aleegis09's picture
Training in progress, step 200, checkpoint
cfc12bd verified
{
"best_metric": 0.5052040219306946,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.0856898029134533,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0004284490145672665,
"grad_norm": 0.228684201836586,
"learning_rate": 1e-05,
"loss": 0.5704,
"step": 1
},
{
"epoch": 0.0004284490145672665,
"eval_loss": 0.6628851890563965,
"eval_runtime": 212.6262,
"eval_samples_per_second": 18.488,
"eval_steps_per_second": 4.623,
"step": 1
},
{
"epoch": 0.000856898029134533,
"grad_norm": 0.3775286078453064,
"learning_rate": 2e-05,
"loss": 0.6377,
"step": 2
},
{
"epoch": 0.0012853470437017994,
"grad_norm": 0.35714787244796753,
"learning_rate": 3e-05,
"loss": 0.6371,
"step": 3
},
{
"epoch": 0.001713796058269066,
"grad_norm": 0.3277561664581299,
"learning_rate": 4e-05,
"loss": 0.5678,
"step": 4
},
{
"epoch": 0.0021422450728363325,
"grad_norm": 0.34369993209838867,
"learning_rate": 5e-05,
"loss": 0.6307,
"step": 5
},
{
"epoch": 0.002570694087403599,
"grad_norm": 0.3120614290237427,
"learning_rate": 6e-05,
"loss": 0.6045,
"step": 6
},
{
"epoch": 0.0029991431019708655,
"grad_norm": 0.33984777331352234,
"learning_rate": 7e-05,
"loss": 0.6314,
"step": 7
},
{
"epoch": 0.003427592116538132,
"grad_norm": 0.3129009008407593,
"learning_rate": 8e-05,
"loss": 0.6123,
"step": 8
},
{
"epoch": 0.0038560411311053984,
"grad_norm": 0.26182106137275696,
"learning_rate": 9e-05,
"loss": 0.572,
"step": 9
},
{
"epoch": 0.004284490145672665,
"grad_norm": 0.2655738890171051,
"learning_rate": 0.0001,
"loss": 0.5868,
"step": 10
},
{
"epoch": 0.004712939160239932,
"grad_norm": 0.2681911587715149,
"learning_rate": 9.999316524962345e-05,
"loss": 0.5773,
"step": 11
},
{
"epoch": 0.005141388174807198,
"grad_norm": 0.27197977900505066,
"learning_rate": 9.997266286704631e-05,
"loss": 0.5254,
"step": 12
},
{
"epoch": 0.005569837189374464,
"grad_norm": 0.2750822603702545,
"learning_rate": 9.993849845741524e-05,
"loss": 0.5189,
"step": 13
},
{
"epoch": 0.005998286203941731,
"grad_norm": 0.2820718586444855,
"learning_rate": 9.989068136093873e-05,
"loss": 0.5428,
"step": 14
},
{
"epoch": 0.006426735218508998,
"grad_norm": 0.2867220342159271,
"learning_rate": 9.98292246503335e-05,
"loss": 0.5554,
"step": 15
},
{
"epoch": 0.006855184233076264,
"grad_norm": 0.3037453591823578,
"learning_rate": 9.975414512725057e-05,
"loss": 0.5417,
"step": 16
},
{
"epoch": 0.00728363324764353,
"grad_norm": 0.27564892172813416,
"learning_rate": 9.966546331768191e-05,
"loss": 0.5407,
"step": 17
},
{
"epoch": 0.007712082262210797,
"grad_norm": 0.26989924907684326,
"learning_rate": 9.956320346634876e-05,
"loss": 0.5653,
"step": 18
},
{
"epoch": 0.008140531276778063,
"grad_norm": 0.32655712962150574,
"learning_rate": 9.944739353007344e-05,
"loss": 0.511,
"step": 19
},
{
"epoch": 0.00856898029134533,
"grad_norm": 0.25957199931144714,
"learning_rate": 9.931806517013612e-05,
"loss": 0.5805,
"step": 20
},
{
"epoch": 0.008997429305912597,
"grad_norm": 0.2876151502132416,
"learning_rate": 9.917525374361912e-05,
"loss": 0.5793,
"step": 21
},
{
"epoch": 0.009425878320479864,
"grad_norm": 0.26574990153312683,
"learning_rate": 9.901899829374047e-05,
"loss": 0.5387,
"step": 22
},
{
"epoch": 0.00985432733504713,
"grad_norm": 0.27396202087402344,
"learning_rate": 9.884934153917997e-05,
"loss": 0.6122,
"step": 23
},
{
"epoch": 0.010282776349614395,
"grad_norm": 0.24738654494285583,
"learning_rate": 9.86663298624003e-05,
"loss": 0.5163,
"step": 24
},
{
"epoch": 0.010711225364181662,
"grad_norm": 0.2576131820678711,
"learning_rate": 9.847001329696653e-05,
"loss": 0.5373,
"step": 25
},
{
"epoch": 0.011139674378748929,
"grad_norm": 0.24154862761497498,
"learning_rate": 9.826044551386744e-05,
"loss": 0.5542,
"step": 26
},
{
"epoch": 0.011568123393316195,
"grad_norm": 0.25771385431289673,
"learning_rate": 9.803768380684242e-05,
"loss": 0.5223,
"step": 27
},
{
"epoch": 0.011996572407883462,
"grad_norm": 0.24631132185459137,
"learning_rate": 9.780178907671789e-05,
"loss": 0.5434,
"step": 28
},
{
"epoch": 0.012425021422450729,
"grad_norm": 0.2378222942352295,
"learning_rate": 9.755282581475769e-05,
"loss": 0.5121,
"step": 29
},
{
"epoch": 0.012853470437017995,
"grad_norm": 0.2787817716598511,
"learning_rate": 9.729086208503174e-05,
"loss": 0.5472,
"step": 30
},
{
"epoch": 0.013281919451585262,
"grad_norm": 0.24504689872264862,
"learning_rate": 9.701596950580806e-05,
"loss": 0.5138,
"step": 31
},
{
"epoch": 0.013710368466152529,
"grad_norm": 0.2304796725511551,
"learning_rate": 9.672822322997305e-05,
"loss": 0.4399,
"step": 32
},
{
"epoch": 0.014138817480719794,
"grad_norm": 0.2308277040719986,
"learning_rate": 9.642770192448536e-05,
"loss": 0.4341,
"step": 33
},
{
"epoch": 0.01456726649528706,
"grad_norm": 0.2508942782878876,
"learning_rate": 9.611448774886924e-05,
"loss": 0.5344,
"step": 34
},
{
"epoch": 0.014995715509854327,
"grad_norm": 0.26426926255226135,
"learning_rate": 9.578866633275288e-05,
"loss": 0.4895,
"step": 35
},
{
"epoch": 0.015424164524421594,
"grad_norm": 0.2649156153202057,
"learning_rate": 9.545032675245813e-05,
"loss": 0.4995,
"step": 36
},
{
"epoch": 0.015852613538988862,
"grad_norm": 0.248934805393219,
"learning_rate": 9.509956150664796e-05,
"loss": 0.4715,
"step": 37
},
{
"epoch": 0.016281062553556127,
"grad_norm": 0.245437890291214,
"learning_rate": 9.473646649103818e-05,
"loss": 0.4491,
"step": 38
},
{
"epoch": 0.016709511568123392,
"grad_norm": 0.25285395979881287,
"learning_rate": 9.43611409721806e-05,
"loss": 0.4832,
"step": 39
},
{
"epoch": 0.01713796058269066,
"grad_norm": 0.24850432574748993,
"learning_rate": 9.397368756032445e-05,
"loss": 0.5504,
"step": 40
},
{
"epoch": 0.017566409597257925,
"grad_norm": 0.27029097080230713,
"learning_rate": 9.357421218136386e-05,
"loss": 0.5167,
"step": 41
},
{
"epoch": 0.017994858611825194,
"grad_norm": 0.2664126753807068,
"learning_rate": 9.316282404787871e-05,
"loss": 0.4809,
"step": 42
},
{
"epoch": 0.01842330762639246,
"grad_norm": 0.26534485816955566,
"learning_rate": 9.273963562927695e-05,
"loss": 0.4804,
"step": 43
},
{
"epoch": 0.018851756640959727,
"grad_norm": 0.3760368227958679,
"learning_rate": 9.230476262104677e-05,
"loss": 0.5311,
"step": 44
},
{
"epoch": 0.019280205655526992,
"grad_norm": 0.28610092401504517,
"learning_rate": 9.185832391312644e-05,
"loss": 0.4844,
"step": 45
},
{
"epoch": 0.01970865467009426,
"grad_norm": 0.2678817808628082,
"learning_rate": 9.140044155740101e-05,
"loss": 0.4829,
"step": 46
},
{
"epoch": 0.020137103684661525,
"grad_norm": 0.26977911591529846,
"learning_rate": 9.093124073433463e-05,
"loss": 0.4264,
"step": 47
},
{
"epoch": 0.02056555269922879,
"grad_norm": 0.31245163083076477,
"learning_rate": 9.045084971874738e-05,
"loss": 0.476,
"step": 48
},
{
"epoch": 0.02099400171379606,
"grad_norm": 0.2824503779411316,
"learning_rate": 8.995939984474624e-05,
"loss": 0.5589,
"step": 49
},
{
"epoch": 0.021422450728363324,
"grad_norm": 0.3318052291870117,
"learning_rate": 8.945702546981969e-05,
"loss": 0.4047,
"step": 50
},
{
"epoch": 0.021422450728363324,
"eval_loss": 0.5233702063560486,
"eval_runtime": 214.582,
"eval_samples_per_second": 18.319,
"eval_steps_per_second": 4.581,
"step": 50
},
{
"epoch": 0.021850899742930592,
"grad_norm": 0.15064652264118195,
"learning_rate": 8.894386393810563e-05,
"loss": 0.4372,
"step": 51
},
{
"epoch": 0.022279348757497857,
"grad_norm": 0.20386983454227448,
"learning_rate": 8.842005554284296e-05,
"loss": 0.5498,
"step": 52
},
{
"epoch": 0.022707797772065125,
"grad_norm": 2.4847986698150635,
"learning_rate": 8.788574348801675e-05,
"loss": 0.4945,
"step": 53
},
{
"epoch": 0.02313624678663239,
"grad_norm": 0.20311777293682098,
"learning_rate": 8.73410738492077e-05,
"loss": 0.5348,
"step": 54
},
{
"epoch": 0.02356469580119966,
"grad_norm": 0.2357204109430313,
"learning_rate": 8.678619553365659e-05,
"loss": 0.5865,
"step": 55
},
{
"epoch": 0.023993144815766924,
"grad_norm": 0.2169618010520935,
"learning_rate": 8.622126023955446e-05,
"loss": 0.5453,
"step": 56
},
{
"epoch": 0.02442159383033419,
"grad_norm": 0.18748903274536133,
"learning_rate": 8.564642241456986e-05,
"loss": 0.4958,
"step": 57
},
{
"epoch": 0.024850042844901457,
"grad_norm": 0.19831594824790955,
"learning_rate": 8.506183921362443e-05,
"loss": 0.5572,
"step": 58
},
{
"epoch": 0.025278491859468722,
"grad_norm": 0.1811814159154892,
"learning_rate": 8.44676704559283e-05,
"loss": 0.5235,
"step": 59
},
{
"epoch": 0.02570694087403599,
"grad_norm": 0.19561834633350372,
"learning_rate": 8.386407858128706e-05,
"loss": 0.4957,
"step": 60
},
{
"epoch": 0.026135389888603255,
"grad_norm": 0.2204512506723404,
"learning_rate": 8.32512286056924e-05,
"loss": 0.5922,
"step": 61
},
{
"epoch": 0.026563838903170524,
"grad_norm": 0.17718099057674408,
"learning_rate": 8.262928807620843e-05,
"loss": 0.4556,
"step": 62
},
{
"epoch": 0.02699228791773779,
"grad_norm": 0.2117452174425125,
"learning_rate": 8.199842702516583e-05,
"loss": 0.5375,
"step": 63
},
{
"epoch": 0.027420736932305057,
"grad_norm": 0.2319151908159256,
"learning_rate": 8.135881792367686e-05,
"loss": 0.5579,
"step": 64
},
{
"epoch": 0.027849185946872322,
"grad_norm": 0.19332152605056763,
"learning_rate": 8.07106356344834e-05,
"loss": 0.5133,
"step": 65
},
{
"epoch": 0.028277634961439587,
"grad_norm": 0.21406444907188416,
"learning_rate": 8.005405736415126e-05,
"loss": 0.5307,
"step": 66
},
{
"epoch": 0.028706083976006855,
"grad_norm": 0.23117361962795258,
"learning_rate": 7.938926261462366e-05,
"loss": 0.54,
"step": 67
},
{
"epoch": 0.02913453299057412,
"grad_norm": 0.21088655292987823,
"learning_rate": 7.871643313414718e-05,
"loss": 0.5812,
"step": 68
},
{
"epoch": 0.02956298200514139,
"grad_norm": 0.20900338888168335,
"learning_rate": 7.803575286758364e-05,
"loss": 0.5061,
"step": 69
},
{
"epoch": 0.029991431019708654,
"grad_norm": 0.22404471039772034,
"learning_rate": 7.734740790612136e-05,
"loss": 0.5556,
"step": 70
},
{
"epoch": 0.030419880034275922,
"grad_norm": 0.20459339022636414,
"learning_rate": 7.66515864363997e-05,
"loss": 0.5004,
"step": 71
},
{
"epoch": 0.030848329048843187,
"grad_norm": 0.2245027720928192,
"learning_rate": 7.594847868906076e-05,
"loss": 0.5351,
"step": 72
},
{
"epoch": 0.031276778063410456,
"grad_norm": 0.18311403691768646,
"learning_rate": 7.52382768867422e-05,
"loss": 0.4642,
"step": 73
},
{
"epoch": 0.031705227077977724,
"grad_norm": 0.21955837309360504,
"learning_rate": 7.452117519152542e-05,
"loss": 0.5077,
"step": 74
},
{
"epoch": 0.032133676092544985,
"grad_norm": 0.2084721326828003,
"learning_rate": 7.379736965185368e-05,
"loss": 0.5319,
"step": 75
},
{
"epoch": 0.032562125107112254,
"grad_norm": 0.21330246329307556,
"learning_rate": 7.30670581489344e-05,
"loss": 0.5585,
"step": 76
},
{
"epoch": 0.03299057412167952,
"grad_norm": 0.24155814945697784,
"learning_rate": 7.233044034264034e-05,
"loss": 0.54,
"step": 77
},
{
"epoch": 0.033419023136246784,
"grad_norm": 0.2249860167503357,
"learning_rate": 7.158771761692464e-05,
"loss": 0.553,
"step": 78
},
{
"epoch": 0.03384747215081405,
"grad_norm": 0.2181163728237152,
"learning_rate": 7.083909302476453e-05,
"loss": 0.5347,
"step": 79
},
{
"epoch": 0.03427592116538132,
"grad_norm": 0.20594443380832672,
"learning_rate": 7.008477123264848e-05,
"loss": 0.5072,
"step": 80
},
{
"epoch": 0.03470437017994859,
"grad_norm": 0.20609448850154877,
"learning_rate": 6.932495846462261e-05,
"loss": 0.4803,
"step": 81
},
{
"epoch": 0.03513281919451585,
"grad_norm": 0.22857272624969482,
"learning_rate": 6.855986244591104e-05,
"loss": 0.5394,
"step": 82
},
{
"epoch": 0.03556126820908312,
"grad_norm": 0.21896202862262726,
"learning_rate": 6.778969234612584e-05,
"loss": 0.5107,
"step": 83
},
{
"epoch": 0.03598971722365039,
"grad_norm": 0.23790735006332397,
"learning_rate": 6.701465872208216e-05,
"loss": 0.5915,
"step": 84
},
{
"epoch": 0.03641816623821765,
"grad_norm": 0.2318210005760193,
"learning_rate": 6.623497346023418e-05,
"loss": 0.5167,
"step": 85
},
{
"epoch": 0.03684661525278492,
"grad_norm": 0.2057870477437973,
"learning_rate": 6.545084971874738e-05,
"loss": 0.47,
"step": 86
},
{
"epoch": 0.037275064267352186,
"grad_norm": 0.2366434782743454,
"learning_rate": 6.466250186922325e-05,
"loss": 0.5018,
"step": 87
},
{
"epoch": 0.037703513281919454,
"grad_norm": 0.2103012651205063,
"learning_rate": 6.387014543809223e-05,
"loss": 0.5134,
"step": 88
},
{
"epoch": 0.038131962296486716,
"grad_norm": 0.21713051199913025,
"learning_rate": 6.307399704769099e-05,
"loss": 0.4617,
"step": 89
},
{
"epoch": 0.038560411311053984,
"grad_norm": 0.21644674241542816,
"learning_rate": 6.227427435703997e-05,
"loss": 0.4271,
"step": 90
},
{
"epoch": 0.03898886032562125,
"grad_norm": 0.2307886928319931,
"learning_rate": 6.147119600233758e-05,
"loss": 0.5383,
"step": 91
},
{
"epoch": 0.03941730934018852,
"grad_norm": 0.24658828973770142,
"learning_rate": 6.066498153718735e-05,
"loss": 0.4651,
"step": 92
},
{
"epoch": 0.03984575835475578,
"grad_norm": 0.24504642188549042,
"learning_rate": 5.985585137257401e-05,
"loss": 0.5077,
"step": 93
},
{
"epoch": 0.04027420736932305,
"grad_norm": 0.22446109354496002,
"learning_rate": 5.90440267166055e-05,
"loss": 0.4376,
"step": 94
},
{
"epoch": 0.04070265638389032,
"grad_norm": 0.2468467354774475,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.4683,
"step": 95
},
{
"epoch": 0.04113110539845758,
"grad_norm": 0.25989946722984314,
"learning_rate": 5.74131823855921e-05,
"loss": 0.4697,
"step": 96
},
{
"epoch": 0.04155955441302485,
"grad_norm": 0.25286898016929626,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.4461,
"step": 97
},
{
"epoch": 0.04198800342759212,
"grad_norm": 0.3009304702281952,
"learning_rate": 5.577423184847932e-05,
"loss": 0.4282,
"step": 98
},
{
"epoch": 0.042416452442159386,
"grad_norm": 0.2842262387275696,
"learning_rate": 5.495227651252315e-05,
"loss": 0.4702,
"step": 99
},
{
"epoch": 0.04284490145672665,
"grad_norm": 0.30349037051200867,
"learning_rate": 5.4128967273616625e-05,
"loss": 0.4609,
"step": 100
},
{
"epoch": 0.04284490145672665,
"eval_loss": 0.5112596750259399,
"eval_runtime": 214.5352,
"eval_samples_per_second": 18.323,
"eval_steps_per_second": 4.582,
"step": 100
},
{
"epoch": 0.043273350471293916,
"grad_norm": 0.13782167434692383,
"learning_rate": 5.330452921628497e-05,
"loss": 0.4901,
"step": 101
},
{
"epoch": 0.043701799485861184,
"grad_norm": 0.15800629556179047,
"learning_rate": 5.247918773366112e-05,
"loss": 0.4876,
"step": 102
},
{
"epoch": 0.044130248500428446,
"grad_norm": 0.16718293726444244,
"learning_rate": 5.165316846586541e-05,
"loss": 0.4929,
"step": 103
},
{
"epoch": 0.044558697514995714,
"grad_norm": 0.17278578877449036,
"learning_rate": 5.0826697238317935e-05,
"loss": 0.4784,
"step": 104
},
{
"epoch": 0.04498714652956298,
"grad_norm": 0.17230898141860962,
"learning_rate": 5e-05,
"loss": 0.5082,
"step": 105
},
{
"epoch": 0.04541559554413025,
"grad_norm": 0.18225736916065216,
"learning_rate": 4.917330276168208e-05,
"loss": 0.5359,
"step": 106
},
{
"epoch": 0.04584404455869751,
"grad_norm": 0.21700350940227509,
"learning_rate": 4.834683153413459e-05,
"loss": 0.5876,
"step": 107
},
{
"epoch": 0.04627249357326478,
"grad_norm": 0.1705765277147293,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.5237,
"step": 108
},
{
"epoch": 0.04670094258783205,
"grad_norm": 0.1833975464105606,
"learning_rate": 4.669547078371504e-05,
"loss": 0.5207,
"step": 109
},
{
"epoch": 0.04712939160239932,
"grad_norm": 0.18565508723258972,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.5221,
"step": 110
},
{
"epoch": 0.04755784061696658,
"grad_norm": 0.1933288723230362,
"learning_rate": 4.504772348747687e-05,
"loss": 0.5597,
"step": 111
},
{
"epoch": 0.04798628963153385,
"grad_norm": 0.18125350773334503,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.4675,
"step": 112
},
{
"epoch": 0.048414738646101116,
"grad_norm": 0.18038061261177063,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.5156,
"step": 113
},
{
"epoch": 0.04884318766066838,
"grad_norm": 0.1880904734134674,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.4652,
"step": 114
},
{
"epoch": 0.049271636675235646,
"grad_norm": 0.18711797893047333,
"learning_rate": 4.17702704859633e-05,
"loss": 0.5126,
"step": 115
},
{
"epoch": 0.049700085689802914,
"grad_norm": 0.2136799395084381,
"learning_rate": 4.095597328339452e-05,
"loss": 0.516,
"step": 116
},
{
"epoch": 0.05012853470437018,
"grad_norm": 0.2224310338497162,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.548,
"step": 117
},
{
"epoch": 0.050556983718937444,
"grad_norm": 0.20538875460624695,
"learning_rate": 3.933501846281267e-05,
"loss": 0.5276,
"step": 118
},
{
"epoch": 0.05098543273350471,
"grad_norm": 0.19813616573810577,
"learning_rate": 3.852880399766243e-05,
"loss": 0.5112,
"step": 119
},
{
"epoch": 0.05141388174807198,
"grad_norm": 0.20466867089271545,
"learning_rate": 3.772572564296005e-05,
"loss": 0.5438,
"step": 120
},
{
"epoch": 0.05184233076263925,
"grad_norm": 0.19969195127487183,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.5154,
"step": 121
},
{
"epoch": 0.05227077977720651,
"grad_norm": 0.20950540900230408,
"learning_rate": 3.612985456190778e-05,
"loss": 0.5391,
"step": 122
},
{
"epoch": 0.05269922879177378,
"grad_norm": 0.21470077335834503,
"learning_rate": 3.533749813077677e-05,
"loss": 0.4861,
"step": 123
},
{
"epoch": 0.05312767780634105,
"grad_norm": 0.2217790186405182,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.4877,
"step": 124
},
{
"epoch": 0.05355612682090831,
"grad_norm": 0.22476041316986084,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.4828,
"step": 125
},
{
"epoch": 0.05398457583547558,
"grad_norm": 0.2222987711429596,
"learning_rate": 3.298534127791785e-05,
"loss": 0.5521,
"step": 126
},
{
"epoch": 0.054413024850042846,
"grad_norm": 0.21620109677314758,
"learning_rate": 3.221030765387417e-05,
"loss": 0.5587,
"step": 127
},
{
"epoch": 0.054841473864610114,
"grad_norm": 0.21934475004673004,
"learning_rate": 3.144013755408895e-05,
"loss": 0.5476,
"step": 128
},
{
"epoch": 0.055269922879177376,
"grad_norm": 0.2131243795156479,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.5333,
"step": 129
},
{
"epoch": 0.055698371893744644,
"grad_norm": 0.23393143713474274,
"learning_rate": 2.991522876735154e-05,
"loss": 0.4969,
"step": 130
},
{
"epoch": 0.05612682090831191,
"grad_norm": 0.2110367864370346,
"learning_rate": 2.916090697523549e-05,
"loss": 0.506,
"step": 131
},
{
"epoch": 0.056555269922879174,
"grad_norm": 0.21449963748455048,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.5089,
"step": 132
},
{
"epoch": 0.05698371893744644,
"grad_norm": 0.23367688059806824,
"learning_rate": 2.766955965735968e-05,
"loss": 0.5119,
"step": 133
},
{
"epoch": 0.05741216795201371,
"grad_norm": 0.21595382690429688,
"learning_rate": 2.693294185106562e-05,
"loss": 0.4819,
"step": 134
},
{
"epoch": 0.05784061696658098,
"grad_norm": 0.24128954112529755,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.5112,
"step": 135
},
{
"epoch": 0.05826906598114824,
"grad_norm": 0.22256414592266083,
"learning_rate": 2.547882480847461e-05,
"loss": 0.5443,
"step": 136
},
{
"epoch": 0.05869751499571551,
"grad_norm": 0.24305784702301025,
"learning_rate": 2.476172311325783e-05,
"loss": 0.5491,
"step": 137
},
{
"epoch": 0.05912596401028278,
"grad_norm": 0.2417302131652832,
"learning_rate": 2.405152131093926e-05,
"loss": 0.5491,
"step": 138
},
{
"epoch": 0.059554413024850046,
"grad_norm": 0.20851919054985046,
"learning_rate": 2.3348413563600325e-05,
"loss": 0.4858,
"step": 139
},
{
"epoch": 0.05998286203941731,
"grad_norm": 0.24059560894966125,
"learning_rate": 2.2652592093878666e-05,
"loss": 0.4792,
"step": 140
},
{
"epoch": 0.060411311053984576,
"grad_norm": 0.23226527869701385,
"learning_rate": 2.196424713241637e-05,
"loss": 0.52,
"step": 141
},
{
"epoch": 0.060839760068551844,
"grad_norm": 0.22085663676261902,
"learning_rate": 2.128356686585282e-05,
"loss": 0.4451,
"step": 142
},
{
"epoch": 0.061268209083119106,
"grad_norm": 0.22734583914279938,
"learning_rate": 2.061073738537635e-05,
"loss": 0.4449,
"step": 143
},
{
"epoch": 0.061696658097686374,
"grad_norm": 0.24727202951908112,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.4737,
"step": 144
},
{
"epoch": 0.06212510711225364,
"grad_norm": 0.2426474243402481,
"learning_rate": 1.928936436551661e-05,
"loss": 0.4693,
"step": 145
},
{
"epoch": 0.06255355612682091,
"grad_norm": 0.23192164301872253,
"learning_rate": 1.8641182076323148e-05,
"loss": 0.4375,
"step": 146
},
{
"epoch": 0.06298200514138817,
"grad_norm": 0.2658597528934479,
"learning_rate": 1.800157297483417e-05,
"loss": 0.4798,
"step": 147
},
{
"epoch": 0.06341045415595545,
"grad_norm": 0.2557027339935303,
"learning_rate": 1.7370711923791567e-05,
"loss": 0.4726,
"step": 148
},
{
"epoch": 0.06383890317052271,
"grad_norm": 0.25804585218429565,
"learning_rate": 1.6748771394307585e-05,
"loss": 0.3949,
"step": 149
},
{
"epoch": 0.06426735218508997,
"grad_norm": 0.275905042886734,
"learning_rate": 1.6135921418712956e-05,
"loss": 0.4108,
"step": 150
},
{
"epoch": 0.06426735218508997,
"eval_loss": 0.5062534213066101,
"eval_runtime": 214.8248,
"eval_samples_per_second": 18.299,
"eval_steps_per_second": 4.576,
"step": 150
},
{
"epoch": 0.06469580119965725,
"grad_norm": 0.12356305122375488,
"learning_rate": 1.553232954407171e-05,
"loss": 0.4292,
"step": 151
},
{
"epoch": 0.06512425021422451,
"grad_norm": 0.17837627232074738,
"learning_rate": 1.4938160786375572e-05,
"loss": 0.5327,
"step": 152
},
{
"epoch": 0.06555269922879177,
"grad_norm": 0.1691794991493225,
"learning_rate": 1.435357758543015e-05,
"loss": 0.5586,
"step": 153
},
{
"epoch": 0.06598114824335904,
"grad_norm": 0.1637227088212967,
"learning_rate": 1.3778739760445552e-05,
"loss": 0.4833,
"step": 154
},
{
"epoch": 0.0664095972579263,
"grad_norm": 0.17156657576560974,
"learning_rate": 1.3213804466343421e-05,
"loss": 0.4976,
"step": 155
},
{
"epoch": 0.06683804627249357,
"grad_norm": 0.17756806313991547,
"learning_rate": 1.2658926150792322e-05,
"loss": 0.4562,
"step": 156
},
{
"epoch": 0.06726649528706084,
"grad_norm": 0.189994215965271,
"learning_rate": 1.2114256511983274e-05,
"loss": 0.49,
"step": 157
},
{
"epoch": 0.0676949443016281,
"grad_norm": 0.19219642877578735,
"learning_rate": 1.157994445715706e-05,
"loss": 0.4925,
"step": 158
},
{
"epoch": 0.06812339331619537,
"grad_norm": 0.18906882405281067,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.5225,
"step": 159
},
{
"epoch": 0.06855184233076264,
"grad_norm": 0.17764447629451752,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.4783,
"step": 160
},
{
"epoch": 0.0689802913453299,
"grad_norm": 0.19509181380271912,
"learning_rate": 1.0040600155253765e-05,
"loss": 0.5781,
"step": 161
},
{
"epoch": 0.06940874035989718,
"grad_norm": 0.1957414448261261,
"learning_rate": 9.549150281252633e-06,
"loss": 0.5117,
"step": 162
},
{
"epoch": 0.06983718937446444,
"grad_norm": 0.18858219683170319,
"learning_rate": 9.068759265665384e-06,
"loss": 0.4528,
"step": 163
},
{
"epoch": 0.0702656383890317,
"grad_norm": 0.19822679460048676,
"learning_rate": 8.599558442598998e-06,
"loss": 0.4929,
"step": 164
},
{
"epoch": 0.07069408740359898,
"grad_norm": 0.18546193838119507,
"learning_rate": 8.141676086873572e-06,
"loss": 0.5002,
"step": 165
},
{
"epoch": 0.07112253641816624,
"grad_norm": 0.20249854028224945,
"learning_rate": 7.695237378953223e-06,
"loss": 0.5415,
"step": 166
},
{
"epoch": 0.0715509854327335,
"grad_norm": 0.19854749739170074,
"learning_rate": 7.260364370723044e-06,
"loss": 0.4906,
"step": 167
},
{
"epoch": 0.07197943444730077,
"grad_norm": 0.20104508101940155,
"learning_rate": 6.837175952121306e-06,
"loss": 0.5106,
"step": 168
},
{
"epoch": 0.07240788346186804,
"grad_norm": 0.19187435507774353,
"learning_rate": 6.425787818636131e-06,
"loss": 0.4818,
"step": 169
},
{
"epoch": 0.0728363324764353,
"grad_norm": 0.20160090923309326,
"learning_rate": 6.026312439675552e-06,
"loss": 0.4764,
"step": 170
},
{
"epoch": 0.07326478149100257,
"grad_norm": 0.2078496366739273,
"learning_rate": 5.6388590278194096e-06,
"loss": 0.5491,
"step": 171
},
{
"epoch": 0.07369323050556983,
"grad_norm": 0.20284205675125122,
"learning_rate": 5.263533508961827e-06,
"loss": 0.55,
"step": 172
},
{
"epoch": 0.07412167952013711,
"grad_norm": 0.23124438524246216,
"learning_rate": 4.900438493352055e-06,
"loss": 0.5559,
"step": 173
},
{
"epoch": 0.07455012853470437,
"grad_norm": 0.19652493298053741,
"learning_rate": 4.549673247541875e-06,
"loss": 0.5053,
"step": 174
},
{
"epoch": 0.07497857754927163,
"grad_norm": 0.19624044001102448,
"learning_rate": 4.2113336672471245e-06,
"loss": 0.455,
"step": 175
},
{
"epoch": 0.07540702656383891,
"grad_norm": 0.21186797320842743,
"learning_rate": 3.885512251130763e-06,
"loss": 0.533,
"step": 176
},
{
"epoch": 0.07583547557840617,
"grad_norm": 0.21794423460960388,
"learning_rate": 3.5722980755146517e-06,
"loss": 0.4801,
"step": 177
},
{
"epoch": 0.07626392459297343,
"grad_norm": 0.2287568598985672,
"learning_rate": 3.271776770026963e-06,
"loss": 0.5806,
"step": 178
},
{
"epoch": 0.0766923736075407,
"grad_norm": 0.2035348117351532,
"learning_rate": 2.9840304941919415e-06,
"loss": 0.4855,
"step": 179
},
{
"epoch": 0.07712082262210797,
"grad_norm": 0.21081854403018951,
"learning_rate": 2.7091379149682685e-06,
"loss": 0.4787,
"step": 180
},
{
"epoch": 0.07754927163667523,
"grad_norm": 0.21942371129989624,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.5068,
"step": 181
},
{
"epoch": 0.0779777206512425,
"grad_norm": 0.21645888686180115,
"learning_rate": 2.1982109232821178e-06,
"loss": 0.5106,
"step": 182
},
{
"epoch": 0.07840616966580977,
"grad_norm": 0.23054279386997223,
"learning_rate": 1.962316193157593e-06,
"loss": 0.5188,
"step": 183
},
{
"epoch": 0.07883461868037704,
"grad_norm": 0.2399861216545105,
"learning_rate": 1.7395544861325718e-06,
"loss": 0.5023,
"step": 184
},
{
"epoch": 0.0792630676949443,
"grad_norm": 0.23975235223770142,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.564,
"step": 185
},
{
"epoch": 0.07969151670951156,
"grad_norm": 0.21397042274475098,
"learning_rate": 1.333670137599713e-06,
"loss": 0.4383,
"step": 186
},
{
"epoch": 0.08011996572407884,
"grad_norm": 0.22963669896125793,
"learning_rate": 1.1506584608200367e-06,
"loss": 0.4878,
"step": 187
},
{
"epoch": 0.0805484147386461,
"grad_norm": 0.22737430036067963,
"learning_rate": 9.810017062595322e-07,
"loss": 0.4714,
"step": 188
},
{
"epoch": 0.08097686375321336,
"grad_norm": 0.21495851874351501,
"learning_rate": 8.247462563808817e-07,
"loss": 0.502,
"step": 189
},
{
"epoch": 0.08140531276778064,
"grad_norm": 0.22086374461650848,
"learning_rate": 6.819348298638839e-07,
"loss": 0.4809,
"step": 190
},
{
"epoch": 0.0818337617823479,
"grad_norm": 0.21731896698474884,
"learning_rate": 5.526064699265753e-07,
"loss": 0.4487,
"step": 191
},
{
"epoch": 0.08226221079691516,
"grad_norm": 0.21713416278362274,
"learning_rate": 4.367965336512403e-07,
"loss": 0.5047,
"step": 192
},
{
"epoch": 0.08269065981148244,
"grad_norm": 0.2234414517879486,
"learning_rate": 3.3453668231809286e-07,
"loss": 0.4845,
"step": 193
},
{
"epoch": 0.0831191088260497,
"grad_norm": 0.23213472962379456,
"learning_rate": 2.458548727494292e-07,
"loss": 0.4695,
"step": 194
},
{
"epoch": 0.08354755784061697,
"grad_norm": 0.23573216795921326,
"learning_rate": 1.7077534966650766e-07,
"loss": 0.4251,
"step": 195
},
{
"epoch": 0.08397600685518423,
"grad_norm": 0.229087695479393,
"learning_rate": 1.0931863906127327e-07,
"loss": 0.4232,
"step": 196
},
{
"epoch": 0.0844044558697515,
"grad_norm": 0.25884193181991577,
"learning_rate": 6.150154258476315e-08,
"loss": 0.4492,
"step": 197
},
{
"epoch": 0.08483290488431877,
"grad_norm": 0.2584173083305359,
"learning_rate": 2.7337132953697554e-08,
"loss": 0.4588,
"step": 198
},
{
"epoch": 0.08526135389888603,
"grad_norm": 0.2601085305213928,
"learning_rate": 6.834750376549792e-09,
"loss": 0.4348,
"step": 199
},
{
"epoch": 0.0856898029134533,
"grad_norm": 0.32536494731903076,
"learning_rate": 0.0,
"loss": 0.4901,
"step": 200
},
{
"epoch": 0.0856898029134533,
"eval_loss": 0.5052040219306946,
"eval_runtime": 214.9884,
"eval_samples_per_second": 18.285,
"eval_steps_per_second": 4.572,
"step": 200
}
],
"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": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.2903966892149965e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}