klora_2000_skill / 100 /trainer_state.json
RayDu0010's picture
Upload folder using huggingface_hub
e5e01d4 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 346,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01447178002894356,
"grad_norm": 1.2414709329605103,
"learning_rate": 1.3793103448275862e-06,
"loss": 1.2575,
"step": 5
},
{
"epoch": 0.02894356005788712,
"grad_norm": 0.995053231716156,
"learning_rate": 3.103448275862069e-06,
"loss": 1.2964,
"step": 10
},
{
"epoch": 0.04341534008683068,
"grad_norm": 0.6870602369308472,
"learning_rate": 4.827586206896552e-06,
"loss": 1.2136,
"step": 15
},
{
"epoch": 0.05788712011577424,
"grad_norm": 0.7477986216545105,
"learning_rate": 6.551724137931035e-06,
"loss": 1.208,
"step": 20
},
{
"epoch": 0.0723589001447178,
"grad_norm": 0.503740131855011,
"learning_rate": 8.275862068965517e-06,
"loss": 1.262,
"step": 25
},
{
"epoch": 0.08683068017366136,
"grad_norm": 0.5463724732398987,
"learning_rate": 9.999999999999999e-06,
"loss": 1.1591,
"step": 30
},
{
"epoch": 0.10130246020260492,
"grad_norm": 0.5826733112335205,
"learning_rate": 1.1724137931034483e-05,
"loss": 1.1859,
"step": 35
},
{
"epoch": 0.11577424023154848,
"grad_norm": 0.478679895401001,
"learning_rate": 1.3448275862068966e-05,
"loss": 1.1185,
"step": 40
},
{
"epoch": 0.13024602026049203,
"grad_norm": 0.45855218172073364,
"learning_rate": 1.517241379310345e-05,
"loss": 1.0916,
"step": 45
},
{
"epoch": 0.1447178002894356,
"grad_norm": 0.4334068298339844,
"learning_rate": 1.6896551724137932e-05,
"loss": 1.1103,
"step": 50
},
{
"epoch": 0.15918958031837915,
"grad_norm": 0.49706199765205383,
"learning_rate": 1.8620689655172415e-05,
"loss": 1.1351,
"step": 55
},
{
"epoch": 0.1736613603473227,
"grad_norm": 0.5013290643692017,
"learning_rate": 2.0344827586206894e-05,
"loss": 1.1267,
"step": 60
},
{
"epoch": 0.18813314037626627,
"grad_norm": 0.4919586181640625,
"learning_rate": 2.206896551724138e-05,
"loss": 1.0824,
"step": 65
},
{
"epoch": 0.20260492040520983,
"grad_norm": 0.4955993890762329,
"learning_rate": 2.3793103448275862e-05,
"loss": 1.088,
"step": 70
},
{
"epoch": 0.2170767004341534,
"grad_norm": 0.47736915946006775,
"learning_rate": 2.5517241379310345e-05,
"loss": 1.097,
"step": 75
},
{
"epoch": 0.23154848046309695,
"grad_norm": 0.4829305112361908,
"learning_rate": 2.7241379310344827e-05,
"loss": 1.0582,
"step": 80
},
{
"epoch": 0.2460202604920405,
"grad_norm": 0.5232416391372681,
"learning_rate": 2.8965517241379313e-05,
"loss": 1.0447,
"step": 85
},
{
"epoch": 0.26049204052098407,
"grad_norm": 0.5268356800079346,
"learning_rate": 2.999989031547876e-05,
"loss": 1.0425,
"step": 90
},
{
"epoch": 0.27496382054992763,
"grad_norm": 0.6044050455093384,
"learning_rate": 2.9998656383036702e-05,
"loss": 0.9967,
"step": 95
},
{
"epoch": 0.2894356005788712,
"grad_norm": 0.5722519755363464,
"learning_rate": 2.9996051525662343e-05,
"loss": 0.9925,
"step": 100
},
{
"epoch": 0.30390738060781475,
"grad_norm": 0.5845656991004944,
"learning_rate": 2.9992075981447947e-05,
"loss": 0.9589,
"step": 105
},
{
"epoch": 0.3183791606367583,
"grad_norm": 0.6687687635421753,
"learning_rate": 2.9986730113770898e-05,
"loss": 0.9607,
"step": 110
},
{
"epoch": 0.33285094066570187,
"grad_norm": 0.5653572678565979,
"learning_rate": 2.9980014411260523e-05,
"loss": 0.9765,
"step": 115
},
{
"epoch": 0.3473227206946454,
"grad_norm": 0.6110051274299622,
"learning_rate": 2.9971929487753402e-05,
"loss": 0.9347,
"step": 120
},
{
"epoch": 0.361794500723589,
"grad_norm": 0.6042832136154175,
"learning_rate": 2.9962476082237285e-05,
"loss": 0.8882,
"step": 125
},
{
"epoch": 0.37626628075253254,
"grad_norm": 0.6558710932731628,
"learning_rate": 2.9951655058783517e-05,
"loss": 0.9611,
"step": 130
},
{
"epoch": 0.3907380607814761,
"grad_norm": 0.6648174524307251,
"learning_rate": 2.993946740646809e-05,
"loss": 0.9514,
"step": 135
},
{
"epoch": 0.40520984081041966,
"grad_norm": 0.6010047793388367,
"learning_rate": 2.992591423928121e-05,
"loss": 0.8977,
"step": 140
},
{
"epoch": 0.4196816208393632,
"grad_norm": 0.594023585319519,
"learning_rate": 2.99109967960255e-05,
"loss": 0.9169,
"step": 145
},
{
"epoch": 0.4341534008683068,
"grad_norm": 0.6303651928901672,
"learning_rate": 2.9894716440202756e-05,
"loss": 0.8779,
"step": 150
},
{
"epoch": 0.44862518089725034,
"grad_norm": 0.6532771587371826,
"learning_rate": 2.9877074659889316e-05,
"loss": 0.8661,
"step": 155
},
{
"epoch": 0.4630969609261939,
"grad_norm": 0.7434287071228027,
"learning_rate": 2.9858073067600054e-05,
"loss": 0.8627,
"step": 160
},
{
"epoch": 0.47756874095513746,
"grad_norm": 0.7219240069389343,
"learning_rate": 2.983771340014098e-05,
"loss": 0.8855,
"step": 165
},
{
"epoch": 0.492040520984081,
"grad_norm": 0.7225666046142578,
"learning_rate": 2.981599751845051e-05,
"loss": 0.8531,
"step": 170
},
{
"epoch": 0.5065123010130246,
"grad_norm": 0.7195663452148438,
"learning_rate": 2.9792927407429344e-05,
"loss": 0.8174,
"step": 175
},
{
"epoch": 0.5209840810419681,
"grad_norm": 0.7346758842468262,
"learning_rate": 2.976850517575906e-05,
"loss": 0.8491,
"step": 180
},
{
"epoch": 0.5354558610709117,
"grad_norm": 0.7614021897315979,
"learning_rate": 2.9742733055709366e-05,
"loss": 0.8102,
"step": 185
},
{
"epoch": 0.5499276410998553,
"grad_norm": 0.7299443483352661,
"learning_rate": 2.9715613402934064e-05,
"loss": 0.7749,
"step": 190
},
{
"epoch": 0.5643994211287988,
"grad_norm": 0.7258509993553162,
"learning_rate": 2.9687148696255737e-05,
"loss": 0.8408,
"step": 195
},
{
"epoch": 0.5788712011577424,
"grad_norm": 0.8355885148048401,
"learning_rate": 2.9657341537439176e-05,
"loss": 0.7793,
"step": 200
},
{
"epoch": 0.5933429811866859,
"grad_norm": 0.7875196933746338,
"learning_rate": 2.9626194650953563e-05,
"loss": 0.8168,
"step": 205
},
{
"epoch": 0.6078147612156295,
"grad_norm": 1.2102893590927124,
"learning_rate": 2.9593710883723465e-05,
"loss": 0.7554,
"step": 210
},
{
"epoch": 0.622286541244573,
"grad_norm": 0.9075624346733093,
"learning_rate": 2.95598932048686e-05,
"loss": 0.7782,
"step": 215
},
{
"epoch": 0.6367583212735166,
"grad_norm": 0.9814792275428772,
"learning_rate": 2.9524744705432446e-05,
"loss": 0.7679,
"step": 220
},
{
"epoch": 0.6512301013024602,
"grad_norm": 0.8673927187919617,
"learning_rate": 2.9488268598099735e-05,
"loss": 0.7131,
"step": 225
},
{
"epoch": 0.6657018813314037,
"grad_norm": 1.2335319519042969,
"learning_rate": 2.945046821690277e-05,
"loss": 0.7368,
"step": 230
},
{
"epoch": 0.6801736613603473,
"grad_norm": 1.0025559663772583,
"learning_rate": 2.9411347016916704e-05,
"loss": 0.7447,
"step": 235
},
{
"epoch": 0.6946454413892909,
"grad_norm": 0.8002074360847473,
"learning_rate": 2.9370908573943737e-05,
"loss": 0.7396,
"step": 240
},
{
"epoch": 0.7091172214182344,
"grad_norm": 0.7924606800079346,
"learning_rate": 2.9329156584186267e-05,
"loss": 0.7821,
"step": 245
},
{
"epoch": 0.723589001447178,
"grad_norm": 0.8294292092323303,
"learning_rate": 2.9286094863909053e-05,
"loss": 0.7546,
"step": 250
},
{
"epoch": 0.7380607814761215,
"grad_norm": 0.8875476121902466,
"learning_rate": 2.924172734909038e-05,
"loss": 0.7541,
"step": 255
},
{
"epoch": 0.7525325615050651,
"grad_norm": 1.0516374111175537,
"learning_rate": 2.919605809506233e-05,
"loss": 0.7339,
"step": 260
},
{
"epoch": 0.7670043415340086,
"grad_norm": 0.9758723378181458,
"learning_rate": 2.9149091276140066e-05,
"loss": 0.7286,
"step": 265
},
{
"epoch": 0.7814761215629522,
"grad_norm": 0.8721650838851929,
"learning_rate": 2.910083118524034e-05,
"loss": 0.7224,
"step": 270
},
{
"epoch": 0.7959479015918958,
"grad_norm": 0.8282304406166077,
"learning_rate": 2.9051282233489065e-05,
"loss": 0.6857,
"step": 275
},
{
"epoch": 0.8104196816208393,
"grad_norm": 0.9779431223869324,
"learning_rate": 2.900044894981813e-05,
"loss": 0.6938,
"step": 280
},
{
"epoch": 0.8248914616497829,
"grad_norm": 0.842149019241333,
"learning_rate": 2.894833598055147e-05,
"loss": 0.6996,
"step": 285
},
{
"epoch": 0.8393632416787264,
"grad_norm": 0.8657100200653076,
"learning_rate": 2.8894948088980338e-05,
"loss": 0.6343,
"step": 290
},
{
"epoch": 0.85383502170767,
"grad_norm": 0.8805454969406128,
"learning_rate": 2.8840290154927955e-05,
"loss": 0.6506,
"step": 295
},
{
"epoch": 0.8683068017366136,
"grad_norm": 0.8671079874038696,
"learning_rate": 2.878436717430346e-05,
"loss": 0.7051,
"step": 300
},
{
"epoch": 0.8827785817655571,
"grad_norm": 0.9610555768013,
"learning_rate": 2.8727184258645276e-05,
"loss": 0.6888,
"step": 305
},
{
"epoch": 0.8972503617945007,
"grad_norm": 0.9625582695007324,
"learning_rate": 2.8668746634653908e-05,
"loss": 0.6669,
"step": 310
},
{
"epoch": 0.9117221418234442,
"grad_norm": 0.8685387372970581,
"learning_rate": 2.860905964371418e-05,
"loss": 0.645,
"step": 315
},
{
"epoch": 0.9261939218523878,
"grad_norm": 1.1596406698226929,
"learning_rate": 2.8548128741407043e-05,
"loss": 0.6432,
"step": 320
},
{
"epoch": 0.9406657018813314,
"grad_norm": 0.9292768239974976,
"learning_rate": 2.8485959497010906e-05,
"loss": 0.6599,
"step": 325
},
{
"epoch": 0.9551374819102749,
"grad_norm": 1.0150357484817505,
"learning_rate": 2.8422557592992584e-05,
"loss": 0.5829,
"step": 330
},
{
"epoch": 0.9696092619392185,
"grad_norm": 1.0730253458023071,
"learning_rate": 2.83579288244879e-05,
"loss": 0.615,
"step": 335
},
{
"epoch": 0.984081041968162,
"grad_norm": 1.0182080268859863,
"learning_rate": 2.829207909877201e-05,
"loss": 0.6109,
"step": 340
},
{
"epoch": 0.9985528219971056,
"grad_norm": 0.9661368131637573,
"learning_rate": 2.8225014434719423e-05,
"loss": 0.5798,
"step": 345
}
],
"logging_steps": 5,
"max_steps": 1730,
"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": 5.213914221804257e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}