klora_2000_skill / 7 /trainer_state.json
RayDu0010's picture
Upload folder using huggingface_hub
4592689 verified
raw
history blame
20.1 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 560,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.017889087656529516,
"grad_norm": 1.506656527519226,
"learning_rate": 1.7142857142857143e-06,
"loss": 1.2584,
"step": 5
},
{
"epoch": 0.03577817531305903,
"grad_norm": 0.9500389695167542,
"learning_rate": 3.857142857142857e-06,
"loss": 1.2642,
"step": 10
},
{
"epoch": 0.05366726296958855,
"grad_norm": 0.7999431490898132,
"learning_rate": 6e-06,
"loss": 1.3278,
"step": 15
},
{
"epoch": 0.07155635062611806,
"grad_norm": 0.679018497467041,
"learning_rate": 8.142857142857142e-06,
"loss": 1.2183,
"step": 20
},
{
"epoch": 0.08944543828264759,
"grad_norm": 0.5348811745643616,
"learning_rate": 1.0285714285714286e-05,
"loss": 1.2252,
"step": 25
},
{
"epoch": 0.1073345259391771,
"grad_norm": 0.6638433337211609,
"learning_rate": 1.242857142857143e-05,
"loss": 1.2385,
"step": 30
},
{
"epoch": 0.1252236135957066,
"grad_norm": 0.7031165361404419,
"learning_rate": 1.4571428571428571e-05,
"loss": 1.2,
"step": 35
},
{
"epoch": 0.14311270125223613,
"grad_norm": 0.39686235785484314,
"learning_rate": 1.6714285714285716e-05,
"loss": 1.161,
"step": 40
},
{
"epoch": 0.16100178890876565,
"grad_norm": 0.5343768000602722,
"learning_rate": 1.8857142857142856e-05,
"loss": 1.2075,
"step": 45
},
{
"epoch": 0.17889087656529518,
"grad_norm": 0.47290146350860596,
"learning_rate": 2.1e-05,
"loss": 1.186,
"step": 50
},
{
"epoch": 0.1967799642218247,
"grad_norm": 0.5593580007553101,
"learning_rate": 2.3142857142857145e-05,
"loss": 1.1161,
"step": 55
},
{
"epoch": 0.2146690518783542,
"grad_norm": 0.4979853332042694,
"learning_rate": 2.5285714285714285e-05,
"loss": 1.176,
"step": 60
},
{
"epoch": 0.23255813953488372,
"grad_norm": 0.5528405904769897,
"learning_rate": 2.7428571428571428e-05,
"loss": 1.1656,
"step": 65
},
{
"epoch": 0.2504472271914132,
"grad_norm": 0.46704745292663574,
"learning_rate": 2.9571428571428575e-05,
"loss": 1.1207,
"step": 70
},
{
"epoch": 0.26833631484794274,
"grad_norm": 0.6753780245780945,
"learning_rate": 2.99993304631594e-05,
"loss": 1.0555,
"step": 75
},
{
"epoch": 0.28622540250447226,
"grad_norm": 0.4959678649902344,
"learning_rate": 2.999661057218302e-05,
"loss": 1.0949,
"step": 80
},
{
"epoch": 0.3041144901610018,
"grad_norm": 0.5355138778686523,
"learning_rate": 2.999179886011389e-05,
"loss": 1.0936,
"step": 85
},
{
"epoch": 0.3220035778175313,
"grad_norm": 0.5441014766693115,
"learning_rate": 2.9984895998119723e-05,
"loss": 1.0513,
"step": 90
},
{
"epoch": 0.33989266547406083,
"grad_norm": 0.5444539785385132,
"learning_rate": 2.99759029490549e-05,
"loss": 1.0729,
"step": 95
},
{
"epoch": 0.35778175313059035,
"grad_norm": 0.5886111855506897,
"learning_rate": 2.996482096732619e-05,
"loss": 1.0365,
"step": 100
},
{
"epoch": 0.3756708407871199,
"grad_norm": 0.6149312853813171,
"learning_rate": 2.9951651598717757e-05,
"loss": 1.0499,
"step": 105
},
{
"epoch": 0.3935599284436494,
"grad_norm": 0.5841829180717468,
"learning_rate": 2.9936396680175547e-05,
"loss": 0.9816,
"step": 110
},
{
"epoch": 0.41144901610017887,
"grad_norm": 0.7359195947647095,
"learning_rate": 2.9919058339551068e-05,
"loss": 0.9981,
"step": 115
},
{
"epoch": 0.4293381037567084,
"grad_norm": 0.6694313883781433,
"learning_rate": 2.9899638995304575e-05,
"loss": 0.955,
"step": 120
},
{
"epoch": 0.4472271914132379,
"grad_norm": 0.7220502495765686,
"learning_rate": 2.9878141356167725e-05,
"loss": 0.8753,
"step": 125
},
{
"epoch": 0.46511627906976744,
"grad_norm": 0.6825446486473083,
"learning_rate": 2.9854568420765768e-05,
"loss": 0.961,
"step": 130
},
{
"epoch": 0.48300536672629696,
"grad_norm": 0.7498815655708313,
"learning_rate": 2.982892347719925e-05,
"loss": 0.9166,
"step": 135
},
{
"epoch": 0.5008944543828264,
"grad_norm": 0.7284743189811707,
"learning_rate": 2.9801210102585393e-05,
"loss": 0.9351,
"step": 140
},
{
"epoch": 0.518783542039356,
"grad_norm": 0.8820511102676392,
"learning_rate": 2.9771432162559113e-05,
"loss": 0.9124,
"step": 145
},
{
"epoch": 0.5366726296958855,
"grad_norm": 0.7539326548576355,
"learning_rate": 2.973959381073384e-05,
"loss": 0.846,
"step": 150
},
{
"epoch": 0.554561717352415,
"grad_norm": 0.7277606129646301,
"learning_rate": 2.970569948812214e-05,
"loss": 0.9432,
"step": 155
},
{
"epoch": 0.5724508050089445,
"grad_norm": 0.7533125281333923,
"learning_rate": 2.966975392251624e-05,
"loss": 0.8557,
"step": 160
},
{
"epoch": 0.590339892665474,
"grad_norm": 0.7943282723426819,
"learning_rate": 2.9631762127828584e-05,
"loss": 0.8635,
"step": 165
},
{
"epoch": 0.6082289803220036,
"grad_norm": 0.8900126814842224,
"learning_rate": 2.9591729403392447e-05,
"loss": 0.856,
"step": 170
},
{
"epoch": 0.6261180679785331,
"grad_norm": 0.8534295558929443,
"learning_rate": 2.9549661333222764e-05,
"loss": 0.8737,
"step": 175
},
{
"epoch": 0.6440071556350626,
"grad_norm": 0.7521919012069702,
"learning_rate": 2.950556378523723e-05,
"loss": 0.8129,
"step": 180
},
{
"epoch": 0.6618962432915921,
"grad_norm": 0.8599235415458679,
"learning_rate": 2.9459442910437798e-05,
"loss": 0.7975,
"step": 185
},
{
"epoch": 0.6797853309481217,
"grad_norm": 0.9698217511177063,
"learning_rate": 2.9411305142052725e-05,
"loss": 0.8128,
"step": 190
},
{
"epoch": 0.6976744186046512,
"grad_norm": 0.9345831871032715,
"learning_rate": 2.9361157194639184e-05,
"loss": 0.7551,
"step": 195
},
{
"epoch": 0.7155635062611807,
"grad_norm": 0.7919726967811584,
"learning_rate": 2.9309006063146716e-05,
"loss": 0.7606,
"step": 200
},
{
"epoch": 0.7334525939177102,
"grad_norm": 0.8289109468460083,
"learning_rate": 2.925485902194151e-05,
"loss": 0.7793,
"step": 205
},
{
"epoch": 0.7513416815742398,
"grad_norm": 0.9304677248001099,
"learning_rate": 2.9198723623791724e-05,
"loss": 0.711,
"step": 210
},
{
"epoch": 0.7692307692307693,
"grad_norm": 1.0459802150726318,
"learning_rate": 2.9140607698814e-05,
"loss": 0.737,
"step": 215
},
{
"epoch": 0.7871198568872988,
"grad_norm": 0.9233027696609497,
"learning_rate": 2.9080519353381243e-05,
"loss": 0.7234,
"step": 220
},
{
"epoch": 0.8050089445438283,
"grad_norm": 0.969067394733429,
"learning_rate": 2.9018466968991913e-05,
"loss": 0.712,
"step": 225
},
{
"epoch": 0.8228980322003577,
"grad_norm": 0.8197952508926392,
"learning_rate": 2.8954459201100916e-05,
"loss": 0.7021,
"step": 230
},
{
"epoch": 0.8407871198568873,
"grad_norm": 0.9914915561676025,
"learning_rate": 2.8888504977912284e-05,
"loss": 0.7463,
"step": 235
},
{
"epoch": 0.8586762075134168,
"grad_norm": 1.0100288391113281,
"learning_rate": 2.8820613499133814e-05,
"loss": 0.7186,
"step": 240
},
{
"epoch": 0.8765652951699463,
"grad_norm": 0.9397743344306946,
"learning_rate": 2.875079423469384e-05,
"loss": 0.704,
"step": 245
},
{
"epoch": 0.8944543828264758,
"grad_norm": 1.116220235824585,
"learning_rate": 2.8679056923420294e-05,
"loss": 0.705,
"step": 250
},
{
"epoch": 0.9123434704830053,
"grad_norm": 0.9566684365272522,
"learning_rate": 2.8605411571682295e-05,
"loss": 0.6645,
"step": 255
},
{
"epoch": 0.9302325581395349,
"grad_norm": 0.884859561920166,
"learning_rate": 2.8529868451994387e-05,
"loss": 0.6604,
"step": 260
},
{
"epoch": 0.9481216457960644,
"grad_norm": 1.0066081285476685,
"learning_rate": 2.8452438101583648e-05,
"loss": 0.6933,
"step": 265
},
{
"epoch": 0.9660107334525939,
"grad_norm": 0.992435097694397,
"learning_rate": 2.8373131320919936e-05,
"loss": 0.6576,
"step": 270
},
{
"epoch": 0.9838998211091234,
"grad_norm": 1.1710649728775024,
"learning_rate": 2.8291959172209314e-05,
"loss": 0.6487,
"step": 275
},
{
"epoch": 1.0,
"grad_norm": 1.4341217279434204,
"learning_rate": 2.820893297785107e-05,
"loss": 0.6293,
"step": 280
},
{
"epoch": 1.0178890876565294,
"grad_norm": 1.1913830041885376,
"learning_rate": 2.812406431885838e-05,
"loss": 0.5798,
"step": 285
},
{
"epoch": 1.035778175313059,
"grad_norm": 0.9532171487808228,
"learning_rate": 2.8037365033242917e-05,
"loss": 0.5752,
"step": 290
},
{
"epoch": 1.0536672629695885,
"grad_norm": 1.3926500082015991,
"learning_rate": 2.794884721436361e-05,
"loss": 0.6038,
"step": 295
},
{
"epoch": 1.071556350626118,
"grad_norm": 1.0542120933532715,
"learning_rate": 2.7858523209239785e-05,
"loss": 0.5491,
"step": 300
},
{
"epoch": 1.0894454382826475,
"grad_norm": 1.1710113286972046,
"learning_rate": 2.7766405616828938e-05,
"loss": 0.5183,
"step": 305
},
{
"epoch": 1.1073345259391771,
"grad_norm": 0.9291325211524963,
"learning_rate": 2.7672507286269332e-05,
"loss": 0.5193,
"step": 310
},
{
"epoch": 1.1252236135957066,
"grad_norm": 0.9673988223075867,
"learning_rate": 2.7576841315087744e-05,
"loss": 0.4956,
"step": 315
},
{
"epoch": 1.1431127012522362,
"grad_norm": 1.3483326435089111,
"learning_rate": 2.747942104737252e-05,
"loss": 0.5407,
"step": 320
},
{
"epoch": 1.1610017889087656,
"grad_norm": 0.9651196002960205,
"learning_rate": 2.738026007191226e-05,
"loss": 0.5261,
"step": 325
},
{
"epoch": 1.1788908765652952,
"grad_norm": 1.0171095132827759,
"learning_rate": 2.727937222030039e-05,
"loss": 0.4733,
"step": 330
},
{
"epoch": 1.1967799642218246,
"grad_norm": 1.0522226095199585,
"learning_rate": 2.7176771565005804e-05,
"loss": 0.496,
"step": 335
},
{
"epoch": 1.2146690518783543,
"grad_norm": 1.230334758758545,
"learning_rate": 2.7072472417410002e-05,
"loss": 0.5143,
"step": 340
},
{
"epoch": 1.2325581395348837,
"grad_norm": 1.0268306732177734,
"learning_rate": 2.6966489325810793e-05,
"loss": 0.5221,
"step": 345
},
{
"epoch": 1.250447227191413,
"grad_norm": 0.9560613632202148,
"learning_rate": 2.685883707339305e-05,
"loss": 0.5079,
"step": 350
},
{
"epoch": 1.2683363148479427,
"grad_norm": 1.0826609134674072,
"learning_rate": 2.6749530676166633e-05,
"loss": 0.4486,
"step": 355
},
{
"epoch": 1.2862254025044724,
"grad_norm": 1.1852221488952637,
"learning_rate": 2.663858538087188e-05,
"loss": 0.5147,
"step": 360
},
{
"epoch": 1.3041144901610018,
"grad_norm": 1.1893274784088135,
"learning_rate": 2.6526016662852887e-05,
"loss": 0.4878,
"step": 365
},
{
"epoch": 1.3220035778175312,
"grad_norm": 1.0597422122955322,
"learning_rate": 2.6411840223898902e-05,
"loss": 0.4802,
"step": 370
},
{
"epoch": 1.3398926654740608,
"grad_norm": 1.0407767295837402,
"learning_rate": 2.6296071990054167e-05,
"loss": 0.4368,
"step": 375
},
{
"epoch": 1.3577817531305905,
"grad_norm": 1.2436342239379883,
"learning_rate": 2.6178728109396413e-05,
"loss": 0.4877,
"step": 380
},
{
"epoch": 1.3756708407871199,
"grad_norm": 1.279242753982544,
"learning_rate": 2.6059824949784474e-05,
"loss": 0.4394,
"step": 385
},
{
"epoch": 1.3935599284436493,
"grad_norm": 1.060095191001892,
"learning_rate": 2.5939379096575156e-05,
"loss": 0.4371,
"step": 390
},
{
"epoch": 1.411449016100179,
"grad_norm": 1.1264623403549194,
"learning_rate": 2.5817407350309825e-05,
"loss": 0.4361,
"step": 395
},
{
"epoch": 1.4293381037567083,
"grad_norm": 1.0541681051254272,
"learning_rate": 2.5693926724370958e-05,
"loss": 0.4431,
"step": 400
},
{
"epoch": 1.447227191413238,
"grad_norm": 1.0380645990371704,
"learning_rate": 2.5568954442609016e-05,
"loss": 0.4025,
"step": 405
},
{
"epoch": 1.4651162790697674,
"grad_norm": 1.122382640838623,
"learning_rate": 2.544250793693995e-05,
"loss": 0.4379,
"step": 410
},
{
"epoch": 1.483005366726297,
"grad_norm": 1.0751020908355713,
"learning_rate": 2.531460484491368e-05,
"loss": 0.4328,
"step": 415
},
{
"epoch": 1.5008944543828264,
"grad_norm": 1.234891653060913,
"learning_rate": 2.5185263007253912e-05,
"loss": 0.4375,
"step": 420
},
{
"epoch": 1.518783542039356,
"grad_norm": 1.4189293384552002,
"learning_rate": 2.5054500465369597e-05,
"loss": 0.4321,
"step": 425
},
{
"epoch": 1.5366726296958855,
"grad_norm": 1.1898143291473389,
"learning_rate": 2.4922335458838397e-05,
"loss": 0.4428,
"step": 430
},
{
"epoch": 1.5545617173524149,
"grad_norm": 0.9852802753448486,
"learning_rate": 2.478878642286253e-05,
"loss": 0.4321,
"step": 435
},
{
"epoch": 1.5724508050089445,
"grad_norm": 1.0897939205169678,
"learning_rate": 2.465387198569729e-05,
"loss": 0.4173,
"step": 440
},
{
"epoch": 1.5903398926654742,
"grad_norm": 1.1859195232391357,
"learning_rate": 2.4517610966052682e-05,
"loss": 0.3929,
"step": 445
},
{
"epoch": 1.6082289803220036,
"grad_norm": 1.2279844284057617,
"learning_rate": 2.4380022370468464e-05,
"loss": 0.4279,
"step": 450
},
{
"epoch": 1.626118067978533,
"grad_norm": 1.1750357151031494,
"learning_rate": 2.4241125390662982e-05,
"loss": 0.3863,
"step": 455
},
{
"epoch": 1.6440071556350626,
"grad_norm": 1.1458582878112793,
"learning_rate": 2.4100939400856216e-05,
"loss": 0.4131,
"step": 460
},
{
"epoch": 1.6618962432915922,
"grad_norm": 1.0942723751068115,
"learning_rate": 2.395948395506731e-05,
"loss": 0.3943,
"step": 465
},
{
"epoch": 1.6797853309481217,
"grad_norm": 0.9955680966377258,
"learning_rate": 2.3816778784387097e-05,
"loss": 0.3774,
"step": 470
},
{
"epoch": 1.697674418604651,
"grad_norm": 1.2159160375595093,
"learning_rate": 2.367284379422584e-05,
"loss": 0.3674,
"step": 475
},
{
"epoch": 1.7155635062611807,
"grad_norm": 1.143467664718628,
"learning_rate": 2.3527699061536726e-05,
"loss": 0.3777,
"step": 480
},
{
"epoch": 1.7334525939177103,
"grad_norm": 1.0947456359863281,
"learning_rate": 2.338136483201539e-05,
"loss": 0.3947,
"step": 485
},
{
"epoch": 1.7513416815742398,
"grad_norm": 1.0965192317962646,
"learning_rate": 2.323386151727595e-05,
"loss": 0.3732,
"step": 490
},
{
"epoch": 1.7692307692307692,
"grad_norm": 1.1917636394500732,
"learning_rate": 2.3085209692003836e-05,
"loss": 0.369,
"step": 495
},
{
"epoch": 1.7871198568872988,
"grad_norm": 1.117609977722168,
"learning_rate": 2.2935430091085904e-05,
"loss": 0.3933,
"step": 500
},
{
"epoch": 1.8050089445438284,
"grad_norm": 1.2263697385787964,
"learning_rate": 2.2784543606718227e-05,
"loss": 0.4066,
"step": 505
},
{
"epoch": 1.8228980322003578,
"grad_norm": 1.1519149541854858,
"learning_rate": 2.263257128549191e-05,
"loss": 0.3776,
"step": 510
},
{
"epoch": 1.8407871198568873,
"grad_norm": 1.001869797706604,
"learning_rate": 2.2479534325457374e-05,
"loss": 0.3576,
"step": 515
},
{
"epoch": 1.8586762075134167,
"grad_norm": 1.0438801050186157,
"learning_rate": 2.2325454073167518e-05,
"loss": 0.3951,
"step": 520
},
{
"epoch": 1.8765652951699463,
"grad_norm": 1.1146963834762573,
"learning_rate": 2.2170352020700187e-05,
"loss": 0.3637,
"step": 525
},
{
"epoch": 1.894454382826476,
"grad_norm": 1.0773694515228271,
"learning_rate": 2.2014249802660297e-05,
"loss": 0.3596,
"step": 530
},
{
"epoch": 1.9123434704830053,
"grad_norm": 1.0742276906967163,
"learning_rate": 2.185716919316212e-05,
"loss": 0.3641,
"step": 535
},
{
"epoch": 1.9302325581395348,
"grad_norm": 1.118898630142212,
"learning_rate": 2.16991321027921e-05,
"loss": 0.3598,
"step": 540
},
{
"epoch": 1.9481216457960644,
"grad_norm": 1.1367541551589966,
"learning_rate": 2.1540160575552604e-05,
"loss": 0.3532,
"step": 545
},
{
"epoch": 1.966010733452594,
"grad_norm": 1.0174490213394165,
"learning_rate": 2.138027678578712e-05,
"loss": 0.3277,
"step": 550
},
{
"epoch": 1.9838998211091234,
"grad_norm": 1.1238727569580078,
"learning_rate": 2.1219503035087202e-05,
"loss": 0.302,
"step": 555
},
{
"epoch": 2.0,
"grad_norm": 1.766844391822815,
"learning_rate": 2.1057861749181743e-05,
"loss": 0.3191,
"step": 560
}
],
"logging_steps": 5,
"max_steps": 1400,
"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": 8.135566147023012e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}