| { | |
| "best_metric": 0.7333333333333333, | |
| "best_model_checkpoint": "CTMAE-P2-V2-S2/checkpoint-3406", | |
| "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": 5.2847771644592285, | |
| "learning_rate": 1.5384615384615387e-07, | |
| "loss": 0.7696, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003076923076923077, | |
| "grad_norm": 1.212140679359436, | |
| "learning_rate": 3.0769230769230774e-07, | |
| "loss": 0.7431, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004615384615384616, | |
| "grad_norm": 1.4698514938354492, | |
| "learning_rate": 4.615384615384616e-07, | |
| "loss": 0.7175, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006153846153846154, | |
| "grad_norm": 1.5410373210906982, | |
| "learning_rate": 6.153846153846155e-07, | |
| "loss": 0.7289, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007692307692307693, | |
| "grad_norm": 4.85338830947876, | |
| "learning_rate": 7.692307692307694e-07, | |
| "loss": 0.7056, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009230769230769232, | |
| "grad_norm": 1.496706485748291, | |
| "learning_rate": 9.230769230769232e-07, | |
| "loss": 0.6967, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010769230769230769, | |
| "grad_norm": 4.367652893066406, | |
| "learning_rate": 1.076923076923077e-06, | |
| "loss": 0.6823, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.012307692307692308, | |
| "grad_norm": 5.289880275726318, | |
| "learning_rate": 1.230769230769231e-06, | |
| "loss": 0.6567, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013846153846153847, | |
| "grad_norm": 4.303277969360352, | |
| "learning_rate": 1.3846153846153848e-06, | |
| "loss": 0.6219, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.015384615384615385, | |
| "grad_norm": 3.9366531372070312, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 0.6273, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016923076923076923, | |
| "grad_norm": 4.274877548217773, | |
| "learning_rate": 1.6923076923076926e-06, | |
| "loss": 0.6458, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.018461538461538463, | |
| "grad_norm": 4.064288139343262, | |
| "learning_rate": 1.8461538461538465e-06, | |
| "loss": 0.4591, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 6.01157808303833, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6135, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.020153846153846154, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.7941694259643555, | |
| "eval_runtime": 17.7468, | |
| "eval_samples_per_second": 2.536, | |
| "eval_steps_per_second": 1.296, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.0013846153846153, | |
| "grad_norm": 5.232850074768066, | |
| "learning_rate": 2.153846153846154e-06, | |
| "loss": 0.5004, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.002923076923077, | |
| "grad_norm": 5.314540863037109, | |
| "learning_rate": 2.307692307692308e-06, | |
| "loss": 0.582, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0044615384615385, | |
| "grad_norm": 6.0984063148498535, | |
| "learning_rate": 2.461538461538462e-06, | |
| "loss": 0.9068, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.006, | |
| "grad_norm": 6.651105880737305, | |
| "learning_rate": 2.615384615384616e-06, | |
| "loss": 0.6342, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0075384615384615, | |
| "grad_norm": 5.469671726226807, | |
| "learning_rate": 2.7692307692307697e-06, | |
| "loss": 0.6402, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.009076923076923, | |
| "grad_norm": 19.993928909301758, | |
| "learning_rate": 2.9230769230769236e-06, | |
| "loss": 0.6455, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0106153846153847, | |
| "grad_norm": 5.2603068351745605, | |
| "learning_rate": 3.0769230769230774e-06, | |
| "loss": 0.669, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0121538461538462, | |
| "grad_norm": 4.615805625915527, | |
| "learning_rate": 3.2307692307692313e-06, | |
| "loss": 0.6588, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.0136923076923077, | |
| "grad_norm": 30.721487045288086, | |
| "learning_rate": 3.384615384615385e-06, | |
| "loss": 0.8104, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0152307692307692, | |
| "grad_norm": 30.413789749145508, | |
| "learning_rate": 3.538461538461539e-06, | |
| "loss": 0.3544, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0167692307692309, | |
| "grad_norm": 45.655120849609375, | |
| "learning_rate": 3.692307692307693e-06, | |
| "loss": 1.481, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0183076923076924, | |
| "grad_norm": 2.3307831287384033, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 1.0255, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0198461538461538, | |
| "grad_norm": 0.3746989369392395, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.4654, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0201538461538462, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 2.2123780250549316, | |
| "eval_runtime": 16.8612, | |
| "eval_samples_per_second": 2.669, | |
| "eval_steps_per_second": 1.364, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.0012307692307694, | |
| "grad_norm": 25.59384536743164, | |
| "learning_rate": 4.1538461538461545e-06, | |
| "loss": 1.9937, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.0027692307692306, | |
| "grad_norm": 6.004070281982422, | |
| "learning_rate": 4.307692307692308e-06, | |
| "loss": 0.7743, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0043076923076923, | |
| "grad_norm": 9.71780014038086, | |
| "learning_rate": 4.461538461538462e-06, | |
| "loss": 0.7844, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.005846153846154, | |
| "grad_norm": 2.8564810752868652, | |
| "learning_rate": 4.615384615384616e-06, | |
| "loss": 0.6274, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0073846153846153, | |
| "grad_norm": 3.12308669090271, | |
| "learning_rate": 4.76923076923077e-06, | |
| "loss": 0.569, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.008923076923077, | |
| "grad_norm": 28.34366226196289, | |
| "learning_rate": 4.923076923076924e-06, | |
| "loss": 0.6533, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.0104615384615383, | |
| "grad_norm": 25.547155380249023, | |
| "learning_rate": 5.076923076923077e-06, | |
| "loss": 0.6547, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.012, | |
| "grad_norm": 2.939312219619751, | |
| "learning_rate": 5.230769230769232e-06, | |
| "loss": 0.9865, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.0135384615384617, | |
| "grad_norm": 1.1657027006149292, | |
| "learning_rate": 5.384615384615385e-06, | |
| "loss": 0.6649, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.015076923076923, | |
| "grad_norm": 21.5581111907959, | |
| "learning_rate": 5.538461538461539e-06, | |
| "loss": 1.2285, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.0166153846153847, | |
| "grad_norm": 2.9709372520446777, | |
| "learning_rate": 5.692307692307692e-06, | |
| "loss": 1.1636, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.018153846153846, | |
| "grad_norm": 0.4270724356174469, | |
| "learning_rate": 5.846153846153847e-06, | |
| "loss": 0.4678, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0196923076923077, | |
| "grad_norm": 29.26959228515625, | |
| "learning_rate": 6e-06, | |
| "loss": 1.1122, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.8385518789291382, | |
| "eval_runtime": 16.9236, | |
| "eval_samples_per_second": 2.659, | |
| "eval_steps_per_second": 1.359, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 3.001076923076923, | |
| "grad_norm": 0.8092571496963501, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 1.0154, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.0026153846153845, | |
| "grad_norm": 16.8879451751709, | |
| "learning_rate": 6.307692307692308e-06, | |
| "loss": 0.606, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.004153846153846, | |
| "grad_norm": 0.8767936825752258, | |
| "learning_rate": 6.461538461538463e-06, | |
| "loss": 1.0086, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.005692307692308, | |
| "grad_norm": 1.1776772737503052, | |
| "learning_rate": 6.615384615384616e-06, | |
| "loss": 1.2581, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.007230769230769, | |
| "grad_norm": 0.7793283462524414, | |
| "learning_rate": 6.76923076923077e-06, | |
| "loss": 0.5119, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.008769230769231, | |
| "grad_norm": 13.737873077392578, | |
| "learning_rate": 6.923076923076923e-06, | |
| "loss": 1.1251, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.010307692307692, | |
| "grad_norm": 24.41330337524414, | |
| "learning_rate": 7.076923076923078e-06, | |
| "loss": 1.1902, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.011846153846154, | |
| "grad_norm": 11.802783012390137, | |
| "learning_rate": 7.230769230769231e-06, | |
| "loss": 0.6729, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.0133846153846156, | |
| "grad_norm": 0.9507260322570801, | |
| "learning_rate": 7.384615384615386e-06, | |
| "loss": 0.8077, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.014923076923077, | |
| "grad_norm": 9.83351993560791, | |
| "learning_rate": 7.538461538461539e-06, | |
| "loss": 1.2555, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.0164615384615385, | |
| "grad_norm": 1.0928640365600586, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.6471, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.018, | |
| "grad_norm": 8.9114990234375, | |
| "learning_rate": 7.846153846153847e-06, | |
| "loss": 1.445, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.0195384615384615, | |
| "grad_norm": 2.2783730030059814, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.7797, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.9344209432601929, | |
| "eval_runtime": 16.6785, | |
| "eval_samples_per_second": 2.698, | |
| "eval_steps_per_second": 1.379, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 4.000923076923077, | |
| "grad_norm": 1.9133858680725098, | |
| "learning_rate": 8.153846153846154e-06, | |
| "loss": 0.3198, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.002461538461539, | |
| "grad_norm": 11.723381996154785, | |
| "learning_rate": 8.307692307692309e-06, | |
| "loss": 0.789, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.004, | |
| "grad_norm": 8.412501335144043, | |
| "learning_rate": 8.461538461538462e-06, | |
| "loss": 0.8407, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.005538461538461, | |
| "grad_norm": 6.085928916931152, | |
| "learning_rate": 8.615384615384617e-06, | |
| "loss": 1.4121, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.007076923076923, | |
| "grad_norm": 3.619480609893799, | |
| "learning_rate": 8.76923076923077e-06, | |
| "loss": 0.5817, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.008615384615385, | |
| "grad_norm": 4.760242938995361, | |
| "learning_rate": 8.923076923076925e-06, | |
| "loss": 0.5719, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.010153846153846, | |
| "grad_norm": 3.11899471282959, | |
| "learning_rate": 9.076923076923078e-06, | |
| "loss": 0.7765, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.011692307692308, | |
| "grad_norm": 18.84898567199707, | |
| "learning_rate": 9.230769230769232e-06, | |
| "loss": 0.6335, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.013230769230769, | |
| "grad_norm": 20.825647354125977, | |
| "learning_rate": 9.384615384615385e-06, | |
| "loss": 0.6309, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.014769230769231, | |
| "grad_norm": 37.241172790527344, | |
| "learning_rate": 9.53846153846154e-06, | |
| "loss": 1.5333, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.016307692307692, | |
| "grad_norm": 3.763845682144165, | |
| "learning_rate": 9.692307692307693e-06, | |
| "loss": 0.6611, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.017846153846154, | |
| "grad_norm": 20.588300704956055, | |
| "learning_rate": 9.846153846153848e-06, | |
| "loss": 0.4795, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.019384615384616, | |
| "grad_norm": 0.8719319701194763, | |
| "learning_rate": 1e-05, | |
| "loss": 1.379, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.5755258798599243, | |
| "eval_runtime": 16.7329, | |
| "eval_samples_per_second": 2.689, | |
| "eval_steps_per_second": 1.375, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 5.00076923076923, | |
| "grad_norm": 0.8349611759185791, | |
| "learning_rate": 9.982905982905984e-06, | |
| "loss": 0.7358, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.002307692307692, | |
| "grad_norm": 0.26314833760261536, | |
| "learning_rate": 9.965811965811966e-06, | |
| "loss": 1.034, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.003846153846154, | |
| "grad_norm": 7.706874847412109, | |
| "learning_rate": 9.94871794871795e-06, | |
| "loss": 1.2344, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.0053846153846155, | |
| "grad_norm": 15.977445602416992, | |
| "learning_rate": 9.931623931623933e-06, | |
| "loss": 0.676, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.006923076923077, | |
| "grad_norm": 1.3869924545288086, | |
| "learning_rate": 9.914529914529915e-06, | |
| "loss": 0.9367, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.008461538461538, | |
| "grad_norm": 1.159854531288147, | |
| "learning_rate": 9.897435897435899e-06, | |
| "loss": 0.7501, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "grad_norm": 29.868873596191406, | |
| "learning_rate": 9.880341880341882e-06, | |
| "loss": 1.0558, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.0115384615384615, | |
| "grad_norm": 1.1816397905349731, | |
| "learning_rate": 9.863247863247864e-06, | |
| "loss": 0.7669, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.013076923076923, | |
| "grad_norm": 14.27903938293457, | |
| "learning_rate": 9.846153846153848e-06, | |
| "loss": 1.0092, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.014615384615385, | |
| "grad_norm": 8.305230140686035, | |
| "learning_rate": 9.82905982905983e-06, | |
| "loss": 0.8387, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.016153846153846, | |
| "grad_norm": 2.076962947845459, | |
| "learning_rate": 9.811965811965812e-06, | |
| "loss": 0.7549, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.0176923076923075, | |
| "grad_norm": 0.31316885352134705, | |
| "learning_rate": 9.794871794871795e-06, | |
| "loss": 0.8166, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.019230769230769, | |
| "grad_norm": 1.080019474029541, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 0.7305, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.4677060842514038, | |
| "eval_runtime": 16.6127, | |
| "eval_samples_per_second": 2.709, | |
| "eval_steps_per_second": 1.384, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 6.000615384615385, | |
| "grad_norm": 12.071111679077148, | |
| "learning_rate": 9.76068376068376e-06, | |
| "loss": 0.7929, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.002153846153846, | |
| "grad_norm": 0.6092038154602051, | |
| "learning_rate": 9.743589743589744e-06, | |
| "loss": 0.9152, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.003692307692308, | |
| "grad_norm": 0.3058328926563263, | |
| "learning_rate": 9.726495726495728e-06, | |
| "loss": 1.0741, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.005230769230769, | |
| "grad_norm": 0.9477494955062866, | |
| "learning_rate": 9.70940170940171e-06, | |
| "loss": 1.1571, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.006769230769231, | |
| "grad_norm": 0.8147485256195068, | |
| "learning_rate": 9.692307692307693e-06, | |
| "loss": 0.5421, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.008307692307692, | |
| "grad_norm": 12.7311372756958, | |
| "learning_rate": 9.675213675213677e-06, | |
| "loss": 1.1544, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.009846153846154, | |
| "grad_norm": 0.5311498045921326, | |
| "learning_rate": 9.658119658119659e-06, | |
| "loss": 0.6643, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.011384615384616, | |
| "grad_norm": 2.1158626079559326, | |
| "learning_rate": 9.641025641025642e-06, | |
| "loss": 1.1313, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.012923076923077, | |
| "grad_norm": 1.427776575088501, | |
| "learning_rate": 9.623931623931626e-06, | |
| "loss": 0.4634, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.014461538461538, | |
| "grad_norm": 1.0464180707931519, | |
| "learning_rate": 9.606837606837607e-06, | |
| "loss": 0.909, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.016, | |
| "grad_norm": 0.2842622697353363, | |
| "learning_rate": 9.589743589743591e-06, | |
| "loss": 0.3163, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.017538461538462, | |
| "grad_norm": 1.2773646116256714, | |
| "learning_rate": 9.572649572649575e-06, | |
| "loss": 1.5998, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.019076923076923, | |
| "grad_norm": 1.1219149827957153, | |
| "learning_rate": 9.555555555555556e-06, | |
| "loss": 0.9115, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.5456373691558838, | |
| "eval_runtime": 16.3982, | |
| "eval_samples_per_second": 2.744, | |
| "eval_steps_per_second": 1.403, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 7.000461538461538, | |
| "grad_norm": 0.5472283959388733, | |
| "learning_rate": 9.53846153846154e-06, | |
| "loss": 0.7122, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 7.002, | |
| "grad_norm": 0.8457459807395935, | |
| "learning_rate": 9.521367521367522e-06, | |
| "loss": 0.9806, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 7.0035384615384615, | |
| "grad_norm": 1.165386438369751, | |
| "learning_rate": 9.504273504273504e-06, | |
| "loss": 0.8217, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 7.005076923076923, | |
| "grad_norm": 12.627142906188965, | |
| "learning_rate": 9.487179487179487e-06, | |
| "loss": 0.7902, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.006615384615385, | |
| "grad_norm": 0.38273462653160095, | |
| "learning_rate": 9.470085470085471e-06, | |
| "loss": 1.0762, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.008153846153846, | |
| "grad_norm": 8.824048042297363, | |
| "learning_rate": 9.452991452991453e-06, | |
| "loss": 1.0086, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.0096923076923074, | |
| "grad_norm": 1.1210700273513794, | |
| "learning_rate": 9.435897435897436e-06, | |
| "loss": 0.6204, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.011230769230769, | |
| "grad_norm": 0.3700163662433624, | |
| "learning_rate": 9.41880341880342e-06, | |
| "loss": 0.8626, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 7.012769230769231, | |
| "grad_norm": 0.08994351327419281, | |
| "learning_rate": 9.401709401709402e-06, | |
| "loss": 0.3818, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.014307692307693, | |
| "grad_norm": 0.21013842523097992, | |
| "learning_rate": 9.384615384615385e-06, | |
| "loss": 0.7605, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.015846153846154, | |
| "grad_norm": 0.6485298871994019, | |
| "learning_rate": 9.367521367521369e-06, | |
| "loss": 1.3477, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.017384615384615, | |
| "grad_norm": 29.354290008544922, | |
| "learning_rate": 9.35042735042735e-06, | |
| "loss": 0.6712, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.018923076923077, | |
| "grad_norm": 0.6328514218330383, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 1.6622, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.21128511428833, | |
| "eval_runtime": 16.6333, | |
| "eval_samples_per_second": 2.705, | |
| "eval_steps_per_second": 1.383, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 8.000307692307691, | |
| "grad_norm": 2.450066566467285, | |
| "learning_rate": 9.316239316239318e-06, | |
| "loss": 0.6484, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 8.001846153846154, | |
| "grad_norm": 0.46529820561408997, | |
| "learning_rate": 9.2991452991453e-06, | |
| "loss": 0.7152, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 8.003384615384615, | |
| "grad_norm": 0.48791271448135376, | |
| "learning_rate": 9.282051282051283e-06, | |
| "loss": 1.435, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 8.004923076923077, | |
| "grad_norm": 0.24947817623615265, | |
| "learning_rate": 9.264957264957267e-06, | |
| "loss": 0.1725, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.006461538461538, | |
| "grad_norm": 27.861791610717773, | |
| "learning_rate": 9.247863247863249e-06, | |
| "loss": 2.2624, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 8.008, | |
| "grad_norm": 2.5722784996032715, | |
| "learning_rate": 9.230769230769232e-06, | |
| "loss": 1.0654, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.009538461538462, | |
| "grad_norm": 1.8892056941986084, | |
| "learning_rate": 9.213675213675214e-06, | |
| "loss": 0.7518, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.011076923076923, | |
| "grad_norm": 0.7132881879806519, | |
| "learning_rate": 9.196581196581196e-06, | |
| "loss": 0.3455, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.012615384615385, | |
| "grad_norm": 0.91068434715271, | |
| "learning_rate": 9.17948717948718e-06, | |
| "loss": 0.6097, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 8.014153846153846, | |
| "grad_norm": 46.84939956665039, | |
| "learning_rate": 9.162393162393163e-06, | |
| "loss": 1.5698, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 8.015692307692309, | |
| "grad_norm": 11.060514450073242, | |
| "learning_rate": 9.145299145299145e-06, | |
| "loss": 0.4629, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.01723076923077, | |
| "grad_norm": 0.8407790064811707, | |
| "learning_rate": 9.128205128205129e-06, | |
| "loss": 0.6518, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.01876923076923, | |
| "grad_norm": 0.9326026439666748, | |
| "learning_rate": 9.111111111111112e-06, | |
| "loss": 0.6868, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.845061182975769, | |
| "eval_runtime": 16.2458, | |
| "eval_samples_per_second": 2.77, | |
| "eval_steps_per_second": 1.416, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 9.000153846153847, | |
| "grad_norm": 0.1979643702507019, | |
| "learning_rate": 9.094017094017094e-06, | |
| "loss": 0.9976, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 9.001692307692307, | |
| "grad_norm": 17.694259643554688, | |
| "learning_rate": 9.076923076923078e-06, | |
| "loss": 0.9565, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 9.00323076923077, | |
| "grad_norm": 0.3465520143508911, | |
| "learning_rate": 9.059829059829061e-06, | |
| "loss": 1.0806, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.00476923076923, | |
| "grad_norm": 8.587890625, | |
| "learning_rate": 9.042735042735043e-06, | |
| "loss": 1.6741, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 9.006307692307692, | |
| "grad_norm": 1.3298053741455078, | |
| "learning_rate": 9.025641025641027e-06, | |
| "loss": 0.7533, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 9.007846153846154, | |
| "grad_norm": 9.232870101928711, | |
| "learning_rate": 9.00854700854701e-06, | |
| "loss": 0.6983, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 9.009384615384615, | |
| "grad_norm": 0.29688847064971924, | |
| "learning_rate": 8.991452991452992e-06, | |
| "loss": 0.3869, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.010923076923078, | |
| "grad_norm": 18.241771697998047, | |
| "learning_rate": 8.974358974358976e-06, | |
| "loss": 0.2829, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 9.012461538461539, | |
| "grad_norm": 0.09337367862462997, | |
| "learning_rate": 8.957264957264959e-06, | |
| "loss": 0.7837, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 9.014, | |
| "grad_norm": 0.968162477016449, | |
| "learning_rate": 8.940170940170941e-06, | |
| "loss": 1.303, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 9.015538461538462, | |
| "grad_norm": 3.651124954223633, | |
| "learning_rate": 8.923076923076925e-06, | |
| "loss": 1.4981, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.017076923076923, | |
| "grad_norm": 11.161046981811523, | |
| "learning_rate": 8.905982905982906e-06, | |
| "loss": 0.5206, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.018615384615385, | |
| "grad_norm": 19.576948165893555, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.6565, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.020153846153846, | |
| "grad_norm": 2.9681556224823, | |
| "learning_rate": 8.871794871794872e-06, | |
| "loss": 1.199, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.362217664718628, | |
| "eval_runtime": 16.2615, | |
| "eval_samples_per_second": 2.767, | |
| "eval_steps_per_second": 1.414, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 10.00153846153846, | |
| "grad_norm": 1.1594372987747192, | |
| "learning_rate": 8.854700854700855e-06, | |
| "loss": 0.7092, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 10.003076923076923, | |
| "grad_norm": 14.658281326293945, | |
| "learning_rate": 8.837606837606837e-06, | |
| "loss": 0.7718, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 10.004615384615384, | |
| "grad_norm": 0.8435935974121094, | |
| "learning_rate": 8.820512820512821e-06, | |
| "loss": 0.5196, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 10.006153846153847, | |
| "grad_norm": 97.72022247314453, | |
| "learning_rate": 8.803418803418804e-06, | |
| "loss": 0.9451, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 10.007692307692308, | |
| "grad_norm": 18.944766998291016, | |
| "learning_rate": 8.786324786324786e-06, | |
| "loss": 0.6124, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 10.009230769230768, | |
| "grad_norm": 2.6716647148132324, | |
| "learning_rate": 8.76923076923077e-06, | |
| "loss": 0.264, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 10.010769230769231, | |
| "grad_norm": 33.82844543457031, | |
| "learning_rate": 8.752136752136753e-06, | |
| "loss": 1.216, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 10.012307692307692, | |
| "grad_norm": 0.49768224358558655, | |
| "learning_rate": 8.735042735042735e-06, | |
| "loss": 0.7663, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 10.013846153846155, | |
| "grad_norm": 28.216794967651367, | |
| "learning_rate": 8.717948717948719e-06, | |
| "loss": 0.6339, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 10.015384615384615, | |
| "grad_norm": 22.059114456176758, | |
| "learning_rate": 8.700854700854702e-06, | |
| "loss": 1.0544, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 10.016923076923076, | |
| "grad_norm": 10.268027305603027, | |
| "learning_rate": 8.683760683760684e-06, | |
| "loss": 1.1307, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 10.018461538461539, | |
| "grad_norm": 4.328457355499268, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 0.2081, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "grad_norm": 8.873617172241211, | |
| "learning_rate": 8.649572649572651e-06, | |
| "loss": 0.7459, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.4034497737884521, | |
| "eval_runtime": 16.439, | |
| "eval_samples_per_second": 2.737, | |
| "eval_steps_per_second": 1.399, | |
| "step": 1441 | |
| }, | |
| { | |
| "epoch": 11.001384615384616, | |
| "grad_norm": 13.98863697052002, | |
| "learning_rate": 8.632478632478633e-06, | |
| "loss": 0.8816, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 11.002923076923077, | |
| "grad_norm": 1.8675132989883423, | |
| "learning_rate": 8.615384615384617e-06, | |
| "loss": 0.6312, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 11.004461538461538, | |
| "grad_norm": 53.308876037597656, | |
| "learning_rate": 8.598290598290599e-06, | |
| "loss": 0.7275, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 11.006, | |
| "grad_norm": 3.0141220092773438, | |
| "learning_rate": 8.58119658119658e-06, | |
| "loss": 1.2114, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 11.007538461538461, | |
| "grad_norm": 15.707778930664062, | |
| "learning_rate": 8.564102564102564e-06, | |
| "loss": 0.7522, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 11.009076923076924, | |
| "grad_norm": 6.552794456481934, | |
| "learning_rate": 8.547008547008548e-06, | |
| "loss": 0.4189, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 11.010615384615384, | |
| "grad_norm": 7.022129535675049, | |
| "learning_rate": 8.52991452991453e-06, | |
| "loss": 0.3288, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 11.012153846153845, | |
| "grad_norm": 0.06730630993843079, | |
| "learning_rate": 8.512820512820513e-06, | |
| "loss": 0.3837, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 11.013692307692308, | |
| "grad_norm": 9.968100547790527, | |
| "learning_rate": 8.495726495726497e-06, | |
| "loss": 1.4934, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 11.015230769230769, | |
| "grad_norm": 5.385005950927734, | |
| "learning_rate": 8.478632478632479e-06, | |
| "loss": 0.5119, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 11.016769230769231, | |
| "grad_norm": 0.6564542055130005, | |
| "learning_rate": 8.461538461538462e-06, | |
| "loss": 0.2784, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 11.018307692307692, | |
| "grad_norm": 21.736820220947266, | |
| "learning_rate": 8.444444444444446e-06, | |
| "loss": 0.8722, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 11.019846153846153, | |
| "grad_norm": 0.22721652686595917, | |
| "learning_rate": 8.427350427350428e-06, | |
| "loss": 0.5574, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 11.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 0.9836074113845825, | |
| "eval_runtime": 16.5216, | |
| "eval_samples_per_second": 2.724, | |
| "eval_steps_per_second": 1.392, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 12.00123076923077, | |
| "grad_norm": 12.297451972961426, | |
| "learning_rate": 8.410256410256411e-06, | |
| "loss": 0.4013, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 12.00276923076923, | |
| "grad_norm": 0.08853779733181, | |
| "learning_rate": 8.393162393162395e-06, | |
| "loss": 0.3198, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 12.004307692307693, | |
| "grad_norm": 34.7601203918457, | |
| "learning_rate": 8.376068376068377e-06, | |
| "loss": 0.4312, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 12.005846153846154, | |
| "grad_norm": 32.825660705566406, | |
| "learning_rate": 8.35897435897436e-06, | |
| "loss": 1.0733, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 12.007384615384616, | |
| "grad_norm": 29.4549560546875, | |
| "learning_rate": 8.341880341880344e-06, | |
| "loss": 0.4764, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 12.008923076923077, | |
| "grad_norm": 0.5384920239448547, | |
| "learning_rate": 8.324786324786326e-06, | |
| "loss": 0.8549, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 12.010461538461538, | |
| "grad_norm": 0.9702091217041016, | |
| "learning_rate": 8.307692307692309e-06, | |
| "loss": 0.9291, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 12.012, | |
| "grad_norm": 0.6406741142272949, | |
| "learning_rate": 8.290598290598293e-06, | |
| "loss": 0.2219, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 12.013538461538461, | |
| "grad_norm": 32.83845138549805, | |
| "learning_rate": 8.273504273504273e-06, | |
| "loss": 0.9183, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 12.015076923076924, | |
| "grad_norm": 0.2027946263551712, | |
| "learning_rate": 8.256410256410256e-06, | |
| "loss": 1.0287, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 12.016615384615385, | |
| "grad_norm": 16.00896453857422, | |
| "learning_rate": 8.23931623931624e-06, | |
| "loss": 0.803, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 12.018153846153846, | |
| "grad_norm": 2.379328966140747, | |
| "learning_rate": 8.222222222222222e-06, | |
| "loss": 0.4899, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 12.019692307692308, | |
| "grad_norm": 10.151841163635254, | |
| "learning_rate": 8.205128205128205e-06, | |
| "loss": 0.3742, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 12.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 0.6933945417404175, | |
| "eval_runtime": 16.5856, | |
| "eval_samples_per_second": 2.713, | |
| "eval_steps_per_second": 1.387, | |
| "step": 1703 | |
| }, | |
| { | |
| "epoch": 13.001076923076923, | |
| "grad_norm": 10.982708930969238, | |
| "learning_rate": 8.188034188034189e-06, | |
| "loss": 0.4252, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 13.002615384615385, | |
| "grad_norm": 37.273311614990234, | |
| "learning_rate": 8.17094017094017e-06, | |
| "loss": 0.2838, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 13.004153846153846, | |
| "grad_norm": 1.007625699043274, | |
| "learning_rate": 8.153846153846154e-06, | |
| "loss": 0.9127, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 13.005692307692307, | |
| "grad_norm": 49.06488800048828, | |
| "learning_rate": 8.136752136752138e-06, | |
| "loss": 1.2232, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 13.00723076923077, | |
| "grad_norm": 7.786661148071289, | |
| "learning_rate": 8.11965811965812e-06, | |
| "loss": 0.2125, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 13.00876923076923, | |
| "grad_norm": 5.816681861877441, | |
| "learning_rate": 8.102564102564103e-06, | |
| "loss": 0.8304, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 13.010307692307693, | |
| "grad_norm": 17.40418815612793, | |
| "learning_rate": 8.085470085470087e-06, | |
| "loss": 0.4443, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 13.011846153846154, | |
| "grad_norm": 0.06860287487506866, | |
| "learning_rate": 8.068376068376069e-06, | |
| "loss": 0.2601, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 13.013384615384615, | |
| "grad_norm": 65.18798828125, | |
| "learning_rate": 8.051282051282052e-06, | |
| "loss": 1.0041, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 13.014923076923077, | |
| "grad_norm": 21.708885192871094, | |
| "learning_rate": 8.034188034188036e-06, | |
| "loss": 0.7033, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 13.016461538461538, | |
| "grad_norm": 9.97461986541748, | |
| "learning_rate": 8.017094017094018e-06, | |
| "loss": 0.7752, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 13.018, | |
| "grad_norm": 0.07399370521306992, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.2674, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 13.019538461538462, | |
| "grad_norm": 2.612962484359741, | |
| "learning_rate": 7.982905982905985e-06, | |
| "loss": 0.3303, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 13.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 0.7161054015159607, | |
| "eval_runtime": 16.5574, | |
| "eval_samples_per_second": 2.718, | |
| "eval_steps_per_second": 1.389, | |
| "step": 1834 | |
| }, | |
| { | |
| "epoch": 14.000923076923076, | |
| "grad_norm": 138.69107055664062, | |
| "learning_rate": 7.965811965811967e-06, | |
| "loss": 0.7016, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 14.002461538461539, | |
| "grad_norm": 34.09086608886719, | |
| "learning_rate": 7.948717948717949e-06, | |
| "loss": 0.14, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 14.004, | |
| "grad_norm": 0.397993803024292, | |
| "learning_rate": 7.931623931623932e-06, | |
| "loss": 0.6063, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 14.005538461538462, | |
| "grad_norm": 3.324629545211792, | |
| "learning_rate": 7.914529914529914e-06, | |
| "loss": 0.383, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 14.007076923076923, | |
| "grad_norm": 0.3402593731880188, | |
| "learning_rate": 7.897435897435898e-06, | |
| "loss": 0.5463, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 14.008615384615384, | |
| "grad_norm": 1.0967109203338623, | |
| "learning_rate": 7.880341880341881e-06, | |
| "loss": 0.4832, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 14.010153846153846, | |
| "grad_norm": 32.570003509521484, | |
| "learning_rate": 7.863247863247863e-06, | |
| "loss": 1.1406, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 14.011692307692307, | |
| "grad_norm": 58.01143264770508, | |
| "learning_rate": 7.846153846153847e-06, | |
| "loss": 0.9745, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 14.01323076923077, | |
| "grad_norm": 38.700782775878906, | |
| "learning_rate": 7.82905982905983e-06, | |
| "loss": 1.5134, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 14.01476923076923, | |
| "grad_norm": 13.631935119628906, | |
| "learning_rate": 7.811965811965812e-06, | |
| "loss": 0.6178, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 14.016307692307691, | |
| "grad_norm": 1.173189401626587, | |
| "learning_rate": 7.794871794871796e-06, | |
| "loss": 0.2417, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 14.017846153846154, | |
| "grad_norm": 0.08922256529331207, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 1.3175, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 14.019384615384615, | |
| "grad_norm": 1.4147545099258423, | |
| "learning_rate": 7.760683760683761e-06, | |
| "loss": 0.8856, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 14.020153846153846, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_loss": 1.5607832670211792, | |
| "eval_runtime": 16.6786, | |
| "eval_samples_per_second": 2.698, | |
| "eval_steps_per_second": 1.379, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 15.000769230769231, | |
| "grad_norm": 0.7007743716239929, | |
| "learning_rate": 7.743589743589745e-06, | |
| "loss": 0.8628, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 15.002307692307692, | |
| "grad_norm": 0.28184232115745544, | |
| "learning_rate": 7.726495726495728e-06, | |
| "loss": 0.3975, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 15.003846153846155, | |
| "grad_norm": 17.967191696166992, | |
| "learning_rate": 7.70940170940171e-06, | |
| "loss": 1.0735, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 15.005384615384616, | |
| "grad_norm": 11.312219619750977, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.6666, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 15.006923076923076, | |
| "grad_norm": 46.481040954589844, | |
| "learning_rate": 7.675213675213677e-06, | |
| "loss": 0.7452, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 15.008461538461539, | |
| "grad_norm": 22.634511947631836, | |
| "learning_rate": 7.658119658119659e-06, | |
| "loss": 0.5875, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "grad_norm": 21.002492904663086, | |
| "learning_rate": 7.641025641025641e-06, | |
| "loss": 1.1613, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 15.011538461538462, | |
| "grad_norm": 0.506847620010376, | |
| "learning_rate": 7.6239316239316244e-06, | |
| "loss": 0.3506, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 15.013076923076923, | |
| "grad_norm": 0.024502774700522423, | |
| "learning_rate": 7.606837606837607e-06, | |
| "loss": 0.3198, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 15.014615384615384, | |
| "grad_norm": 12.380032539367676, | |
| "learning_rate": 7.58974358974359e-06, | |
| "loss": 0.6, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 15.016153846153847, | |
| "grad_norm": 31.284093856811523, | |
| "learning_rate": 7.572649572649573e-06, | |
| "loss": 0.7014, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 15.017692307692307, | |
| "grad_norm": 13.46820068359375, | |
| "learning_rate": 7.555555555555556e-06, | |
| "loss": 1.0454, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 15.01923076923077, | |
| "grad_norm": 57.13776397705078, | |
| "learning_rate": 7.538461538461539e-06, | |
| "loss": 0.186, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 15.020153846153846, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.7781548500061035, | |
| "eval_runtime": 9.7964, | |
| "eval_samples_per_second": 4.594, | |
| "eval_steps_per_second": 2.348, | |
| "step": 2096 | |
| }, | |
| { | |
| "epoch": 16.000615384615383, | |
| "grad_norm": 29.700233459472656, | |
| "learning_rate": 7.521367521367522e-06, | |
| "loss": 0.3342, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 16.002153846153846, | |
| "grad_norm": 41.61544418334961, | |
| "learning_rate": 7.504273504273505e-06, | |
| "loss": 0.6295, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 16.003692307692308, | |
| "grad_norm": 39.3793830871582, | |
| "learning_rate": 7.487179487179488e-06, | |
| "loss": 0.4705, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 16.00523076923077, | |
| "grad_norm": 0.03968028724193573, | |
| "learning_rate": 7.4700854700854706e-06, | |
| "loss": 0.155, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 16.00676923076923, | |
| "grad_norm": 32.486080169677734, | |
| "learning_rate": 7.452991452991454e-06, | |
| "loss": 0.5658, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 16.008307692307692, | |
| "grad_norm": 13.047239303588867, | |
| "learning_rate": 7.435897435897437e-06, | |
| "loss": 0.1824, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 16.009846153846155, | |
| "grad_norm": 25.782119750976562, | |
| "learning_rate": 7.4188034188034196e-06, | |
| "loss": 0.1584, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 16.011384615384614, | |
| "grad_norm": 187.74986267089844, | |
| "learning_rate": 7.401709401709402e-06, | |
| "loss": 0.1838, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 16.012923076923077, | |
| "grad_norm": 0.08439689874649048, | |
| "learning_rate": 7.384615384615386e-06, | |
| "loss": 1.2258, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 16.01446153846154, | |
| "grad_norm": 22.6776065826416, | |
| "learning_rate": 7.3675213675213686e-06, | |
| "loss": 1.4482, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 16.016, | |
| "grad_norm": 6.3266754150390625, | |
| "learning_rate": 7.350427350427351e-06, | |
| "loss": 0.3183, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 16.01753846153846, | |
| "grad_norm": 23.84638214111328, | |
| "learning_rate": 7.333333333333333e-06, | |
| "loss": 0.9045, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 16.019076923076923, | |
| "grad_norm": 16.578397750854492, | |
| "learning_rate": 7.316239316239317e-06, | |
| "loss": 0.7263, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 16.020153846153846, | |
| "eval_accuracy": 0.5777777777777777, | |
| "eval_loss": 1.4438178539276123, | |
| "eval_runtime": 10.5275, | |
| "eval_samples_per_second": 4.275, | |
| "eval_steps_per_second": 2.185, | |
| "step": 2227 | |
| }, | |
| { | |
| "epoch": 17.00046153846154, | |
| "grad_norm": 50.510887145996094, | |
| "learning_rate": 7.299145299145299e-06, | |
| "loss": 0.8142, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 17.002, | |
| "grad_norm": 58.31331253051758, | |
| "learning_rate": 7.282051282051282e-06, | |
| "loss": 0.9803, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 17.00353846153846, | |
| "grad_norm": 85.08041381835938, | |
| "learning_rate": 7.264957264957266e-06, | |
| "loss": 0.6486, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 17.005076923076924, | |
| "grad_norm": 0.11064028739929199, | |
| "learning_rate": 7.247863247863248e-06, | |
| "loss": 0.823, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 17.006615384615383, | |
| "grad_norm": 2.28714919090271, | |
| "learning_rate": 7.230769230769231e-06, | |
| "loss": 0.2777, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 17.008153846153846, | |
| "grad_norm": 105.10900115966797, | |
| "learning_rate": 7.213675213675214e-06, | |
| "loss": 0.4677, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 17.00969230769231, | |
| "grad_norm": 0.5533010363578796, | |
| "learning_rate": 7.196581196581197e-06, | |
| "loss": 0.2372, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 17.01123076923077, | |
| "grad_norm": 0.01793714053928852, | |
| "learning_rate": 7.17948717948718e-06, | |
| "loss": 0.2989, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 17.01276923076923, | |
| "grad_norm": 1.3990322351455688, | |
| "learning_rate": 7.162393162393163e-06, | |
| "loss": 0.2614, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 17.014307692307693, | |
| "grad_norm": 2.7320775985717773, | |
| "learning_rate": 7.145299145299146e-06, | |
| "loss": 0.6144, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 17.015846153846155, | |
| "grad_norm": 118.73646545410156, | |
| "learning_rate": 7.128205128205129e-06, | |
| "loss": 0.637, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 17.017384615384614, | |
| "grad_norm": 5.420734882354736, | |
| "learning_rate": 7.111111111111112e-06, | |
| "loss": 0.5515, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 17.018923076923077, | |
| "grad_norm": 243.23114013671875, | |
| "learning_rate": 7.0940170940170945e-06, | |
| "loss": 1.552, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 17.020153846153846, | |
| "eval_accuracy": 0.6222222222222222, | |
| "eval_loss": 1.2116680145263672, | |
| "eval_runtime": 16.2103, | |
| "eval_samples_per_second": 2.776, | |
| "eval_steps_per_second": 1.419, | |
| "step": 2358 | |
| }, | |
| { | |
| "epoch": 18.000307692307693, | |
| "grad_norm": 134.7728729248047, | |
| "learning_rate": 7.076923076923078e-06, | |
| "loss": 0.7535, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 18.001846153846152, | |
| "grad_norm": 108.6753158569336, | |
| "learning_rate": 7.059829059829061e-06, | |
| "loss": 1.107, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 18.003384615384615, | |
| "grad_norm": 54.20198440551758, | |
| "learning_rate": 7.0427350427350435e-06, | |
| "loss": 0.3146, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 18.004923076923077, | |
| "grad_norm": 0.7513457536697388, | |
| "learning_rate": 7.025641025641025e-06, | |
| "loss": 0.6774, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 18.00646153846154, | |
| "grad_norm": 0.018931642174720764, | |
| "learning_rate": 7.008547008547009e-06, | |
| "loss": 0.425, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 18.008, | |
| "grad_norm": 46.27175521850586, | |
| "learning_rate": 6.991452991452992e-06, | |
| "loss": 0.5133, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 18.00953846153846, | |
| "grad_norm": 40.42552185058594, | |
| "learning_rate": 6.974358974358974e-06, | |
| "loss": 0.3398, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 18.011076923076924, | |
| "grad_norm": 65.7842788696289, | |
| "learning_rate": 6.957264957264958e-06, | |
| "loss": 0.6389, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 18.012615384615383, | |
| "grad_norm": 73.6776123046875, | |
| "learning_rate": 6.940170940170941e-06, | |
| "loss": 0.5362, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 18.014153846153846, | |
| "grad_norm": 47.25505065917969, | |
| "learning_rate": 6.923076923076923e-06, | |
| "loss": 0.6467, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 18.01569230769231, | |
| "grad_norm": 0.12112545967102051, | |
| "learning_rate": 6.905982905982906e-06, | |
| "loss": 0.2206, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 18.017230769230768, | |
| "grad_norm": 0.5958626866340637, | |
| "learning_rate": 6.88888888888889e-06, | |
| "loss": 0.7918, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 18.01876923076923, | |
| "grad_norm": 8.156698226928711, | |
| "learning_rate": 6.871794871794872e-06, | |
| "loss": 0.1031, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 18.020153846153846, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.2174286842346191, | |
| "eval_runtime": 15.496, | |
| "eval_samples_per_second": 2.904, | |
| "eval_steps_per_second": 1.484, | |
| "step": 2489 | |
| }, | |
| { | |
| "epoch": 19.000153846153847, | |
| "grad_norm": 139.62734985351562, | |
| "learning_rate": 6.854700854700855e-06, | |
| "loss": 0.6191, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 19.00169230769231, | |
| "grad_norm": 3.715949773788452, | |
| "learning_rate": 6.837606837606839e-06, | |
| "loss": 0.7586, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 19.00323076923077, | |
| "grad_norm": 1.1952438354492188, | |
| "learning_rate": 6.820512820512821e-06, | |
| "loss": 0.4729, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 19.00476923076923, | |
| "grad_norm": 134.0819091796875, | |
| "learning_rate": 6.803418803418804e-06, | |
| "loss": 1.1116, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 19.006307692307693, | |
| "grad_norm": 24.67700958251953, | |
| "learning_rate": 6.786324786324787e-06, | |
| "loss": 0.477, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 19.007846153846153, | |
| "grad_norm": 35.421531677246094, | |
| "learning_rate": 6.76923076923077e-06, | |
| "loss": 0.6966, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 19.009384615384615, | |
| "grad_norm": 66.65573120117188, | |
| "learning_rate": 6.752136752136753e-06, | |
| "loss": 0.6917, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 19.010923076923078, | |
| "grad_norm": 0.07897038757801056, | |
| "learning_rate": 6.735042735042736e-06, | |
| "loss": 0.4317, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 19.012461538461537, | |
| "grad_norm": 41.582584381103516, | |
| "learning_rate": 6.717948717948718e-06, | |
| "loss": 0.2512, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 19.014, | |
| "grad_norm": 1.2951287031173706, | |
| "learning_rate": 6.700854700854701e-06, | |
| "loss": 0.9583, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 19.015538461538462, | |
| "grad_norm": 4.002734661102295, | |
| "learning_rate": 6.683760683760684e-06, | |
| "loss": 0.1478, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 19.017076923076925, | |
| "grad_norm": 0.046396344900131226, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.2477, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 19.018615384615384, | |
| "grad_norm": 0.16359756886959076, | |
| "learning_rate": 6.64957264957265e-06, | |
| "loss": 0.0484, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 19.020153846153846, | |
| "grad_norm": 199.39109802246094, | |
| "learning_rate": 6.632478632478633e-06, | |
| "loss": 1.193, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 19.020153846153846, | |
| "eval_accuracy": 0.6444444444444445, | |
| "eval_loss": 1.204282283782959, | |
| "eval_runtime": 15.6321, | |
| "eval_samples_per_second": 2.879, | |
| "eval_steps_per_second": 1.471, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 20.001538461538463, | |
| "grad_norm": 154.635009765625, | |
| "learning_rate": 6.615384615384616e-06, | |
| "loss": 0.2689, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 20.00307692307692, | |
| "grad_norm": 2.9944937229156494, | |
| "learning_rate": 6.598290598290598e-06, | |
| "loss": 0.4025, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 20.004615384615384, | |
| "grad_norm": 2.519679546356201, | |
| "learning_rate": 6.581196581196582e-06, | |
| "loss": 0.832, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 20.006153846153847, | |
| "grad_norm": 0.294511616230011, | |
| "learning_rate": 6.564102564102565e-06, | |
| "loss": 0.3218, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 20.00769230769231, | |
| "grad_norm": 0.07732245326042175, | |
| "learning_rate": 6.547008547008547e-06, | |
| "loss": 0.2424, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 20.00923076923077, | |
| "grad_norm": 184.55177307128906, | |
| "learning_rate": 6.529914529914531e-06, | |
| "loss": 0.4748, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 20.01076923076923, | |
| "grad_norm": 0.20970293879508972, | |
| "learning_rate": 6.512820512820514e-06, | |
| "loss": 0.284, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 20.012307692307694, | |
| "grad_norm": 0.1644299477338791, | |
| "learning_rate": 6.495726495726496e-06, | |
| "loss": 0.2748, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 20.013846153846153, | |
| "grad_norm": 86.30721282958984, | |
| "learning_rate": 6.478632478632479e-06, | |
| "loss": 1.1516, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 20.015384615384615, | |
| "grad_norm": 0.20401491224765778, | |
| "learning_rate": 6.461538461538463e-06, | |
| "loss": 0.9673, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 20.016923076923078, | |
| "grad_norm": 82.08517456054688, | |
| "learning_rate": 6.444444444444445e-06, | |
| "loss": 0.3942, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 20.018461538461537, | |
| "grad_norm": 73.53730010986328, | |
| "learning_rate": 6.427350427350428e-06, | |
| "loss": 1.5857, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "grad_norm": 0.6997228860855103, | |
| "learning_rate": 6.410256410256412e-06, | |
| "loss": 0.322, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 20.020153846153846, | |
| "eval_accuracy": 0.6444444444444445, | |
| "eval_loss": 1.363928198814392, | |
| "eval_runtime": 15.9491, | |
| "eval_samples_per_second": 2.821, | |
| "eval_steps_per_second": 1.442, | |
| "step": 2751 | |
| }, | |
| { | |
| "epoch": 21.001384615384616, | |
| "grad_norm": 163.63023376464844, | |
| "learning_rate": 6.3931623931623935e-06, | |
| "loss": 0.8769, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 21.00292307692308, | |
| "grad_norm": 135.60284423828125, | |
| "learning_rate": 6.376068376068376e-06, | |
| "loss": 0.8035, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 21.004461538461538, | |
| "grad_norm": 0.08598937839269638, | |
| "learning_rate": 6.358974358974359e-06, | |
| "loss": 0.3445, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 21.006, | |
| "grad_norm": 0.6145640015602112, | |
| "learning_rate": 6.3418803418803425e-06, | |
| "loss": 0.1945, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 21.007538461538463, | |
| "grad_norm": 93.38436889648438, | |
| "learning_rate": 6.324786324786325e-06, | |
| "loss": 0.7509, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 21.009076923076922, | |
| "grad_norm": 24.876440048217773, | |
| "learning_rate": 6.307692307692308e-06, | |
| "loss": 0.6927, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 21.010615384615384, | |
| "grad_norm": 0.5187433362007141, | |
| "learning_rate": 6.290598290598291e-06, | |
| "loss": 0.2913, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 21.012153846153847, | |
| "grad_norm": 0.010546746663749218, | |
| "learning_rate": 6.273504273504274e-06, | |
| "loss": 0.777, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 21.013692307692306, | |
| "grad_norm": 0.007287884131073952, | |
| "learning_rate": 6.256410256410257e-06, | |
| "loss": 1.1557, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 21.01523076923077, | |
| "grad_norm": 0.09654298424720764, | |
| "learning_rate": 6.23931623931624e-06, | |
| "loss": 0.0208, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 21.01676923076923, | |
| "grad_norm": 186.83726501464844, | |
| "learning_rate": 6.222222222222223e-06, | |
| "loss": 0.5685, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 21.018307692307694, | |
| "grad_norm": 0.9964919686317444, | |
| "learning_rate": 6.205128205128206e-06, | |
| "loss": 0.6973, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 21.019846153846153, | |
| "grad_norm": 0.2815859615802765, | |
| "learning_rate": 6.188034188034189e-06, | |
| "loss": 0.3791, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 21.020153846153846, | |
| "eval_accuracy": 0.6444444444444445, | |
| "eval_loss": 1.310689091682434, | |
| "eval_runtime": 15.4724, | |
| "eval_samples_per_second": 2.908, | |
| "eval_steps_per_second": 1.487, | |
| "step": 2882 | |
| }, | |
| { | |
| "epoch": 22.00123076923077, | |
| "grad_norm": 0.600744903087616, | |
| "learning_rate": 6.170940170940171e-06, | |
| "loss": 0.5233, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 22.002769230769232, | |
| "grad_norm": 30.499425888061523, | |
| "learning_rate": 6.153846153846155e-06, | |
| "loss": 0.9131, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 22.00430769230769, | |
| "grad_norm": 18.746543884277344, | |
| "learning_rate": 6.136752136752138e-06, | |
| "loss": 0.5421, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 22.005846153846154, | |
| "grad_norm": 31.252723693847656, | |
| "learning_rate": 6.11965811965812e-06, | |
| "loss": 0.2288, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 22.007384615384616, | |
| "grad_norm": 3.9572865962982178, | |
| "learning_rate": 6.102564102564104e-06, | |
| "loss": 0.2545, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 22.008923076923075, | |
| "grad_norm": 39.121185302734375, | |
| "learning_rate": 6.085470085470086e-06, | |
| "loss": 0.9026, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 22.010461538461538, | |
| "grad_norm": 10.605064392089844, | |
| "learning_rate": 6.0683760683760684e-06, | |
| "loss": 0.6102, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 22.012, | |
| "grad_norm": 3.3785817623138428, | |
| "learning_rate": 6.051282051282051e-06, | |
| "loss": 0.1496, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 22.013538461538463, | |
| "grad_norm": 0.010982020758092403, | |
| "learning_rate": 6.034188034188035e-06, | |
| "loss": 0.039, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 22.015076923076922, | |
| "grad_norm": 43.723594665527344, | |
| "learning_rate": 6.0170940170940174e-06, | |
| "loss": 0.5827, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 22.016615384615385, | |
| "grad_norm": 0.03211180493235588, | |
| "learning_rate": 6e-06, | |
| "loss": 0.7757, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 22.018153846153847, | |
| "grad_norm": 113.42313385009766, | |
| "learning_rate": 5.982905982905983e-06, | |
| "loss": 0.8933, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 22.019692307692306, | |
| "grad_norm": 136.8942108154297, | |
| "learning_rate": 5.9658119658119664e-06, | |
| "loss": 0.6201, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 22.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.2797292470932007, | |
| "eval_runtime": 15.8657, | |
| "eval_samples_per_second": 2.836, | |
| "eval_steps_per_second": 1.45, | |
| "step": 3013 | |
| }, | |
| { | |
| "epoch": 23.001076923076923, | |
| "grad_norm": 8.482766151428223, | |
| "learning_rate": 5.948717948717949e-06, | |
| "loss": 0.0373, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 23.002615384615385, | |
| "grad_norm": 0.5569808483123779, | |
| "learning_rate": 5.931623931623932e-06, | |
| "loss": 0.4392, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 23.004153846153844, | |
| "grad_norm": 0.01961614191532135, | |
| "learning_rate": 5.914529914529915e-06, | |
| "loss": 0.5029, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 23.005692307692307, | |
| "grad_norm": 0.05487629398703575, | |
| "learning_rate": 5.897435897435898e-06, | |
| "loss": 0.4736, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 23.00723076923077, | |
| "grad_norm": 0.14323970675468445, | |
| "learning_rate": 5.880341880341881e-06, | |
| "loss": 0.4943, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 23.008769230769232, | |
| "grad_norm": 2.3032212257385254, | |
| "learning_rate": 5.863247863247864e-06, | |
| "loss": 0.4989, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 23.01030769230769, | |
| "grad_norm": 0.22451362013816833, | |
| "learning_rate": 5.846153846153847e-06, | |
| "loss": 0.2813, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 23.011846153846154, | |
| "grad_norm": 60.25706100463867, | |
| "learning_rate": 5.82905982905983e-06, | |
| "loss": 0.5081, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 23.013384615384616, | |
| "grad_norm": 0.009288864210247993, | |
| "learning_rate": 5.8119658119658126e-06, | |
| "loss": 0.8284, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 23.014923076923075, | |
| "grad_norm": 300.2200927734375, | |
| "learning_rate": 5.794871794871796e-06, | |
| "loss": 0.2455, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 23.016461538461538, | |
| "grad_norm": 0.04352228716015816, | |
| "learning_rate": 5.777777777777778e-06, | |
| "loss": 1.1711, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 23.018, | |
| "grad_norm": 2.150589942932129, | |
| "learning_rate": 5.760683760683761e-06, | |
| "loss": 0.7021, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 23.019538461538463, | |
| "grad_norm": 65.9561538696289, | |
| "learning_rate": 5.743589743589743e-06, | |
| "loss": 0.9547, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 23.020153846153846, | |
| "eval_accuracy": 0.6444444444444445, | |
| "eval_loss": 1.1653660535812378, | |
| "eval_runtime": 16.1119, | |
| "eval_samples_per_second": 2.793, | |
| "eval_steps_per_second": 1.428, | |
| "step": 3144 | |
| }, | |
| { | |
| "epoch": 24.000923076923076, | |
| "grad_norm": 1.426770567893982, | |
| "learning_rate": 5.726495726495727e-06, | |
| "loss": 0.3791, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 24.00246153846154, | |
| "grad_norm": 0.9266498684883118, | |
| "learning_rate": 5.70940170940171e-06, | |
| "loss": 0.0231, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 24.004, | |
| "grad_norm": 8.946441650390625, | |
| "learning_rate": 5.692307692307692e-06, | |
| "loss": 0.234, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 24.00553846153846, | |
| "grad_norm": 50.16424560546875, | |
| "learning_rate": 5.675213675213675e-06, | |
| "loss": 0.783, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 24.007076923076923, | |
| "grad_norm": 0.28983768820762634, | |
| "learning_rate": 5.658119658119659e-06, | |
| "loss": 0.5953, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 24.008615384615386, | |
| "grad_norm": 0.2605815529823303, | |
| "learning_rate": 5.641025641025641e-06, | |
| "loss": 0.6088, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 24.010153846153845, | |
| "grad_norm": 4.293778896331787, | |
| "learning_rate": 5.623931623931624e-06, | |
| "loss": 0.2547, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 24.011692307692307, | |
| "grad_norm": 0.15170973539352417, | |
| "learning_rate": 5.606837606837608e-06, | |
| "loss": 0.0062, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 24.01323076923077, | |
| "grad_norm": 0.033804938197135925, | |
| "learning_rate": 5.58974358974359e-06, | |
| "loss": 0.343, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 24.014769230769232, | |
| "grad_norm": 3.5693838596343994, | |
| "learning_rate": 5.572649572649573e-06, | |
| "loss": 0.5394, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 24.01630769230769, | |
| "grad_norm": 141.77432250976562, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.9005, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 24.017846153846154, | |
| "grad_norm": 0.08334534615278244, | |
| "learning_rate": 5.538461538461539e-06, | |
| "loss": 0.6584, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 24.019384615384617, | |
| "grad_norm": 95.38099670410156, | |
| "learning_rate": 5.521367521367522e-06, | |
| "loss": 1.4286, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 24.020153846153846, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.4077948331832886, | |
| "eval_runtime": 15.9813, | |
| "eval_samples_per_second": 2.816, | |
| "eval_steps_per_second": 1.439, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 25.00076923076923, | |
| "grad_norm": 0.1690382957458496, | |
| "learning_rate": 5.504273504273505e-06, | |
| "loss": 0.2674, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 25.002307692307692, | |
| "grad_norm": 1.1807458400726318, | |
| "learning_rate": 5.487179487179488e-06, | |
| "loss": 0.5086, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 25.003846153846155, | |
| "grad_norm": 178.8708038330078, | |
| "learning_rate": 5.470085470085471e-06, | |
| "loss": 0.431, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 25.005384615384614, | |
| "grad_norm": 39.4903678894043, | |
| "learning_rate": 5.452991452991453e-06, | |
| "loss": 0.5091, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 25.006923076923076, | |
| "grad_norm": 15.33879566192627, | |
| "learning_rate": 5.435897435897436e-06, | |
| "loss": 0.2901, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 25.00846153846154, | |
| "grad_norm": 0.00622211629524827, | |
| "learning_rate": 5.418803418803419e-06, | |
| "loss": 0.6421, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "grad_norm": 61.33552551269531, | |
| "learning_rate": 5.401709401709402e-06, | |
| "loss": 0.4591, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 25.01153846153846, | |
| "grad_norm": 1.0371230840682983, | |
| "learning_rate": 5.384615384615385e-06, | |
| "loss": 0.5397, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 25.013076923076923, | |
| "grad_norm": 0.5525978207588196, | |
| "learning_rate": 5.367521367521367e-06, | |
| "loss": 0.5579, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 25.014615384615386, | |
| "grad_norm": 1.366528868675232, | |
| "learning_rate": 5.350427350427351e-06, | |
| "loss": 0.2765, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 25.016153846153845, | |
| "grad_norm": 0.07837115228176117, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.4275, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 25.017692307692307, | |
| "grad_norm": 0.45189762115478516, | |
| "learning_rate": 5.316239316239316e-06, | |
| "loss": 0.4231, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 25.01923076923077, | |
| "grad_norm": 0.009556197561323643, | |
| "learning_rate": 5.2991452991453e-06, | |
| "loss": 0.6023, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 25.020153846153846, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 1.5069091320037842, | |
| "eval_runtime": 15.4923, | |
| "eval_samples_per_second": 2.905, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3406 | |
| }, | |
| { | |
| "epoch": 26.000615384615383, | |
| "grad_norm": 4.212526798248291, | |
| "learning_rate": 5.282051282051283e-06, | |
| "loss": 0.5393, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 26.002153846153846, | |
| "grad_norm": 179.57040405273438, | |
| "learning_rate": 5.264957264957265e-06, | |
| "loss": 0.5916, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 26.003692307692308, | |
| "grad_norm": 18.013946533203125, | |
| "learning_rate": 5.247863247863249e-06, | |
| "loss": 0.708, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 26.00523076923077, | |
| "grad_norm": 0.4901110827922821, | |
| "learning_rate": 5.230769230769232e-06, | |
| "loss": 0.3345, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 26.00676923076923, | |
| "grad_norm": 2.597087860107422, | |
| "learning_rate": 5.213675213675214e-06, | |
| "loss": 0.2494, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 26.008307692307692, | |
| "grad_norm": 0.06961245089769363, | |
| "learning_rate": 5.196581196581197e-06, | |
| "loss": 0.0098, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 26.009846153846155, | |
| "grad_norm": 0.09561796486377716, | |
| "learning_rate": 5.179487179487181e-06, | |
| "loss": 0.5873, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 26.011384615384614, | |
| "grad_norm": 0.036112502217292786, | |
| "learning_rate": 5.162393162393163e-06, | |
| "loss": 0.5439, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 26.012923076923077, | |
| "grad_norm": 0.03839242830872536, | |
| "learning_rate": 5.145299145299145e-06, | |
| "loss": 0.0014, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 26.01446153846154, | |
| "grad_norm": 0.1560317873954773, | |
| "learning_rate": 5.128205128205128e-06, | |
| "loss": 0.1146, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 26.016, | |
| "grad_norm": 51.92442321777344, | |
| "learning_rate": 5.1111111111111115e-06, | |
| "loss": 0.7934, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 26.01753846153846, | |
| "grad_norm": 75.53848266601562, | |
| "learning_rate": 5.094017094017094e-06, | |
| "loss": 1.1552, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 26.019076923076923, | |
| "grad_norm": 0.06482236087322235, | |
| "learning_rate": 5.076923076923077e-06, | |
| "loss": 0.2925, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 26.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.4528932571411133, | |
| "eval_runtime": 16.0345, | |
| "eval_samples_per_second": 2.806, | |
| "eval_steps_per_second": 1.434, | |
| "step": 3537 | |
| }, | |
| { | |
| "epoch": 27.00046153846154, | |
| "grad_norm": 3.0287692546844482, | |
| "learning_rate": 5.05982905982906e-06, | |
| "loss": 0.0116, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 27.002, | |
| "grad_norm": 0.04152112081646919, | |
| "learning_rate": 5.042735042735043e-06, | |
| "loss": 0.3428, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 27.00353846153846, | |
| "grad_norm": 0.12934119999408722, | |
| "learning_rate": 5.025641025641026e-06, | |
| "loss": 0.3898, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 27.005076923076924, | |
| "grad_norm": 0.14030040800571442, | |
| "learning_rate": 5.008547008547009e-06, | |
| "loss": 0.0025, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 27.006615384615383, | |
| "grad_norm": 19.873138427734375, | |
| "learning_rate": 4.991452991452992e-06, | |
| "loss": 0.2907, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 27.008153846153846, | |
| "grad_norm": 3.480175733566284, | |
| "learning_rate": 4.974358974358975e-06, | |
| "loss": 0.4019, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 27.00969230769231, | |
| "grad_norm": 0.06078382208943367, | |
| "learning_rate": 4.957264957264958e-06, | |
| "loss": 0.6537, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 27.01123076923077, | |
| "grad_norm": 0.28860241174697876, | |
| "learning_rate": 4.940170940170941e-06, | |
| "loss": 0.1375, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 27.01276923076923, | |
| "grad_norm": 0.03207442909479141, | |
| "learning_rate": 4.923076923076924e-06, | |
| "loss": 0.2118, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 27.014307692307693, | |
| "grad_norm": 0.38180452585220337, | |
| "learning_rate": 4.905982905982906e-06, | |
| "loss": 0.3965, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 27.015846153846155, | |
| "grad_norm": 0.17501138150691986, | |
| "learning_rate": 4.888888888888889e-06, | |
| "loss": 0.6415, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 27.017384615384614, | |
| "grad_norm": 0.003654064144939184, | |
| "learning_rate": 4.871794871794872e-06, | |
| "loss": 0.3292, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 27.018923076923077, | |
| "grad_norm": 467.6424865722656, | |
| "learning_rate": 4.854700854700855e-06, | |
| "loss": 0.1445, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 27.020153846153846, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 1.441672921180725, | |
| "eval_runtime": 16.0446, | |
| "eval_samples_per_second": 2.805, | |
| "eval_steps_per_second": 1.433, | |
| "step": 3668 | |
| }, | |
| { | |
| "epoch": 28.000307692307693, | |
| "grad_norm": 0.13593587279319763, | |
| "learning_rate": 4.837606837606838e-06, | |
| "loss": 0.1851, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 28.001846153846152, | |
| "grad_norm": 19.399213790893555, | |
| "learning_rate": 4.820512820512821e-06, | |
| "loss": 0.3491, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 28.003384615384615, | |
| "grad_norm": 80.5206527709961, | |
| "learning_rate": 4.803418803418804e-06, | |
| "loss": 0.3536, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 28.004923076923077, | |
| "grad_norm": 80.3946533203125, | |
| "learning_rate": 4.786324786324787e-06, | |
| "loss": 0.4156, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 28.00646153846154, | |
| "grad_norm": 0.03089255467057228, | |
| "learning_rate": 4.76923076923077e-06, | |
| "loss": 0.395, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 28.008, | |
| "grad_norm": 1.2272357940673828, | |
| "learning_rate": 4.752136752136752e-06, | |
| "loss": 0.3586, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 28.00953846153846, | |
| "grad_norm": 1.0923726558685303, | |
| "learning_rate": 4.7350427350427355e-06, | |
| "loss": 0.1467, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 28.011076923076924, | |
| "grad_norm": 267.46099853515625, | |
| "learning_rate": 4.717948717948718e-06, | |
| "loss": 1.125, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 28.012615384615383, | |
| "grad_norm": 0.058717723935842514, | |
| "learning_rate": 4.700854700854701e-06, | |
| "loss": 0.0026, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 28.014153846153846, | |
| "grad_norm": 90.66056823730469, | |
| "learning_rate": 4.6837606837606844e-06, | |
| "loss": 0.5662, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 28.01569230769231, | |
| "grad_norm": 0.006864274851977825, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 0.3363, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 28.017230769230768, | |
| "grad_norm": 0.07169032841920853, | |
| "learning_rate": 4.64957264957265e-06, | |
| "loss": 0.5003, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 28.01876923076923, | |
| "grad_norm": 0.035105422139167786, | |
| "learning_rate": 4.6324786324786334e-06, | |
| "loss": 0.2717, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 28.020153846153846, | |
| "eval_accuracy": 0.6444444444444445, | |
| "eval_loss": 2.1237218379974365, | |
| "eval_runtime": 15.6126, | |
| "eval_samples_per_second": 2.882, | |
| "eval_steps_per_second": 1.473, | |
| "step": 3799 | |
| }, | |
| { | |
| "epoch": 29.000153846153847, | |
| "grad_norm": 0.013561666943132877, | |
| "learning_rate": 4.615384615384616e-06, | |
| "loss": 0.276, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 29.00169230769231, | |
| "grad_norm": 0.18230527639389038, | |
| "learning_rate": 4.598290598290598e-06, | |
| "loss": 0.3277, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 29.00323076923077, | |
| "grad_norm": 1.5334808826446533, | |
| "learning_rate": 4.581196581196582e-06, | |
| "loss": 0.8176, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 29.00476923076923, | |
| "grad_norm": 71.27356719970703, | |
| "learning_rate": 4.564102564102564e-06, | |
| "loss": 0.815, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 29.006307692307693, | |
| "grad_norm": 0.6609984040260315, | |
| "learning_rate": 4.547008547008547e-06, | |
| "loss": 0.264, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 29.007846153846153, | |
| "grad_norm": 0.22629307210445404, | |
| "learning_rate": 4.5299145299145306e-06, | |
| "loss": 0.231, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 29.009384615384615, | |
| "grad_norm": 21.790674209594727, | |
| "learning_rate": 4.512820512820513e-06, | |
| "loss": 0.6968, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 29.010923076923078, | |
| "grad_norm": 25.829566955566406, | |
| "learning_rate": 4.495726495726496e-06, | |
| "loss": 0.6857, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 29.012461538461537, | |
| "grad_norm": 0.006461359094828367, | |
| "learning_rate": 4.4786324786324796e-06, | |
| "loss": 0.0078, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 29.014, | |
| "grad_norm": 0.22607067227363586, | |
| "learning_rate": 4.461538461538462e-06, | |
| "loss": 0.2062, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 29.015538461538462, | |
| "grad_norm": 0.0425758883357048, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.5139, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 29.017076923076925, | |
| "grad_norm": 0.11292905360460281, | |
| "learning_rate": 4.427350427350428e-06, | |
| "loss": 0.2216, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 29.018615384615384, | |
| "grad_norm": 127.46011352539062, | |
| "learning_rate": 4.4102564102564104e-06, | |
| "loss": 0.3895, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 29.020153846153846, | |
| "grad_norm": 98.53323364257812, | |
| "learning_rate": 4.393162393162393e-06, | |
| "loss": 0.411, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 29.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.5398510694503784, | |
| "eval_runtime": 15.4849, | |
| "eval_samples_per_second": 2.906, | |
| "eval_steps_per_second": 1.485, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 30.001538461538463, | |
| "grad_norm": 230.3444366455078, | |
| "learning_rate": 4.376068376068377e-06, | |
| "loss": 0.3375, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 30.00307692307692, | |
| "grad_norm": 0.025416241958737373, | |
| "learning_rate": 4.358974358974359e-06, | |
| "loss": 0.1905, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 30.004615384615384, | |
| "grad_norm": 450.90423583984375, | |
| "learning_rate": 4.341880341880342e-06, | |
| "loss": 0.1083, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 30.006153846153847, | |
| "grad_norm": 1.011947512626648, | |
| "learning_rate": 4.324786324786326e-06, | |
| "loss": 0.5049, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 30.00769230769231, | |
| "grad_norm": 0.11824673414230347, | |
| "learning_rate": 4.307692307692308e-06, | |
| "loss": 0.221, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 30.00923076923077, | |
| "grad_norm": 0.0021331242751330137, | |
| "learning_rate": 4.29059829059829e-06, | |
| "loss": 0.0716, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 30.01076923076923, | |
| "grad_norm": 0.39925095438957214, | |
| "learning_rate": 4.273504273504274e-06, | |
| "loss": 0.0264, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 30.012307692307694, | |
| "grad_norm": 0.01983010768890381, | |
| "learning_rate": 4.2564102564102566e-06, | |
| "loss": 0.2665, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 30.013846153846153, | |
| "grad_norm": 0.04118695482611656, | |
| "learning_rate": 4.239316239316239e-06, | |
| "loss": 0.0033, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 30.015384615384615, | |
| "grad_norm": 0.005491225980222225, | |
| "learning_rate": 4.222222222222223e-06, | |
| "loss": 0.0855, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 30.016923076923078, | |
| "grad_norm": 77.31281280517578, | |
| "learning_rate": 4.2051282051282055e-06, | |
| "loss": 1.0343, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 30.018461538461537, | |
| "grad_norm": 0.014068684540688992, | |
| "learning_rate": 4.188034188034188e-06, | |
| "loss": 0.5941, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "grad_norm": 155.13137817382812, | |
| "learning_rate": 4.170940170940172e-06, | |
| "loss": 0.6632, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 30.020153846153846, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 1.628934621810913, | |
| "eval_runtime": 15.7152, | |
| "eval_samples_per_second": 2.863, | |
| "eval_steps_per_second": 1.464, | |
| "step": 4061 | |
| }, | |
| { | |
| "epoch": 31.001384615384616, | |
| "grad_norm": 0.3204585313796997, | |
| "learning_rate": 4.1538461538461545e-06, | |
| "loss": 0.1912, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 31.00292307692308, | |
| "grad_norm": 20.9294376373291, | |
| "learning_rate": 4.136752136752136e-06, | |
| "loss": 0.169, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 31.004461538461538, | |
| "grad_norm": 0.01061111781746149, | |
| "learning_rate": 4.11965811965812e-06, | |
| "loss": 0.5269, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 31.006, | |
| "grad_norm": 0.007479730062186718, | |
| "learning_rate": 4.102564102564103e-06, | |
| "loss": 0.2739, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 31.007538461538463, | |
| "grad_norm": 6.002195835113525, | |
| "learning_rate": 4.085470085470085e-06, | |
| "loss": 0.2087, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 31.009076923076922, | |
| "grad_norm": 21.611835479736328, | |
| "learning_rate": 4.068376068376069e-06, | |
| "loss": 0.2929, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 31.010615384615384, | |
| "grad_norm": 0.06618092209100723, | |
| "learning_rate": 4.051282051282052e-06, | |
| "loss": 0.3559, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 31.012153846153847, | |
| "grad_norm": 0.22110694646835327, | |
| "learning_rate": 4.034188034188034e-06, | |
| "loss": 0.1474, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 31.013692307692306, | |
| "grad_norm": 3.126521348953247, | |
| "learning_rate": 4.017094017094018e-06, | |
| "loss": 0.243, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 31.01523076923077, | |
| "grad_norm": 0.5178878903388977, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.9348, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 31.01676923076923, | |
| "grad_norm": 0.027309775352478027, | |
| "learning_rate": 3.982905982905983e-06, | |
| "loss": 0.1842, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 31.018307692307694, | |
| "grad_norm": 0.04132320359349251, | |
| "learning_rate": 3.965811965811966e-06, | |
| "loss": 0.5938, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 31.019846153846153, | |
| "grad_norm": 0.017868582159280777, | |
| "learning_rate": 3.948717948717949e-06, | |
| "loss": 0.3, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 31.020153846153846, | |
| "eval_accuracy": 0.6222222222222222, | |
| "eval_loss": 1.994438648223877, | |
| "eval_runtime": 15.3883, | |
| "eval_samples_per_second": 2.924, | |
| "eval_steps_per_second": 1.495, | |
| "step": 4192 | |
| }, | |
| { | |
| "epoch": 32.001230769230766, | |
| "grad_norm": 0.003818363882601261, | |
| "learning_rate": 3.9316239316239315e-06, | |
| "loss": 0.0015, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 32.00276923076923, | |
| "grad_norm": 0.0023627039045095444, | |
| "learning_rate": 3.914529914529915e-06, | |
| "loss": 0.0064, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 32.00430769230769, | |
| "grad_norm": 24.88355255126953, | |
| "learning_rate": 3.897435897435898e-06, | |
| "loss": 0.8789, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 32.00584615384616, | |
| "grad_norm": 0.012390919029712677, | |
| "learning_rate": 3.8803418803418805e-06, | |
| "loss": 0.0013, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 32.007384615384616, | |
| "grad_norm": 0.014998218044638634, | |
| "learning_rate": 3.863247863247864e-06, | |
| "loss": 0.0031, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 32.008923076923075, | |
| "grad_norm": 0.38432085514068604, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.0031, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 32.01046153846154, | |
| "grad_norm": 0.0034292784985154867, | |
| "learning_rate": 3.8290598290598295e-06, | |
| "loss": 0.465, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 32.012, | |
| "grad_norm": 0.11992474645376205, | |
| "learning_rate": 3.8119658119658122e-06, | |
| "loss": 0.1482, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 32.01353846153846, | |
| "grad_norm": 0.015120048075914383, | |
| "learning_rate": 3.794871794871795e-06, | |
| "loss": 0.1143, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 32.015076923076926, | |
| "grad_norm": 0.1242688000202179, | |
| "learning_rate": 3.777777777777778e-06, | |
| "loss": 0.0018, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 32.016615384615385, | |
| "grad_norm": 0.011846690438687801, | |
| "learning_rate": 3.760683760683761e-06, | |
| "loss": 0.6984, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 32.018153846153844, | |
| "grad_norm": 0.06057033687829971, | |
| "learning_rate": 3.743589743589744e-06, | |
| "loss": 0.5692, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 32.01969230769231, | |
| "grad_norm": 0.03488287329673767, | |
| "learning_rate": 3.726495726495727e-06, | |
| "loss": 0.386, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 32.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.9271323680877686, | |
| "eval_runtime": 15.6662, | |
| "eval_samples_per_second": 2.872, | |
| "eval_steps_per_second": 1.468, | |
| "step": 4323 | |
| }, | |
| { | |
| "epoch": 33.00107692307692, | |
| "grad_norm": 0.06287211179733276, | |
| "learning_rate": 3.7094017094017098e-06, | |
| "loss": 0.237, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 33.00261538461538, | |
| "grad_norm": 0.002027021022513509, | |
| "learning_rate": 3.692307692307693e-06, | |
| "loss": 0.007, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 33.00415384615385, | |
| "grad_norm": 0.13251464068889618, | |
| "learning_rate": 3.6752136752136756e-06, | |
| "loss": 0.5315, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 33.00569230769231, | |
| "grad_norm": 19.5275821685791, | |
| "learning_rate": 3.6581196581196584e-06, | |
| "loss": 0.7003, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 33.007230769230766, | |
| "grad_norm": 1.463071584701538, | |
| "learning_rate": 3.641025641025641e-06, | |
| "loss": 0.2885, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 33.00876923076923, | |
| "grad_norm": 0.3144843578338623, | |
| "learning_rate": 3.623931623931624e-06, | |
| "loss": 0.2137, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 33.01030769230769, | |
| "grad_norm": 273.07293701171875, | |
| "learning_rate": 3.606837606837607e-06, | |
| "loss": 0.2237, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 33.01184615384616, | |
| "grad_norm": 0.0033913287334144115, | |
| "learning_rate": 3.58974358974359e-06, | |
| "loss": 0.0594, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 33.013384615384616, | |
| "grad_norm": 0.05347070470452309, | |
| "learning_rate": 3.572649572649573e-06, | |
| "loss": 0.4805, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 33.014923076923075, | |
| "grad_norm": 0.019970282912254333, | |
| "learning_rate": 3.555555555555556e-06, | |
| "loss": 0.2014, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 33.01646153846154, | |
| "grad_norm": 30.31960105895996, | |
| "learning_rate": 3.538461538461539e-06, | |
| "loss": 0.0817, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 33.018, | |
| "grad_norm": 0.018641488626599312, | |
| "learning_rate": 3.5213675213675218e-06, | |
| "loss": 0.0087, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 33.01953846153846, | |
| "grad_norm": 0.01596497744321823, | |
| "learning_rate": 3.5042735042735045e-06, | |
| "loss": 0.1569, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 33.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.8172153234481812, | |
| "eval_runtime": 16.2833, | |
| "eval_samples_per_second": 2.764, | |
| "eval_steps_per_second": 1.412, | |
| "step": 4454 | |
| }, | |
| { | |
| "epoch": 34.00092307692308, | |
| "grad_norm": 0.03835725411772728, | |
| "learning_rate": 3.487179487179487e-06, | |
| "loss": 0.0014, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 34.00246153846154, | |
| "grad_norm": 333.5993347167969, | |
| "learning_rate": 3.4700854700854703e-06, | |
| "loss": 0.2775, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 34.004, | |
| "grad_norm": 1.2693521976470947, | |
| "learning_rate": 3.452991452991453e-06, | |
| "loss": 0.0024, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 34.005538461538464, | |
| "grad_norm": 0.018877707421779633, | |
| "learning_rate": 3.435897435897436e-06, | |
| "loss": 0.0033, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 34.00707692307692, | |
| "grad_norm": 0.034215327352285385, | |
| "learning_rate": 3.4188034188034193e-06, | |
| "loss": 0.6114, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 34.00861538461538, | |
| "grad_norm": 0.009692411869764328, | |
| "learning_rate": 3.401709401709402e-06, | |
| "loss": 0.2846, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 34.01015384615385, | |
| "grad_norm": 47.53929138183594, | |
| "learning_rate": 3.384615384615385e-06, | |
| "loss": 0.0062, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 34.01169230769231, | |
| "grad_norm": 0.028419239446520805, | |
| "learning_rate": 3.367521367521368e-06, | |
| "loss": 0.3867, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 34.013230769230766, | |
| "grad_norm": 195.8478546142578, | |
| "learning_rate": 3.3504273504273506e-06, | |
| "loss": 0.4684, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 34.01476923076923, | |
| "grad_norm": 0.0019515907624736428, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0028, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 34.01630769230769, | |
| "grad_norm": 0.03124428540468216, | |
| "learning_rate": 3.3162393162393165e-06, | |
| "loss": 0.3338, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 34.01784615384615, | |
| "grad_norm": 0.10470596700906754, | |
| "learning_rate": 3.299145299145299e-06, | |
| "loss": 0.623, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 34.01938461538462, | |
| "grad_norm": 0.0035076967906206846, | |
| "learning_rate": 3.2820512820512823e-06, | |
| "loss": 0.2135, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 34.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.786167025566101, | |
| "eval_runtime": 16.0225, | |
| "eval_samples_per_second": 2.809, | |
| "eval_steps_per_second": 1.435, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 35.00076923076923, | |
| "grad_norm": 183.2492218017578, | |
| "learning_rate": 3.2649572649572655e-06, | |
| "loss": 0.8074, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 35.002307692307696, | |
| "grad_norm": 0.03299255296587944, | |
| "learning_rate": 3.247863247863248e-06, | |
| "loss": 0.0009, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 35.003846153846155, | |
| "grad_norm": 389.8828125, | |
| "learning_rate": 3.2307692307692313e-06, | |
| "loss": 0.3484, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 35.005384615384614, | |
| "grad_norm": 166.07211303710938, | |
| "learning_rate": 3.213675213675214e-06, | |
| "loss": 0.8559, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 35.00692307692308, | |
| "grad_norm": 0.10510774701833725, | |
| "learning_rate": 3.1965811965811967e-06, | |
| "loss": 0.0327, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 35.00846153846154, | |
| "grad_norm": 0.24084274470806122, | |
| "learning_rate": 3.1794871794871795e-06, | |
| "loss": 0.4283, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "grad_norm": 0.8053629994392395, | |
| "learning_rate": 3.1623931623931626e-06, | |
| "loss": 0.477, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 35.011538461538464, | |
| "grad_norm": 72.67572021484375, | |
| "learning_rate": 3.1452991452991453e-06, | |
| "loss": 0.1098, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 35.01307692307692, | |
| "grad_norm": 0.009601065889000893, | |
| "learning_rate": 3.1282051282051284e-06, | |
| "loss": 0.273, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 35.01461538461538, | |
| "grad_norm": 0.04381426423788071, | |
| "learning_rate": 3.1111111111111116e-06, | |
| "loss": 0.1013, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 35.01615384615385, | |
| "grad_norm": 53.6818962097168, | |
| "learning_rate": 3.0940170940170943e-06, | |
| "loss": 0.541, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 35.01769230769231, | |
| "grad_norm": 0.013097396120429039, | |
| "learning_rate": 3.0769230769230774e-06, | |
| "loss": 0.0006, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 35.01923076923077, | |
| "grad_norm": 0.12090077996253967, | |
| "learning_rate": 3.05982905982906e-06, | |
| "loss": 0.3142, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 35.020153846153846, | |
| "eval_accuracy": 0.7111111111111111, | |
| "eval_loss": 1.690367341041565, | |
| "eval_runtime": 16.0234, | |
| "eval_samples_per_second": 2.808, | |
| "eval_steps_per_second": 1.435, | |
| "step": 4716 | |
| }, | |
| { | |
| "epoch": 36.00061538461539, | |
| "grad_norm": 0.25579309463500977, | |
| "learning_rate": 3.042735042735043e-06, | |
| "loss": 0.0894, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 36.002153846153846, | |
| "grad_norm": 0.026230793446302414, | |
| "learning_rate": 3.0256410256410256e-06, | |
| "loss": 0.2916, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 36.003692307692305, | |
| "grad_norm": 48.51854705810547, | |
| "learning_rate": 3.0085470085470087e-06, | |
| "loss": 0.0039, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 36.00523076923077, | |
| "grad_norm": 0.00251981639303267, | |
| "learning_rate": 2.9914529914529914e-06, | |
| "loss": 0.1385, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 36.00676923076923, | |
| "grad_norm": 45.017940521240234, | |
| "learning_rate": 2.9743589743589746e-06, | |
| "loss": 0.017, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 36.00830769230769, | |
| "grad_norm": 0.0032078921794891357, | |
| "learning_rate": 2.9572649572649577e-06, | |
| "loss": 0.354, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 36.009846153846155, | |
| "grad_norm": 0.0019023590721189976, | |
| "learning_rate": 2.9401709401709404e-06, | |
| "loss": 0.3419, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 36.011384615384614, | |
| "grad_norm": 0.04647968336939812, | |
| "learning_rate": 2.9230769230769236e-06, | |
| "loss": 0.1063, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 36.01292307692308, | |
| "grad_norm": 13.156760215759277, | |
| "learning_rate": 2.9059829059829063e-06, | |
| "loss": 0.3466, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 36.01446153846154, | |
| "grad_norm": 0.0027343109250068665, | |
| "learning_rate": 2.888888888888889e-06, | |
| "loss": 0.6772, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 36.016, | |
| "grad_norm": 0.07394647598266602, | |
| "learning_rate": 2.8717948717948717e-06, | |
| "loss": 0.1069, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 36.017538461538464, | |
| "grad_norm": 0.02956908382475376, | |
| "learning_rate": 2.854700854700855e-06, | |
| "loss": 0.0014, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 36.01907692307692, | |
| "grad_norm": 0.01068050879985094, | |
| "learning_rate": 2.8376068376068376e-06, | |
| "loss": 0.2179, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 36.020153846153846, | |
| "eval_accuracy": 0.7111111111111111, | |
| "eval_loss": 1.9548733234405518, | |
| "eval_runtime": 16.0518, | |
| "eval_samples_per_second": 2.803, | |
| "eval_steps_per_second": 1.433, | |
| "step": 4847 | |
| }, | |
| { | |
| "epoch": 37.000461538461536, | |
| "grad_norm": 27.634742736816406, | |
| "learning_rate": 2.8205128205128207e-06, | |
| "loss": 0.1896, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 37.002, | |
| "grad_norm": 0.03401556983590126, | |
| "learning_rate": 2.803418803418804e-06, | |
| "loss": 0.329, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 37.00353846153846, | |
| "grad_norm": 0.003189301583915949, | |
| "learning_rate": 2.7863247863247866e-06, | |
| "loss": 0.1839, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 37.00507692307692, | |
| "grad_norm": 1.0863280296325684, | |
| "learning_rate": 2.7692307692307697e-06, | |
| "loss": 0.3642, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 37.00661538461539, | |
| "grad_norm": 0.01546609215438366, | |
| "learning_rate": 2.7521367521367524e-06, | |
| "loss": 0.0007, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 37.008153846153846, | |
| "grad_norm": 0.0030060582794249058, | |
| "learning_rate": 2.7350427350427355e-06, | |
| "loss": 0.007, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 37.009692307692305, | |
| "grad_norm": 0.14576101303100586, | |
| "learning_rate": 2.717948717948718e-06, | |
| "loss": 0.0996, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 37.01123076923077, | |
| "grad_norm": 0.3885785639286041, | |
| "learning_rate": 2.700854700854701e-06, | |
| "loss": 0.005, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 37.01276923076923, | |
| "grad_norm": 0.021267851814627647, | |
| "learning_rate": 2.6837606837606837e-06, | |
| "loss": 0.4594, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 37.01430769230769, | |
| "grad_norm": 0.006196276750415564, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.1364, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 37.015846153846155, | |
| "grad_norm": 0.1791180819272995, | |
| "learning_rate": 2.64957264957265e-06, | |
| "loss": 0.6112, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 37.017384615384614, | |
| "grad_norm": 0.032398611307144165, | |
| "learning_rate": 2.6324786324786327e-06, | |
| "loss": 0.0264, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 37.01892307692308, | |
| "grad_norm": 0.09957725554704666, | |
| "learning_rate": 2.615384615384616e-06, | |
| "loss": 0.7634, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 37.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.9366655349731445, | |
| "eval_runtime": 16.2062, | |
| "eval_samples_per_second": 2.777, | |
| "eval_steps_per_second": 1.419, | |
| "step": 4978 | |
| }, | |
| { | |
| "epoch": 38.00030769230769, | |
| "grad_norm": 0.31356412172317505, | |
| "learning_rate": 2.5982905982905985e-06, | |
| "loss": 0.1019, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 38.00184615384615, | |
| "grad_norm": 0.03082280606031418, | |
| "learning_rate": 2.5811965811965817e-06, | |
| "loss": 0.2774, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 38.00338461538462, | |
| "grad_norm": 0.002312706783413887, | |
| "learning_rate": 2.564102564102564e-06, | |
| "loss": 0.0417, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 38.00492307692308, | |
| "grad_norm": 0.002156631788238883, | |
| "learning_rate": 2.547008547008547e-06, | |
| "loss": 0.6043, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 38.00646153846154, | |
| "grad_norm": 89.39801025390625, | |
| "learning_rate": 2.52991452991453e-06, | |
| "loss": 0.1796, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 38.008, | |
| "grad_norm": 0.04753197729587555, | |
| "learning_rate": 2.512820512820513e-06, | |
| "loss": 0.2961, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 38.00953846153846, | |
| "grad_norm": 0.00894290953874588, | |
| "learning_rate": 2.495726495726496e-06, | |
| "loss": 0.0011, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 38.01107692307692, | |
| "grad_norm": 563.5545654296875, | |
| "learning_rate": 2.478632478632479e-06, | |
| "loss": 0.1823, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 38.01261538461539, | |
| "grad_norm": 0.06258624792098999, | |
| "learning_rate": 2.461538461538462e-06, | |
| "loss": 0.8722, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 38.014153846153846, | |
| "grad_norm": 0.030548444017767906, | |
| "learning_rate": 2.4444444444444447e-06, | |
| "loss": 0.0005, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 38.015692307692305, | |
| "grad_norm": 66.49563598632812, | |
| "learning_rate": 2.4273504273504274e-06, | |
| "loss": 0.5514, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 38.01723076923077, | |
| "grad_norm": 177.74008178710938, | |
| "learning_rate": 2.4102564102564105e-06, | |
| "loss": 0.5536, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 38.01876923076923, | |
| "grad_norm": 0.025572186335921288, | |
| "learning_rate": 2.3931623931623937e-06, | |
| "loss": 0.0008, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 38.020153846153846, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.9890376329421997, | |
| "eval_runtime": 15.9552, | |
| "eval_samples_per_second": 2.82, | |
| "eval_steps_per_second": 1.442, | |
| "step": 5109 | |
| }, | |
| { | |
| "epoch": 39.00015384615384, | |
| "grad_norm": 0.0208451971411705, | |
| "learning_rate": 2.376068376068376e-06, | |
| "loss": 0.2269, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 39.00169230769231, | |
| "grad_norm": 1.7030586004257202, | |
| "learning_rate": 2.358974358974359e-06, | |
| "loss": 0.0019, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 39.00323076923077, | |
| "grad_norm": 0.01342712715268135, | |
| "learning_rate": 2.3418803418803422e-06, | |
| "loss": 0.0007, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 39.00476923076923, | |
| "grad_norm": 0.016012514010071754, | |
| "learning_rate": 2.324786324786325e-06, | |
| "loss": 0.0585, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 39.00630769230769, | |
| "grad_norm": 0.037981029599905014, | |
| "learning_rate": 2.307692307692308e-06, | |
| "loss": 0.1554, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 39.00784615384615, | |
| "grad_norm": 0.2056199014186859, | |
| "learning_rate": 2.290598290598291e-06, | |
| "loss": 0.0003, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 39.00938461538462, | |
| "grad_norm": 0.004496376030147076, | |
| "learning_rate": 2.2735042735042735e-06, | |
| "loss": 0.231, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 39.01092307692308, | |
| "grad_norm": 0.0014036957873031497, | |
| "learning_rate": 2.2564102564102566e-06, | |
| "loss": 0.2336, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 39.01246153846154, | |
| "grad_norm": 0.006723294500261545, | |
| "learning_rate": 2.2393162393162398e-06, | |
| "loss": 0.0017, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 39.014, | |
| "grad_norm": 0.022703466936945915, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.0014, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 39.01553846153846, | |
| "grad_norm": 0.041783999651670456, | |
| "learning_rate": 2.2051282051282052e-06, | |
| "loss": 0.6549, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 39.01707692307692, | |
| "grad_norm": 0.24678336083889008, | |
| "learning_rate": 2.1880341880341884e-06, | |
| "loss": 0.0115, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 39.01861538461539, | |
| "grad_norm": 0.0029962738044559956, | |
| "learning_rate": 2.170940170940171e-06, | |
| "loss": 0.2902, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 39.020153846153846, | |
| "grad_norm": 0.0021075329277664423, | |
| "learning_rate": 2.153846153846154e-06, | |
| "loss": 0.1467, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 39.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.9472049474716187, | |
| "eval_runtime": 16.0174, | |
| "eval_samples_per_second": 2.809, | |
| "eval_steps_per_second": 1.436, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 40.00153846153846, | |
| "grad_norm": 0.0024151760153472424, | |
| "learning_rate": 2.136752136752137e-06, | |
| "loss": 0.0135, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 40.003076923076925, | |
| "grad_norm": 342.5179138183594, | |
| "learning_rate": 2.1196581196581196e-06, | |
| "loss": 0.0323, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 40.004615384615384, | |
| "grad_norm": 0.0019280047854408622, | |
| "learning_rate": 2.1025641025641028e-06, | |
| "loss": 0.0003, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 40.00615384615384, | |
| "grad_norm": 0.014891207218170166, | |
| "learning_rate": 2.085470085470086e-06, | |
| "loss": 0.2991, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 40.00769230769231, | |
| "grad_norm": 0.0586637407541275, | |
| "learning_rate": 2.068376068376068e-06, | |
| "loss": 0.0066, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 40.00923076923077, | |
| "grad_norm": 10.247905731201172, | |
| "learning_rate": 2.0512820512820513e-06, | |
| "loss": 1.1058, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 40.01076923076923, | |
| "grad_norm": 0.0016218910459429026, | |
| "learning_rate": 2.0341880341880345e-06, | |
| "loss": 1.2653, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 40.012307692307694, | |
| "grad_norm": 0.0872465968132019, | |
| "learning_rate": 2.017094017094017e-06, | |
| "loss": 0.3343, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 40.01384615384615, | |
| "grad_norm": 0.0031448754016309977, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.3466, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 40.01538461538462, | |
| "grad_norm": 0.024707229807972908, | |
| "learning_rate": 1.982905982905983e-06, | |
| "loss": 0.078, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 40.01692307692308, | |
| "grad_norm": 0.17816458642482758, | |
| "learning_rate": 1.9658119658119658e-06, | |
| "loss": 0.0035, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 40.01846153846154, | |
| "grad_norm": 0.0026180462446063757, | |
| "learning_rate": 1.948717948717949e-06, | |
| "loss": 0.0005, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "grad_norm": 0.0011988329933956265, | |
| "learning_rate": 1.931623931623932e-06, | |
| "loss": 0.6641, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 40.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 2.229515790939331, | |
| "eval_runtime": 15.615, | |
| "eval_samples_per_second": 2.882, | |
| "eval_steps_per_second": 1.473, | |
| "step": 5371 | |
| }, | |
| { | |
| "epoch": 41.001384615384616, | |
| "grad_norm": 0.0012583574280142784, | |
| "learning_rate": 1.9145299145299148e-06, | |
| "loss": 0.0003, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 41.002923076923075, | |
| "grad_norm": 0.01711999624967575, | |
| "learning_rate": 1.8974358974358975e-06, | |
| "loss": 0.0833, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 41.00446153846154, | |
| "grad_norm": 81.41534423828125, | |
| "learning_rate": 1.8803418803418804e-06, | |
| "loss": 0.0113, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 41.006, | |
| "grad_norm": 0.009872028604149818, | |
| "learning_rate": 1.8632478632478635e-06, | |
| "loss": 0.2801, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 41.00753846153846, | |
| "grad_norm": 0.004543512128293514, | |
| "learning_rate": 1.8461538461538465e-06, | |
| "loss": 0.0003, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 41.009076923076925, | |
| "grad_norm": 22.236766815185547, | |
| "learning_rate": 1.8290598290598292e-06, | |
| "loss": 0.0774, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 41.010615384615384, | |
| "grad_norm": 0.004586371593177319, | |
| "learning_rate": 1.811965811965812e-06, | |
| "loss": 0.0938, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 41.01215384615384, | |
| "grad_norm": 0.02045535482466221, | |
| "learning_rate": 1.794871794871795e-06, | |
| "loss": 0.2767, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 41.01369230769231, | |
| "grad_norm": 0.0031150062568485737, | |
| "learning_rate": 1.777777777777778e-06, | |
| "loss": 0.3426, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 41.01523076923077, | |
| "grad_norm": 0.0021908292546868324, | |
| "learning_rate": 1.7606837606837609e-06, | |
| "loss": 0.7493, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 41.01676923076923, | |
| "grad_norm": 328.08953857421875, | |
| "learning_rate": 1.7435897435897436e-06, | |
| "loss": 0.0352, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 41.018307692307694, | |
| "grad_norm": 0.012240348383784294, | |
| "learning_rate": 1.7264957264957265e-06, | |
| "loss": 0.0004, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 41.01984615384615, | |
| "grad_norm": 0.0035047270357608795, | |
| "learning_rate": 1.7094017094017097e-06, | |
| "loss": 0.3125, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 41.020153846153846, | |
| "eval_accuracy": 0.7111111111111111, | |
| "eval_loss": 1.8308573961257935, | |
| "eval_runtime": 15.5061, | |
| "eval_samples_per_second": 2.902, | |
| "eval_steps_per_second": 1.483, | |
| "step": 5502 | |
| }, | |
| { | |
| "epoch": 42.001230769230766, | |
| "grad_norm": 0.02215719036757946, | |
| "learning_rate": 1.6923076923076926e-06, | |
| "loss": 0.254, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 42.00276923076923, | |
| "grad_norm": 0.007011354435235262, | |
| "learning_rate": 1.6752136752136753e-06, | |
| "loss": 0.217, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 42.00430769230769, | |
| "grad_norm": 0.032918259501457214, | |
| "learning_rate": 1.6581196581196582e-06, | |
| "loss": 0.0007, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 42.00584615384616, | |
| "grad_norm": 512.6629028320312, | |
| "learning_rate": 1.6410256410256412e-06, | |
| "loss": 0.4539, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 42.007384615384616, | |
| "grad_norm": 0.16200533509254456, | |
| "learning_rate": 1.623931623931624e-06, | |
| "loss": 0.0003, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 42.008923076923075, | |
| "grad_norm": 0.0022220315877348185, | |
| "learning_rate": 1.606837606837607e-06, | |
| "loss": 0.0046, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 42.01046153846154, | |
| "grad_norm": 244.07183837890625, | |
| "learning_rate": 1.5897435897435897e-06, | |
| "loss": 0.3181, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 42.012, | |
| "grad_norm": 0.0018573395209386945, | |
| "learning_rate": 1.5726495726495727e-06, | |
| "loss": 0.3457, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 42.01353846153846, | |
| "grad_norm": 102.92440032958984, | |
| "learning_rate": 1.5555555555555558e-06, | |
| "loss": 0.1621, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 42.015076923076926, | |
| "grad_norm": 0.13172288239002228, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 0.0037, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 42.016615384615385, | |
| "grad_norm": 0.040461424738168716, | |
| "learning_rate": 1.5213675213675214e-06, | |
| "loss": 0.0004, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 42.018153846153844, | |
| "grad_norm": 0.005434774328023195, | |
| "learning_rate": 1.5042735042735044e-06, | |
| "loss": 0.0003, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 42.01969230769231, | |
| "grad_norm": 56.10285568237305, | |
| "learning_rate": 1.4871794871794873e-06, | |
| "loss": 0.1987, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 42.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 2.1642696857452393, | |
| "eval_runtime": 15.4215, | |
| "eval_samples_per_second": 2.918, | |
| "eval_steps_per_second": 1.491, | |
| "step": 5633 | |
| }, | |
| { | |
| "epoch": 43.00107692307692, | |
| "grad_norm": 0.042919330298900604, | |
| "learning_rate": 1.4700854700854702e-06, | |
| "loss": 0.3619, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 43.00261538461538, | |
| "grad_norm": 0.015451325103640556, | |
| "learning_rate": 1.4529914529914531e-06, | |
| "loss": 0.6791, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 43.00415384615385, | |
| "grad_norm": 0.00853314995765686, | |
| "learning_rate": 1.4358974358974359e-06, | |
| "loss": 0.002, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 43.00569230769231, | |
| "grad_norm": 0.0032931955065578222, | |
| "learning_rate": 1.4188034188034188e-06, | |
| "loss": 0.0011, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 43.007230769230766, | |
| "grad_norm": 0.12060777097940445, | |
| "learning_rate": 1.401709401709402e-06, | |
| "loss": 0.0008, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 43.00876923076923, | |
| "grad_norm": 0.10713399201631546, | |
| "learning_rate": 1.3846153846153848e-06, | |
| "loss": 0.3173, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 43.01030769230769, | |
| "grad_norm": 0.21394962072372437, | |
| "learning_rate": 1.3675213675213678e-06, | |
| "loss": 0.3315, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 43.01184615384616, | |
| "grad_norm": 0.0013513584854081273, | |
| "learning_rate": 1.3504273504273505e-06, | |
| "loss": 0.215, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 43.013384615384616, | |
| "grad_norm": 0.033072855323553085, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.5777, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 43.014923076923075, | |
| "grad_norm": 0.04304918646812439, | |
| "learning_rate": 1.3162393162393163e-06, | |
| "loss": 0.0015, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 43.01646153846154, | |
| "grad_norm": 0.022566115483641624, | |
| "learning_rate": 1.2991452991452993e-06, | |
| "loss": 0.0007, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 43.018, | |
| "grad_norm": 0.017003845423460007, | |
| "learning_rate": 1.282051282051282e-06, | |
| "loss": 0.0006, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 43.01953846153846, | |
| "grad_norm": 0.023580145090818405, | |
| "learning_rate": 1.264957264957265e-06, | |
| "loss": 0.067, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 43.020153846153846, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 2.1775522232055664, | |
| "eval_runtime": 15.3864, | |
| "eval_samples_per_second": 2.925, | |
| "eval_steps_per_second": 1.495, | |
| "step": 5764 | |
| }, | |
| { | |
| "epoch": 44.00092307692308, | |
| "grad_norm": 2.5207345485687256, | |
| "learning_rate": 1.247863247863248e-06, | |
| "loss": 0.2907, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 44.00246153846154, | |
| "grad_norm": 0.019762292504310608, | |
| "learning_rate": 1.230769230769231e-06, | |
| "loss": 0.0009, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 44.004, | |
| "grad_norm": 0.028931161388754845, | |
| "learning_rate": 1.2136752136752137e-06, | |
| "loss": 0.1307, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 44.005538461538464, | |
| "grad_norm": 0.018632153049111366, | |
| "learning_rate": 1.1965811965811968e-06, | |
| "loss": 0.0967, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 44.00707692307692, | |
| "grad_norm": 0.0010644891299307346, | |
| "learning_rate": 1.1794871794871795e-06, | |
| "loss": 0.3249, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 44.00861538461538, | |
| "grad_norm": 0.030815087258815765, | |
| "learning_rate": 1.1623931623931625e-06, | |
| "loss": 0.0032, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 44.01015384615385, | |
| "grad_norm": 0.005695466883480549, | |
| "learning_rate": 1.1452991452991454e-06, | |
| "loss": 0.0002, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 44.01169230769231, | |
| "grad_norm": 0.01355106569826603, | |
| "learning_rate": 1.1282051282051283e-06, | |
| "loss": 0.6507, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 44.013230769230766, | |
| "grad_norm": 0.041898563504219055, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.0011, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 44.01476923076923, | |
| "grad_norm": 0.0023415556643158197, | |
| "learning_rate": 1.0940170940170942e-06, | |
| "loss": 0.0005, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 44.01630769230769, | |
| "grad_norm": 0.021183600649237633, | |
| "learning_rate": 1.076923076923077e-06, | |
| "loss": 0.0272, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 44.01784615384615, | |
| "grad_norm": 0.020908724516630173, | |
| "learning_rate": 1.0598290598290598e-06, | |
| "loss": 0.0042, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 44.01938461538462, | |
| "grad_norm": 0.0010696717072278261, | |
| "learning_rate": 1.042735042735043e-06, | |
| "loss": 0.1513, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 44.020153846153846, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 2.197768211364746, | |
| "eval_runtime": 15.3964, | |
| "eval_samples_per_second": 2.923, | |
| "eval_steps_per_second": 1.494, | |
| "step": 5895 | |
| }, | |
| { | |
| "epoch": 45.00076923076923, | |
| "grad_norm": 0.009786905720829964, | |
| "learning_rate": 1.0256410256410257e-06, | |
| "loss": 0.0169, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 45.002307692307696, | |
| "grad_norm": 0.09270879626274109, | |
| "learning_rate": 1.0085470085470086e-06, | |
| "loss": 0.4358, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 45.003846153846155, | |
| "grad_norm": 0.0011247596703469753, | |
| "learning_rate": 9.914529914529915e-07, | |
| "loss": 0.0002, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 45.005384615384614, | |
| "grad_norm": 110.18008422851562, | |
| "learning_rate": 9.743589743589745e-07, | |
| "loss": 0.0072, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 45.00692307692308, | |
| "grad_norm": 0.011247043497860432, | |
| "learning_rate": 9.572649572649574e-07, | |
| "loss": 0.0059, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 45.00846153846154, | |
| "grad_norm": 0.0025047967210412025, | |
| "learning_rate": 9.401709401709402e-07, | |
| "loss": 0.015, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "grad_norm": 0.0009302306571044028, | |
| "learning_rate": 9.230769230769232e-07, | |
| "loss": 0.3494, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 45.011538461538464, | |
| "grad_norm": 0.04420846328139305, | |
| "learning_rate": 9.05982905982906e-07, | |
| "loss": 0.0009, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 45.01307692307692, | |
| "grad_norm": 0.0010389067465439439, | |
| "learning_rate": 8.88888888888889e-07, | |
| "loss": 0.0002, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 45.01461538461538, | |
| "grad_norm": 0.01501426100730896, | |
| "learning_rate": 8.717948717948718e-07, | |
| "loss": 0.4251, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 45.01615384615385, | |
| "grad_norm": 0.0015382227720692754, | |
| "learning_rate": 8.547008547008548e-07, | |
| "loss": 0.069, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 45.01769230769231, | |
| "grad_norm": 68.94315338134766, | |
| "learning_rate": 8.376068376068377e-07, | |
| "loss": 0.1416, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 45.01923076923077, | |
| "grad_norm": 0.0014991145581007004, | |
| "learning_rate": 8.205128205128206e-07, | |
| "loss": 0.0032, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 45.020153846153846, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 1.9290975332260132, | |
| "eval_runtime": 15.7172, | |
| "eval_samples_per_second": 2.863, | |
| "eval_steps_per_second": 1.463, | |
| "step": 6026 | |
| }, | |
| { | |
| "epoch": 46.00061538461539, | |
| "grad_norm": 0.007120060734450817, | |
| "learning_rate": 8.034188034188035e-07, | |
| "loss": 0.2056, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 46.002153846153846, | |
| "grad_norm": 0.3839905261993408, | |
| "learning_rate": 7.863247863247863e-07, | |
| "loss": 0.0006, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 46.003692307692305, | |
| "grad_norm": 0.01137951947748661, | |
| "learning_rate": 7.692307692307694e-07, | |
| "loss": 0.0004, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 46.00523076923077, | |
| "grad_norm": 278.9681396484375, | |
| "learning_rate": 7.521367521367522e-07, | |
| "loss": 0.2465, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 46.00676923076923, | |
| "grad_norm": 0.0020568182226270437, | |
| "learning_rate": 7.350427350427351e-07, | |
| "loss": 0.0002, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 46.00830769230769, | |
| "grad_norm": 0.16227321326732635, | |
| "learning_rate": 7.179487179487179e-07, | |
| "loss": 0.0004, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 46.009846153846155, | |
| "grad_norm": 0.003921395167708397, | |
| "learning_rate": 7.00854700854701e-07, | |
| "loss": 0.0904, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 46.011384615384614, | |
| "grad_norm": 0.0013251190539449453, | |
| "learning_rate": 6.837606837606839e-07, | |
| "loss": 0.0348, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 46.01292307692308, | |
| "grad_norm": 0.038590025156736374, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 0.0029, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 46.01446153846154, | |
| "grad_norm": 0.528531551361084, | |
| "learning_rate": 6.495726495726496e-07, | |
| "loss": 0.0009, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 46.016, | |
| "grad_norm": 6.073200225830078, | |
| "learning_rate": 6.324786324786325e-07, | |
| "loss": 0.212, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 46.017538461538464, | |
| "grad_norm": 0.014943752437829971, | |
| "learning_rate": 6.153846153846155e-07, | |
| "loss": 0.179, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 46.01907692307692, | |
| "grad_norm": 0.008535191416740417, | |
| "learning_rate": 5.982905982905984e-07, | |
| "loss": 0.2596, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 46.020153846153846, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 2.0960593223571777, | |
| "eval_runtime": 15.7758, | |
| "eval_samples_per_second": 2.852, | |
| "eval_steps_per_second": 1.458, | |
| "step": 6157 | |
| }, | |
| { | |
| "epoch": 47.000461538461536, | |
| "grad_norm": 0.001672409474849701, | |
| "learning_rate": 5.811965811965812e-07, | |
| "loss": 0.0005, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 47.002, | |
| "grad_norm": 0.0025854981504380703, | |
| "learning_rate": 5.641025641025642e-07, | |
| "loss": 0.1463, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 47.00353846153846, | |
| "grad_norm": 0.0020239180885255337, | |
| "learning_rate": 5.470085470085471e-07, | |
| "loss": 0.2607, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 47.00507692307692, | |
| "grad_norm": 99.7693862915039, | |
| "learning_rate": 5.299145299145299e-07, | |
| "loss": 0.0308, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 47.00661538461539, | |
| "grad_norm": 0.14723490178585052, | |
| "learning_rate": 5.128205128205128e-07, | |
| "loss": 0.1749, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 47.008153846153846, | |
| "grad_norm": 0.054609451442956924, | |
| "learning_rate": 4.957264957264958e-07, | |
| "loss": 0.1042, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 47.009692307692305, | |
| "grad_norm": 0.014094150625169277, | |
| "learning_rate": 4.786324786324787e-07, | |
| "loss": 0.0002, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 47.01123076923077, | |
| "grad_norm": 0.0011078680399805307, | |
| "learning_rate": 4.615384615384616e-07, | |
| "loss": 0.2679, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 47.01276923076923, | |
| "grad_norm": 0.0008717267191968858, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 0.0003, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 47.01430769230769, | |
| "grad_norm": 0.001475340686738491, | |
| "learning_rate": 4.273504273504274e-07, | |
| "loss": 0.0718, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 47.015846153846155, | |
| "grad_norm": 0.01086998451501131, | |
| "learning_rate": 4.102564102564103e-07, | |
| "loss": 0.0003, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 47.017384615384614, | |
| "grad_norm": 0.016304757446050644, | |
| "learning_rate": 3.9316239316239316e-07, | |
| "loss": 0.0922, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 47.01892307692308, | |
| "grad_norm": 0.038236528635025024, | |
| "learning_rate": 3.760683760683761e-07, | |
| "loss": 0.0006, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 47.020153846153846, | |
| "eval_accuracy": 0.7111111111111111, | |
| "eval_loss": 2.012601137161255, | |
| "eval_runtime": 15.7365, | |
| "eval_samples_per_second": 2.86, | |
| "eval_steps_per_second": 1.462, | |
| "step": 6288 | |
| }, | |
| { | |
| "epoch": 48.00030769230769, | |
| "grad_norm": 0.0009028087952174246, | |
| "learning_rate": 3.5897435897435896e-07, | |
| "loss": 0.3911, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 48.00184615384615, | |
| "grad_norm": 0.03778388723731041, | |
| "learning_rate": 3.4188034188034194e-07, | |
| "loss": 0.1776, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 48.00338461538462, | |
| "grad_norm": 0.00178238982334733, | |
| "learning_rate": 3.247863247863248e-07, | |
| "loss": 0.0003, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 48.00492307692308, | |
| "grad_norm": 0.0011350319255143404, | |
| "learning_rate": 3.0769230769230774e-07, | |
| "loss": 0.0004, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 48.00646153846154, | |
| "grad_norm": 0.012523042969405651, | |
| "learning_rate": 2.905982905982906e-07, | |
| "loss": 0.2147, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 48.008, | |
| "grad_norm": 0.01577194780111313, | |
| "learning_rate": 2.7350427350427354e-07, | |
| "loss": 0.0006, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 48.00953846153846, | |
| "grad_norm": 0.32982873916625977, | |
| "learning_rate": 2.564102564102564e-07, | |
| "loss": 0.0093, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 48.01107692307692, | |
| "grad_norm": 0.008411101996898651, | |
| "learning_rate": 2.3931623931623934e-07, | |
| "loss": 0.1596, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 48.01261538461539, | |
| "grad_norm": 0.020035186782479286, | |
| "learning_rate": 2.2222222222222224e-07, | |
| "loss": 0.0003, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 48.014153846153846, | |
| "grad_norm": 0.007987803779542446, | |
| "learning_rate": 2.0512820512820514e-07, | |
| "loss": 0.0802, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 48.015692307692305, | |
| "grad_norm": 0.008993521332740784, | |
| "learning_rate": 1.8803418803418804e-07, | |
| "loss": 0.0123, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 48.01723076923077, | |
| "grad_norm": 0.020024364814162254, | |
| "learning_rate": 1.7094017094017097e-07, | |
| "loss": 0.0003, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 48.01876923076923, | |
| "grad_norm": 0.7685058116912842, | |
| "learning_rate": 1.5384615384615387e-07, | |
| "loss": 0.0305, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 48.020153846153846, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 2.002918004989624, | |
| "eval_runtime": 16.0489, | |
| "eval_samples_per_second": 2.804, | |
| "eval_steps_per_second": 1.433, | |
| "step": 6419 | |
| }, | |
| { | |
| "epoch": 49.00015384615384, | |
| "grad_norm": 0.0027175634168088436, | |
| "learning_rate": 1.3675213675213677e-07, | |
| "loss": 0.0002, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 49.00169230769231, | |
| "grad_norm": 9.381722450256348, | |
| "learning_rate": 1.1965811965811967e-07, | |
| "loss": 0.0215, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 49.00323076923077, | |
| "grad_norm": 0.06847649067640305, | |
| "learning_rate": 1.0256410256410257e-07, | |
| "loss": 0.1176, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 49.00476923076923, | |
| "grad_norm": 0.008719404228031635, | |
| "learning_rate": 8.547008547008549e-08, | |
| "loss": 0.0524, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 49.00630769230769, | |
| "grad_norm": 0.028443889692425728, | |
| "learning_rate": 6.837606837606839e-08, | |
| "loss": 0.1821, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 49.00784615384615, | |
| "grad_norm": 0.02021080255508423, | |
| "learning_rate": 5.1282051282051286e-08, | |
| "loss": 0.0022, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 49.00938461538462, | |
| "grad_norm": 0.038820087909698486, | |
| "learning_rate": 3.418803418803419e-08, | |
| "loss": 0.0011, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 49.01092307692308, | |
| "grad_norm": 0.015021397732198238, | |
| "learning_rate": 1.7094017094017096e-08, | |
| "loss": 0.0002, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "grad_norm": 0.00419115275144577, | |
| "learning_rate": 0.0, | |
| "loss": 0.0004, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 2.0025010108947754, | |
| "eval_runtime": 16.8934, | |
| "eval_samples_per_second": 2.664, | |
| "eval_steps_per_second": 1.361, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "step": 6500, | |
| "total_flos": 5.686818180940844e+19, | |
| "train_loss": 0.4763805888665553, | |
| "train_runtime": 12566.3859, | |
| "train_samples_per_second": 1.035, | |
| "train_steps_per_second": 0.517 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 1.5069091320037842, | |
| "eval_runtime": 16.1606, | |
| "eval_samples_per_second": 2.785, | |
| "eval_steps_per_second": 1.423, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 49.01246153846154, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 1.5069090127944946, | |
| "eval_runtime": 16.232, | |
| "eval_samples_per_second": 2.772, | |
| "eval_steps_per_second": 1.417, | |
| "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 | |
| } | |