Files
qwen2.5-3B-cb-1_1/trainer_state.json
ModelHub XC 43e30436f8 初始化项目,由ModelHub XC社区提供模型
Model: introtollm/qwen2.5-3B-cb-1_1
Source: Original Platform
2026-05-02 16:11:40 +08:00

345 lines
8.3 KiB
JSON

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.4536757735068517,
"eval_steps": 500,
"global_step": 2109,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006894768594329053,
"grad_norm": 3.163306713104248,
"learning_rate": 0.0,
"loss": 1.2218,
"step": 1
},
{
"epoch": 0.03447384297164526,
"grad_norm": 1.9950363636016846,
"learning_rate": 1.9999434046461045e-05,
"loss": 1.067,
"step": 50
},
{
"epoch": 0.06894768594329052,
"grad_norm": 1.764167308807373,
"learning_rate": 1.996249692618611e-05,
"loss": 0.8991,
"step": 100
},
{
"epoch": 0.10342152891493579,
"grad_norm": 1.6243094205856323,
"learning_rate": 1.9868053167196865e-05,
"loss": 0.8564,
"step": 150
},
{
"epoch": 0.13789537188658105,
"grad_norm": 1.573244333267212,
"learning_rate": 1.971664792831919e-05,
"loss": 0.836,
"step": 200
},
{
"epoch": 0.17236921485822632,
"grad_norm": 1.599184513092041,
"learning_rate": 1.9509155167802316e-05,
"loss": 0.8218,
"step": 250
},
{
"epoch": 0.20684305782987158,
"grad_norm": 1.5806775093078613,
"learning_rate": 1.9246772598559302e-05,
"loss": 0.8042,
"step": 300
},
{
"epoch": 0.24131690080151685,
"grad_norm": 1.5832141637802124,
"learning_rate": 1.8931014774594656e-05,
"loss": 0.793,
"step": 350
},
{
"epoch": 0.2757907437731621,
"grad_norm": 1.4803227186203003,
"learning_rate": 1.8563704348526337e-05,
"loss": 0.7826,
"step": 400
},
{
"epoch": 0.3102645867448074,
"grad_norm": 1.4616361856460571,
"learning_rate": 1.8146961550666525e-05,
"loss": 0.7661,
"step": 450
},
{
"epoch": 0.34473842971645263,
"grad_norm": 1.559212565422058,
"learning_rate": 1.7683191950391142e-05,
"loss": 0.7585,
"step": 500
},
{
"epoch": 0.37921227268809793,
"grad_norm": 1.5652285814285278,
"learning_rate": 1.717507257044331e-05,
"loss": 0.7478,
"step": 550
},
{
"epoch": 0.41368611565974317,
"grad_norm": 1.4887570142745972,
"learning_rate": 1.6625536434323358e-05,
"loss": 0.7484,
"step": 600
},
{
"epoch": 0.4481599586313884,
"grad_norm": 1.517269492149353,
"learning_rate": 1.6037755635962587e-05,
"loss": 0.7409,
"step": 650
},
{
"epoch": 0.4826338016030337,
"grad_norm": 1.4647221565246582,
"learning_rate": 1.5415123029408046e-05,
"loss": 0.726,
"step": 700
},
{
"epoch": 0.517107644574679,
"grad_norm": 1.4331293106079102,
"learning_rate": 1.4761232644210963e-05,
"loss": 0.7315,
"step": 750
},
{
"epoch": 0.5515814875463242,
"grad_norm": 1.432714819908142,
"learning_rate": 1.4079858939567557e-05,
"loss": 0.7153,
"step": 800
},
{
"epoch": 0.5860553305179695,
"grad_norm": 1.4351866245269775,
"learning_rate": 1.3374935016963595e-05,
"loss": 0.7117,
"step": 850
},
{
"epoch": 0.6205291734896148,
"grad_norm": 1.3949848413467407,
"learning_rate": 1.2650529917086232e-05,
"loss": 0.7136,
"step": 900
},
{
"epoch": 0.65500301646126,
"grad_norm": 1.4337003231048584,
"learning_rate": 1.1910825132052356e-05,
"loss": 0.7056,
"step": 950
},
{
"epoch": 0.6894768594329053,
"grad_norm": 1.465988278388977,
"learning_rate": 1.1160090468532266e-05,
"loss": 0.6969,
"step": 1000
},
{
"epoch": 0.7239507024045505,
"grad_norm": 1.3694732189178467,
"learning_rate": 1.0402659401094154e-05,
"loss": 0.6891,
"step": 1050
},
{
"epoch": 0.7584245453761959,
"grad_norm": 1.4759716987609863,
"learning_rate": 9.642904058037667e-06,
"loss": 0.6841,
"step": 1100
},
{
"epoch": 0.7928983883478411,
"grad_norm": 1.4173362255096436,
"learning_rate": 8.885209984106072e-06,
"loss": 0.6782,
"step": 1150
},
{
"epoch": 0.8273722313194863,
"grad_norm": 1.3540033102035522,
"learning_rate": 8.133950825754511e-06,
"loss": 0.6702,
"step": 1200
},
{
"epoch": 0.8618460742911316,
"grad_norm": 1.472687840461731,
"learning_rate": 7.393463085098886e-06,
"loss": 0.6727,
"step": 1250
},
{
"epoch": 0.8963199172627768,
"grad_norm": 1.4779541492462158,
"learning_rate": 6.6680210882734805e-06,
"loss": 0.6649,
"step": 1300
},
{
"epoch": 0.9307937602344222,
"grad_norm": 1.4042788743972778,
"learning_rate": 5.961812312687689e-06,
"loss": 0.6606,
"step": 1350
},
{
"epoch": 0.9652676032060674,
"grad_norm": 1.3935030698776245,
"learning_rate": 5.278913215600714e-06,
"loss": 0.6558,
"step": 1400
},
{
"epoch": 0.9997414461777127,
"grad_norm": 1.5017318725585938,
"learning_rate": 4.623265703539146e-06,
"loss": 0.6622,
"step": 1450
},
{
"epoch": 1.0337843661122124,
"grad_norm": 1.387417197227478,
"learning_rate": 3.998654378383361e-06,
"loss": 0.4825,
"step": 1500
},
{
"epoch": 1.0682582090838577,
"grad_norm": 1.4467589855194092,
"learning_rate": 3.408684691465355e-06,
"loss": 0.4759,
"step": 1550
},
{
"epoch": 1.1027320520555028,
"grad_norm": 1.4690955877304077,
"learning_rate": 2.85676213177945e-06,
"loss": 0.4703,
"step": 1600
},
{
"epoch": 1.1372058950271482,
"grad_norm": 1.4206316471099854,
"learning_rate": 2.3460725684379002e-06,
"loss": 0.4714,
"step": 1650
},
{
"epoch": 1.1716797379987933,
"grad_norm": 1.477750539779663,
"learning_rate": 1.8795638608410016e-06,
"loss": 0.4648,
"step": 1700
},
{
"epoch": 1.2061535809704387,
"grad_norm": 1.3695833683013916,
"learning_rate": 1.4599288427134283e-06,
"loss": 0.4631,
"step": 1750
},
{
"epoch": 1.240627423942084,
"grad_norm": 1.5380635261535645,
"learning_rate": 1.0895897782283305e-06,
"loss": 0.4683,
"step": 1800
},
{
"epoch": 1.2751012669137292,
"grad_norm": 1.4506001472473145,
"learning_rate": 7.706843799431985e-07,
"loss": 0.463,
"step": 1850
},
{
"epoch": 1.3095751098853745,
"grad_norm": 1.447545051574707,
"learning_rate": 5.050534692564358e-07,
"loss": 0.4694,
"step": 1900
},
{
"epoch": 1.3440489528570199,
"grad_norm": 1.4041807651519775,
"learning_rate": 2.94230350612239e-07,
"loss": 0.4621,
"step": 1950
},
{
"epoch": 1.378522795828665,
"grad_norm": 1.4376499652862549,
"learning_rate": 1.3943196078924247e-07,
"loss": 0.4698,
"step": 2000
},
{
"epoch": 1.4129966388003103,
"grad_norm": 1.4528664350509644,
"learning_rate": 4.155184436196669e-08,
"loss": 0.4617,
"step": 2050
},
{
"epoch": 1.4474704817719555,
"grad_norm": 1.4085997343063354,
"learning_rate": 1.154995882924892e-09,
"loss": 0.4599,
"step": 2100
},
{
"epoch": 1.4536757735068517,
"step": 2109,
"total_flos": 5.7510431551389696e+17,
"train_loss": 0.659755018267263,
"train_runtime": 7509.8532,
"train_samples_per_second": 2.247,
"train_steps_per_second": 0.281
}
],
"logging_steps": 50,
"max_steps": 2109,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 2000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.7510431551389696e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}