| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9957446808510637, | |
| "eval_steps": 500, | |
| "global_step": 1320, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02269503546099291, | |
| "grad_norm": 2.4400690431145335, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9537, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04539007092198582, | |
| "grad_norm": 1.0371553805334768, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8304, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06808510638297872, | |
| "grad_norm": 0.8207371359291633, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7801, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09078014184397164, | |
| "grad_norm": 0.7210586495004421, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7522, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": 0.815177982428463, | |
| "learning_rate": 5e-06, | |
| "loss": 0.739, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13617021276595745, | |
| "grad_norm": 2.1607006669022053, | |
| "learning_rate": 5e-06, | |
| "loss": 0.731, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15886524822695036, | |
| "grad_norm": 0.8260032479277283, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7245, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18156028368794327, | |
| "grad_norm": 0.6043557996158753, | |
| "learning_rate": 5e-06, | |
| "loss": 0.709, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20425531914893616, | |
| "grad_norm": 0.6817812588474443, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7065, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 0.6633270827705589, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7042, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24964539007092199, | |
| "grad_norm": 0.8788640026205816, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6937, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2723404255319149, | |
| "grad_norm": 0.6318189161156693, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6875, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2950354609929078, | |
| "grad_norm": 0.6116775844736505, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6882, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3177304964539007, | |
| "grad_norm": 0.5442399734240484, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6829, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 0.772917712294573, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6778, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.36312056737588655, | |
| "grad_norm": 0.5042750571740913, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6826, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38581560283687943, | |
| "grad_norm": 0.5272476451832978, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6791, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4085106382978723, | |
| "grad_norm": 0.6477667523961554, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6778, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43120567375886526, | |
| "grad_norm": 0.6825001542564298, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6727, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": 0.7223077265284692, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6766, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4765957446808511, | |
| "grad_norm": 0.7610671419515379, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6754, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.49929078014184397, | |
| "grad_norm": 0.5918397478370985, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6707, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5219858156028369, | |
| "grad_norm": 0.5937553589475805, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6695, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5446808510638298, | |
| "grad_norm": 0.6308694971546095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6706, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 0.5145635067713508, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6638, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5900709219858156, | |
| "grad_norm": 0.8960582295099536, | |
| "learning_rate": 5e-06, | |
| "loss": 0.659, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6127659574468085, | |
| "grad_norm": 0.5714201206969344, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6648, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6354609929078014, | |
| "grad_norm": 0.5218865972600176, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6692, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6581560283687943, | |
| "grad_norm": 0.908425551953448, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6603, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.5937599038511239, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6616, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7035460992907802, | |
| "grad_norm": 0.5791492049959488, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6573, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7262411347517731, | |
| "grad_norm": 0.5544912073084471, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6561, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7489361702127659, | |
| "grad_norm": 0.6161595885325214, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6535, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7716312056737589, | |
| "grad_norm": 0.5292955751782062, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6575, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7943262411347518, | |
| "grad_norm": 0.5125989549019483, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6508, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8170212765957446, | |
| "grad_norm": 0.4999207740358057, | |
| "learning_rate": 5e-06, | |
| "loss": 0.652, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8397163120567376, | |
| "grad_norm": 0.5737129637592092, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6487, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8624113475177305, | |
| "grad_norm": 0.697556121614893, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6537, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8851063829787233, | |
| "grad_norm": 0.8803924578376542, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6528, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9078014184397163, | |
| "grad_norm": 0.7209729745886211, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6499, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9304964539007092, | |
| "grad_norm": 0.631225301000223, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6493, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9531914893617022, | |
| "grad_norm": 0.5302593707285189, | |
| "learning_rate": 5e-06, | |
| "loss": 0.651, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.975886524822695, | |
| "grad_norm": 0.5216458807768983, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6438, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9985815602836879, | |
| "grad_norm": 0.5024039028278129, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6478, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9985815602836879, | |
| "eval_loss": 0.64774489402771, | |
| "eval_runtime": 312.1779, | |
| "eval_samples_per_second": 38.036, | |
| "eval_steps_per_second": 0.596, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 0.6519926768853314, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6161, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0439716312056737, | |
| "grad_norm": 0.575055735064131, | |
| "learning_rate": 5e-06, | |
| "loss": 0.589, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.9082080666134971, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5912, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0893617021276596, | |
| "grad_norm": 0.583715919536177, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5913, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1120567375886525, | |
| "grad_norm": 0.5975048919359871, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5976, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1347517730496455, | |
| "grad_norm": 0.5418419185217853, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5931, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1574468085106382, | |
| "grad_norm": 0.638492552707852, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5913, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1801418439716311, | |
| "grad_norm": 0.5450441529585099, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5888, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.202836879432624, | |
| "grad_norm": 0.667596474347774, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5926, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.225531914893617, | |
| "grad_norm": 0.5901671600943978, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5905, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.24822695035461, | |
| "grad_norm": 0.5680819366472465, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5915, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.270921985815603, | |
| "grad_norm": 0.7905201905390314, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2936170212765958, | |
| "grad_norm": 0.5581341122325792, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5904, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3163120567375888, | |
| "grad_norm": 0.5968971489169257, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5927, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3390070921985815, | |
| "grad_norm": 0.6127986193776547, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5889, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.3617021276595744, | |
| "grad_norm": 0.5540746342979398, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5998, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.3843971631205674, | |
| "grad_norm": 0.6578848756357453, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5933, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4070921985815603, | |
| "grad_norm": 0.752983431690844, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5967, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4297872340425533, | |
| "grad_norm": 0.6009296481522326, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5886, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.452482269503546, | |
| "grad_norm": 0.6855926736224828, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5931, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.475177304964539, | |
| "grad_norm": 0.5390133364015494, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5926, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.4978723404255319, | |
| "grad_norm": 0.6338310115530009, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5969, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5205673758865248, | |
| "grad_norm": 0.5298069642997515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5868, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5432624113475177, | |
| "grad_norm": 0.5254529387411777, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5893, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.5659574468085107, | |
| "grad_norm": 0.5090891733108535, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5937, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.5886524822695036, | |
| "grad_norm": 0.6276632546884366, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5856, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6113475177304966, | |
| "grad_norm": 0.5618088874975952, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5796, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6340425531914895, | |
| "grad_norm": 0.5451154576203426, | |
| "learning_rate": 5e-06, | |
| "loss": 0.584, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6567375886524822, | |
| "grad_norm": 0.5751145914968212, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5882, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6794326241134752, | |
| "grad_norm": 0.5457326197852193, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5893, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.702127659574468, | |
| "grad_norm": 0.5538870750639828, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5895, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.724822695035461, | |
| "grad_norm": 0.6482629759445236, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5883, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7475177304964538, | |
| "grad_norm": 0.604796917686035, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5908, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7702127659574467, | |
| "grad_norm": 0.5570179578262068, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5935, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.7929078014184396, | |
| "grad_norm": 0.5359469482507023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5833, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8156028368794326, | |
| "grad_norm": 0.6340496302965002, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5853, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8382978723404255, | |
| "grad_norm": 0.5742298835017674, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5823, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.8609929078014185, | |
| "grad_norm": 0.5827541219871901, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5903, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8836879432624114, | |
| "grad_norm": 0.528321132004614, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5832, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9063829787234043, | |
| "grad_norm": 0.565101788703942, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5855, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.9290780141843973, | |
| "grad_norm": 0.601792497070637, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5842, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9517730496453902, | |
| "grad_norm": 0.5088677439673144, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5821, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.974468085106383, | |
| "grad_norm": 0.6353626361966195, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5865, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9971631205673759, | |
| "grad_norm": 0.627955882058217, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5869, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.9994326241134752, | |
| "eval_loss": 0.63065505027771, | |
| "eval_runtime": 299.005, | |
| "eval_samples_per_second": 39.712, | |
| "eval_steps_per_second": 0.622, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 2.0198581560283686, | |
| "grad_norm": 0.7421753177971604, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5575, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0425531914893615, | |
| "grad_norm": 0.7475116659953, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5333, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0652482269503545, | |
| "grad_norm": 0.6094678843754806, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5281, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.0879432624113474, | |
| "grad_norm": 0.6416679206326653, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5307, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1106382978723404, | |
| "grad_norm": 0.6149270041451872, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5253, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.5944382793137648, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5321, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.1560283687943262, | |
| "grad_norm": 0.5206404660542666, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5327, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.178723404255319, | |
| "grad_norm": 0.5421603421972422, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5283, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.201418439716312, | |
| "grad_norm": 0.630367827768556, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5312, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.224113475177305, | |
| "grad_norm": 0.5289786942278032, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5281, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.246808510638298, | |
| "grad_norm": 0.6186809984064454, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5287, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.269503546099291, | |
| "grad_norm": 0.5941474628916863, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5349, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.2921985815602834, | |
| "grad_norm": 0.570443876715086, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5295, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.3148936170212764, | |
| "grad_norm": 0.6792218051762158, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5323, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.3375886524822693, | |
| "grad_norm": 0.5535124105821935, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5277, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3602836879432623, | |
| "grad_norm": 0.667112587037914, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5276, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.382978723404255, | |
| "grad_norm": 0.5987387148760719, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5295, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.405673758865248, | |
| "grad_norm": 0.5484898675236806, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5328, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.428368794326241, | |
| "grad_norm": 0.5736373550799053, | |
| "learning_rate": 5e-06, | |
| "loss": 0.534, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.451063829787234, | |
| "grad_norm": 0.5626598264859632, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5356, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.473758865248227, | |
| "grad_norm": 0.6153434121318484, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5306, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.49645390070922, | |
| "grad_norm": 0.7252891365142108, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5307, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.519148936170213, | |
| "grad_norm": 0.6153968835692192, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5331, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.541843971631206, | |
| "grad_norm": 0.5969808676825302, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5363, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.5645390070921987, | |
| "grad_norm": 0.5692435999805617, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5391, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5872340425531917, | |
| "grad_norm": 0.6180618030016519, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5299, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.6099290780141846, | |
| "grad_norm": 0.543137746234749, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5374, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.6326241134751776, | |
| "grad_norm": 0.5200265379748215, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5309, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.65531914893617, | |
| "grad_norm": 0.5194882503023576, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5293, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.678014184397163, | |
| "grad_norm": 0.5570786417431203, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5316, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.700709219858156, | |
| "grad_norm": 0.6007520350434941, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5347, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.723404255319149, | |
| "grad_norm": 0.5662193506846984, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5339, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.746099290780142, | |
| "grad_norm": 0.6675198025626778, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5346, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.7687943262411348, | |
| "grad_norm": 0.6689385730256848, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5303, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.7914893617021277, | |
| "grad_norm": 0.6400833035990827, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5315, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.8141843971631206, | |
| "grad_norm": 0.6835204230746162, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5367, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8368794326241136, | |
| "grad_norm": 0.5862756798841194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5346, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.8595744680851065, | |
| "grad_norm": 0.5727844470422598, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5376, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8822695035460995, | |
| "grad_norm": 0.5445857583169009, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5294, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.904964539007092, | |
| "grad_norm": 0.6161117247407584, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5309, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.927659574468085, | |
| "grad_norm": 0.6027552334532725, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5359, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.950354609929078, | |
| "grad_norm": 0.6005574689486347, | |
| "learning_rate": 5e-06, | |
| "loss": 0.531, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9730496453900708, | |
| "grad_norm": 0.5590382510647179, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5348, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.9957446808510637, | |
| "grad_norm": 0.5507647179314145, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5325, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.9957446808510637, | |
| "eval_loss": 0.6309003829956055, | |
| "eval_runtime": 301.6902, | |
| "eval_samples_per_second": 39.358, | |
| "eval_steps_per_second": 0.617, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.9957446808510637, | |
| "step": 1320, | |
| "total_flos": 2210839784325120.0, | |
| "train_loss": 0.6033726125052481, | |
| "train_runtime": 44159.109, | |
| "train_samples_per_second": 15.326, | |
| "train_steps_per_second": 0.03 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1320, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2210839784325120.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |