| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09009009009009009, | |
| "grad_norm": 16.28987693786621, | |
| "learning_rate": 9.90990990990991e-05, | |
| "loss": 0.4883, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18018018018018017, | |
| "grad_norm": 3.943525552749634, | |
| "learning_rate": 9.81981981981982e-05, | |
| "loss": 0.0823, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 7.749650955200195, | |
| "learning_rate": 9.729729729729731e-05, | |
| "loss": 0.0279, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.36036036036036034, | |
| "grad_norm": 1.5577881336212158, | |
| "learning_rate": 9.639639639639641e-05, | |
| "loss": 0.0247, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.45045045045045046, | |
| "grad_norm": 1.7881258726119995, | |
| "learning_rate": 9.54954954954955e-05, | |
| "loss": 0.0162, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 1.0929126739501953, | |
| "learning_rate": 9.45945945945946e-05, | |
| "loss": 0.0127, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6306306306306306, | |
| "grad_norm": 2.1130833625793457, | |
| "learning_rate": 9.36936936936937e-05, | |
| "loss": 0.0069, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "grad_norm": 3.6001977920532227, | |
| "learning_rate": 9.279279279279279e-05, | |
| "loss": 0.0094, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8108108108108109, | |
| "grad_norm": 0.6843027472496033, | |
| "learning_rate": 9.18918918918919e-05, | |
| "loss": 0.0069, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9009009009009009, | |
| "grad_norm": 2.2954471111297607, | |
| "learning_rate": 9.0990990990991e-05, | |
| "loss": 0.0069, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.990990990990991, | |
| "grad_norm": 0.22960656881332397, | |
| "learning_rate": 9.009009009009009e-05, | |
| "loss": 0.0094, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.016822505742311478, | |
| "eval_mse": 0.016822507604956627, | |
| "eval_runtime": 26.347, | |
| "eval_samples_per_second": 8.426, | |
| "eval_steps_per_second": 1.063, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.10217050462961197, | |
| "learning_rate": 8.918918918918919e-05, | |
| "loss": 0.0042, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1711711711711712, | |
| "grad_norm": 5.079370498657227, | |
| "learning_rate": 8.82882882882883e-05, | |
| "loss": 0.0094, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2612612612612613, | |
| "grad_norm": 2.9237141609191895, | |
| "learning_rate": 8.738738738738738e-05, | |
| "loss": 0.0099, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3513513513513513, | |
| "grad_norm": 3.25941801071167, | |
| "learning_rate": 8.64864864864865e-05, | |
| "loss": 0.016, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4414414414414414, | |
| "grad_norm": 0.9882258772850037, | |
| "learning_rate": 8.55855855855856e-05, | |
| "loss": 0.0061, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.5315315315315314, | |
| "grad_norm": 4.510200023651123, | |
| "learning_rate": 8.468468468468469e-05, | |
| "loss": 0.0143, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6216216216216215, | |
| "grad_norm": 0.35400834679603577, | |
| "learning_rate": 8.378378378378379e-05, | |
| "loss": 0.0148, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7117117117117115, | |
| "grad_norm": 3.6332740783691406, | |
| "learning_rate": 8.288288288288289e-05, | |
| "loss": 0.0113, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.8018018018018018, | |
| "grad_norm": 1.811373233795166, | |
| "learning_rate": 8.198198198198198e-05, | |
| "loss": 0.017, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8918918918918919, | |
| "grad_norm": 2.500202178955078, | |
| "learning_rate": 8.108108108108109e-05, | |
| "loss": 0.0062, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.981981981981982, | |
| "grad_norm": 4.341911792755127, | |
| "learning_rate": 8.018018018018019e-05, | |
| "loss": 0.0142, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.008252176456153393, | |
| "eval_mse": 0.008252176456153393, | |
| "eval_runtime": 25.8199, | |
| "eval_samples_per_second": 8.598, | |
| "eval_steps_per_second": 1.084, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.0720720720720722, | |
| "grad_norm": 0.4223078489303589, | |
| "learning_rate": 7.927927927927928e-05, | |
| "loss": 0.01, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "grad_norm": 3.0677056312561035, | |
| "learning_rate": 7.837837837837838e-05, | |
| "loss": 0.0139, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.2522522522522523, | |
| "grad_norm": 0.3952648639678955, | |
| "learning_rate": 7.747747747747748e-05, | |
| "loss": 0.0063, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.3423423423423424, | |
| "grad_norm": 3.6467502117156982, | |
| "learning_rate": 7.657657657657657e-05, | |
| "loss": 0.0122, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.4324324324324325, | |
| "grad_norm": 4.3216352462768555, | |
| "learning_rate": 7.567567567567568e-05, | |
| "loss": 0.0106, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.5225225225225225, | |
| "grad_norm": 3.8619132041931152, | |
| "learning_rate": 7.477477477477479e-05, | |
| "loss": 0.0106, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.6126126126126126, | |
| "grad_norm": 1.1223838329315186, | |
| "learning_rate": 7.387387387387387e-05, | |
| "loss": 0.0086, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.7027027027027026, | |
| "grad_norm": 0.8446173667907715, | |
| "learning_rate": 7.297297297297297e-05, | |
| "loss": 0.0202, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.7927927927927927, | |
| "grad_norm": 0.9771293997764587, | |
| "learning_rate": 7.207207207207208e-05, | |
| "loss": 0.0071, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.8828828828828827, | |
| "grad_norm": 2.6441454887390137, | |
| "learning_rate": 7.117117117117116e-05, | |
| "loss": 0.0093, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.972972972972973, | |
| "grad_norm": 3.6695780754089355, | |
| "learning_rate": 7.027027027027028e-05, | |
| "loss": 0.0067, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.012067927978932858, | |
| "eval_mse": 0.012067928910255432, | |
| "eval_runtime": 26.2024, | |
| "eval_samples_per_second": 8.473, | |
| "eval_steps_per_second": 1.069, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 3.063063063063063, | |
| "grad_norm": 1.334926962852478, | |
| "learning_rate": 6.936936936936938e-05, | |
| "loss": 0.0129, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.153153153153153, | |
| "grad_norm": 3.8143014907836914, | |
| "learning_rate": 6.846846846846847e-05, | |
| "loss": 0.0084, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.2432432432432434, | |
| "grad_norm": 0.529600977897644, | |
| "learning_rate": 6.756756756756757e-05, | |
| "loss": 0.0059, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 6.050387382507324, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0184, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.4234234234234235, | |
| "grad_norm": 0.3079633414745331, | |
| "learning_rate": 6.576576576576577e-05, | |
| "loss": 0.0072, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.5135135135135136, | |
| "grad_norm": 2.165722608566284, | |
| "learning_rate": 6.486486486486487e-05, | |
| "loss": 0.0086, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.6036036036036037, | |
| "grad_norm": 1.4053255319595337, | |
| "learning_rate": 6.396396396396397e-05, | |
| "loss": 0.0063, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.6936936936936937, | |
| "grad_norm": 1.4147133827209473, | |
| "learning_rate": 6.306306306306306e-05, | |
| "loss": 0.0049, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.7837837837837838, | |
| "grad_norm": 0.1397821009159088, | |
| "learning_rate": 6.216216216216216e-05, | |
| "loss": 0.0143, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.873873873873874, | |
| "grad_norm": 2.773983955383301, | |
| "learning_rate": 6.126126126126126e-05, | |
| "loss": 0.0052, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.963963963963964, | |
| "grad_norm": 2.0396511554718018, | |
| "learning_rate": 6.0360360360360365e-05, | |
| "loss": 0.0051, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.00851067528128624, | |
| "eval_mse": 0.00851067528128624, | |
| "eval_runtime": 26.1258, | |
| "eval_samples_per_second": 8.497, | |
| "eval_steps_per_second": 1.072, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 4.054054054054054, | |
| "grad_norm": 1.728843092918396, | |
| "learning_rate": 5.9459459459459466e-05, | |
| "loss": 0.0071, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.1441441441441444, | |
| "grad_norm": 2.8978583812713623, | |
| "learning_rate": 5.855855855855856e-05, | |
| "loss": 0.0072, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.2342342342342345, | |
| "grad_norm": 0.1254826933145523, | |
| "learning_rate": 5.765765765765766e-05, | |
| "loss": 0.0045, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.324324324324325, | |
| "grad_norm": 0.3451184034347534, | |
| "learning_rate": 5.6756756756756757e-05, | |
| "loss": 0.0034, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.414414414414415, | |
| "grad_norm": 0.3993205726146698, | |
| "learning_rate": 5.585585585585585e-05, | |
| "loss": 0.0062, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.504504504504505, | |
| "grad_norm": 1.2357189655303955, | |
| "learning_rate": 5.4954954954954966e-05, | |
| "loss": 0.0109, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.594594594594595, | |
| "grad_norm": 2.587001085281372, | |
| "learning_rate": 5.405405405405406e-05, | |
| "loss": 0.0096, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.684684684684685, | |
| "grad_norm": 1.4181842803955078, | |
| "learning_rate": 5.3153153153153155e-05, | |
| "loss": 0.0053, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.774774774774775, | |
| "grad_norm": 0.5997741222381592, | |
| "learning_rate": 5.2252252252252256e-05, | |
| "loss": 0.0074, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.864864864864865, | |
| "grad_norm": 0.6971381306648254, | |
| "learning_rate": 5.135135135135135e-05, | |
| "loss": 0.0022, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.954954954954955, | |
| "grad_norm": 1.7140687704086304, | |
| "learning_rate": 5.0450450450450445e-05, | |
| "loss": 0.0035, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.011971085332334042, | |
| "eval_mse": 0.011971085332334042, | |
| "eval_runtime": 26.2997, | |
| "eval_samples_per_second": 8.441, | |
| "eval_steps_per_second": 1.065, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 5.045045045045045, | |
| "grad_norm": 1.8608264923095703, | |
| "learning_rate": 4.954954954954955e-05, | |
| "loss": 0.0074, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.135135135135135, | |
| "grad_norm": 0.60817551612854, | |
| "learning_rate": 4.8648648648648654e-05, | |
| "loss": 0.0068, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.225225225225225, | |
| "grad_norm": 1.958824634552002, | |
| "learning_rate": 4.774774774774775e-05, | |
| "loss": 0.006, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.315315315315315, | |
| "grad_norm": 0.3445253372192383, | |
| "learning_rate": 4.684684684684685e-05, | |
| "loss": 0.0049, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.405405405405405, | |
| "grad_norm": 0.22099243104457855, | |
| "learning_rate": 4.594594594594595e-05, | |
| "loss": 0.0039, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.495495495495495, | |
| "grad_norm": 1.4178491830825806, | |
| "learning_rate": 4.5045045045045046e-05, | |
| "loss": 0.0131, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.585585585585585, | |
| "grad_norm": 0.469068706035614, | |
| "learning_rate": 4.414414414414415e-05, | |
| "loss": 0.0025, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.675675675675675, | |
| "grad_norm": 0.772139847278595, | |
| "learning_rate": 4.324324324324325e-05, | |
| "loss": 0.0032, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.7657657657657655, | |
| "grad_norm": 0.21695229411125183, | |
| "learning_rate": 4.234234234234234e-05, | |
| "loss": 0.0026, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.8558558558558556, | |
| "grad_norm": 1.6817526817321777, | |
| "learning_rate": 4.1441441441441444e-05, | |
| "loss": 0.005, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.945945945945946, | |
| "grad_norm": 1.2628576755523682, | |
| "learning_rate": 4.0540540540540545e-05, | |
| "loss": 0.0024, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.008206626400351524, | |
| "eval_mse": 0.008206626400351524, | |
| "eval_runtime": 26.5886, | |
| "eval_samples_per_second": 8.349, | |
| "eval_steps_per_second": 1.053, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 6.036036036036036, | |
| "grad_norm": 1.1488395929336548, | |
| "learning_rate": 3.963963963963964e-05, | |
| "loss": 0.0036, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.126126126126126, | |
| "grad_norm": 1.4983370304107666, | |
| "learning_rate": 3.873873873873874e-05, | |
| "loss": 0.0032, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.216216216216216, | |
| "grad_norm": 0.8290634751319885, | |
| "learning_rate": 3.783783783783784e-05, | |
| "loss": 0.0091, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.306306306306306, | |
| "grad_norm": 0.4906163811683655, | |
| "learning_rate": 3.693693693693694e-05, | |
| "loss": 0.0013, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.396396396396397, | |
| "grad_norm": 0.5014496445655823, | |
| "learning_rate": 3.603603603603604e-05, | |
| "loss": 0.0019, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.486486486486487, | |
| "grad_norm": 0.38546356558799744, | |
| "learning_rate": 3.513513513513514e-05, | |
| "loss": 0.0013, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.576576576576577, | |
| "grad_norm": 2.099214553833008, | |
| "learning_rate": 3.4234234234234234e-05, | |
| "loss": 0.0018, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.1836785525083542, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0013, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.756756756756757, | |
| "grad_norm": 0.2982404828071594, | |
| "learning_rate": 3.2432432432432436e-05, | |
| "loss": 0.0015, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.846846846846847, | |
| "grad_norm": 2.1191866397857666, | |
| "learning_rate": 3.153153153153153e-05, | |
| "loss": 0.0037, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 6.936936936936937, | |
| "grad_norm": 1.7569901943206787, | |
| "learning_rate": 3.063063063063063e-05, | |
| "loss": 0.0079, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.007293929811567068, | |
| "eval_mse": 0.0072939288802444935, | |
| "eval_runtime": 23.2827, | |
| "eval_samples_per_second": 9.535, | |
| "eval_steps_per_second": 1.203, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 7.027027027027027, | |
| "grad_norm": 0.3839648365974426, | |
| "learning_rate": 2.9729729729729733e-05, | |
| "loss": 0.0013, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.117117117117117, | |
| "grad_norm": 0.09070757776498795, | |
| "learning_rate": 2.882882882882883e-05, | |
| "loss": 0.0009, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.207207207207207, | |
| "grad_norm": 0.15580403804779053, | |
| "learning_rate": 2.7927927927927926e-05, | |
| "loss": 0.0006, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.297297297297297, | |
| "grad_norm": 0.6153419017791748, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 0.0015, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.387387387387387, | |
| "grad_norm": 0.3068805932998657, | |
| "learning_rate": 2.6126126126126128e-05, | |
| "loss": 0.0009, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.4774774774774775, | |
| "grad_norm": 0.38947150111198425, | |
| "learning_rate": 2.5225225225225222e-05, | |
| "loss": 0.0018, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 7.5675675675675675, | |
| "grad_norm": 0.3517474830150604, | |
| "learning_rate": 2.4324324324324327e-05, | |
| "loss": 0.0006, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.657657657657658, | |
| "grad_norm": 0.26397421956062317, | |
| "learning_rate": 2.3423423423423425e-05, | |
| "loss": 0.0044, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.747747747747748, | |
| "grad_norm": 0.5078900456428528, | |
| "learning_rate": 2.2522522522522523e-05, | |
| "loss": 0.0018, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 7.837837837837838, | |
| "grad_norm": 0.13668565452098846, | |
| "learning_rate": 2.1621621621621624e-05, | |
| "loss": 0.0006, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 7.927927927927928, | |
| "grad_norm": 0.2840743660926819, | |
| "learning_rate": 2.0720720720720722e-05, | |
| "loss": 0.0005, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.006760227959603071, | |
| "eval_mse": 0.0067602284252643585, | |
| "eval_runtime": 25.9835, | |
| "eval_samples_per_second": 8.544, | |
| "eval_steps_per_second": 1.078, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 8.018018018018019, | |
| "grad_norm": 0.12077564746141434, | |
| "learning_rate": 1.981981981981982e-05, | |
| "loss": 0.0005, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 8.108108108108109, | |
| "grad_norm": 0.14313092827796936, | |
| "learning_rate": 1.891891891891892e-05, | |
| "loss": 0.0007, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.198198198198199, | |
| "grad_norm": 0.04330454021692276, | |
| "learning_rate": 1.801801801801802e-05, | |
| "loss": 0.0002, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.288288288288289, | |
| "grad_norm": 0.09245187044143677, | |
| "learning_rate": 1.7117117117117117e-05, | |
| "loss": 0.0003, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.378378378378379, | |
| "grad_norm": 1.145082950592041, | |
| "learning_rate": 1.6216216216216218e-05, | |
| "loss": 0.0005, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 8.468468468468469, | |
| "grad_norm": 0.16518352925777435, | |
| "learning_rate": 1.5315315315315316e-05, | |
| "loss": 0.0028, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 8.558558558558559, | |
| "grad_norm": 0.21115215122699738, | |
| "learning_rate": 1.4414414414414416e-05, | |
| "loss": 0.0004, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 8.64864864864865, | |
| "grad_norm": 0.5826627612113953, | |
| "learning_rate": 1.3513513513513515e-05, | |
| "loss": 0.0004, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 8.73873873873874, | |
| "grad_norm": 0.5220029354095459, | |
| "learning_rate": 1.2612612612612611e-05, | |
| "loss": 0.0003, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 8.82882882882883, | |
| "grad_norm": 0.10058625787496567, | |
| "learning_rate": 1.1711711711711713e-05, | |
| "loss": 0.0005, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 8.91891891891892, | |
| "grad_norm": 0.5194815993309021, | |
| "learning_rate": 1.0810810810810812e-05, | |
| "loss": 0.0004, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.006972064264118671, | |
| "eval_mse": 0.006972064264118671, | |
| "eval_runtime": 25.2631, | |
| "eval_samples_per_second": 8.788, | |
| "eval_steps_per_second": 1.108, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 9.00900900900901, | |
| "grad_norm": 0.20283883810043335, | |
| "learning_rate": 9.90990990990991e-06, | |
| "loss": 0.0003, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.0990990990991, | |
| "grad_norm": 0.34447431564331055, | |
| "learning_rate": 9.00900900900901e-06, | |
| "loss": 0.0002, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 9.18918918918919, | |
| "grad_norm": 0.08173416554927826, | |
| "learning_rate": 8.108108108108109e-06, | |
| "loss": 0.0002, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 9.27927927927928, | |
| "grad_norm": 0.10527441650629044, | |
| "learning_rate": 7.207207207207208e-06, | |
| "loss": 0.0002, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 9.36936936936937, | |
| "grad_norm": 0.0803741067647934, | |
| "learning_rate": 6.306306306306306e-06, | |
| "loss": 0.0001, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 9.45945945945946, | |
| "grad_norm": 0.10471061617136002, | |
| "learning_rate": 5.405405405405406e-06, | |
| "loss": 0.0002, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 9.54954954954955, | |
| "grad_norm": 0.05206935107707977, | |
| "learning_rate": 4.504504504504505e-06, | |
| "loss": 0.0002, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 9.63963963963964, | |
| "grad_norm": 0.022533565759658813, | |
| "learning_rate": 3.603603603603604e-06, | |
| "loss": 0.0001, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 9.72972972972973, | |
| "grad_norm": 0.08269208669662476, | |
| "learning_rate": 2.702702702702703e-06, | |
| "loss": 0.0002, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 9.81981981981982, | |
| "grad_norm": 0.05740358307957649, | |
| "learning_rate": 1.801801801801802e-06, | |
| "loss": 0.0002, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 9.90990990990991, | |
| "grad_norm": 0.2768089771270752, | |
| "learning_rate": 9.00900900900901e-07, | |
| "loss": 0.001, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.1483727991580963, | |
| "learning_rate": 0.0, | |
| "loss": 0.0001, | |
| "step": 1110 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1110, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |