klora_2000_skill / 48 /trainer_state.json
RayDu0010's picture
Upload folder using huggingface_hub
11ab7d2 verified
raw
history blame
21 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 588,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.017006802721088437,
"grad_norm": 1.1845334768295288,
"learning_rate": 1.6216216216216219e-06,
"loss": 1.3293,
"step": 5
},
{
"epoch": 0.034013605442176874,
"grad_norm": 1.0181540250778198,
"learning_rate": 3.648648648648649e-06,
"loss": 1.2783,
"step": 10
},
{
"epoch": 0.05102040816326531,
"grad_norm": 0.6886288523674011,
"learning_rate": 5.675675675675676e-06,
"loss": 1.2906,
"step": 15
},
{
"epoch": 0.06802721088435375,
"grad_norm": 0.6959572434425354,
"learning_rate": 7.702702702702703e-06,
"loss": 1.2818,
"step": 20
},
{
"epoch": 0.08503401360544217,
"grad_norm": 0.6249067187309265,
"learning_rate": 9.72972972972973e-06,
"loss": 1.2667,
"step": 25
},
{
"epoch": 0.10204081632653061,
"grad_norm": 0.5868192911148071,
"learning_rate": 1.1756756756756757e-05,
"loss": 1.2477,
"step": 30
},
{
"epoch": 0.11904761904761904,
"grad_norm": 0.5181043148040771,
"learning_rate": 1.3783783783783784e-05,
"loss": 1.2207,
"step": 35
},
{
"epoch": 0.1360544217687075,
"grad_norm": 0.4317700266838074,
"learning_rate": 1.5810810810810808e-05,
"loss": 1.21,
"step": 40
},
{
"epoch": 0.15306122448979592,
"grad_norm": 0.4549165964126587,
"learning_rate": 1.783783783783784e-05,
"loss": 1.1368,
"step": 45
},
{
"epoch": 0.17006802721088435,
"grad_norm": 0.5308559536933899,
"learning_rate": 1.9864864864864866e-05,
"loss": 1.1875,
"step": 50
},
{
"epoch": 0.1870748299319728,
"grad_norm": 0.5514539480209351,
"learning_rate": 2.1891891891891892e-05,
"loss": 1.1593,
"step": 55
},
{
"epoch": 0.20408163265306123,
"grad_norm": 0.46228182315826416,
"learning_rate": 2.3918918918918917e-05,
"loss": 1.1345,
"step": 60
},
{
"epoch": 0.22108843537414966,
"grad_norm": 0.5649062395095825,
"learning_rate": 2.594594594594595e-05,
"loss": 1.1065,
"step": 65
},
{
"epoch": 0.23809523809523808,
"grad_norm": 0.49446532130241394,
"learning_rate": 2.7972972972972975e-05,
"loss": 1.1328,
"step": 70
},
{
"epoch": 0.25510204081632654,
"grad_norm": 0.5560067296028137,
"learning_rate": 3e-05,
"loss": 1.1697,
"step": 75
},
{
"epoch": 0.272108843537415,
"grad_norm": 0.4814499616622925,
"learning_rate": 2.999905043303196e-05,
"loss": 1.1659,
"step": 80
},
{
"epoch": 0.2891156462585034,
"grad_norm": 0.5074186325073242,
"learning_rate": 2.999620185235149e-05,
"loss": 1.0924,
"step": 85
},
{
"epoch": 0.30612244897959184,
"grad_norm": 0.592327892780304,
"learning_rate": 2.9991454618614338e-05,
"loss": 1.0793,
"step": 90
},
{
"epoch": 0.3231292517006803,
"grad_norm": 0.5456128120422363,
"learning_rate": 2.998480933286269e-05,
"loss": 1.0836,
"step": 95
},
{
"epoch": 0.3401360544217687,
"grad_norm": 0.6163952946662903,
"learning_rate": 2.9976266836449057e-05,
"loss": 1.0816,
"step": 100
},
{
"epoch": 0.35714285714285715,
"grad_norm": 0.5601843595504761,
"learning_rate": 2.9965828210929758e-05,
"loss": 1.091,
"step": 105
},
{
"epoch": 0.3741496598639456,
"grad_norm": 0.5945920944213867,
"learning_rate": 2.9953494777927995e-05,
"loss": 1.0349,
"step": 110
},
{
"epoch": 0.391156462585034,
"grad_norm": 0.5780587792396545,
"learning_rate": 2.993926809896651e-05,
"loss": 1.0389,
"step": 115
},
{
"epoch": 0.40816326530612246,
"grad_norm": 0.6240988969802856,
"learning_rate": 2.9923149975269885e-05,
"loss": 1.0521,
"step": 120
},
{
"epoch": 0.42517006802721086,
"grad_norm": 0.6076016426086426,
"learning_rate": 2.990514244753651e-05,
"loss": 0.9944,
"step": 125
},
{
"epoch": 0.4421768707482993,
"grad_norm": 0.6623475551605225,
"learning_rate": 2.988524779568018e-05,
"loss": 0.935,
"step": 130
},
{
"epoch": 0.45918367346938777,
"grad_norm": 0.6462083458900452,
"learning_rate": 2.9863468538541466e-05,
"loss": 1.0017,
"step": 135
},
{
"epoch": 0.47619047619047616,
"grad_norm": 0.6660473346710205,
"learning_rate": 2.9839807433568787e-05,
"loss": 0.8931,
"step": 140
},
{
"epoch": 0.4931972789115646,
"grad_norm": 0.680072546005249,
"learning_rate": 2.9814267476469304e-05,
"loss": 0.9786,
"step": 145
},
{
"epoch": 0.5102040816326531,
"grad_norm": 0.6932852268218994,
"learning_rate": 2.9786851900829633e-05,
"loss": 0.9335,
"step": 150
},
{
"epoch": 0.5272108843537415,
"grad_norm": 0.7095908522605896,
"learning_rate": 2.9757564177706448e-05,
"loss": 0.9278,
"step": 155
},
{
"epoch": 0.54421768707483,
"grad_norm": 0.7165976762771606,
"learning_rate": 2.972640801518701e-05,
"loss": 0.9029,
"step": 160
},
{
"epoch": 0.5612244897959183,
"grad_norm": 0.745604395866394,
"learning_rate": 2.969338735791968e-05,
"loss": 0.8675,
"step": 165
},
{
"epoch": 0.5782312925170068,
"grad_norm": 0.6811717748641968,
"learning_rate": 2.9658506386614525e-05,
"loss": 0.9125,
"step": 170
},
{
"epoch": 0.5952380952380952,
"grad_norm": 0.7211567163467407,
"learning_rate": 2.962176951751396e-05,
"loss": 0.8937,
"step": 175
},
{
"epoch": 0.6122448979591837,
"grad_norm": 0.7217546701431274,
"learning_rate": 2.958318140183364e-05,
"loss": 0.9474,
"step": 180
},
{
"epoch": 0.6292517006802721,
"grad_norm": 0.7711513042449951,
"learning_rate": 2.9542746925173566e-05,
"loss": 0.882,
"step": 185
},
{
"epoch": 0.6462585034013606,
"grad_norm": 0.8753324747085571,
"learning_rate": 2.9500471206899528e-05,
"loss": 0.874,
"step": 190
},
{
"epoch": 0.6632653061224489,
"grad_norm": 0.873315691947937,
"learning_rate": 2.945635959949494e-05,
"loss": 0.8252,
"step": 195
},
{
"epoch": 0.6802721088435374,
"grad_norm": 1.0285780429840088,
"learning_rate": 2.9410417687883173e-05,
"loss": 0.885,
"step": 200
},
{
"epoch": 0.6972789115646258,
"grad_norm": 0.8351210951805115,
"learning_rate": 2.936265128872046e-05,
"loss": 0.8756,
"step": 205
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.8613854646682739,
"learning_rate": 2.931306644965944e-05,
"loss": 0.8489,
"step": 210
},
{
"epoch": 0.7312925170068028,
"grad_norm": 0.9348616003990173,
"learning_rate": 2.9261669448583492e-05,
"loss": 0.8657,
"step": 215
},
{
"epoch": 0.7482993197278912,
"grad_norm": 1.0146417617797852,
"learning_rate": 2.9208466792811875e-05,
"loss": 0.815,
"step": 220
},
{
"epoch": 0.7653061224489796,
"grad_norm": 0.9285673499107361,
"learning_rate": 2.915346521827586e-05,
"loss": 0.8164,
"step": 225
},
{
"epoch": 0.782312925170068,
"grad_norm": 0.951054573059082,
"learning_rate": 2.9096671688665893e-05,
"loss": 0.8515,
"step": 230
},
{
"epoch": 0.7993197278911565,
"grad_norm": 0.9739980697631836,
"learning_rate": 2.9038093394549946e-05,
"loss": 0.7521,
"step": 235
},
{
"epoch": 0.8163265306122449,
"grad_norm": 1.0542875528335571,
"learning_rate": 2.8977737752463094e-05,
"loss": 0.8105,
"step": 240
},
{
"epoch": 0.8333333333333334,
"grad_norm": 0.9150990843772888,
"learning_rate": 2.891561240396855e-05,
"loss": 0.8032,
"step": 245
},
{
"epoch": 0.8503401360544217,
"grad_norm": 1.0160540342330933,
"learning_rate": 2.8851725214690155e-05,
"loss": 0.7096,
"step": 250
},
{
"epoch": 0.8673469387755102,
"grad_norm": 0.9452092051506042,
"learning_rate": 2.8786084273316524e-05,
"loss": 0.6958,
"step": 255
},
{
"epoch": 0.8843537414965986,
"grad_norm": 0.8861579895019531,
"learning_rate": 2.8718697890576944e-05,
"loss": 0.7085,
"step": 260
},
{
"epoch": 0.9013605442176871,
"grad_norm": 1.0629994869232178,
"learning_rate": 2.864957459818918e-05,
"loss": 0.6941,
"step": 265
},
{
"epoch": 0.9183673469387755,
"grad_norm": 0.9347429275512695,
"learning_rate": 2.8578723147779237e-05,
"loss": 0.689,
"step": 270
},
{
"epoch": 0.935374149659864,
"grad_norm": 1.0432939529418945,
"learning_rate": 2.850615250977339e-05,
"loss": 0.7042,
"step": 275
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.948538601398468,
"learning_rate": 2.843187187226239e-05,
"loss": 0.7113,
"step": 280
},
{
"epoch": 0.9693877551020408,
"grad_norm": 1.053505778312683,
"learning_rate": 2.835589063983821e-05,
"loss": 0.7173,
"step": 285
},
{
"epoch": 0.9863945578231292,
"grad_norm": 0.9371920824050903,
"learning_rate": 2.827821843240331e-05,
"loss": 0.6272,
"step": 290
},
{
"epoch": 1.0034013605442176,
"grad_norm": 1.1553608179092407,
"learning_rate": 2.8198865083952694e-05,
"loss": 0.6671,
"step": 295
},
{
"epoch": 1.0204081632653061,
"grad_norm": 1.0597134828567505,
"learning_rate": 2.811784064132883e-05,
"loss": 0.6007,
"step": 300
},
{
"epoch": 1.0374149659863945,
"grad_norm": 1.1430370807647705,
"learning_rate": 2.803515536294963e-05,
"loss": 0.6015,
"step": 305
},
{
"epoch": 1.054421768707483,
"grad_norm": 1.0705440044403076,
"learning_rate": 2.795081971750963e-05,
"loss": 0.5987,
"step": 310
},
{
"epoch": 1.0714285714285714,
"grad_norm": 1.1100271940231323,
"learning_rate": 2.786484438265459e-05,
"loss": 0.6058,
"step": 315
},
{
"epoch": 1.08843537414966,
"grad_norm": 1.1145716905593872,
"learning_rate": 2.7777240243629578e-05,
"loss": 0.5264,
"step": 320
},
{
"epoch": 1.1054421768707483,
"grad_norm": 1.0852850675582886,
"learning_rate": 2.7688018391900826e-05,
"loss": 0.549,
"step": 325
},
{
"epoch": 1.1224489795918366,
"grad_norm": 1.1767306327819824,
"learning_rate": 2.7597190123751422e-05,
"loss": 0.5997,
"step": 330
},
{
"epoch": 1.1394557823129252,
"grad_norm": 1.2128592729568481,
"learning_rate": 2.750476693885113e-05,
"loss": 0.5681,
"step": 335
},
{
"epoch": 1.1564625850340136,
"grad_norm": 1.313896894454956,
"learning_rate": 2.7410760538800408e-05,
"loss": 0.5698,
"step": 340
},
{
"epoch": 1.1734693877551021,
"grad_norm": 1.1703464984893799,
"learning_rate": 2.7315182825648895e-05,
"loss": 0.569,
"step": 345
},
{
"epoch": 1.1904761904761905,
"grad_norm": 1.1567600965499878,
"learning_rate": 2.7218045900388504e-05,
"loss": 0.5139,
"step": 350
},
{
"epoch": 1.2074829931972788,
"grad_norm": 1.097703456878662,
"learning_rate": 2.7119362061421303e-05,
"loss": 0.5093,
"step": 355
},
{
"epoch": 1.2244897959183674,
"grad_norm": 1.0932475328445435,
"learning_rate": 2.7019143803002465e-05,
"loss": 0.5731,
"step": 360
},
{
"epoch": 1.2414965986394557,
"grad_norm": 1.2174867391586304,
"learning_rate": 2.6917403813658364e-05,
"loss": 0.5077,
"step": 365
},
{
"epoch": 1.2585034013605443,
"grad_norm": 1.0711535215377808,
"learning_rate": 2.6814154974580092e-05,
"loss": 0.5205,
"step": 370
},
{
"epoch": 1.2755102040816326,
"grad_norm": 1.1222914457321167,
"learning_rate": 2.67094103579926e-05,
"loss": 0.5386,
"step": 375
},
{
"epoch": 1.2925170068027212,
"grad_norm": 1.1327167749404907,
"learning_rate": 2.6603183225499608e-05,
"loss": 0.5446,
"step": 380
},
{
"epoch": 1.3095238095238095,
"grad_norm": 1.2905243635177612,
"learning_rate": 2.6495487026404607e-05,
"loss": 0.5009,
"step": 385
},
{
"epoch": 1.3265306122448979,
"grad_norm": 1.059859037399292,
"learning_rate": 2.6386335396008033e-05,
"loss": 0.4772,
"step": 390
},
{
"epoch": 1.3435374149659864,
"grad_norm": 1.329107403755188,
"learning_rate": 2.6275742153880907e-05,
"loss": 0.5027,
"step": 395
},
{
"epoch": 1.3605442176870748,
"grad_norm": 1.1252979040145874,
"learning_rate": 2.6163721302115184e-05,
"loss": 0.4714,
"step": 400
},
{
"epoch": 1.3775510204081631,
"grad_norm": 1.1349155902862549,
"learning_rate": 2.6050287023550936e-05,
"loss": 0.4851,
"step": 405
},
{
"epoch": 1.3945578231292517,
"grad_norm": 1.0614500045776367,
"learning_rate": 2.59354536799807e-05,
"loss": 0.4893,
"step": 410
},
{
"epoch": 1.4115646258503403,
"grad_norm": 1.2005356550216675,
"learning_rate": 2.5819235810331115e-05,
"loss": 0.5233,
"step": 415
},
{
"epoch": 1.4285714285714286,
"grad_norm": 1.0654675960540771,
"learning_rate": 2.5701648128822205e-05,
"loss": 0.4876,
"step": 420
},
{
"epoch": 1.445578231292517,
"grad_norm": 1.3152744770050049,
"learning_rate": 2.55827055231044e-05,
"loss": 0.5113,
"step": 425
},
{
"epoch": 1.4625850340136055,
"grad_norm": 1.0852030515670776,
"learning_rate": 2.5462423052373628e-05,
"loss": 0.4794,
"step": 430
},
{
"epoch": 1.4795918367346939,
"grad_norm": 1.1766146421432495,
"learning_rate": 2.534081594546469e-05,
"loss": 0.4488,
"step": 435
},
{
"epoch": 1.4965986394557822,
"grad_norm": 1.2981992959976196,
"learning_rate": 2.5217899598923162e-05,
"loss": 0.4567,
"step": 440
},
{
"epoch": 1.5136054421768708,
"grad_norm": 1.0443862676620483,
"learning_rate": 2.5093689575056045e-05,
"loss": 0.4448,
"step": 445
},
{
"epoch": 1.5306122448979593,
"grad_norm": 1.130210280418396,
"learning_rate": 2.4968201599961445e-05,
"loss": 0.439,
"step": 450
},
{
"epoch": 1.5476190476190477,
"grad_norm": 1.3261239528656006,
"learning_rate": 2.4841451561537496e-05,
"loss": 0.4577,
"step": 455
},
{
"epoch": 1.564625850340136,
"grad_norm": 1.1579346656799316,
"learning_rate": 2.471345550747082e-05,
"loss": 0.4915,
"step": 460
},
{
"epoch": 1.5816326530612246,
"grad_norm": 1.1824404001235962,
"learning_rate": 2.4584229643204755e-05,
"loss": 0.4404,
"step": 465
},
{
"epoch": 1.598639455782313,
"grad_norm": 1.175586223602295,
"learning_rate": 2.4453790329887578e-05,
"loss": 0.4649,
"step": 470
},
{
"epoch": 1.6156462585034013,
"grad_norm": 1.5084452629089355,
"learning_rate": 2.4322154082301065e-05,
"loss": 0.4425,
"step": 475
},
{
"epoch": 1.6326530612244898,
"grad_norm": 1.2946665287017822,
"learning_rate": 2.4189337566769545e-05,
"loss": 0.47,
"step": 480
},
{
"epoch": 1.6496598639455784,
"grad_norm": 1.0975319147109985,
"learning_rate": 2.4055357599049807e-05,
"loss": 0.4747,
"step": 485
},
{
"epoch": 1.6666666666666665,
"grad_norm": 1.0334219932556152,
"learning_rate": 2.392023114220209e-05,
"loss": 0.4076,
"step": 490
},
{
"epoch": 1.683673469387755,
"grad_norm": 1.2870817184448242,
"learning_rate": 2.378397530444238e-05,
"loss": 0.4198,
"step": 495
},
{
"epoch": 1.7006802721088436,
"grad_norm": 1.0723446607589722,
"learning_rate": 2.3646607336976375e-05,
"loss": 0.4536,
"step": 500
},
{
"epoch": 1.717687074829932,
"grad_norm": 1.3169423341751099,
"learning_rate": 2.3508144631815326e-05,
"loss": 0.4213,
"step": 505
},
{
"epoch": 1.7346938775510203,
"grad_norm": 1.2261208295822144,
"learning_rate": 2.3368604719574055e-05,
"loss": 0.4414,
"step": 510
},
{
"epoch": 1.751700680272109,
"grad_norm": 1.2695997953414917,
"learning_rate": 2.322800526725141e-05,
"loss": 0.3781,
"step": 515
},
{
"epoch": 1.7687074829931972,
"grad_norm": 1.421828269958496,
"learning_rate": 2.308636407599347e-05,
"loss": 0.4473,
"step": 520
},
{
"epoch": 1.7857142857142856,
"grad_norm": 1.2838345766067505,
"learning_rate": 2.2943699078839783e-05,
"loss": 0.4126,
"step": 525
},
{
"epoch": 1.8027210884353742,
"grad_norm": 1.290840983390808,
"learning_rate": 2.2800028338452853e-05,
"loss": 0.4035,
"step": 530
},
{
"epoch": 1.8197278911564627,
"grad_norm": 1.3847336769104004,
"learning_rate": 2.2655370044831253e-05,
"loss": 0.378,
"step": 535
},
{
"epoch": 1.836734693877551,
"grad_norm": 1.149859070777893,
"learning_rate": 2.2509742513006633e-05,
"loss": 0.3737,
"step": 540
},
{
"epoch": 1.8537414965986394,
"grad_norm": 1.0945329666137695,
"learning_rate": 2.2363164180724828e-05,
"loss": 0.4016,
"step": 545
},
{
"epoch": 1.870748299319728,
"grad_norm": 1.2481576204299927,
"learning_rate": 2.2215653606111515e-05,
"loss": 0.4054,
"step": 550
},
{
"epoch": 1.8877551020408163,
"grad_norm": 1.065503478050232,
"learning_rate": 2.2067229465322578e-05,
"loss": 0.3944,
"step": 555
},
{
"epoch": 1.9047619047619047,
"grad_norm": 1.2339270114898682,
"learning_rate": 2.1917910550179527e-05,
"loss": 0.3505,
"step": 560
},
{
"epoch": 1.9217687074829932,
"grad_norm": 1.1712156534194946,
"learning_rate": 2.1767715765790303e-05,
"loss": 0.3497,
"step": 565
},
{
"epoch": 1.9387755102040818,
"grad_norm": 1.4303723573684692,
"learning_rate": 2.16166641281557e-05,
"loss": 0.3772,
"step": 570
},
{
"epoch": 1.95578231292517,
"grad_norm": 1.123719573020935,
"learning_rate": 2.1464774761761805e-05,
"loss": 0.3558,
"step": 575
},
{
"epoch": 1.9727891156462585,
"grad_norm": 1.1126965284347534,
"learning_rate": 2.131206689715863e-05,
"loss": 0.3763,
"step": 580
},
{
"epoch": 1.989795918367347,
"grad_norm": 1.0419843196868896,
"learning_rate": 2.1158559868525374e-05,
"loss": 0.3507,
"step": 585
}
],
"logging_steps": 5,
"max_steps": 1470,
"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": 8.596227027789414e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}