SmolLM2-360M-sft / trainer_state.json
wassname's picture
End of training
f0a6d5f verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 200,
"global_step": 762,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003940886699507389,
"grad_norm": 1.078125,
"learning_rate": 0.0,
"loss": 1.7215,
"step": 1
},
{
"epoch": 0.019704433497536946,
"grad_norm": 1.078125,
"learning_rate": 1.038961038961039e-05,
"loss": 1.7672,
"step": 5
},
{
"epoch": 0.03940886699507389,
"grad_norm": 0.99609375,
"learning_rate": 2.3376623376623376e-05,
"loss": 1.7749,
"step": 10
},
{
"epoch": 0.059113300492610835,
"grad_norm": 0.8828125,
"learning_rate": 3.6363636363636364e-05,
"loss": 1.7334,
"step": 15
},
{
"epoch": 0.07881773399014778,
"grad_norm": 0.796875,
"learning_rate": 4.9350649350649355e-05,
"loss": 1.7012,
"step": 20
},
{
"epoch": 0.09852216748768473,
"grad_norm": 0.59765625,
"learning_rate": 6.233766233766233e-05,
"loss": 1.6683,
"step": 25
},
{
"epoch": 0.11822660098522167,
"grad_norm": 0.4765625,
"learning_rate": 7.532467532467533e-05,
"loss": 1.6283,
"step": 30
},
{
"epoch": 0.13793103448275862,
"grad_norm": 0.341796875,
"learning_rate": 8.831168831168831e-05,
"loss": 1.5815,
"step": 35
},
{
"epoch": 0.15763546798029557,
"grad_norm": 0.2578125,
"learning_rate": 0.0001012987012987013,
"loss": 1.5755,
"step": 40
},
{
"epoch": 0.17733990147783252,
"grad_norm": 0.2177734375,
"learning_rate": 0.00011428571428571428,
"loss": 1.5314,
"step": 45
},
{
"epoch": 0.19704433497536947,
"grad_norm": 0.185546875,
"learning_rate": 0.00012727272727272728,
"loss": 1.5258,
"step": 50
},
{
"epoch": 0.21674876847290642,
"grad_norm": 0.1611328125,
"learning_rate": 0.00014025974025974028,
"loss": 1.5131,
"step": 55
},
{
"epoch": 0.23645320197044334,
"grad_norm": 0.1484375,
"learning_rate": 0.00015324675324675325,
"loss": 1.498,
"step": 60
},
{
"epoch": 0.2561576354679803,
"grad_norm": 0.1455078125,
"learning_rate": 0.00016623376623376625,
"loss": 1.4953,
"step": 65
},
{
"epoch": 0.27586206896551724,
"grad_norm": 0.1318359375,
"learning_rate": 0.00017922077922077922,
"loss": 1.4889,
"step": 70
},
{
"epoch": 0.2955665024630542,
"grad_norm": 0.1279296875,
"learning_rate": 0.00019220779220779222,
"loss": 1.4768,
"step": 75
},
{
"epoch": 0.31527093596059114,
"grad_norm": 0.12158203125,
"learning_rate": 0.00019999579326114222,
"loss": 1.4826,
"step": 80
},
{
"epoch": 0.33497536945812806,
"grad_norm": 0.1259765625,
"learning_rate": 0.00019994847151359784,
"loss": 1.4514,
"step": 85
},
{
"epoch": 0.35467980295566504,
"grad_norm": 0.115234375,
"learning_rate": 0.0001998485945607536,
"loss": 1.469,
"step": 90
},
{
"epoch": 0.37438423645320196,
"grad_norm": 0.11865234375,
"learning_rate": 0.00019969621492020869,
"loss": 1.4381,
"step": 95
},
{
"epoch": 0.39408866995073893,
"grad_norm": 0.12890625,
"learning_rate": 0.00019949141271668306,
"loss": 1.4513,
"step": 100
},
{
"epoch": 0.41379310344827586,
"grad_norm": 0.107421875,
"learning_rate": 0.00019923429563988614,
"loss": 1.4403,
"step": 105
},
{
"epoch": 0.43349753694581283,
"grad_norm": 0.1083984375,
"learning_rate": 0.00019892499888789098,
"loss": 1.4521,
"step": 110
},
{
"epoch": 0.45320197044334976,
"grad_norm": 0.12158203125,
"learning_rate": 0.00019856368509604412,
"loss": 1.4494,
"step": 115
},
{
"epoch": 0.4729064039408867,
"grad_norm": 0.115234375,
"learning_rate": 0.00019815054425144815,
"loss": 1.4289,
"step": 120
},
{
"epoch": 0.49261083743842365,
"grad_norm": 0.1103515625,
"learning_rate": 0.00019768579359306205,
"loss": 1.4261,
"step": 125
},
{
"epoch": 0.5123152709359606,
"grad_norm": 0.1123046875,
"learning_rate": 0.00019716967749747207,
"loss": 1.4212,
"step": 130
},
{
"epoch": 0.5320197044334976,
"grad_norm": 0.1044921875,
"learning_rate": 0.00019660246735039266,
"loss": 1.4517,
"step": 135
},
{
"epoch": 0.5517241379310345,
"grad_norm": 0.1171875,
"learning_rate": 0.00019598446140396605,
"loss": 1.4208,
"step": 140
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.1103515625,
"learning_rate": 0.00019531598461993392,
"loss": 1.4357,
"step": 145
},
{
"epoch": 0.5911330049261084,
"grad_norm": 0.1015625,
"learning_rate": 0.00019459738849876543,
"loss": 1.4108,
"step": 150
},
{
"epoch": 0.6108374384236454,
"grad_norm": 0.11376953125,
"learning_rate": 0.00019382905089482995,
"loss": 1.4396,
"step": 155
},
{
"epoch": 0.6305418719211823,
"grad_norm": 0.0986328125,
"learning_rate": 0.00019301137581771266,
"loss": 1.4114,
"step": 160
},
{
"epoch": 0.6502463054187192,
"grad_norm": 0.10302734375,
"learning_rate": 0.00019214479321977697,
"loss": 1.4221,
"step": 165
},
{
"epoch": 0.6699507389162561,
"grad_norm": 0.10400390625,
"learning_rate": 0.00019122975877008567,
"loss": 1.4234,
"step": 170
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.1044921875,
"learning_rate": 0.00019026675361479969,
"loss": 1.4378,
"step": 175
},
{
"epoch": 0.7093596059113301,
"grad_norm": 0.10400390625,
"learning_rate": 0.0001892562841241804,
"loss": 1.4178,
"step": 180
},
{
"epoch": 0.729064039408867,
"grad_norm": 0.10693359375,
"learning_rate": 0.00018819888162632838,
"loss": 1.4221,
"step": 185
},
{
"epoch": 0.7487684729064039,
"grad_norm": 0.1005859375,
"learning_rate": 0.00018709510212779903,
"loss": 1.4267,
"step": 190
},
{
"epoch": 0.7684729064039408,
"grad_norm": 0.107421875,
"learning_rate": 0.0001859455260212414,
"loss": 1.4226,
"step": 195
},
{
"epoch": 0.7881773399014779,
"grad_norm": 0.10986328125,
"learning_rate": 0.00018475075778021438,
"loss": 1.4328,
"step": 200
},
{
"epoch": 0.7881773399014779,
"eval_loss": 1.4307746887207031,
"eval_runtime": 143.9646,
"eval_samples_per_second": 50.116,
"eval_steps_per_second": 3.133,
"step": 200
},
{
"epoch": 0.8078817733990148,
"grad_norm": 0.10009765625,
"learning_rate": 0.00018351142564134078,
"loss": 1.4341,
"step": 205
},
{
"epoch": 0.8275862068965517,
"grad_norm": 0.0966796875,
"learning_rate": 0.0001822281812739659,
"loss": 1.4172,
"step": 210
},
{
"epoch": 0.8472906403940886,
"grad_norm": 0.10009765625,
"learning_rate": 0.00018090169943749476,
"loss": 1.41,
"step": 215
},
{
"epoch": 0.8669950738916257,
"grad_norm": 0.10400390625,
"learning_rate": 0.00017953267762658827,
"loss": 1.4099,
"step": 220
},
{
"epoch": 0.8866995073891626,
"grad_norm": 0.099609375,
"learning_rate": 0.00017812183570440428,
"loss": 1.4176,
"step": 225
},
{
"epoch": 0.9064039408866995,
"grad_norm": 0.10546875,
"learning_rate": 0.00017666991552407724,
"loss": 1.4101,
"step": 230
},
{
"epoch": 0.9261083743842364,
"grad_norm": 0.1044921875,
"learning_rate": 0.0001751776805386344,
"loss": 1.4029,
"step": 235
},
{
"epoch": 0.9458128078817734,
"grad_norm": 0.10009765625,
"learning_rate": 0.000173645915399555,
"loss": 1.3944,
"step": 240
},
{
"epoch": 0.9655172413793104,
"grad_norm": 0.0986328125,
"learning_rate": 0.00017207542554418227,
"loss": 1.4001,
"step": 245
},
{
"epoch": 0.9852216748768473,
"grad_norm": 0.103515625,
"learning_rate": 0.000170467036772206,
"loss": 1.4076,
"step": 250
},
{
"epoch": 1.0039408866995074,
"grad_norm": 0.10009765625,
"learning_rate": 0.00016882159481143802,
"loss": 1.4025,
"step": 255
},
{
"epoch": 1.0236453201970444,
"grad_norm": 0.09423828125,
"learning_rate": 0.00016713996487310916,
"loss": 1.405,
"step": 260
},
{
"epoch": 1.0433497536945813,
"grad_norm": 0.09619140625,
"learning_rate": 0.00016542303119692129,
"loss": 1.4017,
"step": 265
},
{
"epoch": 1.0630541871921182,
"grad_norm": 0.10107421875,
"learning_rate": 0.00016367169658609355,
"loss": 1.4038,
"step": 270
},
{
"epoch": 1.0827586206896551,
"grad_norm": 0.0966796875,
"learning_rate": 0.0001618868819326479,
"loss": 1.3942,
"step": 275
},
{
"epoch": 1.102463054187192,
"grad_norm": 0.10595703125,
"learning_rate": 0.00016006952573318278,
"loss": 1.3961,
"step": 280
},
{
"epoch": 1.1221674876847292,
"grad_norm": 0.10107421875,
"learning_rate": 0.00015822058359539002,
"loss": 1.4007,
"step": 285
},
{
"epoch": 1.141871921182266,
"grad_norm": 0.10009765625,
"learning_rate": 0.0001563410277355743,
"loss": 1.4071,
"step": 290
},
{
"epoch": 1.161576354679803,
"grad_norm": 0.09814453125,
"learning_rate": 0.0001544318464674397,
"loss": 1.385,
"step": 295
},
{
"epoch": 1.18128078817734,
"grad_norm": 0.0947265625,
"learning_rate": 0.00015249404368241116,
"loss": 1.3933,
"step": 300
},
{
"epoch": 1.2009852216748769,
"grad_norm": 0.09423828125,
"learning_rate": 0.0001505286383217657,
"loss": 1.3886,
"step": 305
},
{
"epoch": 1.2206896551724138,
"grad_norm": 0.10302734375,
"learning_rate": 0.0001485366638408496,
"loss": 1.387,
"step": 310
},
{
"epoch": 1.2403940886699507,
"grad_norm": 0.107421875,
"learning_rate": 0.0001465191676656634,
"loss": 1.3949,
"step": 315
},
{
"epoch": 1.2600985221674876,
"grad_norm": 0.09423828125,
"learning_rate": 0.00014447721064210186,
"loss": 1.3927,
"step": 320
},
{
"epoch": 1.2798029556650246,
"grad_norm": 0.09619140625,
"learning_rate": 0.00014241186647813626,
"loss": 1.4009,
"step": 325
},
{
"epoch": 1.2995073891625615,
"grad_norm": 0.091796875,
"learning_rate": 0.00014032422117923426,
"loss": 1.3838,
"step": 330
},
{
"epoch": 1.3192118226600984,
"grad_norm": 0.0947265625,
"learning_rate": 0.00013821537247731336,
"loss": 1.3958,
"step": 335
},
{
"epoch": 1.3389162561576355,
"grad_norm": 0.0947265625,
"learning_rate": 0.00013608642925352793,
"loss": 1.4111,
"step": 340
},
{
"epoch": 1.3586206896551725,
"grad_norm": 0.0966796875,
"learning_rate": 0.00013393851095519423,
"loss": 1.4007,
"step": 345
},
{
"epoch": 1.3783251231527094,
"grad_norm": 0.09521484375,
"learning_rate": 0.00013177274700715914,
"loss": 1.3933,
"step": 350
},
{
"epoch": 1.3980295566502463,
"grad_norm": 0.09814453125,
"learning_rate": 0.00012959027621792265,
"loss": 1.3997,
"step": 355
},
{
"epoch": 1.4177339901477832,
"grad_norm": 0.09716796875,
"learning_rate": 0.00012739224618082612,
"loss": 1.4075,
"step": 360
},
{
"epoch": 1.4374384236453202,
"grad_norm": 0.1064453125,
"learning_rate": 0.00012517981267062134,
"loss": 1.3927,
"step": 365
},
{
"epoch": 1.457142857142857,
"grad_norm": 0.095703125,
"learning_rate": 0.00012295413903573756,
"loss": 1.3956,
"step": 370
},
{
"epoch": 1.4768472906403942,
"grad_norm": 0.09423828125,
"learning_rate": 0.00012071639558656614,
"loss": 1.4016,
"step": 375
},
{
"epoch": 1.4965517241379311,
"grad_norm": 0.0947265625,
"learning_rate": 0.00011846775898008438,
"loss": 1.3889,
"step": 380
},
{
"epoch": 1.516256157635468,
"grad_norm": 0.0986328125,
"learning_rate": 0.00011620941160114229,
"loss": 1.3962,
"step": 385
},
{
"epoch": 1.535960591133005,
"grad_norm": 0.095703125,
"learning_rate": 0.0001139425409407374,
"loss": 1.3996,
"step": 390
},
{
"epoch": 1.555665024630542,
"grad_norm": 0.09228515625,
"learning_rate": 0.00011166833897160465,
"loss": 1.4013,
"step": 395
},
{
"epoch": 1.5753694581280788,
"grad_norm": 0.09814453125,
"learning_rate": 0.00010938800152144984,
"loss": 1.3788,
"step": 400
},
{
"epoch": 1.5753694581280788,
"eval_loss": 1.4156588315963745,
"eval_runtime": 144.1156,
"eval_samples_per_second": 50.064,
"eval_steps_per_second": 3.129,
"step": 400
},
{
"epoch": 1.5950738916256157,
"grad_norm": 0.09521484375,
"learning_rate": 0.00010710272764415566,
"loss": 1.3997,
"step": 405
},
{
"epoch": 1.6147783251231527,
"grad_norm": 0.09375,
"learning_rate": 0.00010481371898929186,
"loss": 1.3844,
"step": 410
},
{
"epoch": 1.6344827586206896,
"grad_norm": 0.095703125,
"learning_rate": 0.0001025221791702601,
"loss": 1.4087,
"step": 415
},
{
"epoch": 1.6541871921182265,
"grad_norm": 0.09765625,
"learning_rate": 0.00010022931313140638,
"loss": 1.3909,
"step": 420
},
{
"epoch": 1.6738916256157634,
"grad_norm": 0.091796875,
"learning_rate": 9.793632651443357e-05,
"loss": 1.3925,
"step": 425
},
{
"epoch": 1.6935960591133004,
"grad_norm": 0.09375,
"learning_rate": 9.564442502444735e-05,
"loss": 1.3906,
"step": 430
},
{
"epoch": 1.7133004926108373,
"grad_norm": 0.09521484375,
"learning_rate": 9.33548137959686e-05,
"loss": 1.4122,
"step": 435
},
{
"epoch": 1.7330049261083744,
"grad_norm": 0.1025390625,
"learning_rate": 9.106869675924605e-05,
"loss": 1.3932,
"step": 440
},
{
"epoch": 1.7527093596059113,
"grad_norm": 0.0947265625,
"learning_rate": 8.878727600720207e-05,
"loss": 1.3974,
"step": 445
},
{
"epoch": 1.7724137931034483,
"grad_norm": 0.0927734375,
"learning_rate": 8.651175116334443e-05,
"loss": 1.3872,
"step": 450
},
{
"epoch": 1.7921182266009852,
"grad_norm": 0.09619140625,
"learning_rate": 8.424331875097688e-05,
"loss": 1.4025,
"step": 455
},
{
"epoch": 1.8118226600985223,
"grad_norm": 0.0966796875,
"learning_rate": 8.19831715640394e-05,
"loss": 1.4054,
"step": 460
},
{
"epoch": 1.8315270935960593,
"grad_norm": 0.09326171875,
"learning_rate": 7.973249803991006e-05,
"loss": 1.3878,
"step": 465
},
{
"epoch": 1.8512315270935962,
"grad_norm": 0.0986328125,
"learning_rate": 7.749248163449693e-05,
"loss": 1.3862,
"step": 470
},
{
"epoch": 1.870935960591133,
"grad_norm": 0.099609375,
"learning_rate": 7.526430019995001e-05,
"loss": 1.4118,
"step": 475
},
{
"epoch": 1.89064039408867,
"grad_norm": 0.09326171875,
"learning_rate": 7.304912536531944e-05,
"loss": 1.3954,
"step": 480
},
{
"epoch": 1.910344827586207,
"grad_norm": 0.09130859375,
"learning_rate": 7.084812192048594e-05,
"loss": 1.4003,
"step": 485
},
{
"epoch": 1.9300492610837439,
"grad_norm": 0.1005859375,
"learning_rate": 6.866244720368737e-05,
"loss": 1.3998,
"step": 490
},
{
"epoch": 1.9497536945812808,
"grad_norm": 0.09423828125,
"learning_rate": 6.6493250492964e-05,
"loss": 1.3837,
"step": 495
},
{
"epoch": 1.9694581280788177,
"grad_norm": 0.09326171875,
"learning_rate": 6.434167240184135e-05,
"loss": 1.411,
"step": 500
},
{
"epoch": 1.9891625615763546,
"grad_norm": 0.09228515625,
"learning_rate": 6.220884427956953e-05,
"loss": 1.3949,
"step": 505
},
{
"epoch": 2.007881773399015,
"grad_norm": 0.0927734375,
"learning_rate": 6.0095887616233796e-05,
"loss": 1.3871,
"step": 510
},
{
"epoch": 2.027586206896552,
"grad_norm": 0.09228515625,
"learning_rate": 5.800391345304914e-05,
"loss": 1.3871,
"step": 515
},
{
"epoch": 2.0472906403940887,
"grad_norm": 0.09033203125,
"learning_rate": 5.593402179814944e-05,
"loss": 1.3887,
"step": 520
},
{
"epoch": 2.0669950738916256,
"grad_norm": 0.0927734375,
"learning_rate": 5.388730104817769e-05,
"loss": 1.3913,
"step": 525
},
{
"epoch": 2.0866995073891625,
"grad_norm": 0.095703125,
"learning_rate": 5.18648274159821e-05,
"loss": 1.3854,
"step": 530
},
{
"epoch": 2.1064039408866995,
"grad_norm": 0.09326171875,
"learning_rate": 4.9867664364718725e-05,
"loss": 1.3915,
"step": 535
},
{
"epoch": 2.1261083743842364,
"grad_norm": 0.09033203125,
"learning_rate": 4.7896862048657965e-05,
"loss": 1.3917,
"step": 540
},
{
"epoch": 2.1458128078817733,
"grad_norm": 0.095703125,
"learning_rate": 4.595345676098923e-05,
"loss": 1.3855,
"step": 545
},
{
"epoch": 2.1655172413793102,
"grad_norm": 0.09130859375,
"learning_rate": 4.403847038891424e-05,
"loss": 1.3838,
"step": 550
},
{
"epoch": 2.185221674876847,
"grad_norm": 0.09033203125,
"learning_rate": 4.2152909876315316e-05,
"loss": 1.3919,
"step": 555
},
{
"epoch": 2.204926108374384,
"grad_norm": 0.0966796875,
"learning_rate": 4.0297766694280915e-05,
"loss": 1.3979,
"step": 560
},
{
"epoch": 2.224630541871921,
"grad_norm": 0.091796875,
"learning_rate": 3.8474016319767435e-05,
"loss": 1.3865,
"step": 565
},
{
"epoch": 2.2443349753694584,
"grad_norm": 0.0986328125,
"learning_rate": 3.6682617722671096e-05,
"loss": 1.3903,
"step": 570
},
{
"epoch": 2.264039408866995,
"grad_norm": 0.09033203125,
"learning_rate": 3.4924512861579315e-05,
"loss": 1.3841,
"step": 575
},
{
"epoch": 2.283743842364532,
"grad_norm": 0.09375,
"learning_rate": 3.3200626188467344e-05,
"loss": 1.3965,
"step": 580
},
{
"epoch": 2.303448275862069,
"grad_norm": 0.08984375,
"learning_rate": 3.151186416260006e-05,
"loss": 1.4112,
"step": 585
},
{
"epoch": 2.323152709359606,
"grad_norm": 0.09521484375,
"learning_rate": 2.9859114773895025e-05,
"loss": 1.385,
"step": 590
},
{
"epoch": 2.342857142857143,
"grad_norm": 0.0986328125,
"learning_rate": 2.8243247075996693e-05,
"loss": 1.3838,
"step": 595
},
{
"epoch": 2.36256157635468,
"grad_norm": 0.0927734375,
"learning_rate": 2.6665110729308263e-05,
"loss": 1.3938,
"step": 600
},
{
"epoch": 2.36256157635468,
"eval_loss": 1.4132238626480103,
"eval_runtime": 144.0354,
"eval_samples_per_second": 50.092,
"eval_steps_per_second": 3.131,
"step": 600
},
{
"epoch": 2.382266009852217,
"grad_norm": 0.09423828125,
"learning_rate": 2.5125535554220482e-05,
"loss": 1.3974,
"step": 605
},
{
"epoch": 2.4019704433497537,
"grad_norm": 0.09375,
"learning_rate": 2.3625331094773206e-05,
"loss": 1.3814,
"step": 610
},
{
"epoch": 2.4216748768472907,
"grad_norm": 0.091796875,
"learning_rate": 2.2165286192978342e-05,
"loss": 1.3858,
"step": 615
},
{
"epoch": 2.4413793103448276,
"grad_norm": 0.0947265625,
"learning_rate": 2.074616857402867e-05,
"loss": 1.3804,
"step": 620
},
{
"epoch": 2.4610837438423645,
"grad_norm": 0.0927734375,
"learning_rate": 1.936872444261022e-05,
"loss": 1.3868,
"step": 625
},
{
"epoch": 2.4807881773399014,
"grad_norm": 0.09228515625,
"learning_rate": 1.8033678090530813e-05,
"loss": 1.3923,
"step": 630
},
{
"epoch": 2.5004926108374383,
"grad_norm": 0.091796875,
"learning_rate": 1.6741731515870594e-05,
"loss": 1.3889,
"step": 635
},
{
"epoch": 2.5201970443349753,
"grad_norm": 0.09814453125,
"learning_rate": 1.549356405385538e-05,
"loss": 1.3736,
"step": 640
},
{
"epoch": 2.539901477832512,
"grad_norm": 0.0947265625,
"learning_rate": 1.428983201964662e-05,
"loss": 1.3955,
"step": 645
},
{
"epoch": 2.559605911330049,
"grad_norm": 0.09375,
"learning_rate": 1.313116836323568e-05,
"loss": 1.3946,
"step": 650
},
{
"epoch": 2.5793103448275865,
"grad_norm": 0.09521484375,
"learning_rate": 1.2018182336624273e-05,
"loss": 1.3907,
"step": 655
},
{
"epoch": 2.599014778325123,
"grad_norm": 0.09326171875,
"learning_rate": 1.0951459173465629e-05,
"loss": 1.4041,
"step": 660
},
{
"epoch": 2.6187192118226603,
"grad_norm": 0.09423828125,
"learning_rate": 9.93155978133541e-06,
"loss": 1.391,
"step": 665
},
{
"epoch": 2.638423645320197,
"grad_norm": 0.09033203125,
"learning_rate": 8.959020446793288e-06,
"loss": 1.3882,
"step": 670
},
{
"epoch": 2.658128078817734,
"grad_norm": 0.09375,
"learning_rate": 8.034352553391367e-06,
"loss": 1.4001,
"step": 675
},
{
"epoch": 2.677832512315271,
"grad_norm": 0.0927734375,
"learning_rate": 7.158042312776847e-06,
"loss": 1.3824,
"step": 680
},
{
"epoch": 2.697536945812808,
"grad_norm": 0.0908203125,
"learning_rate": 6.330550509030852e-06,
"loss": 1.379,
"step": 685
},
{
"epoch": 2.717241379310345,
"grad_norm": 0.08984375,
"learning_rate": 5.552312256377423e-06,
"loss": 1.3787,
"step": 690
},
{
"epoch": 2.736945812807882,
"grad_norm": 0.09228515625,
"learning_rate": 4.823736770390552e-06,
"loss": 1.3902,
"step": 695
},
{
"epoch": 2.7566502463054188,
"grad_norm": 0.0927734375,
"learning_rate": 4.14520715281923e-06,
"loss": 1.3991,
"step": 700
},
{
"epoch": 2.7763546798029557,
"grad_norm": 0.09375,
"learning_rate": 3.517080190143629e-06,
"loss": 1.3866,
"step": 705
},
{
"epoch": 2.7960591133004926,
"grad_norm": 0.09033203125,
"learning_rate": 2.9396861659686915e-06,
"loss": 1.3864,
"step": 710
},
{
"epoch": 2.8157635467980295,
"grad_norm": 0.0927734375,
"learning_rate": 2.4133286873533112e-06,
"loss": 1.373,
"step": 715
},
{
"epoch": 2.8354679802955665,
"grad_norm": 0.0966796875,
"learning_rate": 1.9382845251668335e-06,
"loss": 1.384,
"step": 720
},
{
"epoch": 2.8551724137931034,
"grad_norm": 0.091796875,
"learning_rate": 1.514803468556547e-06,
"loss": 1.3768,
"step": 725
},
{
"epoch": 2.8748768472906403,
"grad_norm": 0.0908203125,
"learning_rate": 1.14310819360276e-06,
"loss": 1.3968,
"step": 730
},
{
"epoch": 2.8945812807881772,
"grad_norm": 0.09130859375,
"learning_rate": 8.233941462306271e-07,
"loss": 1.3811,
"step": 735
},
{
"epoch": 2.914285714285714,
"grad_norm": 0.0908203125,
"learning_rate": 5.558294394402253e-07,
"loss": 1.4115,
"step": 740
},
{
"epoch": 2.933990147783251,
"grad_norm": 0.08984375,
"learning_rate": 3.405547649087959e-07,
"loss": 1.4119,
"step": 745
},
{
"epoch": 2.9536945812807884,
"grad_norm": 0.09130859375,
"learning_rate": 1.7768331901187875e-07,
"loss": 1.395,
"step": 750
},
{
"epoch": 2.973399014778325,
"grad_norm": 0.0947265625,
"learning_rate": 6.730074330203451e-08,
"loss": 1.3966,
"step": 755
},
{
"epoch": 2.9931034482758623,
"grad_norm": 0.09228515625,
"learning_rate": 9.46507947655606e-09,
"loss": 1.3686,
"step": 760
},
{
"epoch": 3.0,
"step": 762,
"total_flos": 7.533943292711404e+17,
"train_loss": 1.4212341141200129,
"train_runtime": 13229.3679,
"train_samples_per_second": 14.73,
"train_steps_per_second": 0.058
}
],
"logging_steps": 5,
"max_steps": 762,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 1000000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 7.533943292711404e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}