| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.025718180181570353, |
| "eval_steps": 500, |
| "global_step": 500, |
| "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 |
| } |
| ], |
| "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": 179847569571840.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
