| { | |
| "best_metric": 0.8409090909090909, | |
| "best_model_checkpoint": "CTMAE-P2-V3-3G-S5/checkpoint-3537", | |
| "epoch": 49.01246153846154, | |
| "eval_steps": 500, | |
| "global_step": 6500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015384615384615385, | |
| "grad_norm": 5.810204982757568, | |
| "learning_rate": 1.5384615384615387e-07, | |
| "loss": 0.6966, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003076923076923077, | |
| "grad_norm": 5.34403133392334, | |
| "learning_rate": 3.0769230769230774e-07, | |
| "loss": 0.6957, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004615384615384616, | |
| "grad_norm": 5.617316246032715, | |
| "learning_rate": 4.615384615384616e-07, | |
| "loss": 0.6932, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006153846153846154, | |
| "grad_norm": 2.0365242958068848, | |
| "learning_rate": 6.153846153846155e-07, | |
| "loss": 0.7001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007692307692307693, | |
| "grad_norm": 5.360293865203857, | |
| "learning_rate": 7.692307692307694e-07, | |
| "loss": 0.6989, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009230769230769232, | |
| "grad_norm": 1.7482308149337769, | |
| "learning_rate": 9.230769230769232e-07, | |
| "loss": 0.6685, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010769230769230769, | |
| "grad_norm": 4.691122055053711, | |
| "learning_rate": 1.076923076923077e-06, | |
| "loss": 0.6702, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.012307692307692308, | |
| "grad_norm": 6.402479648590088, | |
| "learning_rate": 1.230769230769231e-06, | |
| "loss": 0.6464, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013846153846153847, | |
| "grad_norm": 4.434910774230957, | |
| "learning_rate": 1.3846153846153848e-06, | |
| "loss": 0.646, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.015384615384615385, | |
| "grad_norm": 5.054368495941162, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 0.6498, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016923076923076923, | |
| "grad_norm": 6.029448509216309, | |
| "learning_rate": 1.6923076923076926e-06, | |
| "loss": 0.6759, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.018461538461538463, | |
| "grad_norm": 4.079063415527344, | |
| "learning_rate": 1.8461538461538465e-06, | |
| "loss": 0.6287, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 4.554880619049072, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6815, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.020153846153846154, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_loss": 0.704614520072937, | |
| "eval_runtime": 18.6209, | |
| "eval_samples_per_second": 2.363, | |
| "eval_steps_per_second": 1.181, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.0013846153846153, | |
| "grad_norm": 2.203511953353882, | |
| "learning_rate": 2.153846153846154e-06, | |
| "loss": 0.6238, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.002923076923077, | |
| "grad_norm": 2.705735683441162, | |
| "learning_rate": 2.307692307692308e-06, | |
| "loss": 0.6499, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0044615384615385, | |
| "grad_norm": 2.7830448150634766, | |
| "learning_rate": 2.461538461538462e-06, | |
| "loss": 0.7487, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.006, | |
| "grad_norm": 2.7263176441192627, | |
| "learning_rate": 2.615384615384616e-06, | |
| "loss": 0.6673, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0075384615384615, | |
| "grad_norm": 1.3468457460403442, | |
| "learning_rate": 2.7692307692307697e-06, | |
| "loss": 0.6768, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.009076923076923, | |
| "grad_norm": 1.9126865863800049, | |
| "learning_rate": 2.9230769230769236e-06, | |
| "loss": 0.6931, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0106153846153847, | |
| "grad_norm": 4.584698677062988, | |
| "learning_rate": 3.0769230769230774e-06, | |
| "loss": 0.6489, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0121538461538462, | |
| "grad_norm": 4.968081951141357, | |
| "learning_rate": 3.2307692307692313e-06, | |
| "loss": 0.6533, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.0136923076923077, | |
| "grad_norm": 3.368180513381958, | |
| "learning_rate": 3.384615384615385e-06, | |
| "loss": 0.6186, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0152307692307692, | |
| "grad_norm": 10.968172073364258, | |
| "learning_rate": 3.538461538461539e-06, | |
| "loss": 0.4942, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0167692307692309, | |
| "grad_norm": 10.32033920288086, | |
| "learning_rate": 3.692307692307693e-06, | |
| "loss": 0.7527, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0183076923076924, | |
| "grad_norm": 4.100514888763428, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.749, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0198461538461538, | |
| "grad_norm": 4.187838554382324, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.4922, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0201538461538462, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_loss": 0.9263423681259155, | |
| "eval_runtime": 17.8777, | |
| "eval_samples_per_second": 2.461, | |
| "eval_steps_per_second": 1.231, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.0012307692307694, | |
| "grad_norm": 30.669509887695312, | |
| "learning_rate": 4.1538461538461545e-06, | |
| "loss": 1.1575, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.0027692307692306, | |
| "grad_norm": 6.6476850509643555, | |
| "learning_rate": 4.307692307692308e-06, | |
| "loss": 0.6512, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0043076923076923, | |
| "grad_norm": 10.883289337158203, | |
| "learning_rate": 4.461538461538462e-06, | |
| "loss": 0.7414, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.005846153846154, | |
| "grad_norm": 2.7271006107330322, | |
| "learning_rate": 4.615384615384616e-06, | |
| "loss": 0.6637, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0073846153846153, | |
| "grad_norm": 9.182909965515137, | |
| "learning_rate": 4.76923076923077e-06, | |
| "loss": 0.5982, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.008923076923077, | |
| "grad_norm": 9.62547492980957, | |
| "learning_rate": 4.923076923076924e-06, | |
| "loss": 0.5303, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.0104615384615383, | |
| "grad_norm": 7.861083030700684, | |
| "learning_rate": 5.076923076923077e-06, | |
| "loss": 0.6198, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.012, | |
| "grad_norm": 1.9585870504379272, | |
| "learning_rate": 5.230769230769232e-06, | |
| "loss": 0.9137, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.0135384615384617, | |
| "grad_norm": 2.116058349609375, | |
| "learning_rate": 5.384615384615385e-06, | |
| "loss": 0.7773, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.015076923076923, | |
| "grad_norm": 7.358627796173096, | |
| "learning_rate": 5.538461538461539e-06, | |
| "loss": 1.0629, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.0166153846153847, | |
| "grad_norm": 3.6382033824920654, | |
| "learning_rate": 5.692307692307692e-06, | |
| "loss": 0.8571, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.018153846153846, | |
| "grad_norm": 4.809838771820068, | |
| "learning_rate": 5.846153846153847e-06, | |
| "loss": 0.6019, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0196923076923077, | |
| "grad_norm": 11.813170433044434, | |
| "learning_rate": 6e-06, | |
| "loss": 0.6484, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.020153846153846, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_loss": 0.7719244360923767, | |
| "eval_runtime": 18.0787, | |
| "eval_samples_per_second": 2.434, | |
| "eval_steps_per_second": 1.217, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 3.001076923076923, | |
| "grad_norm": 5.041421890258789, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 0.7179, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.0026153846153845, | |
| "grad_norm": 10.298470497131348, | |
| "learning_rate": 6.307692307692308e-06, | |
| "loss": 0.4981, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.004153846153846, | |
| "grad_norm": 2.1408026218414307, | |
| "learning_rate": 6.461538461538463e-06, | |
| "loss": 0.5428, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.005692307692308, | |
| "grad_norm": 9.490102767944336, | |
| "learning_rate": 6.615384615384616e-06, | |
| "loss": 0.6698, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.007230769230769, | |
| "grad_norm": 0.6581586003303528, | |
| "learning_rate": 6.76923076923077e-06, | |
| "loss": 0.4011, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.008769230769231, | |
| "grad_norm": 25.044408798217773, | |
| "learning_rate": 6.923076923076923e-06, | |
| "loss": 1.319, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.010307692307692, | |
| "grad_norm": 23.925674438476562, | |
| "learning_rate": 7.076923076923078e-06, | |
| "loss": 1.0828, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.011846153846154, | |
| "grad_norm": 8.783576011657715, | |
| "learning_rate": 7.230769230769231e-06, | |
| "loss": 0.6276, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.0133846153846156, | |
| "grad_norm": 6.744044780731201, | |
| "learning_rate": 7.384615384615386e-06, | |
| "loss": 0.6758, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.014923076923077, | |
| "grad_norm": 4.657675266265869, | |
| "learning_rate": 7.538461538461539e-06, | |
| "loss": 0.7287, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.0164615384615385, | |
| "grad_norm": 6.373889446258545, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.6685, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.018, | |
| "grad_norm": 3.8067166805267334, | |
| "learning_rate": 7.846153846153847e-06, | |
| "loss": 0.7607, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.0195384615384615, | |
| "grad_norm": 5.991115570068359, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.6707, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.020153846153846, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_loss": 0.7503156065940857, | |
| "eval_runtime": 17.9884, | |
| "eval_samples_per_second": 2.446, | |
| "eval_steps_per_second": 1.223, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 4.000923076923077, | |
| "grad_norm": 3.7660489082336426, | |
| "learning_rate": 8.153846153846154e-06, | |
| "loss": 0.4558, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.002461538461539, | |
| "grad_norm": 40.0063591003418, | |
| "learning_rate": 8.307692307692309e-06, | |
| "loss": 1.0401, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.004, | |
| "grad_norm": 17.381956100463867, | |
| "learning_rate": 8.461538461538462e-06, | |
| "loss": 0.7536, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.005538461538461, | |
| "grad_norm": 3.14517879486084, | |
| "learning_rate": 8.615384615384617e-06, | |
| "loss": 1.1134, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.007076923076923, | |
| "grad_norm": 8.866881370544434, | |
| "learning_rate": 8.76923076923077e-06, | |
| "loss": 0.7139, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.008615384615385, | |
| "grad_norm": 8.189030647277832, | |
| "learning_rate": 8.923076923076925e-06, | |
| "loss": 0.5891, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.010153846153846, | |
| "grad_norm": 6.187677383422852, | |
| "learning_rate": 9.076923076923078e-06, | |
| "loss": 0.9197, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.011692307692308, | |
| "grad_norm": 8.224255561828613, | |
| "learning_rate": 9.230769230769232e-06, | |
| "loss": 0.6918, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.013230769230769, | |
| "grad_norm": 14.158226013183594, | |
| "learning_rate": 9.384615384615385e-06, | |
| "loss": 0.585, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.014769230769231, | |
| "grad_norm": 9.437602996826172, | |
| "learning_rate": 9.53846153846154e-06, | |
| "loss": 1.131, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.016307692307692, | |
| "grad_norm": 3.3406591415405273, | |
| "learning_rate": 9.692307692307693e-06, | |
| "loss": 0.6339, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.017846153846154, | |
| "grad_norm": 19.734560012817383, | |
| "learning_rate": 9.846153846153848e-06, | |
| "loss": 0.6134, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.019384615384616, | |
| "grad_norm": 7.464200973510742, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1086, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.020153846153846, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_loss": 0.7398293018341064, | |
| "eval_runtime": 17.7463, | |
| "eval_samples_per_second": 2.479, | |
| "eval_steps_per_second": 1.24, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 5.00076923076923, | |
| "grad_norm": 4.659960746765137, | |
| "learning_rate": 9.982905982905984e-06, | |
| "loss": 0.6226, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.002307692307692, | |
| "grad_norm": 2.4036738872528076, | |
| "learning_rate": 9.965811965811966e-06, | |
| "loss": 0.5823, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.003846153846154, | |
| "grad_norm": 9.837275505065918, | |
| "learning_rate": 9.94871794871795e-06, | |
| "loss": 0.905, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.0053846153846155, | |
| "grad_norm": 12.314562797546387, | |
| "learning_rate": 9.931623931623933e-06, | |
| "loss": 0.7813, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.006923076923077, | |
| "grad_norm": 2.771672487258911, | |
| "learning_rate": 9.914529914529915e-06, | |
| "loss": 0.8457, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.008461538461538, | |
| "grad_norm": 2.72385835647583, | |
| "learning_rate": 9.897435897435899e-06, | |
| "loss": 0.5788, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "grad_norm": 4.614132881164551, | |
| "learning_rate": 9.880341880341882e-06, | |
| "loss": 0.6982, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.0115384615384615, | |
| "grad_norm": 3.8813230991363525, | |
| "learning_rate": 9.863247863247864e-06, | |
| "loss": 0.678, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.013076923076923, | |
| "grad_norm": 4.125026702880859, | |
| "learning_rate": 9.846153846153848e-06, | |
| "loss": 0.6089, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.014615384615385, | |
| "grad_norm": 3.6650466918945312, | |
| "learning_rate": 9.82905982905983e-06, | |
| "loss": 0.6301, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.016153846153846, | |
| "grad_norm": 3.780909776687622, | |
| "learning_rate": 9.811965811965812e-06, | |
| "loss": 0.6756, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.0176923076923075, | |
| "grad_norm": 5.456735134124756, | |
| "learning_rate": 9.794871794871795e-06, | |
| "loss": 0.6356, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.019230769230769, | |
| "grad_norm": 6.2561516761779785, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 0.6679, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.020153846153846, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_loss": 0.6243553161621094, | |
| "eval_runtime": 17.6868, | |
| "eval_samples_per_second": 2.488, | |
| "eval_steps_per_second": 1.244, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 6.000615384615385, | |
| "grad_norm": 7.825150012969971, | |
| "learning_rate": 9.76068376068376e-06, | |
| "loss": 0.5966, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.002153846153846, | |
| "grad_norm": 1.7464479207992554, | |
| "learning_rate": 9.743589743589744e-06, | |
| "loss": 0.5901, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.003692307692308, | |
| "grad_norm": 3.977769136428833, | |
| "learning_rate": 9.726495726495728e-06, | |
| "loss": 0.8718, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.005230769230769, | |
| "grad_norm": 8.31023120880127, | |
| "learning_rate": 9.70940170940171e-06, | |
| "loss": 0.6587, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.006769230769231, | |
| "grad_norm": 1.0462722778320312, | |
| "learning_rate": 9.692307692307693e-06, | |
| "loss": 0.7785, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.008307692307692, | |
| "grad_norm": 28.682655334472656, | |
| "learning_rate": 9.675213675213677e-06, | |
| "loss": 1.3539, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.009846153846154, | |
| "grad_norm": 4.634757041931152, | |
| "learning_rate": 9.658119658119659e-06, | |
| "loss": 0.6419, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.011384615384616, | |
| "grad_norm": 7.105140209197998, | |
| "learning_rate": 9.641025641025642e-06, | |
| "loss": 0.7533, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.012923076923077, | |
| "grad_norm": 4.506667137145996, | |
| "learning_rate": 9.623931623931626e-06, | |
| "loss": 0.6307, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.014461538461538, | |
| "grad_norm": 2.976381540298462, | |
| "learning_rate": 9.606837606837607e-06, | |
| "loss": 0.7824, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.016, | |
| "grad_norm": 7.117905616760254, | |
| "learning_rate": 9.589743589743591e-06, | |
| "loss": 0.4523, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.017538461538462, | |
| "grad_norm": 12.100445747375488, | |
| "learning_rate": 9.572649572649575e-06, | |
| "loss": 1.077, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.019076923076923, | |
| "grad_norm": 6.016343116760254, | |
| "learning_rate": 9.555555555555556e-06, | |
| "loss": 0.7521, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.020153846153846, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_loss": 0.7773373126983643, | |
| "eval_runtime": 17.8043, | |
| "eval_samples_per_second": 2.471, | |
| "eval_steps_per_second": 1.236, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 7.000461538461538, | |
| "grad_norm": 4.935750961303711, | |
| "learning_rate": 9.53846153846154e-06, | |
| "loss": 0.5827, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 7.002, | |
| "grad_norm": 3.738483190536499, | |
| "learning_rate": 9.521367521367522e-06, | |
| "loss": 0.6652, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 7.0035384615384615, | |
| "grad_norm": 4.6160569190979, | |
| "learning_rate": 9.504273504273504e-06, | |
| "loss": 0.739, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 7.005076923076923, | |
| "grad_norm": 8.112672805786133, | |
| "learning_rate": 9.487179487179487e-06, | |
| "loss": 0.7718, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.006615384615385, | |
| "grad_norm": 5.820714473724365, | |
| "learning_rate": 9.470085470085471e-06, | |
| "loss": 0.6709, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.008153846153846, | |
| "grad_norm": 7.109189987182617, | |
| "learning_rate": 9.452991452991453e-06, | |
| "loss": 0.6198, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.0096923076923074, | |
| "grad_norm": 7.797623634338379, | |
| "learning_rate": 9.435897435897436e-06, | |
| "loss": 0.6435, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.011230769230769, | |
| "grad_norm": 25.773204803466797, | |
| "learning_rate": 9.41880341880342e-06, | |
| "loss": 0.9488, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 7.012769230769231, | |
| "grad_norm": 1.7766735553741455, | |
| "learning_rate": 9.401709401709402e-06, | |
| "loss": 0.8984, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.014307692307693, | |
| "grad_norm": 1.582926869392395, | |
| "learning_rate": 9.384615384615385e-06, | |
| "loss": 0.7321, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.015846153846154, | |
| "grad_norm": 6.80787992477417, | |
| "learning_rate": 9.367521367521369e-06, | |
| "loss": 0.5868, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.017384615384615, | |
| "grad_norm": 14.777807235717773, | |
| "learning_rate": 9.35042735042735e-06, | |
| "loss": 0.6512, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.018923076923077, | |
| "grad_norm": 0.8783546686172485, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 1.7822, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.020153846153846, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_loss": 1.4883025884628296, | |
| "eval_runtime": 16.9776, | |
| "eval_samples_per_second": 2.592, | |
| "eval_steps_per_second": 1.296, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 8.000307692307691, | |
| "grad_norm": 0.5634208917617798, | |
| "learning_rate": 9.316239316239318e-06, | |
| "loss": 0.7821, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 8.001846153846154, | |
| "grad_norm": 0.45926526188850403, | |
| "learning_rate": 9.2991452991453e-06, | |
| "loss": 1.0905, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 8.003384615384615, | |
| "grad_norm": 0.7779825329780579, | |
| "learning_rate": 9.282051282051283e-06, | |
| "loss": 1.5414, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 8.004923076923077, | |
| "grad_norm": 0.18315431475639343, | |
| "learning_rate": 9.264957264957267e-06, | |
| "loss": 0.2314, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.006461538461538, | |
| "grad_norm": 19.190664291381836, | |
| "learning_rate": 9.247863247863249e-06, | |
| "loss": 2.8683, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 8.008, | |
| "grad_norm": 2.669875144958496, | |
| "learning_rate": 9.230769230769232e-06, | |
| "loss": 1.084, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.009538461538462, | |
| "grad_norm": 4.050235271453857, | |
| "learning_rate": 9.213675213675214e-06, | |
| "loss": 0.6252, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.011076923076923, | |
| "grad_norm": 2.6902151107788086, | |
| "learning_rate": 9.196581196581196e-06, | |
| "loss": 0.4586, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.012615384615385, | |
| "grad_norm": 1.493703842163086, | |
| "learning_rate": 9.17948717948718e-06, | |
| "loss": 0.7121, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 8.014153846153846, | |
| "grad_norm": 33.15100860595703, | |
| "learning_rate": 9.162393162393163e-06, | |
| "loss": 0.8607, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 8.015692307692309, | |
| "grad_norm": 76.1461410522461, | |
| "learning_rate": 9.145299145299145e-06, | |
| "loss": 0.8259, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.01723076923077, | |
| "grad_norm": 13.362715721130371, | |
| "learning_rate": 9.128205128205129e-06, | |
| "loss": 0.7303, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.01876923076923, | |
| "grad_norm": 49.75516128540039, | |
| "learning_rate": 9.111111111111112e-06, | |
| "loss": 0.7714, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.020153846153846, | |
| "eval_accuracy": 0.5454545454545454, | |
| "eval_loss": 1.068182110786438, | |
| "eval_runtime": 17.2061, | |
| "eval_samples_per_second": 2.557, | |
| "eval_steps_per_second": 1.279, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 9.000153846153847, | |
| "grad_norm": 15.31894588470459, | |
| "learning_rate": 9.094017094017094e-06, | |
| "loss": 0.3311, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 9.001692307692307, | |
| "grad_norm": 14.928643226623535, | |
| "learning_rate": 9.076923076923078e-06, | |
| "loss": 1.1394, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 9.00323076923077, | |
| "grad_norm": 0.79338538646698, | |
| "learning_rate": 9.059829059829061e-06, | |
| "loss": 0.7976, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.00476923076923, | |
| "grad_norm": 9.812045097351074, | |
| "learning_rate": 9.042735042735043e-06, | |
| "loss": 0.9871, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 9.006307692307692, | |
| "grad_norm": 3.9193389415740967, | |
| "learning_rate": 9.025641025641027e-06, | |
| "loss": 0.565, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 9.007846153846154, | |
| "grad_norm": 16.645978927612305, | |
| "learning_rate": 9.00854700854701e-06, | |
| "loss": 0.802, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 9.009384615384615, | |
| "grad_norm": 6.744492530822754, | |
| "learning_rate": 8.991452991452992e-06, | |
| "loss": 0.5488, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.010923076923078, | |
| "grad_norm": 22.02034568786621, | |
| "learning_rate": 8.974358974358976e-06, | |
| "loss": 0.6238, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 9.012461538461539, | |
| "grad_norm": 0.5248557329177856, | |
| "learning_rate": 8.957264957264959e-06, | |
| "loss": 0.5953, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 9.014, | |
| "grad_norm": 3.465864419937134, | |
| "learning_rate": 8.940170940170941e-06, | |
| "loss": 1.2326, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 9.015538461538462, | |
| "grad_norm": 4.062889575958252, | |
| "learning_rate": 8.923076923076925e-06, | |
| "loss": 1.1122, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.017076923076923, | |
| "grad_norm": 11.823551177978516, | |
| "learning_rate": 8.905982905982906e-06, | |
| "loss": 0.6453, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.018615384615385, | |
| "grad_norm": 16.7249813079834, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.6532, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.020153846153846, | |
| "grad_norm": 3.8529834747314453, | |
| "learning_rate": 8.871794871794872e-06, | |
| "loss": 0.5244, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.020153846153846, | |
| "eval_accuracy": 0.5227272727272727, | |
| "eval_loss": 0.7003490924835205, | |
| "eval_runtime": 17.3334, | |
| "eval_samples_per_second": 2.538, | |
| "eval_steps_per_second": 1.269, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 10.00153846153846, | |
| "grad_norm": 12.951416969299316, | |
| "learning_rate": 8.854700854700855e-06, | |
| "loss": 0.5831, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 10.003076923076923, | |
| "grad_norm": 56.81121826171875, | |
| "learning_rate": 8.837606837606837e-06, | |
| "loss": 0.6243, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 10.004615384615384, | |
| "grad_norm": 43.745819091796875, | |
| "learning_rate": 8.820512820512821e-06, | |
| "loss": 0.9341, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 10.006153846153847, | |
| "grad_norm": 24.25783348083496, | |
| "learning_rate": 8.803418803418804e-06, | |
| "loss": 0.5313, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 10.007692307692308, | |
| "grad_norm": 76.15835571289062, | |
| "learning_rate": 8.786324786324786e-06, | |
| "loss": 0.8511, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 10.009230769230768, | |
| "grad_norm": 0.23354579508304596, | |
| "learning_rate": 8.76923076923077e-06, | |
| "loss": 0.6703, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 10.010769230769231, | |
| "grad_norm": 18.77838897705078, | |
| "learning_rate": 8.752136752136753e-06, | |
| "loss": 0.7762, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 10.012307692307692, | |
| "grad_norm": 12.687274932861328, | |
| "learning_rate": 8.735042735042735e-06, | |
| "loss": 0.5625, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 10.013846153846155, | |
| "grad_norm": 8.95459270477295, | |
| "learning_rate": 8.717948717948719e-06, | |
| "loss": 0.4821, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 10.015384615384615, | |
| "grad_norm": 67.87884521484375, | |
| "learning_rate": 8.700854700854702e-06, | |
| "loss": 0.6527, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 10.016923076923076, | |
| "grad_norm": 34.49333190917969, | |
| "learning_rate": 8.683760683760684e-06, | |
| "loss": 0.8536, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 10.018461538461539, | |
| "grad_norm": 2.0554018020629883, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 0.5441, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "grad_norm": 0.20849908888339996, | |
| "learning_rate": 8.649572649572651e-06, | |
| "loss": 0.7346, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.020153846153846, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0285073518753052, | |
| "eval_runtime": 17.2208, | |
| "eval_samples_per_second": 2.555, | |
| "eval_steps_per_second": 1.278, | |
| "step": 1441 | |
| }, | |
| { | |
| "epoch": 11.001384615384616, | |
| "grad_norm": 61.31785583496094, | |
| "learning_rate": 8.632478632478633e-06, | |
| "loss": 1.3833, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 11.002923076923077, | |
| "grad_norm": 1.4455043077468872, | |
| "learning_rate": 8.615384615384617e-06, | |
| "loss": 0.6753, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 11.004461538461538, | |
| "grad_norm": 50.34857940673828, | |
| "learning_rate": 8.598290598290599e-06, | |
| "loss": 0.6089, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 11.006, | |
| "grad_norm": 11.618597030639648, | |
| "learning_rate": 8.58119658119658e-06, | |
| "loss": 0.9113, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 11.007538461538461, | |
| "grad_norm": 2.7635881900787354, | |
| "learning_rate": 8.564102564102564e-06, | |
| "loss": 0.5073, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 11.009076923076924, | |
| "grad_norm": 106.7019271850586, | |
| "learning_rate": 8.547008547008548e-06, | |
| "loss": 0.7127, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 11.010615384615384, | |
| "grad_norm": 10.445947647094727, | |
| "learning_rate": 8.52991452991453e-06, | |
| "loss": 0.6418, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 11.012153846153845, | |
| "grad_norm": 0.2164224237203598, | |
| "learning_rate": 8.512820512820513e-06, | |
| "loss": 0.2935, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 11.013692307692308, | |
| "grad_norm": 28.352243423461914, | |
| "learning_rate": 8.495726495726497e-06, | |
| "loss": 1.3631, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 11.015230769230769, | |
| "grad_norm": 9.945635795593262, | |
| "learning_rate": 8.478632478632479e-06, | |
| "loss": 0.4417, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 11.016769230769231, | |
| "grad_norm": 21.67668342590332, | |
| "learning_rate": 8.461538461538462e-06, | |
| "loss": 0.5417, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 11.018307692307692, | |
| "grad_norm": 2.356503486633301, | |
| "learning_rate": 8.444444444444446e-06, | |
| "loss": 0.518, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 11.019846153846153, | |
| "grad_norm": 0.3581185042858124, | |
| "learning_rate": 8.427350427350428e-06, | |
| "loss": 0.4019, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 11.020153846153846, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 0.6360843181610107, | |
| "eval_runtime": 17.2623, | |
| "eval_samples_per_second": 2.549, | |
| "eval_steps_per_second": 1.274, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 12.00123076923077, | |
| "grad_norm": 34.936927795410156, | |
| "learning_rate": 8.410256410256411e-06, | |
| "loss": 0.6777, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 12.00276923076923, | |
| "grad_norm": 0.0466473251581192, | |
| "learning_rate": 8.393162393162395e-06, | |
| "loss": 0.6172, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 12.004307692307693, | |
| "grad_norm": 112.4150619506836, | |
| "learning_rate": 8.376068376068377e-06, | |
| "loss": 0.5366, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 12.005846153846154, | |
| "grad_norm": 17.809642791748047, | |
| "learning_rate": 8.35897435897436e-06, | |
| "loss": 0.5974, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 12.007384615384616, | |
| "grad_norm": 73.79551696777344, | |
| "learning_rate": 8.341880341880344e-06, | |
| "loss": 0.6061, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 12.008923076923077, | |
| "grad_norm": 46.43046569824219, | |
| "learning_rate": 8.324786324786326e-06, | |
| "loss": 0.5854, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 12.010461538461538, | |
| "grad_norm": 2.960542678833008, | |
| "learning_rate": 8.307692307692309e-06, | |
| "loss": 0.5776, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 12.012, | |
| "grad_norm": 10.185972213745117, | |
| "learning_rate": 8.290598290598293e-06, | |
| "loss": 0.4288, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 12.013538461538461, | |
| "grad_norm": 15.834644317626953, | |
| "learning_rate": 8.273504273504273e-06, | |
| "loss": 1.0885, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 12.015076923076924, | |
| "grad_norm": 22.562030792236328, | |
| "learning_rate": 8.256410256410256e-06, | |
| "loss": 0.5368, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 12.016615384615385, | |
| "grad_norm": 4.261492729187012, | |
| "learning_rate": 8.23931623931624e-06, | |
| "loss": 0.7391, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 12.018153846153846, | |
| "grad_norm": 27.466445922851562, | |
| "learning_rate": 8.222222222222222e-06, | |
| "loss": 0.6743, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 12.019692307692308, | |
| "grad_norm": 24.46636962890625, | |
| "learning_rate": 8.205128205128205e-06, | |
| "loss": 0.7769, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 12.020153846153846, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.4665856659412384, | |
| "eval_runtime": 17.1917, | |
| "eval_samples_per_second": 2.559, | |
| "eval_steps_per_second": 1.28, | |
| "step": 1703 | |
| }, | |
| { | |
| "epoch": 13.001076923076923, | |
| "grad_norm": 0.6057922840118408, | |
| "learning_rate": 8.188034188034189e-06, | |
| "loss": 0.2224, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 13.002615384615385, | |
| "grad_norm": 0.2505128085613251, | |
| "learning_rate": 8.17094017094017e-06, | |
| "loss": 0.3367, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 13.004153846153846, | |
| "grad_norm": 25.089702606201172, | |
| "learning_rate": 8.153846153846154e-06, | |
| "loss": 1.4928, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 13.005692307692307, | |
| "grad_norm": 37.51374816894531, | |
| "learning_rate": 8.136752136752138e-06, | |
| "loss": 0.4689, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 13.00723076923077, | |
| "grad_norm": 11.814014434814453, | |
| "learning_rate": 8.11965811965812e-06, | |
| "loss": 0.5317, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 13.00876923076923, | |
| "grad_norm": 24.946855545043945, | |
| "learning_rate": 8.102564102564103e-06, | |
| "loss": 0.388, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 13.010307692307693, | |
| "grad_norm": 3.4585928916931152, | |
| "learning_rate": 8.085470085470087e-06, | |
| "loss": 0.6089, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 13.011846153846154, | |
| "grad_norm": 19.342430114746094, | |
| "learning_rate": 8.068376068376069e-06, | |
| "loss": 1.0816, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 13.013384615384615, | |
| "grad_norm": 17.996641159057617, | |
| "learning_rate": 8.051282051282052e-06, | |
| "loss": 0.8705, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 13.014923076923077, | |
| "grad_norm": 2.2373054027557373, | |
| "learning_rate": 8.034188034188036e-06, | |
| "loss": 0.8107, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 13.016461538461538, | |
| "grad_norm": 23.976829528808594, | |
| "learning_rate": 8.017094017094018e-06, | |
| "loss": 0.3828, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 13.018, | |
| "grad_norm": 0.07417020201683044, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.479, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 13.019538461538462, | |
| "grad_norm": 74.26486206054688, | |
| "learning_rate": 7.982905982905985e-06, | |
| "loss": 0.6358, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 13.020153846153846, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 1.3154767751693726, | |
| "eval_runtime": 17.2177, | |
| "eval_samples_per_second": 2.556, | |
| "eval_steps_per_second": 1.278, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 14.000923076923076, | |
| "grad_norm": 69.15850830078125, | |
| "learning_rate": 7.965811965811967e-06, | |
| "loss": 0.6193, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 14.002461538461539, | |
| "grad_norm": 0.4998956322669983, | |
| "learning_rate": 7.948717948717949e-06, | |
| "loss": 0.3062, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 14.004, | |
| "grad_norm": 27.482421875, | |
| "learning_rate": 7.931623931623932e-06, | |
| "loss": 0.9816, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 14.005538461538462, | |
| "grad_norm": 12.180825233459473, | |
| "learning_rate": 7.914529914529914e-06, | |
| "loss": 0.6177, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 14.007076923076923, | |
| "grad_norm": 135.8071746826172, | |
| "learning_rate": 7.897435897435898e-06, | |
| "loss": 0.6007, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 14.008615384615384, | |
| "grad_norm": 73.042236328125, | |
| "learning_rate": 7.880341880341881e-06, | |
| "loss": 0.993, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 14.010153846153846, | |
| "grad_norm": 55.56059646606445, | |
| "learning_rate": 7.863247863247863e-06, | |
| "loss": 0.9033, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 14.011692307692307, | |
| "grad_norm": 71.79470825195312, | |
| "learning_rate": 7.846153846153847e-06, | |
| "loss": 1.048, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 14.01323076923077, | |
| "grad_norm": 35.1550407409668, | |
| "learning_rate": 7.82905982905983e-06, | |
| "loss": 1.0577, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 14.01476923076923, | |
| "grad_norm": 0.6700708866119385, | |
| "learning_rate": 7.811965811965812e-06, | |
| "loss": 0.8374, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 14.016307692307691, | |
| "grad_norm": 33.14726638793945, | |
| "learning_rate": 7.794871794871796e-06, | |
| "loss": 0.1462, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 14.017846153846154, | |
| "grad_norm": 2.53395938873291, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.5353, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 14.019384615384615, | |
| "grad_norm": 0.1720552295446396, | |
| "learning_rate": 7.760683760683761e-06, | |
| "loss": 0.5129, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 14.020153846153846, | |
| "eval_accuracy": 0.6818181818181818, | |
| "eval_loss": 1.148544192314148, | |
| "eval_runtime": 16.8196, | |
| "eval_samples_per_second": 2.616, | |
| "eval_steps_per_second": 1.308, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 15.000769230769231, | |
| "grad_norm": 46.41466522216797, | |
| "learning_rate": 7.743589743589745e-06, | |
| "loss": 0.5048, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 15.002307692307692, | |
| "grad_norm": 27.168472290039062, | |
| "learning_rate": 7.726495726495728e-06, | |
| "loss": 0.6371, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 15.003846153846155, | |
| "grad_norm": 62.12626647949219, | |
| "learning_rate": 7.70940170940171e-06, | |
| "loss": 0.528, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 15.005384615384616, | |
| "grad_norm": 13.014984130859375, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 1.2675, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 15.006923076923076, | |
| "grad_norm": 1.9063676595687866, | |
| "learning_rate": 7.675213675213677e-06, | |
| "loss": 0.3608, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 15.008461538461539, | |
| "grad_norm": 33.4384880065918, | |
| "learning_rate": 7.658119658119659e-06, | |
| "loss": 0.6791, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "grad_norm": 6.844511985778809, | |
| "learning_rate": 7.641025641025641e-06, | |
| "loss": 0.4935, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 15.011538461538462, | |
| "grad_norm": 0.04850053787231445, | |
| "learning_rate": 7.6239316239316244e-06, | |
| "loss": 0.8168, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 15.013076923076923, | |
| "grad_norm": 29.334993362426758, | |
| "learning_rate": 7.606837606837607e-06, | |
| "loss": 0.9169, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 15.014615384615384, | |
| "grad_norm": 0.04087604582309723, | |
| "learning_rate": 7.58974358974359e-06, | |
| "loss": 0.7592, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 15.016153846153847, | |
| "grad_norm": 1.3730835914611816, | |
| "learning_rate": 7.572649572649573e-06, | |
| "loss": 0.9987, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 15.017692307692307, | |
| "grad_norm": 39.87520980834961, | |
| "learning_rate": 7.555555555555556e-06, | |
| "loss": 0.6921, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 15.01923076923077, | |
| "grad_norm": 47.55777359008789, | |
| "learning_rate": 7.538461538461539e-06, | |
| "loss": 1.1003, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 15.020153846153846, | |
| "eval_accuracy": 0.7954545454545454, | |
| "eval_loss": 0.5101782083511353, | |
| "eval_runtime": 17.1161, | |
| "eval_samples_per_second": 2.571, | |
| "eval_steps_per_second": 1.285, | |
| "step": 2096 | |
| }, | |
| { | |
| "epoch": 16.000615384615383, | |
| "grad_norm": 126.17413330078125, | |
| "learning_rate": 7.521367521367522e-06, | |
| "loss": 1.1593, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 16.002153846153846, | |
| "grad_norm": 0.08472739905118942, | |
| "learning_rate": 7.504273504273505e-06, | |
| "loss": 0.8393, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 16.003692307692308, | |
| "grad_norm": 1.1038520336151123, | |
| "learning_rate": 7.487179487179488e-06, | |
| "loss": 0.1835, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 16.00523076923077, | |
| "grad_norm": 53.04530715942383, | |
| "learning_rate": 7.4700854700854706e-06, | |
| "loss": 0.7034, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 16.00676923076923, | |
| "grad_norm": 0.7304243445396423, | |
| "learning_rate": 7.452991452991454e-06, | |
| "loss": 0.927, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 16.008307692307692, | |
| "grad_norm": 31.025588989257812, | |
| "learning_rate": 7.435897435897437e-06, | |
| "loss": 1.0181, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 16.009846153846155, | |
| "grad_norm": 32.37491989135742, | |
| "learning_rate": 7.4188034188034196e-06, | |
| "loss": 0.839, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 16.011384615384614, | |
| "grad_norm": 2.9148964881896973, | |
| "learning_rate": 7.401709401709402e-06, | |
| "loss": 1.0666, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 16.012923076923077, | |
| "grad_norm": 32.19853591918945, | |
| "learning_rate": 7.384615384615386e-06, | |
| "loss": 0.8189, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 16.01446153846154, | |
| "grad_norm": 7.5891642570495605, | |
| "learning_rate": 7.3675213675213686e-06, | |
| "loss": 0.5958, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 16.016, | |
| "grad_norm": 0.05911834165453911, | |
| "learning_rate": 7.350427350427351e-06, | |
| "loss": 0.5345, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 16.01753846153846, | |
| "grad_norm": 51.03484344482422, | |
| "learning_rate": 7.333333333333333e-06, | |
| "loss": 0.6812, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 16.019076923076923, | |
| "grad_norm": 11.205198287963867, | |
| "learning_rate": 7.316239316239317e-06, | |
| "loss": 0.7943, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 16.020153846153846, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.6433805227279663, | |
| "eval_runtime": 17.2265, | |
| "eval_samples_per_second": 2.554, | |
| "eval_steps_per_second": 1.277, | |
| "step": 2227 | |
| }, | |
| { | |
| "epoch": 17.00046153846154, | |
| "grad_norm": 145.98776245117188, | |
| "learning_rate": 7.299145299145299e-06, | |
| "loss": 0.1759, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 17.002, | |
| "grad_norm": 50.61044692993164, | |
| "learning_rate": 7.282051282051282e-06, | |
| "loss": 0.388, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 17.00353846153846, | |
| "grad_norm": 2.3488080501556396, | |
| "learning_rate": 7.264957264957266e-06, | |
| "loss": 0.1006, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 17.005076923076924, | |
| "grad_norm": 11.469562530517578, | |
| "learning_rate": 7.247863247863248e-06, | |
| "loss": 1.2389, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 17.006615384615383, | |
| "grad_norm": 0.038995929062366486, | |
| "learning_rate": 7.230769230769231e-06, | |
| "loss": 0.8976, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 17.008153846153846, | |
| "grad_norm": 172.3754119873047, | |
| "learning_rate": 7.213675213675214e-06, | |
| "loss": 0.2172, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 17.00969230769231, | |
| "grad_norm": 54.93113327026367, | |
| "learning_rate": 7.196581196581197e-06, | |
| "loss": 1.4457, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 17.01123076923077, | |
| "grad_norm": 97.9874496459961, | |
| "learning_rate": 7.17948717948718e-06, | |
| "loss": 0.5764, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 17.01276923076923, | |
| "grad_norm": 14.170007705688477, | |
| "learning_rate": 7.162393162393163e-06, | |
| "loss": 0.4372, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 17.014307692307693, | |
| "grad_norm": 91.68878936767578, | |
| "learning_rate": 7.145299145299146e-06, | |
| "loss": 1.3001, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 17.015846153846155, | |
| "grad_norm": 0.1419920176267624, | |
| "learning_rate": 7.128205128205129e-06, | |
| "loss": 0.2408, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 17.017384615384614, | |
| "grad_norm": 1.228349208831787, | |
| "learning_rate": 7.111111111111112e-06, | |
| "loss": 0.5673, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 17.018923076923077, | |
| "grad_norm": 76.46228790283203, | |
| "learning_rate": 7.0940170940170945e-06, | |
| "loss": 0.363, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 17.020153846153846, | |
| "eval_accuracy": 0.7954545454545454, | |
| "eval_loss": 0.9531997442245483, | |
| "eval_runtime": 17.1872, | |
| "eval_samples_per_second": 2.56, | |
| "eval_steps_per_second": 1.28, | |
| "step": 2358 | |
| }, | |
| { | |
| "epoch": 18.000307692307693, | |
| "grad_norm": 110.68145751953125, | |
| "learning_rate": 7.076923076923078e-06, | |
| "loss": 0.6137, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 18.001846153846152, | |
| "grad_norm": 5.415543079376221, | |
| "learning_rate": 7.059829059829061e-06, | |
| "loss": 0.4299, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 18.003384615384615, | |
| "grad_norm": 0.2074529528617859, | |
| "learning_rate": 7.0427350427350435e-06, | |
| "loss": 0.4959, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 18.004923076923077, | |
| "grad_norm": 137.5737762451172, | |
| "learning_rate": 7.025641025641025e-06, | |
| "loss": 0.4315, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 18.00646153846154, | |
| "grad_norm": 0.018603239208459854, | |
| "learning_rate": 7.008547008547009e-06, | |
| "loss": 0.4308, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 18.008, | |
| "grad_norm": 74.88640594482422, | |
| "learning_rate": 6.991452991452992e-06, | |
| "loss": 1.0586, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 18.00953846153846, | |
| "grad_norm": 55.04835510253906, | |
| "learning_rate": 6.974358974358974e-06, | |
| "loss": 0.5296, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 18.011076923076924, | |
| "grad_norm": 232.72503662109375, | |
| "learning_rate": 6.957264957264958e-06, | |
| "loss": 1.0449, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 18.012615384615383, | |
| "grad_norm": 3.959404468536377, | |
| "learning_rate": 6.940170940170941e-06, | |
| "loss": 0.197, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 18.014153846153846, | |
| "grad_norm": 1.5170236825942993, | |
| "learning_rate": 6.923076923076923e-06, | |
| "loss": 0.5844, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 18.01569230769231, | |
| "grad_norm": 25.22974395751953, | |
| "learning_rate": 6.905982905982906e-06, | |
| "loss": 1.0184, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 18.017230769230768, | |
| "grad_norm": 0.4688655734062195, | |
| "learning_rate": 6.88888888888889e-06, | |
| "loss": 0.4208, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 18.01876923076923, | |
| "grad_norm": 75.46017456054688, | |
| "learning_rate": 6.871794871794872e-06, | |
| "loss": 0.2225, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 18.020153846153846, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.6882848143577576, | |
| "eval_runtime": 17.2394, | |
| "eval_samples_per_second": 2.552, | |
| "eval_steps_per_second": 1.276, | |
| "step": 2489 | |
| }, | |
| { | |
| "epoch": 19.000153846153847, | |
| "grad_norm": 0.07271908223628998, | |
| "learning_rate": 6.854700854700855e-06, | |
| "loss": 0.7142, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 19.00169230769231, | |
| "grad_norm": 0.09199730306863785, | |
| "learning_rate": 6.837606837606839e-06, | |
| "loss": 0.2014, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 19.00323076923077, | |
| "grad_norm": 0.1253657191991806, | |
| "learning_rate": 6.820512820512821e-06, | |
| "loss": 0.9613, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 19.00476923076923, | |
| "grad_norm": 199.5366973876953, | |
| "learning_rate": 6.803418803418804e-06, | |
| "loss": 1.2113, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 19.006307692307693, | |
| "grad_norm": 0.11807122081518173, | |
| "learning_rate": 6.786324786324787e-06, | |
| "loss": 0.7792, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 19.007846153846153, | |
| "grad_norm": 1.3684102296829224, | |
| "learning_rate": 6.76923076923077e-06, | |
| "loss": 0.5214, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 19.009384615384615, | |
| "grad_norm": 5.9137701988220215, | |
| "learning_rate": 6.752136752136753e-06, | |
| "loss": 0.5953, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 19.010923076923078, | |
| "grad_norm": 1.5003548860549927, | |
| "learning_rate": 6.735042735042736e-06, | |
| "loss": 0.6229, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 19.012461538461537, | |
| "grad_norm": 16.662288665771484, | |
| "learning_rate": 6.717948717948718e-06, | |
| "loss": 0.2795, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 19.014, | |
| "grad_norm": 0.1418365091085434, | |
| "learning_rate": 6.700854700854701e-06, | |
| "loss": 0.2646, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 19.015538461538462, | |
| "grad_norm": 0.20075255632400513, | |
| "learning_rate": 6.683760683760684e-06, | |
| "loss": 1.2922, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 19.017076923076925, | |
| "grad_norm": 23.262075424194336, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.4401, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 19.018615384615384, | |
| "grad_norm": 16.691574096679688, | |
| "learning_rate": 6.64957264957265e-06, | |
| "loss": 1.0641, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 19.020153846153846, | |
| "grad_norm": 0.7372543811798096, | |
| "learning_rate": 6.632478632478633e-06, | |
| "loss": 0.2107, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 19.020153846153846, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 0.6558916568756104, | |
| "eval_runtime": 17.2476, | |
| "eval_samples_per_second": 2.551, | |
| "eval_steps_per_second": 1.276, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 20.001538461538463, | |
| "grad_norm": 135.16944885253906, | |
| "learning_rate": 6.615384615384616e-06, | |
| "loss": 1.0368, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 20.00307692307692, | |
| "grad_norm": 0.02402227558195591, | |
| "learning_rate": 6.598290598290598e-06, | |
| "loss": 0.4509, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 20.004615384615384, | |
| "grad_norm": 0.04692141339182854, | |
| "learning_rate": 6.581196581196582e-06, | |
| "loss": 0.7248, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 20.006153846153847, | |
| "grad_norm": 86.60577392578125, | |
| "learning_rate": 6.564102564102565e-06, | |
| "loss": 0.0302, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 20.00769230769231, | |
| "grad_norm": 0.05417357012629509, | |
| "learning_rate": 6.547008547008547e-06, | |
| "loss": 0.2041, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 20.00923076923077, | |
| "grad_norm": 59.57062911987305, | |
| "learning_rate": 6.529914529914531e-06, | |
| "loss": 1.0883, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 20.01076923076923, | |
| "grad_norm": 21.541780471801758, | |
| "learning_rate": 6.512820512820514e-06, | |
| "loss": 0.3479, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 20.012307692307694, | |
| "grad_norm": 83.18236541748047, | |
| "learning_rate": 6.495726495726496e-06, | |
| "loss": 0.4984, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 20.013846153846153, | |
| "grad_norm": 2.479140520095825, | |
| "learning_rate": 6.478632478632479e-06, | |
| "loss": 0.3891, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 20.015384615384615, | |
| "grad_norm": 0.31093835830688477, | |
| "learning_rate": 6.461538461538463e-06, | |
| "loss": 0.6918, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 20.016923076923078, | |
| "grad_norm": 260.9107360839844, | |
| "learning_rate": 6.444444444444445e-06, | |
| "loss": 0.7299, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 20.018461538461537, | |
| "grad_norm": 0.3349054157733917, | |
| "learning_rate": 6.427350427350428e-06, | |
| "loss": 1.006, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "grad_norm": 0.016350680962204933, | |
| "learning_rate": 6.410256410256412e-06, | |
| "loss": 1.0048, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 20.020153846153846, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.9783787131309509, | |
| "eval_runtime": 17.6311, | |
| "eval_samples_per_second": 2.496, | |
| "eval_steps_per_second": 1.248, | |
| "step": 2751 | |
| }, | |
| { | |
| "epoch": 21.001384615384616, | |
| "grad_norm": 34.80990982055664, | |
| "learning_rate": 6.3931623931623935e-06, | |
| "loss": 0.1892, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 21.00292307692308, | |
| "grad_norm": 299.0690002441406, | |
| "learning_rate": 6.376068376068376e-06, | |
| "loss": 0.6769, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 21.004461538461538, | |
| "grad_norm": 0.038944438099861145, | |
| "learning_rate": 6.358974358974359e-06, | |
| "loss": 0.4695, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 21.006, | |
| "grad_norm": 69.340087890625, | |
| "learning_rate": 6.3418803418803425e-06, | |
| "loss": 1.2356, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 21.007538461538463, | |
| "grad_norm": 40.3580436706543, | |
| "learning_rate": 6.324786324786325e-06, | |
| "loss": 0.6055, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 21.009076923076922, | |
| "grad_norm": 82.01126098632812, | |
| "learning_rate": 6.307692307692308e-06, | |
| "loss": 0.3317, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 21.010615384615384, | |
| "grad_norm": 243.14962768554688, | |
| "learning_rate": 6.290598290598291e-06, | |
| "loss": 0.7856, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 21.012153846153847, | |
| "grad_norm": 0.04597717523574829, | |
| "learning_rate": 6.273504273504274e-06, | |
| "loss": 1.1229, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 21.013692307692306, | |
| "grad_norm": 0.36362481117248535, | |
| "learning_rate": 6.256410256410257e-06, | |
| "loss": 0.9496, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 21.01523076923077, | |
| "grad_norm": 1.698781132698059, | |
| "learning_rate": 6.23931623931624e-06, | |
| "loss": 0.7826, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 21.01676923076923, | |
| "grad_norm": 114.8482894897461, | |
| "learning_rate": 6.222222222222223e-06, | |
| "loss": 0.8875, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 21.018307692307694, | |
| "grad_norm": 59.702274322509766, | |
| "learning_rate": 6.205128205128206e-06, | |
| "loss": 0.6851, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 21.019846153846153, | |
| "grad_norm": 12.267464637756348, | |
| "learning_rate": 6.188034188034189e-06, | |
| "loss": 0.4285, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 21.020153846153846, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9721286296844482, | |
| "eval_runtime": 17.2202, | |
| "eval_samples_per_second": 2.555, | |
| "eval_steps_per_second": 1.278, | |
| "step": 2882 | |
| }, | |
| { | |
| "epoch": 22.00123076923077, | |
| "grad_norm": 3.8316917419433594, | |
| "learning_rate": 6.170940170940171e-06, | |
| "loss": 1.0335, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 22.002769230769232, | |
| "grad_norm": 0.03957285359501839, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 0.4629, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 22.00430769230769, | |
| "grad_norm": 71.85205078125, | |
| "learning_rate": 6.136752136752138e-06, | |
| "loss": 0.3178, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 22.005846153846154, | |
| "grad_norm": 0.03175584599375725, | |
| "learning_rate": 6.11965811965812e-06, | |
| "loss": 0.0154, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 22.007384615384616, | |
| "grad_norm": 20.19187355041504, | |
| "learning_rate": 6.102564102564104e-06, | |
| "loss": 0.5558, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 22.008923076923075, | |
| "grad_norm": 0.08645563572645187, | |
| "learning_rate": 6.085470085470086e-06, | |
| "loss": 0.7611, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 22.010461538461538, | |
| "grad_norm": 0.2173357456922531, | |
| "learning_rate": 6.0683760683760684e-06, | |
| "loss": 0.353, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 22.012, | |
| "grad_norm": 0.15007656812667847, | |
| "learning_rate": 6.051282051282051e-06, | |
| "loss": 0.6138, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 22.013538461538463, | |
| "grad_norm": 14.587263107299805, | |
| "learning_rate": 6.034188034188035e-06, | |
| "loss": 0.5272, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 22.015076923076922, | |
| "grad_norm": 0.009721710346639156, | |
| "learning_rate": 6.0170940170940174e-06, | |
| "loss": 0.1756, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 22.016615384615385, | |
| "grad_norm": 0.02123158611357212, | |
| "learning_rate": 6e-06, | |
| "loss": 0.4249, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 22.018153846153847, | |
| "grad_norm": 5.372308731079102, | |
| "learning_rate": 5.982905982905983e-06, | |
| "loss": 0.0095, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 22.019692307692306, | |
| "grad_norm": 106.29003143310547, | |
| "learning_rate": 5.9658119658119664e-06, | |
| "loss": 0.0459, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 22.020153846153846, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 0.6199905872344971, | |
| "eval_runtime": 16.9272, | |
| "eval_samples_per_second": 2.599, | |
| "eval_steps_per_second": 1.3, | |
| "step": 3013 | |
| }, | |
| { | |
| "epoch": 23.001076923076923, | |
| "grad_norm": 0.02692323736846447, | |
| "learning_rate": 5.948717948717949e-06, | |
| "loss": 0.9015, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 23.002615384615385, | |
| "grad_norm": 0.16039462387561798, | |
| "learning_rate": 5.931623931623932e-06, | |
| "loss": 0.2277, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 23.004153846153844, | |
| "grad_norm": 175.57980346679688, | |
| "learning_rate": 5.914529914529915e-06, | |
| "loss": 0.184, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 23.005692307692307, | |
| "grad_norm": 0.007878575474023819, | |
| "learning_rate": 5.897435897435898e-06, | |
| "loss": 0.9996, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 23.00723076923077, | |
| "grad_norm": 0.5078413486480713, | |
| "learning_rate": 5.880341880341881e-06, | |
| "loss": 0.3455, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 23.008769230769232, | |
| "grad_norm": 0.08632130175828934, | |
| "learning_rate": 5.863247863247864e-06, | |
| "loss": 0.3746, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 23.01030769230769, | |
| "grad_norm": 0.1660938709974289, | |
| "learning_rate": 5.846153846153847e-06, | |
| "loss": 1.1707, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 23.011846153846154, | |
| "grad_norm": 48.519126892089844, | |
| "learning_rate": 5.82905982905983e-06, | |
| "loss": 0.785, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 23.013384615384616, | |
| "grad_norm": 0.3178129494190216, | |
| "learning_rate": 5.8119658119658126e-06, | |
| "loss": 0.6968, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 23.014923076923075, | |
| "grad_norm": 219.40220642089844, | |
| "learning_rate": 5.794871794871796e-06, | |
| "loss": 0.2892, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 23.016461538461538, | |
| "grad_norm": 0.0710289478302002, | |
| "learning_rate": 5.777777777777778e-06, | |
| "loss": 0.587, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 23.018, | |
| "grad_norm": 0.08974447846412659, | |
| "learning_rate": 5.760683760683761e-06, | |
| "loss": 0.823, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 23.019538461538463, | |
| "grad_norm": 46.28750991821289, | |
| "learning_rate": 5.743589743589743e-06, | |
| "loss": 0.9143, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 23.020153846153846, | |
| "eval_accuracy": 0.6818181818181818, | |
| "eval_loss": 1.4102354049682617, | |
| "eval_runtime": 17.6977, | |
| "eval_samples_per_second": 2.486, | |
| "eval_steps_per_second": 1.243, | |
| "step": 3144 | |
| }, | |
| { | |
| "epoch": 24.000923076923076, | |
| "grad_norm": 0.19848713278770447, | |
| "learning_rate": 5.726495726495727e-06, | |
| "loss": 0.0612, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 24.00246153846154, | |
| "grad_norm": 9.521435737609863, | |
| "learning_rate": 5.70940170940171e-06, | |
| "loss": 0.0521, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 24.004, | |
| "grad_norm": 137.34861755371094, | |
| "learning_rate": 5.692307692307692e-06, | |
| "loss": 0.3496, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 24.00553846153846, | |
| "grad_norm": 5.25358247756958, | |
| "learning_rate": 5.675213675213675e-06, | |
| "loss": 0.0278, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 24.007076923076923, | |
| "grad_norm": 0.1733076125383377, | |
| "learning_rate": 5.658119658119659e-06, | |
| "loss": 0.5, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 24.008615384615386, | |
| "grad_norm": 68.63470458984375, | |
| "learning_rate": 5.641025641025641e-06, | |
| "loss": 0.6781, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 24.010153846153845, | |
| "grad_norm": 27.09019660949707, | |
| "learning_rate": 5.623931623931624e-06, | |
| "loss": 0.2976, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 24.011692307692307, | |
| "grad_norm": 0.00822505448013544, | |
| "learning_rate": 5.606837606837608e-06, | |
| "loss": 0.0936, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 24.01323076923077, | |
| "grad_norm": 0.009600935503840446, | |
| "learning_rate": 5.58974358974359e-06, | |
| "loss": 1.17, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 24.014769230769232, | |
| "grad_norm": 0.8176679015159607, | |
| "learning_rate": 5.572649572649573e-06, | |
| "loss": 0.0032, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 24.01630769230769, | |
| "grad_norm": 1.6206567287445068, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.9834, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 24.017846153846154, | |
| "grad_norm": 0.06503945589065552, | |
| "learning_rate": 5.538461538461539e-06, | |
| "loss": 0.6411, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 24.019384615384617, | |
| "grad_norm": 0.07350800931453705, | |
| "learning_rate": 5.521367521367522e-06, | |
| "loss": 0.426, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 24.020153846153846, | |
| "eval_accuracy": 0.6590909090909091, | |
| "eval_loss": 1.473230004310608, | |
| "eval_runtime": 18.0209, | |
| "eval_samples_per_second": 2.442, | |
| "eval_steps_per_second": 1.221, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 25.00076923076923, | |
| "grad_norm": 0.05409059301018715, | |
| "learning_rate": 5.504273504273505e-06, | |
| "loss": 0.4545, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 25.002307692307692, | |
| "grad_norm": 0.05480729043483734, | |
| "learning_rate": 5.487179487179488e-06, | |
| "loss": 0.4091, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 25.003846153846155, | |
| "grad_norm": 0.7176423668861389, | |
| "learning_rate": 5.470085470085471e-06, | |
| "loss": 0.039, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 25.005384615384614, | |
| "grad_norm": 0.05573283135890961, | |
| "learning_rate": 5.452991452991453e-06, | |
| "loss": 0.0072, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 25.006923076923076, | |
| "grad_norm": 0.4719586670398712, | |
| "learning_rate": 5.435897435897436e-06, | |
| "loss": 0.3121, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 25.00846153846154, | |
| "grad_norm": 0.004770807456225157, | |
| "learning_rate": 5.418803418803419e-06, | |
| "loss": 0.0462, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "grad_norm": 0.01475294679403305, | |
| "learning_rate": 5.401709401709402e-06, | |
| "loss": 0.4428, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 25.01153846153846, | |
| "grad_norm": 0.04962127283215523, | |
| "learning_rate": 5.384615384615385e-06, | |
| "loss": 1.111, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 25.013076923076923, | |
| "grad_norm": 31.48914909362793, | |
| "learning_rate": 5.367521367521367e-06, | |
| "loss": 1.0655, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 25.014615384615386, | |
| "grad_norm": 172.65916442871094, | |
| "learning_rate": 5.350427350427351e-06, | |
| "loss": 0.8228, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 25.016153846153845, | |
| "grad_norm": 15.740141868591309, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.9637, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 25.017692307692307, | |
| "grad_norm": 0.008569518104195595, | |
| "learning_rate": 5.316239316239316e-06, | |
| "loss": 0.1092, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 25.01923076923077, | |
| "grad_norm": 1.651440978050232, | |
| "learning_rate": 5.2991452991453e-06, | |
| "loss": 0.8278, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 25.020153846153846, | |
| "eval_accuracy": 0.7954545454545454, | |
| "eval_loss": 1.0036906003952026, | |
| "eval_runtime": 17.7918, | |
| "eval_samples_per_second": 2.473, | |
| "eval_steps_per_second": 1.237, | |
| "step": 3406 | |
| }, | |
| { | |
| "epoch": 26.000615384615383, | |
| "grad_norm": 59.16725540161133, | |
| "learning_rate": 5.282051282051283e-06, | |
| "loss": 0.5805, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 26.002153846153846, | |
| "grad_norm": 188.58676147460938, | |
| "learning_rate": 5.264957264957265e-06, | |
| "loss": 0.8709, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 26.003692307692308, | |
| "grad_norm": 0.1376463621854782, | |
| "learning_rate": 5.247863247863249e-06, | |
| "loss": 0.2184, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 26.00523076923077, | |
| "grad_norm": 0.006610576529055834, | |
| "learning_rate": 5.230769230769232e-06, | |
| "loss": 0.2502, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 26.00676923076923, | |
| "grad_norm": 18.84449005126953, | |
| "learning_rate": 5.213675213675214e-06, | |
| "loss": 0.7287, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 26.008307692307692, | |
| "grad_norm": 0.020331906154751778, | |
| "learning_rate": 5.196581196581197e-06, | |
| "loss": 0.278, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 26.009846153846155, | |
| "grad_norm": 182.36013793945312, | |
| "learning_rate": 5.179487179487181e-06, | |
| "loss": 0.7604, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 26.011384615384614, | |
| "grad_norm": 1.1830753087997437, | |
| "learning_rate": 5.162393162393163e-06, | |
| "loss": 0.191, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 26.012923076923077, | |
| "grad_norm": 8.558692932128906, | |
| "learning_rate": 5.145299145299145e-06, | |
| "loss": 0.4842, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 26.01446153846154, | |
| "grad_norm": 109.40116882324219, | |
| "learning_rate": 5.128205128205128e-06, | |
| "loss": 0.3731, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 26.016, | |
| "grad_norm": 41.654903411865234, | |
| "learning_rate": 5.1111111111111115e-06, | |
| "loss": 0.5822, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 26.01753846153846, | |
| "grad_norm": 207.07302856445312, | |
| "learning_rate": 5.094017094017094e-06, | |
| "loss": 0.6782, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 26.019076923076923, | |
| "grad_norm": 0.0691024512052536, | |
| "learning_rate": 5.076923076923077e-06, | |
| "loss": 0.7064, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 26.020153846153846, | |
| "eval_accuracy": 0.8409090909090909, | |
| "eval_loss": 0.7553314566612244, | |
| "eval_runtime": 17.6765, | |
| "eval_samples_per_second": 2.489, | |
| "eval_steps_per_second": 1.245, | |
| "step": 3537 | |
| }, | |
| { | |
| "epoch": 27.00046153846154, | |
| "grad_norm": 0.10701064020395279, | |
| "learning_rate": 5.05982905982906e-06, | |
| "loss": 0.8625, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 27.002, | |
| "grad_norm": 0.011954342015087605, | |
| "learning_rate": 5.042735042735043e-06, | |
| "loss": 0.7158, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 27.00353846153846, | |
| "grad_norm": 0.09756641089916229, | |
| "learning_rate": 5.025641025641026e-06, | |
| "loss": 0.2007, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 27.005076923076924, | |
| "grad_norm": 0.10245008021593094, | |
| "learning_rate": 5.008547008547009e-06, | |
| "loss": 0.5035, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 27.006615384615383, | |
| "grad_norm": 0.04461255297064781, | |
| "learning_rate": 4.991452991452992e-06, | |
| "loss": 0.026, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 27.008153846153846, | |
| "grad_norm": 128.31396484375, | |
| "learning_rate": 4.974358974358975e-06, | |
| "loss": 0.5569, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 27.00969230769231, | |
| "grad_norm": 0.10750886797904968, | |
| "learning_rate": 4.957264957264958e-06, | |
| "loss": 0.0086, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 27.01123076923077, | |
| "grad_norm": 372.33111572265625, | |
| "learning_rate": 4.940170940170941e-06, | |
| "loss": 0.1465, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 27.01276923076923, | |
| "grad_norm": 1.2403115034103394, | |
| "learning_rate": 4.923076923076924e-06, | |
| "loss": 1.04, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 27.014307692307693, | |
| "grad_norm": 0.0044847396202385426, | |
| "learning_rate": 4.905982905982906e-06, | |
| "loss": 0.0575, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 27.015846153846155, | |
| "grad_norm": 0.05502178519964218, | |
| "learning_rate": 4.888888888888889e-06, | |
| "loss": 1.2338, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 27.017384615384614, | |
| "grad_norm": 0.011465172283351421, | |
| "learning_rate": 4.871794871794872e-06, | |
| "loss": 0.4592, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 27.018923076923077, | |
| "grad_norm": 0.007825562730431557, | |
| "learning_rate": 4.854700854700855e-06, | |
| "loss": 0.6217, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 27.020153846153846, | |
| "eval_accuracy": 0.7045454545454546, | |
| "eval_loss": 1.578810453414917, | |
| "eval_runtime": 17.6931, | |
| "eval_samples_per_second": 2.487, | |
| "eval_steps_per_second": 1.243, | |
| "step": 3668 | |
| }, | |
| { | |
| "epoch": 28.000307692307693, | |
| "grad_norm": 0.04646565020084381, | |
| "learning_rate": 4.837606837606838e-06, | |
| "loss": 0.3217, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 28.001846153846152, | |
| "grad_norm": 98.77088165283203, | |
| "learning_rate": 4.820512820512821e-06, | |
| "loss": 0.3034, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 28.003384615384615, | |
| "grad_norm": 0.05187759920954704, | |
| "learning_rate": 4.803418803418804e-06, | |
| "loss": 0.9491, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 28.004923076923077, | |
| "grad_norm": 0.17661038041114807, | |
| "learning_rate": 4.786324786324787e-06, | |
| "loss": 0.0031, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 28.00646153846154, | |
| "grad_norm": 0.1141028180718422, | |
| "learning_rate": 4.76923076923077e-06, | |
| "loss": 0.2752, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 28.008, | |
| "grad_norm": 0.052458833903074265, | |
| "learning_rate": 4.752136752136752e-06, | |
| "loss": 0.4143, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 28.00953846153846, | |
| "grad_norm": 0.5310328006744385, | |
| "learning_rate": 4.7350427350427355e-06, | |
| "loss": 0.5349, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 28.011076923076924, | |
| "grad_norm": 0.02830323949456215, | |
| "learning_rate": 4.717948717948718e-06, | |
| "loss": 0.2826, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 28.012615384615383, | |
| "grad_norm": 0.011391979642212391, | |
| "learning_rate": 4.700854700854701e-06, | |
| "loss": 0.6189, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 28.014153846153846, | |
| "grad_norm": 546.1659545898438, | |
| "learning_rate": 4.6837606837606844e-06, | |
| "loss": 0.8617, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 28.01569230769231, | |
| "grad_norm": 0.008102044463157654, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 0.3314, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 28.017230769230768, | |
| "grad_norm": 16.070526123046875, | |
| "learning_rate": 4.64957264957265e-06, | |
| "loss": 0.8471, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 28.01876923076923, | |
| "grad_norm": 0.06964533776044846, | |
| "learning_rate": 4.6324786324786334e-06, | |
| "loss": 0.6104, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 28.020153846153846, | |
| "eval_accuracy": 0.7045454545454546, | |
| "eval_loss": 1.4798736572265625, | |
| "eval_runtime": 17.8111, | |
| "eval_samples_per_second": 2.47, | |
| "eval_steps_per_second": 1.235, | |
| "step": 3799 | |
| }, | |
| { | |
| "epoch": 29.000153846153847, | |
| "grad_norm": 0.03384683281183243, | |
| "learning_rate": 4.615384615384616e-06, | |
| "loss": 0.2272, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 29.00169230769231, | |
| "grad_norm": 0.018132856115698814, | |
| "learning_rate": 4.598290598290598e-06, | |
| "loss": 0.2112, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 29.00323076923077, | |
| "grad_norm": 0.052457358688116074, | |
| "learning_rate": 4.581196581196582e-06, | |
| "loss": 0.0022, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 29.00476923076923, | |
| "grad_norm": 27.76186752319336, | |
| "learning_rate": 4.564102564102564e-06, | |
| "loss": 0.3728, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 29.006307692307693, | |
| "grad_norm": 0.03067011386156082, | |
| "learning_rate": 4.547008547008547e-06, | |
| "loss": 0.5915, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 29.007846153846153, | |
| "grad_norm": 1.035430669784546, | |
| "learning_rate": 4.5299145299145306e-06, | |
| "loss": 0.292, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 29.009384615384615, | |
| "grad_norm": 0.1240568533539772, | |
| "learning_rate": 4.512820512820513e-06, | |
| "loss": 0.2652, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 29.010923076923078, | |
| "grad_norm": 0.005871090106666088, | |
| "learning_rate": 4.495726495726496e-06, | |
| "loss": 0.4622, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 29.012461538461537, | |
| "grad_norm": 0.013633547350764275, | |
| "learning_rate": 4.4786324786324796e-06, | |
| "loss": 0.859, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 29.014, | |
| "grad_norm": 137.29229736328125, | |
| "learning_rate": 4.461538461538462e-06, | |
| "loss": 0.5352, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 29.015538461538462, | |
| "grad_norm": 0.042617082595825195, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.6373, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 29.017076923076925, | |
| "grad_norm": 98.65312957763672, | |
| "learning_rate": 4.427350427350428e-06, | |
| "loss": 0.5134, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 29.018615384615384, | |
| "grad_norm": 156.2729949951172, | |
| "learning_rate": 4.4102564102564104e-06, | |
| "loss": 0.3833, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 29.020153846153846, | |
| "grad_norm": 0.004802621901035309, | |
| "learning_rate": 4.393162393162393e-06, | |
| "loss": 0.4625, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 29.020153846153846, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_loss": 2.0381338596343994, | |
| "eval_runtime": 9.616, | |
| "eval_samples_per_second": 4.576, | |
| "eval_steps_per_second": 2.288, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 30.001538461538463, | |
| "grad_norm": 207.1352081298828, | |
| "learning_rate": 4.376068376068377e-06, | |
| "loss": 1.1738, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 30.00307692307692, | |
| "grad_norm": 0.12229020148515701, | |
| "learning_rate": 4.358974358974359e-06, | |
| "loss": 0.0394, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 30.004615384615384, | |
| "grad_norm": 176.2926483154297, | |
| "learning_rate": 4.341880341880342e-06, | |
| "loss": 0.0691, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 30.006153846153847, | |
| "grad_norm": 0.16938596963882446, | |
| "learning_rate": 4.324786324786326e-06, | |
| "loss": 0.0212, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 30.00769230769231, | |
| "grad_norm": 0.09926075488328934, | |
| "learning_rate": 4.307692307692308e-06, | |
| "loss": 0.7793, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 30.00923076923077, | |
| "grad_norm": 119.69144439697266, | |
| "learning_rate": 4.29059829059829e-06, | |
| "loss": 1.0191, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 30.01076923076923, | |
| "grad_norm": 0.062020666897296906, | |
| "learning_rate": 4.273504273504274e-06, | |
| "loss": 0.8949, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 30.012307692307694, | |
| "grad_norm": 0.02727566286921501, | |
| "learning_rate": 4.2564102564102566e-06, | |
| "loss": 0.2886, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 30.013846153846153, | |
| "grad_norm": 0.03259558975696564, | |
| "learning_rate": 4.239316239316239e-06, | |
| "loss": 0.2814, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 30.015384615384615, | |
| "grad_norm": 0.1853773295879364, | |
| "learning_rate": 4.222222222222223e-06, | |
| "loss": 0.0066, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 30.016923076923078, | |
| "grad_norm": 0.06135905534029007, | |
| "learning_rate": 4.2051282051282055e-06, | |
| "loss": 0.7464, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 30.018461538461537, | |
| "grad_norm": 150.62867736816406, | |
| "learning_rate": 4.188034188034188e-06, | |
| "loss": 0.3704, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "grad_norm": 0.14883188903331757, | |
| "learning_rate": 4.170940170940172e-06, | |
| "loss": 0.1935, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 30.020153846153846, | |
| "eval_accuracy": 0.6136363636363636, | |
| "eval_loss": 1.862363338470459, | |
| "eval_runtime": 15.575, | |
| "eval_samples_per_second": 2.825, | |
| "eval_steps_per_second": 1.413, | |
| "step": 4061 | |
| }, | |
| { | |
| "epoch": 31.001384615384616, | |
| "grad_norm": 27.385068893432617, | |
| "learning_rate": 4.1538461538461545e-06, | |
| "loss": 0.8037, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 31.00292307692308, | |
| "grad_norm": 0.043816737830638885, | |
| "learning_rate": 4.136752136752136e-06, | |
| "loss": 1.1506, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 31.004461538461538, | |
| "grad_norm": 477.7364501953125, | |
| "learning_rate": 4.11965811965812e-06, | |
| "loss": 0.8598, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 31.006, | |
| "grad_norm": 0.055450838059186935, | |
| "learning_rate": 4.102564102564103e-06, | |
| "loss": 0.062, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 31.007538461538463, | |
| "grad_norm": 4.573432445526123, | |
| "learning_rate": 4.085470085470085e-06, | |
| "loss": 0.1854, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 31.009076923076922, | |
| "grad_norm": 103.39335632324219, | |
| "learning_rate": 4.068376068376069e-06, | |
| "loss": 0.1999, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 31.010615384615384, | |
| "grad_norm": 0.06464827060699463, | |
| "learning_rate": 4.051282051282052e-06, | |
| "loss": 0.0474, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 31.012153846153847, | |
| "grad_norm": 0.10956919193267822, | |
| "learning_rate": 4.034188034188034e-06, | |
| "loss": 0.1628, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 31.013692307692306, | |
| "grad_norm": 0.12183642387390137, | |
| "learning_rate": 4.017094017094018e-06, | |
| "loss": 0.2825, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 31.01523076923077, | |
| "grad_norm": 0.13174249231815338, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0393, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 31.01676923076923, | |
| "grad_norm": 0.0611453615128994, | |
| "learning_rate": 3.982905982905983e-06, | |
| "loss": 0.346, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 31.018307692307694, | |
| "grad_norm": 0.18526746332645416, | |
| "learning_rate": 3.965811965811966e-06, | |
| "loss": 1.0192, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 31.019846153846153, | |
| "grad_norm": 404.88861083984375, | |
| "learning_rate": 3.948717948717949e-06, | |
| "loss": 0.3657, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 31.020153846153846, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4569655656814575, | |
| "eval_runtime": 17.3375, | |
| "eval_samples_per_second": 2.538, | |
| "eval_steps_per_second": 1.269, | |
| "step": 4192 | |
| }, | |
| { | |
| "epoch": 32.001230769230766, | |
| "grad_norm": 0.5610682368278503, | |
| "learning_rate": 3.9316239316239315e-06, | |
| "loss": 0.0172, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 32.00276923076923, | |
| "grad_norm": 0.07297376543283463, | |
| "learning_rate": 3.914529914529915e-06, | |
| "loss": 0.6225, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 32.00430769230769, | |
| "grad_norm": 0.06417560577392578, | |
| "learning_rate": 3.897435897435898e-06, | |
| "loss": 0.1106, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 32.00584615384616, | |
| "grad_norm": 0.24836859107017517, | |
| "learning_rate": 3.8803418803418805e-06, | |
| "loss": 0.0068, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 32.007384615384616, | |
| "grad_norm": 0.0073760999366641045, | |
| "learning_rate": 3.863247863247864e-06, | |
| "loss": 0.0035, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 32.008923076923075, | |
| "grad_norm": 0.029691442847251892, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.0054, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 32.01046153846154, | |
| "grad_norm": 0.003888042876496911, | |
| "learning_rate": 3.8290598290598295e-06, | |
| "loss": 0.2511, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 32.012, | |
| "grad_norm": 0.1727166324853897, | |
| "learning_rate": 3.8119658119658122e-06, | |
| "loss": 0.6904, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 32.01353846153846, | |
| "grad_norm": 0.0029368873219937086, | |
| "learning_rate": 3.794871794871795e-06, | |
| "loss": 0.3157, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 32.015076923076926, | |
| "grad_norm": 0.0033048547338694334, | |
| "learning_rate": 3.777777777777778e-06, | |
| "loss": 0.0101, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 32.016615384615385, | |
| "grad_norm": 0.0031597234774380922, | |
| "learning_rate": 3.760683760683761e-06, | |
| "loss": 0.0021, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 32.018153846153844, | |
| "grad_norm": 0.04100479185581207, | |
| "learning_rate": 3.743589743589744e-06, | |
| "loss": 0.1442, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 32.01969230769231, | |
| "grad_norm": 0.01853967271745205, | |
| "learning_rate": 3.726495726495727e-06, | |
| "loss": 0.0952, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 32.020153846153846, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 1.2123234272003174, | |
| "eval_runtime": 17.5646, | |
| "eval_samples_per_second": 2.505, | |
| "eval_steps_per_second": 1.253, | |
| "step": 4323 | |
| }, | |
| { | |
| "epoch": 33.00107692307692, | |
| "grad_norm": 0.035949498414993286, | |
| "learning_rate": 3.7094017094017098e-06, | |
| "loss": 0.0008, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 33.00261538461538, | |
| "grad_norm": 0.025361323729157448, | |
| "learning_rate": 3.692307692307693e-06, | |
| "loss": 0.0007, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 33.00415384615385, | |
| "grad_norm": 0.05266913026571274, | |
| "learning_rate": 3.6752136752136756e-06, | |
| "loss": 0.2574, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 33.00569230769231, | |
| "grad_norm": 0.023882798850536346, | |
| "learning_rate": 3.6581196581196584e-06, | |
| "loss": 1.1168, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 33.007230769230766, | |
| "grad_norm": 0.02024800516664982, | |
| "learning_rate": 3.641025641025641e-06, | |
| "loss": 0.0007, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 33.00876923076923, | |
| "grad_norm": 0.025938618928194046, | |
| "learning_rate": 3.623931623931624e-06, | |
| "loss": 0.0813, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 33.01030769230769, | |
| "grad_norm": 196.16314697265625, | |
| "learning_rate": 3.606837606837607e-06, | |
| "loss": 0.3344, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 33.01184615384616, | |
| "grad_norm": 15.480915069580078, | |
| "learning_rate": 3.58974358974359e-06, | |
| "loss": 0.3552, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 33.013384615384616, | |
| "grad_norm": 0.0065137180499732494, | |
| "learning_rate": 3.572649572649573e-06, | |
| "loss": 0.0676, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 33.014923076923075, | |
| "grad_norm": 0.005011861678212881, | |
| "learning_rate": 3.555555555555556e-06, | |
| "loss": 0.3235, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 33.01646153846154, | |
| "grad_norm": 0.07754269242286682, | |
| "learning_rate": 3.538461538461539e-06, | |
| "loss": 0.5565, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 33.018, | |
| "grad_norm": 0.02991201914846897, | |
| "learning_rate": 3.5213675213675218e-06, | |
| "loss": 0.098, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 33.01953846153846, | |
| "grad_norm": 0.028607971966266632, | |
| "learning_rate": 3.5042735042735045e-06, | |
| "loss": 0.6802, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 33.020153846153846, | |
| "eval_accuracy": 0.8409090909090909, | |
| "eval_loss": 1.1155343055725098, | |
| "eval_runtime": 17.9597, | |
| "eval_samples_per_second": 2.45, | |
| "eval_steps_per_second": 1.225, | |
| "step": 4454 | |
| }, | |
| { | |
| "epoch": 34.00092307692308, | |
| "grad_norm": 0.04091598093509674, | |
| "learning_rate": 3.487179487179487e-06, | |
| "loss": 0.001, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 34.00246153846154, | |
| "grad_norm": 0.05654391273856163, | |
| "learning_rate": 3.4700854700854703e-06, | |
| "loss": 0.2783, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 34.004, | |
| "grad_norm": 585.7238159179688, | |
| "learning_rate": 3.452991452991453e-06, | |
| "loss": 0.7375, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 34.005538461538464, | |
| "grad_norm": 0.0074472674168646336, | |
| "learning_rate": 3.435897435897436e-06, | |
| "loss": 0.3253, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 34.00707692307692, | |
| "grad_norm": 365.37353515625, | |
| "learning_rate": 3.4188034188034193e-06, | |
| "loss": 0.1552, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 34.00861538461538, | |
| "grad_norm": 4.461187362670898, | |
| "learning_rate": 3.401709401709402e-06, | |
| "loss": 0.4934, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 34.01015384615385, | |
| "grad_norm": 76.49549865722656, | |
| "learning_rate": 3.384615384615385e-06, | |
| "loss": 0.3254, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 34.01169230769231, | |
| "grad_norm": 1.2436606884002686, | |
| "learning_rate": 3.367521367521368e-06, | |
| "loss": 0.0037, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 34.013230769230766, | |
| "grad_norm": 0.04588088393211365, | |
| "learning_rate": 3.3504273504273506e-06, | |
| "loss": 0.287, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 34.01476923076923, | |
| "grad_norm": 0.008639726787805557, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.5012, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 34.01630769230769, | |
| "grad_norm": 0.005063442513346672, | |
| "learning_rate": 3.3162393162393165e-06, | |
| "loss": 0.2893, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 34.01784615384615, | |
| "grad_norm": 19.954551696777344, | |
| "learning_rate": 3.299145299145299e-06, | |
| "loss": 0.0117, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 34.01938461538462, | |
| "grad_norm": 0.02637256495654583, | |
| "learning_rate": 3.2820512820512823e-06, | |
| "loss": 0.1602, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 34.020153846153846, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 1.099003553390503, | |
| "eval_runtime": 17.6092, | |
| "eval_samples_per_second": 2.499, | |
| "eval_steps_per_second": 1.249, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 35.00076923076923, | |
| "grad_norm": 0.9376542568206787, | |
| "learning_rate": 3.2649572649572655e-06, | |
| "loss": 0.0089, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 35.002307692307696, | |
| "grad_norm": 0.0895494744181633, | |
| "learning_rate": 3.247863247863248e-06, | |
| "loss": 0.1098, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 35.003846153846155, | |
| "grad_norm": 0.28068679571151733, | |
| "learning_rate": 3.2307692307692313e-06, | |
| "loss": 0.3047, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 35.005384615384614, | |
| "grad_norm": 198.52899169921875, | |
| "learning_rate": 3.213675213675214e-06, | |
| "loss": 0.5894, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 35.00692307692308, | |
| "grad_norm": 1.0711522102355957, | |
| "learning_rate": 3.1965811965811967e-06, | |
| "loss": 0.0017, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 35.00846153846154, | |
| "grad_norm": 0.07613427191972733, | |
| "learning_rate": 3.1794871794871795e-06, | |
| "loss": 0.001, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "grad_norm": 0.17094501852989197, | |
| "learning_rate": 3.1623931623931626e-06, | |
| "loss": 0.2917, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 35.011538461538464, | |
| "grad_norm": 0.04038213565945625, | |
| "learning_rate": 3.1452991452991453e-06, | |
| "loss": 0.309, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 35.01307692307692, | |
| "grad_norm": 0.0034144625533372164, | |
| "learning_rate": 3.1282051282051284e-06, | |
| "loss": 0.001, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 35.01461538461538, | |
| "grad_norm": 0.030976584181189537, | |
| "learning_rate": 3.1111111111111116e-06, | |
| "loss": 0.0017, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 35.01615384615385, | |
| "grad_norm": 0.04863714426755905, | |
| "learning_rate": 3.0940170940170943e-06, | |
| "loss": 0.7633, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 35.01769230769231, | |
| "grad_norm": 0.0021368267480283976, | |
| "learning_rate": 3.0769230769230774e-06, | |
| "loss": 0.0042, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 35.01923076923077, | |
| "grad_norm": 0.07372542470693588, | |
| "learning_rate": 3.05982905982906e-06, | |
| "loss": 0.269, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 35.020153846153846, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 1.337334156036377, | |
| "eval_runtime": 17.7881, | |
| "eval_samples_per_second": 2.474, | |
| "eval_steps_per_second": 1.237, | |
| "step": 4716 | |
| }, | |
| { | |
| "epoch": 36.00061538461539, | |
| "grad_norm": 0.0037069679237902164, | |
| "learning_rate": 3.042735042735043e-06, | |
| "loss": 0.0028, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 36.002153846153846, | |
| "grad_norm": 0.06127461418509483, | |
| "learning_rate": 3.0256410256410256e-06, | |
| "loss": 0.0012, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 36.003692307692305, | |
| "grad_norm": 0.014414296485483646, | |
| "learning_rate": 3.0085470085470087e-06, | |
| "loss": 0.4862, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 36.00523076923077, | |
| "grad_norm": 0.010392235592007637, | |
| "learning_rate": 2.9914529914529914e-06, | |
| "loss": 0.0013, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 36.00676923076923, | |
| "grad_norm": 0.0824984610080719, | |
| "learning_rate": 2.9743589743589746e-06, | |
| "loss": 0.7838, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 36.00830769230769, | |
| "grad_norm": 0.08291416615247726, | |
| "learning_rate": 2.9572649572649577e-06, | |
| "loss": 0.0066, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 36.009846153846155, | |
| "grad_norm": 0.006433951668441296, | |
| "learning_rate": 2.9401709401709404e-06, | |
| "loss": 0.0755, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 36.011384615384614, | |
| "grad_norm": 0.09042423963546753, | |
| "learning_rate": 2.9230769230769236e-06, | |
| "loss": 0.2866, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 36.01292307692308, | |
| "grad_norm": 0.047474589198827744, | |
| "learning_rate": 2.9059829059829063e-06, | |
| "loss": 0.3986, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 36.01446153846154, | |
| "grad_norm": 0.002244462026283145, | |
| "learning_rate": 2.888888888888889e-06, | |
| "loss": 0.003, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 36.016, | |
| "grad_norm": 0.05365893617272377, | |
| "learning_rate": 2.8717948717948717e-06, | |
| "loss": 0.3002, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 36.017538461538464, | |
| "grad_norm": 0.004874803591519594, | |
| "learning_rate": 2.854700854700855e-06, | |
| "loss": 0.638, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 36.01907692307692, | |
| "grad_norm": 0.17770527303218842, | |
| "learning_rate": 2.8376068376068376e-06, | |
| "loss": 0.2087, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 36.020153846153846, | |
| "eval_accuracy": 0.7954545454545454, | |
| "eval_loss": 1.0544697046279907, | |
| "eval_runtime": 17.9779, | |
| "eval_samples_per_second": 2.447, | |
| "eval_steps_per_second": 1.224, | |
| "step": 4847 | |
| }, | |
| { | |
| "epoch": 37.000461538461536, | |
| "grad_norm": 0.06458146870136261, | |
| "learning_rate": 2.8205128205128207e-06, | |
| "loss": 0.15, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 37.002, | |
| "grad_norm": 0.06696410477161407, | |
| "learning_rate": 2.803418803418804e-06, | |
| "loss": 0.5001, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 37.00353846153846, | |
| "grad_norm": 0.007221933454275131, | |
| "learning_rate": 2.7863247863247866e-06, | |
| "loss": 0.2833, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 37.00507692307692, | |
| "grad_norm": 0.15909945964813232, | |
| "learning_rate": 2.7692307692307697e-06, | |
| "loss": 0.1828, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 37.00661538461539, | |
| "grad_norm": 98.72877502441406, | |
| "learning_rate": 2.7521367521367524e-06, | |
| "loss": 0.2224, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 37.008153846153846, | |
| "grad_norm": 0.0615471675992012, | |
| "learning_rate": 2.7350427350427355e-06, | |
| "loss": 0.3348, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 37.009692307692305, | |
| "grad_norm": 0.002571461722254753, | |
| "learning_rate": 2.717948717948718e-06, | |
| "loss": 0.427, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 37.01123076923077, | |
| "grad_norm": 0.8324174880981445, | |
| "learning_rate": 2.700854700854701e-06, | |
| "loss": 0.0013, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 37.01276923076923, | |
| "grad_norm": 0.06796202808618546, | |
| "learning_rate": 2.6837606837606837e-06, | |
| "loss": 0.4073, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 37.01430769230769, | |
| "grad_norm": 269.8399353027344, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.2335, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 37.015846153846155, | |
| "grad_norm": 0.06111394613981247, | |
| "learning_rate": 2.64957264957265e-06, | |
| "loss": 0.3117, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 37.017384615384614, | |
| "grad_norm": 0.04151718318462372, | |
| "learning_rate": 2.6324786324786327e-06, | |
| "loss": 0.2669, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 37.01892307692308, | |
| "grad_norm": 14.552691459655762, | |
| "learning_rate": 2.615384615384616e-06, | |
| "loss": 0.4447, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 37.020153846153846, | |
| "eval_accuracy": 0.7954545454545454, | |
| "eval_loss": 1.1181522607803345, | |
| "eval_runtime": 17.7093, | |
| "eval_samples_per_second": 2.485, | |
| "eval_steps_per_second": 1.242, | |
| "step": 4978 | |
| }, | |
| { | |
| "epoch": 38.00030769230769, | |
| "grad_norm": 0.045465320348739624, | |
| "learning_rate": 2.5982905982905985e-06, | |
| "loss": 0.002, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 38.00184615384615, | |
| "grad_norm": 0.03787988796830177, | |
| "learning_rate": 2.5811965811965817e-06, | |
| "loss": 0.0033, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 38.00338461538462, | |
| "grad_norm": 0.0018119997112080455, | |
| "learning_rate": 2.564102564102564e-06, | |
| "loss": 0.0204, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 38.00492307692308, | |
| "grad_norm": 0.004441489931195974, | |
| "learning_rate": 2.547008547008547e-06, | |
| "loss": 0.1118, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 38.00646153846154, | |
| "grad_norm": 0.0016116894548758864, | |
| "learning_rate": 2.52991452991453e-06, | |
| "loss": 0.5886, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 38.008, | |
| "grad_norm": 0.13636310398578644, | |
| "learning_rate": 2.512820512820513e-06, | |
| "loss": 0.4062, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 38.00953846153846, | |
| "grad_norm": 0.0021477951668202877, | |
| "learning_rate": 2.495726495726496e-06, | |
| "loss": 0.6216, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 38.01107692307692, | |
| "grad_norm": 0.04011191800236702, | |
| "learning_rate": 2.478632478632479e-06, | |
| "loss": 0.0046, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 38.01261538461539, | |
| "grad_norm": 0.10232126712799072, | |
| "learning_rate": 2.461538461538462e-06, | |
| "loss": 0.0694, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 38.014153846153846, | |
| "grad_norm": 0.05692799389362335, | |
| "learning_rate": 2.4444444444444447e-06, | |
| "loss": 0.4071, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 38.015692307692305, | |
| "grad_norm": 0.551006555557251, | |
| "learning_rate": 2.4273504273504274e-06, | |
| "loss": 0.6267, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 38.01723076923077, | |
| "grad_norm": 297.2463073730469, | |
| "learning_rate": 2.4102564102564105e-06, | |
| "loss": 0.023, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 38.01876923076923, | |
| "grad_norm": 0.026338782161474228, | |
| "learning_rate": 2.3931623931623937e-06, | |
| "loss": 0.803, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 38.020153846153846, | |
| "eval_accuracy": 0.7045454545454546, | |
| "eval_loss": 1.9384654760360718, | |
| "eval_runtime": 17.681, | |
| "eval_samples_per_second": 2.489, | |
| "eval_steps_per_second": 1.244, | |
| "step": 5109 | |
| }, | |
| { | |
| "epoch": 39.00015384615384, | |
| "grad_norm": 601.521484375, | |
| "learning_rate": 2.376068376068376e-06, | |
| "loss": 0.5062, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 39.00169230769231, | |
| "grad_norm": 0.08332568407058716, | |
| "learning_rate": 2.358974358974359e-06, | |
| "loss": 0.5951, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 39.00323076923077, | |
| "grad_norm": 0.009220034815371037, | |
| "learning_rate": 2.3418803418803422e-06, | |
| "loss": 0.2551, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 39.00476923076923, | |
| "grad_norm": 0.04447532817721367, | |
| "learning_rate": 2.324786324786325e-06, | |
| "loss": 0.557, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 39.00630769230769, | |
| "grad_norm": 0.18098969757556915, | |
| "learning_rate": 2.307692307692308e-06, | |
| "loss": 0.0693, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 39.00784615384615, | |
| "grad_norm": 178.48533630371094, | |
| "learning_rate": 2.290598290598291e-06, | |
| "loss": 0.0348, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 39.00938461538462, | |
| "grad_norm": 17.192779541015625, | |
| "learning_rate": 2.2735042735042735e-06, | |
| "loss": 0.2677, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 39.01092307692308, | |
| "grad_norm": 0.0028921575285494328, | |
| "learning_rate": 2.2564102564102566e-06, | |
| "loss": 0.0018, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 39.01246153846154, | |
| "grad_norm": 0.010585586540400982, | |
| "learning_rate": 2.2393162393162398e-06, | |
| "loss": 0.2342, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 39.014, | |
| "grad_norm": 525.34375, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.3572, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 39.01553846153846, | |
| "grad_norm": 0.061640914529561996, | |
| "learning_rate": 2.2051282051282052e-06, | |
| "loss": 0.0038, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 39.01707692307692, | |
| "grad_norm": 0.045302629470825195, | |
| "learning_rate": 2.1880341880341884e-06, | |
| "loss": 0.0012, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 39.01861538461539, | |
| "grad_norm": 0.04225580021739006, | |
| "learning_rate": 2.170940170940171e-06, | |
| "loss": 0.0008, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 39.020153846153846, | |
| "grad_norm": 0.002470242092385888, | |
| "learning_rate": 2.153846153846154e-06, | |
| "loss": 0.685, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 39.020153846153846, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 1.507863998413086, | |
| "eval_runtime": 17.7634, | |
| "eval_samples_per_second": 2.477, | |
| "eval_steps_per_second": 1.239, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 40.00153846153846, | |
| "grad_norm": 0.04470238462090492, | |
| "learning_rate": 2.136752136752137e-06, | |
| "loss": 0.2639, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 40.003076923076925, | |
| "grad_norm": 0.0690530464053154, | |
| "learning_rate": 2.1196581196581196e-06, | |
| "loss": 0.318, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 40.004615384615384, | |
| "grad_norm": 0.007012404967099428, | |
| "learning_rate": 2.1025641025641028e-06, | |
| "loss": 0.2909, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 40.00615384615384, | |
| "grad_norm": 0.0480414479970932, | |
| "learning_rate": 2.085470085470086e-06, | |
| "loss": 0.0591, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 40.00769230769231, | |
| "grad_norm": 0.048569098114967346, | |
| "learning_rate": 2.068376068376068e-06, | |
| "loss": 0.0006, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 40.00923076923077, | |
| "grad_norm": 23.753747940063477, | |
| "learning_rate": 2.0512820512820513e-06, | |
| "loss": 0.005, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 40.01076923076923, | |
| "grad_norm": 0.01745321974158287, | |
| "learning_rate": 2.0341880341880345e-06, | |
| "loss": 0.0655, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 40.012307692307694, | |
| "grad_norm": 0.0018270122818648815, | |
| "learning_rate": 2.017094017094017e-06, | |
| "loss": 0.2634, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 40.01384615384615, | |
| "grad_norm": 0.026197049766778946, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6511, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 40.01538461538462, | |
| "grad_norm": 0.003131721168756485, | |
| "learning_rate": 1.982905982905983e-06, | |
| "loss": 0.0009, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 40.01692307692308, | |
| "grad_norm": 0.07359786331653595, | |
| "learning_rate": 1.9658119658119658e-06, | |
| "loss": 0.2398, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 40.01846153846154, | |
| "grad_norm": 0.05890893191099167, | |
| "learning_rate": 1.948717948717949e-06, | |
| "loss": 0.0009, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "grad_norm": 0.00470241904258728, | |
| "learning_rate": 1.931623931623932e-06, | |
| "loss": 0.001, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 40.020153846153846, | |
| "eval_accuracy": 0.7954545454545454, | |
| "eval_loss": 1.3847745656967163, | |
| "eval_runtime": 17.5699, | |
| "eval_samples_per_second": 2.504, | |
| "eval_steps_per_second": 1.252, | |
| "step": 5371 | |
| }, | |
| { | |
| "epoch": 41.001384615384616, | |
| "grad_norm": 0.01356154028326273, | |
| "learning_rate": 1.9145299145299148e-06, | |
| "loss": 0.001, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 41.002923076923075, | |
| "grad_norm": 0.07007551938295364, | |
| "learning_rate": 1.8974358974358975e-06, | |
| "loss": 0.1296, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 41.00446153846154, | |
| "grad_norm": 0.02663712576031685, | |
| "learning_rate": 1.8803418803418804e-06, | |
| "loss": 0.0009, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 41.006, | |
| "grad_norm": 0.05243377387523651, | |
| "learning_rate": 1.8632478632478635e-06, | |
| "loss": 0.001, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 41.00753846153846, | |
| "grad_norm": 0.0023830588907003403, | |
| "learning_rate": 1.8461538461538465e-06, | |
| "loss": 0.0006, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 41.009076923076925, | |
| "grad_norm": 0.09497368335723877, | |
| "learning_rate": 1.8290598290598292e-06, | |
| "loss": 0.3231, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 41.010615384615384, | |
| "grad_norm": 0.004982765763998032, | |
| "learning_rate": 1.811965811965812e-06, | |
| "loss": 0.0003, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 41.01215384615384, | |
| "grad_norm": 0.005158687941730022, | |
| "learning_rate": 1.794871794871795e-06, | |
| "loss": 0.1315, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 41.01369230769231, | |
| "grad_norm": 0.05562686175107956, | |
| "learning_rate": 1.777777777777778e-06, | |
| "loss": 0.001, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 41.01523076923077, | |
| "grad_norm": 0.03336481377482414, | |
| "learning_rate": 1.7606837606837609e-06, | |
| "loss": 0.0307, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 41.01676923076923, | |
| "grad_norm": 0.02353920042514801, | |
| "learning_rate": 1.7435897435897436e-06, | |
| "loss": 0.0127, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 41.018307692307694, | |
| "grad_norm": 0.00431075831875205, | |
| "learning_rate": 1.7264957264957265e-06, | |
| "loss": 0.2484, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 41.01984615384615, | |
| "grad_norm": 0.0029032740276306868, | |
| "learning_rate": 1.7094017094017097e-06, | |
| "loss": 0.7371, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 41.020153846153846, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8425719738006592, | |
| "eval_runtime": 17.5477, | |
| "eval_samples_per_second": 2.507, | |
| "eval_steps_per_second": 1.254, | |
| "step": 5502 | |
| }, | |
| { | |
| "epoch": 42.001230769230766, | |
| "grad_norm": 0.05254608392715454, | |
| "learning_rate": 1.6923076923076926e-06, | |
| "loss": 0.6613, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 42.00276923076923, | |
| "grad_norm": 0.004602998960763216, | |
| "learning_rate": 1.6752136752136753e-06, | |
| "loss": 0.0007, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 42.00430769230769, | |
| "grad_norm": 0.04102243110537529, | |
| "learning_rate": 1.6581196581196582e-06, | |
| "loss": 0.1788, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 42.00584615384616, | |
| "grad_norm": 0.03823509067296982, | |
| "learning_rate": 1.6410256410256412e-06, | |
| "loss": 0.0006, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 42.007384615384616, | |
| "grad_norm": 0.0019409230444580317, | |
| "learning_rate": 1.623931623931624e-06, | |
| "loss": 0.0002, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 42.008923076923075, | |
| "grad_norm": 0.033418264240026474, | |
| "learning_rate": 1.606837606837607e-06, | |
| "loss": 0.2557, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 42.01046153846154, | |
| "grad_norm": 0.01538726408034563, | |
| "learning_rate": 1.5897435897435897e-06, | |
| "loss": 0.6611, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 42.012, | |
| "grad_norm": 0.004290467128157616, | |
| "learning_rate": 1.5726495726495727e-06, | |
| "loss": 0.1861, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 42.01353846153846, | |
| "grad_norm": 0.07905274629592896, | |
| "learning_rate": 1.5555555555555558e-06, | |
| "loss": 0.0012, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 42.015076923076926, | |
| "grad_norm": 0.08152870088815689, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 0.094, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 42.016615384615385, | |
| "grad_norm": 0.016214873641729355, | |
| "learning_rate": 1.5213675213675214e-06, | |
| "loss": 0.2491, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 42.018153846153844, | |
| "grad_norm": 0.01419926155358553, | |
| "learning_rate": 1.5042735042735044e-06, | |
| "loss": 0.578, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 42.01969230769231, | |
| "grad_norm": 0.002875091042369604, | |
| "learning_rate": 1.4871794871794873e-06, | |
| "loss": 0.0008, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 42.020153846153846, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9709961414337158, | |
| "eval_runtime": 17.8535, | |
| "eval_samples_per_second": 2.465, | |
| "eval_steps_per_second": 1.232, | |
| "step": 5633 | |
| }, | |
| { | |
| "epoch": 43.00107692307692, | |
| "grad_norm": 156.9081573486328, | |
| "learning_rate": 1.4700854700854702e-06, | |
| "loss": 0.8723, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 43.00261538461538, | |
| "grad_norm": 0.02744956687092781, | |
| "learning_rate": 1.4529914529914531e-06, | |
| "loss": 0.0008, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 43.00415384615385, | |
| "grad_norm": 0.1306835263967514, | |
| "learning_rate": 1.4358974358974359e-06, | |
| "loss": 0.0472, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 43.00569230769231, | |
| "grad_norm": 0.0026254348922520876, | |
| "learning_rate": 1.4188034188034188e-06, | |
| "loss": 0.0005, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 43.007230769230766, | |
| "grad_norm": 0.7486156821250916, | |
| "learning_rate": 1.401709401709402e-06, | |
| "loss": 0.0014, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 43.00876923076923, | |
| "grad_norm": 0.002213951898738742, | |
| "learning_rate": 1.3846153846153848e-06, | |
| "loss": 0.2504, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 43.01030769230769, | |
| "grad_norm": 0.06451749056577682, | |
| "learning_rate": 1.3675213675213678e-06, | |
| "loss": 0.2848, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 43.01184615384616, | |
| "grad_norm": 0.0941164568066597, | |
| "learning_rate": 1.3504273504273505e-06, | |
| "loss": 0.0006, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 43.013384615384616, | |
| "grad_norm": 0.07757952809333801, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.2559, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 43.014923076923075, | |
| "grad_norm": 0.1075524091720581, | |
| "learning_rate": 1.3162393162393163e-06, | |
| "loss": 0.0007, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 43.01646153846154, | |
| "grad_norm": 0.02597893215715885, | |
| "learning_rate": 1.2991452991452993e-06, | |
| "loss": 0.0005, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 43.018, | |
| "grad_norm": 0.08702472597360611, | |
| "learning_rate": 1.282051282051282e-06, | |
| "loss": 0.0884, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 43.01953846153846, | |
| "grad_norm": 0.002402510493993759, | |
| "learning_rate": 1.264957264957265e-06, | |
| "loss": 0.2964, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 43.020153846153846, | |
| "eval_accuracy": 0.7045454545454546, | |
| "eval_loss": 2.2086830139160156, | |
| "eval_runtime": 17.4539, | |
| "eval_samples_per_second": 2.521, | |
| "eval_steps_per_second": 1.26, | |
| "step": 5764 | |
| }, | |
| { | |
| "epoch": 44.00092307692308, | |
| "grad_norm": 2.7798829078674316, | |
| "learning_rate": 1.247863247863248e-06, | |
| "loss": 0.3667, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 44.00246153846154, | |
| "grad_norm": 0.12651492655277252, | |
| "learning_rate": 1.230769230769231e-06, | |
| "loss": 0.0051, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 44.004, | |
| "grad_norm": 0.05158364400267601, | |
| "learning_rate": 1.2136752136752137e-06, | |
| "loss": 0.1121, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 44.005538461538464, | |
| "grad_norm": 0.021347902715206146, | |
| "learning_rate": 1.1965811965811968e-06, | |
| "loss": 0.262, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 44.00707692307692, | |
| "grad_norm": 0.0025240927934646606, | |
| "learning_rate": 1.1794871794871795e-06, | |
| "loss": 0.0025, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 44.00861538461538, | |
| "grad_norm": 0.1594618260860443, | |
| "learning_rate": 1.1623931623931625e-06, | |
| "loss": 0.4118, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 44.01015384615385, | |
| "grad_norm": 0.002951054833829403, | |
| "learning_rate": 1.1452991452991454e-06, | |
| "loss": 0.0072, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 44.01169230769231, | |
| "grad_norm": 0.03157424181699753, | |
| "learning_rate": 1.1282051282051283e-06, | |
| "loss": 0.0186, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 44.013230769230766, | |
| "grad_norm": 0.03437066078186035, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.2726, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 44.01476923076923, | |
| "grad_norm": 10.564559936523438, | |
| "learning_rate": 1.0940170940170942e-06, | |
| "loss": 0.0014, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 44.01630769230769, | |
| "grad_norm": 0.00581646803766489, | |
| "learning_rate": 1.076923076923077e-06, | |
| "loss": 0.0004, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 44.01784615384615, | |
| "grad_norm": 0.017418500036001205, | |
| "learning_rate": 1.0598290598290598e-06, | |
| "loss": 0.2092, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 44.01938461538462, | |
| "grad_norm": 0.01517485175281763, | |
| "learning_rate": 1.042735042735043e-06, | |
| "loss": 0.0008, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 44.020153846153846, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 1.5877751111984253, | |
| "eval_runtime": 18.208, | |
| "eval_samples_per_second": 2.417, | |
| "eval_steps_per_second": 1.208, | |
| "step": 5895 | |
| }, | |
| { | |
| "epoch": 45.00076923076923, | |
| "grad_norm": 0.013111915439367294, | |
| "learning_rate": 1.0256410256410257e-06, | |
| "loss": 0.0004, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 45.002307692307696, | |
| "grad_norm": 0.03663197532296181, | |
| "learning_rate": 1.0085470085470086e-06, | |
| "loss": 0.2236, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 45.003846153846155, | |
| "grad_norm": 0.0016930019482970238, | |
| "learning_rate": 9.914529914529915e-07, | |
| "loss": 0.0002, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 45.005384615384614, | |
| "grad_norm": 0.18426787853240967, | |
| "learning_rate": 9.743589743589745e-07, | |
| "loss": 0.4888, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 45.00692307692308, | |
| "grad_norm": 0.002058043610304594, | |
| "learning_rate": 9.572649572649574e-07, | |
| "loss": 0.0005, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 45.00846153846154, | |
| "grad_norm": 0.0022759425919502974, | |
| "learning_rate": 9.401709401709402e-07, | |
| "loss": 0.0513, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "grad_norm": 0.01901968941092491, | |
| "learning_rate": 9.230769230769232e-07, | |
| "loss": 0.0003, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 45.011538461538464, | |
| "grad_norm": 0.07206692546606064, | |
| "learning_rate": 9.05982905982906e-07, | |
| "loss": 0.0049, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 45.01307692307692, | |
| "grad_norm": 0.01167149655520916, | |
| "learning_rate": 8.88888888888889e-07, | |
| "loss": 0.0045, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 45.01461538461538, | |
| "grad_norm": 0.007669601123780012, | |
| "learning_rate": 8.717948717948718e-07, | |
| "loss": 0.2417, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 45.01615384615385, | |
| "grad_norm": 0.014131017029285431, | |
| "learning_rate": 8.547008547008548e-07, | |
| "loss": 0.0396, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 45.01769230769231, | |
| "grad_norm": 0.039985980838537216, | |
| "learning_rate": 8.376068376068377e-07, | |
| "loss": 0.0792, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 45.01923076923077, | |
| "grad_norm": 0.02558540366590023, | |
| "learning_rate": 8.205128205128206e-07, | |
| "loss": 0.0005, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 45.020153846153846, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8425674438476562, | |
| "eval_runtime": 17.7182, | |
| "eval_samples_per_second": 2.483, | |
| "eval_steps_per_second": 1.242, | |
| "step": 6026 | |
| }, | |
| { | |
| "epoch": 46.00061538461539, | |
| "grad_norm": 0.013401100412011147, | |
| "learning_rate": 8.034188034188035e-07, | |
| "loss": 0.0056, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 46.002153846153846, | |
| "grad_norm": 0.004234934225678444, | |
| "learning_rate": 7.863247863247863e-07, | |
| "loss": 0.0005, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 46.003692307692305, | |
| "grad_norm": 0.006464138627052307, | |
| "learning_rate": 7.692307692307694e-07, | |
| "loss": 0.0007, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 46.00523076923077, | |
| "grad_norm": 1.2366927862167358, | |
| "learning_rate": 7.521367521367522e-07, | |
| "loss": 0.0004, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 46.00676923076923, | |
| "grad_norm": 0.0016147018177434802, | |
| "learning_rate": 7.350427350427351e-07, | |
| "loss": 0.0436, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 46.00830769230769, | |
| "grad_norm": 0.01653667353093624, | |
| "learning_rate": 7.179487179487179e-07, | |
| "loss": 0.0004, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 46.009846153846155, | |
| "grad_norm": 0.0641694962978363, | |
| "learning_rate": 7.00854700854701e-07, | |
| "loss": 0.371, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 46.011384615384614, | |
| "grad_norm": 0.011850905604660511, | |
| "learning_rate": 6.837606837606839e-07, | |
| "loss": 0.0198, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 46.01292307692308, | |
| "grad_norm": 0.005450480617582798, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 0.0005, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 46.01446153846154, | |
| "grad_norm": 0.10996601730585098, | |
| "learning_rate": 6.495726495726496e-07, | |
| "loss": 0.6024, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 46.016, | |
| "grad_norm": 0.03566615656018257, | |
| "learning_rate": 6.324786324786325e-07, | |
| "loss": 0.0006, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 46.017538461538464, | |
| "grad_norm": 0.002352552255615592, | |
| "learning_rate": 6.153846153846155e-07, | |
| "loss": 0.0217, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 46.01907692307692, | |
| "grad_norm": 37.61919403076172, | |
| "learning_rate": 5.982905982905984e-07, | |
| "loss": 0.4393, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 46.020153846153846, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 1.7192864418029785, | |
| "eval_runtime": 17.5396, | |
| "eval_samples_per_second": 2.509, | |
| "eval_steps_per_second": 1.254, | |
| "step": 6157 | |
| }, | |
| { | |
| "epoch": 47.000461538461536, | |
| "grad_norm": 0.007557816803455353, | |
| "learning_rate": 5.811965811965812e-07, | |
| "loss": 0.3245, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 47.002, | |
| "grad_norm": 0.005661817733198404, | |
| "learning_rate": 5.641025641025642e-07, | |
| "loss": 0.0674, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 47.00353846153846, | |
| "grad_norm": 0.003017798298969865, | |
| "learning_rate": 5.470085470085471e-07, | |
| "loss": 0.0003, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 47.00507692307692, | |
| "grad_norm": 0.0021825481671839952, | |
| "learning_rate": 5.299145299145299e-07, | |
| "loss": 0.0069, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 47.00661538461539, | |
| "grad_norm": 0.007291525602340698, | |
| "learning_rate": 5.128205128205128e-07, | |
| "loss": 0.0029, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 47.008153846153846, | |
| "grad_norm": 0.013350569643080235, | |
| "learning_rate": 4.957264957264958e-07, | |
| "loss": 0.0012, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 47.009692307692305, | |
| "grad_norm": 0.014852489344775677, | |
| "learning_rate": 4.786324786324787e-07, | |
| "loss": 0.3692, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 47.01123076923077, | |
| "grad_norm": 0.0038931334856897593, | |
| "learning_rate": 4.615384615384616e-07, | |
| "loss": 0.0002, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 47.01276923076923, | |
| "grad_norm": 0.004401617683470249, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 0.002, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 47.01430769230769, | |
| "grad_norm": 0.0036828203592449427, | |
| "learning_rate": 4.273504273504274e-07, | |
| "loss": 0.0002, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 47.015846153846155, | |
| "grad_norm": 0.023323748260736465, | |
| "learning_rate": 4.102564102564103e-07, | |
| "loss": 0.0006, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 47.017384615384614, | |
| "grad_norm": 0.026729466393589973, | |
| "learning_rate": 3.9316239316239316e-07, | |
| "loss": 0.2089, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 47.01892307692308, | |
| "grad_norm": 0.02545813098549843, | |
| "learning_rate": 3.760683760683761e-07, | |
| "loss": 0.0036, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 47.020153846153846, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9741100072860718, | |
| "eval_runtime": 17.4395, | |
| "eval_samples_per_second": 2.523, | |
| "eval_steps_per_second": 1.262, | |
| "step": 6288 | |
| }, | |
| { | |
| "epoch": 48.00030769230769, | |
| "grad_norm": 0.0016434225253760815, | |
| "learning_rate": 3.5897435897435896e-07, | |
| "loss": 0.6999, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 48.00184615384615, | |
| "grad_norm": 0.025444453582167625, | |
| "learning_rate": 3.4188034188034194e-07, | |
| "loss": 0.3366, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 48.00338461538462, | |
| "grad_norm": 0.05276023596525192, | |
| "learning_rate": 3.247863247863248e-07, | |
| "loss": 0.0003, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 48.00492307692308, | |
| "grad_norm": 0.0075876726768910885, | |
| "learning_rate": 3.0769230769230774e-07, | |
| "loss": 0.0008, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 48.00646153846154, | |
| "grad_norm": 0.026767443865537643, | |
| "learning_rate": 2.905982905982906e-07, | |
| "loss": 0.0007, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 48.008, | |
| "grad_norm": 0.015468932688236237, | |
| "learning_rate": 2.7350427350427354e-07, | |
| "loss": 0.0004, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 48.00953846153846, | |
| "grad_norm": 0.012135795317590237, | |
| "learning_rate": 2.564102564102564e-07, | |
| "loss": 0.0921, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 48.01107692307692, | |
| "grad_norm": 372.2685241699219, | |
| "learning_rate": 2.3931623931623934e-07, | |
| "loss": 0.4548, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 48.01261538461539, | |
| "grad_norm": 0.0019256267696619034, | |
| "learning_rate": 2.2222222222222224e-07, | |
| "loss": 0.0002, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 48.014153846153846, | |
| "grad_norm": 47.45166778564453, | |
| "learning_rate": 2.0512820512820514e-07, | |
| "loss": 0.5025, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 48.015692307692305, | |
| "grad_norm": 6.303526878356934, | |
| "learning_rate": 1.8803418803418804e-07, | |
| "loss": 0.0102, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 48.01723076923077, | |
| "grad_norm": 0.018150515854358673, | |
| "learning_rate": 1.7094017094017097e-07, | |
| "loss": 0.3414, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 48.01876923076923, | |
| "grad_norm": 0.15965531766414642, | |
| "learning_rate": 1.5384615384615387e-07, | |
| "loss": 0.0005, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 48.020153846153846, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 1.838250994682312, | |
| "eval_runtime": 17.6519, | |
| "eval_samples_per_second": 2.493, | |
| "eval_steps_per_second": 1.246, | |
| "step": 6419 | |
| }, | |
| { | |
| "epoch": 49.00015384615384, | |
| "grad_norm": 0.0094909043982625, | |
| "learning_rate": 1.3675213675213677e-07, | |
| "loss": 0.3577, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 49.00169230769231, | |
| "grad_norm": 0.03169747814536095, | |
| "learning_rate": 1.1965811965811967e-07, | |
| "loss": 0.0004, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 49.00323076923077, | |
| "grad_norm": 0.0018686068942770362, | |
| "learning_rate": 1.0256410256410257e-07, | |
| "loss": 0.0003, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 49.00476923076923, | |
| "grad_norm": 80.7922592163086, | |
| "learning_rate": 8.547008547008549e-08, | |
| "loss": 0.3405, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 49.00630769230769, | |
| "grad_norm": 0.030466891825199127, | |
| "learning_rate": 6.837606837606839e-08, | |
| "loss": 0.0194, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 49.00784615384615, | |
| "grad_norm": 0.017399143427610397, | |
| "learning_rate": 5.1282051282051286e-08, | |
| "loss": 0.0004, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 49.00938461538462, | |
| "grad_norm": 0.010285567492246628, | |
| "learning_rate": 3.418803418803419e-08, | |
| "loss": 0.45, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 49.01092307692308, | |
| "grad_norm": 0.01710204966366291, | |
| "learning_rate": 1.7094017094017096e-08, | |
| "loss": 0.1725, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "grad_norm": 0.008785544894635677, | |
| "learning_rate": 0.0, | |
| "loss": 0.1776, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 1.8362475633621216, | |
| "eval_runtime": 17.9697, | |
| "eval_samples_per_second": 2.449, | |
| "eval_steps_per_second": 1.224, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "step": 6500, | |
| "total_flos": 5.686818180940844e+19, | |
| "train_loss": 0.479073266537269, | |
| "train_runtime": 14090.8004, | |
| "train_samples_per_second": 0.923, | |
| "train_steps_per_second": 0.461 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "eval_accuracy": 0.8409090909090909, | |
| "eval_loss": 0.7553315758705139, | |
| "eval_runtime": 17.4312, | |
| "eval_samples_per_second": 2.524, | |
| "eval_steps_per_second": 1.262, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "eval_accuracy": 0.8409090909090909, | |
| "eval_loss": 0.7553314566612244, | |
| "eval_runtime": 17.4939, | |
| "eval_samples_per_second": 2.515, | |
| "eval_steps_per_second": 1.258, | |
| "step": 6500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 6500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.686818180940844e+19, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |