AgThinker-32B / trainer_state.json
chegde's picture
Add files using upload-large-folder tool
adc11ad verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 698,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.014344629729245113,
"grad_norm": 1.18152568041847,
"learning_rate": 9.99589838831346e-05,
"loss": 0.4095,
"step": 10
},
{
"epoch": 0.028689259458490227,
"grad_norm": 0.7801380066445918,
"learning_rate": 9.981728616718234e-05,
"loss": 0.2924,
"step": 20
},
{
"epoch": 0.04303388918773534,
"grad_norm": 0.4005181099055157,
"learning_rate": 9.957468740965011e-05,
"loss": 0.2772,
"step": 30
},
{
"epoch": 0.05737851891698045,
"grad_norm": 0.37151913590170765,
"learning_rate": 9.923167897546773e-05,
"loss": 0.2624,
"step": 40
},
{
"epoch": 0.07172314864622557,
"grad_norm": 0.3658403711930329,
"learning_rate": 9.878895560156171e-05,
"loss": 0.2597,
"step": 50
},
{
"epoch": 0.08606777837547068,
"grad_norm": 0.36404458095370545,
"learning_rate": 9.824741398971966e-05,
"loss": 0.257,
"step": 60
},
{
"epoch": 0.1004124081047158,
"grad_norm": 0.34348583857313997,
"learning_rate": 9.760815099039044e-05,
"loss": 0.2586,
"step": 70
},
{
"epoch": 0.1147570378339609,
"grad_norm": 0.3546267311821283,
"learning_rate": 9.687246138109887e-05,
"loss": 0.2581,
"step": 80
},
{
"epoch": 0.129101667563206,
"grad_norm": 0.3518328253962369,
"learning_rate": 9.604183524397439e-05,
"loss": 0.259,
"step": 90
},
{
"epoch": 0.14344629729245115,
"grad_norm": 0.37777416169138317,
"learning_rate": 9.511795494770563e-05,
"loss": 0.2561,
"step": 100
},
{
"epoch": 0.15779092702169625,
"grad_norm": 0.34978239214614343,
"learning_rate": 9.410269174003334e-05,
"loss": 0.2548,
"step": 110
},
{
"epoch": 0.17213555675094136,
"grad_norm": 0.35146197680272717,
"learning_rate": 9.29981019576834e-05,
"loss": 0.2526,
"step": 120
},
{
"epoch": 0.1864801864801865,
"grad_norm": 0.3322142658858729,
"learning_rate": 9.180642286141678e-05,
"loss": 0.2495,
"step": 130
},
{
"epoch": 0.2008248162094316,
"grad_norm": 0.32127511964369854,
"learning_rate": 9.053006810463156e-05,
"loss": 0.2499,
"step": 140
},
{
"epoch": 0.2151694459386767,
"grad_norm": 0.3306286284306928,
"learning_rate": 8.917162284469569e-05,
"loss": 0.2461,
"step": 150
},
{
"epoch": 0.2295140756679218,
"grad_norm": 0.33792378428094794,
"learning_rate": 8.773383850691155e-05,
"loss": 0.2406,
"step": 160
},
{
"epoch": 0.24385870539716695,
"grad_norm": 0.3222015509279155,
"learning_rate": 8.621962721171787e-05,
"loss": 0.2365,
"step": 170
},
{
"epoch": 0.258203335126412,
"grad_norm": 0.3224913690900499,
"learning_rate": 8.463205587641614e-05,
"loss": 0.2302,
"step": 180
},
{
"epoch": 0.2725479648556572,
"grad_norm": 0.3282689638964441,
"learning_rate": 8.297434000336781e-05,
"loss": 0.226,
"step": 190
},
{
"epoch": 0.2868925945849023,
"grad_norm": 0.314785088454373,
"learning_rate": 8.124983716724434e-05,
"loss": 0.2261,
"step": 200
},
{
"epoch": 0.3012372243141474,
"grad_norm": 0.31867034269672606,
"learning_rate": 7.94620402145205e-05,
"loss": 0.2246,
"step": 210
},
{
"epoch": 0.3155818540433925,
"grad_norm": 0.34102642937121,
"learning_rate": 7.761457018898536e-05,
"loss": 0.219,
"step": 220
},
{
"epoch": 0.3299264837726376,
"grad_norm": 0.34109961975692005,
"learning_rate": 7.571116899759945e-05,
"loss": 0.2172,
"step": 230
},
{
"epoch": 0.3442711135018827,
"grad_norm": 0.31361120419506927,
"learning_rate": 7.375569183155305e-05,
"loss": 0.2139,
"step": 240
},
{
"epoch": 0.3586157432311278,
"grad_norm": 0.3214909612073443,
"learning_rate": 7.175209935787604e-05,
"loss": 0.2133,
"step": 250
},
{
"epoch": 0.372960372960373,
"grad_norm": 0.3185074747194894,
"learning_rate": 6.970444969741462e-05,
"loss": 0.2152,
"step": 260
},
{
"epoch": 0.3873050026896181,
"grad_norm": 0.2974383790136214,
"learning_rate": 6.761689020542288e-05,
"loss": 0.2106,
"step": 270
},
{
"epoch": 0.4016496324188632,
"grad_norm": 0.2971210798316127,
"learning_rate": 6.549364907141713e-05,
"loss": 0.2053,
"step": 280
},
{
"epoch": 0.4159942621481083,
"grad_norm": 0.31411603403554667,
"learning_rate": 6.333902675530656e-05,
"loss": 0.1984,
"step": 290
},
{
"epoch": 0.4303388918773534,
"grad_norm": 0.3179089356943495,
"learning_rate": 6.115738727714592e-05,
"loss": 0.1976,
"step": 300
},
{
"epoch": 0.4446835216065985,
"grad_norm": 0.31363246830376357,
"learning_rate": 5.895314937815206e-05,
"loss": 0.1922,
"step": 310
},
{
"epoch": 0.4590281513358436,
"grad_norm": 0.28488457188548555,
"learning_rate": 5.673077757088699e-05,
"loss": 0.1887,
"step": 320
},
{
"epoch": 0.47337278106508873,
"grad_norm": 0.29503052547081504,
"learning_rate": 5.449477309673462e-05,
"loss": 0.1864,
"step": 330
},
{
"epoch": 0.4877174107943339,
"grad_norm": 0.2991655081063554,
"learning_rate": 5.2249664808986244e-05,
"loss": 0.1823,
"step": 340
},
{
"epoch": 0.502062040523579,
"grad_norm": 0.2980600376554953,
"learning_rate": 5e-05,
"loss": 0.1819,
"step": 350
},
{
"epoch": 0.516406670252824,
"grad_norm": 0.2783466488589357,
"learning_rate": 4.775033519101378e-05,
"loss": 0.1774,
"step": 360
},
{
"epoch": 0.5307512999820692,
"grad_norm": 0.28992763991000786,
"learning_rate": 4.5505226903265375e-05,
"loss": 0.1762,
"step": 370
},
{
"epoch": 0.5450959297113144,
"grad_norm": 0.28259667009343253,
"learning_rate": 4.326922242911301e-05,
"loss": 0.1727,
"step": 380
},
{
"epoch": 0.5594405594405595,
"grad_norm": 0.2847313831772219,
"learning_rate": 4.104685062184794e-05,
"loss": 0.168,
"step": 390
},
{
"epoch": 0.5737851891698046,
"grad_norm": 0.28155885295327826,
"learning_rate": 3.884261272285409e-05,
"loss": 0.1654,
"step": 400
},
{
"epoch": 0.5881298188990497,
"grad_norm": 0.2684898894630876,
"learning_rate": 3.666097324469344e-05,
"loss": 0.1613,
"step": 410
},
{
"epoch": 0.6024744486282948,
"grad_norm": 0.27221979514870387,
"learning_rate": 3.4506350928582876e-05,
"loss": 0.1567,
"step": 420
},
{
"epoch": 0.6168190783575399,
"grad_norm": 0.2710486003553914,
"learning_rate": 3.238310979457713e-05,
"loss": 0.1544,
"step": 430
},
{
"epoch": 0.631163708086785,
"grad_norm": 0.2697397554786478,
"learning_rate": 3.0295550302585402e-05,
"loss": 0.1541,
"step": 440
},
{
"epoch": 0.6455083378160301,
"grad_norm": 0.2668796661785585,
"learning_rate": 2.824790064212396e-05,
"loss": 0.1514,
"step": 450
},
{
"epoch": 0.6598529675452752,
"grad_norm": 0.2647838900048377,
"learning_rate": 2.6244308168446956e-05,
"loss": 0.1492,
"step": 460
},
{
"epoch": 0.6741975972745203,
"grad_norm": 0.2562570406700666,
"learning_rate": 2.4288831002400574e-05,
"loss": 0.1444,
"step": 470
},
{
"epoch": 0.6885422270037654,
"grad_norm": 0.26315566627182685,
"learning_rate": 2.2385429811014654e-05,
"loss": 0.1431,
"step": 480
},
{
"epoch": 0.7028868567330105,
"grad_norm": 0.2637558074085645,
"learning_rate": 2.0537959785479517e-05,
"loss": 0.1405,
"step": 490
},
{
"epoch": 0.7172314864622557,
"grad_norm": 0.26909423269028165,
"learning_rate": 1.875016283275567e-05,
"loss": 0.1383,
"step": 500
},
{
"epoch": 0.7315761161915008,
"grad_norm": 0.2670316420743111,
"learning_rate": 1.70256599966322e-05,
"loss": 0.1355,
"step": 510
},
{
"epoch": 0.745920745920746,
"grad_norm": 0.26381577703337905,
"learning_rate": 1.5367944123583882e-05,
"loss": 0.1349,
"step": 520
},
{
"epoch": 0.7602653756499911,
"grad_norm": 0.2573409032083678,
"learning_rate": 1.378037278828212e-05,
"loss": 0.1321,
"step": 530
},
{
"epoch": 0.7746100053792362,
"grad_norm": 0.2703336954231402,
"learning_rate": 1.2266161493088463e-05,
"loss": 0.1317,
"step": 540
},
{
"epoch": 0.7889546351084813,
"grad_norm": 0.25704442767816826,
"learning_rate": 1.0828377155304331e-05,
"loss": 0.1287,
"step": 550
},
{
"epoch": 0.8032992648377264,
"grad_norm": 0.2540832845252926,
"learning_rate": 9.469931895368461e-06,
"loss": 0.1265,
"step": 560
},
{
"epoch": 0.8176438945669715,
"grad_norm": 0.25355857325017345,
"learning_rate": 8.193577138583241e-06,
"loss": 0.1241,
"step": 570
},
{
"epoch": 0.8319885242962166,
"grad_norm": 0.256496187113757,
"learning_rate": 7.0018980423166016e-06,
"loss": 0.1241,
"step": 580
},
{
"epoch": 0.8463331540254617,
"grad_norm": 0.25854825665201925,
"learning_rate": 5.897308259966672e-06,
"loss": 0.1247,
"step": 590
},
{
"epoch": 0.8606777837547068,
"grad_norm": 0.2538181796857953,
"learning_rate": 4.882045052294371e-06,
"loss": 0.1227,
"step": 600
},
{
"epoch": 0.8750224134839519,
"grad_norm": 0.24626447646186575,
"learning_rate": 3.958164756025618e-06,
"loss": 0.1208,
"step": 610
},
{
"epoch": 0.889367043213197,
"grad_norm": 0.2515303871680775,
"learning_rate": 3.1275386189011433e-06,
"loss": 0.121,
"step": 620
},
{
"epoch": 0.9037116729424421,
"grad_norm": 0.24642826227075423,
"learning_rate": 2.391849009609559e-06,
"loss": 0.1214,
"step": 630
},
{
"epoch": 0.9180563026716873,
"grad_norm": 0.2519477684757865,
"learning_rate": 1.7525860102803438e-06,
"loss": 0.1214,
"step": 640
},
{
"epoch": 0.9324009324009324,
"grad_norm": 0.24918787252594898,
"learning_rate": 1.2110443984382936e-06,
"loss": 0.1244,
"step": 650
},
{
"epoch": 0.9467455621301775,
"grad_norm": 0.2513072821154767,
"learning_rate": 7.68321024532287e-07,
"loss": 0.1212,
"step": 660
},
{
"epoch": 0.9610901918594227,
"grad_norm": 0.25470600465243254,
"learning_rate": 4.2531259034989667e-07,
"loss": 0.1224,
"step": 670
},
{
"epoch": 0.9754348215886678,
"grad_norm": 0.24818225431416227,
"learning_rate": 1.827138328176603e-07,
"loss": 0.1226,
"step": 680
},
{
"epoch": 0.9897794513179129,
"grad_norm": 0.24705387852393956,
"learning_rate": 4.1016116865394417e-08,
"loss": 0.1215,
"step": 690
},
{
"epoch": 1.0,
"step": 698,
"total_flos": 473362986434560.0,
"train_loss": 0.18736316028843636,
"train_runtime": 57518.7952,
"train_samples_per_second": 0.776,
"train_steps_per_second": 0.012
}
],
"logging_steps": 10,
"max_steps": 698,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 473362986434560.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}