sbf-bert-intent / checkpoint-555 /trainer_state.json
anoaky's picture
Training in progress, epoch 1, checkpoint
0617785 verified
raw
history blame
10.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 555,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.018026137899954935,
"grad_norm": 18.020910263061523,
"learning_rate": 4.9548736462093865e-05,
"loss": 0.6809,
"step": 10
},
{
"epoch": 0.03605227579990987,
"grad_norm": 30.794422149658203,
"learning_rate": 4.909747292418773e-05,
"loss": 0.572,
"step": 20
},
{
"epoch": 0.054078413699864804,
"grad_norm": 24.659021377563477,
"learning_rate": 4.864620938628159e-05,
"loss": 0.554,
"step": 30
},
{
"epoch": 0.07210455159981974,
"grad_norm": 17.13719367980957,
"learning_rate": 4.819494584837546e-05,
"loss": 0.5261,
"step": 40
},
{
"epoch": 0.09013068949977468,
"grad_norm": 50.614078521728516,
"learning_rate": 4.7743682310469314e-05,
"loss": 0.5696,
"step": 50
},
{
"epoch": 0.10815682739972961,
"grad_norm": 16.31667137145996,
"learning_rate": 4.7292418772563177e-05,
"loss": 0.4876,
"step": 60
},
{
"epoch": 0.12618296529968454,
"grad_norm": 41.160762786865234,
"learning_rate": 4.684115523465704e-05,
"loss": 0.4647,
"step": 70
},
{
"epoch": 0.14420910319963948,
"grad_norm": 20.278989791870117,
"learning_rate": 4.63898916967509e-05,
"loss": 0.4525,
"step": 80
},
{
"epoch": 0.16223524109959442,
"grad_norm": 21.479433059692383,
"learning_rate": 4.5938628158844764e-05,
"loss": 0.4511,
"step": 90
},
{
"epoch": 0.18026137899954936,
"grad_norm": 20.85803985595703,
"learning_rate": 4.548736462093863e-05,
"loss": 0.4828,
"step": 100
},
{
"epoch": 0.19828751689950427,
"grad_norm": 19.689502716064453,
"learning_rate": 4.5036101083032495e-05,
"loss": 0.4785,
"step": 110
},
{
"epoch": 0.21631365479945922,
"grad_norm": 23.28278350830078,
"learning_rate": 4.458483754512636e-05,
"loss": 0.4593,
"step": 120
},
{
"epoch": 0.23433979269941416,
"grad_norm": 55.461483001708984,
"learning_rate": 4.413357400722022e-05,
"loss": 0.4265,
"step": 130
},
{
"epoch": 0.25236593059936907,
"grad_norm": 21.591472625732422,
"learning_rate": 4.368231046931408e-05,
"loss": 0.4611,
"step": 140
},
{
"epoch": 0.270392068499324,
"grad_norm": 31.00871467590332,
"learning_rate": 4.3231046931407945e-05,
"loss": 0.4489,
"step": 150
},
{
"epoch": 0.28841820639927895,
"grad_norm": 21.315185546875,
"learning_rate": 4.277978339350181e-05,
"loss": 0.4755,
"step": 160
},
{
"epoch": 0.3064443442992339,
"grad_norm": 25.012041091918945,
"learning_rate": 4.232851985559567e-05,
"loss": 0.4703,
"step": 170
},
{
"epoch": 0.32447048219918884,
"grad_norm": 18.25890350341797,
"learning_rate": 4.187725631768953e-05,
"loss": 0.4456,
"step": 180
},
{
"epoch": 0.3424966200991438,
"grad_norm": 19.33783721923828,
"learning_rate": 4.1425992779783394e-05,
"loss": 0.4764,
"step": 190
},
{
"epoch": 0.3605227579990987,
"grad_norm": 21.992473602294922,
"learning_rate": 4.0974729241877256e-05,
"loss": 0.4204,
"step": 200
},
{
"epoch": 0.3785488958990536,
"grad_norm": 20.253664016723633,
"learning_rate": 4.052346570397112e-05,
"loss": 0.4471,
"step": 210
},
{
"epoch": 0.39657503379900855,
"grad_norm": 17.41029167175293,
"learning_rate": 4.007220216606498e-05,
"loss": 0.4387,
"step": 220
},
{
"epoch": 0.4146011716989635,
"grad_norm": 18.28990364074707,
"learning_rate": 3.962093862815885e-05,
"loss": 0.4283,
"step": 230
},
{
"epoch": 0.43262730959891843,
"grad_norm": 48.463008880615234,
"learning_rate": 3.916967509025271e-05,
"loss": 0.4447,
"step": 240
},
{
"epoch": 0.45065344749887337,
"grad_norm": 15.58568000793457,
"learning_rate": 3.8718411552346575e-05,
"loss": 0.4257,
"step": 250
},
{
"epoch": 0.4686795853988283,
"grad_norm": 31.015850067138672,
"learning_rate": 3.826714801444044e-05,
"loss": 0.4463,
"step": 260
},
{
"epoch": 0.48670572329878325,
"grad_norm": 18.325271606445312,
"learning_rate": 3.78158844765343e-05,
"loss": 0.4207,
"step": 270
},
{
"epoch": 0.5047318611987381,
"grad_norm": 20.241615295410156,
"learning_rate": 3.7364620938628155e-05,
"loss": 0.4084,
"step": 280
},
{
"epoch": 0.5227579990986931,
"grad_norm": 19.043285369873047,
"learning_rate": 3.6913357400722025e-05,
"loss": 0.4345,
"step": 290
},
{
"epoch": 0.540784136998648,
"grad_norm": 19.568265914916992,
"learning_rate": 3.646209386281589e-05,
"loss": 0.4393,
"step": 300
},
{
"epoch": 0.558810274898603,
"grad_norm": 26.981136322021484,
"learning_rate": 3.601083032490975e-05,
"loss": 0.4532,
"step": 310
},
{
"epoch": 0.5768364127985579,
"grad_norm": 17.03878402709961,
"learning_rate": 3.555956678700361e-05,
"loss": 0.4208,
"step": 320
},
{
"epoch": 0.5948625506985128,
"grad_norm": 16.008604049682617,
"learning_rate": 3.5108303249097474e-05,
"loss": 0.4396,
"step": 330
},
{
"epoch": 0.6128886885984678,
"grad_norm": 20.344444274902344,
"learning_rate": 3.4657039711191336e-05,
"loss": 0.4318,
"step": 340
},
{
"epoch": 0.6309148264984227,
"grad_norm": 18.641759872436523,
"learning_rate": 3.42057761732852e-05,
"loss": 0.4481,
"step": 350
},
{
"epoch": 0.6489409643983777,
"grad_norm": 25.64444351196289,
"learning_rate": 3.375451263537907e-05,
"loss": 0.4053,
"step": 360
},
{
"epoch": 0.6669671022983326,
"grad_norm": 23.601179122924805,
"learning_rate": 3.330324909747293e-05,
"loss": 0.4463,
"step": 370
},
{
"epoch": 0.6849932401982876,
"grad_norm": 29.48953628540039,
"learning_rate": 3.2851985559566786e-05,
"loss": 0.4086,
"step": 380
},
{
"epoch": 0.7030193780982424,
"grad_norm": 15.503927230834961,
"learning_rate": 3.240072202166065e-05,
"loss": 0.4402,
"step": 390
},
{
"epoch": 0.7210455159981974,
"grad_norm": 29.575830459594727,
"learning_rate": 3.194945848375451e-05,
"loss": 0.43,
"step": 400
},
{
"epoch": 0.7390716538981523,
"grad_norm": 26.154592514038086,
"learning_rate": 3.149819494584837e-05,
"loss": 0.432,
"step": 410
},
{
"epoch": 0.7570977917981072,
"grad_norm": 25.37771987915039,
"learning_rate": 3.104693140794224e-05,
"loss": 0.4277,
"step": 420
},
{
"epoch": 0.7751239296980622,
"grad_norm": 31.5076904296875,
"learning_rate": 3.0595667870036104e-05,
"loss": 0.4131,
"step": 430
},
{
"epoch": 0.7931500675980171,
"grad_norm": 16.534198760986328,
"learning_rate": 3.0144404332129967e-05,
"loss": 0.433,
"step": 440
},
{
"epoch": 0.8111762054979721,
"grad_norm": 19.064289093017578,
"learning_rate": 2.969314079422383e-05,
"loss": 0.3964,
"step": 450
},
{
"epoch": 0.829202343397927,
"grad_norm": 18.9260196685791,
"learning_rate": 2.924187725631769e-05,
"loss": 0.396,
"step": 460
},
{
"epoch": 0.847228481297882,
"grad_norm": 27.17948341369629,
"learning_rate": 2.879061371841155e-05,
"loss": 0.4079,
"step": 470
},
{
"epoch": 0.8652546191978369,
"grad_norm": 21.348743438720703,
"learning_rate": 2.8339350180505413e-05,
"loss": 0.4545,
"step": 480
},
{
"epoch": 0.8832807570977917,
"grad_norm": 15.41019344329834,
"learning_rate": 2.7888086642599282e-05,
"loss": 0.4024,
"step": 490
},
{
"epoch": 0.9013068949977467,
"grad_norm": 26.81648826599121,
"learning_rate": 2.7436823104693144e-05,
"loss": 0.3888,
"step": 500
},
{
"epoch": 0.9193330328977016,
"grad_norm": 27.93416976928711,
"learning_rate": 2.6985559566787007e-05,
"loss": 0.4086,
"step": 510
},
{
"epoch": 0.9373591707976566,
"grad_norm": 14.353543281555176,
"learning_rate": 2.6534296028880866e-05,
"loss": 0.416,
"step": 520
},
{
"epoch": 0.9553853086976115,
"grad_norm": 15.367998123168945,
"learning_rate": 2.6083032490974728e-05,
"loss": 0.4184,
"step": 530
},
{
"epoch": 0.9734114465975665,
"grad_norm": 22.00202178955078,
"learning_rate": 2.563176895306859e-05,
"loss": 0.4294,
"step": 540
},
{
"epoch": 0.9914375844975214,
"grad_norm": 15.376652717590332,
"learning_rate": 2.518050541516246e-05,
"loss": 0.4068,
"step": 550
},
{
"epoch": 1.0,
"eval_f1": 0.8437814956661963,
"eval_fn": 317,
"eval_fp": 458,
"eval_loss": 0.3667502701282501,
"eval_precision": 0.8204625637005096,
"eval_recall": 0.8684647302904565,
"eval_runtime": 14.8642,
"eval_samples_per_second": 314.379,
"eval_steps_per_second": 39.356,
"eval_tn": 1805,
"eval_tp": 2093,
"step": 555
}
],
"logging_steps": 10,
"max_steps": 1108,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4670747454750720.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}