| { | |
| "best_metric": 2.8364877700805664, | |
| "best_model_checkpoint": "test-hasy-6/checkpoint-1082", | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 1082, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.711106538772583, | |
| "learning_rate": 1.9815157116451017e-05, | |
| "loss": 3.6832, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 3.2622244358062744, | |
| "learning_rate": 1.9630314232902035e-05, | |
| "loss": 3.6516, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 3.6894755363464355, | |
| "learning_rate": 1.944547134935305e-05, | |
| "loss": 3.6016, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 3.1826202869415283, | |
| "learning_rate": 1.9260628465804068e-05, | |
| "loss": 3.5555, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 3.9819042682647705, | |
| "learning_rate": 1.9075785582255083e-05, | |
| "loss": 3.4945, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 3.705105781555176, | |
| "learning_rate": 1.88909426987061e-05, | |
| "loss": 3.5038, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 3.76656174659729, | |
| "learning_rate": 1.8706099815157116e-05, | |
| "loss": 3.472, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 3.7350897789001465, | |
| "learning_rate": 1.8521256931608135e-05, | |
| "loss": 3.6583, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 3.705801486968994, | |
| "learning_rate": 1.833641404805915e-05, | |
| "loss": 3.7701, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 4.12357759475708, | |
| "learning_rate": 1.8151571164510168e-05, | |
| "loss": 3.606, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 3.3650107383728027, | |
| "learning_rate": 1.7966728280961186e-05, | |
| "loss": 3.5468, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 3.4115757942199707, | |
| "learning_rate": 1.77818853974122e-05, | |
| "loss": 3.7078, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 3.238929271697998, | |
| "learning_rate": 1.759704251386322e-05, | |
| "loss": 3.497, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 4.156219005584717, | |
| "learning_rate": 1.7412199630314234e-05, | |
| "loss": 3.4416, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 2.9438037872314453, | |
| "learning_rate": 1.7227356746765253e-05, | |
| "loss": 3.4672, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 4.352924346923828, | |
| "learning_rate": 1.7042513863216268e-05, | |
| "loss": 3.6725, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 3.657327890396118, | |
| "learning_rate": 1.6857670979667286e-05, | |
| "loss": 3.734, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 3.249286651611328, | |
| "learning_rate": 1.66728280961183e-05, | |
| "loss": 3.5018, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 3.500436305999756, | |
| "learning_rate": 1.6487985212569316e-05, | |
| "loss": 3.4335, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 3.593245029449463, | |
| "learning_rate": 1.6303142329020334e-05, | |
| "loss": 3.4789, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 5.4212646484375, | |
| "learning_rate": 1.611829944547135e-05, | |
| "loss": 3.679, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 4.081950664520264, | |
| "learning_rate": 1.5933456561922367e-05, | |
| "loss": 3.3923, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 3.5438432693481445, | |
| "learning_rate": 1.5748613678373382e-05, | |
| "loss": 3.6173, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 3.3405466079711914, | |
| "learning_rate": 1.55637707948244e-05, | |
| "loss": 3.4723, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 4.1731061935424805, | |
| "learning_rate": 1.5378927911275416e-05, | |
| "loss": 3.4844, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 3.103394031524658, | |
| "learning_rate": 1.5194085027726432e-05, | |
| "loss": 3.3946, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 3.5173914432525635, | |
| "learning_rate": 1.5009242144177449e-05, | |
| "loss": 3.5343, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 4.252523899078369, | |
| "learning_rate": 1.4824399260628467e-05, | |
| "loss": 3.4245, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 4.194942474365234, | |
| "learning_rate": 1.4639556377079484e-05, | |
| "loss": 3.457, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 3.6533360481262207, | |
| "learning_rate": 1.44547134935305e-05, | |
| "loss": 3.3204, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 3.9382996559143066, | |
| "learning_rate": 1.4269870609981517e-05, | |
| "loss": 3.3361, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 4.06477165222168, | |
| "learning_rate": 1.4085027726432534e-05, | |
| "loss": 3.3031, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 4.143244743347168, | |
| "learning_rate": 1.390018484288355e-05, | |
| "loss": 3.207, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 4.467826843261719, | |
| "learning_rate": 1.3715341959334567e-05, | |
| "loss": 3.3971, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 3.793196678161621, | |
| "learning_rate": 1.3530499075785584e-05, | |
| "loss": 3.3889, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 3.1169040203094482, | |
| "learning_rate": 1.33456561922366e-05, | |
| "loss": 3.3227, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 4.126261234283447, | |
| "learning_rate": 1.3160813308687617e-05, | |
| "loss": 3.4843, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 4.5660223960876465, | |
| "learning_rate": 1.2975970425138634e-05, | |
| "loss": 3.3331, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 4.103394985198975, | |
| "learning_rate": 1.279112754158965e-05, | |
| "loss": 3.4159, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 4.094814300537109, | |
| "learning_rate": 1.2606284658040667e-05, | |
| "loss": 3.2274, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 4.130598068237305, | |
| "learning_rate": 1.2421441774491683e-05, | |
| "loss": 3.2463, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 3.7482187747955322, | |
| "learning_rate": 1.2236598890942698e-05, | |
| "loss": 3.2457, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 3.43017840385437, | |
| "learning_rate": 1.2051756007393715e-05, | |
| "loss": 3.5525, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 3.194152355194092, | |
| "learning_rate": 1.1866913123844732e-05, | |
| "loss": 3.5108, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 3.5279622077941895, | |
| "learning_rate": 1.1682070240295748e-05, | |
| "loss": 3.3414, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 3.6658153533935547, | |
| "learning_rate": 1.1497227356746765e-05, | |
| "loss": 3.4046, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 3.5500826835632324, | |
| "learning_rate": 1.1312384473197783e-05, | |
| "loss": 3.0882, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 5.9582953453063965, | |
| "learning_rate": 1.11275415896488e-05, | |
| "loss": 3.192, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 5.833331108093262, | |
| "learning_rate": 1.0942698706099817e-05, | |
| "loss": 3.5321, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 3.8356950283050537, | |
| "learning_rate": 1.0757855822550833e-05, | |
| "loss": 3.6224, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 4.684799671173096, | |
| "learning_rate": 1.057301293900185e-05, | |
| "loss": 3.3353, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 3.551720142364502, | |
| "learning_rate": 1.0388170055452866e-05, | |
| "loss": 3.495, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 3.6974239349365234, | |
| "learning_rate": 1.0203327171903883e-05, | |
| "loss": 3.3445, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.8344950675964355, | |
| "learning_rate": 1.00184842883549e-05, | |
| "loss": 3.5095, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.46361746361746364, | |
| "eval_loss": 2.99053692817688, | |
| "eval_runtime": 1.5396, | |
| "eval_samples_per_second": 312.424, | |
| "eval_steps_per_second": 39.621, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 4.154804706573486, | |
| "learning_rate": 9.833641404805916e-06, | |
| "loss": 3.3211, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 3.6485326290130615, | |
| "learning_rate": 9.648798521256933e-06, | |
| "loss": 3.2122, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 4.6978912353515625, | |
| "learning_rate": 9.46395563770795e-06, | |
| "loss": 3.3578, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 3.3605403900146484, | |
| "learning_rate": 9.279112754158966e-06, | |
| "loss": 3.2178, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 4.516849517822266, | |
| "learning_rate": 9.094269870609981e-06, | |
| "loss": 3.3387, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 3.1765856742858887, | |
| "learning_rate": 8.909426987060998e-06, | |
| "loss": 3.3164, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 3.9158923625946045, | |
| "learning_rate": 8.724584103512016e-06, | |
| "loss": 3.2342, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 3.418714761734009, | |
| "learning_rate": 8.539741219963033e-06, | |
| "loss": 3.3066, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 4.705308437347412, | |
| "learning_rate": 8.35489833641405e-06, | |
| "loss": 3.0839, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 3.6252079010009766, | |
| "learning_rate": 8.170055452865066e-06, | |
| "loss": 3.0772, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 3.9924700260162354, | |
| "learning_rate": 7.985212569316083e-06, | |
| "loss": 3.2432, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 4.91044282913208, | |
| "learning_rate": 7.8003696857671e-06, | |
| "loss": 3.2282, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 4.189777374267578, | |
| "learning_rate": 7.615526802218115e-06, | |
| "loss": 3.1491, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 6.070817947387695, | |
| "learning_rate": 7.430683918669132e-06, | |
| "loss": 2.9568, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 3.7259085178375244, | |
| "learning_rate": 7.245841035120148e-06, | |
| "loss": 3.3533, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 5.180878639221191, | |
| "learning_rate": 7.060998151571166e-06, | |
| "loss": 3.2111, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 3.779390811920166, | |
| "learning_rate": 6.876155268022182e-06, | |
| "loss": 3.1691, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 3.938795566558838, | |
| "learning_rate": 6.691312384473199e-06, | |
| "loss": 3.0765, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 4.160928726196289, | |
| "learning_rate": 6.506469500924215e-06, | |
| "loss": 3.2189, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 4.43211555480957, | |
| "learning_rate": 6.321626617375231e-06, | |
| "loss": 3.4135, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 4.024065971374512, | |
| "learning_rate": 6.136783733826248e-06, | |
| "loss": 3.0384, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 4.307715892791748, | |
| "learning_rate": 5.951940850277265e-06, | |
| "loss": 3.429, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 3.6535394191741943, | |
| "learning_rate": 5.767097966728281e-06, | |
| "loss": 3.4501, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 3.8214519023895264, | |
| "learning_rate": 5.582255083179298e-06, | |
| "loss": 3.2541, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 4.626838684082031, | |
| "learning_rate": 5.3974121996303146e-06, | |
| "loss": 3.2509, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 5.32305383682251, | |
| "learning_rate": 5.212569316081332e-06, | |
| "loss": 3.1942, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 6.955519199371338, | |
| "learning_rate": 5.027726432532349e-06, | |
| "loss": 3.0025, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 5.317496299743652, | |
| "learning_rate": 4.8428835489833645e-06, | |
| "loss": 3.02, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 3.5093274116516113, | |
| "learning_rate": 4.658040665434381e-06, | |
| "loss": 3.2135, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 5.330411434173584, | |
| "learning_rate": 4.473197781885398e-06, | |
| "loss": 3.1959, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 6.167944431304932, | |
| "learning_rate": 4.288354898336414e-06, | |
| "loss": 3.2624, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 5.011616230010986, | |
| "learning_rate": 4.103512014787431e-06, | |
| "loss": 3.1496, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 4.2308549880981445, | |
| "learning_rate": 3.918669131238448e-06, | |
| "loss": 3.2032, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 4.570101261138916, | |
| "learning_rate": 3.7338262476894642e-06, | |
| "loss": 3.1373, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 5.977038860321045, | |
| "learning_rate": 3.548983364140481e-06, | |
| "loss": 3.2066, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 3.6211962699890137, | |
| "learning_rate": 3.3641404805914975e-06, | |
| "loss": 3.229, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 4.511559963226318, | |
| "learning_rate": 3.1792975970425146e-06, | |
| "loss": 3.2265, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 4.407166004180908, | |
| "learning_rate": 2.9944547134935308e-06, | |
| "loss": 3.1788, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 3.707716941833496, | |
| "learning_rate": 2.8096118299445474e-06, | |
| "loss": 3.0538, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 3.5526440143585205, | |
| "learning_rate": 2.624768946395564e-06, | |
| "loss": 3.232, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 4.847479820251465, | |
| "learning_rate": 2.4399260628465807e-06, | |
| "loss": 3.1423, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 5.645847797393799, | |
| "learning_rate": 2.2550831792975973e-06, | |
| "loss": 3.015, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 4.522593021392822, | |
| "learning_rate": 2.070240295748614e-06, | |
| "loss": 3.2805, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 4.721327304840088, | |
| "learning_rate": 1.8853974121996305e-06, | |
| "loss": 3.324, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 3.5393543243408203, | |
| "learning_rate": 1.700554528650647e-06, | |
| "loss": 3.0815, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 5.153535842895508, | |
| "learning_rate": 1.5157116451016638e-06, | |
| "loss": 3.0635, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 4.251449108123779, | |
| "learning_rate": 1.3308687615526802e-06, | |
| "loss": 2.9802, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 3.994425058364868, | |
| "learning_rate": 1.1460258780036969e-06, | |
| "loss": 3.5064, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 4.248856544494629, | |
| "learning_rate": 9.611829944547135e-07, | |
| "loss": 2.9155, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 5.162292957305908, | |
| "learning_rate": 7.763401109057302e-07, | |
| "loss": 3.2488, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 4.9712443351745605, | |
| "learning_rate": 5.914972273567468e-07, | |
| "loss": 3.3756, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 4.459498405456543, | |
| "learning_rate": 4.066543438077634e-07, | |
| "loss": 3.1618, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 4.354925155639648, | |
| "learning_rate": 2.2181146025878005e-07, | |
| "loss": 3.1594, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 6.441626071929932, | |
| "learning_rate": 3.696857670979668e-08, | |
| "loss": 2.8453, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4968814968814969, | |
| "eval_loss": 2.8364877700805664, | |
| "eval_runtime": 1.6024, | |
| "eval_samples_per_second": 300.173, | |
| "eval_steps_per_second": 38.068, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 1082, | |
| "total_flos": 6.710386542096384e+17, | |
| "train_loss": 3.3293299987884635, | |
| "train_runtime": 76.1938, | |
| "train_samples_per_second": 113.526, | |
| "train_steps_per_second": 14.201 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4968814968814969, | |
| "eval_loss": 2.8364877700805664, | |
| "eval_runtime": 1.534, | |
| "eval_samples_per_second": 313.565, | |
| "eval_steps_per_second": 39.766, | |
| "step": 1082 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1082, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 6.710386542096384e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |