cls2.0 / checkpoint-1506 /trainer_state.json
assaflehr's picture
Upload folder using huggingface_hub
e4b2f5c verified
{
"best_metric": 0.32059717178344727,
"best_model_checkpoint": "autotrain-z9wst-apic1/checkpoint-1506",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1506,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.016600265604249667,
"grad_norm": 0.7011755108833313,
"learning_rate": 8.27814569536424e-06,
"loss": 0.6938,
"step": 25
},
{
"epoch": 0.033200531208499334,
"grad_norm": 1.692274808883667,
"learning_rate": 1.655629139072848e-05,
"loss": 0.6645,
"step": 50
},
{
"epoch": 0.049800796812749,
"grad_norm": 2.9643406867980957,
"learning_rate": 2.4834437086092715e-05,
"loss": 0.4689,
"step": 75
},
{
"epoch": 0.06640106241699867,
"grad_norm": 6.690465927124023,
"learning_rate": 3.2450331125827816e-05,
"loss": 0.411,
"step": 100
},
{
"epoch": 0.08300132802124834,
"grad_norm": 4.3464460372924805,
"learning_rate": 4.0728476821192055e-05,
"loss": 0.3856,
"step": 125
},
{
"epoch": 0.099601593625498,
"grad_norm": 4.394780158996582,
"learning_rate": 4.900662251655629e-05,
"loss": 0.3458,
"step": 150
},
{
"epoch": 0.11620185922974767,
"grad_norm": 4.849474906921387,
"learning_rate": 4.9967485104175286e-05,
"loss": 0.3469,
"step": 175
},
{
"epoch": 0.13280212483399734,
"grad_norm": 3.016519069671631,
"learning_rate": 4.9851715045824994e-05,
"loss": 0.3273,
"step": 200
},
{
"epoch": 0.14940239043824702,
"grad_norm": 7.323078632354736,
"learning_rate": 4.965247392483274e-05,
"loss": 0.326,
"step": 225
},
{
"epoch": 0.16600265604249667,
"grad_norm": 1.702303171157837,
"learning_rate": 4.937043094523778e-05,
"loss": 0.3507,
"step": 250
},
{
"epoch": 0.18260292164674635,
"grad_norm": 3.314708709716797,
"learning_rate": 4.900653342303719e-05,
"loss": 0.3253,
"step": 275
},
{
"epoch": 0.199203187250996,
"grad_norm": 3.7664265632629395,
"learning_rate": 4.8562003604374334e-05,
"loss": 0.3223,
"step": 300
},
{
"epoch": 0.2158034528552457,
"grad_norm": 2.8503146171569824,
"learning_rate": 4.8038334560301714e-05,
"loss": 0.3276,
"step": 325
},
{
"epoch": 0.23240371845949534,
"grad_norm": 3.164609909057617,
"learning_rate": 4.7437285171906644e-05,
"loss": 0.2694,
"step": 350
},
{
"epoch": 0.24900398406374502,
"grad_norm": 5.1076531410217285,
"learning_rate": 4.676087422264358e-05,
"loss": 0.2641,
"step": 375
},
{
"epoch": 0.2656042496679947,
"grad_norm": 3.561342477798462,
"learning_rate": 4.60113736177156e-05,
"loss": 0.3179,
"step": 400
},
{
"epoch": 0.2822045152722444,
"grad_norm": 5.70325231552124,
"learning_rate": 4.519130075327941e-05,
"loss": 0.2602,
"step": 425
},
{
"epoch": 0.29880478087649404,
"grad_norm": 3.692572593688965,
"learning_rate": 4.43034100611041e-05,
"loss": 0.2565,
"step": 450
},
{
"epoch": 0.3154050464807437,
"grad_norm": 3.2501657009124756,
"learning_rate": 4.3350683757082966e-05,
"loss": 0.2269,
"step": 475
},
{
"epoch": 0.33200531208499334,
"grad_norm": 4.347064971923828,
"learning_rate": 4.233632182467218e-05,
"loss": 0.2527,
"step": 500
},
{
"epoch": 0.34860557768924305,
"grad_norm": 3.8920302391052246,
"learning_rate": 4.126373126689931e-05,
"loss": 0.2233,
"step": 525
},
{
"epoch": 0.3652058432934927,
"grad_norm": 2.748621940612793,
"learning_rate": 4.013651466304197e-05,
"loss": 0.2574,
"step": 550
},
{
"epoch": 0.38180610889774236,
"grad_norm": 1.6398485898971558,
"learning_rate": 3.8958458068411756e-05,
"loss": 0.2627,
"step": 575
},
{
"epoch": 0.398406374501992,
"grad_norm": 3.143782377243042,
"learning_rate": 3.773351829788543e-05,
"loss": 0.2377,
"step": 600
},
{
"epoch": 0.4150066401062417,
"grad_norm": 2.3850388526916504,
"learning_rate": 3.646580963589486e-05,
"loss": 0.2221,
"step": 625
},
{
"epoch": 0.4316069057104914,
"grad_norm": 3.32765531539917,
"learning_rate": 3.5159590017513796e-05,
"loss": 0.2248,
"step": 650
},
{
"epoch": 0.448207171314741,
"grad_norm": 3.9372353553771973,
"learning_rate": 3.381924672705598e-05,
"loss": 0.2127,
"step": 675
},
{
"epoch": 0.4648074369189907,
"grad_norm": 1.9122364521026611,
"learning_rate": 3.2449281662219556e-05,
"loss": 0.2034,
"step": 700
},
{
"epoch": 0.4814077025232404,
"grad_norm": 2.339261054992676,
"learning_rate": 3.105429621327208e-05,
"loss": 0.2036,
"step": 725
},
{
"epoch": 0.49800796812749004,
"grad_norm": 2.478360652923584,
"learning_rate": 2.9638975808063486e-05,
"loss": 0.2134,
"step": 750
},
{
"epoch": 0.5146082337317397,
"grad_norm": 3.1056790351867676,
"learning_rate": 2.8208074174776444e-05,
"loss": 0.2316,
"step": 775
},
{
"epoch": 0.5312084993359893,
"grad_norm": 1.999221920967102,
"learning_rate": 2.676639737527213e-05,
"loss": 0.2325,
"step": 800
},
{
"epoch": 0.547808764940239,
"grad_norm": 1.5150188207626343,
"learning_rate": 2.5318787662659414e-05,
"loss": 0.1733,
"step": 825
},
{
"epoch": 0.5644090305444888,
"grad_norm": 5.388316631317139,
"learning_rate": 2.3870107217306106e-05,
"loss": 0.193,
"step": 850
},
{
"epoch": 0.5810092961487384,
"grad_norm": 2.7311172485351562,
"learning_rate": 2.242522181591934e-05,
"loss": 0.1616,
"step": 875
},
{
"epoch": 0.5976095617529881,
"grad_norm": 1.276823878288269,
"learning_rate": 2.0988984488546643e-05,
"loss": 0.1526,
"step": 900
},
{
"epoch": 0.6142098273572377,
"grad_norm": 1.8383485078811646,
"learning_rate": 1.956621921838998e-05,
"loss": 0.1881,
"step": 925
},
{
"epoch": 0.6308100929614874,
"grad_norm": 4.960041522979736,
"learning_rate": 1.8161704739181486e-05,
"loss": 0.1749,
"step": 950
},
{
"epoch": 0.647410358565737,
"grad_norm": 1.369192361831665,
"learning_rate": 1.6780158484541295e-05,
"loss": 0.1222,
"step": 975
},
{
"epoch": 0.6640106241699867,
"grad_norm": 4.590680122375488,
"learning_rate": 1.54262207432282e-05,
"loss": 0.1664,
"step": 1000
},
{
"epoch": 0.6806108897742363,
"grad_norm": 1.1486464738845825,
"learning_rate": 1.4104439073501647e-05,
"loss": 0.1389,
"step": 1025
},
{
"epoch": 0.6972111553784861,
"grad_norm": 1.1831196546554565,
"learning_rate": 1.2819253028943757e-05,
"loss": 0.1941,
"step": 1050
},
{
"epoch": 0.7138114209827358,
"grad_norm": 1.529694676399231,
"learning_rate": 1.1574979247043486e-05,
"loss": 0.1479,
"step": 1075
},
{
"epoch": 0.7304116865869854,
"grad_norm": 5.450222492218018,
"learning_rate": 1.0375796950627137e-05,
"loss": 0.1561,
"step": 1100
},
{
"epoch": 0.7470119521912351,
"grad_norm": 1.9736617803573608,
"learning_rate": 9.225733910832388e-06,
"loss": 0.1598,
"step": 1125
},
{
"epoch": 0.7636122177954847,
"grad_norm": 4.179745197296143,
"learning_rate": 8.128652918772865e-06,
"loss": 0.1353,
"step": 1150
},
{
"epoch": 0.7802124833997344,
"grad_norm": 5.7941083908081055,
"learning_rate": 7.088238811331752e-06,
"loss": 0.1358,
"step": 1175
},
{
"epoch": 0.796812749003984,
"grad_norm": 2.463935136795044,
"learning_rate": 6.1079860946618685e-06,
"loss": 0.1337,
"step": 1200
},
{
"epoch": 0.8134130146082338,
"grad_norm": 1.1269705295562744,
"learning_rate": 5.19118720696184e-06,
"loss": 0.1538,
"step": 1225
},
{
"epoch": 0.8300132802124834,
"grad_norm": 5.329429626464844,
"learning_rate": 4.340921459950962e-06,
"loss": 0.1323,
"step": 1250
},
{
"epoch": 0.8466135458167331,
"grad_norm": 6.623585224151611,
"learning_rate": 3.56004469618578e-06,
"loss": 0.1455,
"step": 1275
},
{
"epoch": 0.8632138114209827,
"grad_norm": 1.3128626346588135,
"learning_rate": 2.851179696956993e-06,
"loss": 0.1367,
"step": 1300
},
{
"epoch": 0.8798140770252324,
"grad_norm": 4.968562126159668,
"learning_rate": 2.216707372984292e-06,
"loss": 0.0909,
"step": 1325
},
{
"epoch": 0.896414342629482,
"grad_norm": 1.0073035955429077,
"learning_rate": 1.6587587674975424e-06,
"loss": 0.1443,
"step": 1350
},
{
"epoch": 0.9130146082337317,
"grad_norm": 4.145277500152588,
"learning_rate": 1.1792078985640525e-06,
"loss": 0.138,
"step": 1375
},
{
"epoch": 0.9296148738379814,
"grad_norm": 1.9500765800476074,
"learning_rate": 7.796654647029e-07,
"loss": 0.1265,
"step": 1400
},
{
"epoch": 0.9462151394422311,
"grad_norm": 1.5362143516540527,
"learning_rate": 4.614734349276256e-07,
"loss": 0.1555,
"step": 1425
},
{
"epoch": 0.9628154050464808,
"grad_norm": 2.4286270141601562,
"learning_rate": 2.2570054138813246e-07,
"loss": 0.1389,
"step": 1450
},
{
"epoch": 0.9794156706507304,
"grad_norm": 2.250825881958008,
"learning_rate": 7.313868975087345e-08,
"loss": 0.1173,
"step": 1475
},
{
"epoch": 0.9960159362549801,
"grad_norm": 0.48711511492729187,
"learning_rate": 4.3002993740770546e-09,
"loss": 0.1262,
"step": 1500
},
{
"epoch": 1.0,
"eval_accuracy": 0.9163208852005532,
"eval_auc": 0.963556761725483,
"eval_f1": 0.9162629757785468,
"eval_loss": 0.32059717178344727,
"eval_precision": 0.9168975069252078,
"eval_recall": 0.9156293222683264,
"eval_runtime": 39.0094,
"eval_samples_per_second": 148.272,
"eval_steps_per_second": 2.333,
"step": 1506
}
],
"logging_steps": 25,
"max_steps": 1506,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6340037689147392.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}