klora_2000_skill / 2 /trainer_state.json
RayDu0010's picture
Upload folder using huggingface_hub
4eb111c verified
raw
history blame
29.1 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 820,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012195121951219513,
"grad_norm": 1.184765100479126,
"learning_rate": 1.1650485436893204e-06,
"loss": 1.2972,
"step": 5
},
{
"epoch": 0.024390243902439025,
"grad_norm": 0.9755042195320129,
"learning_rate": 2.621359223300971e-06,
"loss": 1.3303,
"step": 10
},
{
"epoch": 0.036585365853658534,
"grad_norm": 0.8106493949890137,
"learning_rate": 4.0776699029126215e-06,
"loss": 1.2908,
"step": 15
},
{
"epoch": 0.04878048780487805,
"grad_norm": 0.6635167002677917,
"learning_rate": 5.533980582524272e-06,
"loss": 1.2413,
"step": 20
},
{
"epoch": 0.06097560975609756,
"grad_norm": 0.5763493180274963,
"learning_rate": 6.990291262135923e-06,
"loss": 1.2209,
"step": 25
},
{
"epoch": 0.07317073170731707,
"grad_norm": 0.49019569158554077,
"learning_rate": 8.446601941747573e-06,
"loss": 1.265,
"step": 30
},
{
"epoch": 0.08536585365853659,
"grad_norm": 0.5669918060302734,
"learning_rate": 9.902912621359224e-06,
"loss": 1.2391,
"step": 35
},
{
"epoch": 0.0975609756097561,
"grad_norm": 0.5410548448562622,
"learning_rate": 1.1359223300970873e-05,
"loss": 1.2694,
"step": 40
},
{
"epoch": 0.10975609756097561,
"grad_norm": 0.489359587430954,
"learning_rate": 1.2815533980582524e-05,
"loss": 1.2039,
"step": 45
},
{
"epoch": 0.12195121951219512,
"grad_norm": 0.6161925792694092,
"learning_rate": 1.4271844660194176e-05,
"loss": 1.1988,
"step": 50
},
{
"epoch": 0.13414634146341464,
"grad_norm": 0.5076792240142822,
"learning_rate": 1.5728155339805827e-05,
"loss": 1.128,
"step": 55
},
{
"epoch": 0.14634146341463414,
"grad_norm": 0.46671441197395325,
"learning_rate": 1.7184466019417476e-05,
"loss": 1.1529,
"step": 60
},
{
"epoch": 0.15853658536585366,
"grad_norm": 0.511127233505249,
"learning_rate": 1.8640776699029126e-05,
"loss": 1.1286,
"step": 65
},
{
"epoch": 0.17073170731707318,
"grad_norm": 0.5400530695915222,
"learning_rate": 2.009708737864078e-05,
"loss": 1.1555,
"step": 70
},
{
"epoch": 0.18292682926829268,
"grad_norm": 0.5800668597221375,
"learning_rate": 2.1553398058252428e-05,
"loss": 1.1579,
"step": 75
},
{
"epoch": 0.1951219512195122,
"grad_norm": 0.5733080506324768,
"learning_rate": 2.3009708737864078e-05,
"loss": 1.2164,
"step": 80
},
{
"epoch": 0.2073170731707317,
"grad_norm": 0.5242522954940796,
"learning_rate": 2.4466019417475727e-05,
"loss": 1.1548,
"step": 85
},
{
"epoch": 0.21951219512195122,
"grad_norm": 0.5192080140113831,
"learning_rate": 2.5922330097087377e-05,
"loss": 1.1127,
"step": 90
},
{
"epoch": 0.23170731707317074,
"grad_norm": 0.6592035889625549,
"learning_rate": 2.737864077669903e-05,
"loss": 1.1187,
"step": 95
},
{
"epoch": 0.24390243902439024,
"grad_norm": 0.5072050094604492,
"learning_rate": 2.8834951456310683e-05,
"loss": 1.1057,
"step": 100
},
{
"epoch": 0.25609756097560976,
"grad_norm": 0.530845582485199,
"learning_rate": 2.9999980473292916e-05,
"loss": 1.0943,
"step": 105
},
{
"epoch": 0.2682926829268293,
"grad_norm": 0.5525540113449097,
"learning_rate": 2.999929704388311e-05,
"loss": 1.0717,
"step": 110
},
{
"epoch": 0.2804878048780488,
"grad_norm": 0.5346278548240662,
"learning_rate": 2.999763732995757e-05,
"loss": 1.0477,
"step": 115
},
{
"epoch": 0.2926829268292683,
"grad_norm": 0.634670615196228,
"learning_rate": 2.999500143954488e-05,
"loss": 1.0227,
"step": 120
},
{
"epoch": 0.3048780487804878,
"grad_norm": 0.6343799829483032,
"learning_rate": 2.9991389544211688e-05,
"loss": 1.0359,
"step": 125
},
{
"epoch": 0.3170731707317073,
"grad_norm": 0.6552476286888123,
"learning_rate": 2.998680187905151e-05,
"loss": 1.0654,
"step": 130
},
{
"epoch": 0.32926829268292684,
"grad_norm": 0.7905762195587158,
"learning_rate": 2.9981238742669432e-05,
"loss": 1.0706,
"step": 135
},
{
"epoch": 0.34146341463414637,
"grad_norm": 0.6723063588142395,
"learning_rate": 2.997470049716269e-05,
"loss": 1.0488,
"step": 140
},
{
"epoch": 0.35365853658536583,
"grad_norm": 0.6034112572669983,
"learning_rate": 2.9967187568097084e-05,
"loss": 1.0492,
"step": 145
},
{
"epoch": 0.36585365853658536,
"grad_norm": 0.5780961513519287,
"learning_rate": 2.995870044447928e-05,
"loss": 0.9935,
"step": 150
},
{
"epoch": 0.3780487804878049,
"grad_norm": 0.6658617854118347,
"learning_rate": 2.9949239678724995e-05,
"loss": 1.046,
"step": 155
},
{
"epoch": 0.3902439024390244,
"grad_norm": 0.6619867086410522,
"learning_rate": 2.993880588662303e-05,
"loss": 0.9965,
"step": 160
},
{
"epoch": 0.4024390243902439,
"grad_norm": 0.7782027721405029,
"learning_rate": 2.9927399747295178e-05,
"loss": 0.9886,
"step": 165
},
{
"epoch": 0.4146341463414634,
"grad_norm": 0.6822337508201599,
"learning_rate": 2.9915022003152058e-05,
"loss": 0.9674,
"step": 170
},
{
"epoch": 0.4268292682926829,
"grad_norm": 0.5955122113227844,
"learning_rate": 2.990167345984475e-05,
"loss": 1.0358,
"step": 175
},
{
"epoch": 0.43902439024390244,
"grad_norm": 0.7010889649391174,
"learning_rate": 2.988735498621238e-05,
"loss": 0.9443,
"step": 180
},
{
"epoch": 0.45121951219512196,
"grad_norm": 0.651681661605835,
"learning_rate": 2.9872067514225565e-05,
"loss": 0.9144,
"step": 185
},
{
"epoch": 0.4634146341463415,
"grad_norm": 0.7048653364181519,
"learning_rate": 2.985581203892575e-05,
"loss": 0.9196,
"step": 190
},
{
"epoch": 0.47560975609756095,
"grad_norm": 0.7128203511238098,
"learning_rate": 2.9838589618360434e-05,
"loss": 0.9225,
"step": 195
},
{
"epoch": 0.4878048780487805,
"grad_norm": 0.7625283002853394,
"learning_rate": 2.9820401373514333e-05,
"loss": 0.9858,
"step": 200
},
{
"epoch": 0.5,
"grad_norm": 0.7980352640151978,
"learning_rate": 2.9801248488236364e-05,
"loss": 0.9252,
"step": 205
},
{
"epoch": 0.5121951219512195,
"grad_norm": 0.6355564594268799,
"learning_rate": 2.978113220916265e-05,
"loss": 0.9262,
"step": 210
},
{
"epoch": 0.524390243902439,
"grad_norm": 0.7836682200431824,
"learning_rate": 2.9760053845635324e-05,
"loss": 0.8971,
"step": 215
},
{
"epoch": 0.5365853658536586,
"grad_norm": 0.7409992218017578,
"learning_rate": 2.973801476961736e-05,
"loss": 0.8825,
"step": 220
},
{
"epoch": 0.5487804878048781,
"grad_norm": 0.6563221216201782,
"learning_rate": 2.9715016415603217e-05,
"loss": 0.8866,
"step": 225
},
{
"epoch": 0.5609756097560976,
"grad_norm": 0.6461041569709778,
"learning_rate": 2.9691060280525506e-05,
"loss": 0.8716,
"step": 230
},
{
"epoch": 0.573170731707317,
"grad_norm": 0.6985337734222412,
"learning_rate": 2.9666147923657552e-05,
"loss": 0.8699,
"step": 235
},
{
"epoch": 0.5853658536585366,
"grad_norm": 0.8816692233085632,
"learning_rate": 2.9640280966511898e-05,
"loss": 0.8506,
"step": 240
},
{
"epoch": 0.5975609756097561,
"grad_norm": 0.7365345358848572,
"learning_rate": 2.961346109273476e-05,
"loss": 0.9093,
"step": 245
},
{
"epoch": 0.6097560975609756,
"grad_norm": 0.8134493827819824,
"learning_rate": 2.9585690047996444e-05,
"loss": 0.7961,
"step": 250
},
{
"epoch": 0.6219512195121951,
"grad_norm": 0.7763360738754272,
"learning_rate": 2.955696963987773e-05,
"loss": 0.8697,
"step": 255
},
{
"epoch": 0.6341463414634146,
"grad_norm": 0.7731444239616394,
"learning_rate": 2.9527301737752196e-05,
"loss": 0.8777,
"step": 260
},
{
"epoch": 0.6463414634146342,
"grad_norm": 0.9481649398803711,
"learning_rate": 2.9496688272664577e-05,
"loss": 0.8514,
"step": 265
},
{
"epoch": 0.6585365853658537,
"grad_norm": 0.827903151512146,
"learning_rate": 2.9465131237205043e-05,
"loss": 0.908,
"step": 270
},
{
"epoch": 0.6707317073170732,
"grad_norm": 0.8994118571281433,
"learning_rate": 2.943263268537953e-05,
"loss": 0.7373,
"step": 275
},
{
"epoch": 0.6829268292682927,
"grad_norm": 0.8990964889526367,
"learning_rate": 2.9399194732476032e-05,
"loss": 0.82,
"step": 280
},
{
"epoch": 0.6951219512195121,
"grad_norm": 0.8939409255981445,
"learning_rate": 2.9364819554926912e-05,
"loss": 0.8102,
"step": 285
},
{
"epoch": 0.7073170731707317,
"grad_norm": 0.9013278484344482,
"learning_rate": 2.932950939016727e-05,
"loss": 0.7655,
"step": 290
},
{
"epoch": 0.7195121951219512,
"grad_norm": 0.7653906941413879,
"learning_rate": 2.929326653648929e-05,
"loss": 0.7864,
"step": 295
},
{
"epoch": 0.7317073170731707,
"grad_norm": 0.9510161876678467,
"learning_rate": 2.9256093352892635e-05,
"loss": 0.7845,
"step": 300
},
{
"epoch": 0.7439024390243902,
"grad_norm": 0.9910411834716797,
"learning_rate": 2.921799225893094e-05,
"loss": 0.8002,
"step": 305
},
{
"epoch": 0.7560975609756098,
"grad_norm": 0.8927392959594727,
"learning_rate": 2.917896573455429e-05,
"loss": 0.7693,
"step": 310
},
{
"epoch": 0.7682926829268293,
"grad_norm": 0.8335655927658081,
"learning_rate": 2.913901631994783e-05,
"loss": 0.7593,
"step": 315
},
{
"epoch": 0.7804878048780488,
"grad_norm": 0.9775434136390686,
"learning_rate": 2.909814661536641e-05,
"loss": 0.7371,
"step": 320
},
{
"epoch": 0.7926829268292683,
"grad_norm": 0.8624247908592224,
"learning_rate": 2.9056359280965345e-05,
"loss": 0.8004,
"step": 325
},
{
"epoch": 0.8048780487804879,
"grad_norm": 1.1061346530914307,
"learning_rate": 2.901365703662726e-05,
"loss": 0.7445,
"step": 330
},
{
"epoch": 0.8170731707317073,
"grad_norm": 0.8500701189041138,
"learning_rate": 2.897004266178508e-05,
"loss": 0.7437,
"step": 335
},
{
"epoch": 0.8292682926829268,
"grad_norm": 0.9865604639053345,
"learning_rate": 2.892551899524109e-05,
"loss": 0.701,
"step": 340
},
{
"epoch": 0.8414634146341463,
"grad_norm": 0.9660606384277344,
"learning_rate": 2.888008893498219e-05,
"loss": 0.7524,
"step": 345
},
{
"epoch": 0.8536585365853658,
"grad_norm": 0.9367020726203918,
"learning_rate": 2.8833755437991242e-05,
"loss": 0.7132,
"step": 350
},
{
"epoch": 0.8658536585365854,
"grad_norm": 1.0071465969085693,
"learning_rate": 2.878652152005462e-05,
"loss": 0.7564,
"step": 355
},
{
"epoch": 0.8780487804878049,
"grad_norm": 1.0385185480117798,
"learning_rate": 2.8738390255565925e-05,
"loss": 0.6634,
"step": 360
},
{
"epoch": 0.8902439024390244,
"grad_norm": 0.9005842208862305,
"learning_rate": 2.8689364777325847e-05,
"loss": 0.6951,
"step": 365
},
{
"epoch": 0.9024390243902439,
"grad_norm": 0.9195963144302368,
"learning_rate": 2.863944827633828e-05,
"loss": 0.7013,
"step": 370
},
{
"epoch": 0.9146341463414634,
"grad_norm": 0.9449793100357056,
"learning_rate": 2.8588644001602623e-05,
"loss": 0.6901,
"step": 375
},
{
"epoch": 0.926829268292683,
"grad_norm": 0.9308488368988037,
"learning_rate": 2.8536955259902283e-05,
"loss": 0.7064,
"step": 380
},
{
"epoch": 0.9390243902439024,
"grad_norm": 0.8601620197296143,
"learning_rate": 2.8484385415589485e-05,
"loss": 0.6913,
"step": 385
},
{
"epoch": 0.9512195121951219,
"grad_norm": 0.8974642157554626,
"learning_rate": 2.843093789036624e-05,
"loss": 0.6692,
"step": 390
},
{
"epoch": 0.9634146341463414,
"grad_norm": 0.890214741230011,
"learning_rate": 2.837661616306166e-05,
"loss": 0.6839,
"step": 395
},
{
"epoch": 0.975609756097561,
"grad_norm": 0.8833136558532715,
"learning_rate": 2.8321423769405538e-05,
"loss": 0.742,
"step": 400
},
{
"epoch": 0.9878048780487805,
"grad_norm": 1.1129741668701172,
"learning_rate": 2.8265364301798175e-05,
"loss": 0.6696,
"step": 405
},
{
"epoch": 1.0,
"grad_norm": 0.957071840763092,
"learning_rate": 2.8208441409076576e-05,
"loss": 0.6266,
"step": 410
},
{
"epoch": 1.0121951219512195,
"grad_norm": 1.0043803453445435,
"learning_rate": 2.8150658796276964e-05,
"loss": 0.6141,
"step": 415
},
{
"epoch": 1.024390243902439,
"grad_norm": 1.0592577457427979,
"learning_rate": 2.8092020224393603e-05,
"loss": 0.5861,
"step": 420
},
{
"epoch": 1.0365853658536586,
"grad_norm": 1.1829588413238525,
"learning_rate": 2.8032529510134008e-05,
"loss": 0.5592,
"step": 425
},
{
"epoch": 1.048780487804878,
"grad_norm": 1.0533852577209473,
"learning_rate": 2.797219052567052e-05,
"loss": 0.6068,
"step": 430
},
{
"epoch": 1.0609756097560976,
"grad_norm": 0.9526946544647217,
"learning_rate": 2.791100719838827e-05,
"loss": 0.5667,
"step": 435
},
{
"epoch": 1.0731707317073171,
"grad_norm": 1.1012799739837646,
"learning_rate": 2.7848983510629554e-05,
"loss": 0.6413,
"step": 440
},
{
"epoch": 1.0853658536585367,
"grad_norm": 1.601194143295288,
"learning_rate": 2.7786123499434642e-05,
"loss": 0.5612,
"step": 445
},
{
"epoch": 1.0975609756097562,
"grad_norm": 0.9721382856369019,
"learning_rate": 2.772243125627896e-05,
"loss": 0.5407,
"step": 450
},
{
"epoch": 1.1097560975609757,
"grad_norm": 1.0757757425308228,
"learning_rate": 2.7657910926806858e-05,
"loss": 0.505,
"step": 455
},
{
"epoch": 1.1219512195121952,
"grad_norm": 1.2296000719070435,
"learning_rate": 2.7592566710561704e-05,
"loss": 0.559,
"step": 460
},
{
"epoch": 1.1341463414634148,
"grad_norm": 0.9386566877365112,
"learning_rate": 2.7526402860712597e-05,
"loss": 0.5553,
"step": 465
},
{
"epoch": 1.146341463414634,
"grad_norm": 1.1901946067810059,
"learning_rate": 2.7459423683777484e-05,
"loss": 0.5844,
"step": 470
},
{
"epoch": 1.1585365853658536,
"grad_norm": 1.1464612483978271,
"learning_rate": 2.73916335393429e-05,
"loss": 0.5492,
"step": 475
},
{
"epoch": 1.170731707317073,
"grad_norm": 1.005790114402771,
"learning_rate": 2.732303683978018e-05,
"loss": 0.553,
"step": 480
},
{
"epoch": 1.1829268292682926,
"grad_norm": 1.2415597438812256,
"learning_rate": 2.725363804995827e-05,
"loss": 0.5452,
"step": 485
},
{
"epoch": 1.1951219512195121,
"grad_norm": 1.0382238626480103,
"learning_rate": 2.7183441686953122e-05,
"loss": 0.5413,
"step": 490
},
{
"epoch": 1.2073170731707317,
"grad_norm": 1.0460742712020874,
"learning_rate": 2.711245231975367e-05,
"loss": 0.5109,
"step": 495
},
{
"epoch": 1.2195121951219512,
"grad_norm": 0.9935807585716248,
"learning_rate": 2.7040674568964454e-05,
"loss": 0.5572,
"step": 500
},
{
"epoch": 1.2317073170731707,
"grad_norm": 1.0190331935882568,
"learning_rate": 2.6968113106504865e-05,
"loss": 0.5075,
"step": 505
},
{
"epoch": 1.2439024390243902,
"grad_norm": 0.9684451818466187,
"learning_rate": 2.689477265530504e-05,
"loss": 0.5295,
"step": 510
},
{
"epoch": 1.2560975609756098,
"grad_norm": 1.0213184356689453,
"learning_rate": 2.68206579889985e-05,
"loss": 0.5119,
"step": 515
},
{
"epoch": 1.2682926829268293,
"grad_norm": 0.9365750551223755,
"learning_rate": 2.674577393161137e-05,
"loss": 0.5111,
"step": 520
},
{
"epoch": 1.2804878048780488,
"grad_norm": 1.0988898277282715,
"learning_rate": 2.667012535724847e-05,
"loss": 0.4914,
"step": 525
},
{
"epoch": 1.2926829268292683,
"grad_norm": 1.0466548204421997,
"learning_rate": 2.6593717189775986e-05,
"loss": 0.4429,
"step": 530
},
{
"epoch": 1.3048780487804879,
"grad_norm": 1.141400694847107,
"learning_rate": 2.6516554402501048e-05,
"loss": 0.4968,
"step": 535
},
{
"epoch": 1.3170731707317074,
"grad_norm": 0.9664748311042786,
"learning_rate": 2.6438642017847983e-05,
"loss": 0.4933,
"step": 540
},
{
"epoch": 1.329268292682927,
"grad_norm": 1.1237977743148804,
"learning_rate": 2.635998510703143e-05,
"loss": 0.4822,
"step": 545
},
{
"epoch": 1.3414634146341464,
"grad_norm": 1.1644905805587769,
"learning_rate": 2.6280588789726257e-05,
"loss": 0.5107,
"step": 550
},
{
"epoch": 1.3536585365853657,
"grad_norm": 1.103337287902832,
"learning_rate": 2.6200458233734316e-05,
"loss": 0.4696,
"step": 555
},
{
"epoch": 1.3658536585365852,
"grad_norm": 1.017683744430542,
"learning_rate": 2.611959865464811e-05,
"loss": 0.4719,
"step": 560
},
{
"epoch": 1.3780487804878048,
"grad_norm": 1.2212704420089722,
"learning_rate": 2.6038015315511284e-05,
"loss": 0.4932,
"step": 565
},
{
"epoch": 1.3902439024390243,
"grad_norm": 1.2683626413345337,
"learning_rate": 2.5955713526476068e-05,
"loss": 0.4822,
"step": 570
},
{
"epoch": 1.4024390243902438,
"grad_norm": 0.9710960984230042,
"learning_rate": 2.587269864445766e-05,
"loss": 0.4526,
"step": 575
},
{
"epoch": 1.4146341463414633,
"grad_norm": 0.9223999977111816,
"learning_rate": 2.578897607278555e-05,
"loss": 0.473,
"step": 580
},
{
"epoch": 1.4268292682926829,
"grad_norm": 1.176310658454895,
"learning_rate": 2.5704551260851786e-05,
"loss": 0.4636,
"step": 585
},
{
"epoch": 1.4390243902439024,
"grad_norm": 1.1532803773880005,
"learning_rate": 2.5619429703756355e-05,
"loss": 0.4549,
"step": 590
},
{
"epoch": 1.451219512195122,
"grad_norm": 0.9891874194145203,
"learning_rate": 2.5533616941949426e-05,
"loss": 0.4909,
"step": 595
},
{
"epoch": 1.4634146341463414,
"grad_norm": 1.1279683113098145,
"learning_rate": 2.5447118560870803e-05,
"loss": 0.4825,
"step": 600
},
{
"epoch": 1.475609756097561,
"grad_norm": 0.9699839353561401,
"learning_rate": 2.5359940190586337e-05,
"loss": 0.4478,
"step": 605
},
{
"epoch": 1.4878048780487805,
"grad_norm": 0.970900297164917,
"learning_rate": 2.5272087505421482e-05,
"loss": 0.5015,
"step": 610
},
{
"epoch": 1.5,
"grad_norm": 1.0708060264587402,
"learning_rate": 2.5183566223591966e-05,
"loss": 0.4883,
"step": 615
},
{
"epoch": 1.5121951219512195,
"grad_norm": 1.0761215686798096,
"learning_rate": 2.509438210683158e-05,
"loss": 0.4213,
"step": 620
},
{
"epoch": 1.524390243902439,
"grad_norm": 1.0248342752456665,
"learning_rate": 2.5004540960017185e-05,
"loss": 0.4311,
"step": 625
},
{
"epoch": 1.5365853658536586,
"grad_norm": 1.1032685041427612,
"learning_rate": 2.4914048630790857e-05,
"loss": 0.4608,
"step": 630
},
{
"epoch": 1.548780487804878,
"grad_norm": 1.1839253902435303,
"learning_rate": 2.482291100917928e-05,
"loss": 0.4604,
"step": 635
},
{
"epoch": 1.5609756097560976,
"grad_norm": 1.2353657484054565,
"learning_rate": 2.473113402721036e-05,
"loss": 0.4499,
"step": 640
},
{
"epoch": 1.5731707317073171,
"grad_norm": 1.177707552909851,
"learning_rate": 2.4638723658527152e-05,
"loss": 0.4172,
"step": 645
},
{
"epoch": 1.5853658536585367,
"grad_norm": 1.0010558366775513,
"learning_rate": 2.4545685917998994e-05,
"loss": 0.4417,
"step": 650
},
{
"epoch": 1.5975609756097562,
"grad_norm": 1.1996454000473022,
"learning_rate": 2.4452026861330054e-05,
"loss": 0.4586,
"step": 655
},
{
"epoch": 1.6097560975609757,
"grad_norm": 1.1821777820587158,
"learning_rate": 2.4357752584665123e-05,
"loss": 0.4828,
"step": 660
},
{
"epoch": 1.6219512195121952,
"grad_norm": 1.1734565496444702,
"learning_rate": 2.426286922419288e-05,
"loss": 0.4167,
"step": 665
},
{
"epoch": 1.6341463414634148,
"grad_norm": 0.9794202446937561,
"learning_rate": 2.416738295574645e-05,
"loss": 0.3879,
"step": 670
},
{
"epoch": 1.6463414634146343,
"grad_norm": 1.191879391670227,
"learning_rate": 2.4071299994401462e-05,
"loss": 0.4004,
"step": 675
},
{
"epoch": 1.6585365853658538,
"grad_norm": 1.0724924802780151,
"learning_rate": 2.397462659407148e-05,
"loss": 0.4385,
"step": 680
},
{
"epoch": 1.6707317073170733,
"grad_norm": 1.1953388452529907,
"learning_rate": 2.387736904710098e-05,
"loss": 0.4674,
"step": 685
},
{
"epoch": 1.6829268292682928,
"grad_norm": 1.089429497718811,
"learning_rate": 2.377953368385577e-05,
"loss": 0.4316,
"step": 690
},
{
"epoch": 1.6951219512195121,
"grad_norm": 1.1765036582946777,
"learning_rate": 2.368112687231095e-05,
"loss": 0.4237,
"step": 695
},
{
"epoch": 1.7073170731707317,
"grad_norm": 1.0054248571395874,
"learning_rate": 2.3582155017636455e-05,
"loss": 0.4639,
"step": 700
},
{
"epoch": 1.7195121951219512,
"grad_norm": 1.0205795764923096,
"learning_rate": 2.3482624561780128e-05,
"loss": 0.3966,
"step": 705
},
{
"epoch": 1.7317073170731707,
"grad_norm": 1.1560744047164917,
"learning_rate": 2.3382541983048425e-05,
"loss": 0.3839,
"step": 710
},
{
"epoch": 1.7439024390243902,
"grad_norm": 1.079033613204956,
"learning_rate": 2.3281913795684757e-05,
"loss": 0.3966,
"step": 715
},
{
"epoch": 1.7560975609756098,
"grad_norm": 1.0057902336120605,
"learning_rate": 2.318074654944547e-05,
"loss": 0.4309,
"step": 720
},
{
"epoch": 1.7682926829268293,
"grad_norm": 1.2559707164764404,
"learning_rate": 2.307904682917357e-05,
"loss": 0.4111,
"step": 725
},
{
"epoch": 1.7804878048780488,
"grad_norm": 1.2369558811187744,
"learning_rate": 2.2976821254370077e-05,
"loss": 0.4051,
"step": 730
},
{
"epoch": 1.7926829268292683,
"grad_norm": 0.968970000743866,
"learning_rate": 2.2874076478763187e-05,
"loss": 0.3857,
"step": 735
},
{
"epoch": 1.8048780487804879,
"grad_norm": 1.0662639141082764,
"learning_rate": 2.277081918987522e-05,
"loss": 0.3677,
"step": 740
},
{
"epoch": 1.8170731707317072,
"grad_norm": 1.0119315385818481,
"learning_rate": 2.266705610858727e-05,
"loss": 0.3887,
"step": 745
},
{
"epoch": 1.8292682926829267,
"grad_norm": 1.0961999893188477,
"learning_rate": 2.2562793988701838e-05,
"loss": 0.4059,
"step": 750
},
{
"epoch": 1.8414634146341462,
"grad_norm": 1.0293822288513184,
"learning_rate": 2.245803961650316e-05,
"loss": 0.3473,
"step": 755
},
{
"epoch": 1.8536585365853657,
"grad_norm": 1.076990008354187,
"learning_rate": 2.2352799810315534e-05,
"loss": 0.3493,
"step": 760
},
{
"epoch": 1.8658536585365852,
"grad_norm": 1.1946849822998047,
"learning_rate": 2.2247081420059526e-05,
"loss": 0.3746,
"step": 765
},
{
"epoch": 1.8780487804878048,
"grad_norm": 1.3098491430282593,
"learning_rate": 2.2140891326806106e-05,
"loss": 0.3596,
"step": 770
},
{
"epoch": 1.8902439024390243,
"grad_norm": 1.1211118698120117,
"learning_rate": 2.203423644232877e-05,
"loss": 0.3514,
"step": 775
},
{
"epoch": 1.9024390243902438,
"grad_norm": 1.046966314315796,
"learning_rate": 2.1927123708653658e-05,
"loss": 0.3954,
"step": 780
},
{
"epoch": 1.9146341463414633,
"grad_norm": 0.9153071045875549,
"learning_rate": 2.1819560097607717e-05,
"loss": 0.3866,
"step": 785
},
{
"epoch": 1.9268292682926829,
"grad_norm": 1.07267427444458,
"learning_rate": 2.1711552610364914e-05,
"loss": 0.39,
"step": 790
},
{
"epoch": 1.9390243902439024,
"grad_norm": 1.155359148979187,
"learning_rate": 2.1603108276990536e-05,
"loss": 0.3738,
"step": 795
},
{
"epoch": 1.951219512195122,
"grad_norm": 1.2188688516616821,
"learning_rate": 2.1494234155983595e-05,
"loss": 0.3394,
"step": 800
},
{
"epoch": 1.9634146341463414,
"grad_norm": 1.0880542993545532,
"learning_rate": 2.1384937333817413e-05,
"loss": 0.3525,
"step": 805
},
{
"epoch": 1.975609756097561,
"grad_norm": 1.1321754455566406,
"learning_rate": 2.1275224924478408e-05,
"loss": 0.324,
"step": 810
},
{
"epoch": 1.9878048780487805,
"grad_norm": 0.9325311779975891,
"learning_rate": 2.1165104069002983e-05,
"loss": 0.3555,
"step": 815
},
{
"epoch": 2.0,
"grad_norm": 0.9841716289520264,
"learning_rate": 2.1054581935012777e-05,
"loss": 0.3838,
"step": 820
}
],
"logging_steps": 5,
"max_steps": 2050,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 2000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.1934379878624788e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}