step": 152 |
| }, |
| { |
| "entropy": 1.0590864270925522, |
| "epoch": 1.4745762711864407, |
| "grad_norm": 0.17723426222801208, |
| "learning_rate": 2.8175445493671972e-05, |
| "loss": 1.051386833190918, |
| "mean_token_accuracy": 0.6834967508912086, |
| "num_tokens": 14770518.0, |
| "step": 153 |
| }, |
| { |
| "entropy": 1.0175726786255836, |
| "epoch": 1.4842615012106537, |
| "grad_norm": 0.17911297082901, |
| "learning_rate": 2.7912083484274266e-05, |
| "loss": 0.9993636012077332, |
| "mean_token_accuracy": 0.6968463584780693, |
| "num_tokens": 14867845.0, |
| "step": 154 |
| }, |
| { |
| "entropy": 1.01533143222332, |
| "epoch": 1.4939467312348669, |
| "grad_norm": 0.17201802134513855, |
| "learning_rate": 2.7648393442985403e-05, |
| "loss": 0.9994634389877319, |
| "mean_token_accuracy": 0.6991591900587082, |
| "num_tokens": 14965851.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 1.0423510372638702, |
| "epoch": 1.5036319612590798, |
| "grad_norm": 0.17345097661018372, |
| "learning_rate": 2.7384405073192454e-05, |
| "loss": 1.0389484167099, |
| "mean_token_accuracy": 0.6870414391160011, |
| "num_tokens": 15063279.0, |
| "step": 156 |
| }, |
| { |
| "entropy": 1.0268240571022034, |
| "epoch": 1.513317191283293, |
| "grad_norm": 0.18508543074131012, |
| "learning_rate": 2.7120148111887732e-05, |
| "loss": 1.029033899307251, |
| "mean_token_accuracy": 0.6905829161405563, |
| "num_tokens": 15160245.0, |
| "step": 157 |
| }, |
| { |
| "entropy": 1.0137058570981026, |
| "epoch": 1.5230024213075062, |
| "grad_norm": 0.1771853119134903, |
| "learning_rate": 2.6855652326319063e-05, |
| "loss": 1.011698603630066, |
| "mean_token_accuracy": 0.6954887434840202, |
| "num_tokens": 15257132.0, |
| "step": 158 |
| }, |
| { |
| "entropy": 1.0114770829677582, |
| "epoch": 1.5326876513317191, |
| "grad_norm": 0.1829320192337036, |
| "learning_rate": 2.659094751063666e-05, |
| "loss": 1.0108840465545654, |
| "mean_token_accuracy": 0.6935675665736198, |
| "num_tokens": 15354561.0, |
| "step": 159 |
| }, |
| { |
| "entropy": 1.0002705082297325, |
| "epoch": 1.542372881355932, |
| "grad_norm": 0.17417006194591522, |
| "learning_rate": 2.6326063482536934e-05, |
| "loss": 0.9976310729980469, |
| "mean_token_accuracy": 0.6973941773176193, |
| "num_tokens": 15451774.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 1.0380558297038078, |
| "epoch": 1.5520581113801453, |
| "grad_norm": 0.18505249917507172, |
| "learning_rate": 2.606103007990371e-05, |
| "loss": 1.027144193649292, |
| "mean_token_accuracy": 0.6899437606334686, |
| "num_tokens": 15545203.0, |
| "step": 161 |
| }, |
| { |
| "entropy": 1.0247594714164734, |
| "epoch": 1.5617433414043584, |
| "grad_norm": 0.17371951043605804, |
| "learning_rate": 2.579587715744712e-05, |
| "loss": 1.0144855976104736, |
| "mean_token_accuracy": 0.6931553333997726, |
| "num_tokens": 15642907.0, |
| "step": 162 |
| }, |
| { |
| "entropy": 1.025797888636589, |
| "epoch": 1.5714285714285714, |
| "grad_norm": 0.17915304005146027, |
| "learning_rate": 2.5530634583340592e-05, |
| "loss": 1.014986276626587, |
| "mean_token_accuracy": 0.6926708817481995, |
| "num_tokens": 15739378.0, |
| "step": 163 |
| }, |
| { |
| "entropy": 1.0104742795228958, |
| "epoch": 1.5811138014527844, |
| "grad_norm": 0.17889732122421265, |
| "learning_rate": 2.526533223585641e-05, |
| "loss": 1.0031661987304688, |
| "mean_token_accuracy": 0.6982422098517418, |
| "num_tokens": 15836007.0, |
| "step": 164 |
| }, |
| { |
| "entropy": 1.0167404934763908, |
| "epoch": 1.5907990314769975, |
| "grad_norm": 0.1768142729997635, |
| "learning_rate": 2.5e-05, |
| "loss": 1.009070634841919, |
| "mean_token_accuracy": 0.6938488930463791, |
| "num_tokens": 15933286.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 0.9942386075854301, |
| "epoch": 1.6004842615012107, |
| "grad_norm": 0.2674974203109741, |
| "learning_rate": 2.47346677641436e-05, |
| "loss": 0.9868994951248169, |
| "mean_token_accuracy": 0.7019253075122833, |
| "num_tokens": 16030240.0, |
| "step": 166 |
| }, |
| { |
| "entropy": 1.0080910325050354, |
| "epoch": 1.6101694915254239, |
| "grad_norm": 0.17362943291664124, |
| "learning_rate": 2.446936541665941e-05, |
| "loss": 1.0053434371948242, |
| "mean_token_accuracy": 0.6974755153059959, |
| "num_tokens": 16127744.0, |
| "step": 167 |
| }, |
| { |
| "entropy": 1.0292630195617676, |
| "epoch": 1.6198547215496368, |
| "grad_norm": 0.18086425960063934, |
| "learning_rate": 2.4204122842552896e-05, |
| "loss": 1.0237219333648682, |
| "mean_token_accuracy": 0.69173414260149, |
| "num_tokens": 16225217.0, |
| "step": 168 |
| }, |
| { |
| "entropy": 1.0308879762887955, |
| "epoch": 1.6295399515738498, |
| "grad_norm": 0.18374203145503998, |
| "learning_rate": 2.39389699200963e-05, |
| "loss": 1.0210704803466797, |
| "mean_token_accuracy": 0.6903956010937691, |
| "num_tokens": 16322913.0, |
| "step": 169 |
| }, |
| { |
| "entropy": 1.026255913078785, |
| "epoch": 1.639225181598063, |
| "grad_norm": 0.18278539180755615, |
| "learning_rate": 2.3673936517463075e-05, |
| "loss": 1.0169858932495117, |
| "mean_token_accuracy": 0.6928274035453796, |
| "num_tokens": 16419439.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.9919314235448837, |
| "epoch": 1.6489104116222761, |
| "grad_norm": 0.17901423573493958, |
| "learning_rate": 2.3409052489363342e-05, |
| "loss": 0.9918413162231445, |
| "mean_token_accuracy": 0.6992172300815582, |
| "num_tokens": 16516410.0, |
| "step": 171 |
| }, |
| { |
| "entropy": 1.0355833768844604, |
| "epoch": 1.658595641646489, |
| "grad_norm": 0.17641407251358032, |
| "learning_rate": 2.3144347673680936e-05, |
| "loss": 1.0381958484649658, |
| "mean_token_accuracy": 0.686020016670227, |
| "num_tokens": 16614080.0, |
| "step": 172 |
| }, |
| { |
| "entropy": 1.0149222612380981, |
| "epoch": 1.668280871670702, |
| "grad_norm": 0.17820627987384796, |
| "learning_rate": 2.287985188811228e-05, |
| "loss": 1.0130999088287354, |
| "mean_token_accuracy": 0.6923095658421516, |
| "num_tokens": 16711804.0, |
| "step": 173 |
| }, |
| { |
| "entropy": 1.0243929624557495, |
| "epoch": 1.6779661016949152, |
| "grad_norm": 0.18051660060882568, |
| "learning_rate": 2.261559492680755e-05, |
| "loss": 1.0211886167526245, |
| "mean_token_accuracy": 0.6929004341363907, |
| "num_tokens": 16808390.0, |
| "step": 174 |
| }, |
| { |
| "entropy": 1.008925937116146, |
| "epoch": 1.6876513317191284, |
| "grad_norm": 0.17846113443374634, |
| "learning_rate": 2.23516065570146e-05, |
| "loss": 0.9855537414550781, |
| "mean_token_accuracy": 0.7024274170398712, |
| "num_tokens": 16905846.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 1.0306098610162735, |
| "epoch": 1.6973365617433414, |
| "grad_norm": 0.17899896204471588, |
| "learning_rate": 2.2087916515725737e-05, |
| "loss": 1.0127032995224, |
| "mean_token_accuracy": 0.6937521025538445, |
| "num_tokens": 17002576.0, |
| "step": 176 |
| }, |
| { |
| "entropy": 1.0314870774745941, |
| "epoch": 1.7070217917675545, |
| "grad_norm": 0.1775345355272293, |
| "learning_rate": 2.182455450632803e-05, |
| "loss": 1.014747142791748, |
| "mean_token_accuracy": 0.6926901116967201, |
| "num_tokens": 17099808.0, |
| "step": 177 |
| }, |
| { |
| "entropy": 0.988661415874958, |
| "epoch": 1.7167070217917675, |
| "grad_norm": 0.18358361721038818, |
| "learning_rate": 2.1561550195257378e-05, |
| "loss": 0.9753472805023193, |
| "mean_token_accuracy": 0.7034848108887672, |
| "num_tokens": 17197523.0, |
| "step": 178 |
| }, |
| { |
| "entropy": 1.0072592198848724, |
| "epoch": 1.7263922518159807, |
| "grad_norm": 0.18197070062160492, |
| "learning_rate": 2.1298933208656718e-05, |
| "loss": 1.0025818347930908, |
| "mean_token_accuracy": 0.6967148259282112, |
| "num_tokens": 17292582.0, |
| "step": 179 |
| }, |
| { |
| "entropy": 1.0190014764666557, |
| "epoch": 1.7360774818401938, |
| "grad_norm": 0.1827293038368225, |
| "learning_rate": 2.103673312903878e-05, |
| "loss": 1.025465726852417, |
| "mean_token_accuracy": 0.691127598285675, |
| "num_tokens": 17389678.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 1.0355056896805763, |
| "epoch": 1.7457627118644068, |
| "grad_norm": 0.19289104640483856, |
| "learning_rate": 2.0774979491953777e-05, |
| "loss": 1.030361533164978, |
| "mean_token_accuracy": 0.6898203268647194, |
| "num_tokens": 17484545.0, |
| "step": 181 |
| }, |
| { |
| "entropy": 1.0205051228404045, |
| "epoch": 1.7554479418886197, |
| "grad_norm": 0.18466636538505554, |
| "learning_rate": 2.0513701782662366e-05, |
| "loss": 1.01216721534729, |
| "mean_token_accuracy": 0.6929588541388512, |
| "num_tokens": 17579500.0, |
| "step": 182 |
| }, |
| { |
| "entropy": 0.9954008832573891, |
| "epoch": 1.765133171912833, |
| "grad_norm": 0.18636250495910645, |
| "learning_rate": 2.025292943281429e-05, |
| "loss": 0.9910628199577332, |
| "mean_token_accuracy": 0.6983159705996513, |
| "num_tokens": 17674413.0, |
| "step": 183 |
| }, |
| { |
| "entropy": 1.00897516310215, |
| "epoch": 1.774818401937046, |
| "grad_norm": 0.1883116513490677, |
| "learning_rate": 1.9992691817133024e-05, |
| "loss": 1.0008057355880737, |
| "mean_token_accuracy": 0.6949929445981979, |
| "num_tokens": 17772206.0, |
| "step": 184 |
| }, |
| { |
| "entropy": 1.0539861172437668, |
| "epoch": 1.784503631961259, |
| "grad_norm": 0.188166081905365, |
| "learning_rate": 1.973301825010685e-05, |
| "loss": 1.0534381866455078, |
| "mean_token_accuracy": 0.6841985285282135, |
| "num_tokens": 17869518.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 1.0237281695008278, |
| "epoch": 1.794188861985472, |
| "grad_norm": 0.18438467383384705, |
| "learning_rate": 1.947393798268676e-05, |
| "loss": 1.0138177871704102, |
| "mean_token_accuracy": 0.6940690726041794, |
| "num_tokens": 17965115.0, |
| "step": 186 |
| }, |
| { |
| "entropy": 1.0318024158477783, |
| "epoch": 1.8038740920096852, |
| "grad_norm": 0.17989851534366608, |
| "learning_rate": 1.9215480198991466e-05, |
| "loss": 1.0178849697113037, |
| "mean_token_accuracy": 0.6889730393886566, |
| "num_tokens": 18062515.0, |
| "step": 187 |
| }, |
| { |
| "entropy": 1.0370707884430885, |
| "epoch": 1.8135593220338984, |
| "grad_norm": 0.18175791203975677, |
| "learning_rate": 1.895767401301994e-05, |
| "loss": 1.0233769416809082, |
| "mean_token_accuracy": 0.689442440867424, |
| "num_tokens": 18159901.0, |
| "step": 188 |
| }, |
| { |
| "entropy": 1.0387394651770592, |
| "epoch": 1.8232445520581115, |
| "grad_norm": 0.1763962209224701, |
| "learning_rate": 1.8700548465371874e-05, |
| "loss": 1.0317208766937256, |
| "mean_token_accuracy": 0.6874615550041199, |
| "num_tokens": 18257746.0, |
| "step": 189 |
| }, |
| { |
| "entropy": 1.016056202352047, |
| "epoch": 1.8329297820823245, |
| "grad_norm": 0.1811491698026657, |
| "learning_rate": 1.84441325199764e-05, |
| "loss": 1.0119330883026123, |
| "mean_token_accuracy": 0.6953575611114502, |
| "num_tokens": 18355948.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.9938200861215591, |
| "epoch": 1.8426150121065374, |
| "grad_norm": 0.1725209653377533, |
| "learning_rate": 1.818845506082943e-05, |
| "loss": 0.9812361598014832, |
| "mean_token_accuracy": 0.7028805017471313, |
| "num_tokens": 18453527.0, |
| "step": 191 |
| }, |
| { |
| "entropy": 1.031374305486679, |
| "epoch": 1.8523002421307506, |
| "grad_norm": 0.18246252834796906, |
| "learning_rate": 1.793354488874006e-05, |
| "loss": 1.0203440189361572, |
| "mean_token_accuracy": 0.6907096654176712, |
| "num_tokens": 18549884.0, |
| "step": 192 |
| }, |
| { |
| "entropy": 0.9885724261403084, |
| "epoch": 1.8619854721549638, |
| "grad_norm": 0.1804785132408142, |
| "learning_rate": 1.7679430718086243e-05, |
| "loss": 0.9796859622001648, |
| "mean_token_accuracy": 0.702710434794426, |
| "num_tokens": 18647122.0, |
| "step": 193 |
| }, |
| { |
| "entropy": 0.9969891235232353, |
| "epoch": 1.8716707021791767, |
| "grad_norm": 0.2115977555513382, |
| "learning_rate": 1.742614117358029e-05, |
| "loss": 0.9887296557426453, |
| "mean_token_accuracy": 0.6984992548823357, |
| "num_tokens": 18743129.0, |
| "step": 194 |
| }, |
| { |
| "entropy": 0.9905409216880798, |
| "epoch": 1.8813559322033897, |
| "grad_norm": 0.18363232910633087, |
| "learning_rate": 1.7173704787044446e-05, |
| "loss": 0.9921536445617676, |
| "mean_token_accuracy": 0.697743609547615, |
| "num_tokens": 18841235.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 0.9967489168047905, |
| "epoch": 1.8910411622276029, |
| "grad_norm": 0.1787017434835434, |
| "learning_rate": 1.6922149994196878e-05, |
| "loss": 1.0015537738800049, |
| "mean_token_accuracy": 0.6942943632602692, |
| "num_tokens": 18938405.0, |
| "step": 196 |
| }, |
| { |
| "entropy": 1.017027884721756, |
| "epoch": 1.900726392251816, |
| "grad_norm": 0.1760513335466385, |
| "learning_rate": 1.667150513144856e-05, |
| "loss": 1.0226783752441406, |
| "mean_token_accuracy": 0.691545270383358, |
| "num_tokens": 19036103.0, |
| "step": 197 |
| }, |
| { |
| "entropy": 1.0095921084284782, |
| "epoch": 1.910411622276029, |
| "grad_norm": 0.1807909458875656, |
| "learning_rate": 1.6421798432711345e-05, |
| "loss": 1.004764437675476, |
| "mean_token_accuracy": 0.6964360028505325, |
| "num_tokens": 19131869.0, |
| "step": 198 |
| }, |
| { |
| "entropy": 1.0117909163236618, |
| "epoch": 1.9200968523002422, |
| "grad_norm": 0.18069379031658173, |
| "learning_rate": 1.617305802621748e-05, |
| "loss": 0.9964424967765808, |
| "mean_token_accuracy": 0.6977855116128922, |
| "num_tokens": 19229332.0, |
| "step": 199 |
| }, |
| { |
| "entropy": 1.0152455270290375, |
| "epoch": 1.9297820823244551, |
| "grad_norm": 0.1750374287366867, |
| "learning_rate": 1.5925311931351172e-05, |
| "loss": 1.0085126161575317, |
| "mean_token_accuracy": 0.6957272365689278, |
| "num_tokens": 19326511.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 1.0058443173766136, |
| "epoch": 1.9394673123486683, |
| "grad_norm": 0.17271851003170013, |
| "learning_rate": 1.567858805549229e-05, |
| "loss": 0.9887601733207703, |
| "mean_token_accuracy": 0.6980008259415627, |
| "num_tokens": 19423560.0, |
| "step": 201 |
| }, |
| { |
| "entropy": 1.0228681191802025, |
| "epoch": 1.9491525423728815, |
| "grad_norm": 0.17884734272956848, |
| "learning_rate": 1.5432914190872757e-05, |
| "loss": 1.0131609439849854, |
| "mean_token_accuracy": 0.692680798470974, |
| "num_tokens": 19520842.0, |
| "step": 202 |
| }, |
| { |
| "entropy": 1.0089232549071312, |
| "epoch": 1.9588377723970944, |
| "grad_norm": 0.16985908150672913, |
| "learning_rate": 1.5188318011445906e-05, |
| "loss": 1.0013556480407715, |
| "mean_token_accuracy": 0.6970010101795197, |
| "num_tokens": 19618823.0, |
| "step": 203 |
| }, |
| { |
| "entropy": 1.0016749277710915, |
| "epoch": 1.9685230024213074, |
| "grad_norm": 0.1778869777917862, |
| "learning_rate": 1.4944827069769123e-05, |
| "loss": 0.9919571876525879, |
| "mean_token_accuracy": 0.7001852169632912, |
| "num_tokens": 19716713.0, |
| "step": 204 |
| }, |
| { |
| "entropy": 1.0164751634001732, |
| "epoch": 1.9782082324455206, |
| "grad_norm": 0.18251122534275055, |
| "learning_rate": 1.4702468793900188e-05, |
| "loss": 1.0077866315841675, |
| "mean_token_accuracy": 0.6937248483300209, |
| "num_tokens": 19813324.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 1.0116839110851288, |
| "epoch": 1.9878934624697338, |
| "grad_norm": 0.17308309674263, |
| "learning_rate": 1.4461270484307643e-05, |
| "loss": 1.0083445310592651, |
| "mean_token_accuracy": 0.6930299252271652, |
| "num_tokens": 19910449.0, |
| "step": 206 |
| }, |
| { |
| "entropy": 1.0046918392181396, |
| "epoch": 1.9975786924939467, |
| "grad_norm": 0.17221423983573914, |
| "learning_rate": 1.4221259310795543e-05, |
| "loss": 0.9961509704589844, |
| "mean_token_accuracy": 0.6965227276086807, |
| "num_tokens": 20008513.0, |
| "step": 207 |
| }, |
| { |
| "entropy": 1.0230849385261536, |
| "epoch": 2.0, |
| "grad_norm": 0.35064876079559326, |
| "learning_rate": 1.3982462309442889e-05, |
| "loss": 1.0117878913879395, |
| "mean_token_accuracy": 0.6928033828735352, |
| "num_tokens": 20032830.0, |
| "step": 208 |
| }, |
| { |
| "entropy": 0.9964845478534698, |
| "epoch": 2.009685230024213, |
| "grad_norm": 0.17636848986148834, |
| "learning_rate": 1.3744906379558165e-05, |
| "loss": 0.9579638242721558, |
| "mean_token_accuracy": 0.705834411084652, |
| "num_tokens": 20129870.0, |
| "step": 209 |
| }, |
| { |
| "entropy": 1.0106598287820816, |
| "epoch": 2.0193704600484264, |
| "grad_norm": 0.1803821325302124, |
| "learning_rate": 1.3508618280649255e-05, |
| "loss": 0.9775141477584839, |
| "mean_token_accuracy": 0.7011803910136223, |
| "num_tokens": 20226728.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 1.0030332654714584, |
| "epoch": 2.029055690072639, |
| "grad_norm": 0.18877284228801727, |
| "learning_rate": 1.3273624629409082e-05, |
| "loss": 0.9775636196136475, |
| "mean_token_accuracy": 0.7004503831267357, |
| "num_tokens": 20321345.0, |
| "step": 211 |
| }, |
| { |
| "entropy": 1.0126233249902725, |
| "epoch": 2.0387409200968523, |
| "grad_norm": 0.18291965126991272, |
| "learning_rate": 1.3039951896717445e-05, |
| "loss": 0.9895316362380981, |
| "mean_token_accuracy": 0.6989523768424988, |
| "num_tokens": 20418998.0, |
| "step": 212 |
| }, |
| { |
| "entropy": 0.994785726070404, |
| "epoch": 2.0484261501210654, |
| "grad_norm": 0.17805488407611847, |
| "learning_rate": 1.2807626404659142e-05, |
| "loss": 0.9779917597770691, |
| "mean_token_accuracy": 0.7008749172091484, |
| "num_tokens": 20516839.0, |
| "step": 213 |
| }, |
| { |
| "entropy": 0.981712318956852, |
| "epoch": 2.0581113801452786, |
| "grad_norm": 0.1821916103363037, |
| "learning_rate": 1.2576674323558929e-05, |
| "loss": 0.9739880561828613, |
| "mean_token_accuracy": 0.7004686295986176, |
| "num_tokens": 20614245.0, |
| "step": 214 |
| }, |
| { |
| "entropy": 0.9724540486931801, |
| "epoch": 2.0677966101694913, |
| "grad_norm": 0.18674227595329285, |
| "learning_rate": 1.234712166903359e-05, |
| "loss": 0.9675310850143433, |
| "mean_token_accuracy": 0.7027364075183868, |
| "num_tokens": 20711954.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 0.9729701578617096, |
| "epoch": 2.0774818401937045, |
| "grad_norm": 0.18655931949615479, |
| "learning_rate": 1.2118994299061376e-05, |
| "loss": 0.9668871760368347, |
| "mean_token_accuracy": 0.7026202082633972, |
| "num_tokens": 20807522.0, |
| "step": 216 |
| }, |
| { |
| "entropy": 0.9427368491888046, |
| "epoch": 2.0871670702179177, |
| "grad_norm": 0.17658740282058716, |
| "learning_rate": 1.1892317911069212e-05, |
| "loss": 0.9401254653930664, |
| "mean_token_accuracy": 0.709912471473217, |
| "num_tokens": 20905595.0, |
| "step": 217 |
| }, |
| { |
| "entropy": 0.9661683440208435, |
| "epoch": 2.096852300242131, |
| "grad_norm": 0.18123148381710052, |
| "learning_rate": 1.1667118039038064e-05, |
| "loss": 0.9703402519226074, |
| "mean_token_accuracy": 0.7052091136574745, |
| "num_tokens": 21002063.0, |
| "step": 218 |
| }, |
| { |
| "entropy": 0.9760492444038391, |
| "epoch": 2.106537530266344, |
| "grad_norm": 0.18296928703784943, |
| "learning_rate": 1.1443420050626625e-05, |
| "loss": 0.9792553782463074, |
| "mean_token_accuracy": 0.6997263431549072, |
| "num_tokens": 21099209.0, |
| "step": 219 |
| }, |
| { |
| "entropy": 0.9762522503733635, |
| "epoch": 2.116222760290557, |
| "grad_norm": 0.18274007737636566, |
| "learning_rate": 1.1221249144313778e-05, |
| "loss": 0.9795980453491211, |
| "mean_token_accuracy": 0.7015334367752075, |
| "num_tokens": 21196971.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.9688016548752785, |
| "epoch": 2.12590799031477, |
| "grad_norm": 0.1775023192167282, |
| "learning_rate": 1.1000630346560117e-05, |
| "loss": 0.9678329229354858, |
| "mean_token_accuracy": 0.7037922069430351, |
| "num_tokens": 21294641.0, |
| "step": 221 |
| }, |
| { |
| "entropy": 0.9825037941336632, |
| "epoch": 2.135593220338983, |
| "grad_norm": 0.1812477856874466, |
| "learning_rate": 1.078158850898883e-05, |
| "loss": 0.9817320108413696, |
| "mean_token_accuracy": 0.699578233063221, |
| "num_tokens": 21391604.0, |
| "step": 222 |
| }, |
| { |
| "entropy": 0.9769124090671539, |
| "epoch": 2.1452784503631963, |
| "grad_norm": 0.1791737824678421, |
| "learning_rate": 1.0564148305586296e-05, |
| "loss": 0.9674513339996338, |
| "mean_token_accuracy": 0.7023534849286079, |
| "num_tokens": 21488724.0, |
| "step": 223 |
| }, |
| { |
| "entropy": 1.0039660334587097, |
| "epoch": 2.154963680387409, |
| "grad_norm": 0.1795329749584198, |
| "learning_rate": 1.0348334229922677e-05, |
| "loss": 0.9883779287338257, |
| "mean_token_accuracy": 0.697204701602459, |
| "num_tokens": 21585010.0, |
| "step": 224 |
| }, |
| { |
| "entropy": 0.974880613386631, |
| "epoch": 2.164648910411622, |
| "grad_norm": 0.18022607266902924, |
| "learning_rate": 1.0134170592392836e-05, |
| "loss": 0.9638246297836304, |
| "mean_token_accuracy": 0.7034358531236649, |
| "num_tokens": 21682815.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 0.9704831093549728, |
| "epoch": 2.1743341404358354, |
| "grad_norm": 0.17907658219337463, |
| "learning_rate": 9.9216815174779e-06, |
| "loss": 0.9586762189865112, |
| "mean_token_accuracy": 0.7059309855103493, |
| "num_tokens": 21780813.0, |
| "step": 226 |
| }, |
| { |
| "entropy": 0.9787583351135254, |
| "epoch": 2.1840193704600486, |
| "grad_norm": 0.17604723572731018, |
| "learning_rate": 9.710890941027722e-06, |
| "loss": 0.9592881202697754, |
| "mean_token_accuracy": 0.7065609246492386, |
| "num_tokens": 21876431.0, |
| "step": 227 |
| }, |
| { |
| "entropy": 0.997703529894352, |
| "epoch": 2.1937046004842613, |
| "grad_norm": 0.1816512644290924, |
| "learning_rate": 9.501822607564678e-06, |
| "loss": 0.983452320098877, |
| "mean_token_accuracy": 0.7003907486796379, |
| "num_tokens": 21974059.0, |
| "step": 228 |
| }, |
| { |
| "entropy": 0.9781674444675446, |
| "epoch": 2.2033898305084745, |
| "grad_norm": 0.17929424345493317, |
| "learning_rate": 9.29450006760894e-06, |
| "loss": 0.9610666632652283, |
| "mean_token_accuracy": 0.704089567065239, |
| "num_tokens": 22071550.0, |
| "step": 229 |
| }, |
| { |
| "entropy": 0.9733332246541977, |
| "epoch": 2.2130750605326877, |
| "grad_norm": 0.17849525809288025, |
| "learning_rate": 9.088946675025605e-06, |
| "loss": 0.9660186171531677, |
| "mean_token_accuracy": 0.7035543248057365, |
| "num_tokens": 22169195.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.9842173457145691, |
| "epoch": 2.222760290556901, |
| "grad_norm": 0.19081687927246094, |
| "learning_rate": 8.88518558439402e-06, |
| "loss": 0.9738259315490723, |
| "mean_token_accuracy": 0.700490303337574, |
| "num_tokens": 22264238.0, |
| "step": 231 |
| }, |
| { |
| "entropy": 0.9491748958826065, |
| "epoch": 2.232445520581114, |
| "grad_norm": 0.17600634694099426, |
| "learning_rate": 8.683239748399539e-06, |
| "loss": 0.9415581226348877, |
| "mean_token_accuracy": 0.7125281170010567, |
| "num_tokens": 22361030.0, |
| "step": 232 |
| }, |
| { |
| "entropy": 0.9827496632933617, |
| "epoch": 2.2421307506053267, |
| "grad_norm": 0.18011201918125153, |
| "learning_rate": 8.483131915247968e-06, |
| "loss": 0.9686768054962158, |
| "mean_token_accuracy": 0.7024280056357384, |
| "num_tokens": 22458625.0, |
| "step": 233 |
| }, |
| { |
| "entropy": 0.9476987347006798, |
| "epoch": 2.25181598062954, |
| "grad_norm": 0.18301460146903992, |
| "learning_rate": 8.284884626103165e-06, |
| "loss": 0.9361698031425476, |
| "mean_token_accuracy": 0.7130703330039978, |
| "num_tokens": 22555860.0, |
| "step": 234 |
| }, |
| { |
| "entropy": 0.9788018614053726, |
| "epoch": 2.261501210653753, |
| "grad_norm": 0.2318762242794037, |
| "learning_rate": 8.088520212547831e-06, |
| "loss": 0.9733133316040039, |
| "mean_token_accuracy": 0.7013382613658905, |
| "num_tokens": 22653497.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 0.9619165509939194, |
| "epoch": 2.2711864406779663, |
| "grad_norm": 0.17698800563812256, |
| "learning_rate": 7.894060794067987e-06, |
| "loss": 0.96214759349823, |
| "mean_token_accuracy": 0.7057057321071625, |
| "num_tokens": 22750035.0, |
| "step": 236 |
| }, |
| { |
| "entropy": 0.9869695082306862, |
| "epoch": 2.280871670702179, |
| "grad_norm": 0.2705877721309662, |
| "learning_rate": 7.701528275561348e-06, |
| "loss": 0.9887737035751343, |
| "mean_token_accuracy": 0.6977095082402229, |
| "num_tokens": 22846771.0, |
| "step": 237 |
| }, |
| { |
| "entropy": 0.9492938369512558, |
| "epoch": 2.290556900726392, |
| "grad_norm": 0.18406817317008972, |
| "learning_rate": 7.510944344869774e-06, |
| "loss": 0.94698166847229, |
| "mean_token_accuracy": 0.7091076523065567, |
| "num_tokens": 22940363.0, |
| "step": 238 |
| }, |
| { |
| "entropy": 0.9718275740742683, |
| "epoch": 2.3002421307506054, |
| "grad_norm": 0.17744125425815582, |
| "learning_rate": 7.3223304703363135e-06, |
| "loss": 0.9602268934249878, |
| "mean_token_accuracy": 0.7047717645764351, |
| "num_tokens": 23037771.0, |
| "step": 239 |
| }, |
| { |
| "entropy": 0.997263103723526, |
| "epoch": 2.3099273607748185, |
| "grad_norm": 0.17902712523937225, |
| "learning_rate": 7.13570789838687e-06, |
| "loss": 0.9941853880882263, |
| "mean_token_accuracy": 0.6950124651193619, |
| "num_tokens": 23135752.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.9768236577510834, |
| "epoch": 2.3196125907990313, |
| "grad_norm": 0.1829724907875061, |
| "learning_rate": 6.951097651136889e-06, |
| "loss": 0.9629150629043579, |
| "mean_token_accuracy": 0.7058604136109352, |
| "num_tokens": 23231870.0, |
| "step": 241 |
| }, |
| { |
| "entropy": 0.963948056101799, |
| "epoch": 2.3292978208232444, |
| "grad_norm": 0.17480851709842682, |
| "learning_rate": 6.768520524023348e-06, |
| "loss": 0.9460391998291016, |
| "mean_token_accuracy": 0.7081798017024994, |
| "num_tokens": 23330052.0, |
| "step": 242 |
| }, |
| { |
| "entropy": 0.9842232093214989, |
| "epoch": 2.3389830508474576, |
| "grad_norm": 0.1877422034740448, |
| "learning_rate": 6.587997083462197e-06, |
| "loss": 0.9799100756645203, |
| "mean_token_accuracy": 0.701549656689167, |
| "num_tokens": 23427424.0, |
| "step": 243 |
| }, |
| { |
| "entropy": 0.9613497108221054, |
| "epoch": 2.348668280871671, |
| "grad_norm": 0.18304583430290222, |
| "learning_rate": 6.4095476645317346e-06, |
| "loss": 0.9574179649353027, |
| "mean_token_accuracy": 0.7060347571969032, |
| "num_tokens": 23524347.0, |
| "step": 244 |
| }, |
| { |
| "entropy": 0.9711159467697144, |
| "epoch": 2.358353510895884, |
| "grad_norm": 0.1803869903087616, |
| "learning_rate": 6.23319236868189e-06, |
| "loss": 0.965959906578064, |
| "mean_token_accuracy": 0.7031628713011742, |
| "num_tokens": 23621709.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 0.9694511815905571, |
| "epoch": 2.3680387409200967, |
| "grad_norm": 0.177644744515419, |
| "learning_rate": 6.058951061469931e-06, |
| "loss": 0.9606213569641113, |
| "mean_token_accuracy": 0.7050533071160316, |
| "num_tokens": 23718487.0, |
| "step": 246 |
| }, |
| { |
| "entropy": 0.9582285434007645, |
| "epoch": 2.37772397094431, |
| "grad_norm": 0.1824142336845398, |
| "learning_rate": 5.886843370322692e-06, |
| "loss": 0.9482771158218384, |
| "mean_token_accuracy": 0.7099712938070297, |
| "num_tokens": 23815121.0, |
| "step": 247 |
| }, |
| { |
| "entropy": 0.9778466373682022, |
| "epoch": 2.387409200968523, |
| "grad_norm": 0.18152157962322235, |
| "learning_rate": 5.7168886823256355e-06, |
| "loss": 0.9651317596435547, |
| "mean_token_accuracy": 0.7042052671313286, |
| "num_tokens": 23912149.0, |
| "step": 248 |
| }, |
| { |
| "entropy": 0.9690630733966827, |
| "epoch": 2.3970944309927362, |
| "grad_norm": 0.2793174386024475, |
| "learning_rate": 5.549106142039018e-06, |
| "loss": 0.9617438316345215, |
| "mean_token_accuracy": 0.7056540101766586, |
| "num_tokens": 24009273.0, |
| "step": 249 |
| }, |
| { |
| "entropy": 0.9750760719180107, |
| "epoch": 2.406779661016949, |
| "grad_norm": 0.17681074142456055, |
| "learning_rate": 5.38351464934132e-06, |
| "loss": 0.9575906991958618, |
| "mean_token_accuracy": 0.7047781273722649, |
| "num_tokens": 24107354.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.9507534727454185, |
| "epoch": 2.416464891041162, |
| "grad_norm": 0.18025094270706177, |
| "learning_rate": 5.220132857300286e-06, |
| "loss": 0.9377824664115906, |
| "mean_token_accuracy": 0.7107547968626022, |
| "num_tokens": 24204737.0, |
| "step": 251 |
| }, |
| { |
| "entropy": 0.9844745770096779, |
| "epoch": 2.4261501210653753, |
| "grad_norm": 0.17789708077907562, |
| "learning_rate": 5.058979170071754e-06, |
| "loss": 0.9699742197990417, |
| "mean_token_accuracy": 0.7021560966968536, |
| "num_tokens": 24301999.0, |
| "step": 252 |
| }, |
| { |
| "entropy": 0.9685339778661728, |
| "epoch": 2.4358353510895885, |
| "grad_norm": 0.17267119884490967, |
| "learning_rate": 4.900071740826489e-06, |
| "loss": 0.9629323482513428, |
| "mean_token_accuracy": 0.7057926878333092, |
| "num_tokens": 24398022.0, |
| "step": 253 |
| }, |
| { |
| "entropy": 0.965476855635643, |
| "epoch": 2.4455205811138017, |
| "grad_norm": 0.18101957440376282, |
| "learning_rate": 4.743428469705335e-06, |
| "loss": 0.955784022808075, |
| "mean_token_accuracy": 0.7057157456874847, |
| "num_tokens": 24494712.0, |
| "step": 254 |
| }, |
| { |
| "entropy": 0.9631841853260994, |
| "epoch": 2.4552058111380144, |
| "grad_norm": 0.17928491532802582, |
| "learning_rate": 4.58906700180286e-06, |
| "loss": 0.9480952024459839, |
| "mean_token_accuracy": 0.7076999545097351, |
| "num_tokens": 24591559.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 0.9611305594444275, |
| "epoch": 2.4648910411622276, |
| "grad_norm": 0.17541737854480743, |
| "learning_rate": 4.437004725179713e-06, |
| "loss": 0.9549427032470703, |
| "mean_token_accuracy": 0.7060576677322388, |
| "num_tokens": 24689494.0, |
| "step": 256 |
| }, |
| { |
| "entropy": 0.9543889611959457, |
| "epoch": 2.4745762711864407, |
| "grad_norm": 0.1807403564453125, |
| "learning_rate": 4.2872587689039484e-06, |
| "loss": 0.9523176550865173, |
| "mean_token_accuracy": 0.7074451968073845, |
| "num_tokens": 24786283.0, |
| "step": 257 |
| }, |
| { |
| "entropy": 0.9686412364244461, |
| "epoch": 2.484261501210654, |
| "grad_norm": 0.19152818620204926, |
| "learning_rate": 4.139846001121514e-06, |
| "loss": 0.9642741680145264, |
| "mean_token_accuracy": 0.7037565931677818, |
| "num_tokens": 24883368.0, |
| "step": 258 |
| }, |
| { |
| "entropy": 0.9706502631306648, |
| "epoch": 2.4939467312348667, |
| "grad_norm": 0.18040058016777039, |
| "learning_rate": 3.9947830271561435e-06, |
| "loss": 0.9643933773040771, |
| "mean_token_accuracy": 0.7022472470998764, |
| "num_tokens": 24979284.0, |
| "step": 259 |
| }, |
| { |
| "entropy": 0.9656544327735901, |
| "epoch": 2.50363196125908, |
| "grad_norm": 0.17672894895076752, |
| "learning_rate": 3.852086187638846e-06, |
| "loss": 0.9573478102684021, |
| "mean_token_accuracy": 0.7059909179806709, |
| "num_tokens": 25076441.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.9618352204561234, |
| "epoch": 2.513317191283293, |
| "grad_norm": 0.1795944720506668, |
| "learning_rate": 3.711771556667218e-06, |
| "loss": 0.9508000612258911, |
| "mean_token_accuracy": 0.7096266373991966, |
| "num_tokens": 25174061.0, |
| "step": 261 |
| }, |
| { |
| "entropy": 0.9842494279146194, |
| "epoch": 2.523002421307506, |
| "grad_norm": 0.17950080335140228, |
| "learning_rate": 3.57385493999477e-06, |
| "loss": 0.9755753874778748, |
| "mean_token_accuracy": 0.7001539990305901, |
| "num_tokens": 25272103.0, |
| "step": 262 |
| }, |
| { |
| "entropy": 0.9461641684174538, |
| "epoch": 2.5326876513317194, |
| "grad_norm": 0.18211127817630768, |
| "learning_rate": 3.438351873250492e-06, |
| "loss": 0.9435604810714722, |
| "mean_token_accuracy": 0.7120839208364487, |
| "num_tokens": 25368715.0, |
| "step": 263 |
| }, |
| { |
| "entropy": 0.9493983089923859, |
| "epoch": 2.542372881355932, |
| "grad_norm": 0.17652387917041779, |
| "learning_rate": 3.305277620188826e-06, |
| "loss": 0.9497734904289246, |
| "mean_token_accuracy": 0.7066553607583046, |
| "num_tokens": 25466014.0, |
| "step": 264 |
| }, |
| { |
| "entropy": 0.9618336409330368, |
| "epoch": 2.5520581113801453, |
| "grad_norm": 0.2031353861093521, |
| "learning_rate": 3.1746471709702964e-06, |
| "loss": 0.9585392475128174, |
| "mean_token_accuracy": 0.7073178961873055, |
| "num_tokens": 25563415.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 0.979316346347332, |
| "epoch": 2.5617433414043584, |
| "grad_norm": 0.18086563050746918, |
| "learning_rate": 3.0464752404729484e-06, |
| "loss": 0.975259006023407, |
| "mean_token_accuracy": 0.6986003741621971, |
| "num_tokens": 25661061.0, |
| "step": 266 |
| }, |
| { |
| "entropy": 0.9475531205534935, |
| "epoch": 2.571428571428571, |
| "grad_norm": 0.1784556657075882, |
| "learning_rate": 2.920776266634767e-06, |
| "loss": 0.9324929118156433, |
| "mean_token_accuracy": 0.7109888419508934, |
| "num_tokens": 25757833.0, |
| "step": 267 |
| }, |
| { |
| "entropy": 0.9776372313499451, |
| "epoch": 2.5811138014527844, |
| "grad_norm": 0.18078093230724335, |
| "learning_rate": 2.797564408827319e-06, |
| "loss": 0.963403582572937, |
| "mean_token_accuracy": 0.7044354677200317, |
| "num_tokens": 25853862.0, |
| "step": 268 |
| }, |
| { |
| "entropy": 0.9847007617354393, |
| "epoch": 2.5907990314769975, |
| "grad_norm": 0.17774543166160583, |
| "learning_rate": 2.676853546260791e-06, |
| "loss": 0.9728066921234131, |
| "mean_token_accuracy": 0.7033195123076439, |
| "num_tokens": 25951398.0, |
| "step": 269 |
| }, |
| { |
| "entropy": 0.9523753523826599, |
| "epoch": 2.6004842615012107, |
| "grad_norm": 0.1763666272163391, |
| "learning_rate": 2.558657276420526e-06, |
| "loss": 0.94881671667099, |
| "mean_token_accuracy": 0.7090617269277573, |
| "num_tokens": 26049292.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.9992275238037109, |
| "epoch": 2.610169491525424, |
| "grad_norm": 0.1775253713130951, |
| "learning_rate": 2.442988913535374e-06, |
| "loss": 0.9929525852203369, |
| "mean_token_accuracy": 0.6952389478683472, |
| "num_tokens": 26146570.0, |
| "step": 271 |
| }, |
| { |
| "entropy": 0.9768842831254005, |
| "epoch": 2.619854721549637, |
| "grad_norm": 0.18197324872016907, |
| "learning_rate": 2.3298614870778835e-06, |
| "loss": 0.9748570322990417, |
| "mean_token_accuracy": 0.7011555060744286, |
| "num_tokens": 26244193.0, |
| "step": 272 |
| }, |
| { |
| "entropy": 0.9624940007925034, |
| "epoch": 2.62953995157385, |
| "grad_norm": 0.1776597946882248, |
| "learning_rate": 2.219287740296605e-06, |
| "loss": 0.9518307447433472, |
| "mean_token_accuracy": 0.7069382146000862, |
| "num_tokens": 26341731.0, |
| "step": 273 |
| }, |
| { |
| "entropy": 0.9795135259628296, |
| "epoch": 2.639225181598063, |
| "grad_norm": 0.20650646090507507, |
| "learning_rate": 2.1112801287806378e-06, |
| "loss": 0.9681733846664429, |
| "mean_token_accuracy": 0.7024837136268616, |
| "num_tokens": 26438264.0, |
| "step": 274 |
| }, |
| { |
| "entropy": 0.966120146214962, |
| "epoch": 2.648910411622276, |
| "grad_norm": 0.18002614378929138, |
| "learning_rate": 2.0058508190565315e-06, |
| "loss": 0.9650594592094421, |
| "mean_token_accuracy": 0.7058759182691574, |
| "num_tokens": 26536362.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 0.9701863154768944, |
| "epoch": 2.658595641646489, |
| "grad_norm": 0.1820772886276245, |
| "learning_rate": 1.9030116872178316e-06, |
| "loss": 0.9537088871002197, |
| "mean_token_accuracy": 0.7048317566514015, |
| "num_tokens": 26633878.0, |
| "step": 276 |
| }, |
| { |
| "entropy": 0.9413173869252205, |
| "epoch": 2.668280871670702, |
| "grad_norm": 0.1845010668039322, |
| "learning_rate": 1.8027743175872664e-06, |
| "loss": 0.930335283279419, |
| "mean_token_accuracy": 0.7123815342783928, |
| "num_tokens": 26731252.0, |
| "step": 277 |
| }, |
| { |
| "entropy": 0.9709818363189697, |
| "epoch": 2.6779661016949152, |
| "grad_norm": 0.18073733150959015, |
| "learning_rate": 1.7051500014118454e-06, |
| "loss": 0.9600517153739929, |
| "mean_token_accuracy": 0.7052488699555397, |
| "num_tokens": 26827337.0, |
| "step": 278 |
| }, |
| { |
| "entropy": 0.9786422699689865, |
| "epoch": 2.6876513317191284, |
| "grad_norm": 0.17675380408763885, |
| "learning_rate": 1.610149735590949e-06, |
| "loss": 0.9669743776321411, |
| "mean_token_accuracy": 0.7031452357769012, |
| "num_tokens": 26924020.0, |
| "step": 279 |
| }, |
| { |
| "entropy": 0.9676607623696327, |
| "epoch": 2.6973365617433416, |
| "grad_norm": 0.1773083359003067, |
| "learning_rate": 1.517784221437568e-06, |
| "loss": 0.9580140113830566, |
| "mean_token_accuracy": 0.7057247683405876, |
| "num_tokens": 27020699.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.9538565576076508, |
| "epoch": 2.7070217917675548, |
| "grad_norm": 0.17378197610378265, |
| "learning_rate": 1.428063863472895e-06, |
| "loss": 0.9394268989562988, |
| "mean_token_accuracy": 0.7104142755270004, |
| "num_tokens": 27117563.0, |
| "step": 281 |
| }, |
| { |
| "entropy": 0.9721490517258644, |
| "epoch": 2.7167070217917675, |
| "grad_norm": 0.1738930642604828, |
| "learning_rate": 1.3409987682542619e-06, |
| "loss": 0.9649605751037598, |
| "mean_token_accuracy": 0.70272546261549, |
| "num_tokens": 27215426.0, |
| "step": 282 |
| }, |
| { |
| "entropy": 0.9914449229836464, |
| "epoch": 2.7263922518159807, |
| "grad_norm": 0.18021667003631592, |
| "learning_rate": 1.2565987432367033e-06, |
| "loss": 0.9891276359558105, |
| "mean_token_accuracy": 0.6978868618607521, |
| "num_tokens": 27312182.0, |
| "step": 283 |
| }, |
| { |
| "entropy": 0.9563105776906013, |
| "epoch": 2.736077481840194, |
| "grad_norm": 0.17998550832271576, |
| "learning_rate": 1.1748732956682025e-06, |
| "loss": 0.9561561346054077, |
| "mean_token_accuracy": 0.7088183015584946, |
| "num_tokens": 27409659.0, |
| "step": 284 |
| }, |
| { |
| "entropy": 0.9712988957762718, |
| "epoch": 2.7457627118644066, |
| "grad_norm": 0.17391616106033325, |
| "learning_rate": 1.095831631518729e-06, |
| "loss": 0.9587939977645874, |
| "mean_token_accuracy": 0.7066119387745857, |
| "num_tokens": 27507879.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 0.9707677364349365, |
| "epoch": 2.7554479418886197, |
| "grad_norm": 0.17616266012191772, |
| "learning_rate": 1.0194826544432518e-06, |
| "loss": 0.9611558318138123, |
| "mean_token_accuracy": 0.7038435861468315, |
| "num_tokens": 27604015.0, |
| "step": 286 |
| }, |
| { |
| "entropy": 0.9944893270730972, |
| "epoch": 2.765133171912833, |
| "grad_norm": 0.17953266203403473, |
| "learning_rate": 9.458349647787662e-07, |
| "loss": 0.9858497977256775, |
| "mean_token_accuracy": 0.7003906443715096, |
| "num_tokens": 27701604.0, |
| "step": 287 |
| }, |
| { |
| "entropy": 0.9667356237769127, |
| "epoch": 2.774818401937046, |
| "grad_norm": 0.1791837066411972, |
| "learning_rate": 8.748968585755274e-07, |
| "loss": 0.9597692489624023, |
| "mean_token_accuracy": 0.7067226842045784, |
| "num_tokens": 27799036.0, |
| "step": 288 |
| }, |
| { |
| "entropy": 0.9621480256319046, |
| "epoch": 2.7845036319612593, |
| "grad_norm": 0.17390349507331848, |
| "learning_rate": 8.066763266625282e-07, |
| "loss": 0.9528490900993347, |
| "mean_token_accuracy": 0.7082757875323296, |
| "num_tokens": 27896645.0, |
| "step": 289 |
| }, |
| { |
| "entropy": 0.9826484322547913, |
| "epoch": 2.794188861985472, |
| "grad_norm": 0.1810206174850464, |
| "learning_rate": 7.411810537473752e-07, |
| "loss": 0.978987455368042, |
| "mean_token_accuracy": 0.7006519734859467, |
| "num_tokens": 27992284.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.9421405792236328, |
| "epoch": 2.803874092009685, |
| "grad_norm": 0.1830003559589386, |
| "learning_rate": 6.784184175506358e-07, |
| "loss": 0.9335393905639648, |
| "mean_token_accuracy": 0.7116543427109718, |
| "num_tokens": 28086308.0, |
| "step": 291 |
| }, |
| { |
| "entropy": 0.9940215274691582, |
| "epoch": 2.8135593220338984, |
| "grad_norm": 0.18031619489192963, |
| "learning_rate": 6.18395487974796e-07, |
| "loss": 0.9852080345153809, |
| "mean_token_accuracy": 0.6984784379601479, |
| "num_tokens": 28181742.0, |
| "step": 292 |
| }, |
| { |
| "entropy": 0.9698458909988403, |
| "epoch": 2.8232445520581115, |
| "grad_norm": 0.2049950659275055, |
| "learning_rate": 5.611190263078464e-07, |
| "loss": 0.9612412452697754, |
| "mean_token_accuracy": 0.7049182057380676, |
| "num_tokens": 28278865.0, |
| "step": 293 |
| }, |
| { |
| "entropy": 0.9680915996432304, |
| "epoch": 2.8329297820823243, |
| "grad_norm": 0.17655394971370697, |
| "learning_rate": 5.065954844616721e-07, |
| "loss": 0.954717755317688, |
| "mean_token_accuracy": 0.7056088149547577, |
| "num_tokens": 28376330.0, |
| "step": 294 |
| }, |
| { |
| "entropy": 0.9611566066741943, |
| "epoch": 2.8426150121065374, |
| "grad_norm": 0.18384459614753723, |
| "learning_rate": 4.548310042452736e-07, |
| "loss": 0.9458622336387634, |
| "mean_token_accuracy": 0.7086897045373917, |
| "num_tokens": 28473794.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 0.9896327629685402, |
| "epoch": 2.8523002421307506, |
| "grad_norm": 0.17493842542171478, |
| "learning_rate": 4.05831416672911e-07, |
| "loss": 0.981327474117279, |
| "mean_token_accuracy": 0.7018685564398766, |
| "num_tokens": 28571821.0, |
| "step": 296 |
| }, |
| { |
| "entropy": 0.9739344343543053, |
| "epoch": 2.861985472154964, |
| "grad_norm": 0.17228510975837708, |
| "learning_rate": 3.5960224130728857e-07, |
| "loss": 0.966514527797699, |
| "mean_token_accuracy": 0.7024144753813744, |
| "num_tokens": 28669376.0, |
| "step": 297 |
| }, |
| { |
| "entropy": 0.9500202685594559, |
| "epoch": 2.871670702179177, |
| "grad_norm": 0.18412764370441437, |
| "learning_rate": 3.1614868563778487e-07, |
| "loss": 0.9380296468734741, |
| "mean_token_accuracy": 0.7122134119272232, |
| "num_tokens": 28766843.0, |
| "step": 298 |
| }, |
| { |
| "entropy": 0.9886195659637451, |
| "epoch": 2.8813559322033897, |
| "grad_norm": 0.174481600522995, |
| "learning_rate": 2.7547564449386664e-07, |
| "loss": 0.9791684150695801, |
| "mean_token_accuracy": 0.7002565562725067, |
| "num_tokens": 28863956.0, |
| "step": 299 |
| }, |
| { |
| "entropy": 0.9633003771305084, |
| "epoch": 2.891041162227603, |
| "grad_norm": 0.17495881021022797, |
| "learning_rate": 2.3758769949370762e-07, |
| "loss": 0.9534497261047363, |
| "mean_token_accuracy": 0.7069478556513786, |
| "num_tokens": 28961301.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.9598926454782486, |
| "epoch": 2.900726392251816, |
| "grad_norm": 0.18199527263641357, |
| "learning_rate": 2.0248911852807916e-07, |
| "loss": 0.9594986438751221, |
| "mean_token_accuracy": 0.7057793438434601, |
| "num_tokens": 29058457.0, |
| "step": 301 |
| }, |
| { |
| "entropy": 0.9787684008479118, |
| "epoch": 2.910411622276029, |
| "grad_norm": 0.17845535278320312, |
| "learning_rate": 1.7018385527961533e-07, |
| "loss": 0.9728447794914246, |
| "mean_token_accuracy": 0.7033894285559654, |
| "num_tokens": 29155076.0, |
| "step": 302 |
| }, |
| { |
| "entropy": 0.9754829704761505, |
| "epoch": 2.920096852300242, |
| "grad_norm": 0.17794829607009888, |
| "learning_rate": 1.406755487774386e-07, |
| "loss": 0.964917778968811, |
| "mean_token_accuracy": 0.7027197331190109, |
| "num_tokens": 29251719.0, |
| "step": 303 |
| }, |
| { |
| "entropy": 0.9619567468762398, |
| "epoch": 2.929782082324455, |
| "grad_norm": 0.1754407286643982, |
| "learning_rate": 1.1396752298723501e-07, |
| "loss": 0.9576239585876465, |
| "mean_token_accuracy": 0.706841915845871, |
| "num_tokens": 29347947.0, |
| "step": 304 |
| }, |
| { |
| "entropy": 0.9863602966070175, |
| "epoch": 2.9394673123486683, |
| "grad_norm": 0.17757053673267365, |
| "learning_rate": 9.006278643683696e-08, |
| "loss": 0.9789604544639587, |
| "mean_token_accuracy": 0.7016789391636848, |
| "num_tokens": 29445507.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 0.9918009713292122, |
| "epoch": 2.9491525423728815, |
| "grad_norm": 0.18638379871845245, |
| "learning_rate": 6.896403187732215e-08, |
| "loss": 0.9897012710571289, |
| "mean_token_accuracy": 0.6980951949954033, |
| "num_tokens": 29542632.0, |
| "step": 306 |
| }, |
| { |
| "entropy": 0.9726842790842056, |
| "epoch": 2.9588377723970947, |
| "grad_norm": 0.17771297693252563, |
| "learning_rate": 5.0673635979686665e-08, |
| "loss": 0.9664013385772705, |
| "mean_token_accuracy": 0.7052607387304306, |
| "num_tokens": 29639414.0, |
| "step": 307 |
| }, |
| { |
| "entropy": 0.9628136456012726, |
| "epoch": 2.9685230024213074, |
| "grad_norm": 0.1774171143770218, |
| "learning_rate": 3.5193659067131455e-08, |
| "loss": 0.95008385181427, |
| "mean_token_accuracy": 0.7064594179391861, |
| "num_tokens": 29734105.0, |
| "step": 308 |
| }, |
| { |
| "entropy": 0.9817704111337662, |
| "epoch": 2.9782082324455206, |
| "grad_norm": 0.17644129693508148, |
| "learning_rate": 2.2525844882964607e-08, |
| "loss": 0.9797781705856323, |
| "mean_token_accuracy": 0.6994470730423927, |
| "num_tokens": 29832091.0, |
| "step": 309 |
| }, |
| { |
| "entropy": 0.9816061109304428, |
| "epoch": 2.9878934624697338, |
| "grad_norm": 0.17975273728370667, |
| "learning_rate": 1.267162039418901e-08, |
| "loss": 0.976552426815033, |
| "mean_token_accuracy": 0.698183961212635, |
| "num_tokens": 29929348.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.961225301027298, |
| "epoch": 2.9975786924939465, |
| "grad_norm": 0.17494691908359528, |
| "learning_rate": 5.632095630764278e-09, |
| "loss": 0.9551951885223389, |
| "mean_token_accuracy": 0.7057754248380661, |
| "num_tokens": 30025466.0, |
| "step": 311 |
| }, |
| { |
| "entropy": 0.9253799617290497, |
| "epoch": 3.0, |
| "grad_norm": 0.3442399203777313, |
| "learning_rate": 1.4080635605512316e-09, |
| "loss": 0.9125053882598877, |
| "mean_token_accuracy": 0.716167688369751, |
| "num_tokens": 30049245.0, |
| "step": 312 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 312, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 4.2267649894294487e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
