| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.10287272072628141, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 10.7425612449646, |
| "epoch": 0.0002571818018157035, |
| "grad_norm": 5.65625, |
| "learning_rate": 2e-06, |
| "loss": 10.7388, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 9030.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 10.742591857910156, |
| "epoch": 0.000514363603631407, |
| "grad_norm": 5.25, |
| "learning_rate": 4.5e-06, |
| "loss": 10.7331, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 18084.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 10.742617130279541, |
| "epoch": 0.0007715454054471106, |
| "grad_norm": 5.1875, |
| "learning_rate": 7e-06, |
| "loss": 10.6991, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 26309.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 10.742614936828613, |
| "epoch": 0.001028727207262814, |
| "grad_norm": 5.1875, |
| "learning_rate": 9.5e-06, |
| "loss": 10.661, |
| "mean_token_accuracy": 0.0013652202673256398, |
| "num_tokens": 35204.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 10.74255428314209, |
| "epoch": 0.0012859090090785177, |
| "grad_norm": 4.3125, |
| "learning_rate": 1.2e-05, |
| "loss": 10.5708, |
| "mean_token_accuracy": 0.009783844836056233, |
| "num_tokens": 44540.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 10.74219331741333, |
| "epoch": 0.0015430908108942211, |
| "grad_norm": 4.03125, |
| "learning_rate": 1.4500000000000002e-05, |
| "loss": 10.4335, |
| "mean_token_accuracy": 0.035427753999829295, |
| "num_tokens": 53118.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 10.740796661376953, |
| "epoch": 0.0018002726127099246, |
| "grad_norm": 3.28125, |
| "learning_rate": 1.7000000000000003e-05, |
| "loss": 10.3091, |
| "mean_token_accuracy": 0.04362985044717789, |
| "num_tokens": 61753.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 10.736623382568359, |
| "epoch": 0.002057454414525628, |
| "grad_norm": 2.765625, |
| "learning_rate": 1.95e-05, |
| "loss": 10.1821, |
| "mean_token_accuracy": 0.044929017499089244, |
| "num_tokens": 71102.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 10.729742622375488, |
| "epoch": 0.0023146362163413317, |
| "grad_norm": 2.3125, |
| "learning_rate": 2.2e-05, |
| "loss": 10.0932, |
| "mean_token_accuracy": 0.04235424343496561, |
| "num_tokens": 80094.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 10.723683643341065, |
| "epoch": 0.0025718180181570354, |
| "grad_norm": 2.109375, |
| "learning_rate": 2.4500000000000003e-05, |
| "loss": 9.9838, |
| "mean_token_accuracy": 0.04485577754676342, |
| "num_tokens": 88770.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 10.720681381225585, |
| "epoch": 0.0028289998199727386, |
| "grad_norm": 2.046875, |
| "learning_rate": 2.7e-05, |
| "loss": 9.944, |
| "mean_token_accuracy": 0.043965942412614825, |
| "num_tokens": 97608.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 10.717811107635498, |
| "epoch": 0.0030861816217884423, |
| "grad_norm": 1.875, |
| "learning_rate": 2.95e-05, |
| "loss": 9.8684, |
| "mean_token_accuracy": 0.04390094466507435, |
| "num_tokens": 106204.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 10.713484477996825, |
| "epoch": 0.003343363423604146, |
| "grad_norm": 1.90625, |
| "learning_rate": 3.2e-05, |
| "loss": 9.841, |
| "mean_token_accuracy": 0.04340735748410225, |
| "num_tokens": 115241.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 10.708874225616455, |
| "epoch": 0.003600545225419849, |
| "grad_norm": 1.984375, |
| "learning_rate": 3.4500000000000005e-05, |
| "loss": 9.7416, |
| "mean_token_accuracy": 0.04423734098672867, |
| "num_tokens": 123734.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 10.703791618347168, |
| "epoch": 0.003857727027235553, |
| "grad_norm": 1.8984375, |
| "learning_rate": 3.7e-05, |
| "loss": 9.7488, |
| "mean_token_accuracy": 0.04389217719435692, |
| "num_tokens": 132701.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 10.697965526580811, |
| "epoch": 0.004114908829051256, |
| "grad_norm": 1.921875, |
| "learning_rate": 3.95e-05, |
| "loss": 9.6173, |
| "mean_token_accuracy": 0.04561489634215832, |
| "num_tokens": 141064.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 10.6871018409729, |
| "epoch": 0.00437209063086696, |
| "grad_norm": 1.96875, |
| "learning_rate": 4.2000000000000004e-05, |
| "loss": 9.5084, |
| "mean_token_accuracy": 0.05098861046135426, |
| "num_tokens": 149340.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 10.67187786102295, |
| "epoch": 0.004629272432682663, |
| "grad_norm": 1.828125, |
| "learning_rate": 4.45e-05, |
| "loss": 9.4949, |
| "mean_token_accuracy": 0.05393466129899025, |
| "num_tokens": 158312.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 10.659277820587159, |
| "epoch": 0.004886454234498367, |
| "grad_norm": 1.640625, |
| "learning_rate": 4.7000000000000004e-05, |
| "loss": 9.445, |
| "mean_token_accuracy": 0.0573005523532629, |
| "num_tokens": 167203.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 10.643789291381836, |
| "epoch": 0.005143636036314071, |
| "grad_norm": 1.8046875, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 9.2598, |
| "mean_token_accuracy": 0.0629499789327383, |
| "num_tokens": 175929.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 10.604194068908692, |
| "epoch": 0.0054008178381297735, |
| "grad_norm": 1.7734375, |
| "learning_rate": 5.2e-05, |
| "loss": 9.2354, |
| "mean_token_accuracy": 0.05866244621574879, |
| "num_tokens": 185619.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 10.549863052368163, |
| "epoch": 0.005657999639945477, |
| "grad_norm": 1.6875, |
| "learning_rate": 5.45e-05, |
| "loss": 9.1507, |
| "mean_token_accuracy": 0.05989648550748825, |
| "num_tokens": 195005.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 10.489420223236085, |
| "epoch": 0.005915181441761181, |
| "grad_norm": 1.59375, |
| "learning_rate": 5.7e-05, |
| "loss": 8.9373, |
| "mean_token_accuracy": 0.0647052500396967, |
| "num_tokens": 203392.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 10.426068687438965, |
| "epoch": 0.0061723632435768845, |
| "grad_norm": 1.578125, |
| "learning_rate": 5.9499999999999996e-05, |
| "loss": 8.8217, |
| "mean_token_accuracy": 0.060671578347682956, |
| "num_tokens": 211689.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 10.359361457824708, |
| "epoch": 0.006429545045392588, |
| "grad_norm": 1.4296875, |
| "learning_rate": 6.2e-05, |
| "loss": 8.756, |
| "mean_token_accuracy": 0.06377223357558251, |
| "num_tokens": 220798.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 10.30004062652588, |
| "epoch": 0.006686726847208292, |
| "grad_norm": 1.4453125, |
| "learning_rate": 6.450000000000001e-05, |
| "loss": 8.6622, |
| "mean_token_accuracy": 0.06106479801237583, |
| "num_tokens": 229652.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 10.221406269073487, |
| "epoch": 0.006943908649023995, |
| "grad_norm": 1.453125, |
| "learning_rate": 6.7e-05, |
| "loss": 8.4588, |
| "mean_token_accuracy": 0.06428722217679024, |
| "num_tokens": 238320.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 10.105729293823241, |
| "epoch": 0.007201090450839698, |
| "grad_norm": 1.5, |
| "learning_rate": 6.950000000000001e-05, |
| "loss": 8.431, |
| "mean_token_accuracy": 0.06200639493763447, |
| "num_tokens": 247033.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 9.967057228088379, |
| "epoch": 0.007458272252655402, |
| "grad_norm": 1.203125, |
| "learning_rate": 7.2e-05, |
| "loss": 8.3441, |
| "mean_token_accuracy": 0.06121456101536751, |
| "num_tokens": 256666.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 9.81930513381958, |
| "epoch": 0.007715454054471106, |
| "grad_norm": 1.15625, |
| "learning_rate": 7.45e-05, |
| "loss": 8.1686, |
| "mean_token_accuracy": 0.06682926267385483, |
| "num_tokens": 265689.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 9.67783327102661, |
| "epoch": 0.00797263585628681, |
| "grad_norm": 0.9921875, |
| "learning_rate": 7.7e-05, |
| "loss": 8.1019, |
| "mean_token_accuracy": 0.06226279996335506, |
| "num_tokens": 274276.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 9.495966053009033, |
| "epoch": 0.008229817658102512, |
| "grad_norm": 1.0703125, |
| "learning_rate": 7.950000000000001e-05, |
| "loss": 7.9704, |
| "mean_token_accuracy": 0.06119140088558197, |
| "num_tokens": 283825.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 9.309716987609864, |
| "epoch": 0.008486999459918217, |
| "grad_norm": 0.96484375, |
| "learning_rate": 8.2e-05, |
| "loss": 7.8795, |
| "mean_token_accuracy": 0.06309534795582294, |
| "num_tokens": 292223.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 9.042353534698487, |
| "epoch": 0.00874418126173392, |
| "grad_norm": 0.8046875, |
| "learning_rate": 8.450000000000001e-05, |
| "loss": 7.8385, |
| "mean_token_accuracy": 0.06506023034453393, |
| "num_tokens": 300889.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 8.90816011428833, |
| "epoch": 0.009001363063549624, |
| "grad_norm": 1.0078125, |
| "learning_rate": 8.7e-05, |
| "loss": 7.7842, |
| "mean_token_accuracy": 0.0640747856348753, |
| "num_tokens": 309729.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 8.687435150146484, |
| "epoch": 0.009258544865365327, |
| "grad_norm": 0.8125, |
| "learning_rate": 8.95e-05, |
| "loss": 7.7211, |
| "mean_token_accuracy": 0.060701503232121465, |
| "num_tokens": 318611.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 8.534039783477784, |
| "epoch": 0.00951572666718103, |
| "grad_norm": 0.8828125, |
| "learning_rate": 9.2e-05, |
| "loss": 7.6722, |
| "mean_token_accuracy": 0.06427375338971615, |
| "num_tokens": 326948.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 8.478750228881836, |
| "epoch": 0.009772908468996734, |
| "grad_norm": 0.81640625, |
| "learning_rate": 9.45e-05, |
| "loss": 7.6806, |
| "mean_token_accuracy": 0.06457847729325294, |
| "num_tokens": 336249.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 8.388401317596436, |
| "epoch": 0.010030090270812437, |
| "grad_norm": 0.7265625, |
| "learning_rate": 9.7e-05, |
| "loss": 7.6163, |
| "mean_token_accuracy": 0.06882799975574017, |
| "num_tokens": 345182.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 8.318638229370118, |
| "epoch": 0.010287272072628141, |
| "grad_norm": 0.79296875, |
| "learning_rate": 9.95e-05, |
| "loss": 7.632, |
| "mean_token_accuracy": 0.06467234715819359, |
| "num_tokens": 353642.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 8.238949489593505, |
| "epoch": 0.010544453874443844, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.000102, |
| "loss": 7.6098, |
| "mean_token_accuracy": 0.06644487231969834, |
| "num_tokens": 362269.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 8.207266712188721, |
| "epoch": 0.010801635676259547, |
| "grad_norm": 0.92578125, |
| "learning_rate": 0.00010449999999999999, |
| "loss": 7.5609, |
| "mean_token_accuracy": 0.06878665201365948, |
| "num_tokens": 371024.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 8.225072002410888, |
| "epoch": 0.011058817478075252, |
| "grad_norm": 0.8671875, |
| "learning_rate": 0.000107, |
| "loss": 7.5979, |
| "mean_token_accuracy": 0.06695215404033661, |
| "num_tokens": 379876.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 8.130556297302245, |
| "epoch": 0.011315999279890954, |
| "grad_norm": 0.8671875, |
| "learning_rate": 0.0001095, |
| "loss": 7.6058, |
| "mean_token_accuracy": 0.06531222015619279, |
| "num_tokens": 388907.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 8.187319278717041, |
| "epoch": 0.011573181081706659, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.000112, |
| "loss": 7.5483, |
| "mean_token_accuracy": 0.0684064768254757, |
| "num_tokens": 397629.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 8.132099628448486, |
| "epoch": 0.011830362883522362, |
| "grad_norm": 0.87890625, |
| "learning_rate": 0.0001145, |
| "loss": 7.5356, |
| "mean_token_accuracy": 0.06274137385189534, |
| "num_tokens": 406919.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 8.15430727005005, |
| "epoch": 0.012087544685338066, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.00011700000000000001, |
| "loss": 7.5962, |
| "mean_token_accuracy": 0.068911187723279, |
| "num_tokens": 415471.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 8.099409580230713, |
| "epoch": 0.012344726487153769, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00011949999999999999, |
| "loss": 7.5735, |
| "mean_token_accuracy": 0.0665768850594759, |
| "num_tokens": 424532.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 8.095283269882202, |
| "epoch": 0.012601908288969472, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.000122, |
| "loss": 7.5317, |
| "mean_token_accuracy": 0.06533802710473538, |
| "num_tokens": 433457.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 8.048843669891358, |
| "epoch": 0.012859090090785176, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.0001245, |
| "loss": 7.5112, |
| "mean_token_accuracy": 0.06810796111822129, |
| "num_tokens": 442765.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 8.033838605880737, |
| "epoch": 0.01311627189260088, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.000127, |
| "loss": 7.5382, |
| "mean_token_accuracy": 0.06802100911736489, |
| "num_tokens": 451853.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 8.045299959182739, |
| "epoch": 0.013373453694416584, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0001295, |
| "loss": 7.4256, |
| "mean_token_accuracy": 0.07066994272172451, |
| "num_tokens": 460210.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 7.9866725444793705, |
| "epoch": 0.013630635496232286, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.000132, |
| "loss": 7.4002, |
| "mean_token_accuracy": 0.08060714676976204, |
| "num_tokens": 468673.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 8.092905473709106, |
| "epoch": 0.01388781729804799, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00013450000000000002, |
| "loss": 7.4123, |
| "mean_token_accuracy": 0.07691804766654968, |
| "num_tokens": 477194.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 7.961445760726929, |
| "epoch": 0.014144999099863694, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00013700000000000002, |
| "loss": 7.381, |
| "mean_token_accuracy": 0.07125308774411679, |
| "num_tokens": 486869.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 7.966795444488525, |
| "epoch": 0.014402180901679397, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0001395, |
| "loss": 7.3379, |
| "mean_token_accuracy": 0.07665478959679603, |
| "num_tokens": 495731.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 7.958342027664185, |
| "epoch": 0.014659362703495101, |
| "grad_norm": 0.94140625, |
| "learning_rate": 0.00014199999999999998, |
| "loss": 7.3933, |
| "mean_token_accuracy": 0.07646878808736801, |
| "num_tokens": 504071.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 7.9638275623321535, |
| "epoch": 0.014916544505310804, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0001445, |
| "loss": 7.4247, |
| "mean_token_accuracy": 0.07719123288989067, |
| "num_tokens": 512927.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 7.965741872787476, |
| "epoch": 0.015173726307126508, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.000147, |
| "loss": 7.2639, |
| "mean_token_accuracy": 0.07586801275610924, |
| "num_tokens": 521405.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 7.823179912567139, |
| "epoch": 0.015430908108942211, |
| "grad_norm": 0.8984375, |
| "learning_rate": 0.0001495, |
| "loss": 7.3976, |
| "mean_token_accuracy": 0.07964370101690292, |
| "num_tokens": 530473.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 7.85285005569458, |
| "epoch": 0.015688089910757916, |
| "grad_norm": 0.90625, |
| "learning_rate": 0.000152, |
| "loss": 7.3457, |
| "mean_token_accuracy": 0.07974019274115562, |
| "num_tokens": 540058.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 7.974370861053467, |
| "epoch": 0.01594527171257362, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.00015450000000000001, |
| "loss": 7.407, |
| "mean_token_accuracy": 0.07686455249786377, |
| "num_tokens": 548492.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 7.900070238113403, |
| "epoch": 0.01620245351438932, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.000157, |
| "loss": 7.313, |
| "mean_token_accuracy": 0.07973849661648273, |
| "num_tokens": 556788.0, |
| "step": 315 |
| }, |
| { |
| "entropy": 7.812545537948608, |
| "epoch": 0.016459635316205024, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0001595, |
| "loss": 7.2565, |
| "mean_token_accuracy": 0.07418388202786445, |
| "num_tokens": 566122.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 7.9200437545776365, |
| "epoch": 0.01671681711802073, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000162, |
| "loss": 7.2952, |
| "mean_token_accuracy": 0.07806292176246643, |
| "num_tokens": 575574.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 7.8590294361114506, |
| "epoch": 0.016973998919836433, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.00016450000000000001, |
| "loss": 7.3445, |
| "mean_token_accuracy": 0.07793254256248475, |
| "num_tokens": 584552.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 7.8465721130371096, |
| "epoch": 0.017231180721652136, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00016700000000000002, |
| "loss": 7.3252, |
| "mean_token_accuracy": 0.07768969610333443, |
| "num_tokens": 593572.0, |
| "step": 335 |
| }, |
| { |
| "entropy": 7.80656795501709, |
| "epoch": 0.01748836252346784, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00016950000000000003, |
| "loss": 7.2293, |
| "mean_token_accuracy": 0.07511881664395333, |
| "num_tokens": 603205.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 7.84014139175415, |
| "epoch": 0.01774554432528354, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00017199999999999998, |
| "loss": 7.2884, |
| "mean_token_accuracy": 0.07499681413173676, |
| "num_tokens": 612268.0, |
| "step": 345 |
| }, |
| { |
| "entropy": 7.784244871139526, |
| "epoch": 0.018002726127099248, |
| "grad_norm": 0.93359375, |
| "learning_rate": 0.00017449999999999999, |
| "loss": 7.2643, |
| "mean_token_accuracy": 0.07596472017467022, |
| "num_tokens": 621213.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 7.803834342956543, |
| "epoch": 0.01825990792891495, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.000177, |
| "loss": 7.3069, |
| "mean_token_accuracy": 0.08319237679243088, |
| "num_tokens": 630231.0, |
| "step": 355 |
| }, |
| { |
| "entropy": 7.815704870223999, |
| "epoch": 0.018517089730730654, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0001795, |
| "loss": 7.2149, |
| "mean_token_accuracy": 0.0825786791741848, |
| "num_tokens": 639217.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 7.837387752532959, |
| "epoch": 0.018774271532546356, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000182, |
| "loss": 7.2476, |
| "mean_token_accuracy": 0.07730407565832138, |
| "num_tokens": 648233.0, |
| "step": 365 |
| }, |
| { |
| "entropy": 7.710758781433105, |
| "epoch": 0.01903145333436206, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.0001845, |
| "loss": 7.2316, |
| "mean_token_accuracy": 0.08014441356062889, |
| "num_tokens": 657817.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 7.747053003311157, |
| "epoch": 0.019288635136177765, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.000187, |
| "loss": 7.1701, |
| "mean_token_accuracy": 0.08062060177326202, |
| "num_tokens": 666335.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 7.7258199691772464, |
| "epoch": 0.019545816937993468, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0001895, |
| "loss": 7.0682, |
| "mean_token_accuracy": 0.08676183447241784, |
| "num_tokens": 674766.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 7.720611429214477, |
| "epoch": 0.01980299873980917, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.000192, |
| "loss": 7.1426, |
| "mean_token_accuracy": 0.0820883870124817, |
| "num_tokens": 683125.0, |
| "step": 385 |
| }, |
| { |
| "entropy": 7.673658752441407, |
| "epoch": 0.020060180541624874, |
| "grad_norm": 0.9453125, |
| "learning_rate": 0.0001945, |
| "loss": 7.1867, |
| "mean_token_accuracy": 0.08598564639687538, |
| "num_tokens": 691561.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 7.715641736984253, |
| "epoch": 0.020317362343440577, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00019700000000000002, |
| "loss": 7.1201, |
| "mean_token_accuracy": 0.08909595757722855, |
| "num_tokens": 701015.0, |
| "step": 395 |
| }, |
| { |
| "entropy": 7.7091387748718265, |
| "epoch": 0.020574544145256283, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.00019950000000000002, |
| "loss": 7.1455, |
| "mean_token_accuracy": 0.0916555643081665, |
| "num_tokens": 709940.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 7.6161031246185305, |
| "epoch": 0.020831725947071986, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.000202, |
| "loss": 7.0992, |
| "mean_token_accuracy": 0.08667092099785804, |
| "num_tokens": 719304.0, |
| "step": 405 |
| }, |
| { |
| "entropy": 7.635785293579102, |
| "epoch": 0.02108890774888769, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00020449999999999998, |
| "loss": 7.1057, |
| "mean_token_accuracy": 0.08669973537325859, |
| "num_tokens": 728489.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 7.667731189727784, |
| "epoch": 0.02134608955070339, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000207, |
| "loss": 7.1789, |
| "mean_token_accuracy": 0.08465257212519646, |
| "num_tokens": 737769.0, |
| "step": 415 |
| }, |
| { |
| "entropy": 7.64384446144104, |
| "epoch": 0.021603271352519094, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0002095, |
| "loss": 7.0319, |
| "mean_token_accuracy": 0.08635761365294456, |
| "num_tokens": 746540.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 7.658045482635498, |
| "epoch": 0.0218604531543348, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000212, |
| "loss": 7.216, |
| "mean_token_accuracy": 0.08415560573339462, |
| "num_tokens": 756118.0, |
| "step": 425 |
| }, |
| { |
| "entropy": 7.623081970214844, |
| "epoch": 0.022117634956150503, |
| "grad_norm": 1.3203125, |
| "learning_rate": 0.0002145, |
| "loss": 7.0563, |
| "mean_token_accuracy": 0.09152830839157104, |
| "num_tokens": 764091.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 7.5571778297424315, |
| "epoch": 0.022374816757966206, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00021700000000000002, |
| "loss": 7.0872, |
| "mean_token_accuracy": 0.08672986775636674, |
| "num_tokens": 773220.0, |
| "step": 435 |
| }, |
| { |
| "entropy": 7.645488929748535, |
| "epoch": 0.02263199855978191, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0002195, |
| "loss": 7.1345, |
| "mean_token_accuracy": 0.08709268644452095, |
| "num_tokens": 781937.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 7.57753210067749, |
| "epoch": 0.022889180361597615, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000222, |
| "loss": 7.0728, |
| "mean_token_accuracy": 0.08992104157805443, |
| "num_tokens": 791685.0, |
| "step": 445 |
| }, |
| { |
| "entropy": 7.5337488651275635, |
| "epoch": 0.023146362163413318, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0002245, |
| "loss": 6.9439, |
| "mean_token_accuracy": 0.08900289312005043, |
| "num_tokens": 800759.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 7.569718551635742, |
| "epoch": 0.02340354396522902, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00022700000000000002, |
| "loss": 7.0617, |
| "mean_token_accuracy": 0.08903328478336334, |
| "num_tokens": 809508.0, |
| "step": 455 |
| }, |
| { |
| "entropy": 7.4335291385650635, |
| "epoch": 0.023660725767044723, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.00022950000000000002, |
| "loss": 6.9777, |
| "mean_token_accuracy": 0.08975348770618438, |
| "num_tokens": 819262.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 7.5286821842193605, |
| "epoch": 0.023917907568860426, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.00023200000000000003, |
| "loss": 7.0061, |
| "mean_token_accuracy": 0.09333336725831032, |
| "num_tokens": 827902.0, |
| "step": 465 |
| }, |
| { |
| "entropy": 7.5438226699829105, |
| "epoch": 0.024175089370676132, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00023449999999999998, |
| "loss": 7.071, |
| "mean_token_accuracy": 0.08738465905189514, |
| "num_tokens": 836678.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 7.578305292129516, |
| "epoch": 0.024432271172491835, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000237, |
| "loss": 7.0481, |
| "mean_token_accuracy": 0.08780269175767899, |
| "num_tokens": 845604.0, |
| "step": 475 |
| }, |
| { |
| "entropy": 7.495909070968628, |
| "epoch": 0.024689452974307538, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0002395, |
| "loss": 6.9237, |
| "mean_token_accuracy": 0.09766526669263839, |
| "num_tokens": 854530.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 7.472972011566162, |
| "epoch": 0.02494663477612324, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.000242, |
| "loss": 6.9801, |
| "mean_token_accuracy": 0.08929606899619102, |
| "num_tokens": 863038.0, |
| "step": 485 |
| }, |
| { |
| "entropy": 7.4176201820373535, |
| "epoch": 0.025203816577938944, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0002445, |
| "loss": 6.9488, |
| "mean_token_accuracy": 0.09348267316818237, |
| "num_tokens": 871691.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 7.523787260055542, |
| "epoch": 0.02546099837975465, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000247, |
| "loss": 6.9412, |
| "mean_token_accuracy": 0.09506363123655319, |
| "num_tokens": 881026.0, |
| "step": 495 |
| }, |
| { |
| "entropy": 7.421153450012207, |
| "epoch": 0.025718180181570353, |
| "grad_norm": 1.28125, |
| "learning_rate": 0.0002495, |
| "loss": 6.9932, |
| "mean_token_accuracy": 0.0955754928290844, |
| "num_tokens": 889829.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 7.390109062194824, |
| "epoch": 0.025975361983386056, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.000252, |
| "loss": 7.0112, |
| "mean_token_accuracy": 0.0914897546172142, |
| "num_tokens": 898992.0, |
| "step": 505 |
| }, |
| { |
| "entropy": 7.555384731292724, |
| "epoch": 0.02623254378520176, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0002545, |
| "loss": 7.0507, |
| "mean_token_accuracy": 0.08820229396224022, |
| "num_tokens": 908237.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 7.433199691772461, |
| "epoch": 0.02648972558701746, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000257, |
| "loss": 6.8716, |
| "mean_token_accuracy": 0.09959734976291656, |
| "num_tokens": 916715.0, |
| "step": 515 |
| }, |
| { |
| "entropy": 7.360012674331665, |
| "epoch": 0.026746907388833167, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0002595, |
| "loss": 6.9746, |
| "mean_token_accuracy": 0.0938393734395504, |
| "num_tokens": 925834.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 7.439189624786377, |
| "epoch": 0.02700408919064887, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.000262, |
| "loss": 6.9216, |
| "mean_token_accuracy": 0.09481378644704819, |
| "num_tokens": 935725.0, |
| "step": 525 |
| }, |
| { |
| "entropy": 7.516362428665161, |
| "epoch": 0.027261270992464573, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00026450000000000003, |
| "loss": 7.0258, |
| "mean_token_accuracy": 0.09422887191176414, |
| "num_tokens": 944788.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 7.29243836402893, |
| "epoch": 0.027518452794280276, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00026700000000000004, |
| "loss": 6.8317, |
| "mean_token_accuracy": 0.09764747545123101, |
| "num_tokens": 953561.0, |
| "step": 535 |
| }, |
| { |
| "entropy": 7.504419994354248, |
| "epoch": 0.02777563459609598, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00026950000000000005, |
| "loss": 6.9259, |
| "mean_token_accuracy": 0.09662783890962601, |
| "num_tokens": 961942.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 7.3940901279449465, |
| "epoch": 0.028032816397911685, |
| "grad_norm": 1.34375, |
| "learning_rate": 0.00027200000000000005, |
| "loss": 6.8816, |
| "mean_token_accuracy": 0.09403559938073158, |
| "num_tokens": 970699.0, |
| "step": 545 |
| }, |
| { |
| "entropy": 7.347795295715332, |
| "epoch": 0.028289998199727388, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0002745, |
| "loss": 6.9946, |
| "mean_token_accuracy": 0.09083672165870667, |
| "num_tokens": 980352.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 7.459839010238648, |
| "epoch": 0.02854718000154309, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.000277, |
| "loss": 6.8925, |
| "mean_token_accuracy": 0.09576373025774956, |
| "num_tokens": 988771.0, |
| "step": 555 |
| }, |
| { |
| "entropy": 7.296186876296997, |
| "epoch": 0.028804361803358793, |
| "grad_norm": 1.2734375, |
| "learning_rate": 0.0002795, |
| "loss": 6.7979, |
| "mean_token_accuracy": 0.09578228294849396, |
| "num_tokens": 997564.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 7.341630935668945, |
| "epoch": 0.0290615436051745, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00028199999999999997, |
| "loss": 6.8745, |
| "mean_token_accuracy": 0.09284131526947022, |
| "num_tokens": 1005945.0, |
| "step": 565 |
| }, |
| { |
| "entropy": 7.347255086898803, |
| "epoch": 0.029318725406990202, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0002845, |
| "loss": 6.9394, |
| "mean_token_accuracy": 0.09283768609166146, |
| "num_tokens": 1015012.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 7.4236492156982425, |
| "epoch": 0.029575907208805905, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000287, |
| "loss": 6.9536, |
| "mean_token_accuracy": 0.09391803517937661, |
| "num_tokens": 1024240.0, |
| "step": 575 |
| }, |
| { |
| "entropy": 7.367508506774902, |
| "epoch": 0.029833089010621608, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.0002895, |
| "loss": 6.8857, |
| "mean_token_accuracy": 0.09755372777581214, |
| "num_tokens": 1033277.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 7.279513311386109, |
| "epoch": 0.03009027081243731, |
| "grad_norm": 1.34375, |
| "learning_rate": 0.000292, |
| "loss": 6.8268, |
| "mean_token_accuracy": 0.09293166324496269, |
| "num_tokens": 1042312.0, |
| "step": 585 |
| }, |
| { |
| "entropy": 7.353345108032227, |
| "epoch": 0.030347452614253017, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.0002945, |
| "loss": 6.8653, |
| "mean_token_accuracy": 0.0949218288064003, |
| "num_tokens": 1052756.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 7.368993330001831, |
| "epoch": 0.03060463441606872, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.000297, |
| "loss": 6.8974, |
| "mean_token_accuracy": 0.10047846585512162, |
| "num_tokens": 1061563.0, |
| "step": 595 |
| }, |
| { |
| "entropy": 7.286983442306519, |
| "epoch": 0.030861816217884423, |
| "grad_norm": 1.4140625, |
| "learning_rate": 0.0002995, |
| "loss": 6.7907, |
| "mean_token_accuracy": 0.10389479920268059, |
| "num_tokens": 1070177.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 7.252815437316895, |
| "epoch": 0.031118998019700125, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.000302, |
| "loss": 6.8292, |
| "mean_token_accuracy": 0.09795110002160072, |
| "num_tokens": 1079662.0, |
| "step": 605 |
| }, |
| { |
| "entropy": 7.261862182617188, |
| "epoch": 0.03137617982151583, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0003045, |
| "loss": 6.7916, |
| "mean_token_accuracy": 0.0980616994202137, |
| "num_tokens": 1088719.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 7.310345602035523, |
| "epoch": 0.03163336162333153, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000307, |
| "loss": 6.7727, |
| "mean_token_accuracy": 0.10127385258674622, |
| "num_tokens": 1096663.0, |
| "step": 615 |
| }, |
| { |
| "entropy": 7.34635648727417, |
| "epoch": 0.03189054342514724, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0003095, |
| "loss": 6.8751, |
| "mean_token_accuracy": 0.0975107342004776, |
| "num_tokens": 1105484.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 7.2787559032440186, |
| "epoch": 0.032147725226962943, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.000312, |
| "loss": 6.8409, |
| "mean_token_accuracy": 0.096168252825737, |
| "num_tokens": 1114781.0, |
| "step": 625 |
| }, |
| { |
| "entropy": 7.194593715667724, |
| "epoch": 0.03240490702877864, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0003145, |
| "loss": 6.8495, |
| "mean_token_accuracy": 0.1023260697722435, |
| "num_tokens": 1124075.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 7.284073257446289, |
| "epoch": 0.03266208883059435, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.000317, |
| "loss": 6.7928, |
| "mean_token_accuracy": 0.09392334222793579, |
| "num_tokens": 1132863.0, |
| "step": 635 |
| }, |
| { |
| "entropy": 7.23821120262146, |
| "epoch": 0.03291927063241005, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0003195, |
| "loss": 6.8477, |
| "mean_token_accuracy": 0.10305669158697128, |
| "num_tokens": 1141324.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 7.2563272476196286, |
| "epoch": 0.033176452434225755, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.000322, |
| "loss": 6.716, |
| "mean_token_accuracy": 0.10566487908363342, |
| "num_tokens": 1149406.0, |
| "step": 645 |
| }, |
| { |
| "entropy": 7.335630702972412, |
| "epoch": 0.03343363423604146, |
| "grad_norm": 1.3359375, |
| "learning_rate": 0.00032450000000000003, |
| "loss": 6.8656, |
| "mean_token_accuracy": 0.09870733916759492, |
| "num_tokens": 1158488.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 7.255077314376831, |
| "epoch": 0.03369081603785716, |
| "grad_norm": 1.3203125, |
| "learning_rate": 0.00032700000000000003, |
| "loss": 6.8075, |
| "mean_token_accuracy": 0.10482278540730476, |
| "num_tokens": 1166756.0, |
| "step": 655 |
| }, |
| { |
| "entropy": 7.2207207679748535, |
| "epoch": 0.03394799783967287, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00032950000000000004, |
| "loss": 6.7814, |
| "mean_token_accuracy": 0.10137899518013001, |
| "num_tokens": 1175930.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 7.146165227890014, |
| "epoch": 0.034205179641488566, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00033200000000000005, |
| "loss": 6.7864, |
| "mean_token_accuracy": 0.1040356308221817, |
| "num_tokens": 1184348.0, |
| "step": 665 |
| }, |
| { |
| "entropy": 7.224062728881836, |
| "epoch": 0.03446236144330427, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.00033450000000000005, |
| "loss": 6.7721, |
| "mean_token_accuracy": 0.10236084014177323, |
| "num_tokens": 1192800.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 7.279936122894287, |
| "epoch": 0.03471954324511998, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000337, |
| "loss": 6.8795, |
| "mean_token_accuracy": 0.09708840399980545, |
| "num_tokens": 1201446.0, |
| "step": 675 |
| }, |
| { |
| "entropy": 7.065876436233521, |
| "epoch": 0.03497672504693568, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.0003395, |
| "loss": 6.6507, |
| "mean_token_accuracy": 0.1062047965824604, |
| "num_tokens": 1210088.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 7.077348375320435, |
| "epoch": 0.035233906848751384, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.000342, |
| "loss": 6.5917, |
| "mean_token_accuracy": 0.11215948089957237, |
| "num_tokens": 1219425.0, |
| "step": 685 |
| }, |
| { |
| "entropy": 7.214649200439453, |
| "epoch": 0.03549108865056708, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00034449999999999997, |
| "loss": 6.7802, |
| "mean_token_accuracy": 0.09808368533849716, |
| "num_tokens": 1228332.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 7.219751453399658, |
| "epoch": 0.03574827045238279, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.000347, |
| "loss": 6.8329, |
| "mean_token_accuracy": 0.09870714694261551, |
| "num_tokens": 1237953.0, |
| "step": 695 |
| }, |
| { |
| "entropy": 7.24316897392273, |
| "epoch": 0.036005452254198496, |
| "grad_norm": 1.265625, |
| "learning_rate": 0.0003495, |
| "loss": 6.8479, |
| "mean_token_accuracy": 0.09783646762371064, |
| "num_tokens": 1247387.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 7.2066491603851315, |
| "epoch": 0.036262634056014195, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.000352, |
| "loss": 6.7471, |
| "mean_token_accuracy": 0.10154265984892845, |
| "num_tokens": 1256215.0, |
| "step": 705 |
| }, |
| { |
| "entropy": 7.0408368587493895, |
| "epoch": 0.0365198158578299, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.0003545, |
| "loss": 6.6315, |
| "mean_token_accuracy": 0.10381938368082047, |
| "num_tokens": 1265963.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 7.164453172683716, |
| "epoch": 0.0367769976596456, |
| "grad_norm": 1.28125, |
| "learning_rate": 0.000357, |
| "loss": 6.6903, |
| "mean_token_accuracy": 0.1119053155183792, |
| "num_tokens": 1275024.0, |
| "step": 715 |
| }, |
| { |
| "entropy": 7.111461877822876, |
| "epoch": 0.03703417946146131, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0003595, |
| "loss": 6.7586, |
| "mean_token_accuracy": 0.10169535055756569, |
| "num_tokens": 1283981.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 7.1354100704193115, |
| "epoch": 0.03729136126327701, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000362, |
| "loss": 6.62, |
| "mean_token_accuracy": 0.10666845366358757, |
| "num_tokens": 1292834.0, |
| "step": 725 |
| }, |
| { |
| "entropy": 7.122345590591431, |
| "epoch": 0.03754854306509271, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.0003645, |
| "loss": 6.7978, |
| "mean_token_accuracy": 0.1032055139541626, |
| "num_tokens": 1301429.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 7.0510656356811525, |
| "epoch": 0.03780572486690842, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000367, |
| "loss": 6.7053, |
| "mean_token_accuracy": 0.10353485718369485, |
| "num_tokens": 1310088.0, |
| "step": 735 |
| }, |
| { |
| "entropy": 7.182754850387573, |
| "epoch": 0.03806290666872412, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0003695, |
| "loss": 6.7723, |
| "mean_token_accuracy": 0.10199789181351662, |
| "num_tokens": 1318249.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 7.0828611850738525, |
| "epoch": 0.038320088470539825, |
| "grad_norm": 1.3046875, |
| "learning_rate": 0.000372, |
| "loss": 6.6795, |
| "mean_token_accuracy": 0.10390995517373085, |
| "num_tokens": 1327075.0, |
| "step": 745 |
| }, |
| { |
| "entropy": 7.114889192581177, |
| "epoch": 0.03857727027235553, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0003745, |
| "loss": 6.7128, |
| "mean_token_accuracy": 0.1041706345975399, |
| "num_tokens": 1335995.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 7.040337038040161, |
| "epoch": 0.03883445207417123, |
| "grad_norm": 1.28125, |
| "learning_rate": 0.000377, |
| "loss": 6.6914, |
| "mean_token_accuracy": 0.10317371264100075, |
| "num_tokens": 1344789.0, |
| "step": 755 |
| }, |
| { |
| "entropy": 7.120604038238525, |
| "epoch": 0.039091633875986936, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.0003795, |
| "loss": 6.6955, |
| "mean_token_accuracy": 0.10629725456237793, |
| "num_tokens": 1352940.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 7.052408075332641, |
| "epoch": 0.039348815677802636, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.000382, |
| "loss": 6.637, |
| "mean_token_accuracy": 0.10945691764354706, |
| "num_tokens": 1361803.0, |
| "step": 765 |
| }, |
| { |
| "entropy": 7.069132375717163, |
| "epoch": 0.03960599747961834, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0003845, |
| "loss": 6.7294, |
| "mean_token_accuracy": 0.10019565001130104, |
| "num_tokens": 1371647.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 7.164604377746582, |
| "epoch": 0.03986317928143405, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.00038700000000000003, |
| "loss": 6.7523, |
| "mean_token_accuracy": 0.10618292987346649, |
| "num_tokens": 1380447.0, |
| "step": 775 |
| }, |
| { |
| "entropy": 7.114570999145508, |
| "epoch": 0.04012036108324975, |
| "grad_norm": 1.453125, |
| "learning_rate": 0.00038950000000000003, |
| "loss": 6.7284, |
| "mean_token_accuracy": 0.09737010598182679, |
| "num_tokens": 1388902.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 7.0223623752594, |
| "epoch": 0.040377542885065454, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00039200000000000004, |
| "loss": 6.5808, |
| "mean_token_accuracy": 0.1079009048640728, |
| "num_tokens": 1398178.0, |
| "step": 785 |
| }, |
| { |
| "entropy": 7.056776905059815, |
| "epoch": 0.04063472468688115, |
| "grad_norm": 1.2890625, |
| "learning_rate": 0.00039450000000000005, |
| "loss": 6.6511, |
| "mean_token_accuracy": 0.11126778572797776, |
| "num_tokens": 1406042.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 7.084379482269287, |
| "epoch": 0.04089190648869686, |
| "grad_norm": 1.2890625, |
| "learning_rate": 0.00039700000000000005, |
| "loss": 6.6815, |
| "mean_token_accuracy": 0.10524625033140182, |
| "num_tokens": 1415562.0, |
| "step": 795 |
| }, |
| { |
| "entropy": 7.051506662368775, |
| "epoch": 0.041149088290512566, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0003995, |
| "loss": 6.6008, |
| "mean_token_accuracy": 0.10510810911655426, |
| "num_tokens": 1424782.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 6.966880178451538, |
| "epoch": 0.041406270092328265, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000402, |
| "loss": 6.6177, |
| "mean_token_accuracy": 0.10489397794008255, |
| "num_tokens": 1433737.0, |
| "step": 805 |
| }, |
| { |
| "entropy": 7.0082066535949705, |
| "epoch": 0.04166345189414397, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0004045, |
| "loss": 6.6886, |
| "mean_token_accuracy": 0.10373986288905143, |
| "num_tokens": 1442948.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 7.030193662643432, |
| "epoch": 0.04192063369595967, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00040699999999999997, |
| "loss": 6.617, |
| "mean_token_accuracy": 0.1067310206592083, |
| "num_tokens": 1452333.0, |
| "step": 815 |
| }, |
| { |
| "entropy": 6.962583208084107, |
| "epoch": 0.04217781549777538, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004095, |
| "loss": 6.6201, |
| "mean_token_accuracy": 0.10676174983382225, |
| "num_tokens": 1461160.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 6.962631416320801, |
| "epoch": 0.04243499729959108, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000412, |
| "loss": 6.6449, |
| "mean_token_accuracy": 0.10844494923949241, |
| "num_tokens": 1470248.0, |
| "step": 825 |
| }, |
| { |
| "entropy": 7.0632740497589115, |
| "epoch": 0.04269217910140678, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004145, |
| "loss": 6.6382, |
| "mean_token_accuracy": 0.11155002191662788, |
| "num_tokens": 1478992.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 7.077846574783325, |
| "epoch": 0.04294936090322249, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.000417, |
| "loss": 6.6672, |
| "mean_token_accuracy": 0.1010983519256115, |
| "num_tokens": 1488341.0, |
| "step": 835 |
| }, |
| { |
| "entropy": 6.8585468292236325, |
| "epoch": 0.04320654270503819, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.0004195, |
| "loss": 6.5807, |
| "mean_token_accuracy": 0.10849210470914841, |
| "num_tokens": 1496986.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 7.0004956245422365, |
| "epoch": 0.043463724506853894, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000422, |
| "loss": 6.5236, |
| "mean_token_accuracy": 0.11627273112535477, |
| "num_tokens": 1505455.0, |
| "step": 845 |
| }, |
| { |
| "entropy": 7.062360429763794, |
| "epoch": 0.0437209063086696, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004245, |
| "loss": 6.6677, |
| "mean_token_accuracy": 0.11094246879220009, |
| "num_tokens": 1515240.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 6.843272590637207, |
| "epoch": 0.0439780881104853, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000427, |
| "loss": 6.4627, |
| "mean_token_accuracy": 0.11083339005708695, |
| "num_tokens": 1523234.0, |
| "step": 855 |
| }, |
| { |
| "entropy": 6.870317792892456, |
| "epoch": 0.044235269912301006, |
| "grad_norm": 1.25, |
| "learning_rate": 0.0004295, |
| "loss": 6.5185, |
| "mean_token_accuracy": 0.10689858049154281, |
| "num_tokens": 1531836.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 6.954329633712769, |
| "epoch": 0.04449245171411671, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.000432, |
| "loss": 6.5619, |
| "mean_token_accuracy": 0.1082220919430256, |
| "num_tokens": 1540611.0, |
| "step": 865 |
| }, |
| { |
| "entropy": 6.9597697257995605, |
| "epoch": 0.04474963351593241, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0004345, |
| "loss": 6.5767, |
| "mean_token_accuracy": 0.10847441479563713, |
| "num_tokens": 1549652.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 6.933281469345093, |
| "epoch": 0.04500681531774812, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.000437, |
| "loss": 6.654, |
| "mean_token_accuracy": 0.10323531776666642, |
| "num_tokens": 1559040.0, |
| "step": 875 |
| }, |
| { |
| "entropy": 6.976513767242432, |
| "epoch": 0.04526399711956382, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004395, |
| "loss": 6.5506, |
| "mean_token_accuracy": 0.10878390446305275, |
| "num_tokens": 1567745.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 6.939139747619629, |
| "epoch": 0.045521178921379524, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.000442, |
| "loss": 6.5311, |
| "mean_token_accuracy": 0.11226821094751357, |
| "num_tokens": 1576077.0, |
| "step": 885 |
| }, |
| { |
| "entropy": 6.885157585144043, |
| "epoch": 0.04577836072319523, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.0004445, |
| "loss": 6.597, |
| "mean_token_accuracy": 0.10303749218583107, |
| "num_tokens": 1584641.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 6.9989728927612305, |
| "epoch": 0.04603554252501093, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000447, |
| "loss": 6.5356, |
| "mean_token_accuracy": 0.10896688029170036, |
| "num_tokens": 1594131.0, |
| "step": 895 |
| }, |
| { |
| "entropy": 6.9140125751495365, |
| "epoch": 0.046292724326826636, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00044950000000000003, |
| "loss": 6.5217, |
| "mean_token_accuracy": 0.10893905013799668, |
| "num_tokens": 1603099.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 6.941550970077515, |
| "epoch": 0.046549906128642335, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00045200000000000004, |
| "loss": 6.5503, |
| "mean_token_accuracy": 0.11116070300340652, |
| "num_tokens": 1611453.0, |
| "step": 905 |
| }, |
| { |
| "entropy": 6.77474455833435, |
| "epoch": 0.04680708793045804, |
| "grad_norm": 1.25, |
| "learning_rate": 0.00045450000000000004, |
| "loss": 6.5397, |
| "mean_token_accuracy": 0.10877310186624527, |
| "num_tokens": 1619577.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 7.0068763256072994, |
| "epoch": 0.04706426973227375, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00045700000000000005, |
| "loss": 6.6618, |
| "mean_token_accuracy": 0.10706020519137383, |
| "num_tokens": 1629026.0, |
| "step": 915 |
| }, |
| { |
| "entropy": 6.97544412612915, |
| "epoch": 0.04732145153408945, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00045950000000000006, |
| "loss": 6.5855, |
| "mean_token_accuracy": 0.11112762615084648, |
| "num_tokens": 1638556.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 6.83156042098999, |
| "epoch": 0.04757863333590515, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.000462, |
| "loss": 6.4674, |
| "mean_token_accuracy": 0.11065400391817093, |
| "num_tokens": 1647756.0, |
| "step": 925 |
| }, |
| { |
| "entropy": 6.925829887390137, |
| "epoch": 0.04783581513772085, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004645, |
| "loss": 6.5459, |
| "mean_token_accuracy": 0.10694767236709594, |
| "num_tokens": 1656614.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 6.851103353500366, |
| "epoch": 0.04809299693953656, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.000467, |
| "loss": 6.5566, |
| "mean_token_accuracy": 0.11177869439125061, |
| "num_tokens": 1666213.0, |
| "step": 935 |
| }, |
| { |
| "entropy": 6.823415803909302, |
| "epoch": 0.048350178741352265, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004695, |
| "loss": 6.5108, |
| "mean_token_accuracy": 0.11019086241722106, |
| "num_tokens": 1675435.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 6.8377485275268555, |
| "epoch": 0.048607360543167964, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.000472, |
| "loss": 6.4806, |
| "mean_token_accuracy": 0.11481974124908448, |
| "num_tokens": 1684268.0, |
| "step": 945 |
| }, |
| { |
| "entropy": 6.837112474441528, |
| "epoch": 0.04886454234498367, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004745, |
| "loss": 6.566, |
| "mean_token_accuracy": 0.10879503637552261, |
| "num_tokens": 1692665.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 7.00029149055481, |
| "epoch": 0.04912172414679937, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000477, |
| "loss": 6.6023, |
| "mean_token_accuracy": 0.11165886968374253, |
| "num_tokens": 1701321.0, |
| "step": 955 |
| }, |
| { |
| "entropy": 6.796492385864258, |
| "epoch": 0.049378905948615076, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004795, |
| "loss": 6.5413, |
| "mean_token_accuracy": 0.10716139823198319, |
| "num_tokens": 1710476.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 6.805513620376587, |
| "epoch": 0.04963608775043078, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000482, |
| "loss": 6.4891, |
| "mean_token_accuracy": 0.10693883448839188, |
| "num_tokens": 1719949.0, |
| "step": 965 |
| }, |
| { |
| "entropy": 6.972143602371216, |
| "epoch": 0.04989326955224648, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004845, |
| "loss": 6.6165, |
| "mean_token_accuracy": 0.10792995691299438, |
| "num_tokens": 1729362.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 6.834133863449097, |
| "epoch": 0.05015045135406219, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.000487, |
| "loss": 6.5197, |
| "mean_token_accuracy": 0.10525891557335854, |
| "num_tokens": 1739001.0, |
| "step": 975 |
| }, |
| { |
| "entropy": 6.7445004940032955, |
| "epoch": 0.05040763315587789, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004895, |
| "loss": 6.4256, |
| "mean_token_accuracy": 0.11702816039323807, |
| "num_tokens": 1748249.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 6.755212068557739, |
| "epoch": 0.050664814957693594, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000492, |
| "loss": 6.4386, |
| "mean_token_accuracy": 0.1141409620642662, |
| "num_tokens": 1757070.0, |
| "step": 985 |
| }, |
| { |
| "entropy": 6.799167490005493, |
| "epoch": 0.0509219967595093, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004945, |
| "loss": 6.4032, |
| "mean_token_accuracy": 0.11792294010519981, |
| "num_tokens": 1765737.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 6.891513156890869, |
| "epoch": 0.051179178561325, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000497, |
| "loss": 6.5878, |
| "mean_token_accuracy": 0.11050201207399368, |
| "num_tokens": 1774942.0, |
| "step": 995 |
| }, |
| { |
| "entropy": 6.857363891601563, |
| "epoch": 0.051436360363140705, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004995, |
| "loss": 6.5936, |
| "mean_token_accuracy": 0.10368210449814796, |
| "num_tokens": 1784256.0, |
| "step": 1000 |
| }, |
| { |
| "entropy": 6.849530935287476, |
| "epoch": 0.051693542164956405, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.000499998026082006, |
| "loss": 6.5383, |
| "mean_token_accuracy": 0.10572032853960991, |
| "num_tokens": 1792926.0, |
| "step": 1005 |
| }, |
| { |
| "entropy": 6.72293267250061, |
| "epoch": 0.05195072396677211, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0004999900070995136, |
| "loss": 6.4893, |
| "mean_token_accuracy": 0.11575818508863449, |
| "num_tokens": 1802070.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 6.841842365264893, |
| "epoch": 0.05220790576858782, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0004999758199023239, |
| "loss": 6.5344, |
| "mean_token_accuracy": 0.10665113478899002, |
| "num_tokens": 1811507.0, |
| "step": 1015 |
| }, |
| { |
| "entropy": 6.851677942276001, |
| "epoch": 0.05246508757040352, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.0004999554648793858, |
| "loss": 6.4522, |
| "mean_token_accuracy": 0.11116268336772919, |
| "num_tokens": 1820311.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 6.710117959976197, |
| "epoch": 0.05272226937221922, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004999289425887425, |
| "loss": 6.4099, |
| "mean_token_accuracy": 0.1138461858034134, |
| "num_tokens": 1828948.0, |
| "step": 1025 |
| }, |
| { |
| "entropy": 6.834085750579834, |
| "epoch": 0.05297945117403492, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004998962537575161, |
| "loss": 6.5724, |
| "mean_token_accuracy": 0.1098745584487915, |
| "num_tokens": 1838350.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 6.842246675491333, |
| "epoch": 0.05323663297585063, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0004998573992818874, |
| "loss": 6.4004, |
| "mean_token_accuracy": 0.12005882859230041, |
| "num_tokens": 1847162.0, |
| "step": 1035 |
| }, |
| { |
| "entropy": 6.665293884277344, |
| "epoch": 0.053493814777666335, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004998123802270715, |
| "loss": 6.4849, |
| "mean_token_accuracy": 0.11263752803206444, |
| "num_tokens": 1856275.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 6.729813432693481, |
| "epoch": 0.053750996579482034, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0004997611978272886, |
| "loss": 6.3855, |
| "mean_token_accuracy": 0.11651406660676003, |
| "num_tokens": 1864663.0, |
| "step": 1045 |
| }, |
| { |
| "entropy": 6.733455944061279, |
| "epoch": 0.05400817838129774, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004997038534857298, |
| "loss": 6.424, |
| "mean_token_accuracy": 0.1177938535809517, |
| "num_tokens": 1874622.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 6.7023192882537845, |
| "epoch": 0.05426536018311344, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004996403487745194, |
| "loss": 6.3922, |
| "mean_token_accuracy": 0.11079680770635605, |
| "num_tokens": 1884257.0, |
| "step": 1055 |
| }, |
| { |
| "entropy": 6.801939916610718, |
| "epoch": 0.054522541984929146, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.000499570685434671, |
| "loss": 6.4462, |
| "mean_token_accuracy": 0.11080927178263664, |
| "num_tokens": 1894336.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 6.734097909927368, |
| "epoch": 0.05477972378674485, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0004994948653760405, |
| "loss": 6.4129, |
| "mean_token_accuracy": 0.11459591910243035, |
| "num_tokens": 1903305.0, |
| "step": 1065 |
| }, |
| { |
| "entropy": 6.686365461349487, |
| "epoch": 0.05503690558856055, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0004994128906772729, |
| "loss": 6.4414, |
| "mean_token_accuracy": 0.11344051584601403, |
| "num_tokens": 1911992.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 6.707837152481079, |
| "epoch": 0.05529408739037626, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000499324763585746, |
| "loss": 6.3462, |
| "mean_token_accuracy": 0.12238444536924362, |
| "num_tokens": 1920826.0, |
| "step": 1075 |
| }, |
| { |
| "entropy": 6.851500606536865, |
| "epoch": 0.05555126919219196, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004992304865175085, |
| "loss": 6.5005, |
| "mean_token_accuracy": 0.11342206448316575, |
| "num_tokens": 1930181.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 6.683105993270874, |
| "epoch": 0.05580845099400766, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004991300620572138, |
| "loss": 6.3627, |
| "mean_token_accuracy": 0.11612597554922104, |
| "num_tokens": 1938865.0, |
| "step": 1085 |
| }, |
| { |
| "entropy": 6.6627490520477295, |
| "epoch": 0.05606563279582337, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004990234929580494, |
| "loss": 6.3018, |
| "mean_token_accuracy": 0.11800351217389107, |
| "num_tokens": 1947979.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 6.705393505096436, |
| "epoch": 0.05632281459763907, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004989107821416609, |
| "loss": 6.4207, |
| "mean_token_accuracy": 0.11706310212612152, |
| "num_tokens": 1957012.0, |
| "step": 1095 |
| }, |
| { |
| "entropy": 6.785688734054565, |
| "epoch": 0.056579996399454775, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004987919326980723, |
| "loss": 6.5063, |
| "mean_token_accuracy": 0.11153422519564629, |
| "num_tokens": 1966613.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 6.662994146347046, |
| "epoch": 0.05683717820127048, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004986669478856011, |
| "loss": 6.4567, |
| "mean_token_accuracy": 0.11049317792057992, |
| "num_tokens": 1975878.0, |
| "step": 1105 |
| }, |
| { |
| "entropy": 6.703376007080078, |
| "epoch": 0.05709436000308618, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004985358311307688, |
| "loss": 6.3858, |
| "mean_token_accuracy": 0.12022560909390449, |
| "num_tokens": 1984828.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 6.687681436538696, |
| "epoch": 0.05735154180490189, |
| "grad_norm": 1.25, |
| "learning_rate": 0.0004983985860282081, |
| "loss": 6.3282, |
| "mean_token_accuracy": 0.11830979585647583, |
| "num_tokens": 1992706.0, |
| "step": 1115 |
| }, |
| { |
| "entropy": 6.691852474212647, |
| "epoch": 0.057608723606717586, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004982552163405623, |
| "loss": 6.3836, |
| "mean_token_accuracy": 0.11681668907403946, |
| "num_tokens": 2001461.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 6.5880796909332275, |
| "epoch": 0.05786590540853329, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004981057259983839, |
| "loss": 6.3809, |
| "mean_token_accuracy": 0.11749306172132493, |
| "num_tokens": 2011029.0, |
| "step": 1125 |
| }, |
| { |
| "entropy": 6.7658202171325685, |
| "epoch": 0.058123087210349, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004979501191000262, |
| "loss": 6.4011, |
| "mean_token_accuracy": 0.11484191119670868, |
| "num_tokens": 2019712.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 6.552847003936767, |
| "epoch": 0.0583802690121647, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004977883999115311, |
| "loss": 6.2373, |
| "mean_token_accuracy": 0.12176965028047562, |
| "num_tokens": 2028411.0, |
| "step": 1135 |
| }, |
| { |
| "entropy": 6.681560611724853, |
| "epoch": 0.058637450813980405, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004976205728665113, |
| "loss": 6.395, |
| "mean_token_accuracy": 0.11524997726082802, |
| "num_tokens": 2037874.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 6.68039722442627, |
| "epoch": 0.058894632615796104, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0004974466425660307, |
| "loss": 6.3971, |
| "mean_token_accuracy": 0.11318053975701332, |
| "num_tokens": 2046752.0, |
| "step": 1145 |
| }, |
| { |
| "entropy": 6.605433797836303, |
| "epoch": 0.05915181441761181, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004972666137784759, |
| "loss": 6.3035, |
| "mean_token_accuracy": 0.12526411563158035, |
| "num_tokens": 2054893.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 6.69100604057312, |
| "epoch": 0.059408996219427516, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0004970804914394271, |
| "loss": 6.2801, |
| "mean_token_accuracy": 0.12134814634919167, |
| "num_tokens": 2062794.0, |
| "step": 1155 |
| }, |
| { |
| "entropy": 6.600447416305542, |
| "epoch": 0.059666178021243216, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0004968882806515225, |
| "loss": 6.4006, |
| "mean_token_accuracy": 0.11898823902010917, |
| "num_tokens": 2072225.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 6.584507894515991, |
| "epoch": 0.05992335982305892, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.0004966899866843177, |
| "loss": 6.3768, |
| "mean_token_accuracy": 0.11224907487630845, |
| "num_tokens": 2080521.0, |
| "step": 1165 |
| }, |
| { |
| "entropy": 6.6145092964172365, |
| "epoch": 0.06018054162487462, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000496485614974142, |
| "loss": 6.2801, |
| "mean_token_accuracy": 0.1179177112877369, |
| "num_tokens": 2090633.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 6.679648780822754, |
| "epoch": 0.06043772342669033, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.0004962751711239492, |
| "loss": 6.4617, |
| "mean_token_accuracy": 0.1087147168815136, |
| "num_tokens": 2100284.0, |
| "step": 1175 |
| }, |
| { |
| "entropy": 6.599804067611695, |
| "epoch": 0.060694905228506034, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004960586609031636, |
| "loss": 6.2978, |
| "mean_token_accuracy": 0.11903873831033707, |
| "num_tokens": 2109612.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 6.658626890182495, |
| "epoch": 0.06095208703032173, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004958360902475224, |
| "loss": 6.3076, |
| "mean_token_accuracy": 0.1250632882118225, |
| "num_tokens": 2117817.0, |
| "step": 1185 |
| }, |
| { |
| "entropy": 6.6112429141998295, |
| "epoch": 0.06120926883213744, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004956074652589125, |
| "loss": 6.4007, |
| "mean_token_accuracy": 0.1222650684416294, |
| "num_tokens": 2126283.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 6.64881386756897, |
| "epoch": 0.06146645063395314, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0004953727922052035, |
| "loss": 6.3017, |
| "mean_token_accuracy": 0.11719283163547516, |
| "num_tokens": 2134361.0, |
| "step": 1195 |
| }, |
| { |
| "entropy": 6.705007314682007, |
| "epoch": 0.061723632435768845, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004951320775200756, |
| "loss": 6.389, |
| "mean_token_accuracy": 0.11199460625648498, |
| "num_tokens": 2143304.0, |
| "step": 1200 |
| }, |
| { |
| "entropy": 6.519802904129028, |
| "epoch": 0.06198081423758455, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.0004948853278028436, |
| "loss": 6.2467, |
| "mean_token_accuracy": 0.11709044873714447, |
| "num_tokens": 2151650.0, |
| "step": 1205 |
| }, |
| { |
| "entropy": 6.573320007324218, |
| "epoch": 0.06223799603940025, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004946325498182755, |
| "loss": 6.3113, |
| "mean_token_accuracy": 0.11818666979670525, |
| "num_tokens": 2161139.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 6.78554859161377, |
| "epoch": 0.06249517784121596, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004943737504964076, |
| "loss": 6.4733, |
| "mean_token_accuracy": 0.11637833341956139, |
| "num_tokens": 2170606.0, |
| "step": 1215 |
| }, |
| { |
| "entropy": 6.549322175979614, |
| "epoch": 0.06275235964303166, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.000494108936932354, |
| "loss": 6.3382, |
| "mean_token_accuracy": 0.11747744753956794, |
| "num_tokens": 2180284.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 6.6795018196105955, |
| "epoch": 0.06300954144484737, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0004938381163861124, |
| "loss": 6.3362, |
| "mean_token_accuracy": 0.12103840410709381, |
| "num_tokens": 2189130.0, |
| "step": 1225 |
| }, |
| { |
| "entropy": 6.5853265762329105, |
| "epoch": 0.06326672324666306, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004935612962823645, |
| "loss": 6.3564, |
| "mean_token_accuracy": 0.11555552780628205, |
| "num_tokens": 2198083.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 6.717031812667846, |
| "epoch": 0.06352390504847877, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0004932784842102739, |
| "loss": 6.3463, |
| "mean_token_accuracy": 0.12118180245161056, |
| "num_tokens": 2206470.0, |
| "step": 1235 |
| }, |
| { |
| "entropy": 6.5396645069122314, |
| "epoch": 0.06378108685029447, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004929896879232758, |
| "loss": 6.3004, |
| "mean_token_accuracy": 0.12020415365695954, |
| "num_tokens": 2215241.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 6.611561393737793, |
| "epoch": 0.06403826865211018, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004926949153388668, |
| "loss": 6.3158, |
| "mean_token_accuracy": 0.12042762041091919, |
| "num_tokens": 2224047.0, |
| "step": 1245 |
| }, |
| { |
| "entropy": 6.717500877380371, |
| "epoch": 0.06429545045392589, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004923941745383859, |
| "loss": 6.4761, |
| "mean_token_accuracy": 0.11400299072265625, |
| "num_tokens": 2234030.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 6.551206016540528, |
| "epoch": 0.06455263225574158, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000492087473766794, |
| "loss": 6.2506, |
| "mean_token_accuracy": 0.12165699452161789, |
| "num_tokens": 2243123.0, |
| "step": 1255 |
| }, |
| { |
| "entropy": 6.559505128860474, |
| "epoch": 0.06480981405755729, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000491774821432448, |
| "loss": 6.2329, |
| "mean_token_accuracy": 0.12427677810192109, |
| "num_tokens": 2251778.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 6.605167245864868, |
| "epoch": 0.06506699585937299, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004914562261068693, |
| "loss": 6.2228, |
| "mean_token_accuracy": 0.12148385569453239, |
| "num_tokens": 2261552.0, |
| "step": 1265 |
| }, |
| { |
| "entropy": 6.4509941101074215, |
| "epoch": 0.0653241776611887, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0004911316965245098, |
| "loss": 6.2464, |
| "mean_token_accuracy": 0.12392940372228622, |
| "num_tokens": 2270543.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 6.684006547927856, |
| "epoch": 0.0655813594630044, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.000490801241582512, |
| "loss": 6.2811, |
| "mean_token_accuracy": 0.12095867022871971, |
| "num_tokens": 2278856.0, |
| "step": 1275 |
| }, |
| { |
| "entropy": 6.489159202575683, |
| "epoch": 0.0658385412648201, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.000490464870340465, |
| "loss": 6.2578, |
| "mean_token_accuracy": 0.12322199791669845, |
| "num_tokens": 2287208.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 6.573577213287353, |
| "epoch": 0.0660957230666358, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004901225920201563, |
| "loss": 6.3295, |
| "mean_token_accuracy": 0.11680645272135734, |
| "num_tokens": 2296947.0, |
| "step": 1285 |
| }, |
| { |
| "entropy": 6.5740087032318115, |
| "epoch": 0.06635290486845151, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000489774416005319, |
| "loss": 6.2783, |
| "mean_token_accuracy": 0.12419264763593674, |
| "num_tokens": 2305853.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 6.506151580810547, |
| "epoch": 0.06661008667026722, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004894203518413742, |
| "loss": 6.2311, |
| "mean_token_accuracy": 0.11923173069953918, |
| "num_tokens": 2315344.0, |
| "step": 1295 |
| }, |
| { |
| "entropy": 6.499106740951538, |
| "epoch": 0.06686726847208292, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0004890604092351701, |
| "loss": 6.2209, |
| "mean_token_accuracy": 0.1210881769657135, |
| "num_tokens": 2324007.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 6.517620944976807, |
| "epoch": 0.06712445027389861, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000488694598054715, |
| "loss": 6.2672, |
| "mean_token_accuracy": 0.11856792867183685, |
| "num_tokens": 2332613.0, |
| "step": 1305 |
| }, |
| { |
| "entropy": 6.554975318908691, |
| "epoch": 0.06738163207571432, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004883229283289071, |
| "loss": 6.2676, |
| "mean_token_accuracy": 0.12289687469601632, |
| "num_tokens": 2342019.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 6.47722110748291, |
| "epoch": 0.06763881387753003, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00048794541024725993, |
| "loss": 6.2182, |
| "mean_token_accuracy": 0.12205516248941421, |
| "num_tokens": 2350715.0, |
| "step": 1315 |
| }, |
| { |
| "entropy": 6.656716966629029, |
| "epoch": 0.06789599567934573, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004875620541596221, |
| "loss": 6.3923, |
| "mean_token_accuracy": 0.12098478376865388, |
| "num_tokens": 2359699.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 6.4792803764343265, |
| "epoch": 0.06815317748116144, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00048717287057589454, |
| "loss": 6.1595, |
| "mean_token_accuracy": 0.12839691638946532, |
| "num_tokens": 2368782.0, |
| "step": 1325 |
| }, |
| { |
| "entropy": 6.383249664306641, |
| "epoch": 0.06841035928297713, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004867778701657417, |
| "loss": 6.0096, |
| "mean_token_accuracy": 0.13362448140978814, |
| "num_tokens": 2377235.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 6.409832763671875, |
| "epoch": 0.06866754108479284, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00048637706375829955, |
| "loss": 6.2013, |
| "mean_token_accuracy": 0.12747161388397216, |
| "num_tokens": 2386265.0, |
| "step": 1335 |
| }, |
| { |
| "entropy": 6.527412176132202, |
| "epoch": 0.06892472288660854, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.000485970462341878, |
| "loss": 6.1131, |
| "mean_token_accuracy": 0.1332041934132576, |
| "num_tokens": 2394953.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 6.503418636322022, |
| "epoch": 0.06918190468842425, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00048555807706366044, |
| "loss": 6.3003, |
| "mean_token_accuracy": 0.11948163360357285, |
| "num_tokens": 2403792.0, |
| "step": 1345 |
| }, |
| { |
| "entropy": 6.4240118026733395, |
| "epoch": 0.06943908649023996, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00048513991922939756, |
| "loss": 6.1478, |
| "mean_token_accuracy": 0.1259373866021633, |
| "num_tokens": 2412252.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 6.6844557762146, |
| "epoch": 0.06969626829205565, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00048471600030309744, |
| "loss": 6.2847, |
| "mean_token_accuracy": 0.1220081552863121, |
| "num_tokens": 2420364.0, |
| "step": 1355 |
| }, |
| { |
| "entropy": 6.442555618286133, |
| "epoch": 0.06995345009387136, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00048428633190671186, |
| "loss": 6.1597, |
| "mean_token_accuracy": 0.12498654872179031, |
| "num_tokens": 2429333.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 6.515508556365967, |
| "epoch": 0.07021063189568706, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004838509258198167, |
| "loss": 6.2702, |
| "mean_token_accuracy": 0.12291633188724518, |
| "num_tokens": 2437439.0, |
| "step": 1365 |
| }, |
| { |
| "entropy": 6.4559262752532955, |
| "epoch": 0.07046781369750277, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00048340979397929, |
| "loss": 6.2392, |
| "mean_token_accuracy": 0.12877265959978104, |
| "num_tokens": 2446084.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 6.574571943283081, |
| "epoch": 0.07072499549931847, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00048296294847898386, |
| "loss": 6.2038, |
| "mean_token_accuracy": 0.11378729492425918, |
| "num_tokens": 2455613.0, |
| "step": 1375 |
| }, |
| { |
| "entropy": 6.547432279586792, |
| "epoch": 0.07098217730113417, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.0004825104015693934, |
| "loss": 6.336, |
| "mean_token_accuracy": 0.12563420534133912, |
| "num_tokens": 2464123.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 6.496583318710327, |
| "epoch": 0.07123935910294987, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004820521656573208, |
| "loss": 6.2003, |
| "mean_token_accuracy": 0.12900396287441254, |
| "num_tokens": 2472972.0, |
| "step": 1385 |
| }, |
| { |
| "entropy": 6.55055980682373, |
| "epoch": 0.07149654090476558, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00048158825330553505, |
| "loss": 6.3127, |
| "mean_token_accuracy": 0.12014695033431053, |
| "num_tokens": 2482017.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 6.498235702514648, |
| "epoch": 0.07175372270658129, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00048111867723242763, |
| "loss": 6.1993, |
| "mean_token_accuracy": 0.12744636759161948, |
| "num_tokens": 2490771.0, |
| "step": 1395 |
| }, |
| { |
| "entropy": 6.492023563385009, |
| "epoch": 0.07201090450839699, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0004806434503116637, |
| "loss": 6.2633, |
| "mean_token_accuracy": 0.12012107148766518, |
| "num_tokens": 2501047.0, |
| "step": 1400 |
| }, |
| { |
| "entropy": 6.459356260299683, |
| "epoch": 0.07226808631021268, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004801625855718296, |
| "loss": 6.2797, |
| "mean_token_accuracy": 0.12193729802966118, |
| "num_tokens": 2509689.0, |
| "step": 1405 |
| }, |
| { |
| "entropy": 6.523634672164917, |
| "epoch": 0.07252526811202839, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00047967609619607477, |
| "loss": 6.2162, |
| "mean_token_accuracy": 0.1272864632308483, |
| "num_tokens": 2519067.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 6.3656079292297365, |
| "epoch": 0.0727824499138441, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004791839955217513, |
| "loss": 6.1233, |
| "mean_token_accuracy": 0.12799235731363295, |
| "num_tokens": 2527921.0, |
| "step": 1415 |
| }, |
| { |
| "entropy": 6.555266809463501, |
| "epoch": 0.0730396317156598, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00047868629704004786, |
| "loss": 6.2048, |
| "mean_token_accuracy": 0.12755087167024612, |
| "num_tokens": 2536424.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 6.4298278331756595, |
| "epoch": 0.07329681351747551, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00047818301439561965, |
| "loss": 6.1967, |
| "mean_token_accuracy": 0.12071703523397445, |
| "num_tokens": 2546029.0, |
| "step": 1425 |
| }, |
| { |
| "entropy": 6.526437473297119, |
| "epoch": 0.0735539953192912, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00047767416138621454, |
| "loss": 6.2481, |
| "mean_token_accuracy": 0.12410413399338723, |
| "num_tokens": 2554861.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 6.460501337051392, |
| "epoch": 0.07381117712110691, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.000477159751962295, |
| "loss": 6.1015, |
| "mean_token_accuracy": 0.12634221836924553, |
| "num_tokens": 2563405.0, |
| "step": 1435 |
| }, |
| { |
| "entropy": 6.288591575622559, |
| "epoch": 0.07406835892292261, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00047663980022665507, |
| "loss": 6.0832, |
| "mean_token_accuracy": 0.1300654336810112, |
| "num_tokens": 2571409.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 6.524644994735718, |
| "epoch": 0.07432554072473832, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.00047611432043403437, |
| "loss": 6.323, |
| "mean_token_accuracy": 0.11622402295470238, |
| "num_tokens": 2581233.0, |
| "step": 1445 |
| }, |
| { |
| "entropy": 6.429956722259521, |
| "epoch": 0.07458272252655403, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004755833269907267, |
| "loss": 6.273, |
| "mean_token_accuracy": 0.11982614472508431, |
| "num_tokens": 2591528.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 6.653250694274902, |
| "epoch": 0.07483990432836972, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004750468344541857, |
| "loss": 6.2093, |
| "mean_token_accuracy": 0.1260430246591568, |
| "num_tokens": 2600033.0, |
| "step": 1455 |
| }, |
| { |
| "entropy": 6.354333925247192, |
| "epoch": 0.07509708613018543, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00047450485753262525, |
| "loss": 6.1861, |
| "mean_token_accuracy": 0.12549542263150215, |
| "num_tokens": 2608648.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 6.368370294570923, |
| "epoch": 0.07535426793200113, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00047395741108461633, |
| "loss": 6.0852, |
| "mean_token_accuracy": 0.13009310886263847, |
| "num_tokens": 2617727.0, |
| "step": 1465 |
| }, |
| { |
| "entropy": 6.389603805541992, |
| "epoch": 0.07561144973381684, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00047340451011867985, |
| "loss": 6.0666, |
| "mean_token_accuracy": 0.13752511888742447, |
| "num_tokens": 2625463.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 6.439476728439331, |
| "epoch": 0.07586863153563254, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00047284616979287515, |
| "loss": 6.1768, |
| "mean_token_accuracy": 0.12700055465102195, |
| "num_tokens": 2635050.0, |
| "step": 1475 |
| }, |
| { |
| "entropy": 6.452608394622803, |
| "epoch": 0.07612581333744824, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00047228240541438433, |
| "loss": 6.2373, |
| "mean_token_accuracy": 0.1270735152065754, |
| "num_tokens": 2645129.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 6.402850103378296, |
| "epoch": 0.07638299513926394, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00047171323243909257, |
| "loss": 6.1132, |
| "mean_token_accuracy": 0.12463590428233147, |
| "num_tokens": 2653966.0, |
| "step": 1485 |
| }, |
| { |
| "entropy": 6.413847303390503, |
| "epoch": 0.07664017694107965, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00047113866647116457, |
| "loss": 6.1521, |
| "mean_token_accuracy": 0.1268475502729416, |
| "num_tokens": 2663219.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 6.427061939239502, |
| "epoch": 0.07689735874289536, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004705587232626164, |
| "loss": 6.0832, |
| "mean_token_accuracy": 0.1297985441982746, |
| "num_tokens": 2671468.0, |
| "step": 1495 |
| }, |
| { |
| "entropy": 6.292563104629517, |
| "epoch": 0.07715454054471106, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00046997341871288424, |
| "loss": 6.036, |
| "mean_token_accuracy": 0.1342359036207199, |
| "num_tokens": 2680380.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 6.436664009094239, |
| "epoch": 0.07741172234652675, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004693827688683879, |
| "loss": 6.1687, |
| "mean_token_accuracy": 0.12308031022548675, |
| "num_tokens": 2689976.0, |
| "step": 1505 |
| }, |
| { |
| "entropy": 6.508772373199463, |
| "epoch": 0.07766890414834246, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004687867899220914, |
| "loss": 6.1793, |
| "mean_token_accuracy": 0.12510153502225876, |
| "num_tokens": 2698780.0, |
| "step": 1510 |
| }, |
| { |
| "entropy": 6.226078796386719, |
| "epoch": 0.07792608595015817, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00046818549821305846, |
| "loss": 6.03, |
| "mean_token_accuracy": 0.13029744401574134, |
| "num_tokens": 2706887.0, |
| "step": 1515 |
| }, |
| { |
| "entropy": 6.41196641921997, |
| "epoch": 0.07818326775197387, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00046757891022600494, |
| "loss": 6.0603, |
| "mean_token_accuracy": 0.1270065888762474, |
| "num_tokens": 2715484.0, |
| "step": 1520 |
| }, |
| { |
| "entropy": 6.334155130386352, |
| "epoch": 0.07844044955378958, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004669670425908471, |
| "loss": 6.1788, |
| "mean_token_accuracy": 0.12362223640084266, |
| "num_tokens": 2724272.0, |
| "step": 1525 |
| }, |
| { |
| "entropy": 6.397065687179565, |
| "epoch": 0.07869763135560527, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004663499120822451, |
| "loss": 6.0992, |
| "mean_token_accuracy": 0.13246706426143645, |
| "num_tokens": 2733379.0, |
| "step": 1530 |
| }, |
| { |
| "entropy": 6.365872526168824, |
| "epoch": 0.07895481315742098, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004657275356191437, |
| "loss": 6.0708, |
| "mean_token_accuracy": 0.13027092143893243, |
| "num_tokens": 2742584.0, |
| "step": 1535 |
| }, |
| { |
| "entropy": 6.467748212814331, |
| "epoch": 0.07921199495923668, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00046509993026430804, |
| "loss": 6.2481, |
| "mean_token_accuracy": 0.12418549954891205, |
| "num_tokens": 2751491.0, |
| "step": 1540 |
| }, |
| { |
| "entropy": 6.414959955215454, |
| "epoch": 0.07946917676105239, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004644671132238558, |
| "loss": 6.0621, |
| "mean_token_accuracy": 0.1291202872991562, |
| "num_tokens": 2760320.0, |
| "step": 1545 |
| }, |
| { |
| "entropy": 6.405585384368896, |
| "epoch": 0.0797263585628681, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00046382910184678585, |
| "loss": 6.2345, |
| "mean_token_accuracy": 0.11954343914985657, |
| "num_tokens": 2770247.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 6.431417655944824, |
| "epoch": 0.07998354036468379, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004631859136245025, |
| "loss": 6.0881, |
| "mean_token_accuracy": 0.13392823338508605, |
| "num_tokens": 2779969.0, |
| "step": 1555 |
| }, |
| { |
| "entropy": 6.324232196807861, |
| "epoch": 0.0802407221664995, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0004625375661903357, |
| "loss": 6.1817, |
| "mean_token_accuracy": 0.13248204365372657, |
| "num_tokens": 2788584.0, |
| "step": 1560 |
| }, |
| { |
| "entropy": 6.307961273193359, |
| "epoch": 0.0804979039683152, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.00046188407731905787, |
| "loss": 6.0618, |
| "mean_token_accuracy": 0.13163200318813323, |
| "num_tokens": 2796982.0, |
| "step": 1565 |
| }, |
| { |
| "entropy": 6.487869310379028, |
| "epoch": 0.08075508577013091, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00046122546492639643, |
| "loss": 6.2135, |
| "mean_token_accuracy": 0.12365017086267471, |
| "num_tokens": 2806788.0, |
| "step": 1570 |
| }, |
| { |
| "entropy": 6.321759557723999, |
| "epoch": 0.08101226757194661, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000460561747068543, |
| "loss": 6.0832, |
| "mean_token_accuracy": 0.12752610817551613, |
| "num_tokens": 2816086.0, |
| "step": 1575 |
| }, |
| { |
| "entropy": 6.285551452636719, |
| "epoch": 0.0812694493737623, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0004598929419416578, |
| "loss": 6.084, |
| "mean_token_accuracy": 0.12898513302206993, |
| "num_tokens": 2825623.0, |
| "step": 1580 |
| }, |
| { |
| "entropy": 6.406826734542847, |
| "epoch": 0.08152663117557801, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00045921906788137123, |
| "loss": 6.229, |
| "mean_token_accuracy": 0.1251101866364479, |
| "num_tokens": 2835241.0, |
| "step": 1585 |
| }, |
| { |
| "entropy": 6.380240058898925, |
| "epoch": 0.08178381297739372, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00045854014336228115, |
| "loss": 6.0826, |
| "mean_token_accuracy": 0.1333278901875019, |
| "num_tokens": 2843428.0, |
| "step": 1590 |
| }, |
| { |
| "entropy": 6.348821783065796, |
| "epoch": 0.08204099477920943, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00045785618699744615, |
| "loss": 6.0808, |
| "mean_token_accuracy": 0.1321525380015373, |
| "num_tokens": 2852662.0, |
| "step": 1595 |
| }, |
| { |
| "entropy": 6.395787191390991, |
| "epoch": 0.08229817658102513, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.00045716721753787543, |
| "loss": 6.0908, |
| "mean_token_accuracy": 0.13208872005343436, |
| "num_tokens": 2861094.0, |
| "step": 1600 |
| }, |
| { |
| "entropy": 6.31074743270874, |
| "epoch": 0.08255535838284082, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004564732538720148, |
| "loss": 5.9817, |
| "mean_token_accuracy": 0.1272851899266243, |
| "num_tokens": 2870214.0, |
| "step": 1605 |
| }, |
| { |
| "entropy": 6.283258056640625, |
| "epoch": 0.08281254018465653, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00045577431502522877, |
| "loss": 6.1137, |
| "mean_token_accuracy": 0.1351046971976757, |
| "num_tokens": 2878876.0, |
| "step": 1610 |
| }, |
| { |
| "entropy": 6.478934669494629, |
| "epoch": 0.08306972198647224, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004550704201592787, |
| "loss": 6.1111, |
| "mean_token_accuracy": 0.12919269502162933, |
| "num_tokens": 2888111.0, |
| "step": 1615 |
| }, |
| { |
| "entropy": 6.340307664871216, |
| "epoch": 0.08332690378828794, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004543615885717981, |
| "loss": 6.1395, |
| "mean_token_accuracy": 0.13248469904065133, |
| "num_tokens": 2897589.0, |
| "step": 1620 |
| }, |
| { |
| "entropy": 6.388657903671264, |
| "epoch": 0.08358408559010365, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00045364783969576296, |
| "loss": 6.0822, |
| "mean_token_accuracy": 0.1332689106464386, |
| "num_tokens": 2906803.0, |
| "step": 1625 |
| }, |
| { |
| "entropy": 6.2963072776794435, |
| "epoch": 0.08384126739191934, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004529291930989592, |
| "loss": 5.9716, |
| "mean_token_accuracy": 0.13755856528878213, |
| "num_tokens": 2916903.0, |
| "step": 1630 |
| }, |
| { |
| "entropy": 6.342654514312744, |
| "epoch": 0.08409844919373505, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004522056684834464, |
| "loss": 6.0949, |
| "mean_token_accuracy": 0.13052690103650094, |
| "num_tokens": 2925952.0, |
| "step": 1635 |
| }, |
| { |
| "entropy": 6.325797176361084, |
| "epoch": 0.08435563099555075, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0004514772856850173, |
| "loss": 6.0416, |
| "mean_token_accuracy": 0.12649609819054602, |
| "num_tokens": 2934538.0, |
| "step": 1640 |
| }, |
| { |
| "entropy": 6.3612961769104, |
| "epoch": 0.08461281279736646, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004507440646726542, |
| "loss": 6.1471, |
| "mean_token_accuracy": 0.132496327906847, |
| "num_tokens": 2943553.0, |
| "step": 1645 |
| }, |
| { |
| "entropy": 6.292884588241577, |
| "epoch": 0.08486999459918217, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004500060255479818, |
| "loss": 6.031, |
| "mean_token_accuracy": 0.1341935083270073, |
| "num_tokens": 2951854.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 6.448796558380127, |
| "epoch": 0.08512717640099786, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0004492631885447151, |
| "loss": 6.1977, |
| "mean_token_accuracy": 0.12419203296303749, |
| "num_tokens": 2961684.0, |
| "step": 1655 |
| }, |
| { |
| "entropy": 6.379677057266235, |
| "epoch": 0.08538435820281357, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00044851557402810616, |
| "loss": 6.0526, |
| "mean_token_accuracy": 0.12697965502738953, |
| "num_tokens": 2970984.0, |
| "step": 1660 |
| }, |
| { |
| "entropy": 6.304157495498657, |
| "epoch": 0.08564154000462927, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00044776320249438444, |
| "loss": 6.0435, |
| "mean_token_accuracy": 0.12820193246006967, |
| "num_tokens": 2979319.0, |
| "step": 1665 |
| }, |
| { |
| "entropy": 6.231897449493408, |
| "epoch": 0.08589872180644498, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00044700609457019565, |
| "loss": 5.9506, |
| "mean_token_accuracy": 0.1356399580836296, |
| "num_tokens": 2987780.0, |
| "step": 1670 |
| }, |
| { |
| "entropy": 6.239076566696167, |
| "epoch": 0.08615590360826068, |
| "grad_norm": 0.96875, |
| "learning_rate": 0.0004462442710120359, |
| "loss": 6.0657, |
| "mean_token_accuracy": 0.12994374260306357, |
| "num_tokens": 2996890.0, |
| "step": 1675 |
| }, |
| { |
| "entropy": 6.530197525024414, |
| "epoch": 0.08641308541007638, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000445477752705683, |
| "loss": 6.1939, |
| "mean_token_accuracy": 0.12460953146219253, |
| "num_tokens": 3005736.0, |
| "step": 1680 |
| }, |
| { |
| "entropy": 6.189916801452637, |
| "epoch": 0.08667026721189208, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00044470656066562336, |
| "loss": 5.9827, |
| "mean_token_accuracy": 0.13694657981395722, |
| "num_tokens": 3014167.0, |
| "step": 1685 |
| }, |
| { |
| "entropy": 6.1757958889007565, |
| "epoch": 0.08692744901370779, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004439307160344765, |
| "loss": 5.9809, |
| "mean_token_accuracy": 0.140267164260149, |
| "num_tokens": 3023018.0, |
| "step": 1690 |
| }, |
| { |
| "entropy": 6.499619054794311, |
| "epoch": 0.0871846308155235, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.00044315024008241473, |
| "loss": 6.1587, |
| "mean_token_accuracy": 0.12271130084991455, |
| "num_tokens": 3032659.0, |
| "step": 1695 |
| }, |
| { |
| "entropy": 6.313583087921143, |
| "epoch": 0.0874418126173392, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004423651542065806, |
| "loss": 5.9887, |
| "mean_token_accuracy": 0.13750137612223626, |
| "num_tokens": 3040882.0, |
| "step": 1700 |
| }, |
| { |
| "entropy": 6.182634162902832, |
| "epoch": 0.0876989944191549, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00044157547993050006, |
| "loss": 5.9244, |
| "mean_token_accuracy": 0.13822244331240655, |
| "num_tokens": 3050242.0, |
| "step": 1705 |
| }, |
| { |
| "entropy": 6.321706867218017, |
| "epoch": 0.0879561762209706, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00044078123890349227, |
| "loss": 6.0384, |
| "mean_token_accuracy": 0.12941291332244872, |
| "num_tokens": 3059928.0, |
| "step": 1710 |
| }, |
| { |
| "entropy": 6.401517152786255, |
| "epoch": 0.0882133580227863, |
| "grad_norm": 0.98046875, |
| "learning_rate": 0.00043998245290007606, |
| "loss": 6.2233, |
| "mean_token_accuracy": 0.12163035720586776, |
| "num_tokens": 3069787.0, |
| "step": 1715 |
| }, |
| { |
| "entropy": 6.403897905349732, |
| "epoch": 0.08847053982460201, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00043917914381937323, |
| "loss": 6.1021, |
| "mean_token_accuracy": 0.12949455678462982, |
| "num_tokens": 3079171.0, |
| "step": 1720 |
| }, |
| { |
| "entropy": 6.267082691192627, |
| "epoch": 0.08872772162641772, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00043837133368450815, |
| "loss": 6.0348, |
| "mean_token_accuracy": 0.13504951894283296, |
| "num_tokens": 3088371.0, |
| "step": 1725 |
| }, |
| { |
| "entropy": 6.264813995361328, |
| "epoch": 0.08898490342823343, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004375590446420037, |
| "loss": 6.0367, |
| "mean_token_accuracy": 0.13473087251186372, |
| "num_tokens": 3098489.0, |
| "step": 1730 |
| }, |
| { |
| "entropy": 6.363276672363281, |
| "epoch": 0.08924208523004912, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0004367422989611743, |
| "loss": 6.1169, |
| "mean_token_accuracy": 0.12966250479221345, |
| "num_tokens": 3107161.0, |
| "step": 1735 |
| }, |
| { |
| "entropy": 6.385274219512939, |
| "epoch": 0.08949926703186482, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004359211190335153, |
| "loss": 6.0351, |
| "mean_token_accuracy": 0.13608441054821013, |
| "num_tokens": 3115435.0, |
| "step": 1740 |
| }, |
| { |
| "entropy": 6.3607177734375, |
| "epoch": 0.08975644883368053, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00043509552737208923, |
| "loss": 6.1034, |
| "mean_token_accuracy": 0.13773850798606874, |
| "num_tokens": 3124543.0, |
| "step": 1745 |
| }, |
| { |
| "entropy": 6.311847782135009, |
| "epoch": 0.09001363063549624, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.00043426554661090853, |
| "loss": 5.9807, |
| "mean_token_accuracy": 0.12751075103878975, |
| "num_tokens": 3133856.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 6.20699553489685, |
| "epoch": 0.09027081243731194, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00043343119950431516, |
| "loss": 6.0226, |
| "mean_token_accuracy": 0.13111255168914795, |
| "num_tokens": 3143643.0, |
| "step": 1755 |
| }, |
| { |
| "entropy": 6.388123416900635, |
| "epoch": 0.09052799423912763, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00043259250892635644, |
| "loss": 6.0525, |
| "mean_token_accuracy": 0.13792511597275733, |
| "num_tokens": 3152084.0, |
| "step": 1760 |
| }, |
| { |
| "entropy": 6.389042806625366, |
| "epoch": 0.09078517604094334, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004317494978701582, |
| "loss": 6.0266, |
| "mean_token_accuracy": 0.13580404818058014, |
| "num_tokens": 3160091.0, |
| "step": 1765 |
| }, |
| { |
| "entropy": 6.2101809024810795, |
| "epoch": 0.09104235784275905, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004309021894472943, |
| "loss": 6.014, |
| "mean_token_accuracy": 0.12847821563482284, |
| "num_tokens": 3169569.0, |
| "step": 1770 |
| }, |
| { |
| "entropy": 6.378039360046387, |
| "epoch": 0.09129953964457475, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004300506068871534, |
| "loss": 6.1253, |
| "mean_token_accuracy": 0.12418064251542091, |
| "num_tokens": 3179974.0, |
| "step": 1775 |
| }, |
| { |
| "entropy": 6.311042928695679, |
| "epoch": 0.09155672144639046, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00042919477353630135, |
| "loss": 6.0914, |
| "mean_token_accuracy": 0.13122028410434722, |
| "num_tokens": 3189489.0, |
| "step": 1780 |
| }, |
| { |
| "entropy": 6.401360130310058, |
| "epoch": 0.09181390324820615, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.000428334712857842, |
| "loss": 6.1483, |
| "mean_token_accuracy": 0.1267679288983345, |
| "num_tokens": 3198335.0, |
| "step": 1785 |
| }, |
| { |
| "entropy": 6.154367589950562, |
| "epoch": 0.09207108505002186, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00042747044843077304, |
| "loss": 5.8831, |
| "mean_token_accuracy": 0.1401224859058857, |
| "num_tokens": 3206400.0, |
| "step": 1790 |
| }, |
| { |
| "entropy": 6.391241455078125, |
| "epoch": 0.09232826685183756, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.00042660200394934047, |
| "loss": 5.9885, |
| "mean_token_accuracy": 0.1355439156293869, |
| "num_tokens": 3214480.0, |
| "step": 1795 |
| }, |
| { |
| "entropy": 6.293077850341797, |
| "epoch": 0.09258544865365327, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00042572940322238844, |
| "loss": 6.0104, |
| "mean_token_accuracy": 0.13572105020284653, |
| "num_tokens": 3222386.0, |
| "step": 1800 |
| }, |
| { |
| "entropy": 6.25052399635315, |
| "epoch": 0.09284263045546898, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00042485267017270664, |
| "loss": 5.9602, |
| "mean_token_accuracy": 0.13466379642486573, |
| "num_tokens": 3231203.0, |
| "step": 1805 |
| }, |
| { |
| "entropy": 6.233933353424073, |
| "epoch": 0.09309981225728467, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004239718288363745, |
| "loss": 6.0089, |
| "mean_token_accuracy": 0.1300691097974777, |
| "num_tokens": 3240693.0, |
| "step": 1810 |
| }, |
| { |
| "entropy": 6.2747550964355465, |
| "epoch": 0.09335699405910038, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004230869033621023, |
| "loss": 6.0764, |
| "mean_token_accuracy": 0.13697424307465553, |
| "num_tokens": 3249518.0, |
| "step": 1815 |
| }, |
| { |
| "entropy": 6.3998106002807615, |
| "epoch": 0.09361417586091608, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0004221979180105688, |
| "loss": 6.0622, |
| "mean_token_accuracy": 0.1327414371073246, |
| "num_tokens": 3258712.0, |
| "step": 1820 |
| }, |
| { |
| "entropy": 6.279940986633301, |
| "epoch": 0.09387135766273179, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00042130489715375645, |
| "loss": 5.9342, |
| "mean_token_accuracy": 0.140862063318491, |
| "num_tokens": 3266797.0, |
| "step": 1825 |
| }, |
| { |
| "entropy": 6.2281848907470705, |
| "epoch": 0.0941285394645475, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00042040786527428335, |
| "loss": 6.0584, |
| "mean_token_accuracy": 0.13048559799790382, |
| "num_tokens": 3275811.0, |
| "step": 1830 |
| }, |
| { |
| "entropy": 6.248003005981445, |
| "epoch": 0.09438572126636319, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004195068469647315, |
| "loss": 5.9652, |
| "mean_token_accuracy": 0.13584049865603448, |
| "num_tokens": 3284813.0, |
| "step": 1835 |
| }, |
| { |
| "entropy": 6.284520101547241, |
| "epoch": 0.0946429030681789, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00041860186692697297, |
| "loss": 6.0291, |
| "mean_token_accuracy": 0.1311030738055706, |
| "num_tokens": 3293509.0, |
| "step": 1840 |
| }, |
| { |
| "entropy": 6.319161224365234, |
| "epoch": 0.0949000848699946, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00041769294997149264, |
| "loss": 5.9418, |
| "mean_token_accuracy": 0.1394168458878994, |
| "num_tokens": 3302010.0, |
| "step": 1845 |
| }, |
| { |
| "entropy": 6.28194146156311, |
| "epoch": 0.0951572666718103, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.0004167801210167081, |
| "loss": 6.0737, |
| "mean_token_accuracy": 0.13149803429841994, |
| "num_tokens": 3312307.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 6.298348474502563, |
| "epoch": 0.09541444847362601, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0004158634050882861, |
| "loss": 6.0619, |
| "mean_token_accuracy": 0.12632458582520484, |
| "num_tokens": 3321859.0, |
| "step": 1855 |
| }, |
| { |
| "entropy": 6.352298450469971, |
| "epoch": 0.0956716302754417, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.0004149428273184569, |
| "loss": 6.0642, |
| "mean_token_accuracy": 0.13412729203701018, |
| "num_tokens": 3331727.0, |
| "step": 1860 |
| }, |
| { |
| "entropy": 6.263995742797851, |
| "epoch": 0.09592881207725741, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004140184129453253, |
| "loss": 5.9321, |
| "mean_token_accuracy": 0.13026233464479448, |
| "num_tokens": 3340449.0, |
| "step": 1865 |
| }, |
| { |
| "entropy": 6.30117506980896, |
| "epoch": 0.09618599387907312, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.000413090187312178, |
| "loss": 5.9886, |
| "mean_token_accuracy": 0.13512412831187248, |
| "num_tokens": 3349374.0, |
| "step": 1870 |
| }, |
| { |
| "entropy": 6.266588401794434, |
| "epoch": 0.09644317568088882, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.0004121581758667898, |
| "loss": 6.0195, |
| "mean_token_accuracy": 0.13124436065554618, |
| "num_tokens": 3358792.0, |
| "step": 1875 |
| }, |
| { |
| "entropy": 6.184923267364502, |
| "epoch": 0.09670035748270453, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00041122240416072533, |
| "loss": 5.9184, |
| "mean_token_accuracy": 0.13883327171206475, |
| "num_tokens": 3368066.0, |
| "step": 1880 |
| }, |
| { |
| "entropy": 6.24156346321106, |
| "epoch": 0.09695753928452022, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004102828978486385, |
| "loss": 5.954, |
| "mean_token_accuracy": 0.13969675824046135, |
| "num_tokens": 3376872.0, |
| "step": 1885 |
| }, |
| { |
| "entropy": 6.241713762283325, |
| "epoch": 0.09721472108633593, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004093396826875695, |
| "loss": 5.9471, |
| "mean_token_accuracy": 0.13266203328967094, |
| "num_tokens": 3385851.0, |
| "step": 1890 |
| }, |
| { |
| "entropy": 6.231948804855347, |
| "epoch": 0.09747190288815163, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00040839278453623837, |
| "loss": 6.0056, |
| "mean_token_accuracy": 0.1346826121211052, |
| "num_tokens": 3395263.0, |
| "step": 1895 |
| }, |
| { |
| "entropy": 6.228415203094483, |
| "epoch": 0.09772908468996734, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004074422293543363, |
| "loss": 6.0445, |
| "mean_token_accuracy": 0.13088179305195807, |
| "num_tokens": 3404814.0, |
| "step": 1900 |
| }, |
| { |
| "entropy": 6.329216241836548, |
| "epoch": 0.09798626649178305, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004064880432018137, |
| "loss": 6.1074, |
| "mean_token_accuracy": 0.1315300315618515, |
| "num_tokens": 3413822.0, |
| "step": 1905 |
| }, |
| { |
| "entropy": 6.301573801040649, |
| "epoch": 0.09824344829359874, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00040553025223816615, |
| "loss": 6.0124, |
| "mean_token_accuracy": 0.13628942891955376, |
| "num_tokens": 3422318.0, |
| "step": 1910 |
| }, |
| { |
| "entropy": 6.206828165054321, |
| "epoch": 0.09850063009541445, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00040456888272171653, |
| "loss": 5.9329, |
| "mean_token_accuracy": 0.13764095306396484, |
| "num_tokens": 3431066.0, |
| "step": 1915 |
| }, |
| { |
| "entropy": 6.251052141189575, |
| "epoch": 0.09875781189723015, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00040360396100889577, |
| "loss": 5.9485, |
| "mean_token_accuracy": 0.1366151362657547, |
| "num_tokens": 3439822.0, |
| "step": 1920 |
| }, |
| { |
| "entropy": 6.248995113372803, |
| "epoch": 0.09901499369904586, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004026355135535202, |
| "loss": 6.0449, |
| "mean_token_accuracy": 0.13020109459757806, |
| "num_tokens": 3449430.0, |
| "step": 1925 |
| }, |
| { |
| "entropy": 6.266049480438232, |
| "epoch": 0.09927217550086156, |
| "grad_norm": 1.125, |
| "learning_rate": 0.000401663566906066, |
| "loss": 5.9646, |
| "mean_token_accuracy": 0.13827199935913087, |
| "num_tokens": 3457519.0, |
| "step": 1930 |
| }, |
| { |
| "entropy": 6.185720539093017, |
| "epoch": 0.09952935730267726, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00040068814771294134, |
| "loss": 5.8726, |
| "mean_token_accuracy": 0.13870462104678155, |
| "num_tokens": 3466328.0, |
| "step": 1935 |
| }, |
| { |
| "entropy": 6.133827590942383, |
| "epoch": 0.09978653910449296, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0003997092827157562, |
| "loss": 5.8982, |
| "mean_token_accuracy": 0.1401980772614479, |
| "num_tokens": 3475821.0, |
| "step": 1940 |
| }, |
| { |
| "entropy": 6.2277813911437985, |
| "epoch": 0.10004372090630867, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000398726998750589, |
| "loss": 5.9881, |
| "mean_token_accuracy": 0.1336817152798176, |
| "num_tokens": 3484902.0, |
| "step": 1945 |
| }, |
| { |
| "entropy": 6.296745872497558, |
| "epoch": 0.10030090270812438, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00039774132274725076, |
| "loss": 6.0906, |
| "mean_token_accuracy": 0.12511072233319281, |
| "num_tokens": 3494951.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 6.261813402175903, |
| "epoch": 0.10055808450994008, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00039675228172854707, |
| "loss": 5.9523, |
| "mean_token_accuracy": 0.14045180454850198, |
| "num_tokens": 3503688.0, |
| "step": 1955 |
| }, |
| { |
| "entropy": 6.224357604980469, |
| "epoch": 0.10081526631175577, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0003957599028095371, |
| "loss": 5.9971, |
| "mean_token_accuracy": 0.13452794998884202, |
| "num_tokens": 3512337.0, |
| "step": 1960 |
| }, |
| { |
| "entropy": 6.310317754745483, |
| "epoch": 0.10107244811357148, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00039476421319679017, |
| "loss": 6.0837, |
| "mean_token_accuracy": 0.1328693710267544, |
| "num_tokens": 3521370.0, |
| "step": 1965 |
| }, |
| { |
| "entropy": 6.193576526641846, |
| "epoch": 0.10132962991538719, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00039376524018764, |
| "loss": 5.8877, |
| "mean_token_accuracy": 0.14604497849941253, |
| "num_tokens": 3530225.0, |
| "step": 1970 |
| }, |
| { |
| "entropy": 6.205514764785766, |
| "epoch": 0.1015868117172029, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00039276301116943616, |
| "loss": 5.9687, |
| "mean_token_accuracy": 0.14247402623295785, |
| "num_tokens": 3538843.0, |
| "step": 1975 |
| }, |
| { |
| "entropy": 6.286650371551514, |
| "epoch": 0.1018439935190186, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0003917575536187936, |
| "loss": 5.9858, |
| "mean_token_accuracy": 0.1346484936773777, |
| "num_tokens": 3547833.0, |
| "step": 1980 |
| }, |
| { |
| "entropy": 6.177884578704834, |
| "epoch": 0.10210117532083429, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00039074889510083894, |
| "loss": 5.9072, |
| "mean_token_accuracy": 0.1447339817881584, |
| "num_tokens": 3556021.0, |
| "step": 1985 |
| }, |
| { |
| "entropy": 6.251054954528809, |
| "epoch": 0.10235835712265, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.00038973706326845495, |
| "loss": 5.8984, |
| "mean_token_accuracy": 0.13767489194869995, |
| "num_tokens": 3564483.0, |
| "step": 1990 |
| }, |
| { |
| "entropy": 6.208160734176635, |
| "epoch": 0.1026155389244657, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0003887220858615225, |
| "loss": 5.9995, |
| "mean_token_accuracy": 0.12966525331139564, |
| "num_tokens": 3574761.0, |
| "step": 1995 |
| }, |
| { |
| "entropy": 6.26411509513855, |
| "epoch": 0.10287272072628141, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0003877039907061597, |
| "loss": 6.0126, |
| "mean_token_accuracy": 0.13828732147812844, |
| "num_tokens": 3583401.0, |
| "step": 2000 |
| } |
| ], |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 717815269785600.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
