| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1269, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02364066193853428, | |
| "grad_norm": 2.72535029902805, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8948, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04728132387706856, | |
| "grad_norm": 1.349869757361133, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7791, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07092198581560284, | |
| "grad_norm": 1.1982665750771995, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7498, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09456264775413711, | |
| "grad_norm": 1.3901014180682558, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7383, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1182033096926714, | |
| "grad_norm": 1.6352055235262863, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7156, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14184397163120568, | |
| "grad_norm": 0.9228519705928501, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7113, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16548463356973994, | |
| "grad_norm": 0.6109421695741598, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7015, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18912529550827423, | |
| "grad_norm": 1.1570191508750998, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6928, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 0.5479664575799189, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6881, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2364066193853428, | |
| "grad_norm": 0.6511091776660864, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6791, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26004728132387706, | |
| "grad_norm": 0.48965953407572976, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6875, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 0.5366385574454531, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6943, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3073286052009456, | |
| "grad_norm": 0.5940009124876445, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6732, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3309692671394799, | |
| "grad_norm": 0.5363561097267587, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6705, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3546099290780142, | |
| "grad_norm": 0.47312672873118417, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6736, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37825059101654845, | |
| "grad_norm": 0.5936177797142055, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6714, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.40189125295508277, | |
| "grad_norm": 0.559796603492257, | |
| "learning_rate": 5e-06, | |
| "loss": 0.677, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 0.6712065525809435, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6739, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4491725768321513, | |
| "grad_norm": 0.6276897126428631, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6712, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4728132387706856, | |
| "grad_norm": 0.5058454380091781, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6704, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.49645390070921985, | |
| "grad_norm": 0.4856083261066063, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6734, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5200945626477541, | |
| "grad_norm": 0.47853309599062016, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6679, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5437352245862884, | |
| "grad_norm": 0.5028725498074064, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6603, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 0.573425790046604, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6666, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5910165484633569, | |
| "grad_norm": 0.5450174649743487, | |
| "learning_rate": 5e-06, | |
| "loss": 0.663, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6146572104018913, | |
| "grad_norm": 0.6439202377303648, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6619, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 0.6134638277704878, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6537, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6619385342789598, | |
| "grad_norm": 0.5994186482549169, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6618, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6855791962174941, | |
| "grad_norm": 0.5012460436454785, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6608, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7092198581560284, | |
| "grad_norm": 0.5441826630708447, | |
| "learning_rate": 5e-06, | |
| "loss": 0.66, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7328605200945626, | |
| "grad_norm": 0.522329425801996, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6568, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7565011820330969, | |
| "grad_norm": 0.4758083660420685, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6554, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7801418439716312, | |
| "grad_norm": 0.49940764507627, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6566, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8037825059101655, | |
| "grad_norm": 0.6679446252287796, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6604, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8274231678486997, | |
| "grad_norm": 0.4668378880080796, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6542, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.6341578495542675, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6517, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8747044917257684, | |
| "grad_norm": 0.4656594360564299, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6535, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8983451536643026, | |
| "grad_norm": 0.44357749005248587, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6606, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9219858156028369, | |
| "grad_norm": 0.4530641632992077, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6507, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9456264775413712, | |
| "grad_norm": 0.5037838223896282, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6555, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9692671394799054, | |
| "grad_norm": 0.6623305884354875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6534, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9929078014184397, | |
| "grad_norm": 0.43978357483041475, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6503, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6491107940673828, | |
| "eval_runtime": 40.7764, | |
| "eval_samples_per_second": 279.304, | |
| "eval_steps_per_second": 1.104, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.016548463356974, | |
| "grad_norm": 0.6718862738139351, | |
| "learning_rate": 5e-06, | |
| "loss": 0.626, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0401891252955082, | |
| "grad_norm": 0.5240286124375526, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6033, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 0.5544933380864768, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6171, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0874704491725768, | |
| "grad_norm": 0.5500112360385622, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6138, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.6555691233512699, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6114, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1347517730496455, | |
| "grad_norm": 0.460930139599731, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6141, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1583924349881798, | |
| "grad_norm": 0.5188774400467296, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6158, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1820330969267139, | |
| "grad_norm": 0.4640360714483605, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6154, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2056737588652482, | |
| "grad_norm": 0.6093764843000187, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6093, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2293144208037825, | |
| "grad_norm": 0.6555953339288757, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6096, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2529550827423168, | |
| "grad_norm": 0.5237254449671765, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6133, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 0.6077697942607891, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6087, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.3002364066193852, | |
| "grad_norm": 0.4959290366758788, | |
| "learning_rate": 5e-06, | |
| "loss": 0.603, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3238770685579198, | |
| "grad_norm": 0.5120427167213613, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6104, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.3475177304964538, | |
| "grad_norm": 0.467013186042987, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6095, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3711583924349882, | |
| "grad_norm": 0.49118088063072135, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6166, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3947990543735225, | |
| "grad_norm": 0.48826248333502054, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6055, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4184397163120568, | |
| "grad_norm": 0.5012542755180496, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6091, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.442080378250591, | |
| "grad_norm": 0.41199293127019976, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6111, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4657210401891252, | |
| "grad_norm": 0.5227856582567488, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6094, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4893617021276595, | |
| "grad_norm": 0.4396680922197246, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6053, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5130023640661938, | |
| "grad_norm": 0.4667905586119019, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6083, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5366430260047281, | |
| "grad_norm": 0.4909469537010317, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6047, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5602836879432624, | |
| "grad_norm": 0.44596683795863395, | |
| "learning_rate": 5e-06, | |
| "loss": 0.612, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5839243498817965, | |
| "grad_norm": 0.5717586109502525, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6095, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.607565011820331, | |
| "grad_norm": 0.4490571190501361, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6085, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6312056737588652, | |
| "grad_norm": 0.5286431637266866, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6074, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.6548463356973995, | |
| "grad_norm": 0.5173624908943171, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6038, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6784869976359338, | |
| "grad_norm": 0.43453587339422367, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6128, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.702127659574468, | |
| "grad_norm": 0.4902717681255394, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6036, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7257683215130024, | |
| "grad_norm": 0.4350343628276203, | |
| "learning_rate": 5e-06, | |
| "loss": 0.605, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7494089834515365, | |
| "grad_norm": 0.528540441581878, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6095, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.773049645390071, | |
| "grad_norm": 0.600684912479072, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6106, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7966903073286051, | |
| "grad_norm": 0.5051323358574029, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6091, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.8203309692671394, | |
| "grad_norm": 0.47055245921215216, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6052, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.8439716312056738, | |
| "grad_norm": 0.40634667845025374, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6077, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.867612293144208, | |
| "grad_norm": 0.42084763446520207, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6101, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8912529550827424, | |
| "grad_norm": 0.4874640354448252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6064, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9148936170212765, | |
| "grad_norm": 0.4503284940019477, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6057, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.938534278959811, | |
| "grad_norm": 0.5426691149205667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6066, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.962174940898345, | |
| "grad_norm": 0.44537977097090253, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6082, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9858156028368794, | |
| "grad_norm": 0.47774839135537583, | |
| "learning_rate": 5e-06, | |
| "loss": 0.602, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6393836736679077, | |
| "eval_runtime": 41.0339, | |
| "eval_samples_per_second": 277.551, | |
| "eval_steps_per_second": 1.097, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 2.0094562647754137, | |
| "grad_norm": 0.6118720101139726, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5868, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.033096926713948, | |
| "grad_norm": 0.5572904299838869, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5582, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.0567375886524824, | |
| "grad_norm": 0.5303184511401988, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5637, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.0803782505910164, | |
| "grad_norm": 0.46454295303538246, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5592, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.104018912529551, | |
| "grad_norm": 0.6361956702505728, | |
| "learning_rate": 5e-06, | |
| "loss": 0.562, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": 0.7820428278668116, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5611, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.1513002364066196, | |
| "grad_norm": 0.45298061775995824, | |
| "learning_rate": 5e-06, | |
| "loss": 0.562, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.1749408983451537, | |
| "grad_norm": 0.5810391810087593, | |
| "learning_rate": 5e-06, | |
| "loss": 0.566, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.198581560283688, | |
| "grad_norm": 0.4908474714534316, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5634, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.46389513213427735, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5634, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.2458628841607564, | |
| "grad_norm": 0.6367614359838906, | |
| "learning_rate": 5e-06, | |
| "loss": 0.566, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.269503546099291, | |
| "grad_norm": 0.6141281239807579, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5674, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.293144208037825, | |
| "grad_norm": 0.542025677626535, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5651, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.3167848699763596, | |
| "grad_norm": 0.551857948487274, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5661, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.3404255319148937, | |
| "grad_norm": 0.5734053167546258, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5656, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.3640661938534278, | |
| "grad_norm": 0.5234453524143412, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5741, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3877068557919623, | |
| "grad_norm": 0.45374696937088277, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5671, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.4113475177304964, | |
| "grad_norm": 0.4880786886377219, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5721, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.434988179669031, | |
| "grad_norm": 0.5028949189688434, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5667, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.458628841607565, | |
| "grad_norm": 0.49048839220420004, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5643, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.482269503546099, | |
| "grad_norm": 0.5197651600869932, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5692, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.5059101654846336, | |
| "grad_norm": 0.4874044145512749, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5667, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5295508274231677, | |
| "grad_norm": 0.4664634995358468, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5671, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": 0.48656363327654745, | |
| "learning_rate": 5e-06, | |
| "loss": 0.574, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.5768321513002364, | |
| "grad_norm": 0.5305320232208198, | |
| "learning_rate": 5e-06, | |
| "loss": 0.572, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.6004728132387704, | |
| "grad_norm": 0.4910484019313719, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5732, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.624113475177305, | |
| "grad_norm": 0.5239661409291978, | |
| "learning_rate": 5e-06, | |
| "loss": 0.571, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.6477541371158395, | |
| "grad_norm": 0.46223769122758984, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5734, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.6713947990543736, | |
| "grad_norm": 0.5142173641545875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5694, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.6950354609929077, | |
| "grad_norm": 0.5294027287882332, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5646, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.7186761229314422, | |
| "grad_norm": 0.5331405829578174, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5723, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.7423167848699763, | |
| "grad_norm": 0.44857073429789307, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5683, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.7659574468085104, | |
| "grad_norm": 0.474611592323436, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5786, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.789598108747045, | |
| "grad_norm": 0.4950458376766123, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5741, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.813238770685579, | |
| "grad_norm": 0.5359701758991028, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5728, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.8368794326241136, | |
| "grad_norm": 0.43477013271067744, | |
| "learning_rate": 5e-06, | |
| "loss": 0.569, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.8605200945626477, | |
| "grad_norm": 0.46358204115129703, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5694, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.884160756501182, | |
| "grad_norm": 0.4374097557825778, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5689, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.9078014184397163, | |
| "grad_norm": 0.5145958315798522, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5738, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.9314420803782504, | |
| "grad_norm": 0.5316891926922875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5748, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.955082742316785, | |
| "grad_norm": 0.4296286799595667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5663, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.978723404255319, | |
| "grad_norm": 0.5500793615243753, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5681, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6408979892730713, | |
| "eval_runtime": 40.071, | |
| "eval_samples_per_second": 284.22, | |
| "eval_steps_per_second": 1.123, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1269, | |
| "total_flos": 2125622264463360.0, | |
| "train_loss": 0.6192652515955475, | |
| "train_runtime": 7838.8261, | |
| "train_samples_per_second": 82.815, | |
| "train_steps_per_second": 0.162 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1269, | |
| "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": 2125622264463360.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |