| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.10829103214890017, |
| "eval_steps": 500, |
| "global_step": 4000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 10.69199342727661, |
| "epoch": 0.00013536379018612522, |
| "grad_norm": 11.5625, |
| "learning_rate": 2e-06, |
| "loss": 10.8479, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 12791.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 10.691878128051759, |
| "epoch": 0.00027072758037225043, |
| "grad_norm": 11.0, |
| "learning_rate": 4.5e-06, |
| "loss": 10.8142, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 26683.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 10.691429710388183, |
| "epoch": 0.0004060913705583756, |
| "grad_norm": 9.3125, |
| "learning_rate": 7e-06, |
| "loss": 10.5672, |
| "mean_token_accuracy": 0.011101403925567865, |
| "num_tokens": 39347.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 10.686277675628663, |
| "epoch": 0.0005414551607445009, |
| "grad_norm": 5.375, |
| "learning_rate": 9.5e-06, |
| "loss": 10.3174, |
| "mean_token_accuracy": 0.030114291980862618, |
| "num_tokens": 54329.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 10.660668087005615, |
| "epoch": 0.0006768189509306261, |
| "grad_norm": 4.09375, |
| "learning_rate": 1.2e-05, |
| "loss": 10.0145, |
| "mean_token_accuracy": 0.032822173461318015, |
| "num_tokens": 67393.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 10.637198734283448, |
| "epoch": 0.0008121827411167512, |
| "grad_norm": 3.0625, |
| "learning_rate": 1.4500000000000002e-05, |
| "loss": 9.8798, |
| "mean_token_accuracy": 0.03450996596366167, |
| "num_tokens": 81383.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 10.631521320343017, |
| "epoch": 0.0009475465313028764, |
| "grad_norm": 2.515625, |
| "learning_rate": 1.7000000000000003e-05, |
| "loss": 9.8183, |
| "mean_token_accuracy": 0.03217146322131157, |
| "num_tokens": 95991.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 10.626516151428223, |
| "epoch": 0.0010829103214890017, |
| "grad_norm": 2.515625, |
| "learning_rate": 1.95e-05, |
| "loss": 9.7088, |
| "mean_token_accuracy": 0.03352573178708553, |
| "num_tokens": 108504.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 10.627447319030761, |
| "epoch": 0.001218274111675127, |
| "grad_norm": 2.1875, |
| "learning_rate": 2.2e-05, |
| "loss": 9.7785, |
| "mean_token_accuracy": 0.030551478266716003, |
| "num_tokens": 123286.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 10.629091835021972, |
| "epoch": 0.0013536379018612521, |
| "grad_norm": 2.296875, |
| "learning_rate": 2.4500000000000003e-05, |
| "loss": 9.6538, |
| "mean_token_accuracy": 0.03104141727089882, |
| "num_tokens": 135493.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 10.618868160247803, |
| "epoch": 0.0014890016920473773, |
| "grad_norm": 2.078125, |
| "learning_rate": 2.7e-05, |
| "loss": 9.6537, |
| "mean_token_accuracy": 0.03736583907157183, |
| "num_tokens": 150376.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 10.596181201934815, |
| "epoch": 0.0016243654822335025, |
| "grad_norm": 2.109375, |
| "learning_rate": 2.95e-05, |
| "loss": 9.5976, |
| "mean_token_accuracy": 0.03170219026505947, |
| "num_tokens": 165805.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 10.606531143188477, |
| "epoch": 0.0017597292724196277, |
| "grad_norm": 2.09375, |
| "learning_rate": 3.2e-05, |
| "loss": 9.4608, |
| "mean_token_accuracy": 0.03743585981428623, |
| "num_tokens": 179043.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 10.577856731414794, |
| "epoch": 0.0018950930626057529, |
| "grad_norm": 2.09375, |
| "learning_rate": 3.4500000000000005e-05, |
| "loss": 9.3947, |
| "mean_token_accuracy": 0.03445138856768608, |
| "num_tokens": 191847.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 10.561034107208252, |
| "epoch": 0.0020304568527918783, |
| "grad_norm": 2.125, |
| "learning_rate": 3.7e-05, |
| "loss": 9.2778, |
| "mean_token_accuracy": 0.03577356971800327, |
| "num_tokens": 207116.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 10.546807861328125, |
| "epoch": 0.0021658206429780035, |
| "grad_norm": 2.03125, |
| "learning_rate": 3.95e-05, |
| "loss": 9.2156, |
| "mean_token_accuracy": 0.03288109693676233, |
| "num_tokens": 219651.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 10.532037448883056, |
| "epoch": 0.0023011844331641287, |
| "grad_norm": 2.015625, |
| "learning_rate": 4.2000000000000004e-05, |
| "loss": 9.16, |
| "mean_token_accuracy": 0.03139570262283087, |
| "num_tokens": 233183.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 10.499158573150634, |
| "epoch": 0.002436548223350254, |
| "grad_norm": 2.0625, |
| "learning_rate": 4.45e-05, |
| "loss": 8.9864, |
| "mean_token_accuracy": 0.0376906756311655, |
| "num_tokens": 246291.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 10.423231887817384, |
| "epoch": 0.002571912013536379, |
| "grad_norm": 2.15625, |
| "learning_rate": 4.7000000000000004e-05, |
| "loss": 8.8533, |
| "mean_token_accuracy": 0.04000245779752731, |
| "num_tokens": 259606.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 10.371912956237793, |
| "epoch": 0.0027072758037225042, |
| "grad_norm": 2.0, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 8.7521, |
| "mean_token_accuracy": 0.04012820441275835, |
| "num_tokens": 275174.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 10.304845333099365, |
| "epoch": 0.0028426395939086294, |
| "grad_norm": 2.25, |
| "learning_rate": 5.2e-05, |
| "loss": 8.5952, |
| "mean_token_accuracy": 0.04803745746612549, |
| "num_tokens": 287873.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 10.202454662322998, |
| "epoch": 0.0029780033840947546, |
| "grad_norm": 1.9453125, |
| "learning_rate": 5.45e-05, |
| "loss": 8.4264, |
| "mean_token_accuracy": 0.052891625463962554, |
| "num_tokens": 301243.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 10.146648788452149, |
| "epoch": 0.00311336717428088, |
| "grad_norm": 2.140625, |
| "learning_rate": 5.7e-05, |
| "loss": 8.3599, |
| "mean_token_accuracy": 0.04921769984066486, |
| "num_tokens": 314246.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 9.991413021087647, |
| "epoch": 0.003248730964467005, |
| "grad_norm": 1.671875, |
| "learning_rate": 5.9499999999999996e-05, |
| "loss": 8.1824, |
| "mean_token_accuracy": 0.05792190656065941, |
| "num_tokens": 327131.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 9.899451637268067, |
| "epoch": 0.00338409475465313, |
| "grad_norm": 1.7734375, |
| "learning_rate": 6.2e-05, |
| "loss": 8.0577, |
| "mean_token_accuracy": 0.054864197969436646, |
| "num_tokens": 340932.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 9.722916507720948, |
| "epoch": 0.0035194585448392554, |
| "grad_norm": 1.671875, |
| "learning_rate": 6.450000000000001e-05, |
| "loss": 7.9419, |
| "mean_token_accuracy": 0.05465308241546154, |
| "num_tokens": 355280.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 9.517075347900391, |
| "epoch": 0.0036548223350253805, |
| "grad_norm": 1.546875, |
| "learning_rate": 6.7e-05, |
| "loss": 7.863, |
| "mean_token_accuracy": 0.06392355933785439, |
| "num_tokens": 370159.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 9.312166881561279, |
| "epoch": 0.0037901861252115057, |
| "grad_norm": 1.4609375, |
| "learning_rate": 6.950000000000001e-05, |
| "loss": 7.7284, |
| "mean_token_accuracy": 0.060528535023331644, |
| "num_tokens": 385660.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 9.113211154937744, |
| "epoch": 0.003925549915397631, |
| "grad_norm": 1.3359375, |
| "learning_rate": 7.2e-05, |
| "loss": 7.6437, |
| "mean_token_accuracy": 0.05836181789636612, |
| "num_tokens": 401147.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 8.787345790863037, |
| "epoch": 0.0040609137055837565, |
| "grad_norm": 1.5625, |
| "learning_rate": 7.45e-05, |
| "loss": 7.4136, |
| "mean_token_accuracy": 0.07278152294456959, |
| "num_tokens": 413888.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 8.64449052810669, |
| "epoch": 0.004196277495769882, |
| "grad_norm": 1.40625, |
| "learning_rate": 7.7e-05, |
| "loss": 7.3884, |
| "mean_token_accuracy": 0.06653538607060909, |
| "num_tokens": 427538.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 8.441664218902588, |
| "epoch": 0.004331641285956007, |
| "grad_norm": 2.125, |
| "learning_rate": 7.950000000000001e-05, |
| "loss": 7.3251, |
| "mean_token_accuracy": 0.069814383238554, |
| "num_tokens": 441236.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 8.356950950622558, |
| "epoch": 0.004467005076142132, |
| "grad_norm": 1.3984375, |
| "learning_rate": 8.2e-05, |
| "loss": 7.4254, |
| "mean_token_accuracy": 0.0740208551287651, |
| "num_tokens": 454231.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 8.19385576248169, |
| "epoch": 0.004602368866328257, |
| "grad_norm": 1.5234375, |
| "learning_rate": 8.450000000000001e-05, |
| "loss": 7.2457, |
| "mean_token_accuracy": 0.07566015087068081, |
| "num_tokens": 468791.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 8.173048114776611, |
| "epoch": 0.0047377326565143825, |
| "grad_norm": 1.6328125, |
| "learning_rate": 8.7e-05, |
| "loss": 7.3934, |
| "mean_token_accuracy": 0.06828283667564392, |
| "num_tokens": 481866.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 8.059328603744508, |
| "epoch": 0.004873096446700508, |
| "grad_norm": 1.4296875, |
| "learning_rate": 8.95e-05, |
| "loss": 7.2376, |
| "mean_token_accuracy": 0.07703411132097245, |
| "num_tokens": 495060.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 8.006558561325074, |
| "epoch": 0.005008460236886633, |
| "grad_norm": 1.2890625, |
| "learning_rate": 9.2e-05, |
| "loss": 7.1953, |
| "mean_token_accuracy": 0.07884187921881676, |
| "num_tokens": 508485.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 7.988453817367554, |
| "epoch": 0.005143824027072758, |
| "grad_norm": 1.3984375, |
| "learning_rate": 9.45e-05, |
| "loss": 7.2074, |
| "mean_token_accuracy": 0.07364003024995328, |
| "num_tokens": 522642.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 7.911316013336181, |
| "epoch": 0.005279187817258883, |
| "grad_norm": 1.234375, |
| "learning_rate": 9.7e-05, |
| "loss": 7.1742, |
| "mean_token_accuracy": 0.07427211254835128, |
| "num_tokens": 536967.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 7.899316692352295, |
| "epoch": 0.0054145516074450084, |
| "grad_norm": 1.4296875, |
| "learning_rate": 9.95e-05, |
| "loss": 7.1728, |
| "mean_token_accuracy": 0.0805082306265831, |
| "num_tokens": 548389.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 7.799197435379028, |
| "epoch": 0.005549915397631134, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.000102, |
| "loss": 7.1509, |
| "mean_token_accuracy": 0.07738717347383499, |
| "num_tokens": 560609.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 7.819343090057373, |
| "epoch": 0.005685279187817259, |
| "grad_norm": 1.3046875, |
| "learning_rate": 0.00010449999999999999, |
| "loss": 7.1254, |
| "mean_token_accuracy": 0.07640378400683404, |
| "num_tokens": 574689.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 7.777826452255249, |
| "epoch": 0.005820642978003384, |
| "grad_norm": 1.3515625, |
| "learning_rate": 0.000107, |
| "loss": 7.0691, |
| "mean_token_accuracy": 0.07349300533533096, |
| "num_tokens": 588789.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 7.698786115646362, |
| "epoch": 0.005956006768189509, |
| "grad_norm": 1.3125, |
| "learning_rate": 0.0001095, |
| "loss": 7.1439, |
| "mean_token_accuracy": 0.07730361446738243, |
| "num_tokens": 603609.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 7.7466569423675535, |
| "epoch": 0.006091370558375634, |
| "grad_norm": 1.4453125, |
| "learning_rate": 0.000112, |
| "loss": 7.0113, |
| "mean_token_accuracy": 0.07942908927798271, |
| "num_tokens": 616403.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 7.682626628875733, |
| "epoch": 0.00622673434856176, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0001145, |
| "loss": 7.1202, |
| "mean_token_accuracy": 0.08443130478262902, |
| "num_tokens": 630831.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 7.731028842926025, |
| "epoch": 0.006362098138747885, |
| "grad_norm": 1.5078125, |
| "learning_rate": 0.00011700000000000001, |
| "loss": 7.0225, |
| "mean_token_accuracy": 0.08779790177941323, |
| "num_tokens": 646501.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 7.661398029327392, |
| "epoch": 0.00649746192893401, |
| "grad_norm": 1.8671875, |
| "learning_rate": 0.00011949999999999999, |
| "loss": 7.0941, |
| "mean_token_accuracy": 0.08079206757247448, |
| "num_tokens": 661193.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 7.572637605667114, |
| "epoch": 0.006632825719120135, |
| "grad_norm": 1.734375, |
| "learning_rate": 0.000122, |
| "loss": 7.0787, |
| "mean_token_accuracy": 0.08005881682038307, |
| "num_tokens": 675523.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 7.636332321166992, |
| "epoch": 0.00676818950930626, |
| "grad_norm": 1.5859375, |
| "learning_rate": 0.0001245, |
| "loss": 7.0674, |
| "mean_token_accuracy": 0.07794632315635681, |
| "num_tokens": 691106.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 7.519766235351563, |
| "epoch": 0.0069035532994923855, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.000127, |
| "loss": 6.9381, |
| "mean_token_accuracy": 0.08541512936353683, |
| "num_tokens": 704312.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 7.561954641342163, |
| "epoch": 0.007038917089678511, |
| "grad_norm": 1.4375, |
| "learning_rate": 0.0001295, |
| "loss": 6.9601, |
| "mean_token_accuracy": 0.0883929617702961, |
| "num_tokens": 717026.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 7.570081567764282, |
| "epoch": 0.007174280879864636, |
| "grad_norm": 1.328125, |
| "learning_rate": 0.000132, |
| "loss": 6.9123, |
| "mean_token_accuracy": 0.08829773366451263, |
| "num_tokens": 729605.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 7.463983678817749, |
| "epoch": 0.007309644670050761, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.00013450000000000002, |
| "loss": 6.9353, |
| "mean_token_accuracy": 0.09122553616762161, |
| "num_tokens": 743208.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 7.550097227096558, |
| "epoch": 0.007445008460236886, |
| "grad_norm": 1.2578125, |
| "learning_rate": 0.00013700000000000002, |
| "loss": 6.9287, |
| "mean_token_accuracy": 0.08519787713885307, |
| "num_tokens": 755127.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 7.398041200637818, |
| "epoch": 0.0075803722504230115, |
| "grad_norm": 1.53125, |
| "learning_rate": 0.0001395, |
| "loss": 6.8231, |
| "mean_token_accuracy": 0.08911917060613632, |
| "num_tokens": 769725.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 7.364175844192505, |
| "epoch": 0.007715736040609137, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00014199999999999998, |
| "loss": 6.7527, |
| "mean_token_accuracy": 0.09069294035434723, |
| "num_tokens": 783788.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 7.450532627105713, |
| "epoch": 0.007851099830795263, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0001445, |
| "loss": 6.934, |
| "mean_token_accuracy": 0.08614907264709473, |
| "num_tokens": 797214.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 7.43695821762085, |
| "epoch": 0.007986463620981387, |
| "grad_norm": 1.6328125, |
| "learning_rate": 0.000147, |
| "loss": 6.897, |
| "mean_token_accuracy": 0.09108028039336205, |
| "num_tokens": 809731.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 7.286933469772339, |
| "epoch": 0.008121827411167513, |
| "grad_norm": 1.4296875, |
| "learning_rate": 0.0001495, |
| "loss": 6.8591, |
| "mean_token_accuracy": 0.09137310981750488, |
| "num_tokens": 825021.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 7.2696253776550295, |
| "epoch": 0.008257191201353637, |
| "grad_norm": 1.40625, |
| "learning_rate": 0.000152, |
| "loss": 6.9029, |
| "mean_token_accuracy": 0.09101672545075416, |
| "num_tokens": 839153.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 7.386481237411499, |
| "epoch": 0.008392554991539763, |
| "grad_norm": 1.3984375, |
| "learning_rate": 0.00015450000000000001, |
| "loss": 6.8276, |
| "mean_token_accuracy": 0.08859616219997406, |
| "num_tokens": 853120.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 7.337709522247314, |
| "epoch": 0.008527918781725888, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.000157, |
| "loss": 6.8448, |
| "mean_token_accuracy": 0.08571028485894203, |
| "num_tokens": 867268.0, |
| "step": 315 |
| }, |
| { |
| "entropy": 7.340923023223877, |
| "epoch": 0.008663282571912014, |
| "grad_norm": 1.3515625, |
| "learning_rate": 0.0001595, |
| "loss": 6.8255, |
| "mean_token_accuracy": 0.09267906844615936, |
| "num_tokens": 879062.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 7.282296800613404, |
| "epoch": 0.008798646362098138, |
| "grad_norm": 1.4140625, |
| "learning_rate": 0.000162, |
| "loss": 6.7932, |
| "mean_token_accuracy": 0.09626845642924309, |
| "num_tokens": 892178.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 7.201563024520874, |
| "epoch": 0.008934010152284264, |
| "grad_norm": 1.3125, |
| "learning_rate": 0.00016450000000000001, |
| "loss": 6.671, |
| "mean_token_accuracy": 0.09671695902943611, |
| "num_tokens": 904809.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 7.275315999984741, |
| "epoch": 0.009069373942470389, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.00016700000000000002, |
| "loss": 6.8034, |
| "mean_token_accuracy": 0.09026706293225288, |
| "num_tokens": 917660.0, |
| "step": 335 |
| }, |
| { |
| "entropy": 7.179704904556274, |
| "epoch": 0.009204737732656515, |
| "grad_norm": 1.328125, |
| "learning_rate": 0.00016950000000000003, |
| "loss": 6.6849, |
| "mean_token_accuracy": 0.09763308465480805, |
| "num_tokens": 932773.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 7.1569760799407955, |
| "epoch": 0.009340101522842639, |
| "grad_norm": 1.3359375, |
| "learning_rate": 0.00017199999999999998, |
| "loss": 6.707, |
| "mean_token_accuracy": 0.09705711230635643, |
| "num_tokens": 946688.0, |
| "step": 345 |
| }, |
| { |
| "entropy": 7.123394393920899, |
| "epoch": 0.009475465313028765, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.00017449999999999999, |
| "loss": 6.6188, |
| "mean_token_accuracy": 0.10255519598722458, |
| "num_tokens": 960621.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 7.114657831192017, |
| "epoch": 0.00961082910321489, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.000177, |
| "loss": 6.7525, |
| "mean_token_accuracy": 0.0939077839255333, |
| "num_tokens": 976705.0, |
| "step": 355 |
| }, |
| { |
| "entropy": 7.13629846572876, |
| "epoch": 0.009746192893401015, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.0001795, |
| "loss": 6.6798, |
| "mean_token_accuracy": 0.09904273673892021, |
| "num_tokens": 989175.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 7.18667254447937, |
| "epoch": 0.00988155668358714, |
| "grad_norm": 1.25, |
| "learning_rate": 0.000182, |
| "loss": 6.7875, |
| "mean_token_accuracy": 0.095027344673872, |
| "num_tokens": 1003899.0, |
| "step": 365 |
| }, |
| { |
| "entropy": 7.018054962158203, |
| "epoch": 0.010016920473773266, |
| "grad_norm": 1.4765625, |
| "learning_rate": 0.0001845, |
| "loss": 6.6248, |
| "mean_token_accuracy": 0.09302543699741364, |
| "num_tokens": 1017823.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 7.214749193191528, |
| "epoch": 0.01015228426395939, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.000187, |
| "loss": 6.8025, |
| "mean_token_accuracy": 0.0944581039249897, |
| "num_tokens": 1031556.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 7.06955304145813, |
| "epoch": 0.010287648054145516, |
| "grad_norm": 1.375, |
| "learning_rate": 0.0001895, |
| "loss": 6.6582, |
| "mean_token_accuracy": 0.10281435176730155, |
| "num_tokens": 1044245.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 7.121717023849487, |
| "epoch": 0.01042301184433164, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.000192, |
| "loss": 6.6908, |
| "mean_token_accuracy": 0.09887115061283111, |
| "num_tokens": 1058288.0, |
| "step": 385 |
| }, |
| { |
| "entropy": 7.069799566268921, |
| "epoch": 0.010558375634517767, |
| "grad_norm": 1.546875, |
| "learning_rate": 0.0001945, |
| "loss": 6.623, |
| "mean_token_accuracy": 0.09829980209469795, |
| "num_tokens": 1072234.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 7.062967205047608, |
| "epoch": 0.010693739424703893, |
| "grad_norm": 1.484375, |
| "learning_rate": 0.00019700000000000002, |
| "loss": 6.6287, |
| "mean_token_accuracy": 0.0978606753051281, |
| "num_tokens": 1085463.0, |
| "step": 395 |
| }, |
| { |
| "entropy": 6.952229833602905, |
| "epoch": 0.010829103214890017, |
| "grad_norm": 1.4375, |
| "learning_rate": 0.00019950000000000002, |
| "loss": 6.6629, |
| "mean_token_accuracy": 0.09642241895198822, |
| "num_tokens": 1101393.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 7.105423212051392, |
| "epoch": 0.010964467005076143, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000202, |
| "loss": 6.6263, |
| "mean_token_accuracy": 0.09685642644762993, |
| "num_tokens": 1117150.0, |
| "step": 405 |
| }, |
| { |
| "entropy": 6.972289943695069, |
| "epoch": 0.011099830795262267, |
| "grad_norm": 1.3515625, |
| "learning_rate": 0.00020449999999999998, |
| "loss": 6.6594, |
| "mean_token_accuracy": 0.10496844202280045, |
| "num_tokens": 1130674.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 7.087021827697754, |
| "epoch": 0.011235194585448393, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.000207, |
| "loss": 6.6508, |
| "mean_token_accuracy": 0.09535380229353904, |
| "num_tokens": 1144016.0, |
| "step": 415 |
| }, |
| { |
| "entropy": 6.9751802444458, |
| "epoch": 0.011370558375634518, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0002095, |
| "loss": 6.646, |
| "mean_token_accuracy": 0.09546661153435707, |
| "num_tokens": 1160200.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 7.048429536819458, |
| "epoch": 0.011505922165820644, |
| "grad_norm": 1.484375, |
| "learning_rate": 0.000212, |
| "loss": 6.5651, |
| "mean_token_accuracy": 0.1022900827229023, |
| "num_tokens": 1173266.0, |
| "step": 425 |
| }, |
| { |
| "entropy": 6.974373769760132, |
| "epoch": 0.011641285956006768, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0002145, |
| "loss": 6.6353, |
| "mean_token_accuracy": 0.09445997178554535, |
| "num_tokens": 1187977.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 6.9971846580505375, |
| "epoch": 0.011776649746192894, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.00021700000000000002, |
| "loss": 6.6389, |
| "mean_token_accuracy": 0.09972369968891144, |
| "num_tokens": 1202369.0, |
| "step": 435 |
| }, |
| { |
| "entropy": 6.966669607162475, |
| "epoch": 0.011912013536379018, |
| "grad_norm": 1.3203125, |
| "learning_rate": 0.0002195, |
| "loss": 6.5354, |
| "mean_token_accuracy": 0.09552454426884652, |
| "num_tokens": 1216956.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 6.981910848617554, |
| "epoch": 0.012047377326565144, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.000222, |
| "loss": 6.6403, |
| "mean_token_accuracy": 0.09657183811068534, |
| "num_tokens": 1230958.0, |
| "step": 445 |
| }, |
| { |
| "entropy": 6.972163391113281, |
| "epoch": 0.012182741116751269, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.0002245, |
| "loss": 6.5568, |
| "mean_token_accuracy": 0.1032287061214447, |
| "num_tokens": 1244512.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 6.940069246292114, |
| "epoch": 0.012318104906937395, |
| "grad_norm": 1.5078125, |
| "learning_rate": 0.00022700000000000002, |
| "loss": 6.4972, |
| "mean_token_accuracy": 0.10796320661902428, |
| "num_tokens": 1257469.0, |
| "step": 455 |
| }, |
| { |
| "entropy": 6.870718479156494, |
| "epoch": 0.01245346869712352, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.00022950000000000002, |
| "loss": 6.5861, |
| "mean_token_accuracy": 0.10574530512094497, |
| "num_tokens": 1273533.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 6.932940578460693, |
| "epoch": 0.012588832487309645, |
| "grad_norm": 1.25, |
| "learning_rate": 0.00023200000000000003, |
| "loss": 6.5387, |
| "mean_token_accuracy": 0.10031782239675521, |
| "num_tokens": 1288385.0, |
| "step": 465 |
| }, |
| { |
| "entropy": 6.920595693588257, |
| "epoch": 0.01272419627749577, |
| "grad_norm": 1.3203125, |
| "learning_rate": 0.00023449999999999998, |
| "loss": 6.6012, |
| "mean_token_accuracy": 0.10496116429567337, |
| "num_tokens": 1300721.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 6.878480577468872, |
| "epoch": 0.012859560067681896, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.000237, |
| "loss": 6.4915, |
| "mean_token_accuracy": 0.1057609498500824, |
| "num_tokens": 1313125.0, |
| "step": 475 |
| }, |
| { |
| "entropy": 6.905995321273804, |
| "epoch": 0.01299492385786802, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.0002395, |
| "loss": 6.5534, |
| "mean_token_accuracy": 0.09937024191021919, |
| "num_tokens": 1326226.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 6.928886890411377, |
| "epoch": 0.013130287648054146, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000242, |
| "loss": 6.4614, |
| "mean_token_accuracy": 0.10791765451431275, |
| "num_tokens": 1339932.0, |
| "step": 485 |
| }, |
| { |
| "entropy": 6.82708158493042, |
| "epoch": 0.01326565143824027, |
| "grad_norm": 1.3359375, |
| "learning_rate": 0.0002445, |
| "loss": 6.5553, |
| "mean_token_accuracy": 0.09961838722229004, |
| "num_tokens": 1354015.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 6.846263122558594, |
| "epoch": 0.013401015228426396, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.000247, |
| "loss": 6.5473, |
| "mean_token_accuracy": 0.100076574832201, |
| "num_tokens": 1369333.0, |
| "step": 495 |
| }, |
| { |
| "entropy": 6.777434158325195, |
| "epoch": 0.01353637901861252, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.0002495, |
| "loss": 6.5092, |
| "mean_token_accuracy": 0.10239997878670692, |
| "num_tokens": 1383141.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 6.814955854415894, |
| "epoch": 0.013671742808798647, |
| "grad_norm": 1.2890625, |
| "learning_rate": 0.000252, |
| "loss": 6.5148, |
| "mean_token_accuracy": 0.10957075208425522, |
| "num_tokens": 1398273.0, |
| "step": 505 |
| }, |
| { |
| "entropy": 6.813977956771851, |
| "epoch": 0.013807106598984771, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.0002545, |
| "loss": 6.4406, |
| "mean_token_accuracy": 0.10602880343794822, |
| "num_tokens": 1412562.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 6.782559490203857, |
| "epoch": 0.013942470389170897, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.000257, |
| "loss": 6.4008, |
| "mean_token_accuracy": 0.1101540595293045, |
| "num_tokens": 1426024.0, |
| "step": 515 |
| }, |
| { |
| "entropy": 6.743443441390991, |
| "epoch": 0.014077834179357021, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0002595, |
| "loss": 6.4539, |
| "mean_token_accuracy": 0.10084594711661339, |
| "num_tokens": 1439774.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 6.744311380386352, |
| "epoch": 0.014213197969543147, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.000262, |
| "loss": 6.386, |
| "mean_token_accuracy": 0.11141050532460213, |
| "num_tokens": 1453041.0, |
| "step": 525 |
| }, |
| { |
| "entropy": 6.779989385604859, |
| "epoch": 0.014348561759729272, |
| "grad_norm": 1.25, |
| "learning_rate": 0.00026450000000000003, |
| "loss": 6.3421, |
| "mean_token_accuracy": 0.10815011188387871, |
| "num_tokens": 1466487.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 6.666443109512329, |
| "epoch": 0.014483925549915398, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.00026700000000000004, |
| "loss": 6.4193, |
| "mean_token_accuracy": 0.107712272554636, |
| "num_tokens": 1480142.0, |
| "step": 535 |
| }, |
| { |
| "entropy": 6.692905330657959, |
| "epoch": 0.014619289340101522, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00026950000000000005, |
| "loss": 6.3428, |
| "mean_token_accuracy": 0.1036965548992157, |
| "num_tokens": 1493427.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 6.6241538524627686, |
| "epoch": 0.014754653130287648, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.00027200000000000005, |
| "loss": 6.3301, |
| "mean_token_accuracy": 0.11499745398759842, |
| "num_tokens": 1506055.0, |
| "step": 545 |
| }, |
| { |
| "entropy": 6.726637983322144, |
| "epoch": 0.014890016920473773, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0002745, |
| "loss": 6.4916, |
| "mean_token_accuracy": 0.10548164397478103, |
| "num_tokens": 1519239.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 6.79321608543396, |
| "epoch": 0.015025380710659899, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.000277, |
| "loss": 6.4433, |
| "mean_token_accuracy": 0.10511932224035263, |
| "num_tokens": 1533630.0, |
| "step": 555 |
| }, |
| { |
| "entropy": 6.68529486656189, |
| "epoch": 0.015160744500846023, |
| "grad_norm": 1.4375, |
| "learning_rate": 0.0002795, |
| "loss": 6.3701, |
| "mean_token_accuracy": 0.11614254266023635, |
| "num_tokens": 1546749.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 6.61783242225647, |
| "epoch": 0.015296108291032149, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00028199999999999997, |
| "loss": 6.3126, |
| "mean_token_accuracy": 0.11469681560993195, |
| "num_tokens": 1560568.0, |
| "step": 565 |
| }, |
| { |
| "entropy": 6.697822999954224, |
| "epoch": 0.015431472081218273, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.0002845, |
| "loss": 6.383, |
| "mean_token_accuracy": 0.10437465310096741, |
| "num_tokens": 1574414.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 6.622760200500489, |
| "epoch": 0.0155668358714044, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.000287, |
| "loss": 6.3839, |
| "mean_token_accuracy": 0.10195678994059562, |
| "num_tokens": 1588906.0, |
| "step": 575 |
| }, |
| { |
| "entropy": 6.643900966644287, |
| "epoch": 0.015702199661590525, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0002895, |
| "loss": 6.3656, |
| "mean_token_accuracy": 0.11110272482037545, |
| "num_tokens": 1603181.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 6.722048425674439, |
| "epoch": 0.01583756345177665, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000292, |
| "loss": 6.365, |
| "mean_token_accuracy": 0.1083282358944416, |
| "num_tokens": 1617262.0, |
| "step": 585 |
| }, |
| { |
| "entropy": 6.704953336715699, |
| "epoch": 0.015972927241962774, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.0002945, |
| "loss": 6.4147, |
| "mean_token_accuracy": 0.10933435037732124, |
| "num_tokens": 1631618.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 6.532735300064087, |
| "epoch": 0.016108291032148902, |
| "grad_norm": 1.28125, |
| "learning_rate": 0.000297, |
| "loss": 6.1685, |
| "mean_token_accuracy": 0.11916324943304062, |
| "num_tokens": 1644717.0, |
| "step": 595 |
| }, |
| { |
| "entropy": 6.565193223953247, |
| "epoch": 0.016243654822335026, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0002995, |
| "loss": 6.3201, |
| "mean_token_accuracy": 0.1078986182808876, |
| "num_tokens": 1661888.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 6.5602422714233395, |
| "epoch": 0.01637901861252115, |
| "grad_norm": 1.3203125, |
| "learning_rate": 0.000302, |
| "loss": 6.3369, |
| "mean_token_accuracy": 0.11532969921827316, |
| "num_tokens": 1676103.0, |
| "step": 605 |
| }, |
| { |
| "entropy": 6.621259689331055, |
| "epoch": 0.016514382402707275, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0003045, |
| "loss": 6.3879, |
| "mean_token_accuracy": 0.10770049318671227, |
| "num_tokens": 1690902.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 6.530938911437988, |
| "epoch": 0.016649746192893403, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.000307, |
| "loss": 6.3262, |
| "mean_token_accuracy": 0.11129384264349937, |
| "num_tokens": 1705861.0, |
| "step": 615 |
| }, |
| { |
| "entropy": 6.601020479202271, |
| "epoch": 0.016785109983079527, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0003095, |
| "loss": 6.2688, |
| "mean_token_accuracy": 0.1109300784766674, |
| "num_tokens": 1719893.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 6.542957210540772, |
| "epoch": 0.01692047377326565, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.000312, |
| "loss": 6.2874, |
| "mean_token_accuracy": 0.10827434211969375, |
| "num_tokens": 1733411.0, |
| "step": 625 |
| }, |
| { |
| "entropy": 6.561354637145996, |
| "epoch": 0.017055837563451776, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.0003145, |
| "loss": 6.2397, |
| "mean_token_accuracy": 0.11391478329896927, |
| "num_tokens": 1747374.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 6.587129735946656, |
| "epoch": 0.017191201353637903, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.000317, |
| "loss": 6.3487, |
| "mean_token_accuracy": 0.11469378024339676, |
| "num_tokens": 1761520.0, |
| "step": 635 |
| }, |
| { |
| "entropy": 6.594478893280029, |
| "epoch": 0.017326565143824028, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0003195, |
| "loss": 6.3577, |
| "mean_token_accuracy": 0.10972927659749984, |
| "num_tokens": 1777499.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 6.581266975402832, |
| "epoch": 0.017461928934010152, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.000322, |
| "loss": 6.2463, |
| "mean_token_accuracy": 0.12096798866987228, |
| "num_tokens": 1791308.0, |
| "step": 645 |
| }, |
| { |
| "entropy": 6.4111003398895265, |
| "epoch": 0.017597292724196276, |
| "grad_norm": 1.25, |
| "learning_rate": 0.00032450000000000003, |
| "loss": 6.1953, |
| "mean_token_accuracy": 0.11683537811040878, |
| "num_tokens": 1804545.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 6.54813027381897, |
| "epoch": 0.017732656514382404, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.00032700000000000003, |
| "loss": 6.2866, |
| "mean_token_accuracy": 0.11415853798389435, |
| "num_tokens": 1818499.0, |
| "step": 655 |
| }, |
| { |
| "entropy": 6.5606420040130615, |
| "epoch": 0.01786802030456853, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00032950000000000004, |
| "loss": 6.2876, |
| "mean_token_accuracy": 0.10897349566221237, |
| "num_tokens": 1833582.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 6.524020147323609, |
| "epoch": 0.018003384094754653, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.00033200000000000005, |
| "loss": 6.26, |
| "mean_token_accuracy": 0.11666257977485657, |
| "num_tokens": 1847514.0, |
| "step": 665 |
| }, |
| { |
| "entropy": 6.450877380371094, |
| "epoch": 0.018138747884940777, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00033450000000000005, |
| "loss": 6.2948, |
| "mean_token_accuracy": 0.11785768866539001, |
| "num_tokens": 1860177.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 6.518109226226807, |
| "epoch": 0.018274111675126905, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.000337, |
| "loss": 6.3086, |
| "mean_token_accuracy": 0.11776039749383926, |
| "num_tokens": 1873317.0, |
| "step": 675 |
| }, |
| { |
| "entropy": 6.405819511413574, |
| "epoch": 0.01840947546531303, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0003395, |
| "loss": 6.1447, |
| "mean_token_accuracy": 0.11899075359106064, |
| "num_tokens": 1885974.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 6.473683166503906, |
| "epoch": 0.018544839255499154, |
| "grad_norm": 1.125, |
| "learning_rate": 0.000342, |
| "loss": 6.3167, |
| "mean_token_accuracy": 0.11156651675701142, |
| "num_tokens": 1901894.0, |
| "step": 685 |
| }, |
| { |
| "entropy": 6.5223006248474125, |
| "epoch": 0.018680203045685278, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.00034449999999999997, |
| "loss": 6.2982, |
| "mean_token_accuracy": 0.11568359285593033, |
| "num_tokens": 1916276.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 6.437406921386719, |
| "epoch": 0.018815566835871406, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000347, |
| "loss": 6.3, |
| "mean_token_accuracy": 0.10904626250267029, |
| "num_tokens": 1929574.0, |
| "step": 695 |
| }, |
| { |
| "entropy": 6.493116617202759, |
| "epoch": 0.01895093062605753, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.0003495, |
| "loss": 6.2389, |
| "mean_token_accuracy": 0.10819176211953163, |
| "num_tokens": 1943220.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 6.54621901512146, |
| "epoch": 0.019086294416243654, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.000352, |
| "loss": 6.2556, |
| "mean_token_accuracy": 0.10982774049043656, |
| "num_tokens": 1957834.0, |
| "step": 705 |
| }, |
| { |
| "entropy": 6.512110996246338, |
| "epoch": 0.01922165820642978, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0003545, |
| "loss": 6.3302, |
| "mean_token_accuracy": 0.11116872280836106, |
| "num_tokens": 1972649.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 6.418754625320434, |
| "epoch": 0.019357021996615906, |
| "grad_norm": 1.265625, |
| "learning_rate": 0.000357, |
| "loss": 6.1538, |
| "mean_token_accuracy": 0.12162703573703766, |
| "num_tokens": 1984181.0, |
| "step": 715 |
| }, |
| { |
| "entropy": 6.399659919738769, |
| "epoch": 0.01949238578680203, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.0003595, |
| "loss": 6.2047, |
| "mean_token_accuracy": 0.11393127739429473, |
| "num_tokens": 2000616.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 6.4549713134765625, |
| "epoch": 0.019627749576988155, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000362, |
| "loss": 6.1698, |
| "mean_token_accuracy": 0.11860272511839867, |
| "num_tokens": 2015344.0, |
| "step": 725 |
| }, |
| { |
| "entropy": 6.458272075653076, |
| "epoch": 0.01976311336717428, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0003645, |
| "loss": 6.2536, |
| "mean_token_accuracy": 0.11021775305271149, |
| "num_tokens": 2029823.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 6.360110950469971, |
| "epoch": 0.019898477157360407, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.000367, |
| "loss": 6.1363, |
| "mean_token_accuracy": 0.11379259899258613, |
| "num_tokens": 2043680.0, |
| "step": 735 |
| }, |
| { |
| "entropy": 6.4546263217926025, |
| "epoch": 0.02003384094754653, |
| "grad_norm": 1.2890625, |
| "learning_rate": 0.0003695, |
| "loss": 6.2118, |
| "mean_token_accuracy": 0.11678453311324119, |
| "num_tokens": 2056211.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 6.301215696334839, |
| "epoch": 0.020169204737732656, |
| "grad_norm": 1.3125, |
| "learning_rate": 0.000372, |
| "loss": 6.2223, |
| "mean_token_accuracy": 0.11474345549941063, |
| "num_tokens": 2069775.0, |
| "step": 745 |
| }, |
| { |
| "entropy": 6.343719387054444, |
| "epoch": 0.02030456852791878, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.0003745, |
| "loss": 6.0669, |
| "mean_token_accuracy": 0.12363717705011368, |
| "num_tokens": 2084423.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 6.379573202133178, |
| "epoch": 0.020439932318104908, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000377, |
| "loss": 6.2006, |
| "mean_token_accuracy": 0.11517359465360641, |
| "num_tokens": 2099702.0, |
| "step": 755 |
| }, |
| { |
| "entropy": 6.35660948753357, |
| "epoch": 0.020575296108291032, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.0003795, |
| "loss": 6.1424, |
| "mean_token_accuracy": 0.116712386906147, |
| "num_tokens": 2114938.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 6.33174843788147, |
| "epoch": 0.020710659898477157, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000382, |
| "loss": 6.0715, |
| "mean_token_accuracy": 0.12017848417162895, |
| "num_tokens": 2128039.0, |
| "step": 765 |
| }, |
| { |
| "entropy": 6.483924388885498, |
| "epoch": 0.02084602368866328, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0003845, |
| "loss": 6.2675, |
| "mean_token_accuracy": 0.11350229382514954, |
| "num_tokens": 2144244.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 6.299388790130616, |
| "epoch": 0.02098138747884941, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.00038700000000000003, |
| "loss": 6.0745, |
| "mean_token_accuracy": 0.12214050814509392, |
| "num_tokens": 2156050.0, |
| "step": 775 |
| }, |
| { |
| "entropy": 6.339807558059692, |
| "epoch": 0.021116751269035533, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00038950000000000003, |
| "loss": 6.1324, |
| "mean_token_accuracy": 0.11614297851920127, |
| "num_tokens": 2170083.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 6.346547555923462, |
| "epoch": 0.021252115059221657, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00039200000000000004, |
| "loss": 6.1194, |
| "mean_token_accuracy": 0.12128575146198273, |
| "num_tokens": 2184536.0, |
| "step": 785 |
| }, |
| { |
| "entropy": 6.332412433624268, |
| "epoch": 0.021387478849407785, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00039450000000000005, |
| "loss": 6.1629, |
| "mean_token_accuracy": 0.11224813610315323, |
| "num_tokens": 2199324.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 6.236615514755249, |
| "epoch": 0.02152284263959391, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00039700000000000005, |
| "loss": 6.1244, |
| "mean_token_accuracy": 0.1139693059027195, |
| "num_tokens": 2215191.0, |
| "step": 795 |
| }, |
| { |
| "entropy": 6.423162221908569, |
| "epoch": 0.021658206429780034, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.0003995, |
| "loss": 6.1789, |
| "mean_token_accuracy": 0.11178024560213089, |
| "num_tokens": 2229354.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 6.281933403015136, |
| "epoch": 0.021793570219966158, |
| "grad_norm": 1.0, |
| "learning_rate": 0.000402, |
| "loss": 6.1912, |
| "mean_token_accuracy": 0.11805299371480941, |
| "num_tokens": 2243804.0, |
| "step": 805 |
| }, |
| { |
| "entropy": 6.288844728469849, |
| "epoch": 0.021928934010152286, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004045, |
| "loss": 6.0841, |
| "mean_token_accuracy": 0.11569216102361679, |
| "num_tokens": 2258267.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 6.315207052230835, |
| "epoch": 0.02206429780033841, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00040699999999999997, |
| "loss": 6.1319, |
| "mean_token_accuracy": 0.12272850275039673, |
| "num_tokens": 2271854.0, |
| "step": 815 |
| }, |
| { |
| "entropy": 6.263217782974243, |
| "epoch": 0.022199661590524535, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004095, |
| "loss": 6.1651, |
| "mean_token_accuracy": 0.11350240483880043, |
| "num_tokens": 2285897.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 6.2891233444213865, |
| "epoch": 0.02233502538071066, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.000412, |
| "loss": 6.1208, |
| "mean_token_accuracy": 0.11810638681054116, |
| "num_tokens": 2299354.0, |
| "step": 825 |
| }, |
| { |
| "entropy": 6.323483896255493, |
| "epoch": 0.022470389170896787, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004145, |
| "loss": 6.1693, |
| "mean_token_accuracy": 0.1183534987270832, |
| "num_tokens": 2313111.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 6.299751424789429, |
| "epoch": 0.02260575296108291, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.000417, |
| "loss": 6.1459, |
| "mean_token_accuracy": 0.12177513241767883, |
| "num_tokens": 2325556.0, |
| "step": 835 |
| }, |
| { |
| "entropy": 6.354130220413208, |
| "epoch": 0.022741116751269035, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0004195, |
| "loss": 6.1991, |
| "mean_token_accuracy": 0.11779833287000656, |
| "num_tokens": 2340033.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 6.290956926345825, |
| "epoch": 0.02287648054145516, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.000422, |
| "loss": 6.1439, |
| "mean_token_accuracy": 0.12168726176023484, |
| "num_tokens": 2353916.0, |
| "step": 845 |
| }, |
| { |
| "entropy": 6.26514630317688, |
| "epoch": 0.023011844331641287, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0004245, |
| "loss": 6.1255, |
| "mean_token_accuracy": 0.12298965677618981, |
| "num_tokens": 2367161.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 6.297455596923828, |
| "epoch": 0.02314720812182741, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.000427, |
| "loss": 6.1707, |
| "mean_token_accuracy": 0.11453822180628777, |
| "num_tokens": 2382562.0, |
| "step": 855 |
| }, |
| { |
| "entropy": 6.278497695922852, |
| "epoch": 0.023282571912013536, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.0004295, |
| "loss": 6.084, |
| "mean_token_accuracy": 0.12197378650307655, |
| "num_tokens": 2395671.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 6.201052713394165, |
| "epoch": 0.02341793570219966, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000432, |
| "loss": 6.1328, |
| "mean_token_accuracy": 0.11925875097513199, |
| "num_tokens": 2409902.0, |
| "step": 865 |
| }, |
| { |
| "entropy": 6.319374704360962, |
| "epoch": 0.023553299492385788, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004345, |
| "loss": 6.1155, |
| "mean_token_accuracy": 0.11418568938970566, |
| "num_tokens": 2424405.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 6.211519432067871, |
| "epoch": 0.023688663282571912, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.000437, |
| "loss": 6.0401, |
| "mean_token_accuracy": 0.11908271163702011, |
| "num_tokens": 2440256.0, |
| "step": 875 |
| }, |
| { |
| "entropy": 6.258747959136963, |
| "epoch": 0.023824027072758037, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004395, |
| "loss": 6.1066, |
| "mean_token_accuracy": 0.11787782683968544, |
| "num_tokens": 2453224.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 6.132023286819458, |
| "epoch": 0.02395939086294416, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.000442, |
| "loss": 5.9843, |
| "mean_token_accuracy": 0.1226534366607666, |
| "num_tokens": 2468101.0, |
| "step": 885 |
| }, |
| { |
| "entropy": 6.3332679271698, |
| "epoch": 0.02409475465313029, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.0004445, |
| "loss": 6.2065, |
| "mean_token_accuracy": 0.12027881368994713, |
| "num_tokens": 2483221.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 6.218679809570313, |
| "epoch": 0.024230118443316413, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.000447, |
| "loss": 6.0992, |
| "mean_token_accuracy": 0.11610312834382057, |
| "num_tokens": 2496389.0, |
| "step": 895 |
| }, |
| { |
| "entropy": 6.1929422378540036, |
| "epoch": 0.024365482233502538, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00044950000000000003, |
| "loss": 6.0435, |
| "mean_token_accuracy": 0.11607689782977104, |
| "num_tokens": 2510988.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 6.248309087753296, |
| "epoch": 0.024500846023688662, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00045200000000000004, |
| "loss": 6.1425, |
| "mean_token_accuracy": 0.12013140320777893, |
| "num_tokens": 2525341.0, |
| "step": 905 |
| }, |
| { |
| "entropy": 6.198721647262573, |
| "epoch": 0.02463620981387479, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00045450000000000004, |
| "loss": 6.1277, |
| "mean_token_accuracy": 0.11830744370818139, |
| "num_tokens": 2538706.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 6.277400732040405, |
| "epoch": 0.024771573604060914, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00045700000000000005, |
| "loss": 6.1407, |
| "mean_token_accuracy": 0.1180431790649891, |
| "num_tokens": 2554056.0, |
| "step": 915 |
| }, |
| { |
| "entropy": 6.122376012802124, |
| "epoch": 0.02490693739424704, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00045950000000000006, |
| "loss": 6.0363, |
| "mean_token_accuracy": 0.12817837595939635, |
| "num_tokens": 2569073.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 6.23994255065918, |
| "epoch": 0.025042301184433163, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000462, |
| "loss": 6.0807, |
| "mean_token_accuracy": 0.12659804597496987, |
| "num_tokens": 2582519.0, |
| "step": 925 |
| }, |
| { |
| "entropy": 6.254793930053711, |
| "epoch": 0.02517766497461929, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004645, |
| "loss": 6.138, |
| "mean_token_accuracy": 0.11910348609089852, |
| "num_tokens": 2597308.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 6.186693382263184, |
| "epoch": 0.025313028764805415, |
| "grad_norm": 1.125, |
| "learning_rate": 0.000467, |
| "loss": 6.1146, |
| "mean_token_accuracy": 0.12513377815485, |
| "num_tokens": 2610388.0, |
| "step": 935 |
| }, |
| { |
| "entropy": 6.133151054382324, |
| "epoch": 0.02544839255499154, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004695, |
| "loss": 5.9744, |
| "mean_token_accuracy": 0.1229440450668335, |
| "num_tokens": 2624701.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 6.227858448028565, |
| "epoch": 0.025583756345177663, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000472, |
| "loss": 6.1629, |
| "mean_token_accuracy": 0.11275116056203842, |
| "num_tokens": 2639582.0, |
| "step": 945 |
| }, |
| { |
| "entropy": 6.088177108764649, |
| "epoch": 0.02571912013536379, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004745, |
| "loss": 5.9973, |
| "mean_token_accuracy": 0.12648221775889396, |
| "num_tokens": 2653808.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 6.13272876739502, |
| "epoch": 0.025854483925549916, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000477, |
| "loss": 6.001, |
| "mean_token_accuracy": 0.12153996378183365, |
| "num_tokens": 2667423.0, |
| "step": 955 |
| }, |
| { |
| "entropy": 6.150818300247193, |
| "epoch": 0.02598984771573604, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004795, |
| "loss": 6.0237, |
| "mean_token_accuracy": 0.12148027569055557, |
| "num_tokens": 2683296.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 6.043711376190186, |
| "epoch": 0.026125211505922164, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.000482, |
| "loss": 5.9768, |
| "mean_token_accuracy": 0.13035187423229216, |
| "num_tokens": 2697230.0, |
| "step": 965 |
| }, |
| { |
| "entropy": 6.165330123901367, |
| "epoch": 0.026260575296108292, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004845, |
| "loss": 5.9685, |
| "mean_token_accuracy": 0.1219008818268776, |
| "num_tokens": 2711689.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 6.072505140304566, |
| "epoch": 0.026395939086294416, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.000487, |
| "loss": 6.0051, |
| "mean_token_accuracy": 0.12370155230164528, |
| "num_tokens": 2725786.0, |
| "step": 975 |
| }, |
| { |
| "entropy": 6.097587728500367, |
| "epoch": 0.02653130287648054, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004895, |
| "loss": 6.0078, |
| "mean_token_accuracy": 0.12946900948882104, |
| "num_tokens": 2739444.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 6.165721845626831, |
| "epoch": 0.02666666666666667, |
| "grad_norm": 0.9140625, |
| "learning_rate": 0.000492, |
| "loss": 5.9966, |
| "mean_token_accuracy": 0.12653872296214103, |
| "num_tokens": 2754692.0, |
| "step": 985 |
| }, |
| { |
| "entropy": 6.010534715652466, |
| "epoch": 0.026802030456852793, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004945, |
| "loss": 5.9195, |
| "mean_token_accuracy": 0.1301392510533333, |
| "num_tokens": 2767847.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 6.176916885375976, |
| "epoch": 0.026937394247038917, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.000497, |
| "loss": 6.147, |
| "mean_token_accuracy": 0.11529367789626122, |
| "num_tokens": 2783919.0, |
| "step": 995 |
| }, |
| { |
| "entropy": 6.178207778930664, |
| "epoch": 0.02707275803722504, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004995, |
| "loss": 6.049, |
| "mean_token_accuracy": 0.11618730947375297, |
| "num_tokens": 2797758.0, |
| "step": 1000 |
| }, |
| { |
| "entropy": 6.0772298812866214, |
| "epoch": 0.02720812182741117, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.000499998026082006, |
| "loss": 5.9816, |
| "mean_token_accuracy": 0.12454243823885917, |
| "num_tokens": 2811266.0, |
| "step": 1005 |
| }, |
| { |
| "entropy": 6.178618955612182, |
| "epoch": 0.027343485617597293, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004999900070995136, |
| "loss": 6.1008, |
| "mean_token_accuracy": 0.12391449511051178, |
| "num_tokens": 2825546.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 6.09156231880188, |
| "epoch": 0.027478849407783418, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004999758199023239, |
| "loss": 6.0494, |
| "mean_token_accuracy": 0.12795282825827597, |
| "num_tokens": 2840284.0, |
| "step": 1015 |
| }, |
| { |
| "entropy": 6.100447702407837, |
| "epoch": 0.027614213197969542, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.0004999554648793858, |
| "loss": 6.0469, |
| "mean_token_accuracy": 0.12443553805351257, |
| "num_tokens": 2851891.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 6.141157817840576, |
| "epoch": 0.02774957698815567, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.0004999289425887425, |
| "loss": 5.9993, |
| "mean_token_accuracy": 0.12068658322095871, |
| "num_tokens": 2864393.0, |
| "step": 1025 |
| }, |
| { |
| "entropy": 6.0899200439453125, |
| "epoch": 0.027884940778341794, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004998962537575161, |
| "loss": 6.0697, |
| "mean_token_accuracy": 0.12269674092531205, |
| "num_tokens": 2878581.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 6.183287048339844, |
| "epoch": 0.02802030456852792, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004998573992818874, |
| "loss": 6.1252, |
| "mean_token_accuracy": 0.12084309384226799, |
| "num_tokens": 2891217.0, |
| "step": 1035 |
| }, |
| { |
| "entropy": 6.048014736175537, |
| "epoch": 0.028155668358714043, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004998123802270715, |
| "loss": 5.9877, |
| "mean_token_accuracy": 0.1275292307138443, |
| "num_tokens": 2902261.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 6.180945777893067, |
| "epoch": 0.02829103214890017, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004997611978272886, |
| "loss": 6.0715, |
| "mean_token_accuracy": 0.1172533318400383, |
| "num_tokens": 2915455.0, |
| "step": 1045 |
| }, |
| { |
| "entropy": 6.057958126068115, |
| "epoch": 0.028426395939086295, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0004997038534857298, |
| "loss": 6.0513, |
| "mean_token_accuracy": 0.11567913889884948, |
| "num_tokens": 2930873.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 6.126917505264283, |
| "epoch": 0.02856175972927242, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004996403487745194, |
| "loss": 6.0191, |
| "mean_token_accuracy": 0.12455897256731988, |
| "num_tokens": 2945768.0, |
| "step": 1055 |
| }, |
| { |
| "entropy": 6.160192489624023, |
| "epoch": 0.028697123519458544, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.000499570685434671, |
| "loss": 6.0718, |
| "mean_token_accuracy": 0.12326753437519074, |
| "num_tokens": 2960052.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 6.049477672576904, |
| "epoch": 0.02883248730964467, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004994948653760405, |
| "loss": 5.907, |
| "mean_token_accuracy": 0.12975608184933662, |
| "num_tokens": 2974252.0, |
| "step": 1065 |
| }, |
| { |
| "entropy": 5.922494602203369, |
| "epoch": 0.028967851099830796, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0004994128906772729, |
| "loss": 5.9723, |
| "mean_token_accuracy": 0.12408508732914925, |
| "num_tokens": 2988414.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 6.076635503768921, |
| "epoch": 0.02910321489001692, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.000499324763585746, |
| "loss": 6.0159, |
| "mean_token_accuracy": 0.12376472353935242, |
| "num_tokens": 3005833.0, |
| "step": 1075 |
| }, |
| { |
| "entropy": 6.0643566131591795, |
| "epoch": 0.029238578680203044, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.0004992304865175085, |
| "loss": 6.0162, |
| "mean_token_accuracy": 0.11739084795117379, |
| "num_tokens": 3019722.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 6.0612537384033205, |
| "epoch": 0.029373942470389172, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0004991300620572138, |
| "loss": 5.9597, |
| "mean_token_accuracy": 0.12137619629502297, |
| "num_tokens": 3033643.0, |
| "step": 1085 |
| }, |
| { |
| "entropy": 6.003667545318604, |
| "epoch": 0.029509306260575296, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004990234929580494, |
| "loss": 5.9007, |
| "mean_token_accuracy": 0.12919754460453986, |
| "num_tokens": 3047311.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 6.16131591796875, |
| "epoch": 0.02964467005076142, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.0004989107821416609, |
| "loss": 6.0886, |
| "mean_token_accuracy": 0.12004212662577629, |
| "num_tokens": 3062823.0, |
| "step": 1095 |
| }, |
| { |
| "entropy": 6.068430328369141, |
| "epoch": 0.029780033840947545, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004987919326980723, |
| "loss": 5.9748, |
| "mean_token_accuracy": 0.13052917644381523, |
| "num_tokens": 3076828.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 5.9808131694793705, |
| "epoch": 0.029915397631133673, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0004986669478856011, |
| "loss": 5.9151, |
| "mean_token_accuracy": 0.132940074801445, |
| "num_tokens": 3089369.0, |
| "step": 1105 |
| }, |
| { |
| "entropy": 6.049989414215088, |
| "epoch": 0.030050761421319797, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004985358311307688, |
| "loss": 6.0077, |
| "mean_token_accuracy": 0.13002250343561172, |
| "num_tokens": 3100518.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 6.067233991622925, |
| "epoch": 0.03018612521150592, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004983985860282081, |
| "loss": 5.9342, |
| "mean_token_accuracy": 0.1303796499967575, |
| "num_tokens": 3113599.0, |
| "step": 1115 |
| }, |
| { |
| "entropy": 5.986032724380493, |
| "epoch": 0.030321489001692046, |
| "grad_norm": 0.9765625, |
| "learning_rate": 0.0004982552163405623, |
| "loss": 5.9344, |
| "mean_token_accuracy": 0.13099692836403848, |
| "num_tokens": 3126725.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 6.01772027015686, |
| "epoch": 0.030456852791878174, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004981057259983839, |
| "loss": 5.9407, |
| "mean_token_accuracy": 0.13005468547344207, |
| "num_tokens": 3140170.0, |
| "step": 1125 |
| }, |
| { |
| "entropy": 5.947785377502441, |
| "epoch": 0.030592216582064298, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.0004979501191000262, |
| "loss": 5.9137, |
| "mean_token_accuracy": 0.12703290432691575, |
| "num_tokens": 3154154.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 6.0017212390899655, |
| "epoch": 0.030727580372250422, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.0004977883999115311, |
| "loss": 5.9814, |
| "mean_token_accuracy": 0.12780916765332223, |
| "num_tokens": 3170061.0, |
| "step": 1135 |
| }, |
| { |
| "entropy": 6.102719736099243, |
| "epoch": 0.030862944162436547, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.0004976205728665113, |
| "loss": 6.0419, |
| "mean_token_accuracy": 0.12874573692679406, |
| "num_tokens": 3183167.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 5.993436717987061, |
| "epoch": 0.030998307952622674, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004974466425660307, |
| "loss": 6.1286, |
| "mean_token_accuracy": 0.1163134016096592, |
| "num_tokens": 3197764.0, |
| "step": 1145 |
| }, |
| { |
| "entropy": 6.101684427261352, |
| "epoch": 0.0311336717428088, |
| "grad_norm": 0.9375, |
| "learning_rate": 0.0004972666137784759, |
| "loss": 5.8899, |
| "mean_token_accuracy": 0.12967644035816192, |
| "num_tokens": 3212909.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 6.056351280212402, |
| "epoch": 0.03126903553299493, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0004970804914394271, |
| "loss": 6.0213, |
| "mean_token_accuracy": 0.12962342649698258, |
| "num_tokens": 3224140.0, |
| "step": 1155 |
| }, |
| { |
| "entropy": 5.998062562942505, |
| "epoch": 0.03140439932318105, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004968882806515225, |
| "loss": 5.959, |
| "mean_token_accuracy": 0.13079651519656182, |
| "num_tokens": 3237827.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 6.0129087448120115, |
| "epoch": 0.031539763113367175, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004966899866843177, |
| "loss": 5.9242, |
| "mean_token_accuracy": 0.12941501662135124, |
| "num_tokens": 3250552.0, |
| "step": 1165 |
| }, |
| { |
| "entropy": 5.929322099685669, |
| "epoch": 0.0316751269035533, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000496485614974142, |
| "loss": 5.9082, |
| "mean_token_accuracy": 0.13116575181484222, |
| "num_tokens": 3265108.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 5.910490798950195, |
| "epoch": 0.031810490693739424, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004962751711239492, |
| "loss": 5.8957, |
| "mean_token_accuracy": 0.13716685473918916, |
| "num_tokens": 3277399.0, |
| "step": 1175 |
| }, |
| { |
| "entropy": 5.90950288772583, |
| "epoch": 0.03194585448392555, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.0004960586609031636, |
| "loss": 5.8656, |
| "mean_token_accuracy": 0.13133470267057418, |
| "num_tokens": 3292261.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 6.02558069229126, |
| "epoch": 0.03208121827411167, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0004958360902475224, |
| "loss": 5.9481, |
| "mean_token_accuracy": 0.12776122540235518, |
| "num_tokens": 3305914.0, |
| "step": 1185 |
| }, |
| { |
| "entropy": 5.877729225158691, |
| "epoch": 0.032216582064297804, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004956074652589125, |
| "loss": 5.8461, |
| "mean_token_accuracy": 0.13402740731835366, |
| "num_tokens": 3319731.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 5.983613348007202, |
| "epoch": 0.03235194585448393, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.0004953727922052035, |
| "loss": 5.9026, |
| "mean_token_accuracy": 0.1287564866244793, |
| "num_tokens": 3335865.0, |
| "step": 1195 |
| }, |
| { |
| "entropy": 5.955887413024902, |
| "epoch": 0.03248730964467005, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0004951320775200756, |
| "loss": 5.8795, |
| "mean_token_accuracy": 0.13347595036029816, |
| "num_tokens": 3350692.0, |
| "step": 1200 |
| }, |
| { |
| "entropy": 5.869665241241455, |
| "epoch": 0.03262267343485618, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004948853278028436, |
| "loss": 5.8414, |
| "mean_token_accuracy": 0.1349584087729454, |
| "num_tokens": 3364477.0, |
| "step": 1205 |
| }, |
| { |
| "entropy": 6.077768468856812, |
| "epoch": 0.0327580372250423, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0004946325498182755, |
| "loss": 6.0202, |
| "mean_token_accuracy": 0.13227369338274003, |
| "num_tokens": 3377976.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 5.928851127624512, |
| "epoch": 0.032893401015228425, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004943737504964076, |
| "loss": 5.8941, |
| "mean_token_accuracy": 0.13219523280858994, |
| "num_tokens": 3391797.0, |
| "step": 1215 |
| }, |
| { |
| "entropy": 5.968907499313355, |
| "epoch": 0.03302876480541455, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000494108936932354, |
| "loss": 5.904, |
| "mean_token_accuracy": 0.1308644212782383, |
| "num_tokens": 3406175.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 5.953116321563721, |
| "epoch": 0.033164128595600674, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004938381163861124, |
| "loss": 5.8953, |
| "mean_token_accuracy": 0.13571116998791694, |
| "num_tokens": 3419314.0, |
| "step": 1225 |
| }, |
| { |
| "entropy": 5.968687200546265, |
| "epoch": 0.033299492385786805, |
| "grad_norm": 0.91015625, |
| "learning_rate": 0.0004935612962823645, |
| "loss": 5.9639, |
| "mean_token_accuracy": 0.12865443304181098, |
| "num_tokens": 3436286.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 5.994656372070312, |
| "epoch": 0.03343485617597293, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004932784842102739, |
| "loss": 5.9152, |
| "mean_token_accuracy": 0.13279383033514022, |
| "num_tokens": 3450743.0, |
| "step": 1235 |
| }, |
| { |
| "entropy": 5.880604553222656, |
| "epoch": 0.033570219966159054, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.0004929896879232758, |
| "loss": 5.9593, |
| "mean_token_accuracy": 0.1276319444179535, |
| "num_tokens": 3465265.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 6.054373121261596, |
| "epoch": 0.03370558375634518, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004926949153388668, |
| "loss": 5.9635, |
| "mean_token_accuracy": 0.13033603355288506, |
| "num_tokens": 3479850.0, |
| "step": 1245 |
| }, |
| { |
| "entropy": 6.004738473892212, |
| "epoch": 0.0338409475465313, |
| "grad_norm": 0.93359375, |
| "learning_rate": 0.0004923941745383859, |
| "loss": 6.0149, |
| "mean_token_accuracy": 0.12755341306328774, |
| "num_tokens": 3494388.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 6.05593056678772, |
| "epoch": 0.03397631133671743, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.000492087473766794, |
| "loss": 5.9944, |
| "mean_token_accuracy": 0.129459198564291, |
| "num_tokens": 3508609.0, |
| "step": 1255 |
| }, |
| { |
| "entropy": 5.989010000228882, |
| "epoch": 0.03411167512690355, |
| "grad_norm": 0.84765625, |
| "learning_rate": 0.000491774821432448, |
| "loss": 5.9484, |
| "mean_token_accuracy": 0.12573069110512733, |
| "num_tokens": 3524252.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 5.86044340133667, |
| "epoch": 0.034247038917089676, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.0004914562261068693, |
| "loss": 5.8538, |
| "mean_token_accuracy": 0.13299454674124717, |
| "num_tokens": 3540431.0, |
| "step": 1265 |
| }, |
| { |
| "entropy": 5.977858638763427, |
| "epoch": 0.03438240270727581, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004911316965245098, |
| "loss": 5.936, |
| "mean_token_accuracy": 0.1308388702571392, |
| "num_tokens": 3555452.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 5.904463481903076, |
| "epoch": 0.03451776649746193, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.000490801241582512, |
| "loss": 5.8326, |
| "mean_token_accuracy": 0.13622485026717185, |
| "num_tokens": 3569414.0, |
| "step": 1275 |
| }, |
| { |
| "entropy": 5.986747741699219, |
| "epoch": 0.034653130287648055, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.000490464870340465, |
| "loss": 6.0092, |
| "mean_token_accuracy": 0.12418872565031051, |
| "num_tokens": 3585926.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 5.979127502441406, |
| "epoch": 0.03478849407783418, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004901225920201563, |
| "loss": 5.8517, |
| "mean_token_accuracy": 0.12628912925720215, |
| "num_tokens": 3598692.0, |
| "step": 1285 |
| }, |
| { |
| "entropy": 5.866104936599731, |
| "epoch": 0.034923857868020304, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.000489774416005319, |
| "loss": 5.8145, |
| "mean_token_accuracy": 0.13827023953199385, |
| "num_tokens": 3610579.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 5.940866851806641, |
| "epoch": 0.03505922165820643, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0004894203518413742, |
| "loss": 5.8967, |
| "mean_token_accuracy": 0.13155581057071686, |
| "num_tokens": 3622955.0, |
| "step": 1295 |
| }, |
| { |
| "entropy": 5.965740633010864, |
| "epoch": 0.03519458544839255, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004890604092351701, |
| "loss": 5.848, |
| "mean_token_accuracy": 0.13300148025155067, |
| "num_tokens": 3636465.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 5.9097521781921385, |
| "epoch": 0.03532994923857868, |
| "grad_norm": 0.93359375, |
| "learning_rate": 0.000488694598054715, |
| "loss": 5.8418, |
| "mean_token_accuracy": 0.13007594645023346, |
| "num_tokens": 3650490.0, |
| "step": 1305 |
| }, |
| { |
| "entropy": 5.989442920684814, |
| "epoch": 0.03546531302876481, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.0004883229283289071, |
| "loss": 5.9325, |
| "mean_token_accuracy": 0.13511626422405243, |
| "num_tokens": 3666952.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 5.868106698989868, |
| "epoch": 0.03560067681895093, |
| "grad_norm": 0.88671875, |
| "learning_rate": 0.00048794541024725993, |
| "loss": 5.8828, |
| "mean_token_accuracy": 0.13127233758568763, |
| "num_tokens": 3681741.0, |
| "step": 1315 |
| }, |
| { |
| "entropy": 6.05716724395752, |
| "epoch": 0.03573604060913706, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.0004875620541596221, |
| "loss": 6.0203, |
| "mean_token_accuracy": 0.12015189900994301, |
| "num_tokens": 3696309.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 5.87901759147644, |
| "epoch": 0.03587140439932318, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00048717287057589454, |
| "loss": 5.8183, |
| "mean_token_accuracy": 0.13341830670833588, |
| "num_tokens": 3710972.0, |
| "step": 1325 |
| }, |
| { |
| "entropy": 5.910233020782471, |
| "epoch": 0.036006768189509306, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004867778701657417, |
| "loss": 5.8272, |
| "mean_token_accuracy": 0.1385295033454895, |
| "num_tokens": 3723619.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 5.879352235794068, |
| "epoch": 0.03614213197969543, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00048637706375829955, |
| "loss": 5.8317, |
| "mean_token_accuracy": 0.13691574931144715, |
| "num_tokens": 3736947.0, |
| "step": 1335 |
| }, |
| { |
| "entropy": 5.879655885696411, |
| "epoch": 0.036277495769881554, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.000485970462341878, |
| "loss": 5.8283, |
| "mean_token_accuracy": 0.13367267698049545, |
| "num_tokens": 3751488.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 5.861524868011474, |
| "epoch": 0.03641285956006768, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00048555807706366044, |
| "loss": 5.8149, |
| "mean_token_accuracy": 0.12982808873057367, |
| "num_tokens": 3764169.0, |
| "step": 1345 |
| }, |
| { |
| "entropy": 5.923907041549683, |
| "epoch": 0.03654822335025381, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00048513991922939756, |
| "loss": 5.8853, |
| "mean_token_accuracy": 0.1327181950211525, |
| "num_tokens": 3777786.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 5.872652530670166, |
| "epoch": 0.036683587140439934, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00048471600030309744, |
| "loss": 5.7489, |
| "mean_token_accuracy": 0.13938361927866935, |
| "num_tokens": 3793618.0, |
| "step": 1355 |
| }, |
| { |
| "entropy": 5.832516002655029, |
| "epoch": 0.03681895093062606, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.00048428633190671186, |
| "loss": 5.7986, |
| "mean_token_accuracy": 0.13645398393273353, |
| "num_tokens": 3807477.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 5.874223041534424, |
| "epoch": 0.03695431472081218, |
| "grad_norm": 0.921875, |
| "learning_rate": 0.0004838509258198167, |
| "loss": 5.7628, |
| "mean_token_accuracy": 0.1414404109120369, |
| "num_tokens": 3821423.0, |
| "step": 1365 |
| }, |
| { |
| "entropy": 5.7999297142028805, |
| "epoch": 0.03708967851099831, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00048340979397929, |
| "loss": 5.8377, |
| "mean_token_accuracy": 0.13525271713733672, |
| "num_tokens": 3835023.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 5.952495384216308, |
| "epoch": 0.03722504230118443, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00048296294847898386, |
| "loss": 5.8599, |
| "mean_token_accuracy": 0.13231865540146828, |
| "num_tokens": 3849230.0, |
| "step": 1375 |
| }, |
| { |
| "entropy": 5.886288738250732, |
| "epoch": 0.037360406091370556, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004825104015693934, |
| "loss": 5.8341, |
| "mean_token_accuracy": 0.1299556814134121, |
| "num_tokens": 3863884.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 5.7548364162445065, |
| "epoch": 0.03749576988155669, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0004820521656573208, |
| "loss": 5.6259, |
| "mean_token_accuracy": 0.14474526271224022, |
| "num_tokens": 3875444.0, |
| "step": 1385 |
| }, |
| { |
| "entropy": 5.954405307769775, |
| "epoch": 0.03763113367174281, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00048158825330553505, |
| "loss": 5.9888, |
| "mean_token_accuracy": 0.132489612698555, |
| "num_tokens": 3888875.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 5.784528350830078, |
| "epoch": 0.037766497461928936, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00048111867723242763, |
| "loss": 5.7374, |
| "mean_token_accuracy": 0.13683436438441277, |
| "num_tokens": 3904124.0, |
| "step": 1395 |
| }, |
| { |
| "entropy": 5.800213289260864, |
| "epoch": 0.03790186125211506, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.0004806434503116637, |
| "loss": 5.7543, |
| "mean_token_accuracy": 0.1421910360455513, |
| "num_tokens": 3917976.0, |
| "step": 1400 |
| }, |
| { |
| "entropy": 5.8708749294281, |
| "epoch": 0.038037225042301184, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.0004801625855718296, |
| "loss": 5.8518, |
| "mean_token_accuracy": 0.13218354880809785, |
| "num_tokens": 3932835.0, |
| "step": 1405 |
| }, |
| { |
| "entropy": 5.92179274559021, |
| "epoch": 0.03817258883248731, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.00047967609619607477, |
| "loss": 5.7986, |
| "mean_token_accuracy": 0.14245062917470933, |
| "num_tokens": 3945938.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 5.76557936668396, |
| "epoch": 0.03830795262267343, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004791839955217513, |
| "loss": 5.7599, |
| "mean_token_accuracy": 0.14098661318421363, |
| "num_tokens": 3958447.0, |
| "step": 1415 |
| }, |
| { |
| "entropy": 5.868845748901367, |
| "epoch": 0.03844331641285956, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00047868629704004786, |
| "loss": 5.871, |
| "mean_token_accuracy": 0.13354070782661437, |
| "num_tokens": 3972105.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 5.96793303489685, |
| "epoch": 0.03857868020304569, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00047818301439561965, |
| "loss": 5.835, |
| "mean_token_accuracy": 0.13661837428808213, |
| "num_tokens": 3984935.0, |
| "step": 1425 |
| }, |
| { |
| "entropy": 5.800432634353638, |
| "epoch": 0.03871404399323181, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00047767416138621454, |
| "loss": 5.8082, |
| "mean_token_accuracy": 0.13442106992006303, |
| "num_tokens": 3998223.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 5.826992130279541, |
| "epoch": 0.03884940778341794, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.000477159751962295, |
| "loss": 5.7446, |
| "mean_token_accuracy": 0.14261322766542434, |
| "num_tokens": 4012876.0, |
| "step": 1435 |
| }, |
| { |
| "entropy": 5.842947864532471, |
| "epoch": 0.03898477157360406, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00047663980022665507, |
| "loss": 5.7954, |
| "mean_token_accuracy": 0.1379825048148632, |
| "num_tokens": 4025607.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 5.807746267318725, |
| "epoch": 0.039120135363790186, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00047611432043403437, |
| "loss": 5.7896, |
| "mean_token_accuracy": 0.13704527392983437, |
| "num_tokens": 4038093.0, |
| "step": 1445 |
| }, |
| { |
| "entropy": 5.849174070358276, |
| "epoch": 0.03925549915397631, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.0004755833269907267, |
| "loss": 5.8395, |
| "mean_token_accuracy": 0.13505658283829688, |
| "num_tokens": 4052159.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 5.945993661880493, |
| "epoch": 0.039390862944162434, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004750468344541857, |
| "loss": 5.8492, |
| "mean_token_accuracy": 0.1315135531127453, |
| "num_tokens": 4065893.0, |
| "step": 1455 |
| }, |
| { |
| "entropy": 5.7644538402557375, |
| "epoch": 0.03952622673434856, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.00047450485753262525, |
| "loss": 5.8021, |
| "mean_token_accuracy": 0.1386327899992466, |
| "num_tokens": 4079274.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 5.907123756408692, |
| "epoch": 0.03966159052453469, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00047395741108461633, |
| "loss": 5.8496, |
| "mean_token_accuracy": 0.1314863942563534, |
| "num_tokens": 4092579.0, |
| "step": 1465 |
| }, |
| { |
| "entropy": 5.845654916763306, |
| "epoch": 0.039796954314720814, |
| "grad_norm": 0.91015625, |
| "learning_rate": 0.00047340451011867985, |
| "loss": 5.7645, |
| "mean_token_accuracy": 0.13576920554041863, |
| "num_tokens": 4106484.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 5.8357702732086185, |
| "epoch": 0.03993231810490694, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00047284616979287515, |
| "loss": 5.7565, |
| "mean_token_accuracy": 0.14051191210746766, |
| "num_tokens": 4120600.0, |
| "step": 1475 |
| }, |
| { |
| "entropy": 5.734717130661011, |
| "epoch": 0.04006768189509306, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.00047228240541438433, |
| "loss": 5.6607, |
| "mean_token_accuracy": 0.14902638792991638, |
| "num_tokens": 4134962.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 5.739231395721435, |
| "epoch": 0.04020304568527919, |
| "grad_norm": 0.921875, |
| "learning_rate": 0.00047171323243909257, |
| "loss": 5.7377, |
| "mean_token_accuracy": 0.1390654683113098, |
| "num_tokens": 4148876.0, |
| "step": 1485 |
| }, |
| { |
| "entropy": 5.851029348373413, |
| "epoch": 0.04033840947546531, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00047113866647116457, |
| "loss": 5.8167, |
| "mean_token_accuracy": 0.13390154615044594, |
| "num_tokens": 4163566.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 5.882148790359497, |
| "epoch": 0.040473773265651436, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.0004705587232626164, |
| "loss": 5.7981, |
| "mean_token_accuracy": 0.1364994041621685, |
| "num_tokens": 4179057.0, |
| "step": 1495 |
| }, |
| { |
| "entropy": 5.747499704360962, |
| "epoch": 0.04060913705583756, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00046997341871288424, |
| "loss": 5.737, |
| "mean_token_accuracy": 0.14035099148750305, |
| "num_tokens": 4192277.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 5.826932811737061, |
| "epoch": 0.04074450084602369, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004693827688683879, |
| "loss": 5.7834, |
| "mean_token_accuracy": 0.1409361645579338, |
| "num_tokens": 4206481.0, |
| "step": 1505 |
| }, |
| { |
| "entropy": 5.8263192653656, |
| "epoch": 0.040879864636209816, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.0004687867899220914, |
| "loss": 5.7582, |
| "mean_token_accuracy": 0.14131638035178185, |
| "num_tokens": 4220498.0, |
| "step": 1510 |
| }, |
| { |
| "entropy": 5.7734416961669925, |
| "epoch": 0.04101522842639594, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.00046818549821305846, |
| "loss": 5.7781, |
| "mean_token_accuracy": 0.13451047241687775, |
| "num_tokens": 4234718.0, |
| "step": 1515 |
| }, |
| { |
| "entropy": 5.835545301437378, |
| "epoch": 0.041150592216582065, |
| "grad_norm": 0.9765625, |
| "learning_rate": 0.00046757891022600494, |
| "loss": 5.7595, |
| "mean_token_accuracy": 0.1417396955192089, |
| "num_tokens": 4247333.0, |
| "step": 1520 |
| }, |
| { |
| "entropy": 5.764037847518921, |
| "epoch": 0.04128595600676819, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0004669670425908471, |
| "loss": 5.745, |
| "mean_token_accuracy": 0.14303724765777587, |
| "num_tokens": 4261059.0, |
| "step": 1525 |
| }, |
| { |
| "entropy": 5.744110727310181, |
| "epoch": 0.04142131979695431, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004663499120822451, |
| "loss": 5.7091, |
| "mean_token_accuracy": 0.13828182518482207, |
| "num_tokens": 4273500.0, |
| "step": 1530 |
| }, |
| { |
| "entropy": 5.809609127044678, |
| "epoch": 0.04155668358714044, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.0004657275356191437, |
| "loss": 5.8712, |
| "mean_token_accuracy": 0.1299389272928238, |
| "num_tokens": 4288422.0, |
| "step": 1535 |
| }, |
| { |
| "entropy": 5.870568370819091, |
| "epoch": 0.04169204737732656, |
| "grad_norm": 0.87890625, |
| "learning_rate": 0.00046509993026430804, |
| "loss": 5.71, |
| "mean_token_accuracy": 0.13911089226603507, |
| "num_tokens": 4303700.0, |
| "step": 1540 |
| }, |
| { |
| "entropy": 5.763344049453735, |
| "epoch": 0.04182741116751269, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004644671132238558, |
| "loss": 5.7506, |
| "mean_token_accuracy": 0.1399180144071579, |
| "num_tokens": 4317887.0, |
| "step": 1545 |
| }, |
| { |
| "entropy": 5.775641632080078, |
| "epoch": 0.04196277495769882, |
| "grad_norm": 0.9765625, |
| "learning_rate": 0.00046382910184678585, |
| "loss": 5.6546, |
| "mean_token_accuracy": 0.14635862186551094, |
| "num_tokens": 4332834.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 5.7155317783355715, |
| "epoch": 0.04209813874788494, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.0004631859136245025, |
| "loss": 5.7051, |
| "mean_token_accuracy": 0.1462951496243477, |
| "num_tokens": 4347341.0, |
| "step": 1555 |
| }, |
| { |
| "entropy": 5.828639984130859, |
| "epoch": 0.042233502538071066, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.0004625375661903357, |
| "loss": 5.7721, |
| "mean_token_accuracy": 0.13997872620821, |
| "num_tokens": 4361359.0, |
| "step": 1560 |
| }, |
| { |
| "entropy": 5.7016510486602785, |
| "epoch": 0.04236886632825719, |
| "grad_norm": 0.8984375, |
| "learning_rate": 0.00046188407731905787, |
| "loss": 5.6941, |
| "mean_token_accuracy": 0.14500250071287155, |
| "num_tokens": 4376677.0, |
| "step": 1565 |
| }, |
| { |
| "entropy": 5.75781831741333, |
| "epoch": 0.042504230118443315, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00046122546492639643, |
| "loss": 5.6234, |
| "mean_token_accuracy": 0.14894023090600966, |
| "num_tokens": 4389507.0, |
| "step": 1570 |
| }, |
| { |
| "entropy": 5.712439489364624, |
| "epoch": 0.04263959390862944, |
| "grad_norm": 0.83203125, |
| "learning_rate": 0.000460561747068543, |
| "loss": 5.7554, |
| "mean_token_accuracy": 0.1388566166162491, |
| "num_tokens": 4406626.0, |
| "step": 1575 |
| }, |
| { |
| "entropy": 5.756133127212524, |
| "epoch": 0.04277495769881557, |
| "grad_norm": 0.88671875, |
| "learning_rate": 0.0004598929419416578, |
| "loss": 5.7679, |
| "mean_token_accuracy": 0.13815426528453828, |
| "num_tokens": 4421131.0, |
| "step": 1580 |
| }, |
| { |
| "entropy": 5.868128299713135, |
| "epoch": 0.042910321489001695, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.00045921906788137123, |
| "loss": 5.76, |
| "mean_token_accuracy": 0.14222174808382987, |
| "num_tokens": 4435107.0, |
| "step": 1585 |
| }, |
| { |
| "entropy": 5.801052570343018, |
| "epoch": 0.04304568527918782, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00045854014336228115, |
| "loss": 5.7288, |
| "mean_token_accuracy": 0.14501179829239846, |
| "num_tokens": 4449294.0, |
| "step": 1590 |
| }, |
| { |
| "entropy": 5.750652313232422, |
| "epoch": 0.04318104906937394, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.00045785618699744615, |
| "loss": 5.6444, |
| "mean_token_accuracy": 0.14286767169833184, |
| "num_tokens": 4462731.0, |
| "step": 1595 |
| }, |
| { |
| "entropy": 5.717151927947998, |
| "epoch": 0.04331641285956007, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00045716721753787543, |
| "loss": 5.7299, |
| "mean_token_accuracy": 0.1389971673488617, |
| "num_tokens": 4476956.0, |
| "step": 1600 |
| }, |
| { |
| "entropy": 5.819956731796265, |
| "epoch": 0.04345177664974619, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0004564732538720148, |
| "loss": 5.7267, |
| "mean_token_accuracy": 0.14786600917577744, |
| "num_tokens": 4491356.0, |
| "step": 1605 |
| }, |
| { |
| "entropy": 5.665336084365845, |
| "epoch": 0.043587140439932316, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00045577431502522877, |
| "loss": 5.7028, |
| "mean_token_accuracy": 0.14309961274266242, |
| "num_tokens": 4504900.0, |
| "step": 1610 |
| }, |
| { |
| "entropy": 5.760229158401489, |
| "epoch": 0.04372250423011844, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.0004550704201592787, |
| "loss": 5.688, |
| "mean_token_accuracy": 0.14546218365430832, |
| "num_tokens": 4517879.0, |
| "step": 1615 |
| }, |
| { |
| "entropy": 5.720965814590454, |
| "epoch": 0.04385786802030457, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004543615885717981, |
| "loss": 5.7713, |
| "mean_token_accuracy": 0.14266854301095008, |
| "num_tokens": 4531356.0, |
| "step": 1620 |
| }, |
| { |
| "entropy": 5.802320337295532, |
| "epoch": 0.043993231810490696, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00045364783969576296, |
| "loss": 5.6383, |
| "mean_token_accuracy": 0.14731594622135163, |
| "num_tokens": 4545262.0, |
| "step": 1625 |
| }, |
| { |
| "entropy": 5.625383090972901, |
| "epoch": 0.04412859560067682, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004529291930989592, |
| "loss": 5.6253, |
| "mean_token_accuracy": 0.14481477811932564, |
| "num_tokens": 4558713.0, |
| "step": 1630 |
| }, |
| { |
| "entropy": 5.767266464233399, |
| "epoch": 0.044263959390862945, |
| "grad_norm": 0.921875, |
| "learning_rate": 0.0004522056684834464, |
| "loss": 5.6935, |
| "mean_token_accuracy": 0.14441011399030684, |
| "num_tokens": 4571891.0, |
| "step": 1635 |
| }, |
| { |
| "entropy": 5.778782510757447, |
| "epoch": 0.04439932318104907, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.0004514772856850173, |
| "loss": 5.6935, |
| "mean_token_accuracy": 0.14748022928833962, |
| "num_tokens": 4585822.0, |
| "step": 1640 |
| }, |
| { |
| "entropy": 5.753904867172241, |
| "epoch": 0.04453468697123519, |
| "grad_norm": 0.9453125, |
| "learning_rate": 0.0004507440646726542, |
| "loss": 5.6979, |
| "mean_token_accuracy": 0.14199129566550256, |
| "num_tokens": 4600023.0, |
| "step": 1645 |
| }, |
| { |
| "entropy": 5.6777363300323485, |
| "epoch": 0.04467005076142132, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004500060255479818, |
| "loss": 5.5957, |
| "mean_token_accuracy": 0.15256337970495223, |
| "num_tokens": 4611259.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 5.784216976165771, |
| "epoch": 0.04480541455160744, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.0004492631885447151, |
| "loss": 5.6981, |
| "mean_token_accuracy": 0.13937234207987786, |
| "num_tokens": 4625195.0, |
| "step": 1655 |
| }, |
| { |
| "entropy": 5.828709125518799, |
| "epoch": 0.04494077834179357, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00044851557402810616, |
| "loss": 5.6685, |
| "mean_token_accuracy": 0.1433462306857109, |
| "num_tokens": 4639159.0, |
| "step": 1660 |
| }, |
| { |
| "entropy": 5.694344997406006, |
| "epoch": 0.0450761421319797, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00044776320249438444, |
| "loss": 5.7065, |
| "mean_token_accuracy": 0.143716399371624, |
| "num_tokens": 4650967.0, |
| "step": 1665 |
| }, |
| { |
| "entropy": 5.757909107208252, |
| "epoch": 0.04521150592216582, |
| "grad_norm": 0.8828125, |
| "learning_rate": 0.00044700609457019565, |
| "loss": 5.6969, |
| "mean_token_accuracy": 0.14098843336105346, |
| "num_tokens": 4667107.0, |
| "step": 1670 |
| }, |
| { |
| "entropy": 5.704726076126098, |
| "epoch": 0.045346869712351946, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.0004462442710120359, |
| "loss": 5.6458, |
| "mean_token_accuracy": 0.15384480953216553, |
| "num_tokens": 4680966.0, |
| "step": 1675 |
| }, |
| { |
| "entropy": 5.788536548614502, |
| "epoch": 0.04548223350253807, |
| "grad_norm": 0.86328125, |
| "learning_rate": 0.000445477752705683, |
| "loss": 5.715, |
| "mean_token_accuracy": 0.14432019889354705, |
| "num_tokens": 4696365.0, |
| "step": 1680 |
| }, |
| { |
| "entropy": 5.778404951095581, |
| "epoch": 0.045617597292724195, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00044470656066562336, |
| "loss": 5.7505, |
| "mean_token_accuracy": 0.14002010300755502, |
| "num_tokens": 4709059.0, |
| "step": 1685 |
| }, |
| { |
| "entropy": 5.779723358154297, |
| "epoch": 0.04575296108291032, |
| "grad_norm": 0.8828125, |
| "learning_rate": 0.0004439307160344765, |
| "loss": 5.6813, |
| "mean_token_accuracy": 0.1479523077607155, |
| "num_tokens": 4722922.0, |
| "step": 1690 |
| }, |
| { |
| "entropy": 5.69294548034668, |
| "epoch": 0.045888324873096444, |
| "grad_norm": 0.921875, |
| "learning_rate": 0.00044315024008241473, |
| "loss": 5.5964, |
| "mean_token_accuracy": 0.15145878940820695, |
| "num_tokens": 4737204.0, |
| "step": 1695 |
| }, |
| { |
| "entropy": 5.7257462501525875, |
| "epoch": 0.046023688663282575, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.0004423651542065806, |
| "loss": 5.6956, |
| "mean_token_accuracy": 0.14550104588270188, |
| "num_tokens": 4752111.0, |
| "step": 1700 |
| }, |
| { |
| "entropy": 5.752708816528321, |
| "epoch": 0.0461590524534687, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00044157547993050006, |
| "loss": 5.6762, |
| "mean_token_accuracy": 0.14675524830818176, |
| "num_tokens": 4766353.0, |
| "step": 1705 |
| }, |
| { |
| "entropy": 5.750765705108643, |
| "epoch": 0.04629441624365482, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00044078123890349227, |
| "loss": 5.7321, |
| "mean_token_accuracy": 0.14695569574832917, |
| "num_tokens": 4779551.0, |
| "step": 1710 |
| }, |
| { |
| "entropy": 5.675897407531738, |
| "epoch": 0.04642978003384095, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00043998245290007606, |
| "loss": 5.6578, |
| "mean_token_accuracy": 0.14759555011987685, |
| "num_tokens": 4794073.0, |
| "step": 1715 |
| }, |
| { |
| "entropy": 5.697209167480469, |
| "epoch": 0.04656514382402707, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.00043917914381937323, |
| "loss": 5.5765, |
| "mean_token_accuracy": 0.15185517072677612, |
| "num_tokens": 4806855.0, |
| "step": 1720 |
| }, |
| { |
| "entropy": 5.63714861869812, |
| "epoch": 0.046700507614213196, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00043837133368450815, |
| "loss": 5.681, |
| "mean_token_accuracy": 0.138708233833313, |
| "num_tokens": 4820880.0, |
| "step": 1725 |
| }, |
| { |
| "entropy": 5.834238338470459, |
| "epoch": 0.04683587140439932, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.0004375590446420037, |
| "loss": 5.6772, |
| "mean_token_accuracy": 0.14852887466549874, |
| "num_tokens": 4833906.0, |
| "step": 1730 |
| }, |
| { |
| "entropy": 5.651483774185181, |
| "epoch": 0.046971235194585445, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.0004367422989611743, |
| "loss": 5.6429, |
| "mean_token_accuracy": 0.15046416074037552, |
| "num_tokens": 4849251.0, |
| "step": 1735 |
| }, |
| { |
| "entropy": 5.713845062255859, |
| "epoch": 0.047106598984771576, |
| "grad_norm": 0.91015625, |
| "learning_rate": 0.0004359211190335153, |
| "loss": 5.6968, |
| "mean_token_accuracy": 0.14156146496534347, |
| "num_tokens": 4863896.0, |
| "step": 1740 |
| }, |
| { |
| "entropy": 5.769553709030151, |
| "epoch": 0.0472419627749577, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00043509552737208923, |
| "loss": 5.655, |
| "mean_token_accuracy": 0.15236809402704238, |
| "num_tokens": 4876392.0, |
| "step": 1745 |
| }, |
| { |
| "entropy": 5.665567684173584, |
| "epoch": 0.047377326565143825, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.00043426554661090853, |
| "loss": 5.6206, |
| "mean_token_accuracy": 0.15215253382921218, |
| "num_tokens": 4889803.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 5.653515958786011, |
| "epoch": 0.04751269035532995, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.00043343119950431516, |
| "loss": 5.5148, |
| "mean_token_accuracy": 0.1512528494000435, |
| "num_tokens": 4903975.0, |
| "step": 1755 |
| }, |
| { |
| "entropy": 5.731270265579224, |
| "epoch": 0.047648054145516074, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00043259250892635644, |
| "loss": 5.7402, |
| "mean_token_accuracy": 0.14076657742261886, |
| "num_tokens": 4916667.0, |
| "step": 1760 |
| }, |
| { |
| "entropy": 5.772264051437378, |
| "epoch": 0.0477834179357022, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.0004317494978701582, |
| "loss": 5.6871, |
| "mean_token_accuracy": 0.15338942259550095, |
| "num_tokens": 4929908.0, |
| "step": 1765 |
| }, |
| { |
| "entropy": 5.600496244430542, |
| "epoch": 0.04791878172588832, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.0004309021894472943, |
| "loss": 5.5895, |
| "mean_token_accuracy": 0.1531106323003769, |
| "num_tokens": 4943685.0, |
| "step": 1770 |
| }, |
| { |
| "entropy": 5.86819052696228, |
| "epoch": 0.048054145516074454, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004300506068871534, |
| "loss": 5.7578, |
| "mean_token_accuracy": 0.13543773368000983, |
| "num_tokens": 4959796.0, |
| "step": 1775 |
| }, |
| { |
| "entropy": 5.58793797492981, |
| "epoch": 0.04818950930626058, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00042919477353630135, |
| "loss": 5.5691, |
| "mean_token_accuracy": 0.15354569405317306, |
| "num_tokens": 4973208.0, |
| "step": 1780 |
| }, |
| { |
| "entropy": 5.736422824859619, |
| "epoch": 0.0483248730964467, |
| "grad_norm": 0.8671875, |
| "learning_rate": 0.000428334712857842, |
| "loss": 5.6892, |
| "mean_token_accuracy": 0.14086781814694405, |
| "num_tokens": 4989755.0, |
| "step": 1785 |
| }, |
| { |
| "entropy": 5.694100475311279, |
| "epoch": 0.048460236886632826, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00042747044843077304, |
| "loss": 5.6608, |
| "mean_token_accuracy": 0.14808935225009917, |
| "num_tokens": 5003501.0, |
| "step": 1790 |
| }, |
| { |
| "entropy": 5.70287938117981, |
| "epoch": 0.04859560067681895, |
| "grad_norm": 0.93359375, |
| "learning_rate": 0.00042660200394934047, |
| "loss": 5.691, |
| "mean_token_accuracy": 0.1464019276201725, |
| "num_tokens": 5016657.0, |
| "step": 1795 |
| }, |
| { |
| "entropy": 5.6858762264251705, |
| "epoch": 0.048730964467005075, |
| "grad_norm": 0.93359375, |
| "learning_rate": 0.00042572940322238844, |
| "loss": 5.6081, |
| "mean_token_accuracy": 0.1505765825510025, |
| "num_tokens": 5029741.0, |
| "step": 1800 |
| }, |
| { |
| "entropy": 5.6079450130462645, |
| "epoch": 0.0488663282571912, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00042485267017270664, |
| "loss": 5.5026, |
| "mean_token_accuracy": 0.15048226863145828, |
| "num_tokens": 5042973.0, |
| "step": 1805 |
| }, |
| { |
| "entropy": 5.652156972885132, |
| "epoch": 0.049001692047377324, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.0004239718288363745, |
| "loss": 5.5519, |
| "mean_token_accuracy": 0.151530858874321, |
| "num_tokens": 5057981.0, |
| "step": 1810 |
| }, |
| { |
| "entropy": 5.653716611862182, |
| "epoch": 0.049137055837563455, |
| "grad_norm": 0.89453125, |
| "learning_rate": 0.0004230869033621023, |
| "loss": 5.6339, |
| "mean_token_accuracy": 0.13919498771429062, |
| "num_tokens": 5072832.0, |
| "step": 1815 |
| }, |
| { |
| "entropy": 5.74049973487854, |
| "epoch": 0.04927241962774958, |
| "grad_norm": 0.89453125, |
| "learning_rate": 0.0004221979180105688, |
| "loss": 5.6291, |
| "mean_token_accuracy": 0.14582021906971931, |
| "num_tokens": 5086141.0, |
| "step": 1820 |
| }, |
| { |
| "entropy": 5.67672643661499, |
| "epoch": 0.049407783417935704, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.00042130489715375645, |
| "loss": 5.6638, |
| "mean_token_accuracy": 0.146046045422554, |
| "num_tokens": 5100480.0, |
| "step": 1825 |
| }, |
| { |
| "entropy": 5.680028295516967, |
| "epoch": 0.04954314720812183, |
| "grad_norm": 0.89453125, |
| "learning_rate": 0.00042040786527428335, |
| "loss": 5.5843, |
| "mean_token_accuracy": 0.14439646974205972, |
| "num_tokens": 5117197.0, |
| "step": 1830 |
| }, |
| { |
| "entropy": 5.5879209518432615, |
| "epoch": 0.04967851099830795, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.0004195068469647315, |
| "loss": 5.5534, |
| "mean_token_accuracy": 0.1488366484642029, |
| "num_tokens": 5132561.0, |
| "step": 1835 |
| }, |
| { |
| "entropy": 5.6617508888244625, |
| "epoch": 0.04981387478849408, |
| "grad_norm": 0.93359375, |
| "learning_rate": 0.00041860186692697297, |
| "loss": 5.7145, |
| "mean_token_accuracy": 0.1438066452741623, |
| "num_tokens": 5146905.0, |
| "step": 1840 |
| }, |
| { |
| "entropy": 5.724303245544434, |
| "epoch": 0.0499492385786802, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00041769294997149264, |
| "loss": 5.5646, |
| "mean_token_accuracy": 0.15083335638046264, |
| "num_tokens": 5161581.0, |
| "step": 1845 |
| }, |
| { |
| "entropy": 5.6070271015167235, |
| "epoch": 0.050084602368866325, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.0004167801210167081, |
| "loss": 5.5805, |
| "mean_token_accuracy": 0.1544129729270935, |
| "num_tokens": 5176317.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 5.684096813201904, |
| "epoch": 0.05021996615905246, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004158634050882861, |
| "loss": 5.5168, |
| "mean_token_accuracy": 0.15208376348018646, |
| "num_tokens": 5188651.0, |
| "step": 1855 |
| }, |
| { |
| "entropy": 5.55376296043396, |
| "epoch": 0.05035532994923858, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.0004149428273184569, |
| "loss": 5.5148, |
| "mean_token_accuracy": 0.15063736736774444, |
| "num_tokens": 5202035.0, |
| "step": 1860 |
| }, |
| { |
| "entropy": 5.612833023071289, |
| "epoch": 0.050490693739424705, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004140184129453253, |
| "loss": 5.486, |
| "mean_token_accuracy": 0.1544868603348732, |
| "num_tokens": 5215471.0, |
| "step": 1865 |
| }, |
| { |
| "entropy": 5.704241132736206, |
| "epoch": 0.05062605752961083, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.000413090187312178, |
| "loss": 5.6414, |
| "mean_token_accuracy": 0.1538958489894867, |
| "num_tokens": 5228328.0, |
| "step": 1870 |
| }, |
| { |
| "entropy": 5.698283338546753, |
| "epoch": 0.050761421319796954, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.0004121581758667898, |
| "loss": 5.6058, |
| "mean_token_accuracy": 0.1486688494682312, |
| "num_tokens": 5240586.0, |
| "step": 1875 |
| }, |
| { |
| "entropy": 5.515977621078491, |
| "epoch": 0.05089678510998308, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00041122240416072533, |
| "loss": 5.4453, |
| "mean_token_accuracy": 0.15285620093345642, |
| "num_tokens": 5252569.0, |
| "step": 1880 |
| }, |
| { |
| "entropy": 5.644832372665405, |
| "epoch": 0.0510321489001692, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004102828978486385, |
| "loss": 5.6534, |
| "mean_token_accuracy": 0.14334431514143944, |
| "num_tokens": 5264975.0, |
| "step": 1885 |
| }, |
| { |
| "entropy": 5.681633806228637, |
| "epoch": 0.05116751269035533, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.0004093396826875695, |
| "loss": 5.527, |
| "mean_token_accuracy": 0.15328461825847625, |
| "num_tokens": 5279688.0, |
| "step": 1890 |
| }, |
| { |
| "entropy": 5.622284603118897, |
| "epoch": 0.05130287648054146, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.00040839278453623837, |
| "loss": 5.5739, |
| "mean_token_accuracy": 0.15425852686166763, |
| "num_tokens": 5294266.0, |
| "step": 1895 |
| }, |
| { |
| "entropy": 5.633177900314331, |
| "epoch": 0.05143824027072758, |
| "grad_norm": 0.9453125, |
| "learning_rate": 0.0004074422293543363, |
| "loss": 5.5835, |
| "mean_token_accuracy": 0.14945923388004304, |
| "num_tokens": 5308719.0, |
| "step": 1900 |
| }, |
| { |
| "entropy": 5.672901391983032, |
| "epoch": 0.05157360406091371, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.0004064880432018137, |
| "loss": 5.6778, |
| "mean_token_accuracy": 0.1480257421731949, |
| "num_tokens": 5324227.0, |
| "step": 1905 |
| }, |
| { |
| "entropy": 5.7078780174255375, |
| "epoch": 0.05170896785109983, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00040553025223816615, |
| "loss": 5.603, |
| "mean_token_accuracy": 0.153351391851902, |
| "num_tokens": 5338353.0, |
| "step": 1910 |
| }, |
| { |
| "entropy": 5.629157209396363, |
| "epoch": 0.051844331641285955, |
| "grad_norm": 0.8828125, |
| "learning_rate": 0.00040456888272171653, |
| "loss": 5.4822, |
| "mean_token_accuracy": 0.1563638061285019, |
| "num_tokens": 5354182.0, |
| "step": 1915 |
| }, |
| { |
| "entropy": 5.617384052276611, |
| "epoch": 0.05197969543147208, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00040360396100889577, |
| "loss": 5.6056, |
| "mean_token_accuracy": 0.14689816236495973, |
| "num_tokens": 5366448.0, |
| "step": 1920 |
| }, |
| { |
| "entropy": 5.651615858078003, |
| "epoch": 0.052115059221658204, |
| "grad_norm": 0.87109375, |
| "learning_rate": 0.0004026355135535202, |
| "loss": 5.5636, |
| "mean_token_accuracy": 0.1531040221452713, |
| "num_tokens": 5381430.0, |
| "step": 1925 |
| }, |
| { |
| "entropy": 5.6194452285766605, |
| "epoch": 0.05225042301184433, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000401663566906066, |
| "loss": 5.5743, |
| "mean_token_accuracy": 0.15186812579631806, |
| "num_tokens": 5393626.0, |
| "step": 1930 |
| }, |
| { |
| "entropy": 5.7036806583404545, |
| "epoch": 0.05238578680203046, |
| "grad_norm": 0.9375, |
| "learning_rate": 0.00040068814771294134, |
| "loss": 5.5539, |
| "mean_token_accuracy": 0.15736090689897536, |
| "num_tokens": 5407257.0, |
| "step": 1935 |
| }, |
| { |
| "entropy": 5.583117723464966, |
| "epoch": 0.052521150592216584, |
| "grad_norm": 0.90234375, |
| "learning_rate": 0.0003997092827157562, |
| "loss": 5.5588, |
| "mean_token_accuracy": 0.14819036424160004, |
| "num_tokens": 5421798.0, |
| "step": 1940 |
| }, |
| { |
| "entropy": 5.655210685729981, |
| "epoch": 0.05265651438240271, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.000398726998750589, |
| "loss": 5.5823, |
| "mean_token_accuracy": 0.1502937689423561, |
| "num_tokens": 5437455.0, |
| "step": 1945 |
| }, |
| { |
| "entropy": 5.628138160705566, |
| "epoch": 0.05279187817258883, |
| "grad_norm": 0.828125, |
| "learning_rate": 0.00039774132274725076, |
| "loss": 5.508, |
| "mean_token_accuracy": 0.15878963768482207, |
| "num_tokens": 5451593.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 5.5857048511505125, |
| "epoch": 0.05292724196277496, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00039675228172854707, |
| "loss": 5.5671, |
| "mean_token_accuracy": 0.15036417841911315, |
| "num_tokens": 5466807.0, |
| "step": 1955 |
| }, |
| { |
| "entropy": 5.578492784500122, |
| "epoch": 0.05306260575296108, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0003957599028095371, |
| "loss": 5.472, |
| "mean_token_accuracy": 0.15736704617738723, |
| "num_tokens": 5480113.0, |
| "step": 1960 |
| }, |
| { |
| "entropy": 5.58995213508606, |
| "epoch": 0.053197969543147205, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.00039476421319679017, |
| "loss": 5.576, |
| "mean_token_accuracy": 0.14943182319402695, |
| "num_tokens": 5494694.0, |
| "step": 1965 |
| }, |
| { |
| "entropy": 5.649091339111328, |
| "epoch": 0.05333333333333334, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.00039376524018764, |
| "loss": 5.5204, |
| "mean_token_accuracy": 0.15763673931360245, |
| "num_tokens": 5508858.0, |
| "step": 1970 |
| }, |
| { |
| "entropy": 5.544556760787964, |
| "epoch": 0.05346869712351946, |
| "grad_norm": 0.9765625, |
| "learning_rate": 0.00039276301116943616, |
| "loss": 5.4916, |
| "mean_token_accuracy": 0.1559601128101349, |
| "num_tokens": 5523142.0, |
| "step": 1975 |
| }, |
| { |
| "entropy": 5.637435817718506, |
| "epoch": 0.053604060913705585, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0003917575536187936, |
| "loss": 5.5495, |
| "mean_token_accuracy": 0.1537593424320221, |
| "num_tokens": 5536882.0, |
| "step": 1980 |
| }, |
| { |
| "entropy": 5.666303062438965, |
| "epoch": 0.05373942470389171, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00039074889510083894, |
| "loss": 5.5746, |
| "mean_token_accuracy": 0.14690756425261497, |
| "num_tokens": 5550882.0, |
| "step": 1985 |
| }, |
| { |
| "entropy": 5.601831579208374, |
| "epoch": 0.053874788494077834, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.00038973706326845495, |
| "loss": 5.5869, |
| "mean_token_accuracy": 0.14608050435781478, |
| "num_tokens": 5566187.0, |
| "step": 1990 |
| }, |
| { |
| "entropy": 5.604721736907959, |
| "epoch": 0.05401015228426396, |
| "grad_norm": 0.87890625, |
| "learning_rate": 0.0003887220858615225, |
| "loss": 5.5083, |
| "mean_token_accuracy": 0.1559429183602333, |
| "num_tokens": 5580568.0, |
| "step": 1995 |
| }, |
| { |
| "entropy": 5.609822750091553, |
| "epoch": 0.05414551607445008, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.0003877039907061597, |
| "loss": 5.5986, |
| "mean_token_accuracy": 0.15086540579795837, |
| "num_tokens": 5594827.0, |
| "step": 2000 |
| }, |
| { |
| "entropy": 5.6352800846099855, |
| "epoch": 0.05428087986463621, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003866828057139598, |
| "loss": 5.5726, |
| "mean_token_accuracy": 0.14980787187814712, |
| "num_tokens": 5607643.0, |
| "step": 2005 |
| }, |
| { |
| "entropy": 5.583590316772461, |
| "epoch": 0.05441624365482234, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00038565855888122503, |
| "loss": 5.5041, |
| "mean_token_accuracy": 0.1583167791366577, |
| "num_tokens": 5619178.0, |
| "step": 2010 |
| }, |
| { |
| "entropy": 5.708728361129761, |
| "epoch": 0.05455160744500846, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.00038463127828819975, |
| "loss": 5.5384, |
| "mean_token_accuracy": 0.15386256724596023, |
| "num_tokens": 5632724.0, |
| "step": 2015 |
| }, |
| { |
| "entropy": 5.479742050170898, |
| "epoch": 0.05468697123519459, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00038360099209830043, |
| "loss": 5.5745, |
| "mean_token_accuracy": 0.15379853323101997, |
| "num_tokens": 5646090.0, |
| "step": 2020 |
| }, |
| { |
| "entropy": 5.633185243606567, |
| "epoch": 0.05482233502538071, |
| "grad_norm": 0.93359375, |
| "learning_rate": 0.0003825677285573433, |
| "loss": 5.507, |
| "mean_token_accuracy": 0.15375496149063111, |
| "num_tokens": 5660734.0, |
| "step": 2025 |
| }, |
| { |
| "entropy": 5.631849336624145, |
| "epoch": 0.054957698815566836, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00038153151599277027, |
| "loss": 5.5224, |
| "mean_token_accuracy": 0.15756209194660187, |
| "num_tokens": 5674885.0, |
| "step": 2030 |
| }, |
| { |
| "entropy": 5.569233798980713, |
| "epoch": 0.05509306260575296, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.0003804923828128723, |
| "loss": 5.4979, |
| "mean_token_accuracy": 0.15912836641073227, |
| "num_tokens": 5687464.0, |
| "step": 2035 |
| }, |
| { |
| "entropy": 5.671593904495239, |
| "epoch": 0.055228426395939084, |
| "grad_norm": 0.91015625, |
| "learning_rate": 0.0003794503575060104, |
| "loss": 5.5796, |
| "mean_token_accuracy": 0.15338214933872224, |
| "num_tokens": 5701569.0, |
| "step": 2040 |
| }, |
| { |
| "entropy": 5.604352951049805, |
| "epoch": 0.05536379018612521, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.00037840546863983484, |
| "loss": 5.5662, |
| "mean_token_accuracy": 0.14921343475580215, |
| "num_tokens": 5716021.0, |
| "step": 2045 |
| }, |
| { |
| "entropy": 5.676676845550537, |
| "epoch": 0.05549915397631134, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.0003773577448605015, |
| "loss": 5.4733, |
| "mean_token_accuracy": 0.1577136844396591, |
| "num_tokens": 5731219.0, |
| "step": 2050 |
| }, |
| { |
| "entropy": 5.5694435119628904, |
| "epoch": 0.055634517766497464, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0003763072148918872, |
| "loss": 5.566, |
| "mean_token_accuracy": 0.15062549114227294, |
| "num_tokens": 5745864.0, |
| "step": 2055 |
| }, |
| { |
| "entropy": 5.537994909286499, |
| "epoch": 0.05576988155668359, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003752539075348017, |
| "loss": 5.4265, |
| "mean_token_accuracy": 0.16346251368522643, |
| "num_tokens": 5758852.0, |
| "step": 2060 |
| }, |
| { |
| "entropy": 5.655580282211304, |
| "epoch": 0.05590524534686971, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.00037419785166619817, |
| "loss": 5.5961, |
| "mean_token_accuracy": 0.1531015492975712, |
| "num_tokens": 5774474.0, |
| "step": 2065 |
| }, |
| { |
| "entropy": 5.5935293674469, |
| "epoch": 0.05604060913705584, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.0003731390762383818, |
| "loss": 5.4934, |
| "mean_token_accuracy": 0.15586720108985902, |
| "num_tokens": 5788077.0, |
| "step": 2070 |
| }, |
| { |
| "entropy": 5.6637038230896, |
| "epoch": 0.05617597292724196, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.0003720776102782158, |
| "loss": 5.6647, |
| "mean_token_accuracy": 0.1455085203051567, |
| "num_tokens": 5805257.0, |
| "step": 2075 |
| }, |
| { |
| "entropy": 5.570231914520264, |
| "epoch": 0.056311336717428086, |
| "grad_norm": 0.9765625, |
| "learning_rate": 0.00037101348288632555, |
| "loss": 5.431, |
| "mean_token_accuracy": 0.1498264342546463, |
| "num_tokens": 5819518.0, |
| "step": 2080 |
| }, |
| { |
| "entropy": 5.5381348609924315, |
| "epoch": 0.05644670050761421, |
| "grad_norm": 0.9375, |
| "learning_rate": 0.0003699467232363012, |
| "loss": 5.3706, |
| "mean_token_accuracy": 0.16544263809919357, |
| "num_tokens": 5833228.0, |
| "step": 2085 |
| }, |
| { |
| "entropy": 5.588838815689087, |
| "epoch": 0.05658206429780034, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0003688773605738973, |
| "loss": 5.4515, |
| "mean_token_accuracy": 0.15661462396383286, |
| "num_tokens": 5847714.0, |
| "step": 2090 |
| }, |
| { |
| "entropy": 5.516980886459351, |
| "epoch": 0.056717428087986466, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.00036780542421623134, |
| "loss": 5.4794, |
| "mean_token_accuracy": 0.15581640005111694, |
| "num_tokens": 5861775.0, |
| "step": 2095 |
| }, |
| { |
| "entropy": 5.556796646118164, |
| "epoch": 0.05685279187817259, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.0003667309435509802, |
| "loss": 5.5511, |
| "mean_token_accuracy": 0.15586237907409667, |
| "num_tokens": 5875679.0, |
| "step": 2100 |
| }, |
| { |
| "entropy": 5.692843914031982, |
| "epoch": 0.056988155668358714, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.0003656539480355741, |
| "loss": 5.6027, |
| "mean_token_accuracy": 0.15197229087352754, |
| "num_tokens": 5889127.0, |
| "step": 2105 |
| }, |
| { |
| "entropy": 5.658493995666504, |
| "epoch": 0.05712351945854484, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0003645744671963891, |
| "loss": 5.5212, |
| "mean_token_accuracy": 0.16027260273694993, |
| "num_tokens": 5902710.0, |
| "step": 2110 |
| }, |
| { |
| "entropy": 5.55581750869751, |
| "epoch": 0.05725888324873096, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0003634925306279376, |
| "loss": 5.5784, |
| "mean_token_accuracy": 0.1552097924053669, |
| "num_tokens": 5914823.0, |
| "step": 2115 |
| }, |
| { |
| "entropy": 5.566669940948486, |
| "epoch": 0.05739424703891709, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.0003624081679920574, |
| "loss": 5.5149, |
| "mean_token_accuracy": 0.15782447010278702, |
| "num_tokens": 5929553.0, |
| "step": 2120 |
| }, |
| { |
| "entropy": 5.509809684753418, |
| "epoch": 0.05752961082910321, |
| "grad_norm": 0.9140625, |
| "learning_rate": 0.0003613214090170977, |
| "loss": 5.416, |
| "mean_token_accuracy": 0.16114599555730819, |
| "num_tokens": 5942364.0, |
| "step": 2125 |
| }, |
| { |
| "entropy": 5.570280456542969, |
| "epoch": 0.05766497461928934, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.0003602322834971048, |
| "loss": 5.5507, |
| "mean_token_accuracy": 0.15223699808120728, |
| "num_tokens": 5954874.0, |
| "step": 2130 |
| }, |
| { |
| "entropy": 5.599170875549317, |
| "epoch": 0.05780033840947547, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.0003591408212910051, |
| "loss": 5.4627, |
| "mean_token_accuracy": 0.15489756017923356, |
| "num_tokens": 5968635.0, |
| "step": 2135 |
| }, |
| { |
| "entropy": 5.590338897705078, |
| "epoch": 0.05793570219966159, |
| "grad_norm": 0.9765625, |
| "learning_rate": 0.0003580470523217863, |
| "loss": 5.559, |
| "mean_token_accuracy": 0.1588521420955658, |
| "num_tokens": 5983887.0, |
| "step": 2140 |
| }, |
| { |
| "entropy": 5.656904172897339, |
| "epoch": 0.058071065989847716, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.0003569510065756771, |
| "loss": 5.5177, |
| "mean_token_accuracy": 0.14795053601264954, |
| "num_tokens": 5998996.0, |
| "step": 2145 |
| }, |
| { |
| "entropy": 5.560834264755249, |
| "epoch": 0.05820642978003384, |
| "grad_norm": 0.9140625, |
| "learning_rate": 0.0003558527141013254, |
| "loss": 5.4962, |
| "mean_token_accuracy": 0.1533253774046898, |
| "num_tokens": 6013399.0, |
| "step": 2150 |
| }, |
| { |
| "entropy": 5.6488504886627195, |
| "epoch": 0.058341793570219964, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0003547522050089742, |
| "loss": 5.5268, |
| "mean_token_accuracy": 0.154144811630249, |
| "num_tokens": 6025858.0, |
| "step": 2155 |
| }, |
| { |
| "entropy": 5.50015172958374, |
| "epoch": 0.05847715736040609, |
| "grad_norm": 0.8828125, |
| "learning_rate": 0.00035364950946963606, |
| "loss": 5.4178, |
| "mean_token_accuracy": 0.1639969304203987, |
| "num_tokens": 6040129.0, |
| "step": 2160 |
| }, |
| { |
| "entropy": 5.572449398040772, |
| "epoch": 0.05861252115059222, |
| "grad_norm": 0.9375, |
| "learning_rate": 0.0003525446577142663, |
| "loss": 5.5237, |
| "mean_token_accuracy": 0.15481064915657045, |
| "num_tokens": 6052988.0, |
| "step": 2165 |
| }, |
| { |
| "entropy": 5.599097108840942, |
| "epoch": 0.058747884940778344, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.00035143768003293395, |
| "loss": 5.4731, |
| "mean_token_accuracy": 0.16200729161500932, |
| "num_tokens": 6066901.0, |
| "step": 2170 |
| }, |
| { |
| "entropy": 5.604894495010376, |
| "epoch": 0.05888324873096447, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0003503286067739913, |
| "loss": 5.4809, |
| "mean_token_accuracy": 0.15721836537122727, |
| "num_tokens": 6080221.0, |
| "step": 2175 |
| }, |
| { |
| "entropy": 5.617720413208008, |
| "epoch": 0.05901861252115059, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00034921746834324193, |
| "loss": 5.5341, |
| "mean_token_accuracy": 0.14920639246702194, |
| "num_tokens": 6093591.0, |
| "step": 2180 |
| }, |
| { |
| "entropy": 5.5153953552246096, |
| "epoch": 0.05915397631133672, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.0003481042952031072, |
| "loss": 5.4102, |
| "mean_token_accuracy": 0.15838973969221115, |
| "num_tokens": 6107427.0, |
| "step": 2185 |
| }, |
| { |
| "entropy": 5.622984933853149, |
| "epoch": 0.05928934010152284, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.0003469891178717911, |
| "loss": 5.5577, |
| "mean_token_accuracy": 0.15597878992557526, |
| "num_tokens": 6121355.0, |
| "step": 2190 |
| }, |
| { |
| "entropy": 5.5580566883087155, |
| "epoch": 0.059424703891708966, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0003458719669224436, |
| "loss": 5.5422, |
| "mean_token_accuracy": 0.15654557049274445, |
| "num_tokens": 6133328.0, |
| "step": 2195 |
| }, |
| { |
| "entropy": 5.6222865104675295, |
| "epoch": 0.05956006768189509, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.0003447528729823221, |
| "loss": 5.4815, |
| "mean_token_accuracy": 0.15166250467300416, |
| "num_tokens": 6149486.0, |
| "step": 2200 |
| }, |
| { |
| "entropy": 5.561207914352417, |
| "epoch": 0.05969543147208122, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0003436318667319525, |
| "loss": 5.4912, |
| "mean_token_accuracy": 0.1630606085062027, |
| "num_tokens": 6161447.0, |
| "step": 2205 |
| }, |
| { |
| "entropy": 5.557836532592773, |
| "epoch": 0.059830795262267346, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.00034250897890428716, |
| "loss": 5.5187, |
| "mean_token_accuracy": 0.15890539884567262, |
| "num_tokens": 6176368.0, |
| "step": 2210 |
| }, |
| { |
| "entropy": 5.5497699737548825, |
| "epoch": 0.05996615905245347, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.0003413842402838633, |
| "loss": 5.4567, |
| "mean_token_accuracy": 0.1620472937822342, |
| "num_tokens": 6190248.0, |
| "step": 2215 |
| }, |
| { |
| "entropy": 5.514479446411133, |
| "epoch": 0.060101522842639594, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.00034025768170595834, |
| "loss": 5.3753, |
| "mean_token_accuracy": 0.16145753711462021, |
| "num_tokens": 6205507.0, |
| "step": 2220 |
| }, |
| { |
| "entropy": 5.512839603424072, |
| "epoch": 0.06023688663282572, |
| "grad_norm": 0.875, |
| "learning_rate": 0.0003391293340557446, |
| "loss": 5.4593, |
| "mean_token_accuracy": 0.15989638343453408, |
| "num_tokens": 6218970.0, |
| "step": 2225 |
| }, |
| { |
| "entropy": 5.630588674545288, |
| "epoch": 0.06037225042301184, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0003379992282674431, |
| "loss": 5.5762, |
| "mean_token_accuracy": 0.15546667575836182, |
| "num_tokens": 6232095.0, |
| "step": 2230 |
| }, |
| { |
| "entropy": 5.60104660987854, |
| "epoch": 0.06050761421319797, |
| "grad_norm": 0.8203125, |
| "learning_rate": 0.0003368673953234749, |
| "loss": 5.4843, |
| "mean_token_accuracy": 0.16127849221229554, |
| "num_tokens": 6247195.0, |
| "step": 2235 |
| }, |
| { |
| "entropy": 5.5306642055511475, |
| "epoch": 0.06064297800338409, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.00033573386625361176, |
| "loss": 5.5001, |
| "mean_token_accuracy": 0.15367966145277023, |
| "num_tokens": 6262704.0, |
| "step": 2240 |
| }, |
| { |
| "entropy": 5.612587547302246, |
| "epoch": 0.06077834179357022, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.00033459867213412567, |
| "loss": 5.5317, |
| "mean_token_accuracy": 0.15857135504484177, |
| "num_tokens": 6277115.0, |
| "step": 2245 |
| }, |
| { |
| "entropy": 5.64555606842041, |
| "epoch": 0.06091370558375635, |
| "grad_norm": 0.9453125, |
| "learning_rate": 0.000333461844086937, |
| "loss": 5.5412, |
| "mean_token_accuracy": 0.15073265060782431, |
| "num_tokens": 6291597.0, |
| "step": 2250 |
| }, |
| { |
| "entropy": 5.520713806152344, |
| "epoch": 0.06104906937394247, |
| "grad_norm": 0.90234375, |
| "learning_rate": 0.00033232341327876097, |
| "loss": 5.4102, |
| "mean_token_accuracy": 0.16134743243455887, |
| "num_tokens": 6306256.0, |
| "step": 2255 |
| }, |
| { |
| "entropy": 5.444108724594116, |
| "epoch": 0.061184433164128596, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.0003311834109202531, |
| "loss": 5.4201, |
| "mean_token_accuracy": 0.16176949292421341, |
| "num_tokens": 6320853.0, |
| "step": 2260 |
| }, |
| { |
| "entropy": 5.6139593601226805, |
| "epoch": 0.06131979695431472, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.00033004186826515416, |
| "loss": 5.4732, |
| "mean_token_accuracy": 0.15738911405205727, |
| "num_tokens": 6334681.0, |
| "step": 2265 |
| }, |
| { |
| "entropy": 5.526891708374023, |
| "epoch": 0.061455160744500845, |
| "grad_norm": 0.9140625, |
| "learning_rate": 0.0003288988166094324, |
| "loss": 5.4956, |
| "mean_token_accuracy": 0.15784757435321808, |
| "num_tokens": 6350426.0, |
| "step": 2270 |
| }, |
| { |
| "entropy": 5.58657021522522, |
| "epoch": 0.06159052453468697, |
| "grad_norm": 0.921875, |
| "learning_rate": 0.00032775428729042656, |
| "loss": 5.4416, |
| "mean_token_accuracy": 0.16237595677375793, |
| "num_tokens": 6364646.0, |
| "step": 2275 |
| }, |
| { |
| "entropy": 5.508593463897705, |
| "epoch": 0.06172588832487309, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.000326608311685986, |
| "loss": 5.4866, |
| "mean_token_accuracy": 0.16056797206401824, |
| "num_tokens": 6380020.0, |
| "step": 2280 |
| }, |
| { |
| "entropy": 5.6077048778533936, |
| "epoch": 0.061861252115059225, |
| "grad_norm": 0.91015625, |
| "learning_rate": 0.0003254609212136108, |
| "loss": 5.4236, |
| "mean_token_accuracy": 0.16293450444936752, |
| "num_tokens": 6393124.0, |
| "step": 2285 |
| }, |
| { |
| "entropy": 5.595155477523804, |
| "epoch": 0.06199661590524535, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.00032431214732959036, |
| "loss": 5.5536, |
| "mean_token_accuracy": 0.1563761591911316, |
| "num_tokens": 6409125.0, |
| "step": 2290 |
| }, |
| { |
| "entropy": 5.585239553451538, |
| "epoch": 0.06213197969543147, |
| "grad_norm": 0.8828125, |
| "learning_rate": 0.000323162021528141, |
| "loss": 5.4177, |
| "mean_token_accuracy": 0.16349790394306182, |
| "num_tokens": 6423597.0, |
| "step": 2295 |
| }, |
| { |
| "entropy": 5.47139458656311, |
| "epoch": 0.0622673434856176, |
| "grad_norm": 0.86328125, |
| "learning_rate": 0.00032201057534054264, |
| "loss": 5.349, |
| "mean_token_accuracy": 0.16430194079875945, |
| "num_tokens": 6437897.0, |
| "step": 2300 |
| }, |
| { |
| "entropy": 5.547074794769287, |
| "epoch": 0.06240270727580372, |
| "grad_norm": 0.91015625, |
| "learning_rate": 0.00032085784033427414, |
| "loss": 5.5022, |
| "mean_token_accuracy": 0.15308141559362412, |
| "num_tokens": 6451760.0, |
| "step": 2305 |
| }, |
| { |
| "entropy": 5.511609315872192, |
| "epoch": 0.06253807106598985, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0003197038481121478, |
| "loss": 5.3525, |
| "mean_token_accuracy": 0.16880294680595398, |
| "num_tokens": 6465182.0, |
| "step": 2310 |
| }, |
| { |
| "entropy": 5.574721622467041, |
| "epoch": 0.06267343485617598, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.0003185486303114436, |
| "loss": 5.4606, |
| "mean_token_accuracy": 0.15778982043266296, |
| "num_tokens": 6479146.0, |
| "step": 2315 |
| }, |
| { |
| "entropy": 5.50466685295105, |
| "epoch": 0.0628087986463621, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.0003173922186030409, |
| "loss": 5.3229, |
| "mean_token_accuracy": 0.16876034587621688, |
| "num_tokens": 6492562.0, |
| "step": 2320 |
| }, |
| { |
| "entropy": 5.41968674659729, |
| "epoch": 0.06294416243654823, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000316234644690551, |
| "loss": 5.38, |
| "mean_token_accuracy": 0.16006240993738174, |
| "num_tokens": 6506530.0, |
| "step": 2325 |
| }, |
| { |
| "entropy": 5.528688192367554, |
| "epoch": 0.06307952622673435, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.0003150759403094473, |
| "loss": 5.434, |
| "mean_token_accuracy": 0.16276055127382277, |
| "num_tokens": 6521676.0, |
| "step": 2330 |
| }, |
| { |
| "entropy": 5.513411903381348, |
| "epoch": 0.06321489001692047, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00031391613722619587, |
| "loss": 5.3759, |
| "mean_token_accuracy": 0.1745678424835205, |
| "num_tokens": 6532997.0, |
| "step": 2335 |
| }, |
| { |
| "entropy": 5.529337978363037, |
| "epoch": 0.0633502538071066, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.000312755267237384, |
| "loss": 5.4224, |
| "mean_token_accuracy": 0.16465317010879515, |
| "num_tokens": 6548174.0, |
| "step": 2340 |
| }, |
| { |
| "entropy": 5.6073933124542235, |
| "epoch": 0.06348561759729272, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.0003115933621688488, |
| "loss": 5.5427, |
| "mean_token_accuracy": 0.15725521594285966, |
| "num_tokens": 6563064.0, |
| "step": 2345 |
| }, |
| { |
| "entropy": 5.537544775009155, |
| "epoch": 0.06362098138747885, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00031043045387480487, |
| "loss": 5.5134, |
| "mean_token_accuracy": 0.15672265142202377, |
| "num_tokens": 6576582.0, |
| "step": 2350 |
| }, |
| { |
| "entropy": 5.655880641937256, |
| "epoch": 0.06375634517766497, |
| "grad_norm": 0.90234375, |
| "learning_rate": 0.0003092665742369703, |
| "loss": 5.4981, |
| "mean_token_accuracy": 0.153935007750988, |
| "num_tokens": 6592583.0, |
| "step": 2355 |
| }, |
| { |
| "entropy": 5.640050649642944, |
| "epoch": 0.0638917089678511, |
| "grad_norm": 0.8984375, |
| "learning_rate": 0.00030810175516369343, |
| "loss": 5.5216, |
| "mean_token_accuracy": 0.1580222949385643, |
| "num_tokens": 6608513.0, |
| "step": 2360 |
| }, |
| { |
| "entropy": 5.569810676574707, |
| "epoch": 0.06402707275803722, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.0003069360285890775, |
| "loss": 5.4921, |
| "mean_token_accuracy": 0.15731192976236344, |
| "num_tokens": 6622427.0, |
| "step": 2365 |
| }, |
| { |
| "entropy": 5.60255537033081, |
| "epoch": 0.06416243654822334, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.00030576942647210547, |
| "loss": 5.4613, |
| "mean_token_accuracy": 0.16770876348018646, |
| "num_tokens": 6636196.0, |
| "step": 2370 |
| }, |
| { |
| "entropy": 5.543747758865356, |
| "epoch": 0.06429780033840947, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00030460198079576355, |
| "loss": 5.4506, |
| "mean_token_accuracy": 0.16442616730928422, |
| "num_tokens": 6648393.0, |
| "step": 2375 |
| }, |
| { |
| "entropy": 5.5761157989501955, |
| "epoch": 0.06443316412859561, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.0003034337235661648, |
| "loss": 5.4201, |
| "mean_token_accuracy": 0.16427001357078552, |
| "num_tokens": 6662062.0, |
| "step": 2380 |
| }, |
| { |
| "entropy": 5.5971932888031, |
| "epoch": 0.06456852791878173, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.0003022646868116714, |
| "loss": 5.4853, |
| "mean_token_accuracy": 0.1576756104826927, |
| "num_tokens": 6677299.0, |
| "step": 2385 |
| }, |
| { |
| "entropy": 5.595594882965088, |
| "epoch": 0.06470389170896786, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0003010949025820163, |
| "loss": 5.5071, |
| "mean_token_accuracy": 0.15385562032461167, |
| "num_tokens": 6692573.0, |
| "step": 2390 |
| }, |
| { |
| "entropy": 5.709032297134399, |
| "epoch": 0.06483925549915398, |
| "grad_norm": 0.9453125, |
| "learning_rate": 0.0002999244029474252, |
| "loss": 5.5817, |
| "mean_token_accuracy": 0.15576104819774628, |
| "num_tokens": 6706081.0, |
| "step": 2395 |
| }, |
| { |
| "entropy": 5.572895097732544, |
| "epoch": 0.0649746192893401, |
| "grad_norm": 0.8515625, |
| "learning_rate": 0.00029875321999773684, |
| "loss": 5.4139, |
| "mean_token_accuracy": 0.1568359524011612, |
| "num_tokens": 6721662.0, |
| "step": 2400 |
| }, |
| { |
| "entropy": 5.530266189575196, |
| "epoch": 0.06510998307952623, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00029758138584152333, |
| "loss": 5.5371, |
| "mean_token_accuracy": 0.15827345550060273, |
| "num_tokens": 6735226.0, |
| "step": 2405 |
| }, |
| { |
| "entropy": 5.741498231887817, |
| "epoch": 0.06524534686971235, |
| "grad_norm": 0.87890625, |
| "learning_rate": 0.0002964089326052102, |
| "loss": 5.61, |
| "mean_token_accuracy": 0.1486797995865345, |
| "num_tokens": 6750351.0, |
| "step": 2410 |
| }, |
| { |
| "entropy": 5.482465362548828, |
| "epoch": 0.06538071065989848, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0002952358924321949, |
| "loss": 5.343, |
| "mean_token_accuracy": 0.1717396318912506, |
| "num_tokens": 6762285.0, |
| "step": 2415 |
| }, |
| { |
| "entropy": 5.579564380645752, |
| "epoch": 0.0655160744500846, |
| "grad_norm": 0.9453125, |
| "learning_rate": 0.00029406229748196657, |
| "loss": 5.5056, |
| "mean_token_accuracy": 0.15708825439214708, |
| "num_tokens": 6778866.0, |
| "step": 2420 |
| }, |
| { |
| "entropy": 5.575643253326416, |
| "epoch": 0.06565143824027073, |
| "grad_norm": 0.9140625, |
| "learning_rate": 0.0002928881799292235, |
| "loss": 5.3694, |
| "mean_token_accuracy": 0.16926451921463012, |
| "num_tokens": 6792127.0, |
| "step": 2425 |
| }, |
| { |
| "entropy": 5.550977325439453, |
| "epoch": 0.06578680203045685, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00029171357196299154, |
| "loss": 5.5019, |
| "mean_token_accuracy": 0.15696292817592622, |
| "num_tokens": 6805692.0, |
| "step": 2430 |
| }, |
| { |
| "entropy": 5.502995109558105, |
| "epoch": 0.06592216582064298, |
| "grad_norm": 0.86328125, |
| "learning_rate": 0.0002905385057857414, |
| "loss": 5.4826, |
| "mean_token_accuracy": 0.15718090236186982, |
| "num_tokens": 6820533.0, |
| "step": 2435 |
| }, |
| { |
| "entropy": 5.5539785861969, |
| "epoch": 0.0660575296108291, |
| "grad_norm": 0.8671875, |
| "learning_rate": 0.0002893630136125058, |
| "loss": 5.38, |
| "mean_token_accuracy": 0.1642708361148834, |
| "num_tokens": 6834746.0, |
| "step": 2440 |
| }, |
| { |
| "entropy": 5.579140996932983, |
| "epoch": 0.06619289340101522, |
| "grad_norm": 0.9375, |
| "learning_rate": 0.0002881871276699967, |
| "loss": 5.432, |
| "mean_token_accuracy": 0.1649514243006706, |
| "num_tokens": 6848480.0, |
| "step": 2445 |
| }, |
| { |
| "entropy": 5.482105016708374, |
| "epoch": 0.06632825719120135, |
| "grad_norm": 0.875, |
| "learning_rate": 0.00028701088019572114, |
| "loss": 5.4089, |
| "mean_token_accuracy": 0.16585078686475754, |
| "num_tokens": 6863817.0, |
| "step": 2450 |
| }, |
| { |
| "entropy": 5.485904407501221, |
| "epoch": 0.06646362098138747, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.0002858343034370977, |
| "loss": 5.3672, |
| "mean_token_accuracy": 0.1629736080765724, |
| "num_tokens": 6879028.0, |
| "step": 2455 |
| }, |
| { |
| "entropy": 5.567845058441162, |
| "epoch": 0.06659898477157361, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00028465742965057267, |
| "loss": 5.4993, |
| "mean_token_accuracy": 0.1671033576130867, |
| "num_tokens": 6892582.0, |
| "step": 2460 |
| }, |
| { |
| "entropy": 5.588065147399902, |
| "epoch": 0.06673434856175973, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.00028348029110073533, |
| "loss": 5.3907, |
| "mean_token_accuracy": 0.15922013744711877, |
| "num_tokens": 6905716.0, |
| "step": 2465 |
| }, |
| { |
| "entropy": 5.482119083404541, |
| "epoch": 0.06686971235194586, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00028230292005943365, |
| "loss": 5.3633, |
| "mean_token_accuracy": 0.17306406795978546, |
| "num_tokens": 6920266.0, |
| "step": 2470 |
| }, |
| { |
| "entropy": 5.454979324340821, |
| "epoch": 0.06700507614213198, |
| "grad_norm": 0.83984375, |
| "learning_rate": 0.00028112534880488945, |
| "loss": 5.4226, |
| "mean_token_accuracy": 0.16642075926065444, |
| "num_tokens": 6934274.0, |
| "step": 2475 |
| }, |
| { |
| "entropy": 5.539786052703858, |
| "epoch": 0.06714043993231811, |
| "grad_norm": 0.8984375, |
| "learning_rate": 0.0002799476096208137, |
| "loss": 5.4063, |
| "mean_token_accuracy": 0.16389644294977188, |
| "num_tokens": 6949020.0, |
| "step": 2480 |
| }, |
| { |
| "entropy": 5.504109811782837, |
| "epoch": 0.06727580372250423, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00027876973479552087, |
| "loss": 5.3474, |
| "mean_token_accuracy": 0.16669356375932692, |
| "num_tokens": 6962687.0, |
| "step": 2485 |
| }, |
| { |
| "entropy": 5.562744235992431, |
| "epoch": 0.06741116751269036, |
| "grad_norm": 0.87890625, |
| "learning_rate": 0.00027759175662104424, |
| "loss": 5.5178, |
| "mean_token_accuracy": 0.15945329070091246, |
| "num_tokens": 6977877.0, |
| "step": 2490 |
| }, |
| { |
| "entropy": 5.653814268112183, |
| "epoch": 0.06754653130287648, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.0002764137073922508, |
| "loss": 5.561, |
| "mean_token_accuracy": 0.15105569660663604, |
| "num_tokens": 6992784.0, |
| "step": 2495 |
| }, |
| { |
| "entropy": 5.4771082401275635, |
| "epoch": 0.0676818950930626, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00027523561940595505, |
| "loss": 5.3698, |
| "mean_token_accuracy": 0.17183669209480285, |
| "num_tokens": 7007496.0, |
| "step": 2500 |
| }, |
| { |
| "entropy": 5.495787239074707, |
| "epoch": 0.06781725888324873, |
| "grad_norm": 0.875, |
| "learning_rate": 0.0002740575249600342, |
| "loss": 5.3815, |
| "mean_token_accuracy": 0.16253670752048494, |
| "num_tokens": 7020482.0, |
| "step": 2505 |
| }, |
| { |
| "entropy": 5.591378307342529, |
| "epoch": 0.06795262267343485, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.00027287945635254263, |
| "loss": 5.4631, |
| "mean_token_accuracy": 0.15494969636201858, |
| "num_tokens": 7034021.0, |
| "step": 2510 |
| }, |
| { |
| "entropy": 5.639207792282105, |
| "epoch": 0.06808798646362098, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00027170144588082635, |
| "loss": 5.4504, |
| "mean_token_accuracy": 0.156061589717865, |
| "num_tokens": 7046897.0, |
| "step": 2515 |
| }, |
| { |
| "entropy": 5.4708277702331545, |
| "epoch": 0.0682233502538071, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00027052352584063763, |
| "loss": 5.3641, |
| "mean_token_accuracy": 0.16388892978429795, |
| "num_tokens": 7060916.0, |
| "step": 2520 |
| }, |
| { |
| "entropy": 5.4516136169433596, |
| "epoch": 0.06835871404399323, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00026934572852524907, |
| "loss": 5.3295, |
| "mean_token_accuracy": 0.1627664878964424, |
| "num_tokens": 7074298.0, |
| "step": 2525 |
| }, |
| { |
| "entropy": 5.521515798568726, |
| "epoch": 0.06849407783417935, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00026816808622456937, |
| "loss": 5.3544, |
| "mean_token_accuracy": 0.16788979172706603, |
| "num_tokens": 7088716.0, |
| "step": 2530 |
| }, |
| { |
| "entropy": 5.494029998779297, |
| "epoch": 0.06862944162436548, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.0002669906312242569, |
| "loss": 5.346, |
| "mean_token_accuracy": 0.17190950810909272, |
| "num_tokens": 7103508.0, |
| "step": 2535 |
| }, |
| { |
| "entropy": 5.537734889984131, |
| "epoch": 0.06876480541455161, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00026581339580483525, |
| "loss": 5.4624, |
| "mean_token_accuracy": 0.161481374502182, |
| "num_tokens": 7117534.0, |
| "step": 2540 |
| }, |
| { |
| "entropy": 5.570920372009278, |
| "epoch": 0.06890016920473774, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0002646364122408082, |
| "loss": 5.4882, |
| "mean_token_accuracy": 0.15791051536798478, |
| "num_tokens": 7130707.0, |
| "step": 2545 |
| }, |
| { |
| "entropy": 5.582677364349365, |
| "epoch": 0.06903553299492386, |
| "grad_norm": 0.9453125, |
| "learning_rate": 0.0002634597127997749, |
| "loss": 5.482, |
| "mean_token_accuracy": 0.16266081035137175, |
| "num_tokens": 7146298.0, |
| "step": 2550 |
| }, |
| { |
| "entropy": 5.409732484817505, |
| "epoch": 0.06917089678510999, |
| "grad_norm": 0.84375, |
| "learning_rate": 0.0002622833297415445, |
| "loss": 5.2559, |
| "mean_token_accuracy": 0.17082736790180206, |
| "num_tokens": 7161266.0, |
| "step": 2555 |
| }, |
| { |
| "entropy": 5.504514932632446, |
| "epoch": 0.06930626057529611, |
| "grad_norm": 0.875, |
| "learning_rate": 0.0002611072953172531, |
| "loss": 5.3892, |
| "mean_token_accuracy": 0.16824420988559724, |
| "num_tokens": 7175543.0, |
| "step": 2560 |
| }, |
| { |
| "entropy": 5.419651794433594, |
| "epoch": 0.06944162436548224, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00025993164176847845, |
| "loss": 5.3044, |
| "mean_token_accuracy": 0.17822718918323516, |
| "num_tokens": 7189617.0, |
| "step": 2565 |
| }, |
| { |
| "entropy": 5.537864732742309, |
| "epoch": 0.06957698815566836, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0002587564013263564, |
| "loss": 5.3945, |
| "mean_token_accuracy": 0.1665595144033432, |
| "num_tokens": 7203722.0, |
| "step": 2570 |
| }, |
| { |
| "entropy": 5.484334468841553, |
| "epoch": 0.06971235194585448, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.0002575816062106974, |
| "loss": 5.3907, |
| "mean_token_accuracy": 0.1719420000910759, |
| "num_tokens": 7215988.0, |
| "step": 2575 |
| }, |
| { |
| "entropy": 5.398307371139526, |
| "epoch": 0.06984771573604061, |
| "grad_norm": 0.8828125, |
| "learning_rate": 0.00025640728862910293, |
| "loss": 5.2727, |
| "mean_token_accuracy": 0.16697476506233216, |
| "num_tokens": 7231974.0, |
| "step": 2580 |
| }, |
| { |
| "entropy": 5.451391649246216, |
| "epoch": 0.06998307952622673, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00025523348077608285, |
| "loss": 5.334, |
| "mean_token_accuracy": 0.16734268814325332, |
| "num_tokens": 7247564.0, |
| "step": 2585 |
| }, |
| { |
| "entropy": 5.557687759399414, |
| "epoch": 0.07011844331641286, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.00025406021483217225, |
| "loss": 5.3802, |
| "mean_token_accuracy": 0.16443277895450592, |
| "num_tokens": 7262757.0, |
| "step": 2590 |
| }, |
| { |
| "entropy": 5.511172676086426, |
| "epoch": 0.07025380710659898, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.00025288752296304963, |
| "loss": 5.4948, |
| "mean_token_accuracy": 0.15715145468711852, |
| "num_tokens": 7277354.0, |
| "step": 2595 |
| }, |
| { |
| "entropy": 5.5072393894195555, |
| "epoch": 0.0703891708967851, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.000251715437318655, |
| "loss": 5.3905, |
| "mean_token_accuracy": 0.1723044529557228, |
| "num_tokens": 7291468.0, |
| "step": 2600 |
| }, |
| { |
| "entropy": 5.505620288848877, |
| "epoch": 0.07052453468697123, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0002505439900323084, |
| "loss": 5.2772, |
| "mean_token_accuracy": 0.17259037345647812, |
| "num_tokens": 7304480.0, |
| "step": 2605 |
| }, |
| { |
| "entropy": 5.533134651184082, |
| "epoch": 0.07065989847715735, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00024937321321982894, |
| "loss": 5.388, |
| "mean_token_accuracy": 0.15711098909378052, |
| "num_tokens": 7318827.0, |
| "step": 2610 |
| }, |
| { |
| "entropy": 5.462842607498169, |
| "epoch": 0.07079526226734349, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.00024820313897865433, |
| "loss": 5.4047, |
| "mean_token_accuracy": 0.16648803055286407, |
| "num_tokens": 7331988.0, |
| "step": 2615 |
| }, |
| { |
| "entropy": 5.606928825378418, |
| "epoch": 0.07093062605752962, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.00024703379938696105, |
| "loss": 5.3909, |
| "mean_token_accuracy": 0.16330956071615219, |
| "num_tokens": 7345740.0, |
| "step": 2620 |
| }, |
| { |
| "entropy": 5.496723222732544, |
| "epoch": 0.07106598984771574, |
| "grad_norm": 0.86328125, |
| "learning_rate": 0.00024586522650278447, |
| "loss": 5.3324, |
| "mean_token_accuracy": 0.1629031166434288, |
| "num_tokens": 7359100.0, |
| "step": 2625 |
| }, |
| { |
| "entropy": 5.492794418334961, |
| "epoch": 0.07120135363790187, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.00024469745236314064, |
| "loss": 5.4332, |
| "mean_token_accuracy": 0.16518517211079597, |
| "num_tokens": 7373261.0, |
| "step": 2630 |
| }, |
| { |
| "entropy": 5.497795438766479, |
| "epoch": 0.07133671742808799, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00024353050898314767, |
| "loss": 5.3778, |
| "mean_token_accuracy": 0.16042957752943038, |
| "num_tokens": 7386125.0, |
| "step": 2635 |
| }, |
| { |
| "entropy": 5.579156875610352, |
| "epoch": 0.07147208121827411, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00024236442835514743, |
| "loss": 5.4228, |
| "mean_token_accuracy": 0.16269408017396927, |
| "num_tokens": 7400206.0, |
| "step": 2640 |
| }, |
| { |
| "entropy": 5.575217056274414, |
| "epoch": 0.07160744500846024, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.00024119924244782965, |
| "loss": 5.3759, |
| "mean_token_accuracy": 0.16886017620563507, |
| "num_tokens": 7414133.0, |
| "step": 2645 |
| }, |
| { |
| "entropy": 5.414534330368042, |
| "epoch": 0.07174280879864636, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.00024003498320535462, |
| "loss": 5.2814, |
| "mean_token_accuracy": 0.17329987585544587, |
| "num_tokens": 7428976.0, |
| "step": 2650 |
| }, |
| { |
| "entropy": 5.428465366363525, |
| "epoch": 0.07187817258883249, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.00023887168254647727, |
| "loss": 5.2716, |
| "mean_token_accuracy": 0.16944997161626815, |
| "num_tokens": 7442821.0, |
| "step": 2655 |
| }, |
| { |
| "entropy": 5.4997495174407955, |
| "epoch": 0.07201353637901861, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.00023770937236367308, |
| "loss": 5.3966, |
| "mean_token_accuracy": 0.16241525560617448, |
| "num_tokens": 7459447.0, |
| "step": 2660 |
| }, |
| { |
| "entropy": 5.482759618759156, |
| "epoch": 0.07214890016920474, |
| "grad_norm": 0.89453125, |
| "learning_rate": 0.00023654808452226278, |
| "loss": 5.3326, |
| "mean_token_accuracy": 0.17035989910364152, |
| "num_tokens": 7474103.0, |
| "step": 2665 |
| }, |
| { |
| "entropy": 5.577449703216553, |
| "epoch": 0.07228426395939086, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00023538785085953912, |
| "loss": 5.4343, |
| "mean_token_accuracy": 0.16333755105733871, |
| "num_tokens": 7487976.0, |
| "step": 2670 |
| }, |
| { |
| "entropy": 5.547738122940063, |
| "epoch": 0.07241962774957698, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.00023422870318389404, |
| "loss": 5.4574, |
| "mean_token_accuracy": 0.15718373358249665, |
| "num_tokens": 7501915.0, |
| "step": 2675 |
| }, |
| { |
| "entropy": 5.518865013122559, |
| "epoch": 0.07255499153976311, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0002330706732739468, |
| "loss": 5.4122, |
| "mean_token_accuracy": 0.16701352149248122, |
| "num_tokens": 7514901.0, |
| "step": 2680 |
| }, |
| { |
| "entropy": 5.494342899322509, |
| "epoch": 0.07269035532994923, |
| "grad_norm": 0.859375, |
| "learning_rate": 0.00023191379287767211, |
| "loss": 5.3231, |
| "mean_token_accuracy": 0.16684457957744597, |
| "num_tokens": 7528840.0, |
| "step": 2685 |
| }, |
| { |
| "entropy": 5.474505853652954, |
| "epoch": 0.07282571912013536, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.0002307580937115305, |
| "loss": 5.3626, |
| "mean_token_accuracy": 0.16770108044147491, |
| "num_tokens": 7543417.0, |
| "step": 2690 |
| }, |
| { |
| "entropy": 5.518067264556885, |
| "epoch": 0.0729610829103215, |
| "grad_norm": 0.91015625, |
| "learning_rate": 0.00022960360745959846, |
| "loss": 5.3038, |
| "mean_token_accuracy": 0.1747143894433975, |
| "num_tokens": 7556468.0, |
| "step": 2695 |
| }, |
| { |
| "entropy": 5.466390228271484, |
| "epoch": 0.07309644670050762, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.00022845036577269972, |
| "loss": 5.4043, |
| "mean_token_accuracy": 0.16157454401254653, |
| "num_tokens": 7570917.0, |
| "step": 2700 |
| }, |
| { |
| "entropy": 5.378308916091919, |
| "epoch": 0.07323181049069374, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.00022729840026753777, |
| "loss": 5.2936, |
| "mean_token_accuracy": 0.17287229299545287, |
| "num_tokens": 7585650.0, |
| "step": 2705 |
| }, |
| { |
| "entropy": 5.49935736656189, |
| "epoch": 0.07336717428087987, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.0002261477425258287, |
| "loss": 5.3034, |
| "mean_token_accuracy": 0.16764113306999207, |
| "num_tokens": 7599526.0, |
| "step": 2710 |
| }, |
| { |
| "entropy": 5.5813967227935795, |
| "epoch": 0.07350253807106599, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0002249984240934358, |
| "loss": 5.373, |
| "mean_token_accuracy": 0.16482538282871245, |
| "num_tokens": 7612788.0, |
| "step": 2715 |
| }, |
| { |
| "entropy": 5.462430143356324, |
| "epoch": 0.07363790186125212, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.00022385047647950464, |
| "loss": 5.3176, |
| "mean_token_accuracy": 0.1712317556142807, |
| "num_tokens": 7626130.0, |
| "step": 2720 |
| }, |
| { |
| "entropy": 5.512141418457031, |
| "epoch": 0.07377326565143824, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.0002227039311555986, |
| "loss": 5.4048, |
| "mean_token_accuracy": 0.16659581065177917, |
| "num_tokens": 7641082.0, |
| "step": 2725 |
| }, |
| { |
| "entropy": 5.458144950866699, |
| "epoch": 0.07390862944162437, |
| "grad_norm": 0.88671875, |
| "learning_rate": 0.0002215588195548372, |
| "loss": 5.279, |
| "mean_token_accuracy": 0.17415901124477387, |
| "num_tokens": 7656106.0, |
| "step": 2730 |
| }, |
| { |
| "entropy": 5.5800501823425295, |
| "epoch": 0.07404399323181049, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00022041517307103337, |
| "loss": 5.4972, |
| "mean_token_accuracy": 0.1576918765902519, |
| "num_tokens": 7669987.0, |
| "step": 2735 |
| }, |
| { |
| "entropy": 5.4527280807495115, |
| "epoch": 0.07417935702199661, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0002192730230578331, |
| "loss": 5.254, |
| "mean_token_accuracy": 0.17619728147983552, |
| "num_tokens": 7684919.0, |
| "step": 2740 |
| }, |
| { |
| "entropy": 5.430622720718384, |
| "epoch": 0.07431472081218274, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.0002181324008278559, |
| "loss": 5.2826, |
| "mean_token_accuracy": 0.17135830372571945, |
| "num_tokens": 7696787.0, |
| "step": 2745 |
| }, |
| { |
| "entropy": 5.481793308258057, |
| "epoch": 0.07445008460236886, |
| "grad_norm": 0.875, |
| "learning_rate": 0.00021699333765183655, |
| "loss": 5.3837, |
| "mean_token_accuracy": 0.16583613455295562, |
| "num_tokens": 7709630.0, |
| "step": 2750 |
| }, |
| { |
| "entropy": 5.461789512634278, |
| "epoch": 0.07458544839255499, |
| "grad_norm": 0.87890625, |
| "learning_rate": 0.0002158558647577673, |
| "loss": 5.343, |
| "mean_token_accuracy": 0.16185439378023148, |
| "num_tokens": 7724842.0, |
| "step": 2755 |
| }, |
| { |
| "entropy": 5.428160953521728, |
| "epoch": 0.07472081218274111, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00021472001333004215, |
| "loss": 5.1693, |
| "mean_token_accuracy": 0.17251513451337813, |
| "num_tokens": 7739569.0, |
| "step": 2760 |
| }, |
| { |
| "entropy": 5.427040004730225, |
| "epoch": 0.07485617597292724, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.00021358581450860186, |
| "loss": 5.207, |
| "mean_token_accuracy": 0.17038764506578447, |
| "num_tokens": 7753711.0, |
| "step": 2765 |
| }, |
| { |
| "entropy": 5.465088510513306, |
| "epoch": 0.07499153976311337, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.0002124532993880799, |
| "loss": 5.3172, |
| "mean_token_accuracy": 0.16422780603170395, |
| "num_tokens": 7768388.0, |
| "step": 2770 |
| }, |
| { |
| "entropy": 5.467406845092773, |
| "epoch": 0.0751269035532995, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.00021132249901695044, |
| "loss": 5.3397, |
| "mean_token_accuracy": 0.1675926923751831, |
| "num_tokens": 7783723.0, |
| "step": 2775 |
| }, |
| { |
| "entropy": 5.510707998275757, |
| "epoch": 0.07526226734348562, |
| "grad_norm": 0.87890625, |
| "learning_rate": 0.00021019344439667705, |
| "loss": 5.3986, |
| "mean_token_accuracy": 0.16413299441337587, |
| "num_tokens": 7799084.0, |
| "step": 2780 |
| }, |
| { |
| "entropy": 5.533675479888916, |
| "epoch": 0.07539763113367175, |
| "grad_norm": 0.84765625, |
| "learning_rate": 0.00020906616648086213, |
| "loss": 5.3946, |
| "mean_token_accuracy": 0.1620550975203514, |
| "num_tokens": 7814644.0, |
| "step": 2785 |
| }, |
| { |
| "entropy": 5.467060947418213, |
| "epoch": 0.07553299492385787, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00020794069617439942, |
| "loss": 5.2889, |
| "mean_token_accuracy": 0.17744391411542892, |
| "num_tokens": 7829458.0, |
| "step": 2790 |
| }, |
| { |
| "entropy": 5.52356595993042, |
| "epoch": 0.075668358714044, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00020681706433262593, |
| "loss": 5.3376, |
| "mean_token_accuracy": 0.17330960631370546, |
| "num_tokens": 7844811.0, |
| "step": 2795 |
| }, |
| { |
| "entropy": 5.436047220230103, |
| "epoch": 0.07580372250423012, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.00020569530176047602, |
| "loss": 5.245, |
| "mean_token_accuracy": 0.17710321843624116, |
| "num_tokens": 7857008.0, |
| "step": 2800 |
| }, |
| { |
| "entropy": 5.451122379302978, |
| "epoch": 0.07593908629441624, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.0002045754392116374, |
| "loss": 5.3629, |
| "mean_token_accuracy": 0.17095964550971984, |
| "num_tokens": 7871976.0, |
| "step": 2805 |
| }, |
| { |
| "entropy": 5.513166713714599, |
| "epoch": 0.07607445008460237, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00020345750738770757, |
| "loss": 5.2591, |
| "mean_token_accuracy": 0.16977263540029525, |
| "num_tokens": 7885961.0, |
| "step": 2810 |
| }, |
| { |
| "entropy": 5.454839134216309, |
| "epoch": 0.07620981387478849, |
| "grad_norm": 0.828125, |
| "learning_rate": 0.00020234153693735214, |
| "loss": 5.2422, |
| "mean_token_accuracy": 0.18533623367547988, |
| "num_tokens": 7900771.0, |
| "step": 2815 |
| }, |
| { |
| "entropy": 5.501101541519165, |
| "epoch": 0.07634517766497462, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.0002012275584554647, |
| "loss": 5.3521, |
| "mean_token_accuracy": 0.16500504612922667, |
| "num_tokens": 7914177.0, |
| "step": 2820 |
| }, |
| { |
| "entropy": 5.530455732345581, |
| "epoch": 0.07648054145516074, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.00020011560248232803, |
| "loss": 5.3338, |
| "mean_token_accuracy": 0.17148594111204146, |
| "num_tokens": 7926304.0, |
| "step": 2825 |
| }, |
| { |
| "entropy": 5.51822681427002, |
| "epoch": 0.07661590524534687, |
| "grad_norm": 0.875, |
| "learning_rate": 0.00019900569950277692, |
| "loss": 5.3958, |
| "mean_token_accuracy": 0.17159417718648912, |
| "num_tokens": 7940643.0, |
| "step": 2830 |
| }, |
| { |
| "entropy": 5.498433589935303, |
| "epoch": 0.07675126903553299, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00019789787994536228, |
| "loss": 5.3133, |
| "mean_token_accuracy": 0.1724165916442871, |
| "num_tokens": 7953973.0, |
| "step": 2835 |
| }, |
| { |
| "entropy": 5.487789058685303, |
| "epoch": 0.07688663282571911, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.00019679217418151667, |
| "loss": 5.2822, |
| "mean_token_accuracy": 0.175179585814476, |
| "num_tokens": 7968097.0, |
| "step": 2840 |
| }, |
| { |
| "entropy": 5.485777091979981, |
| "epoch": 0.07702199661590524, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00019568861252472236, |
| "loss": 5.4075, |
| "mean_token_accuracy": 0.17055005431175232, |
| "num_tokens": 7981377.0, |
| "step": 2845 |
| }, |
| { |
| "entropy": 5.480043888092041, |
| "epoch": 0.07715736040609138, |
| "grad_norm": 0.8984375, |
| "learning_rate": 0.00019458722522967952, |
| "loss": 5.2816, |
| "mean_token_accuracy": 0.17032997757196428, |
| "num_tokens": 7996347.0, |
| "step": 2850 |
| }, |
| { |
| "entropy": 5.440441513061524, |
| "epoch": 0.0772927241962775, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00019348804249147723, |
| "loss": 5.2801, |
| "mean_token_accuracy": 0.16763708293437957, |
| "num_tokens": 8009085.0, |
| "step": 2855 |
| }, |
| { |
| "entropy": 5.496013021469116, |
| "epoch": 0.07742808798646363, |
| "grad_norm": 0.9453125, |
| "learning_rate": 0.0001923910944447655, |
| "loss": 5.3578, |
| "mean_token_accuracy": 0.1683908924460411, |
| "num_tokens": 8022972.0, |
| "step": 2860 |
| }, |
| { |
| "entropy": 5.463598155975342, |
| "epoch": 0.07756345177664975, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00019129641116292928, |
| "loss": 5.2517, |
| "mean_token_accuracy": 0.17301710844039916, |
| "num_tokens": 8036721.0, |
| "step": 2865 |
| }, |
| { |
| "entropy": 5.497069406509399, |
| "epoch": 0.07769881556683587, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.00019020402265726343, |
| "loss": 5.3642, |
| "mean_token_accuracy": 0.17259056568145753, |
| "num_tokens": 8051907.0, |
| "step": 2870 |
| }, |
| { |
| "entropy": 5.599059247970581, |
| "epoch": 0.077834179357022, |
| "grad_norm": 0.83984375, |
| "learning_rate": 0.0001891139588761509, |
| "loss": 5.4207, |
| "mean_token_accuracy": 0.15925686806440353, |
| "num_tokens": 8067550.0, |
| "step": 2875 |
| }, |
| { |
| "entropy": 5.518371534347534, |
| "epoch": 0.07796954314720812, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.00018802624970424076, |
| "loss": 5.3844, |
| "mean_token_accuracy": 0.17436740100383757, |
| "num_tokens": 8081188.0, |
| "step": 2880 |
| }, |
| { |
| "entropy": 5.424393129348755, |
| "epoch": 0.07810490693739425, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00018694092496162945, |
| "loss": 5.2155, |
| "mean_token_accuracy": 0.17726275324821472, |
| "num_tokens": 8095991.0, |
| "step": 2885 |
| }, |
| { |
| "entropy": 5.458485412597656, |
| "epoch": 0.07824027072758037, |
| "grad_norm": 0.9765625, |
| "learning_rate": 0.00018585801440304306, |
| "loss": 5.3427, |
| "mean_token_accuracy": 0.16206988841295242, |
| "num_tokens": 8110424.0, |
| "step": 2890 |
| }, |
| { |
| "entropy": 5.579003047943115, |
| "epoch": 0.0783756345177665, |
| "grad_norm": 0.80859375, |
| "learning_rate": 0.00018477754771702165, |
| "loss": 5.4071, |
| "mean_token_accuracy": 0.16417887508869172, |
| "num_tokens": 8127483.0, |
| "step": 2895 |
| }, |
| { |
| "entropy": 5.4810065746307375, |
| "epoch": 0.07851099830795262, |
| "grad_norm": 0.8671875, |
| "learning_rate": 0.00018369955452510506, |
| "loss": 5.2518, |
| "mean_token_accuracy": 0.16933856457471846, |
| "num_tokens": 8144871.0, |
| "step": 2900 |
| }, |
| { |
| "entropy": 5.363333082199096, |
| "epoch": 0.07864636209813874, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0001826240643810212, |
| "loss": 5.2339, |
| "mean_token_accuracy": 0.18072881251573564, |
| "num_tokens": 8159166.0, |
| "step": 2905 |
| }, |
| { |
| "entropy": 5.459006214141846, |
| "epoch": 0.07878172588832487, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.0001815511067698758, |
| "loss": 5.3428, |
| "mean_token_accuracy": 0.1761472001671791, |
| "num_tokens": 8173679.0, |
| "step": 2910 |
| }, |
| { |
| "entropy": 5.487945318222046, |
| "epoch": 0.078917089678511, |
| "grad_norm": 0.84375, |
| "learning_rate": 0.0001804807111073436, |
| "loss": 5.3272, |
| "mean_token_accuracy": 0.1742970734834671, |
| "num_tokens": 8189905.0, |
| "step": 2915 |
| }, |
| { |
| "entropy": 5.556151533126831, |
| "epoch": 0.07905245346869712, |
| "grad_norm": 0.89453125, |
| "learning_rate": 0.0001794129067388625, |
| "loss": 5.3454, |
| "mean_token_accuracy": 0.16954322308301925, |
| "num_tokens": 8204091.0, |
| "step": 2920 |
| }, |
| { |
| "entropy": 5.4311378479003904, |
| "epoch": 0.07918781725888324, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00017834772293882868, |
| "loss": 5.271, |
| "mean_token_accuracy": 0.1795088216662407, |
| "num_tokens": 8217298.0, |
| "step": 2925 |
| }, |
| { |
| "entropy": 5.476504468917847, |
| "epoch": 0.07932318104906938, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.000177285188909794, |
| "loss": 5.3071, |
| "mean_token_accuracy": 0.1695019334554672, |
| "num_tokens": 8231131.0, |
| "step": 2930 |
| }, |
| { |
| "entropy": 5.490973567962646, |
| "epoch": 0.0794585448392555, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0001762253337816656, |
| "loss": 5.3456, |
| "mean_token_accuracy": 0.1681083619594574, |
| "num_tokens": 8245409.0, |
| "step": 2935 |
| }, |
| { |
| "entropy": 5.53462929725647, |
| "epoch": 0.07959390862944163, |
| "grad_norm": 0.9765625, |
| "learning_rate": 0.00017516818661090738, |
| "loss": 5.3796, |
| "mean_token_accuracy": 0.16535060852766037, |
| "num_tokens": 8259802.0, |
| "step": 2940 |
| }, |
| { |
| "entropy": 5.458170461654663, |
| "epoch": 0.07972927241962775, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.0001741137763797428, |
| "loss": 5.2636, |
| "mean_token_accuracy": 0.1764928162097931, |
| "num_tokens": 8273833.0, |
| "step": 2945 |
| }, |
| { |
| "entropy": 5.407339096069336, |
| "epoch": 0.07986463620981388, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00017306213199536115, |
| "loss": 5.2234, |
| "mean_token_accuracy": 0.176323065161705, |
| "num_tokens": 8287181.0, |
| "step": 2950 |
| }, |
| { |
| "entropy": 5.467682838439941, |
| "epoch": 0.08, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.0001720132822891243, |
| "loss": 5.2588, |
| "mean_token_accuracy": 0.16995817869901658, |
| "num_tokens": 8300432.0, |
| "step": 2955 |
| }, |
| { |
| "entropy": 5.419669437408447, |
| "epoch": 0.08013536379018613, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.0001709672560157769, |
| "loss": 5.2418, |
| "mean_token_accuracy": 0.18255811035633088, |
| "num_tokens": 8313873.0, |
| "step": 2960 |
| }, |
| { |
| "entropy": 5.462170553207398, |
| "epoch": 0.08027072758037225, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.00016992408185265758, |
| "loss": 5.3659, |
| "mean_token_accuracy": 0.16571080684661865, |
| "num_tokens": 8329781.0, |
| "step": 2965 |
| }, |
| { |
| "entropy": 5.4735033988952635, |
| "epoch": 0.08040609137055837, |
| "grad_norm": 0.86328125, |
| "learning_rate": 0.00016888378839891298, |
| "loss": 5.3732, |
| "mean_token_accuracy": 0.16627077162265777, |
| "num_tokens": 8346691.0, |
| "step": 2970 |
| }, |
| { |
| "entropy": 5.496302556991577, |
| "epoch": 0.0805414551607445, |
| "grad_norm": 0.89453125, |
| "learning_rate": 0.0001678464041747137, |
| "loss": 5.323, |
| "mean_token_accuracy": 0.1704434260725975, |
| "num_tokens": 8361779.0, |
| "step": 2975 |
| }, |
| { |
| "entropy": 5.521384286880493, |
| "epoch": 0.08067681895093062, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00016681195762047223, |
| "loss": 5.3293, |
| "mean_token_accuracy": 0.16714472323656082, |
| "num_tokens": 8376285.0, |
| "step": 2980 |
| }, |
| { |
| "entropy": 5.463702249526977, |
| "epoch": 0.08081218274111675, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.00016578047709606337, |
| "loss": 5.2956, |
| "mean_token_accuracy": 0.1701137751340866, |
| "num_tokens": 8389645.0, |
| "step": 2985 |
| }, |
| { |
| "entropy": 5.453202438354492, |
| "epoch": 0.08094754653130287, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00016475199088004678, |
| "loss": 5.2889, |
| "mean_token_accuracy": 0.17482130378484725, |
| "num_tokens": 8401728.0, |
| "step": 2990 |
| }, |
| { |
| "entropy": 5.434600925445556, |
| "epoch": 0.081082910321489, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.00016372652716889163, |
| "loss": 5.2305, |
| "mean_token_accuracy": 0.1778161495923996, |
| "num_tokens": 8416862.0, |
| "step": 2995 |
| }, |
| { |
| "entropy": 5.486732912063599, |
| "epoch": 0.08121827411167512, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0001627041140762035, |
| "loss": 5.3317, |
| "mean_token_accuracy": 0.17365986555814744, |
| "num_tokens": 8430674.0, |
| "step": 3000 |
| }, |
| { |
| "entropy": 5.424360466003418, |
| "epoch": 0.08135363790186126, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.00016168477963195382, |
| "loss": 5.2288, |
| "mean_token_accuracy": 0.1797449544072151, |
| "num_tokens": 8443736.0, |
| "step": 3005 |
| }, |
| { |
| "entropy": 5.399167108535766, |
| "epoch": 0.08148900169204738, |
| "grad_norm": 0.8359375, |
| "learning_rate": 0.0001606685517817114, |
| "loss": 5.2675, |
| "mean_token_accuracy": 0.17130256146192552, |
| "num_tokens": 8458551.0, |
| "step": 3010 |
| }, |
| { |
| "entropy": 5.441774988174439, |
| "epoch": 0.08162436548223351, |
| "grad_norm": 0.84375, |
| "learning_rate": 0.00015965545838587592, |
| "loss": 5.2618, |
| "mean_token_accuracy": 0.16794567108154296, |
| "num_tokens": 8473802.0, |
| "step": 3015 |
| }, |
| { |
| "entropy": 5.47581901550293, |
| "epoch": 0.08175972927241963, |
| "grad_norm": 0.87109375, |
| "learning_rate": 0.00015864552721891467, |
| "loss": 5.3247, |
| "mean_token_accuracy": 0.16786827743053437, |
| "num_tokens": 8488927.0, |
| "step": 3020 |
| }, |
| { |
| "entropy": 5.440992641448974, |
| "epoch": 0.08189509306260576, |
| "grad_norm": 0.9453125, |
| "learning_rate": 0.00015763878596860076, |
| "loss": 5.1973, |
| "mean_token_accuracy": 0.16612706929445267, |
| "num_tokens": 8501604.0, |
| "step": 3025 |
| }, |
| { |
| "entropy": 5.433175420761108, |
| "epoch": 0.08203045685279188, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00015663526223525412, |
| "loss": 5.2937, |
| "mean_token_accuracy": 0.1712185561656952, |
| "num_tokens": 8514228.0, |
| "step": 3030 |
| }, |
| { |
| "entropy": 5.443940877914429, |
| "epoch": 0.082165820642978, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.0001556349835309848, |
| "loss": 5.2669, |
| "mean_token_accuracy": 0.16782645732164383, |
| "num_tokens": 8528327.0, |
| "step": 3035 |
| }, |
| { |
| "entropy": 5.410441637039185, |
| "epoch": 0.08230118443316413, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.0001546379772789389, |
| "loss": 5.2322, |
| "mean_token_accuracy": 0.17801001518964768, |
| "num_tokens": 8542672.0, |
| "step": 3040 |
| }, |
| { |
| "entropy": 5.466415166854858, |
| "epoch": 0.08243654822335025, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.00015364427081254622, |
| "loss": 5.2928, |
| "mean_token_accuracy": 0.16680212169885636, |
| "num_tokens": 8556950.0, |
| "step": 3045 |
| }, |
| { |
| "entropy": 5.480651140213013, |
| "epoch": 0.08257191201353638, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00015265389137477165, |
| "loss": 5.3176, |
| "mean_token_accuracy": 0.16717551946640014, |
| "num_tokens": 8568976.0, |
| "step": 3050 |
| }, |
| { |
| "entropy": 5.471415328979492, |
| "epoch": 0.0827072758037225, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.00015166686611736786, |
| "loss": 5.279, |
| "mean_token_accuracy": 0.16722955107688903, |
| "num_tokens": 8582972.0, |
| "step": 3055 |
| }, |
| { |
| "entropy": 5.384100437164307, |
| "epoch": 0.08284263959390863, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.00015068322210013064, |
| "loss": 5.1654, |
| "mean_token_accuracy": 0.18055080026388168, |
| "num_tokens": 8595513.0, |
| "step": 3060 |
| }, |
| { |
| "entropy": 5.395313358306884, |
| "epoch": 0.08297800338409475, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0001497029862901578, |
| "loss": 5.3037, |
| "mean_token_accuracy": 0.17951921373605728, |
| "num_tokens": 8608918.0, |
| "step": 3065 |
| }, |
| { |
| "entropy": 5.4258056640625, |
| "epoch": 0.08311336717428087, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.00014872618556110905, |
| "loss": 5.205, |
| "mean_token_accuracy": 0.17827895432710647, |
| "num_tokens": 8622730.0, |
| "step": 3070 |
| }, |
| { |
| "entropy": 5.463824796676636, |
| "epoch": 0.083248730964467, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00014775284669246992, |
| "loss": 5.2471, |
| "mean_token_accuracy": 0.17934898436069488, |
| "num_tokens": 8635412.0, |
| "step": 3075 |
| }, |
| { |
| "entropy": 5.453006887435913, |
| "epoch": 0.08338409475465312, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.00014678299636881716, |
| "loss": 5.3157, |
| "mean_token_accuracy": 0.17817512452602385, |
| "num_tokens": 8648105.0, |
| "step": 3080 |
| }, |
| { |
| "entropy": 5.489534902572632, |
| "epoch": 0.08351945854483926, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0001458166611790873, |
| "loss": 5.3456, |
| "mean_token_accuracy": 0.16926711797714233, |
| "num_tokens": 8660690.0, |
| "step": 3085 |
| }, |
| { |
| "entropy": 5.469047117233276, |
| "epoch": 0.08365482233502539, |
| "grad_norm": 0.93359375, |
| "learning_rate": 0.00014485386761584773, |
| "loss": 5.226, |
| "mean_token_accuracy": 0.17681361138820648, |
| "num_tokens": 8674585.0, |
| "step": 3090 |
| }, |
| { |
| "entropy": 5.430918836593628, |
| "epoch": 0.08379018612521151, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.00014389464207457042, |
| "loss": 5.2677, |
| "mean_token_accuracy": 0.17809636294841766, |
| "num_tokens": 8689490.0, |
| "step": 3095 |
| }, |
| { |
| "entropy": 5.406502294540405, |
| "epoch": 0.08392554991539763, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.00014293901085290795, |
| "loss": 5.2227, |
| "mean_token_accuracy": 0.17613164633512496, |
| "num_tokens": 8704597.0, |
| "step": 3100 |
| }, |
| { |
| "entropy": 5.466963195800782, |
| "epoch": 0.08406091370558376, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.00014198700014997307, |
| "loss": 5.2596, |
| "mean_token_accuracy": 0.17903373539447784, |
| "num_tokens": 8718430.0, |
| "step": 3105 |
| }, |
| { |
| "entropy": 5.424066495895386, |
| "epoch": 0.08419627749576988, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00014103863606562016, |
| "loss": 5.2084, |
| "mean_token_accuracy": 0.17104987502098085, |
| "num_tokens": 8733983.0, |
| "step": 3110 |
| }, |
| { |
| "entropy": 5.4510743618011475, |
| "epoch": 0.08433164128595601, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.00014009394459972964, |
| "loss": 5.2121, |
| "mean_token_accuracy": 0.177804896235466, |
| "num_tokens": 8747359.0, |
| "step": 3115 |
| }, |
| { |
| "entropy": 5.4852707862854, |
| "epoch": 0.08446700507614213, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.00013915295165149513, |
| "loss": 5.2506, |
| "mean_token_accuracy": 0.17922114282846452, |
| "num_tokens": 8759625.0, |
| "step": 3120 |
| }, |
| { |
| "entropy": 5.454599332809448, |
| "epoch": 0.08460236886632826, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00013821568301871384, |
| "loss": 5.2401, |
| "mean_token_accuracy": 0.17472292929887773, |
| "num_tokens": 8772700.0, |
| "step": 3125 |
| }, |
| { |
| "entropy": 5.432861709594727, |
| "epoch": 0.08473773265651438, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.00013728216439707862, |
| "loss": 5.2968, |
| "mean_token_accuracy": 0.17653030455112456, |
| "num_tokens": 8784952.0, |
| "step": 3130 |
| }, |
| { |
| "entropy": 5.500757789611816, |
| "epoch": 0.0848730964467005, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.00013635242137947419, |
| "loss": 5.3983, |
| "mean_token_accuracy": 0.16601879745721818, |
| "num_tokens": 8798983.0, |
| "step": 3135 |
| }, |
| { |
| "entropy": 5.466593456268311, |
| "epoch": 0.08500846023688663, |
| "grad_norm": 0.8671875, |
| "learning_rate": 0.00013542647945527498, |
| "loss": 5.2634, |
| "mean_token_accuracy": 0.178488627076149, |
| "num_tokens": 8812987.0, |
| "step": 3140 |
| }, |
| { |
| "entropy": 5.500957775115967, |
| "epoch": 0.08514382402707275, |
| "grad_norm": 0.8984375, |
| "learning_rate": 0.0001345043640096465, |
| "loss": 5.377, |
| "mean_token_accuracy": 0.17290503680706024, |
| "num_tokens": 8827359.0, |
| "step": 3145 |
| }, |
| { |
| "entropy": 5.442121982574463, |
| "epoch": 0.08527918781725888, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.00013358610032284957, |
| "loss": 5.1985, |
| "mean_token_accuracy": 0.18115333914756776, |
| "num_tokens": 8841025.0, |
| "step": 3150 |
| }, |
| { |
| "entropy": 5.534852075576782, |
| "epoch": 0.085414551607445, |
| "grad_norm": 1.0, |
| "learning_rate": 0.000132671713569547, |
| "loss": 5.3334, |
| "mean_token_accuracy": 0.16925936341285705, |
| "num_tokens": 8855062.0, |
| "step": 3155 |
| }, |
| { |
| "entropy": 5.458619165420532, |
| "epoch": 0.08554991539763114, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.0001317612288181136, |
| "loss": 5.2077, |
| "mean_token_accuracy": 0.17451809644699096, |
| "num_tokens": 8869516.0, |
| "step": 3160 |
| }, |
| { |
| "entropy": 5.454307651519775, |
| "epoch": 0.08568527918781726, |
| "grad_norm": 0.875, |
| "learning_rate": 0.00013085467102994864, |
| "loss": 5.3441, |
| "mean_token_accuracy": 0.1724272206425667, |
| "num_tokens": 8883758.0, |
| "step": 3165 |
| }, |
| { |
| "entropy": 5.4530314922332765, |
| "epoch": 0.08582064297800339, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00012995206505879198, |
| "loss": 5.2512, |
| "mean_token_accuracy": 0.17589752674102782, |
| "num_tokens": 8898484.0, |
| "step": 3170 |
| }, |
| { |
| "entropy": 5.444612312316894, |
| "epoch": 0.08595600676818951, |
| "grad_norm": 0.88671875, |
| "learning_rate": 0.0001290534356500421, |
| "loss": 5.2609, |
| "mean_token_accuracy": 0.1797889545559883, |
| "num_tokens": 8912852.0, |
| "step": 3175 |
| }, |
| { |
| "entropy": 5.440249586105347, |
| "epoch": 0.08609137055837564, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.00012815880744007827, |
| "loss": 5.2379, |
| "mean_token_accuracy": 0.17183031737804413, |
| "num_tokens": 8927714.0, |
| "step": 3180 |
| }, |
| { |
| "entropy": 5.478732442855835, |
| "epoch": 0.08622673434856176, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00012726820495558483, |
| "loss": 5.2562, |
| "mean_token_accuracy": 0.17183429449796678, |
| "num_tokens": 8941572.0, |
| "step": 3185 |
| }, |
| { |
| "entropy": 5.467626094818115, |
| "epoch": 0.08636209813874789, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00012638165261287868, |
| "loss": 5.2982, |
| "mean_token_accuracy": 0.17230871319770813, |
| "num_tokens": 8956091.0, |
| "step": 3190 |
| }, |
| { |
| "entropy": 5.453297138214111, |
| "epoch": 0.08649746192893401, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.0001254991747172402, |
| "loss": 5.2286, |
| "mean_token_accuracy": 0.1784089371562004, |
| "num_tokens": 8970743.0, |
| "step": 3195 |
| }, |
| { |
| "entropy": 5.512088012695313, |
| "epoch": 0.08663282571912014, |
| "grad_norm": 0.90234375, |
| "learning_rate": 0.00012462079546224662, |
| "loss": 5.3266, |
| "mean_token_accuracy": 0.16639686971902848, |
| "num_tokens": 8986444.0, |
| "step": 3200 |
| }, |
| { |
| "entropy": 5.445282125473023, |
| "epoch": 0.08676818950930626, |
| "grad_norm": 0.90234375, |
| "learning_rate": 0.00012374653892910896, |
| "loss": 5.2591, |
| "mean_token_accuracy": 0.17210991233587264, |
| "num_tokens": 9001382.0, |
| "step": 3205 |
| }, |
| { |
| "entropy": 5.500101709365845, |
| "epoch": 0.08690355329949238, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00012287642908601166, |
| "loss": 5.3364, |
| "mean_token_accuracy": 0.17057666778564454, |
| "num_tokens": 9013719.0, |
| "step": 3210 |
| }, |
| { |
| "entropy": 5.416972064971924, |
| "epoch": 0.08703891708967851, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00012201048978745569, |
| "loss": 5.2549, |
| "mean_token_accuracy": 0.1811564639210701, |
| "num_tokens": 9027790.0, |
| "step": 3215 |
| }, |
| { |
| "entropy": 5.453947591781616, |
| "epoch": 0.08717428087986463, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00012114874477360427, |
| "loss": 5.242, |
| "mean_token_accuracy": 0.17207376956939696, |
| "num_tokens": 9041632.0, |
| "step": 3220 |
| }, |
| { |
| "entropy": 5.452928781509399, |
| "epoch": 0.08730964467005076, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.00012029121766963236, |
| "loss": 5.3083, |
| "mean_token_accuracy": 0.16890519112348557, |
| "num_tokens": 9055562.0, |
| "step": 3225 |
| }, |
| { |
| "entropy": 5.4277173519134525, |
| "epoch": 0.08744500846023688, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.00011943793198507858, |
| "loss": 5.1347, |
| "mean_token_accuracy": 0.181647826731205, |
| "num_tokens": 9068872.0, |
| "step": 3230 |
| }, |
| { |
| "entropy": 5.400438642501831, |
| "epoch": 0.087580372250423, |
| "grad_norm": 0.828125, |
| "learning_rate": 0.00011858891111320104, |
| "loss": 5.1768, |
| "mean_token_accuracy": 0.17398682236671448, |
| "num_tokens": 9083206.0, |
| "step": 3235 |
| }, |
| { |
| "entropy": 5.3835385799407955, |
| "epoch": 0.08771573604060914, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.0001177441783303359, |
| "loss": 5.1512, |
| "mean_token_accuracy": 0.1808776617050171, |
| "num_tokens": 9097034.0, |
| "step": 3240 |
| }, |
| { |
| "entropy": 5.417808389663696, |
| "epoch": 0.08785109983079527, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00011690375679525896, |
| "loss": 5.2195, |
| "mean_token_accuracy": 0.17991944402456284, |
| "num_tokens": 9110326.0, |
| "step": 3245 |
| }, |
| { |
| "entropy": 5.3836017608642575, |
| "epoch": 0.08798646362098139, |
| "grad_norm": 0.8984375, |
| "learning_rate": 0.00011606766954855124, |
| "loss": 5.1837, |
| "mean_token_accuracy": 0.17912977635860444, |
| "num_tokens": 9124025.0, |
| "step": 3250 |
| }, |
| { |
| "entropy": 5.433529281616211, |
| "epoch": 0.08812182741116752, |
| "grad_norm": 0.93359375, |
| "learning_rate": 0.00011523593951196702, |
| "loss": 5.1581, |
| "mean_token_accuracy": 0.1803836077451706, |
| "num_tokens": 9137357.0, |
| "step": 3255 |
| }, |
| { |
| "entropy": 5.4744508266448975, |
| "epoch": 0.08825719120135364, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.00011440858948780523, |
| "loss": 5.3428, |
| "mean_token_accuracy": 0.16637975126504898, |
| "num_tokens": 9152364.0, |
| "step": 3260 |
| }, |
| { |
| "entropy": 5.516168022155762, |
| "epoch": 0.08839255499153977, |
| "grad_norm": 0.8515625, |
| "learning_rate": 0.00011358564215828484, |
| "loss": 5.32, |
| "mean_token_accuracy": 0.17344362288713455, |
| "num_tokens": 9167182.0, |
| "step": 3265 |
| }, |
| { |
| "entropy": 5.532025480270386, |
| "epoch": 0.08852791878172589, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.00011276712008492254, |
| "loss": 5.3615, |
| "mean_token_accuracy": 0.1667541205883026, |
| "num_tokens": 9181427.0, |
| "step": 3270 |
| }, |
| { |
| "entropy": 5.429120492935181, |
| "epoch": 0.08866328257191201, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.00011195304570791451, |
| "loss": 5.1506, |
| "mean_token_accuracy": 0.18498873859643936, |
| "num_tokens": 9194525.0, |
| "step": 3275 |
| }, |
| { |
| "entropy": 5.465721178054809, |
| "epoch": 0.08879864636209814, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.00011114344134552094, |
| "loss": 5.2907, |
| "mean_token_accuracy": 0.1747796967625618, |
| "num_tokens": 9209100.0, |
| "step": 3280 |
| }, |
| { |
| "entropy": 5.464006948471069, |
| "epoch": 0.08893401015228426, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.0001103383291934545, |
| "loss": 5.2596, |
| "mean_token_accuracy": 0.17388538867235184, |
| "num_tokens": 9222821.0, |
| "step": 3285 |
| }, |
| { |
| "entropy": 5.484611940383911, |
| "epoch": 0.08906937394247039, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00010953773132427141, |
| "loss": 5.2351, |
| "mean_token_accuracy": 0.17779595404863358, |
| "num_tokens": 9234861.0, |
| "step": 3290 |
| }, |
| { |
| "entropy": 5.528689193725586, |
| "epoch": 0.08920473773265651, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.00010874166968676677, |
| "loss": 5.3835, |
| "mean_token_accuracy": 0.16561046987771988, |
| "num_tokens": 9249083.0, |
| "step": 3295 |
| }, |
| { |
| "entropy": 5.44285945892334, |
| "epoch": 0.08934010152284264, |
| "grad_norm": 0.91015625, |
| "learning_rate": 0.00010795016610537251, |
| "loss": 5.2817, |
| "mean_token_accuracy": 0.16983783692121507, |
| "num_tokens": 9264952.0, |
| "step": 3300 |
| }, |
| { |
| "entropy": 5.4330676078796385, |
| "epoch": 0.08947546531302876, |
| "grad_norm": 0.921875, |
| "learning_rate": 0.00010716324227955904, |
| "loss": 5.216, |
| "mean_token_accuracy": 0.17587786316871643, |
| "num_tokens": 9280403.0, |
| "step": 3305 |
| }, |
| { |
| "entropy": 5.457645463943481, |
| "epoch": 0.08961082910321488, |
| "grad_norm": 0.859375, |
| "learning_rate": 0.0001063809197832406, |
| "loss": 5.2906, |
| "mean_token_accuracy": 0.17256036549806594, |
| "num_tokens": 9295280.0, |
| "step": 3310 |
| }, |
| { |
| "entropy": 5.43573489189148, |
| "epoch": 0.08974619289340101, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00010560322006418368, |
| "loss": 5.2939, |
| "mean_token_accuracy": 0.17864404022693633, |
| "num_tokens": 9307588.0, |
| "step": 3315 |
| }, |
| { |
| "entropy": 5.478760576248169, |
| "epoch": 0.08988155668358715, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.00010483016444341887, |
| "loss": 5.2257, |
| "mean_token_accuracy": 0.17621223032474517, |
| "num_tokens": 9323057.0, |
| "step": 3320 |
| }, |
| { |
| "entropy": 5.40908203125, |
| "epoch": 0.09001692047377327, |
| "grad_norm": 0.9296875, |
| "learning_rate": 0.00010406177411465654, |
| "loss": 5.1673, |
| "mean_token_accuracy": 0.17435249239206313, |
| "num_tokens": 9337031.0, |
| "step": 3325 |
| }, |
| { |
| "entropy": 5.4669163703918455, |
| "epoch": 0.0901522842639594, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00010329807014370562, |
| "loss": 5.2439, |
| "mean_token_accuracy": 0.17599764615297317, |
| "num_tokens": 9351241.0, |
| "step": 3330 |
| }, |
| { |
| "entropy": 5.4449389457702635, |
| "epoch": 0.09028764805414552, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00010253907346789632, |
| "loss": 5.2455, |
| "mean_token_accuracy": 0.1750466227531433, |
| "num_tokens": 9365191.0, |
| "step": 3335 |
| }, |
| { |
| "entropy": 5.429995393753051, |
| "epoch": 0.09042301184433164, |
| "grad_norm": 0.90234375, |
| "learning_rate": 0.00010178480489550596, |
| "loss": 5.2899, |
| "mean_token_accuracy": 0.1745767444372177, |
| "num_tokens": 9380472.0, |
| "step": 3340 |
| }, |
| { |
| "entropy": 5.522990751266479, |
| "epoch": 0.09055837563451777, |
| "grad_norm": 0.87109375, |
| "learning_rate": 0.00010103528510518836, |
| "loss": 5.3416, |
| "mean_token_accuracy": 0.16517020910978317, |
| "num_tokens": 9397192.0, |
| "step": 3345 |
| }, |
| { |
| "entropy": 5.44988055229187, |
| "epoch": 0.09069373942470389, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0001002905346454073, |
| "loss": 5.2139, |
| "mean_token_accuracy": 0.1854239895939827, |
| "num_tokens": 9408900.0, |
| "step": 3350 |
| }, |
| { |
| "entropy": 5.466029644012451, |
| "epoch": 0.09082910321489002, |
| "grad_norm": 0.88671875, |
| "learning_rate": 9.955057393387285e-05, |
| "loss": 5.2705, |
| "mean_token_accuracy": 0.177003213763237, |
| "num_tokens": 9423048.0, |
| "step": 3355 |
| }, |
| { |
| "entropy": 5.428363418579101, |
| "epoch": 0.09096446700507614, |
| "grad_norm": 0.953125, |
| "learning_rate": 9.88154232569816e-05, |
| "loss": 5.2474, |
| "mean_token_accuracy": 0.17786458134651184, |
| "num_tokens": 9435378.0, |
| "step": 3360 |
| }, |
| { |
| "entropy": 5.495788192749023, |
| "epoch": 0.09109983079526227, |
| "grad_norm": 0.9765625, |
| "learning_rate": 9.808510276926075e-05, |
| "loss": 5.2937, |
| "mean_token_accuracy": 0.17255342304706572, |
| "num_tokens": 9449534.0, |
| "step": 3365 |
| }, |
| { |
| "entropy": 5.452598905563354, |
| "epoch": 0.09123519458544839, |
| "grad_norm": 0.9921875, |
| "learning_rate": 9.735963249281549e-05, |
| "loss": 5.2001, |
| "mean_token_accuracy": 0.17846726328134538, |
| "num_tokens": 9462970.0, |
| "step": 3370 |
| }, |
| { |
| "entropy": 5.47204852104187, |
| "epoch": 0.09137055837563451, |
| "grad_norm": 0.953125, |
| "learning_rate": 9.663903231677974e-05, |
| "loss": 5.2927, |
| "mean_token_accuracy": 0.1703501284122467, |
| "num_tokens": 9475539.0, |
| "step": 3375 |
| }, |
| { |
| "entropy": 5.42021541595459, |
| "epoch": 0.09150592216582064, |
| "grad_norm": 1.0625, |
| "learning_rate": 9.592332199677145e-05, |
| "loss": 5.2138, |
| "mean_token_accuracy": 0.18433151245117188, |
| "num_tokens": 9490219.0, |
| "step": 3380 |
| }, |
| { |
| "entropy": 5.477157497406006, |
| "epoch": 0.09164128595600676, |
| "grad_norm": 0.99609375, |
| "learning_rate": 9.521252115435061e-05, |
| "loss": 5.2509, |
| "mean_token_accuracy": 0.17215492874383925, |
| "num_tokens": 9503304.0, |
| "step": 3385 |
| }, |
| { |
| "entropy": 5.442840576171875, |
| "epoch": 0.09177664974619289, |
| "grad_norm": 1.2265625, |
| "learning_rate": 9.450664927648126e-05, |
| "loss": 5.2477, |
| "mean_token_accuracy": 0.17944649904966353, |
| "num_tokens": 9514721.0, |
| "step": 3390 |
| }, |
| { |
| "entropy": 5.427846240997314, |
| "epoch": 0.09191201353637903, |
| "grad_norm": 0.98828125, |
| "learning_rate": 9.380572571499758e-05, |
| "loss": 5.2161, |
| "mean_token_accuracy": 0.17255792617797852, |
| "num_tokens": 9529360.0, |
| "step": 3395 |
| }, |
| { |
| "entropy": 5.546936416625977, |
| "epoch": 0.09204737732656515, |
| "grad_norm": 0.8359375, |
| "learning_rate": 9.310976968607307e-05, |
| "loss": 5.2605, |
| "mean_token_accuracy": 0.1750967487692833, |
| "num_tokens": 9543512.0, |
| "step": 3400 |
| }, |
| { |
| "entropy": 5.449555110931397, |
| "epoch": 0.09218274111675127, |
| "grad_norm": 1.1015625, |
| "learning_rate": 9.241880026969381e-05, |
| "loss": 5.2019, |
| "mean_token_accuracy": 0.1844763919711113, |
| "num_tokens": 9556305.0, |
| "step": 3405 |
| }, |
| { |
| "entropy": 5.465081453323364, |
| "epoch": 0.0923181049069374, |
| "grad_norm": 0.96484375, |
| "learning_rate": 9.173283640913537e-05, |
| "loss": 5.2264, |
| "mean_token_accuracy": 0.17751589566469192, |
| "num_tokens": 9569304.0, |
| "step": 3410 |
| }, |
| { |
| "entropy": 5.456621789932251, |
| "epoch": 0.09245346869712352, |
| "grad_norm": 1.0, |
| "learning_rate": 9.10518969104436e-05, |
| "loss": 5.2101, |
| "mean_token_accuracy": 0.18279945403337478, |
| "num_tokens": 9582470.0, |
| "step": 3415 |
| }, |
| { |
| "entropy": 5.4090142250061035, |
| "epoch": 0.09258883248730965, |
| "grad_norm": 0.99609375, |
| "learning_rate": 9.037600044191868e-05, |
| "loss": 5.2236, |
| "mean_token_accuracy": 0.17098118364810944, |
| "num_tokens": 9595990.0, |
| "step": 3420 |
| }, |
| { |
| "entropy": 5.401455307006836, |
| "epoch": 0.09272419627749577, |
| "grad_norm": 0.9296875, |
| "learning_rate": 8.970516553360383e-05, |
| "loss": 5.1762, |
| "mean_token_accuracy": 0.17664928287267684, |
| "num_tokens": 9610814.0, |
| "step": 3425 |
| }, |
| { |
| "entropy": 5.409914445877075, |
| "epoch": 0.0928595600676819, |
| "grad_norm": 0.95703125, |
| "learning_rate": 8.903941057677692e-05, |
| "loss": 5.1037, |
| "mean_token_accuracy": 0.17462638914585113, |
| "num_tokens": 9625206.0, |
| "step": 3430 |
| }, |
| { |
| "entropy": 5.535821390151978, |
| "epoch": 0.09299492385786802, |
| "grad_norm": 1.0, |
| "learning_rate": 8.837875382344635e-05, |
| "loss": 5.3614, |
| "mean_token_accuracy": 0.17211337238550187, |
| "num_tokens": 9641154.0, |
| "step": 3435 |
| }, |
| { |
| "entropy": 5.494901990890503, |
| "epoch": 0.09313028764805414, |
| "grad_norm": 0.99609375, |
| "learning_rate": 8.772321338585076e-05, |
| "loss": 5.3006, |
| "mean_token_accuracy": 0.1777035564184189, |
| "num_tokens": 9655099.0, |
| "step": 3440 |
| }, |
| { |
| "entropy": 5.447452878952026, |
| "epoch": 0.09326565143824027, |
| "grad_norm": 1.0, |
| "learning_rate": 8.707280723596242e-05, |
| "loss": 5.2329, |
| "mean_token_accuracy": 0.179787740111351, |
| "num_tokens": 9668329.0, |
| "step": 3445 |
| }, |
| { |
| "entropy": 5.473836851119995, |
| "epoch": 0.09340101522842639, |
| "grad_norm": 0.94140625, |
| "learning_rate": 8.64275532049944e-05, |
| "loss": 5.2943, |
| "mean_token_accuracy": 0.1728879228234291, |
| "num_tokens": 9681972.0, |
| "step": 3450 |
| }, |
| { |
| "entropy": 5.432269954681397, |
| "epoch": 0.09353637901861252, |
| "grad_norm": 0.98046875, |
| "learning_rate": 8.578746898291198e-05, |
| "loss": 5.2292, |
| "mean_token_accuracy": 0.18144699335098266, |
| "num_tokens": 9695989.0, |
| "step": 3455 |
| }, |
| { |
| "entropy": 5.46670126914978, |
| "epoch": 0.09367174280879864, |
| "grad_norm": 0.8203125, |
| "learning_rate": 8.515257211794742e-05, |
| "loss": 5.2274, |
| "mean_token_accuracy": 0.1761029839515686, |
| "num_tokens": 9710769.0, |
| "step": 3460 |
| }, |
| { |
| "entropy": 5.407367706298828, |
| "epoch": 0.09380710659898477, |
| "grad_norm": 0.953125, |
| "learning_rate": 8.452288001611896e-05, |
| "loss": 5.1674, |
| "mean_token_accuracy": 0.1863648325204849, |
| "num_tokens": 9724251.0, |
| "step": 3465 |
| }, |
| { |
| "entropy": 5.461634397506714, |
| "epoch": 0.09394247038917089, |
| "grad_norm": 0.890625, |
| "learning_rate": 8.389840994075379e-05, |
| "loss": 5.2588, |
| "mean_token_accuracy": 0.17784644812345504, |
| "num_tokens": 9738229.0, |
| "step": 3470 |
| }, |
| { |
| "entropy": 5.495303535461426, |
| "epoch": 0.09407783417935703, |
| "grad_norm": 0.82421875, |
| "learning_rate": 8.327917901201435e-05, |
| "loss": 5.3132, |
| "mean_token_accuracy": 0.17286971658468248, |
| "num_tokens": 9752971.0, |
| "step": 3475 |
| }, |
| { |
| "entropy": 5.416939926147461, |
| "epoch": 0.09421319796954315, |
| "grad_norm": 0.89453125, |
| "learning_rate": 8.266520420642931e-05, |
| "loss": 5.1684, |
| "mean_token_accuracy": 0.18302588760852814, |
| "num_tokens": 9766579.0, |
| "step": 3480 |
| }, |
| { |
| "entropy": 5.4572412967681885, |
| "epoch": 0.09434856175972928, |
| "grad_norm": 0.984375, |
| "learning_rate": 8.205650235642828e-05, |
| "loss": 5.2161, |
| "mean_token_accuracy": 0.18117392659187317, |
| "num_tokens": 9778847.0, |
| "step": 3485 |
| }, |
| { |
| "entropy": 5.548181772232056, |
| "epoch": 0.0944839255499154, |
| "grad_norm": 0.83984375, |
| "learning_rate": 8.145309014987978e-05, |
| "loss": 5.3412, |
| "mean_token_accuracy": 0.16816486120224, |
| "num_tokens": 9794524.0, |
| "step": 3490 |
| }, |
| { |
| "entropy": 5.509027767181396, |
| "epoch": 0.09461928934010153, |
| "grad_norm": 0.96875, |
| "learning_rate": 8.085498412963437e-05, |
| "loss": 5.2257, |
| "mean_token_accuracy": 0.17833439260721207, |
| "num_tokens": 9808447.0, |
| "step": 3495 |
| }, |
| { |
| "entropy": 5.419754076004028, |
| "epoch": 0.09475465313028765, |
| "grad_norm": 1.0078125, |
| "learning_rate": 8.026220069307078e-05, |
| "loss": 5.2201, |
| "mean_token_accuracy": 0.17646121084690095, |
| "num_tokens": 9822690.0, |
| "step": 3500 |
| }, |
| { |
| "entropy": 5.4755147933959964, |
| "epoch": 0.09489001692047377, |
| "grad_norm": 0.88671875, |
| "learning_rate": 7.967475609164621e-05, |
| "loss": 5.2813, |
| "mean_token_accuracy": 0.17337468415498733, |
| "num_tokens": 9838460.0, |
| "step": 3505 |
| }, |
| { |
| "entropy": 5.434066534042358, |
| "epoch": 0.0950253807106599, |
| "grad_norm": 0.9375, |
| "learning_rate": 7.909266643045124e-05, |
| "loss": 5.218, |
| "mean_token_accuracy": 0.17817495465278627, |
| "num_tokens": 9852301.0, |
| "step": 3510 |
| }, |
| { |
| "entropy": 5.470828866958618, |
| "epoch": 0.09516074450084602, |
| "grad_norm": 0.99609375, |
| "learning_rate": 7.851594766776802e-05, |
| "loss": 5.2477, |
| "mean_token_accuracy": 0.1855323702096939, |
| "num_tokens": 9867281.0, |
| "step": 3515 |
| }, |
| { |
| "entropy": 5.4018556594848635, |
| "epoch": 0.09529610829103215, |
| "grad_norm": 0.87890625, |
| "learning_rate": 7.794461561463265e-05, |
| "loss": 5.1356, |
| "mean_token_accuracy": 0.1820910558104515, |
| "num_tokens": 9881523.0, |
| "step": 3520 |
| }, |
| { |
| "entropy": 5.3998528003692625, |
| "epoch": 0.09543147208121827, |
| "grad_norm": 1.046875, |
| "learning_rate": 7.7378685934402e-05, |
| "loss": 5.1708, |
| "mean_token_accuracy": 0.18137171864509583, |
| "num_tokens": 9894865.0, |
| "step": 3525 |
| }, |
| { |
| "entropy": 5.467069101333618, |
| "epoch": 0.0955668358714044, |
| "grad_norm": 0.96484375, |
| "learning_rate": 7.68181741423242e-05, |
| "loss": 5.2332, |
| "mean_token_accuracy": 0.1749477729201317, |
| "num_tokens": 9910598.0, |
| "step": 3530 |
| }, |
| { |
| "entropy": 5.46595401763916, |
| "epoch": 0.09570219966159052, |
| "grad_norm": 1.0625, |
| "learning_rate": 7.626309560511313e-05, |
| "loss": 5.3158, |
| "mean_token_accuracy": 0.1718402922153473, |
| "num_tokens": 9924811.0, |
| "step": 3535 |
| }, |
| { |
| "entropy": 5.37374210357666, |
| "epoch": 0.09583756345177664, |
| "grad_norm": 0.921875, |
| "learning_rate": 7.571346554052724e-05, |
| "loss": 5.1803, |
| "mean_token_accuracy": 0.1788783609867096, |
| "num_tokens": 9939839.0, |
| "step": 3540 |
| }, |
| { |
| "entropy": 5.477428960800171, |
| "epoch": 0.09597292724196277, |
| "grad_norm": 0.9453125, |
| "learning_rate": 7.516929901695249e-05, |
| "loss": 5.2214, |
| "mean_token_accuracy": 0.18248335421085357, |
| "num_tokens": 9952556.0, |
| "step": 3545 |
| }, |
| { |
| "entropy": 5.493585300445557, |
| "epoch": 0.09610829103214891, |
| "grad_norm": 0.9140625, |
| "learning_rate": 7.463061095298893e-05, |
| "loss": 5.2934, |
| "mean_token_accuracy": 0.17488276362419128, |
| "num_tokens": 9968060.0, |
| "step": 3550 |
| }, |
| { |
| "entropy": 5.420634984970093, |
| "epoch": 0.09624365482233503, |
| "grad_norm": 1.0078125, |
| "learning_rate": 7.409741611704198e-05, |
| "loss": 5.1702, |
| "mean_token_accuracy": 0.18496295660734177, |
| "num_tokens": 9982607.0, |
| "step": 3555 |
| }, |
| { |
| "entropy": 5.412036561965943, |
| "epoch": 0.09637901861252116, |
| "grad_norm": 1.0078125, |
| "learning_rate": 7.35697291269174e-05, |
| "loss": 5.1884, |
| "mean_token_accuracy": 0.1730993464589119, |
| "num_tokens": 9997447.0, |
| "step": 3560 |
| }, |
| { |
| "entropy": 5.38278169631958, |
| "epoch": 0.09651438240270728, |
| "grad_norm": 1.046875, |
| "learning_rate": 7.304756444942056e-05, |
| "loss": 5.1539, |
| "mean_token_accuracy": 0.1781917095184326, |
| "num_tokens": 10010124.0, |
| "step": 3565 |
| }, |
| { |
| "entropy": 5.462849140167236, |
| "epoch": 0.0966497461928934, |
| "grad_norm": 0.93359375, |
| "learning_rate": 7.253093639995994e-05, |
| "loss": 5.2831, |
| "mean_token_accuracy": 0.17512934952974318, |
| "num_tokens": 10024441.0, |
| "step": 3570 |
| }, |
| { |
| "entropy": 5.478954744338989, |
| "epoch": 0.09678510998307953, |
| "grad_norm": 0.94140625, |
| "learning_rate": 7.20198591421544e-05, |
| "loss": 5.2943, |
| "mean_token_accuracy": 0.171660877764225, |
| "num_tokens": 10038886.0, |
| "step": 3575 |
| }, |
| { |
| "entropy": 5.500023937225341, |
| "epoch": 0.09692047377326565, |
| "grad_norm": 0.9296875, |
| "learning_rate": 7.151434668744517e-05, |
| "loss": 5.3161, |
| "mean_token_accuracy": 0.17876716703176498, |
| "num_tokens": 10052929.0, |
| "step": 3580 |
| }, |
| { |
| "entropy": 5.483731269836426, |
| "epoch": 0.09705583756345178, |
| "grad_norm": 1.0625, |
| "learning_rate": 7.101441289471153e-05, |
| "loss": 5.2905, |
| "mean_token_accuracy": 0.17570538371801375, |
| "num_tokens": 10066239.0, |
| "step": 3585 |
| }, |
| { |
| "entropy": 5.421175622940064, |
| "epoch": 0.0971912013536379, |
| "grad_norm": 1.046875, |
| "learning_rate": 7.052007146989098e-05, |
| "loss": 5.1395, |
| "mean_token_accuracy": 0.179901522397995, |
| "num_tokens": 10079525.0, |
| "step": 3590 |
| }, |
| { |
| "entropy": 5.384795904159546, |
| "epoch": 0.09732656514382403, |
| "grad_norm": 0.96484375, |
| "learning_rate": 7.003133596560341e-05, |
| "loss": 5.1582, |
| "mean_token_accuracy": 0.18871900141239167, |
| "num_tokens": 10093915.0, |
| "step": 3595 |
| }, |
| { |
| "entropy": 5.387734842300415, |
| "epoch": 0.09746192893401015, |
| "grad_norm": 0.92578125, |
| "learning_rate": 6.954821978077952e-05, |
| "loss": 5.1844, |
| "mean_token_accuracy": 0.18447159379720687, |
| "num_tokens": 10108406.0, |
| "step": 3600 |
| }, |
| { |
| "entropy": 5.421917963027954, |
| "epoch": 0.09759729272419627, |
| "grad_norm": 0.87890625, |
| "learning_rate": 6.907073616029356e-05, |
| "loss": 5.2285, |
| "mean_token_accuracy": 0.17513605952262878, |
| "num_tokens": 10122768.0, |
| "step": 3605 |
| }, |
| { |
| "entropy": 5.47025580406189, |
| "epoch": 0.0977326565143824, |
| "grad_norm": 0.96875, |
| "learning_rate": 6.85988981946002e-05, |
| "loss": 5.317, |
| "mean_token_accuracy": 0.16671132892370225, |
| "num_tokens": 10137705.0, |
| "step": 3610 |
| }, |
| { |
| "entropy": 5.41975588798523, |
| "epoch": 0.09786802030456852, |
| "grad_norm": 0.94921875, |
| "learning_rate": 6.813271881937564e-05, |
| "loss": 5.1786, |
| "mean_token_accuracy": 0.1797885350883007, |
| "num_tokens": 10153065.0, |
| "step": 3615 |
| }, |
| { |
| "entropy": 5.474036645889282, |
| "epoch": 0.09800338409475465, |
| "grad_norm": 0.921875, |
| "learning_rate": 6.767221081516286e-05, |
| "loss": 5.2658, |
| "mean_token_accuracy": 0.17338726818561553, |
| "num_tokens": 10168430.0, |
| "step": 3620 |
| }, |
| { |
| "entropy": 5.443027448654175, |
| "epoch": 0.09813874788494077, |
| "grad_norm": 0.93359375, |
| "learning_rate": 6.72173868070215e-05, |
| "loss": 5.1754, |
| "mean_token_accuracy": 0.1833331510424614, |
| "num_tokens": 10182222.0, |
| "step": 3625 |
| }, |
| { |
| "entropy": 5.503278112411499, |
| "epoch": 0.09827411167512691, |
| "grad_norm": 0.86328125, |
| "learning_rate": 6.676825926418149e-05, |
| "loss": 5.2927, |
| "mean_token_accuracy": 0.17598096579313277, |
| "num_tokens": 10198470.0, |
| "step": 3630 |
| }, |
| { |
| "entropy": 5.457680559158325, |
| "epoch": 0.09840947546531303, |
| "grad_norm": 0.91015625, |
| "learning_rate": 6.632484049970122e-05, |
| "loss": 5.2838, |
| "mean_token_accuracy": 0.17474121153354644, |
| "num_tokens": 10212676.0, |
| "step": 3635 |
| }, |
| { |
| "entropy": 5.431332063674927, |
| "epoch": 0.09854483925549916, |
| "grad_norm": 0.99609375, |
| "learning_rate": 6.588714267013019e-05, |
| "loss": 5.2276, |
| "mean_token_accuracy": 0.17433813363313674, |
| "num_tokens": 10224893.0, |
| "step": 3640 |
| }, |
| { |
| "entropy": 5.483983039855957, |
| "epoch": 0.09868020304568528, |
| "grad_norm": 0.8984375, |
| "learning_rate": 6.545517777517544e-05, |
| "loss": 5.2464, |
| "mean_token_accuracy": 0.1813598617911339, |
| "num_tokens": 10238786.0, |
| "step": 3645 |
| }, |
| { |
| "entropy": 5.4722819328308105, |
| "epoch": 0.09881556683587141, |
| "grad_norm": 0.92578125, |
| "learning_rate": 6.502895765737281e-05, |
| "loss": 5.252, |
| "mean_token_accuracy": 0.16823621690273285, |
| "num_tokens": 10252831.0, |
| "step": 3650 |
| }, |
| { |
| "entropy": 5.427985715866089, |
| "epoch": 0.09895093062605753, |
| "grad_norm": 0.84375, |
| "learning_rate": 6.460849400176212e-05, |
| "loss": 5.2286, |
| "mean_token_accuracy": 0.1749664455652237, |
| "num_tokens": 10268886.0, |
| "step": 3655 |
| }, |
| { |
| "entropy": 5.503793334960937, |
| "epoch": 0.09908629441624366, |
| "grad_norm": 1.0546875, |
| "learning_rate": 6.419379833556694e-05, |
| "loss": 5.3155, |
| "mean_token_accuracy": 0.17741915136575698, |
| "num_tokens": 10282332.0, |
| "step": 3660 |
| }, |
| { |
| "entropy": 5.452091121673584, |
| "epoch": 0.09922165820642978, |
| "grad_norm": 1.0078125, |
| "learning_rate": 6.378488202787835e-05, |
| "loss": 5.2168, |
| "mean_token_accuracy": 0.17554211616516113, |
| "num_tokens": 10295262.0, |
| "step": 3665 |
| }, |
| { |
| "entropy": 5.445429563522339, |
| "epoch": 0.0993570219966159, |
| "grad_norm": 0.92578125, |
| "learning_rate": 6.33817562893435e-05, |
| "loss": 5.2164, |
| "mean_token_accuracy": 0.18022813349962236, |
| "num_tokens": 10310202.0, |
| "step": 3670 |
| }, |
| { |
| "entropy": 5.478223133087158, |
| "epoch": 0.09949238578680203, |
| "grad_norm": 0.93359375, |
| "learning_rate": 6.29844321718582e-05, |
| "loss": 5.2857, |
| "mean_token_accuracy": 0.17693584710359572, |
| "num_tokens": 10322581.0, |
| "step": 3675 |
| }, |
| { |
| "entropy": 5.501222801208496, |
| "epoch": 0.09962774957698815, |
| "grad_norm": 1.046875, |
| "learning_rate": 6.259292056826383e-05, |
| "loss": 5.3048, |
| "mean_token_accuracy": 0.17106766849756241, |
| "num_tokens": 10335451.0, |
| "step": 3680 |
| }, |
| { |
| "entropy": 5.453751420974731, |
| "epoch": 0.09976311336717428, |
| "grad_norm": 0.921875, |
| "learning_rate": 6.220723221204873e-05, |
| "loss": 5.1911, |
| "mean_token_accuracy": 0.18236185610294342, |
| "num_tokens": 10349664.0, |
| "step": 3685 |
| }, |
| { |
| "entropy": 5.482261371612549, |
| "epoch": 0.0998984771573604, |
| "grad_norm": 1.078125, |
| "learning_rate": 6.182737767705406e-05, |
| "loss": 5.2385, |
| "mean_token_accuracy": 0.17836161702871323, |
| "num_tokens": 10363222.0, |
| "step": 3690 |
| }, |
| { |
| "entropy": 5.414063405990601, |
| "epoch": 0.10003384094754653, |
| "grad_norm": 0.984375, |
| "learning_rate": 6.145336737718375e-05, |
| "loss": 5.2521, |
| "mean_token_accuracy": 0.1778153583407402, |
| "num_tokens": 10377084.0, |
| "step": 3695 |
| }, |
| { |
| "entropy": 5.439861106872558, |
| "epoch": 0.10016920473773265, |
| "grad_norm": 0.96875, |
| "learning_rate": 6.10852115661191e-05, |
| "loss": 5.2042, |
| "mean_token_accuracy": 0.1773260474205017, |
| "num_tokens": 10391151.0, |
| "step": 3700 |
| }, |
| { |
| "entropy": 5.38260555267334, |
| "epoch": 0.10030456852791877, |
| "grad_norm": 0.85546875, |
| "learning_rate": 6.072292033703766e-05, |
| "loss": 5.1476, |
| "mean_token_accuracy": 0.18702121675014496, |
| "num_tokens": 10404601.0, |
| "step": 3705 |
| }, |
| { |
| "entropy": 5.455022859573364, |
| "epoch": 0.10043993231810491, |
| "grad_norm": 1.015625, |
| "learning_rate": 6.036650362233648e-05, |
| "loss": 5.3161, |
| "mean_token_accuracy": 0.16847151815891265, |
| "num_tokens": 10418201.0, |
| "step": 3710 |
| }, |
| { |
| "entropy": 5.4407267570495605, |
| "epoch": 0.10057529610829104, |
| "grad_norm": 1.03125, |
| "learning_rate": 6.0015971193359824e-05, |
| "loss": 5.1724, |
| "mean_token_accuracy": 0.18162354379892348, |
| "num_tokens": 10431030.0, |
| "step": 3715 |
| }, |
| { |
| "entropy": 5.465402412414551, |
| "epoch": 0.10071065989847716, |
| "grad_norm": 1.015625, |
| "learning_rate": 5.9671332660131306e-05, |
| "loss": 5.2411, |
| "mean_token_accuracy": 0.17822658121585847, |
| "num_tokens": 10444470.0, |
| "step": 3720 |
| }, |
| { |
| "entropy": 5.4923155307769775, |
| "epoch": 0.10084602368866329, |
| "grad_norm": 1.015625, |
| "learning_rate": 5.933259747109042e-05, |
| "loss": 5.2845, |
| "mean_token_accuracy": 0.17237729281187059, |
| "num_tokens": 10457686.0, |
| "step": 3725 |
| }, |
| { |
| "entropy": 5.421149730682373, |
| "epoch": 0.10098138747884941, |
| "grad_norm": 0.91015625, |
| "learning_rate": 5.899977491283351e-05, |
| "loss": 5.1355, |
| "mean_token_accuracy": 0.18317325860261918, |
| "num_tokens": 10472039.0, |
| "step": 3730 |
| }, |
| { |
| "entropy": 5.476395988464356, |
| "epoch": 0.10111675126903553, |
| "grad_norm": 0.91796875, |
| "learning_rate": 5.867287410985908e-05, |
| "loss": 5.1902, |
| "mean_token_accuracy": 0.17925067692995073, |
| "num_tokens": 10485161.0, |
| "step": 3735 |
| }, |
| { |
| "entropy": 5.387272596359253, |
| "epoch": 0.10125211505922166, |
| "grad_norm": 0.92578125, |
| "learning_rate": 5.835190402431779e-05, |
| "loss": 5.2151, |
| "mean_token_accuracy": 0.18368397653102875, |
| "num_tokens": 10499106.0, |
| "step": 3740 |
| }, |
| { |
| "entropy": 5.504530429840088, |
| "epoch": 0.10138747884940778, |
| "grad_norm": 1.0078125, |
| "learning_rate": 5.803687345576673e-05, |
| "loss": 5.2795, |
| "mean_token_accuracy": 0.1814903661608696, |
| "num_tokens": 10513209.0, |
| "step": 3745 |
| }, |
| { |
| "entropy": 5.465247631072998, |
| "epoch": 0.10152284263959391, |
| "grad_norm": 0.99609375, |
| "learning_rate": 5.7727791040927977e-05, |
| "loss": 5.2493, |
| "mean_token_accuracy": 0.17284207046031952, |
| "num_tokens": 10527883.0, |
| "step": 3750 |
| }, |
| { |
| "entropy": 5.473253870010376, |
| "epoch": 0.10165820642978003, |
| "grad_norm": 0.921875, |
| "learning_rate": 5.742466525345213e-05, |
| "loss": 5.1674, |
| "mean_token_accuracy": 0.1791956305503845, |
| "num_tokens": 10541871.0, |
| "step": 3755 |
| }, |
| { |
| "entropy": 5.41374135017395, |
| "epoch": 0.10179357021996616, |
| "grad_norm": 0.87890625, |
| "learning_rate": 5.7127504403685775e-05, |
| "loss": 5.1771, |
| "mean_token_accuracy": 0.17775085270404817, |
| "num_tokens": 10556322.0, |
| "step": 3760 |
| }, |
| { |
| "entropy": 5.441633033752441, |
| "epoch": 0.10192893401015228, |
| "grad_norm": 0.96875, |
| "learning_rate": 5.6836316638443664e-05, |
| "loss": 5.1265, |
| "mean_token_accuracy": 0.18571407794952394, |
| "num_tokens": 10569399.0, |
| "step": 3765 |
| }, |
| { |
| "entropy": 5.494030094146728, |
| "epoch": 0.1020642978003384, |
| "grad_norm": 0.94921875, |
| "learning_rate": 5.655110994078553e-05, |
| "loss": 5.2973, |
| "mean_token_accuracy": 0.17363038361072541, |
| "num_tokens": 10583481.0, |
| "step": 3770 |
| }, |
| { |
| "entropy": 5.452342128753662, |
| "epoch": 0.10219966159052453, |
| "grad_norm": 0.9375, |
| "learning_rate": 5.6271892129797056e-05, |
| "loss": 5.1813, |
| "mean_token_accuracy": 0.17757375687360763, |
| "num_tokens": 10597706.0, |
| "step": 3775 |
| }, |
| { |
| "entropy": 5.386959171295166, |
| "epoch": 0.10233502538071065, |
| "grad_norm": 0.94921875, |
| "learning_rate": 5.599867086037556e-05, |
| "loss": 5.0745, |
| "mean_token_accuracy": 0.18331465721130372, |
| "num_tokens": 10611437.0, |
| "step": 3780 |
| }, |
| { |
| "entropy": 5.468786334991455, |
| "epoch": 0.10247038917089679, |
| "grad_norm": 0.94140625, |
| "learning_rate": 5.573145362302012e-05, |
| "loss": 5.3312, |
| "mean_token_accuracy": 0.17515545785427095, |
| "num_tokens": 10624076.0, |
| "step": 3785 |
| }, |
| { |
| "entropy": 5.486022806167602, |
| "epoch": 0.10260575296108292, |
| "grad_norm": 0.9609375, |
| "learning_rate": 5.5470247743626404e-05, |
| "loss": 5.3145, |
| "mean_token_accuracy": 0.16346433609724045, |
| "num_tokens": 10639696.0, |
| "step": 3790 |
| }, |
| { |
| "entropy": 5.462622547149659, |
| "epoch": 0.10274111675126904, |
| "grad_norm": 1.0234375, |
| "learning_rate": 5.5215060383285414e-05, |
| "loss": 5.2871, |
| "mean_token_accuracy": 0.17402675300836562, |
| "num_tokens": 10652098.0, |
| "step": 3795 |
| }, |
| { |
| "entropy": 5.46808557510376, |
| "epoch": 0.10287648054145516, |
| "grad_norm": 1.0546875, |
| "learning_rate": 5.496589853808759e-05, |
| "loss": 5.2574, |
| "mean_token_accuracy": 0.17415528744459152, |
| "num_tokens": 10666968.0, |
| "step": 3800 |
| }, |
| { |
| "entropy": 5.4186664581298825, |
| "epoch": 0.10301184433164129, |
| "grad_norm": 1.0546875, |
| "learning_rate": 5.47227690389308e-05, |
| "loss": 5.1148, |
| "mean_token_accuracy": 0.1816213309764862, |
| "num_tokens": 10679663.0, |
| "step": 3805 |
| }, |
| { |
| "entropy": 5.4264075756073, |
| "epoch": 0.10314720812182741, |
| "grad_norm": 0.9453125, |
| "learning_rate": 5.448567855133306e-05, |
| "loss": 5.1901, |
| "mean_token_accuracy": 0.17645768374204635, |
| "num_tokens": 10692660.0, |
| "step": 3810 |
| }, |
| { |
| "entropy": 5.4301145553588865, |
| "epoch": 0.10328257191201354, |
| "grad_norm": 0.984375, |
| "learning_rate": 5.425463357524986e-05, |
| "loss": 5.2028, |
| "mean_token_accuracy": 0.18301489800214768, |
| "num_tokens": 10705806.0, |
| "step": 3815 |
| }, |
| { |
| "entropy": 5.47904863357544, |
| "epoch": 0.10341793570219966, |
| "grad_norm": 0.875, |
| "learning_rate": 5.402964044489591e-05, |
| "loss": 5.2943, |
| "mean_token_accuracy": 0.1806845486164093, |
| "num_tokens": 10720408.0, |
| "step": 3820 |
| }, |
| { |
| "entropy": 5.505579853057862, |
| "epoch": 0.10355329949238579, |
| "grad_norm": 0.90234375, |
| "learning_rate": 5.381070532857153e-05, |
| "loss": 5.2817, |
| "mean_token_accuracy": 0.17546553611755372, |
| "num_tokens": 10737031.0, |
| "step": 3825 |
| }, |
| { |
| "entropy": 5.478611946105957, |
| "epoch": 0.10368866328257191, |
| "grad_norm": 1.03125, |
| "learning_rate": 5.359783422849357e-05, |
| "loss": 5.2734, |
| "mean_token_accuracy": 0.17541965693235398, |
| "num_tokens": 10750669.0, |
| "step": 3830 |
| }, |
| { |
| "entropy": 5.435742044448853, |
| "epoch": 0.10382402707275803, |
| "grad_norm": 0.94921875, |
| "learning_rate": 5.3391032980630736e-05, |
| "loss": 5.2713, |
| "mean_token_accuracy": 0.17451788634061813, |
| "num_tokens": 10766303.0, |
| "step": 3835 |
| }, |
| { |
| "entropy": 5.460405540466309, |
| "epoch": 0.10395939086294416, |
| "grad_norm": 1.09375, |
| "learning_rate": 5.31903072545437e-05, |
| "loss": 5.2081, |
| "mean_token_accuracy": 0.18736861348152162, |
| "num_tokens": 10780288.0, |
| "step": 3840 |
| }, |
| { |
| "entropy": 5.429828453063965, |
| "epoch": 0.10409475465313028, |
| "grad_norm": 0.984375, |
| "learning_rate": 5.29956625532297e-05, |
| "loss": 5.2529, |
| "mean_token_accuracy": 0.1730156198143959, |
| "num_tokens": 10793844.0, |
| "step": 3845 |
| }, |
| { |
| "entropy": 5.420657110214234, |
| "epoch": 0.10423011844331641, |
| "grad_norm": 1.046875, |
| "learning_rate": 5.280710421297146e-05, |
| "loss": 5.2018, |
| "mean_token_accuracy": 0.18210601955652236, |
| "num_tokens": 10808050.0, |
| "step": 3850 |
| }, |
| { |
| "entropy": 5.409189033508301, |
| "epoch": 0.10436548223350253, |
| "grad_norm": 0.91015625, |
| "learning_rate": 5.2624637403191165e-05, |
| "loss": 5.1812, |
| "mean_token_accuracy": 0.18174512237310408, |
| "num_tokens": 10822598.0, |
| "step": 3855 |
| }, |
| { |
| "entropy": 5.432131004333496, |
| "epoch": 0.10450084602368866, |
| "grad_norm": 0.953125, |
| "learning_rate": 5.2448267126308605e-05, |
| "loss": 5.1928, |
| "mean_token_accuracy": 0.17888483554124832, |
| "num_tokens": 10835679.0, |
| "step": 3860 |
| }, |
| { |
| "entropy": 5.4485198020935055, |
| "epoch": 0.1046362098138748, |
| "grad_norm": 1.1015625, |
| "learning_rate": 5.2277998217603954e-05, |
| "loss": 5.1937, |
| "mean_token_accuracy": 0.17868861109018325, |
| "num_tokens": 10848896.0, |
| "step": 3865 |
| }, |
| { |
| "entropy": 5.490707921981811, |
| "epoch": 0.10477157360406092, |
| "grad_norm": 1.03125, |
| "learning_rate": 5.211383534508541e-05, |
| "loss": 5.212, |
| "mean_token_accuracy": 0.1784048408269882, |
| "num_tokens": 10861562.0, |
| "step": 3870 |
| }, |
| { |
| "entropy": 5.42482328414917, |
| "epoch": 0.10490693739424704, |
| "grad_norm": 0.9921875, |
| "learning_rate": 5.1955783009361044e-05, |
| "loss": 5.1451, |
| "mean_token_accuracy": 0.18526836186647416, |
| "num_tokens": 10873483.0, |
| "step": 3875 |
| }, |
| { |
| "entropy": 5.435460948944092, |
| "epoch": 0.10504230118443317, |
| "grad_norm": 0.95703125, |
| "learning_rate": 5.180384554351543e-05, |
| "loss": 5.2047, |
| "mean_token_accuracy": 0.17779654264450073, |
| "num_tokens": 10887788.0, |
| "step": 3880 |
| }, |
| { |
| "entropy": 5.426501941680908, |
| "epoch": 0.10517766497461929, |
| "grad_norm": 0.953125, |
| "learning_rate": 5.1658027112990976e-05, |
| "loss": 5.1484, |
| "mean_token_accuracy": 0.17941227555274963, |
| "num_tokens": 10901017.0, |
| "step": 3885 |
| }, |
| { |
| "entropy": 5.390911626815796, |
| "epoch": 0.10531302876480542, |
| "grad_norm": 0.84375, |
| "learning_rate": 5.151833171547365e-05, |
| "loss": 5.1484, |
| "mean_token_accuracy": 0.1830310583114624, |
| "num_tokens": 10914480.0, |
| "step": 3890 |
| }, |
| { |
| "entropy": 5.433801603317261, |
| "epoch": 0.10544839255499154, |
| "grad_norm": 1.0, |
| "learning_rate": 5.1384763180783274e-05, |
| "loss": 5.2588, |
| "mean_token_accuracy": 0.1759231224656105, |
| "num_tokens": 10929732.0, |
| "step": 3895 |
| }, |
| { |
| "entropy": 5.408439302444458, |
| "epoch": 0.10558375634517767, |
| "grad_norm": 0.96484375, |
| "learning_rate": 5.125732517076876e-05, |
| "loss": 5.1889, |
| "mean_token_accuracy": 0.18901487439870834, |
| "num_tokens": 10942125.0, |
| "step": 3900 |
| }, |
| { |
| "entropy": 5.334071922302246, |
| "epoch": 0.10571912013536379, |
| "grad_norm": 1.015625, |
| "learning_rate": 5.113602117920747e-05, |
| "loss": 5.072, |
| "mean_token_accuracy": 0.1919448718428612, |
| "num_tokens": 10954469.0, |
| "step": 3905 |
| }, |
| { |
| "entropy": 5.39621148109436, |
| "epoch": 0.10585448392554991, |
| "grad_norm": 0.8671875, |
| "learning_rate": 5.102085453170966e-05, |
| "loss": 5.1551, |
| "mean_token_accuracy": 0.18375782817602157, |
| "num_tokens": 10969401.0, |
| "step": 3910 |
| }, |
| { |
| "entropy": 5.453270816802979, |
| "epoch": 0.10598984771573604, |
| "grad_norm": 1.0625, |
| "learning_rate": 5.091182838562709e-05, |
| "loss": 5.2563, |
| "mean_token_accuracy": 0.17768552899360657, |
| "num_tokens": 10984192.0, |
| "step": 3915 |
| }, |
| { |
| "entropy": 5.491350603103638, |
| "epoch": 0.10612521150592216, |
| "grad_norm": 0.85546875, |
| "learning_rate": 5.0808945729966716e-05, |
| "loss": 5.2631, |
| "mean_token_accuracy": 0.17394644767045975, |
| "num_tokens": 10999855.0, |
| "step": 3920 |
| }, |
| { |
| "entropy": 5.465265512466431, |
| "epoch": 0.10626057529610829, |
| "grad_norm": 1.015625, |
| "learning_rate": 5.071220938530844e-05, |
| "loss": 5.2407, |
| "mean_token_accuracy": 0.17272032648324967, |
| "num_tokens": 11011371.0, |
| "step": 3925 |
| }, |
| { |
| "entropy": 5.422465705871582, |
| "epoch": 0.10639593908629441, |
| "grad_norm": 0.97265625, |
| "learning_rate": 5.0621622003728026e-05, |
| "loss": 5.2047, |
| "mean_token_accuracy": 0.18466399610042572, |
| "num_tokens": 11025141.0, |
| "step": 3930 |
| }, |
| { |
| "entropy": 5.506776142120361, |
| "epoch": 0.10653130287648054, |
| "grad_norm": 0.9296875, |
| "learning_rate": 5.053718606872433e-05, |
| "loss": 5.3006, |
| "mean_token_accuracy": 0.178793703019619, |
| "num_tokens": 11038750.0, |
| "step": 3935 |
| }, |
| { |
| "entropy": 5.444697284698487, |
| "epoch": 0.10666666666666667, |
| "grad_norm": 0.93359375, |
| "learning_rate": 5.0458903895151134e-05, |
| "loss": 5.2158, |
| "mean_token_accuracy": 0.17911358028650284, |
| "num_tokens": 11052146.0, |
| "step": 3940 |
| }, |
| { |
| "entropy": 5.430838108062744, |
| "epoch": 0.1068020304568528, |
| "grad_norm": 0.98828125, |
| "learning_rate": 5.038677762915381e-05, |
| "loss": 5.1231, |
| "mean_token_accuracy": 0.1867231696844101, |
| "num_tokens": 11065091.0, |
| "step": 3945 |
| }, |
| { |
| "entropy": 5.3946521282196045, |
| "epoch": 0.10693739424703892, |
| "grad_norm": 0.94140625, |
| "learning_rate": 5.032080924811033e-05, |
| "loss": 5.2273, |
| "mean_token_accuracy": 0.1766382023692131, |
| "num_tokens": 11081124.0, |
| "step": 3950 |
| }, |
| { |
| "entropy": 5.479502820968628, |
| "epoch": 0.10707275803722505, |
| "grad_norm": 1.0234375, |
| "learning_rate": 5.026100056057718e-05, |
| "loss": 5.283, |
| "mean_token_accuracy": 0.17816594392061233, |
| "num_tokens": 11093540.0, |
| "step": 3955 |
| }, |
| { |
| "entropy": 5.48756160736084, |
| "epoch": 0.10720812182741117, |
| "grad_norm": 0.859375, |
| "learning_rate": 5.0207353206239764e-05, |
| "loss": 5.2695, |
| "mean_token_accuracy": 0.17074304521083833, |
| "num_tokens": 11108039.0, |
| "step": 3960 |
| }, |
| { |
| "entropy": 5.424608612060547, |
| "epoch": 0.1073434856175973, |
| "grad_norm": 0.828125, |
| "learning_rate": 5.0159868655867436e-05, |
| "loss": 5.2348, |
| "mean_token_accuracy": 0.1750531792640686, |
| "num_tokens": 11123472.0, |
| "step": 3965 |
| }, |
| { |
| "entropy": 5.406925106048584, |
| "epoch": 0.10747884940778342, |
| "grad_norm": 0.8828125, |
| "learning_rate": 5.011854821127305e-05, |
| "loss": 5.141, |
| "mean_token_accuracy": 0.1887975424528122, |
| "num_tokens": 11136791.0, |
| "step": 3970 |
| }, |
| { |
| "entropy": 5.442727184295654, |
| "epoch": 0.10761421319796954, |
| "grad_norm": 0.91015625, |
| "learning_rate": 5.008339300527755e-05, |
| "loss": 5.1939, |
| "mean_token_accuracy": 0.18285703808069229, |
| "num_tokens": 11149103.0, |
| "step": 3975 |
| }, |
| { |
| "entropy": 5.368607807159424, |
| "epoch": 0.10774957698815567, |
| "grad_norm": 0.87109375, |
| "learning_rate": 5.005440400167859e-05, |
| "loss": 5.0833, |
| "mean_token_accuracy": 0.19177746623754502, |
| "num_tokens": 11163824.0, |
| "step": 3980 |
| }, |
| { |
| "entropy": 5.486799526214599, |
| "epoch": 0.10788494077834179, |
| "grad_norm": 0.96484375, |
| "learning_rate": 5.003158199522442e-05, |
| "loss": 5.241, |
| "mean_token_accuracy": 0.17701994627714157, |
| "num_tokens": 11177750.0, |
| "step": 3985 |
| }, |
| { |
| "entropy": 5.478089284896851, |
| "epoch": 0.10802030456852792, |
| "grad_norm": 0.859375, |
| "learning_rate": 5.0014927611591806e-05, |
| "loss": 5.2495, |
| "mean_token_accuracy": 0.17373744398355484, |
| "num_tokens": 11192089.0, |
| "step": 3990 |
| }, |
| { |
| "entropy": 5.414667749404908, |
| "epoch": 0.10815566835871404, |
| "grad_norm": 0.95703125, |
| "learning_rate": 5.000444130736916e-05, |
| "loss": 5.1754, |
| "mean_token_accuracy": 0.17795276492834092, |
| "num_tokens": 11206240.0, |
| "step": 3995 |
| }, |
| { |
| "entropy": 5.448756742477417, |
| "epoch": 0.10829103214890017, |
| "grad_norm": 0.84765625, |
| "learning_rate": 5.0000123370043736e-05, |
| "loss": 5.2278, |
| "mean_token_accuracy": 0.18019841909408568, |
| "num_tokens": 11219972.0, |
| "step": 4000 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 4000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.9961559926784e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
