| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05653976630229928, | |
| "eval_steps": 50, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003769317753486619, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.004e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003769317753486619, | |
| "eval_loss": NaN, | |
| "eval_runtime": 104.6478, | |
| "eval_samples_per_second": 10.674, | |
| "eval_steps_per_second": 2.676, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007538635506973238, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.008e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011307953260459858, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.012e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015077271013946476, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.016e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018846588767433095, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.02e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022615906520919715, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.024e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002638522427440633, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.028e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003015454202789295, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.032e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003392385978137957, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.036000000000001e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003769317753486619, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001004, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0041462495288352805, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987157894736842e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004523181304183943, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.934315789473684e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004900113079532605, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.881473684210525e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005277044854881266, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.828631578947369e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005653976630229929, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.77578947368421e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00603090840557859, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.722947368421052e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006407840180927252, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.670105263157895e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006784771956275914, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.617263157894737e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007161703731624576, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.564421052631579e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007538635506973238, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.511578947368421e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0079155672823219, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.458736842105264e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008292499057670561, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.405894736842106e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008669430833019224, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.353052631578947e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009046362608367886, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.300210526315789e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009423294383716547, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.247368421052631e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00980022615906521, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.194526315789473e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010177157934413872, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.141684210526316e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010554089709762533, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.088842105263158e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010931021485111195, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.036000000000001e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011307953260459858, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.983157894736843e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011684885035808518, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930315789473684e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01206181681115718, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.877473684210526e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012438748586505842, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.824631578947368e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.012815680361854504, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.771789473684211e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013192612137203167, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.718947368421053e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013569543912551827, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.666105263157895e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01394647568790049, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.613263157894737e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014323407463249152, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.560421052631578e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.014700339238597813, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.50757894736842e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015077271013946476, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.454736842105263e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015454202789295138, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.401894736842106e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0158311345646438, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.349052631578948e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01620806633999246, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.29621052631579e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.016584998115341122, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.243368421052632e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.016961929890689786, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.190526315789474e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.017338861666038447, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.137684210526315e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017715793441387108, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.084842105263157e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.018092725216735772, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.032e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018469656992084433, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.979157894736842e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.018846588767433094, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.926315789473684e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018846588767433094, | |
| "eval_loss": NaN, | |
| "eval_runtime": 104.3188, | |
| "eval_samples_per_second": 10.708, | |
| "eval_steps_per_second": 2.684, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.019223520542781758, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.873473684210526e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01960045231813042, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.820631578947369e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.01997738409347908, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.76778947368421e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.020354315868827744, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.714947368421052e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.020731247644176404, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.662105263157896e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.021108179419525065, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.609263157894737e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.02148511119487373, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.556421052631579e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.02186204297022239, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.503578947368421e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.02223897474557105, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.450736842105263e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.022615906520919715, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.397894736842105e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.022992838296268376, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.345052631578948e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.023369770071617037, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.29221052631579e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.023746701846965697, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.239368421052631e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02412363362231436, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.186526315789474e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.024500565397663022, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.133684210526316e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.024877497173011683, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.080842105263158e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.025254428948360347, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.028e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.025631360723709008, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.975157894736843e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.02600829249905767, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.922315789473685e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.026385224274406333, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.869473684210527e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.026762156049754994, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.816631578947368e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.027139087825103655, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.76378947368421e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.02751601960045232, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710947368421052e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.02789295137580098, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.658105263157894e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02826988315114964, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.605263157894737e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.028646814926498305, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.55242105263158e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.029023746701846966, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.499578947368422e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.029400678477195626, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.446736842105264e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.02977761025254429, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.393894736842105e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.03015454202789295, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.341052631578947e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.030531473803241612, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.288210526315789e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.030908405578590276, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.235368421052632e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.03128533735393894, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.182526315789474e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.0316622691292876, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.129684210526316e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.03203920090463626, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.076842105263158e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03241613267998492, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.024e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.03279306445533359, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.971157894736842e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.033169996230682244, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9183157894736835e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.03354692800603091, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8654736842105267e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.03392385978137957, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8126315789473684e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03430079155672823, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.759789473684211e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.034677723332076894, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.706947368421053e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.03505465510742556, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6541052631578945e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.035431586882774216, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.601263157894736e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.03580851865812288, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5484210526315794e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.036185450433471544, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.495578947368421e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.0365623822088202, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.442736842105264e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.036939313984168866, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3898947368421055e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.03731624575951753, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.337052631578947e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.03769317753486619, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.284210526315789e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03769317753486619, | |
| "eval_loss": NaN, | |
| "eval_runtime": 104.3204, | |
| "eval_samples_per_second": 10.707, | |
| "eval_steps_per_second": 2.684, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03807010931021485, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.231368421052631e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.038447041085563516, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.178526315789474e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.03882397286091217, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1256842105263165e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.03920090463626084, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.072842105263158e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.0395778364116095, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.02e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.03995476818695816, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.967157894736842e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.04033169996230682, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.914315789473684e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.04070863173765549, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.861473684210526e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.041085563513004145, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8086315789473686e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.04146249528835281, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7557894736842104e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04183942706370147, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.702947368421053e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.04221635883905013, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6501052631578946e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.042593290614398795, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5972631578947364e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.04297022238974746, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.544421052631579e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.043347154165096116, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4915789473684213e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.04372408594044478, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.438736842105263e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.044101017715793445, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3858947368421056e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.0444779494911421, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3330526315789474e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.044854881266490766, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.280210526315789e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.04523181304183943, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2273684210526317e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04560874481718809, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.174526315789474e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.04598567659253675, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.121684210526316e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.046362608367885416, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.068842105263158e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.04673954014323407, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.016e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.04711647191858274, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.963157894736842e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.047493403693931395, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9103157894736844e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.04787033546928006, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.857473684210526e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.04824726724462872, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.804631578947369e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.04862419901997738, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7517894736842105e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.049001130795326045, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.698947368421052e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.04937806257067471, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.646105263157895e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.049754994346023367, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.593263157894737e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.05013192612137203, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.540421052631579e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.050508857896720695, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4875789473684215e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.05088578967206935, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.434736842105263e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.051262721447418017, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.381894736842105e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.05163965322276668, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.329052631578947e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.05201658499811534, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.27621052631579e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.052393516773464, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.223368421052632e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.052770448548812667, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1705263157894736e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.053147380324161324, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.117684210526316e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.05352431209950999, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.064842105263158e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.05390124387485865, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.012e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.05427817565020731, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9591578947368418e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.054655107425555974, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9063157894736842e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.05503203920090464, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8534736842105264e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.055408970976253295, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.800631578947368e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.05578590275160196, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7477894736842106e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.056162834526950624, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6949473684210527e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.05653976630229928, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6421052631578945e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05653976630229928, | |
| "eval_loss": NaN, | |
| "eval_runtime": 104.3131, | |
| "eval_samples_per_second": 10.708, | |
| "eval_steps_per_second": 2.684, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 289249689600.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |