arpandeepk's picture
upload rmu_Llama-3.1-8B_20260427_203908
77e8fad verified
Raw
History Blame Contribute Delete
43.6 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 534,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0,
"forget_loss": 0.00946044921875,
"retain_loss": 0.0,
"step": 0
},
{
"epoch": 0,
"forget_loss": 0.00994873046875,
"retain_loss": 0.0,
"step": 0
},
{
"epoch": 0,
"forget_loss": 0.00958251953125,
"retain_loss": 0.0,
"step": 0
},
{
"epoch": 0,
"forget_loss": 0.009521484375,
"retain_loss": 0.0,
"step": 0
},
{
"epoch": 0.003755868544600939,
"grad_norm": 0.11474609375,
"learning_rate": 0.0,
"loss": 0.0096282958984375,
"step": 1
},
{
"epoch": 0.03755868544600939,
"grad_norm": 0.09814453125,
"learning_rate": 4.5e-06,
"loss": 0.009236653645833334,
"step": 10
},
{
"epoch": 0.03755868544600939,
"forget_loss": 0.00799560546875,
"retain_loss": 1.919269561767578e-05,
"step": 10
},
{
"epoch": 0.03755868544600939,
"forget_loss": 0.008056640625,
"retain_loss": 1.6570091247558594e-05,
"step": 10
},
{
"epoch": 0.03755868544600939,
"forget_loss": 0.0081787109375,
"retain_loss": 2.2649765014648438e-05,
"step": 10
},
{
"epoch": 0.03755868544600939,
"forget_loss": 0.00823974609375,
"retain_loss": 2.1457672119140625e-05,
"step": 10
},
{
"epoch": 0.07511737089201878,
"grad_norm": 0.047607421875,
"learning_rate": 9.5e-06,
"loss": 0.00635223388671875,
"step": 20
},
{
"epoch": 0.07511737089201878,
"forget_loss": 0.003662109375,
"retain_loss": 0.00022602081298828125,
"step": 20
},
{
"epoch": 0.07511737089201878,
"forget_loss": 0.004425048828125,
"retain_loss": 0.0002880096435546875,
"step": 20
},
{
"epoch": 0.07511737089201878,
"forget_loss": 0.0037078857421875,
"retain_loss": 0.00020885467529296875,
"step": 20
},
{
"epoch": 0.07511737089201878,
"forget_loss": 0.00421142578125,
"retain_loss": 0.00021457672119140625,
"step": 20
},
{
"epoch": 0.11267605633802817,
"grad_norm": 0.123046875,
"learning_rate": 9.82490272373541e-06,
"loss": 0.00320587158203125,
"step": 30
},
{
"epoch": 0.11267605633802817,
"forget_loss": 0.0018310546875,
"retain_loss": 0.00054168701171875,
"step": 30
},
{
"epoch": 0.11267605633802817,
"forget_loss": 0.00177001953125,
"retain_loss": 0.0004177093505859375,
"step": 30
},
{
"epoch": 0.11267605633802817,
"forget_loss": 0.00177001953125,
"retain_loss": 0.0002956390380859375,
"step": 30
},
{
"epoch": 0.11267605633802817,
"forget_loss": 0.0016937255859375,
"retain_loss": 0.000331878662109375,
"step": 30
},
{
"epoch": 0.15023474178403756,
"grad_norm": 0.05517578125,
"learning_rate": 9.63035019455253e-06,
"loss": 0.0016145706176757812,
"step": 40
},
{
"epoch": 0.15023474178403756,
"forget_loss": 0.0007781982421875,
"retain_loss": 0.00021648406982421875,
"step": 40
},
{
"epoch": 0.15023474178403756,
"forget_loss": 0.000762939453125,
"retain_loss": 0.0004100799560546875,
"step": 40
},
{
"epoch": 0.15023474178403756,
"forget_loss": 0.000766754150390625,
"retain_loss": 0.000331878662109375,
"step": 40
},
{
"epoch": 0.15023474178403756,
"forget_loss": 0.0007781982421875,
"retain_loss": 0.00038909912109375,
"step": 40
},
{
"epoch": 0.18779342723004694,
"grad_norm": 0.1416015625,
"learning_rate": 9.435797665369651e-06,
"loss": 0.000954437255859375,
"step": 50
},
{
"epoch": 0.18779342723004694,
"forget_loss": 0.0003452301025390625,
"retain_loss": 0.00020599365234375,
"step": 50
},
{
"epoch": 0.18779342723004694,
"forget_loss": 0.0003814697265625,
"retain_loss": 0.00020694732666015625,
"step": 50
},
{
"epoch": 0.18779342723004694,
"forget_loss": 0.000415802001953125,
"retain_loss": 0.0003604888916015625,
"step": 50
},
{
"epoch": 0.18779342723004694,
"forget_loss": 0.0003719329833984375,
"retain_loss": 0.0001964569091796875,
"step": 50
},
{
"epoch": 0.22535211267605634,
"grad_norm": 0.06396484375,
"learning_rate": 9.241245136186772e-06,
"loss": 0.0008329868316650391,
"step": 60
},
{
"epoch": 0.22535211267605634,
"forget_loss": 0.0002574920654296875,
"retain_loss": 0.0002727508544921875,
"step": 60
},
{
"epoch": 0.22535211267605634,
"forget_loss": 0.00019931793212890625,
"retain_loss": 0.00010919570922851562,
"step": 60
},
{
"epoch": 0.22535211267605634,
"forget_loss": 0.0001983642578125,
"retain_loss": 0.000202178955078125,
"step": 60
},
{
"epoch": 0.22535211267605634,
"forget_loss": 0.00023365020751953125,
"retain_loss": 0.0002002716064453125,
"step": 60
},
{
"epoch": 0.26291079812206575,
"grad_norm": 0.28515625,
"learning_rate": 9.046692607003892e-06,
"loss": 0.0006081581115722657,
"step": 70
},
{
"epoch": 0.26291079812206575,
"forget_loss": 0.00018405914306640625,
"retain_loss": 0.0002689361572265625,
"step": 70
},
{
"epoch": 0.26291079812206575,
"forget_loss": 0.0001811981201171875,
"retain_loss": 8.535385131835938e-05,
"step": 70
},
{
"epoch": 0.26291079812206575,
"forget_loss": 0.00022792816162109375,
"retain_loss": 0.00010728836059570312,
"step": 70
},
{
"epoch": 0.26291079812206575,
"forget_loss": 0.0003643035888671875,
"retain_loss": 0.00011777877807617188,
"step": 70
},
{
"epoch": 0.3004694835680751,
"grad_norm": 0.07177734375,
"learning_rate": 8.852140077821012e-06,
"loss": 0.0004550933837890625,
"step": 80
},
{
"epoch": 0.3004694835680751,
"forget_loss": 0.0002155303955078125,
"retain_loss": 0.000110626220703125,
"step": 80
},
{
"epoch": 0.3004694835680751,
"forget_loss": 0.00014019012451171875,
"retain_loss": 6.723403930664062e-05,
"step": 80
},
{
"epoch": 0.3004694835680751,
"forget_loss": 0.0001773834228515625,
"retain_loss": 0.000331878662109375,
"step": 80
},
{
"epoch": 0.3004694835680751,
"forget_loss": 0.00016498565673828125,
"retain_loss": 9.489059448242188e-05,
"step": 80
},
{
"epoch": 0.3380281690140845,
"grad_norm": 0.0810546875,
"learning_rate": 8.657587548638134e-06,
"loss": 0.0003980875015258789,
"step": 90
},
{
"epoch": 0.3380281690140845,
"forget_loss": 0.00015735626220703125,
"retain_loss": 0.0001544952392578125,
"step": 90
},
{
"epoch": 0.3380281690140845,
"forget_loss": 0.000133514404296875,
"retain_loss": 0.00080108642578125,
"step": 90
},
{
"epoch": 0.3380281690140845,
"forget_loss": 0.00014781951904296875,
"retain_loss": 0.000431060791015625,
"step": 90
},
{
"epoch": 0.3380281690140845,
"forget_loss": 0.00014400482177734375,
"retain_loss": 0.00031280517578125,
"step": 90
},
{
"epoch": 0.3755868544600939,
"grad_norm": 0.025146484375,
"learning_rate": 8.463035019455253e-06,
"loss": 0.00032124519348144533,
"step": 100
},
{
"epoch": 0.3755868544600939,
"forget_loss": 0.00015163421630859375,
"retain_loss": 0.00015926361083984375,
"step": 100
},
{
"epoch": 0.3755868544600939,
"forget_loss": 0.0001506805419921875,
"retain_loss": 0.00011587142944335938,
"step": 100
},
{
"epoch": 0.3755868544600939,
"forget_loss": 0.00013065338134765625,
"retain_loss": 0.000125885009765625,
"step": 100
},
{
"epoch": 0.3755868544600939,
"forget_loss": 0.0001239776611328125,
"retain_loss": 0.0001277923583984375,
"step": 100
},
{
"epoch": 0.4131455399061033,
"grad_norm": 0.06884765625,
"learning_rate": 8.268482490272373e-06,
"loss": 0.00034072399139404295,
"step": 110
},
{
"epoch": 0.4131455399061033,
"forget_loss": 0.0001544952392578125,
"retain_loss": 7.2479248046875e-05,
"step": 110
},
{
"epoch": 0.4131455399061033,
"forget_loss": 0.0001373291015625,
"retain_loss": 0.000270843505859375,
"step": 110
},
{
"epoch": 0.4131455399061033,
"forget_loss": 0.0001125335693359375,
"retain_loss": 9.965896606445312e-05,
"step": 110
},
{
"epoch": 0.4131455399061033,
"forget_loss": 0.00011205673217773438,
"retain_loss": 6.866455078125e-05,
"step": 110
},
{
"epoch": 0.4507042253521127,
"grad_norm": 0.08544921875,
"learning_rate": 8.073929961089495e-06,
"loss": 0.0002372264862060547,
"step": 120
},
{
"epoch": 0.4507042253521127,
"forget_loss": 0.000179290771484375,
"retain_loss": 7.05718994140625e-05,
"step": 120
},
{
"epoch": 0.4507042253521127,
"forget_loss": 0.0001277923583984375,
"retain_loss": 9.250640869140625e-05,
"step": 120
},
{
"epoch": 0.4507042253521127,
"forget_loss": 0.00013446807861328125,
"retain_loss": 8.630752563476562e-05,
"step": 120
},
{
"epoch": 0.4507042253521127,
"forget_loss": 0.0001735687255859375,
"retain_loss": 8.106231689453125e-05,
"step": 120
},
{
"epoch": 0.48826291079812206,
"grad_norm": 0.0361328125,
"learning_rate": 7.879377431906614e-06,
"loss": 0.0002105236053466797,
"step": 130
},
{
"epoch": 0.48826291079812206,
"forget_loss": 0.00010776519775390625,
"retain_loss": 5.221366882324219e-05,
"step": 130
},
{
"epoch": 0.48826291079812206,
"forget_loss": 0.00010728836059570312,
"retain_loss": 5.1021575927734375e-05,
"step": 130
},
{
"epoch": 0.48826291079812206,
"forget_loss": 0.00010204315185546875,
"retain_loss": 0.00011110305786132812,
"step": 130
},
{
"epoch": 0.48826291079812206,
"forget_loss": 0.000156402587890625,
"retain_loss": 7.05718994140625e-05,
"step": 130
},
{
"epoch": 0.5258215962441315,
"grad_norm": 0.035400390625,
"learning_rate": 7.684824902723736e-06,
"loss": 0.000272369384765625,
"step": 140
},
{
"epoch": 0.5258215962441315,
"forget_loss": 0.0001087188720703125,
"retain_loss": 7.009506225585938e-05,
"step": 140
},
{
"epoch": 0.5258215962441315,
"forget_loss": 0.0001239776611328125,
"retain_loss": 7.963180541992188e-05,
"step": 140
},
{
"epoch": 0.5258215962441315,
"forget_loss": 0.00017070770263671875,
"retain_loss": 6.29425048828125e-05,
"step": 140
},
{
"epoch": 0.5258215962441315,
"forget_loss": 0.00013446807861328125,
"retain_loss": 5.5789947509765625e-05,
"step": 140
},
{
"epoch": 0.5633802816901409,
"grad_norm": 0.0177001953125,
"learning_rate": 7.4902723735408565e-06,
"loss": 0.00019230842590332032,
"step": 150
},
{
"epoch": 0.5633802816901409,
"forget_loss": 0.00010585784912109375,
"retain_loss": 5.793571472167969e-05,
"step": 150
},
{
"epoch": 0.5633802816901409,
"forget_loss": 0.00011157989501953125,
"retain_loss": 0.00015163421630859375,
"step": 150
},
{
"epoch": 0.5633802816901409,
"forget_loss": 8.821487426757812e-05,
"retain_loss": 6.866455078125e-05,
"step": 150
},
{
"epoch": 0.5633802816901409,
"forget_loss": 9.059906005859375e-05,
"retain_loss": 0.00010251998901367188,
"step": 150
},
{
"epoch": 0.6009389671361502,
"grad_norm": 0.06591796875,
"learning_rate": 7.295719844357977e-06,
"loss": 0.00020923614501953126,
"step": 160
},
{
"epoch": 0.6009389671361502,
"forget_loss": 0.00010156631469726562,
"retain_loss": 8.535385131835938e-05,
"step": 160
},
{
"epoch": 0.6009389671361502,
"forget_loss": 9.441375732421875e-05,
"retain_loss": 7.05718994140625e-05,
"step": 160
},
{
"epoch": 0.6009389671361502,
"forget_loss": 9.489059448242188e-05,
"retain_loss": 6.151199340820312e-05,
"step": 160
},
{
"epoch": 0.6009389671361502,
"forget_loss": 9.679794311523438e-05,
"retain_loss": 5.984306335449219e-05,
"step": 160
},
{
"epoch": 0.6384976525821596,
"grad_norm": 0.0152587890625,
"learning_rate": 7.101167315175098e-06,
"loss": 0.0001931428909301758,
"step": 170
},
{
"epoch": 0.6384976525821596,
"forget_loss": 9.489059448242188e-05,
"retain_loss": 6.079673767089844e-05,
"step": 170
},
{
"epoch": 0.6384976525821596,
"forget_loss": 0.000110626220703125,
"retain_loss": 7.104873657226562e-05,
"step": 170
},
{
"epoch": 0.6384976525821596,
"forget_loss": 0.00010776519775390625,
"retain_loss": 0.00011539459228515625,
"step": 170
},
{
"epoch": 0.6384976525821596,
"forget_loss": 9.441375732421875e-05,
"retain_loss": 0.00011682510375976562,
"step": 170
},
{
"epoch": 0.676056338028169,
"grad_norm": 0.0306396484375,
"learning_rate": 6.9066147859922184e-06,
"loss": 0.00021104812622070314,
"step": 180
},
{
"epoch": 0.676056338028169,
"forget_loss": 0.000125885009765625,
"retain_loss": 0.0001239776611328125,
"step": 180
},
{
"epoch": 0.676056338028169,
"forget_loss": 0.00010395050048828125,
"retain_loss": 8.96453857421875e-05,
"step": 180
},
{
"epoch": 0.676056338028169,
"forget_loss": 8.869171142578125e-05,
"retain_loss": 8.20159912109375e-05,
"step": 180
},
{
"epoch": 0.676056338028169,
"forget_loss": 9.107589721679688e-05,
"retain_loss": 5.316734313964844e-05,
"step": 180
},
{
"epoch": 0.7136150234741784,
"grad_norm": 0.0230712890625,
"learning_rate": 6.712062256809338e-06,
"loss": 0.0001739978790283203,
"step": 190
},
{
"epoch": 0.7136150234741784,
"forget_loss": 9.059906005859375e-05,
"retain_loss": 5.793571472167969e-05,
"step": 190
},
{
"epoch": 0.7136150234741784,
"forget_loss": 9.5367431640625e-05,
"retain_loss": 5.0067901611328125e-05,
"step": 190
},
{
"epoch": 0.7136150234741784,
"forget_loss": 8.869171142578125e-05,
"retain_loss": 5.7220458984375e-05,
"step": 190
},
{
"epoch": 0.7136150234741784,
"forget_loss": 0.00010919570922851562,
"retain_loss": 4.9591064453125e-05,
"step": 190
},
{
"epoch": 0.7511737089201878,
"grad_norm": 0.01068115234375,
"learning_rate": 6.51750972762646e-06,
"loss": 0.00019364356994628907,
"step": 200
},
{
"epoch": 0.7511737089201878,
"forget_loss": 0.00010204315185546875,
"retain_loss": 5.14984130859375e-05,
"step": 200
},
{
"epoch": 0.7511737089201878,
"forget_loss": 8.249282836914062e-05,
"retain_loss": 4.887580871582031e-05,
"step": 200
},
{
"epoch": 0.7511737089201878,
"forget_loss": 7.772445678710938e-05,
"retain_loss": 4.076957702636719e-05,
"step": 200
},
{
"epoch": 0.7511737089201878,
"forget_loss": 0.00012683868408203125,
"retain_loss": 6.341934204101562e-05,
"step": 200
},
{
"epoch": 0.7887323943661971,
"grad_norm": 0.016357421875,
"learning_rate": 6.32295719844358e-06,
"loss": 0.00015709400177001953,
"step": 210
},
{
"epoch": 0.7887323943661971,
"forget_loss": 0.00010585784912109375,
"retain_loss": 7.009506225585938e-05,
"step": 210
},
{
"epoch": 0.7887323943661971,
"forget_loss": 8.58306884765625e-05,
"retain_loss": 4.2438507080078125e-05,
"step": 210
},
{
"epoch": 0.7887323943661971,
"forget_loss": 8.440017700195312e-05,
"retain_loss": 4.744529724121094e-05,
"step": 210
},
{
"epoch": 0.7887323943661971,
"forget_loss": 0.0001010894775390625,
"retain_loss": 4.4345855712890625e-05,
"step": 210
},
{
"epoch": 0.8262910798122066,
"grad_norm": 0.01806640625,
"learning_rate": 6.128404669260701e-06,
"loss": 0.0001538991928100586,
"step": 220
},
{
"epoch": 0.8262910798122066,
"forget_loss": 9.72747802734375e-05,
"retain_loss": 4.8160552978515625e-05,
"step": 220
},
{
"epoch": 0.8262910798122066,
"forget_loss": 8.0108642578125e-05,
"retain_loss": 7.200241088867188e-05,
"step": 220
},
{
"epoch": 0.8262910798122066,
"forget_loss": 7.82012939453125e-05,
"retain_loss": 4.3392181396484375e-05,
"step": 220
},
{
"epoch": 0.8262910798122066,
"forget_loss": 0.0001049041748046875,
"retain_loss": 7.009506225585938e-05,
"step": 220
},
{
"epoch": 0.863849765258216,
"grad_norm": 0.0184326171875,
"learning_rate": 5.933852140077822e-06,
"loss": 0.00015753507614135742,
"step": 230
},
{
"epoch": 0.863849765258216,
"forget_loss": 8.678436279296875e-05,
"retain_loss": 4.38690185546875e-05,
"step": 230
},
{
"epoch": 0.863849765258216,
"forget_loss": 8.344650268554688e-05,
"retain_loss": 0.000942230224609375,
"step": 230
},
{
"epoch": 0.863849765258216,
"forget_loss": 9.1552734375e-05,
"retain_loss": 4.410743713378906e-05,
"step": 230
},
{
"epoch": 0.863849765258216,
"forget_loss": 8.296966552734375e-05,
"retain_loss": 7.486343383789062e-05,
"step": 230
},
{
"epoch": 0.9014084507042254,
"grad_norm": 0.0238037109375,
"learning_rate": 5.7392996108949415e-06,
"loss": 0.00017303228378295898,
"step": 240
},
{
"epoch": 0.9014084507042254,
"forget_loss": 8.296966552734375e-05,
"retain_loss": 4.291534423828125e-05,
"step": 240
},
{
"epoch": 0.9014084507042254,
"forget_loss": 8.96453857421875e-05,
"retain_loss": 3.814697265625e-05,
"step": 240
},
{
"epoch": 0.9014084507042254,
"forget_loss": 8.726119995117188e-05,
"retain_loss": 4.839897155761719e-05,
"step": 240
},
{
"epoch": 0.9014084507042254,
"forget_loss": 7.200241088867188e-05,
"retain_loss": 4.839897155761719e-05,
"step": 240
},
{
"epoch": 0.9389671361502347,
"grad_norm": 0.05908203125,
"learning_rate": 5.544747081712063e-06,
"loss": 0.00014340877532958984,
"step": 250
},
{
"epoch": 0.9389671361502347,
"forget_loss": 0.00010442733764648438,
"retain_loss": 5.626678466796875e-05,
"step": 250
},
{
"epoch": 0.9389671361502347,
"forget_loss": 8.726119995117188e-05,
"retain_loss": 9.059906005859375e-05,
"step": 250
},
{
"epoch": 0.9389671361502347,
"forget_loss": 8.344650268554688e-05,
"retain_loss": 3.647804260253906e-05,
"step": 250
},
{
"epoch": 0.9389671361502347,
"forget_loss": 8.821487426757812e-05,
"retain_loss": 4.220008850097656e-05,
"step": 250
},
{
"epoch": 0.9765258215962441,
"grad_norm": 0.0181884765625,
"learning_rate": 5.350194552529184e-06,
"loss": 0.00015048980712890626,
"step": 260
},
{
"epoch": 0.9765258215962441,
"forget_loss": 8.153915405273438e-05,
"retain_loss": 6.580352783203125e-05,
"step": 260
},
{
"epoch": 0.9765258215962441,
"forget_loss": 8.7738037109375e-05,
"retain_loss": 3.6716461181640625e-05,
"step": 260
},
{
"epoch": 0.9765258215962441,
"forget_loss": 9.918212890625e-05,
"retain_loss": 4.363059997558594e-05,
"step": 260
},
{
"epoch": 0.9765258215962441,
"forget_loss": 9.870529174804688e-05,
"retain_loss": 0.0001506805419921875,
"step": 260
},
{
"epoch": 1.0112676056338028,
"grad_norm": 0.00848388671875,
"learning_rate": 5.155642023346303e-06,
"loss": 0.00013761520385742189,
"step": 270
},
{
"epoch": 1.0112676056338028,
"forget_loss": 6.866455078125e-05,
"retain_loss": 5.9604644775390625e-05,
"step": 270
},
{
"epoch": 1.0112676056338028,
"forget_loss": 8.249282836914062e-05,
"retain_loss": 3.5762786865234375e-05,
"step": 270
},
{
"epoch": 1.0112676056338028,
"forget_loss": 8.392333984375e-05,
"retain_loss": 6.246566772460938e-05,
"step": 270
},
{
"epoch": 1.0112676056338028,
"forget_loss": 8.916854858398438e-05,
"retain_loss": 3.695487976074219e-05,
"step": 270
},
{
"epoch": 1.0488262910798123,
"grad_norm": 0.0137939453125,
"learning_rate": 4.961089494163425e-06,
"loss": 0.00013872385025024415,
"step": 280
},
{
"epoch": 1.0488262910798123,
"forget_loss": 7.772445678710938e-05,
"retain_loss": 4.982948303222656e-05,
"step": 280
},
{
"epoch": 1.0488262910798123,
"forget_loss": 6.771087646484375e-05,
"retain_loss": 4.5299530029296875e-05,
"step": 280
},
{
"epoch": 1.0488262910798123,
"forget_loss": 6.961822509765625e-05,
"retain_loss": 5.14984130859375e-05,
"step": 280
},
{
"epoch": 1.0488262910798123,
"forget_loss": 7.05718994140625e-05,
"retain_loss": 5.245208740234375e-05,
"step": 280
},
{
"epoch": 1.0863849765258216,
"grad_norm": 0.01275634765625,
"learning_rate": 4.7665369649805455e-06,
"loss": 0.00014275312423706055,
"step": 290
},
{
"epoch": 1.0863849765258216,
"forget_loss": 8.20159912109375e-05,
"retain_loss": 4.38690185546875e-05,
"step": 290
},
{
"epoch": 1.0863849765258216,
"forget_loss": 7.62939453125e-05,
"retain_loss": 5.745887756347656e-05,
"step": 290
},
{
"epoch": 1.0863849765258216,
"forget_loss": 9.059906005859375e-05,
"retain_loss": 5.269050598144531e-05,
"step": 290
},
{
"epoch": 1.0863849765258216,
"forget_loss": 8.106231689453125e-05,
"retain_loss": 5.507469177246094e-05,
"step": 290
},
{
"epoch": 1.123943661971831,
"grad_norm": 0.0140380859375,
"learning_rate": 4.571984435797665e-06,
"loss": 0.00013855695724487304,
"step": 300
},
{
"epoch": 1.123943661971831,
"forget_loss": 8.344650268554688e-05,
"retain_loss": 3.695487976074219e-05,
"step": 300
},
{
"epoch": 1.123943661971831,
"forget_loss": 8.249282836914062e-05,
"retain_loss": 4.100799560546875e-05,
"step": 300
},
{
"epoch": 1.123943661971831,
"forget_loss": 0.00010395050048828125,
"retain_loss": 3.504753112792969e-05,
"step": 300
},
{
"epoch": 1.123943661971831,
"forget_loss": 6.4849853515625e-05,
"retain_loss": 5.5789947509765625e-05,
"step": 300
},
{
"epoch": 1.1615023474178403,
"grad_norm": 0.019775390625,
"learning_rate": 4.377431906614786e-06,
"loss": 0.0001352071762084961,
"step": 310
},
{
"epoch": 1.1615023474178403,
"forget_loss": 7.62939453125e-05,
"retain_loss": 7.772445678710938e-05,
"step": 310
},
{
"epoch": 1.1615023474178403,
"forget_loss": 8.58306884765625e-05,
"retain_loss": 5.459785461425781e-05,
"step": 310
},
{
"epoch": 1.1615023474178403,
"forget_loss": 7.05718994140625e-05,
"retain_loss": 7.05718994140625e-05,
"step": 310
},
{
"epoch": 1.1615023474178403,
"forget_loss": 7.82012939453125e-05,
"retain_loss": 3.337860107421875e-05,
"step": 310
},
{
"epoch": 1.1990610328638498,
"grad_norm": 0.020751953125,
"learning_rate": 4.1828793774319074e-06,
"loss": 0.000127410888671875,
"step": 320
},
{
"epoch": 1.1990610328638498,
"forget_loss": 7.867813110351562e-05,
"retain_loss": 3.695487976074219e-05,
"step": 320
},
{
"epoch": 1.1990610328638498,
"forget_loss": 8.249282836914062e-05,
"retain_loss": 5.412101745605469e-05,
"step": 320
},
{
"epoch": 1.1990610328638498,
"forget_loss": 9.775161743164062e-05,
"retain_loss": 5.340576171875e-05,
"step": 320
},
{
"epoch": 1.1990610328638498,
"forget_loss": 7.152557373046875e-05,
"retain_loss": 8.106231689453125e-05,
"step": 320
},
{
"epoch": 1.236619718309859,
"grad_norm": 0.0091552734375,
"learning_rate": 3.988326848249028e-06,
"loss": 0.00014822483062744142,
"step": 330
},
{
"epoch": 1.236619718309859,
"forget_loss": 9.72747802734375e-05,
"retain_loss": 4.506111145019531e-05,
"step": 330
},
{
"epoch": 1.236619718309859,
"forget_loss": 0.00010919570922851562,
"retain_loss": 3.2901763916015625e-05,
"step": 330
},
{
"epoch": 1.236619718309859,
"forget_loss": 6.723403930664062e-05,
"retain_loss": 4.029273986816406e-05,
"step": 330
},
{
"epoch": 1.236619718309859,
"forget_loss": 6.914138793945312e-05,
"retain_loss": 7.724761962890625e-05,
"step": 330
},
{
"epoch": 1.2741784037558685,
"grad_norm": 0.011962890625,
"learning_rate": 3.793774319066148e-06,
"loss": 0.0001390695571899414,
"step": 340
},
{
"epoch": 1.2741784037558685,
"forget_loss": 8.535385131835938e-05,
"retain_loss": 4.506111145019531e-05,
"step": 340
},
{
"epoch": 1.2741784037558685,
"forget_loss": 6.866455078125e-05,
"retain_loss": 3.2901763916015625e-05,
"step": 340
},
{
"epoch": 1.2741784037558685,
"forget_loss": 6.723403930664062e-05,
"retain_loss": 5.0067901611328125e-05,
"step": 340
},
{
"epoch": 1.2741784037558685,
"forget_loss": 8.344650268554688e-05,
"retain_loss": 3.5762786865234375e-05,
"step": 340
},
{
"epoch": 1.3117370892018778,
"grad_norm": 0.01239013671875,
"learning_rate": 3.599221789883269e-06,
"loss": 0.00013332366943359376,
"step": 350
},
{
"epoch": 1.3117370892018778,
"forget_loss": 7.772445678710938e-05,
"retain_loss": 3.0040740966796875e-05,
"step": 350
},
{
"epoch": 1.3117370892018778,
"forget_loss": 7.963180541992188e-05,
"retain_loss": 4.363059997558594e-05,
"step": 350
},
{
"epoch": 1.3117370892018778,
"forget_loss": 8.630752563476562e-05,
"retain_loss": 4.6253204345703125e-05,
"step": 350
},
{
"epoch": 1.3117370892018778,
"forget_loss": 8.487701416015625e-05,
"retain_loss": 5.030632019042969e-05,
"step": 350
},
{
"epoch": 1.3492957746478873,
"grad_norm": 0.01177978515625,
"learning_rate": 3.4046692607003896e-06,
"loss": 0.00012853145599365235,
"step": 360
},
{
"epoch": 1.3492957746478873,
"forget_loss": 0.00010395050048828125,
"retain_loss": 3.3855438232421875e-05,
"step": 360
},
{
"epoch": 1.3492957746478873,
"forget_loss": 9.250640869140625e-05,
"retain_loss": 4.553794860839844e-05,
"step": 360
},
{
"epoch": 1.3492957746478873,
"forget_loss": 7.009506225585938e-05,
"retain_loss": 5.6743621826171875e-05,
"step": 360
},
{
"epoch": 1.3492957746478873,
"forget_loss": 6.961822509765625e-05,
"retain_loss": 4.00543212890625e-05,
"step": 360
},
{
"epoch": 1.3868544600938968,
"grad_norm": 0.012451171875,
"learning_rate": 3.2101167315175102e-06,
"loss": 0.00012967586517333984,
"step": 370
},
{
"epoch": 1.3868544600938968,
"forget_loss": 8.296966552734375e-05,
"retain_loss": 5.435943603515625e-05,
"step": 370
},
{
"epoch": 1.3868544600938968,
"forget_loss": 7.581710815429688e-05,
"retain_loss": 3.647804260253906e-05,
"step": 370
},
{
"epoch": 1.3868544600938968,
"forget_loss": 7.05718994140625e-05,
"retain_loss": 3.075599670410156e-05,
"step": 370
},
{
"epoch": 1.3868544600938968,
"forget_loss": 7.104873657226562e-05,
"retain_loss": 0.00010776519775390625,
"step": 370
},
{
"epoch": 1.424413145539906,
"grad_norm": 0.0162353515625,
"learning_rate": 3.0155642023346305e-06,
"loss": 0.0001344442367553711,
"step": 380
},
{
"epoch": 1.424413145539906,
"forget_loss": 7.62939453125e-05,
"retain_loss": 5.793571472167969e-05,
"step": 380
},
{
"epoch": 1.424413145539906,
"forget_loss": 6.246566772460938e-05,
"retain_loss": 3.838539123535156e-05,
"step": 380
},
{
"epoch": 1.424413145539906,
"forget_loss": 0.00010538101196289062,
"retain_loss": 4.291534423828125e-05,
"step": 380
},
{
"epoch": 1.424413145539906,
"forget_loss": 7.009506225585938e-05,
"retain_loss": 4.482269287109375e-05,
"step": 380
},
{
"epoch": 1.4619718309859155,
"grad_norm": 0.00567626953125,
"learning_rate": 2.821011673151751e-06,
"loss": 0.00012153387069702148,
"step": 390
},
{
"epoch": 1.4619718309859155,
"forget_loss": 8.440017700195312e-05,
"retain_loss": 5.7697296142578125e-05,
"step": 390
},
{
"epoch": 1.4619718309859155,
"forget_loss": 7.390975952148438e-05,
"retain_loss": 5.793571472167969e-05,
"step": 390
},
{
"epoch": 1.4619718309859155,
"forget_loss": 9.489059448242188e-05,
"retain_loss": 3.647804260253906e-05,
"step": 390
},
{
"epoch": 1.4619718309859155,
"forget_loss": 9.059906005859375e-05,
"retain_loss": 3.504753112792969e-05,
"step": 390
},
{
"epoch": 1.4995305164319248,
"grad_norm": 0.0308837890625,
"learning_rate": 2.6264591439688717e-06,
"loss": 0.00013158321380615234,
"step": 400
},
{
"epoch": 1.4995305164319248,
"forget_loss": 6.29425048828125e-05,
"retain_loss": 4.4345855712890625e-05,
"step": 400
},
{
"epoch": 1.4995305164319248,
"forget_loss": 7.534027099609375e-05,
"retain_loss": 4.5299530029296875e-05,
"step": 400
},
{
"epoch": 1.4995305164319248,
"forget_loss": 6.580352783203125e-05,
"retain_loss": 4.673004150390625e-05,
"step": 400
},
{
"epoch": 1.4995305164319248,
"forget_loss": 6.961822509765625e-05,
"retain_loss": 4.887580871582031e-05,
"step": 400
},
{
"epoch": 1.5370892018779343,
"grad_norm": 0.0159912109375,
"learning_rate": 2.4319066147859924e-06,
"loss": 0.00012365579605102539,
"step": 410
},
{
"epoch": 1.5370892018779343,
"forget_loss": 6.031990051269531e-05,
"retain_loss": 3.266334533691406e-05,
"step": 410
},
{
"epoch": 1.5370892018779343,
"forget_loss": 8.296966552734375e-05,
"retain_loss": 6.151199340820312e-05,
"step": 410
},
{
"epoch": 1.5370892018779343,
"forget_loss": 6.771087646484375e-05,
"retain_loss": 4.673004150390625e-05,
"step": 410
},
{
"epoch": 1.5370892018779343,
"forget_loss": 6.532669067382812e-05,
"retain_loss": 4.2438507080078125e-05,
"step": 410
},
{
"epoch": 1.5746478873239438,
"grad_norm": 0.00909423828125,
"learning_rate": 2.237354085603113e-06,
"loss": 0.0001282811164855957,
"step": 420
},
{
"epoch": 1.5746478873239438,
"forget_loss": 6.532669067382812e-05,
"retain_loss": 3.0994415283203125e-05,
"step": 420
},
{
"epoch": 1.5746478873239438,
"forget_loss": 6.29425048828125e-05,
"retain_loss": 3.337860107421875e-05,
"step": 420
},
{
"epoch": 1.5746478873239438,
"forget_loss": 7.581710815429688e-05,
"retain_loss": 4.220008850097656e-05,
"step": 420
},
{
"epoch": 1.5746478873239438,
"forget_loss": 8.487701416015625e-05,
"retain_loss": 3.4809112548828125e-05,
"step": 420
},
{
"epoch": 1.612206572769953,
"grad_norm": 0.007720947265625,
"learning_rate": 2.0428015564202337e-06,
"loss": 0.0001214742660522461,
"step": 430
},
{
"epoch": 1.612206572769953,
"forget_loss": 6.198883056640625e-05,
"retain_loss": 4.839897155761719e-05,
"step": 430
},
{
"epoch": 1.612206572769953,
"forget_loss": 8.20159912109375e-05,
"retain_loss": 5.364418029785156e-05,
"step": 430
},
{
"epoch": 1.612206572769953,
"forget_loss": 6.914138793945312e-05,
"retain_loss": 5.626678466796875e-05,
"step": 430
},
{
"epoch": 1.612206572769953,
"forget_loss": 7.43865966796875e-05,
"retain_loss": 3.170967102050781e-05,
"step": 430
},
{
"epoch": 1.6497652582159623,
"grad_norm": 0.0157470703125,
"learning_rate": 1.8482490272373543e-06,
"loss": 0.00011962652206420898,
"step": 440
},
{
"epoch": 1.6497652582159623,
"forget_loss": 7.486343383789062e-05,
"retain_loss": 4.315376281738281e-05,
"step": 440
},
{
"epoch": 1.6497652582159623,
"forget_loss": 0.00011205673217773438,
"retain_loss": 7.724761962890625e-05,
"step": 440
},
{
"epoch": 1.6497652582159623,
"forget_loss": 0.00010013580322265625,
"retain_loss": 5.245208740234375e-05,
"step": 440
},
{
"epoch": 1.6497652582159623,
"forget_loss": 0.00010824203491210938,
"retain_loss": 5.2928924560546875e-05,
"step": 440
},
{
"epoch": 1.6873239436619718,
"grad_norm": 0.017822265625,
"learning_rate": 1.6536964980544747e-06,
"loss": 0.000124359130859375,
"step": 450
},
{
"epoch": 1.6873239436619718,
"forget_loss": 9.202957153320312e-05,
"retain_loss": 3.24249267578125e-05,
"step": 450
},
{
"epoch": 1.6873239436619718,
"forget_loss": 6.151199340820312e-05,
"retain_loss": 4.267692565917969e-05,
"step": 450
},
{
"epoch": 1.6873239436619718,
"forget_loss": 6.437301635742188e-05,
"retain_loss": 5.245208740234375e-05,
"step": 450
},
{
"epoch": 1.6873239436619718,
"forget_loss": 5.698204040527344e-05,
"retain_loss": 6.341934204101562e-05,
"step": 450
},
{
"epoch": 1.7248826291079813,
"grad_norm": 0.0067138671875,
"learning_rate": 1.4591439688715956e-06,
"loss": 0.00012021064758300781,
"step": 460
},
{
"epoch": 1.7248826291079813,
"forget_loss": 6.914138793945312e-05,
"retain_loss": 5.125999450683594e-05,
"step": 460
},
{
"epoch": 1.7248826291079813,
"forget_loss": 7.772445678710938e-05,
"retain_loss": 3.647804260253906e-05,
"step": 460
},
{
"epoch": 1.7248826291079813,
"forget_loss": 7.200241088867188e-05,
"retain_loss": 3.266334533691406e-05,
"step": 460
},
{
"epoch": 1.7248826291079813,
"forget_loss": 8.678436279296875e-05,
"retain_loss": 7.581710815429688e-05,
"step": 460
},
{
"epoch": 1.7624413145539906,
"grad_norm": 0.01202392578125,
"learning_rate": 1.264591439688716e-06,
"loss": 0.0001221299171447754,
"step": 470
},
{
"epoch": 1.7624413145539906,
"forget_loss": 8.678436279296875e-05,
"retain_loss": 4.363059997558594e-05,
"step": 470
},
{
"epoch": 1.7624413145539906,
"forget_loss": 6.723403930664062e-05,
"retain_loss": 3.337860107421875e-05,
"step": 470
},
{
"epoch": 1.7624413145539906,
"forget_loss": 7.343292236328125e-05,
"retain_loss": 8.249282836914062e-05,
"step": 470
},
{
"epoch": 1.7624413145539906,
"forget_loss": 7.581710815429688e-05,
"retain_loss": 2.682209014892578e-05,
"step": 470
},
{
"epoch": 1.8,
"grad_norm": 0.00830078125,
"learning_rate": 1.0700389105058367e-06,
"loss": 0.00011826753616333008,
"step": 480
},
{
"epoch": 1.8,
"forget_loss": 7.390975952148438e-05,
"retain_loss": 3.3855438232421875e-05,
"step": 480
},
{
"epoch": 1.8,
"forget_loss": 6.723403930664062e-05,
"retain_loss": 9.059906005859375e-05,
"step": 480
},
{
"epoch": 1.8,
"forget_loss": 8.0108642578125e-05,
"retain_loss": 4.7206878662109375e-05,
"step": 480
},
{
"epoch": 1.8,
"forget_loss": 6.151199340820312e-05,
"retain_loss": 4.76837158203125e-05,
"step": 480
},
{
"epoch": 1.8375586854460093,
"grad_norm": 0.0045166015625,
"learning_rate": 8.754863813229572e-07,
"loss": 0.00012172460556030274,
"step": 490
},
{
"epoch": 1.8375586854460093,
"forget_loss": 7.05718994140625e-05,
"retain_loss": 4.315376281738281e-05,
"step": 490
},
{
"epoch": 1.8375586854460093,
"forget_loss": 5.793571472167969e-05,
"retain_loss": 3.5762786865234375e-05,
"step": 490
},
{
"epoch": 1.8375586854460093,
"forget_loss": 6.008148193359375e-05,
"retain_loss": 3.4809112548828125e-05,
"step": 490
},
{
"epoch": 1.8375586854460093,
"forget_loss": 7.82012939453125e-05,
"retain_loss": 3.838539123535156e-05,
"step": 490
},
{
"epoch": 1.8751173708920188,
"grad_norm": 0.01422119140625,
"learning_rate": 6.809338521400779e-07,
"loss": 0.00011525154113769531,
"step": 500
},
{
"epoch": 1.8751173708920188,
"forget_loss": 6.818771362304688e-05,
"retain_loss": 3.838539123535156e-05,
"step": 500
},
{
"epoch": 1.8751173708920188,
"forget_loss": 9.489059448242188e-05,
"retain_loss": 8.58306884765625e-05,
"step": 500
},
{
"epoch": 1.8751173708920188,
"forget_loss": 9.298324584960938e-05,
"retain_loss": 4.4345855712890625e-05,
"step": 500
},
{
"epoch": 1.8751173708920188,
"forget_loss": 6.151199340820312e-05,
"retain_loss": 6.723403930664062e-05,
"step": 500
},
{
"epoch": 1.9126760563380283,
"grad_norm": 0.01080322265625,
"learning_rate": 4.863813229571985e-07,
"loss": 0.00011955499649047851,
"step": 510
},
{
"epoch": 1.9126760563380283,
"forget_loss": 7.62939453125e-05,
"retain_loss": 4.2438507080078125e-05,
"step": 510
},
{
"epoch": 1.9126760563380283,
"forget_loss": 8.630752563476562e-05,
"retain_loss": 4.863739013671875e-05,
"step": 510
},
{
"epoch": 1.9126760563380283,
"forget_loss": 8.96453857421875e-05,
"retain_loss": 5.1021575927734375e-05,
"step": 510
},
{
"epoch": 1.9126760563380283,
"forget_loss": 7.677078247070312e-05,
"retain_loss": 4.076957702636719e-05,
"step": 510
},
{
"epoch": 1.9502347417840376,
"grad_norm": 0.006256103515625,
"learning_rate": 2.918287937743191e-07,
"loss": 0.00011934041976928711,
"step": 520
},
{
"epoch": 1.9502347417840376,
"forget_loss": 7.152557373046875e-05,
"retain_loss": 5.8650970458984375e-05,
"step": 520
},
{
"epoch": 1.9502347417840376,
"forget_loss": 7.343292236328125e-05,
"retain_loss": 4.553794860839844e-05,
"step": 520
},
{
"epoch": 1.9502347417840376,
"forget_loss": 6.771087646484375e-05,
"retain_loss": 3.647804260253906e-05,
"step": 520
},
{
"epoch": 1.9502347417840376,
"forget_loss": 6.29425048828125e-05,
"retain_loss": 3.361701965332031e-05,
"step": 520
},
{
"epoch": 1.9877934272300468,
"grad_norm": 0.01611328125,
"learning_rate": 9.727626459143969e-08,
"loss": 0.00012475252151489258,
"step": 530
},
{
"epoch": 1.9877934272300468,
"forget_loss": 7.104873657226562e-05,
"retain_loss": 5.745887756347656e-05,
"step": 530
},
{
"epoch": 1.9877934272300468,
"forget_loss": 8.296966552734375e-05,
"retain_loss": 3.6716461181640625e-05,
"step": 530
},
{
"epoch": 1.9877934272300468,
"forget_loss": 6.818771362304688e-05,
"retain_loss": 5.1021575927734375e-05,
"step": 530
},
{
"epoch": 1.9877934272300468,
"forget_loss": 6.437301635742188e-05,
"retain_loss": 4.601478576660156e-05,
"step": 530
}
],
"logging_steps": 10,
"max_steps": 534,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 200,
"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
}