| { |
| "best_metric": 0.9180880188941956, |
| "best_model_checkpoint": "./fine_tuned_models/kvkk/Llama-3.1-8B-Instruct/checkpoint-2600", |
| "epoch": 2.5669135802469136, |
| "eval_steps": 100, |
| "global_step": 2600, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.019753086419753086, |
| "grad_norm": 1.1142268180847168, |
| "learning_rate": 1.9736842105263157e-06, |
| "loss": 2.0286, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03950617283950617, |
| "grad_norm": 1.1114156246185303, |
| "learning_rate": 3.9473684210526315e-06, |
| "loss": 2.012, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05925925925925926, |
| "grad_norm": 1.0126515626907349, |
| "learning_rate": 5.921052631578948e-06, |
| "loss": 1.8797, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 1.0541017055511475, |
| "learning_rate": 7.894736842105263e-06, |
| "loss": 1.5698, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.09876543209876543, |
| "grad_norm": 0.8761700391769409, |
| "learning_rate": 9.868421052631579e-06, |
| "loss": 1.2906, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09876543209876543, |
| "eval_loss": 1.1851595640182495, |
| "eval_runtime": 402.5327, |
| "eval_samples_per_second": 4.472, |
| "eval_steps_per_second": 1.118, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.7023137211799622, |
| "learning_rate": 1.1842105263157895e-05, |
| "loss": 1.1435, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.1382716049382716, |
| "grad_norm": 0.7056591510772705, |
| "learning_rate": 1.3815789473684211e-05, |
| "loss": 1.1222, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.6742960810661316, |
| "learning_rate": 1.5789473684210526e-05, |
| "loss": 1.1008, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.17777777777777778, |
| "grad_norm": 0.6822540760040283, |
| "learning_rate": 1.7763157894736842e-05, |
| "loss": 1.0732, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.7084145545959473, |
| "learning_rate": 1.9736842105263158e-05, |
| "loss": 1.0525, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "eval_loss": 1.0499310493469238, |
| "eval_runtime": 402.5074, |
| "eval_samples_per_second": 4.472, |
| "eval_steps_per_second": 1.118, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21728395061728395, |
| "grad_norm": 0.8174996972084045, |
| "learning_rate": 2.1710526315789474e-05, |
| "loss": 1.0711, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 0.8514217138290405, |
| "learning_rate": 2.368421052631579e-05, |
| "loss": 1.0147, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.25679012345679014, |
| "grad_norm": 0.8636080622673035, |
| "learning_rate": 2.5657894736842107e-05, |
| "loss": 1.032, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.8430706262588501, |
| "learning_rate": 2.7631578947368423e-05, |
| "loss": 1.0326, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "grad_norm": 0.9532914757728577, |
| "learning_rate": 2.9605263157894735e-05, |
| "loss": 1.0488, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "eval_loss": 1.0270123481750488, |
| "eval_runtime": 402.3395, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.118, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.9832524061203003, |
| "learning_rate": 2.9997461206762896e-05, |
| "loss": 1.0209, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.3358024691358025, |
| "grad_norm": 0.9382938146591187, |
| "learning_rate": 2.998714883211034e-05, |
| "loss": 1.0287, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.03255295753479, |
| "learning_rate": 2.9968909651554313e-05, |
| "loss": 1.0195, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.37530864197530867, |
| "grad_norm": 1.0193625688552856, |
| "learning_rate": 2.994275331192262e-05, |
| "loss": 1.0104, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.9543349146842957, |
| "learning_rate": 2.9908693647482852e-05, |
| "loss": 1.0032, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 1.0094538927078247, |
| "eval_runtime": 402.3092, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.119, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.4148148148148148, |
| "grad_norm": 1.0028969049453735, |
| "learning_rate": 2.9866748672625354e-05, |
| "loss": 1.0, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.1169507503509521, |
| "learning_rate": 2.9816940572335275e-05, |
| "loss": 1.0028, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.454320987654321, |
| "grad_norm": 1.0066871643066406, |
| "learning_rate": 2.9759295690458793e-05, |
| "loss": 0.9991, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 1.1250879764556885, |
| "learning_rate": 2.9693844515769658e-05, |
| "loss": 1.0275, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.49382716049382713, |
| "grad_norm": 0.9638034701347351, |
| "learning_rate": 2.9620621665843482e-05, |
| "loss": 1.0097, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.49382716049382713, |
| "eval_loss": 0.9942829012870789, |
| "eval_runtime": 402.3967, |
| "eval_samples_per_second": 4.473, |
| "eval_steps_per_second": 1.118, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 1.106367826461792, |
| "learning_rate": 2.953966586874827e-05, |
| "loss": 1.0219, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 1.0724130868911743, |
| "learning_rate": 2.9451019942560854e-05, |
| "loss": 0.9827, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 1.0933202505111694, |
| "learning_rate": 2.9354730772720152e-05, |
| "loss": 1.0033, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.5728395061728395, |
| "grad_norm": 1.089522123336792, |
| "learning_rate": 2.9250849287229115e-05, |
| "loss": 0.9558, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 1.0908564329147339, |
| "learning_rate": 2.9139430429718557e-05, |
| "loss": 0.9702, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "eval_loss": 0.9849551916122437, |
| "eval_runtime": 402.4211, |
| "eval_samples_per_second": 4.473, |
| "eval_steps_per_second": 1.118, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.6123456790123457, |
| "grad_norm": 1.0643543004989624, |
| "learning_rate": 2.90205331303871e-05, |
| "loss": 0.9678, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 1.1446090936660767, |
| "learning_rate": 2.889422027483259e-05, |
| "loss": 0.9617, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.6518518518518519, |
| "grad_norm": 1.2303221225738525, |
| "learning_rate": 2.876055867079146e-05, |
| "loss": 0.9939, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 1.1191219091415405, |
| "learning_rate": 2.8619619012803674e-05, |
| "loss": 0.986, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.691358024691358, |
| "grad_norm": 1.2467299699783325, |
| "learning_rate": 2.847147584482188e-05, |
| "loss": 0.9787, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.691358024691358, |
| "eval_loss": 0.9761277437210083, |
| "eval_runtime": 402.3652, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.118, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 1.1553202867507935, |
| "learning_rate": 2.8316207520784622e-05, |
| "loss": 0.9545, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.7308641975308642, |
| "grad_norm": 1.162398338317871, |
| "learning_rate": 2.81538961631744e-05, |
| "loss": 0.9876, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 1.1037890911102295, |
| "learning_rate": 2.7984627619582507e-05, |
| "loss": 0.9526, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.7703703703703704, |
| "grad_norm": 1.1114506721496582, |
| "learning_rate": 2.7808491417303672e-05, |
| "loss": 1.0013, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 1.140010118484497, |
| "learning_rate": 2.7625580715984452e-05, |
| "loss": 0.9754, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.9668111205101013, |
| "eval_runtime": 402.4946, |
| "eval_samples_per_second": 4.472, |
| "eval_steps_per_second": 1.118, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.8098765432098766, |
| "grad_norm": 1.1689811944961548, |
| "learning_rate": 2.7435992258350444e-05, |
| "loss": 0.979, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 1.045784592628479, |
| "learning_rate": 2.7239826319038413e-05, |
| "loss": 0.9723, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.8493827160493828, |
| "grad_norm": 1.1769437789916992, |
| "learning_rate": 2.703718665156033e-05, |
| "loss": 0.9709, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 1.0712182521820068, |
| "learning_rate": 2.6828180433427437e-05, |
| "loss": 0.964, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 1.4096373319625854, |
| "learning_rate": 2.6612918209463323e-05, |
| "loss": 0.9775, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "eval_loss": 0.963696300983429, |
| "eval_runtime": 402.3913, |
| "eval_samples_per_second": 4.473, |
| "eval_steps_per_second": 1.118, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 1.0928242206573486, |
| "learning_rate": 2.6391513833336013e-05, |
| "loss": 0.9557, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.928395061728395, |
| "grad_norm": 1.1433868408203125, |
| "learning_rate": 2.616408440733997e-05, |
| "loss": 0.9321, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 1.1303808689117432, |
| "learning_rate": 2.5930750220459893e-05, |
| "loss": 0.9873, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.9679012345679012, |
| "grad_norm": 1.2201975584030151, |
| "learning_rate": 2.569163468474906e-05, |
| "loss": 0.9635, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 1.1534947156906128, |
| "learning_rate": 2.5446864270055825e-05, |
| "loss": 0.9749, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "eval_loss": 0.9554852843284607, |
| "eval_runtime": 402.4957, |
| "eval_samples_per_second": 4.472, |
| "eval_steps_per_second": 1.118, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0069135802469136, |
| "grad_norm": 1.2161285877227783, |
| "learning_rate": 2.5196568437132855e-05, |
| "loss": 0.946, |
| "step": 1020 |
| }, |
| { |
| "epoch": 1.0266666666666666, |
| "grad_norm": 1.110687255859375, |
| "learning_rate": 2.4940879569164453e-05, |
| "loss": 0.9553, |
| "step": 1040 |
| }, |
| { |
| "epoch": 1.0464197530864197, |
| "grad_norm": 1.1861077547073364, |
| "learning_rate": 2.467993290174819e-05, |
| "loss": 0.9416, |
| "step": 1060 |
| }, |
| { |
| "epoch": 1.066172839506173, |
| "grad_norm": 1.2155508995056152, |
| "learning_rate": 2.4413866451367836e-05, |
| "loss": 0.9075, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.085925925925926, |
| "grad_norm": 1.3916659355163574, |
| "learning_rate": 2.414282094239555e-05, |
| "loss": 0.9344, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.085925925925926, |
| "eval_loss": 0.9527194499969482, |
| "eval_runtime": 402.3177, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.119, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.105679012345679, |
| "grad_norm": 1.2178341150283813, |
| "learning_rate": 2.386693973266173e-05, |
| "loss": 0.9271, |
| "step": 1120 |
| }, |
| { |
| "epoch": 1.125432098765432, |
| "grad_norm": 1.295937418937683, |
| "learning_rate": 2.3586368737632124e-05, |
| "loss": 0.9078, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.145185185185185, |
| "grad_norm": 1.3823224306106567, |
| "learning_rate": 2.3301256353232112e-05, |
| "loss": 0.9113, |
| "step": 1160 |
| }, |
| { |
| "epoch": 1.1649382716049383, |
| "grad_norm": 1.3728779554367065, |
| "learning_rate": 2.3011753377359084e-05, |
| "loss": 0.9135, |
| "step": 1180 |
| }, |
| { |
| "epoch": 1.1846913580246914, |
| "grad_norm": 1.2611992359161377, |
| "learning_rate": 2.2718012930124407e-05, |
| "loss": 0.9178, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.1846913580246914, |
| "eval_loss": 0.9479934573173523, |
| "eval_runtime": 402.3084, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.119, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.2044444444444444, |
| "grad_norm": 1.2411032915115356, |
| "learning_rate": 2.2420190372867144e-05, |
| "loss": 0.9159, |
| "step": 1220 |
| }, |
| { |
| "epoch": 1.2241975308641975, |
| "grad_norm": 1.3021560907363892, |
| "learning_rate": 2.2118443225982365e-05, |
| "loss": 0.8981, |
| "step": 1240 |
| }, |
| { |
| "epoch": 1.2439506172839505, |
| "grad_norm": 1.3610398769378662, |
| "learning_rate": 2.1812931085607537e-05, |
| "loss": 0.9121, |
| "step": 1260 |
| }, |
| { |
| "epoch": 1.2637037037037038, |
| "grad_norm": 1.310373067855835, |
| "learning_rate": 2.1503815539211034e-05, |
| "loss": 0.8987, |
| "step": 1280 |
| }, |
| { |
| "epoch": 1.2834567901234568, |
| "grad_norm": 1.2247895002365112, |
| "learning_rate": 2.119126008012741e-05, |
| "loss": 0.9115, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.2834567901234568, |
| "eval_loss": 0.9459941983222961, |
| "eval_runtime": 402.3726, |
| "eval_samples_per_second": 4.473, |
| "eval_steps_per_second": 1.118, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.3032098765432099, |
| "grad_norm": 1.2773354053497314, |
| "learning_rate": 2.0875430021084665e-05, |
| "loss": 0.924, |
| "step": 1320 |
| }, |
| { |
| "epoch": 1.322962962962963, |
| "grad_norm": 1.2930251359939575, |
| "learning_rate": 2.0556492406769176e-05, |
| "loss": 0.9201, |
| "step": 1340 |
| }, |
| { |
| "epoch": 1.342716049382716, |
| "grad_norm": 1.255893349647522, |
| "learning_rate": 2.0234615925474648e-05, |
| "loss": 0.9378, |
| "step": 1360 |
| }, |
| { |
| "epoch": 1.3624691358024692, |
| "grad_norm": 1.2988559007644653, |
| "learning_rate": 1.9909970819881708e-05, |
| "loss": 0.9004, |
| "step": 1380 |
| }, |
| { |
| "epoch": 1.3822222222222222, |
| "grad_norm": 1.328128457069397, |
| "learning_rate": 1.9582728797015385e-05, |
| "loss": 0.921, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.3822222222222222, |
| "eval_loss": 0.9410489797592163, |
| "eval_runtime": 402.2547, |
| "eval_samples_per_second": 4.475, |
| "eval_steps_per_second": 1.119, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.4019753086419753, |
| "grad_norm": 1.3988349437713623, |
| "learning_rate": 1.9253062937428073e-05, |
| "loss": 0.9056, |
| "step": 1420 |
| }, |
| { |
| "epoch": 1.4217283950617283, |
| "grad_norm": 1.256790041923523, |
| "learning_rate": 1.892114760365605e-05, |
| "loss": 0.9073, |
| "step": 1440 |
| }, |
| { |
| "epoch": 1.4414814814814814, |
| "grad_norm": 1.3246599435806274, |
| "learning_rate": 1.8587158347997932e-05, |
| "loss": 0.9097, |
| "step": 1460 |
| }, |
| { |
| "epoch": 1.4612345679012346, |
| "grad_norm": 1.2596899271011353, |
| "learning_rate": 1.8251271819663863e-05, |
| "loss": 0.9104, |
| "step": 1480 |
| }, |
| { |
| "epoch": 1.4809876543209877, |
| "grad_norm": 1.2959362268447876, |
| "learning_rate": 1.7913665671344526e-05, |
| "loss": 0.8994, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.4809876543209877, |
| "eval_loss": 0.9367458820343018, |
| "eval_runtime": 402.3021, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.119, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.5007407407407407, |
| "grad_norm": 1.2440412044525146, |
| "learning_rate": 1.7574518465249413e-05, |
| "loss": 0.9056, |
| "step": 1520 |
| }, |
| { |
| "epoch": 1.520493827160494, |
| "grad_norm": 1.441502571105957, |
| "learning_rate": 1.7234009578664066e-05, |
| "loss": 0.9264, |
| "step": 1540 |
| }, |
| { |
| "epoch": 1.5402469135802468, |
| "grad_norm": 1.3158551454544067, |
| "learning_rate": 1.6892319109076183e-05, |
| "loss": 0.8845, |
| "step": 1560 |
| }, |
| { |
| "epoch": 1.56, |
| "grad_norm": 1.5368109941482544, |
| "learning_rate": 1.654962777892081e-05, |
| "loss": 0.9141, |
| "step": 1580 |
| }, |
| { |
| "epoch": 1.579753086419753, |
| "grad_norm": 1.3186088800430298, |
| "learning_rate": 1.6206116839995033e-05, |
| "loss": 0.8878, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.579753086419753, |
| "eval_loss": 0.9328420758247375, |
| "eval_runtime": 402.4724, |
| "eval_samples_per_second": 4.472, |
| "eval_steps_per_second": 1.118, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.5995061728395061, |
| "grad_norm": 1.448764443397522, |
| "learning_rate": 1.5861967977592642e-05, |
| "loss": 0.8936, |
| "step": 1620 |
| }, |
| { |
| "epoch": 1.6192592592592594, |
| "grad_norm": 1.3021979331970215, |
| "learning_rate": 1.5517363214409528e-05, |
| "loss": 0.9185, |
| "step": 1640 |
| }, |
| { |
| "epoch": 1.6390123456790122, |
| "grad_norm": 1.3101555109024048, |
| "learning_rate": 1.5172484814270635e-05, |
| "loss": 0.9109, |
| "step": 1660 |
| }, |
| { |
| "epoch": 1.6587654320987655, |
| "grad_norm": 1.3461183309555054, |
| "learning_rate": 1.4827515185729368e-05, |
| "loss": 0.9045, |
| "step": 1680 |
| }, |
| { |
| "epoch": 1.6785185185185185, |
| "grad_norm": 1.3536429405212402, |
| "learning_rate": 1.4482636785590474e-05, |
| "loss": 0.8981, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.6785185185185185, |
| "eval_loss": 0.9300320148468018, |
| "eval_runtime": 402.5102, |
| "eval_samples_per_second": 4.472, |
| "eval_steps_per_second": 1.118, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.6982716049382716, |
| "grad_norm": 1.2944140434265137, |
| "learning_rate": 1.413803202240736e-05, |
| "loss": 0.9127, |
| "step": 1720 |
| }, |
| { |
| "epoch": 1.7180246913580248, |
| "grad_norm": 1.3316771984100342, |
| "learning_rate": 1.3793883160004971e-05, |
| "loss": 0.9157, |
| "step": 1740 |
| }, |
| { |
| "epoch": 1.7377777777777776, |
| "grad_norm": 1.403693675994873, |
| "learning_rate": 1.3450372221079193e-05, |
| "loss": 0.8998, |
| "step": 1760 |
| }, |
| { |
| "epoch": 1.757530864197531, |
| "grad_norm": 1.3952233791351318, |
| "learning_rate": 1.3107680890923821e-05, |
| "loss": 0.9139, |
| "step": 1780 |
| }, |
| { |
| "epoch": 1.777283950617284, |
| "grad_norm": 1.3515853881835938, |
| "learning_rate": 1.2765990421335937e-05, |
| "loss": 0.9178, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.777283950617284, |
| "eval_loss": 0.9266696572303772, |
| "eval_runtime": 402.3456, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.118, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.797037037037037, |
| "grad_norm": 1.3852437734603882, |
| "learning_rate": 1.2425481534750591e-05, |
| "loss": 0.9189, |
| "step": 1820 |
| }, |
| { |
| "epoch": 1.8167901234567903, |
| "grad_norm": 1.372295618057251, |
| "learning_rate": 1.2086334328655478e-05, |
| "loss": 0.8969, |
| "step": 1840 |
| }, |
| { |
| "epoch": 1.836543209876543, |
| "grad_norm": 1.6304378509521484, |
| "learning_rate": 1.1748728180336137e-05, |
| "loss": 0.903, |
| "step": 1860 |
| }, |
| { |
| "epoch": 1.8562962962962963, |
| "grad_norm": 1.3534801006317139, |
| "learning_rate": 1.141284165200207e-05, |
| "loss": 0.9219, |
| "step": 1880 |
| }, |
| { |
| "epoch": 1.8760493827160494, |
| "grad_norm": 1.4054875373840332, |
| "learning_rate": 1.1078852396343955e-05, |
| "loss": 0.9009, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.8760493827160494, |
| "eval_loss": 0.923714280128479, |
| "eval_runtime": 402.3854, |
| "eval_samples_per_second": 4.473, |
| "eval_steps_per_second": 1.118, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.8958024691358024, |
| "grad_norm": 1.385722279548645, |
| "learning_rate": 1.0746937062571928e-05, |
| "loss": 0.9103, |
| "step": 1920 |
| }, |
| { |
| "epoch": 1.9155555555555557, |
| "grad_norm": 1.3441500663757324, |
| "learning_rate": 1.0417271202984614e-05, |
| "loss": 0.9465, |
| "step": 1940 |
| }, |
| { |
| "epoch": 1.9353086419753085, |
| "grad_norm": 1.5040432214736938, |
| "learning_rate": 1.0090029180118293e-05, |
| "loss": 0.881, |
| "step": 1960 |
| }, |
| { |
| "epoch": 1.9550617283950618, |
| "grad_norm": 1.401288390159607, |
| "learning_rate": 9.765384074525358e-06, |
| "loss": 0.901, |
| "step": 1980 |
| }, |
| { |
| "epoch": 1.9748148148148148, |
| "grad_norm": 1.439374327659607, |
| "learning_rate": 9.443507593230829e-06, |
| "loss": 0.904, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.9748148148148148, |
| "eval_loss": 0.9219183921813965, |
| "eval_runtime": 402.3558, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.118, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.9945679012345678, |
| "grad_norm": 1.63518488407135, |
| "learning_rate": 9.124569978915336e-06, |
| "loss": 0.9222, |
| "step": 2020 |
| }, |
| { |
| "epoch": 2.013827160493827, |
| "grad_norm": 1.3853759765625, |
| "learning_rate": 8.808739919872588e-06, |
| "loss": 0.8659, |
| "step": 2040 |
| }, |
| { |
| "epoch": 2.0335802469135804, |
| "grad_norm": 1.3967058658599854, |
| "learning_rate": 8.496184460788969e-06, |
| "loss": 0.8865, |
| "step": 2060 |
| }, |
| { |
| "epoch": 2.0533333333333332, |
| "grad_norm": 1.3898597955703735, |
| "learning_rate": 8.187068914392464e-06, |
| "loss": 0.8473, |
| "step": 2080 |
| }, |
| { |
| "epoch": 2.0730864197530865, |
| "grad_norm": 1.4539365768432617, |
| "learning_rate": 7.881556774017635e-06, |
| "loss": 0.8638, |
| "step": 2100 |
| }, |
| { |
| "epoch": 2.0730864197530865, |
| "eval_loss": 0.9233973622322083, |
| "eval_runtime": 402.3351, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.118, |
| "step": 2100 |
| }, |
| { |
| "epoch": 2.0928395061728393, |
| "grad_norm": 1.4145288467407227, |
| "learning_rate": 7.579809627132857e-06, |
| "loss": 0.8393, |
| "step": 2120 |
| }, |
| { |
| "epoch": 2.1125925925925926, |
| "grad_norm": 1.436933994293213, |
| "learning_rate": 7.281987069875591e-06, |
| "loss": 0.8841, |
| "step": 2140 |
| }, |
| { |
| "epoch": 2.132345679012346, |
| "grad_norm": 1.4067989587783813, |
| "learning_rate": 6.988246622640921e-06, |
| "loss": 0.8516, |
| "step": 2160 |
| }, |
| { |
| "epoch": 2.1520987654320987, |
| "grad_norm": 1.5077627897262573, |
| "learning_rate": 6.698743646767891e-06, |
| "loss": 0.8749, |
| "step": 2180 |
| }, |
| { |
| "epoch": 2.171851851851852, |
| "grad_norm": 1.599204182624817, |
| "learning_rate": 6.413631262367882e-06, |
| "loss": 0.8678, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.171851851851852, |
| "eval_loss": 0.9224557876586914, |
| "eval_runtime": 402.3427, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.118, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.1916049382716047, |
| "grad_norm": 1.4863977432250977, |
| "learning_rate": 6.1330602673382725e-06, |
| "loss": 0.8517, |
| "step": 2220 |
| }, |
| { |
| "epoch": 2.211358024691358, |
| "grad_norm": 1.3517553806304932, |
| "learning_rate": 5.857179057604451e-06, |
| "loss": 0.8445, |
| "step": 2240 |
| }, |
| { |
| "epoch": 2.2311111111111113, |
| "grad_norm": 1.5938282012939453, |
| "learning_rate": 5.586133548632161e-06, |
| "loss": 0.8475, |
| "step": 2260 |
| }, |
| { |
| "epoch": 2.250864197530864, |
| "grad_norm": 1.5121272802352905, |
| "learning_rate": 5.320067098251815e-06, |
| "loss": 0.852, |
| "step": 2280 |
| }, |
| { |
| "epoch": 2.2706172839506173, |
| "grad_norm": 1.5417536497116089, |
| "learning_rate": 5.0591204308355465e-06, |
| "loss": 0.8463, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.2706172839506173, |
| "eval_loss": 0.9209318161010742, |
| "eval_runtime": 402.2865, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.119, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.29037037037037, |
| "grad_norm": 1.4710192680358887, |
| "learning_rate": 4.803431562867145e-06, |
| "loss": 0.8782, |
| "step": 2320 |
| }, |
| { |
| "epoch": 2.3101234567901234, |
| "grad_norm": 1.4649263620376587, |
| "learning_rate": 4.5531357299441774e-06, |
| "loss": 0.8881, |
| "step": 2340 |
| }, |
| { |
| "epoch": 2.3298765432098767, |
| "grad_norm": 1.5059787034988403, |
| "learning_rate": 4.3083653152509434e-06, |
| "loss": 0.859, |
| "step": 2360 |
| }, |
| { |
| "epoch": 2.3496296296296295, |
| "grad_norm": 1.481704831123352, |
| "learning_rate": 4.069249779540108e-06, |
| "loss": 0.8733, |
| "step": 2380 |
| }, |
| { |
| "epoch": 2.3693827160493828, |
| "grad_norm": 1.5068329572677612, |
| "learning_rate": 3.835915592660032e-06, |
| "loss": 0.832, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.3693827160493828, |
| "eval_loss": 0.9204065203666687, |
| "eval_runtime": 402.3595, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.118, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.389135802469136, |
| "grad_norm": 1.5572285652160645, |
| "learning_rate": 3.6084861666639856e-06, |
| "loss": 0.8649, |
| "step": 2420 |
| }, |
| { |
| "epoch": 2.408888888888889, |
| "grad_norm": 1.519260287284851, |
| "learning_rate": 3.387081790536677e-06, |
| "loss": 0.8452, |
| "step": 2440 |
| }, |
| { |
| "epoch": 2.428641975308642, |
| "grad_norm": 1.5407612323760986, |
| "learning_rate": 3.171819566572563e-06, |
| "loss": 0.8637, |
| "step": 2460 |
| }, |
| { |
| "epoch": 2.448395061728395, |
| "grad_norm": 1.5315485000610352, |
| "learning_rate": 2.962813348439669e-06, |
| "loss": 0.8348, |
| "step": 2480 |
| }, |
| { |
| "epoch": 2.468148148148148, |
| "grad_norm": 1.5446561574935913, |
| "learning_rate": 2.7601736809615883e-06, |
| "loss": 0.8572, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.468148148148148, |
| "eval_loss": 0.9187188148498535, |
| "eval_runtime": 402.5088, |
| "eval_samples_per_second": 4.472, |
| "eval_steps_per_second": 1.118, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.487901234567901, |
| "grad_norm": 1.7411221265792847, |
| "learning_rate": 2.564007741649559e-06, |
| "loss": 0.8592, |
| "step": 2520 |
| }, |
| { |
| "epoch": 2.5076543209876543, |
| "grad_norm": 1.5264136791229248, |
| "learning_rate": 2.374419284015552e-06, |
| "loss": 0.841, |
| "step": 2540 |
| }, |
| { |
| "epoch": 2.5274074074074075, |
| "grad_norm": 1.6637004613876343, |
| "learning_rate": 2.191508582696329e-06, |
| "loss": 0.8427, |
| "step": 2560 |
| }, |
| { |
| "epoch": 2.5471604938271604, |
| "grad_norm": 1.4840551614761353, |
| "learning_rate": 2.0153723804174945e-06, |
| "loss": 0.8604, |
| "step": 2580 |
| }, |
| { |
| "epoch": 2.5669135802469136, |
| "grad_norm": 1.530154824256897, |
| "learning_rate": 1.8461038368256027e-06, |
| "loss": 0.8788, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.5669135802469136, |
| "eval_loss": 0.9180880188941956, |
| "eval_runtime": 402.2861, |
| "eval_samples_per_second": 4.474, |
| "eval_steps_per_second": 1.119, |
| "step": 2600 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 3036, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.8563300999472087e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
