tzchen07/ShieldGemma-2B-SFT-X9c
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: tzchen07/ShieldGemma-2B-SFT-X9c
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-12 22:37:16 +08:00
commit 5f57a63b36
50 changed files with 9027 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

314
checkpoint-200/trainer_state.json Normal file
View File

@@ -0,0 +1,314 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0417482061317678,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02609262883235486,
"grad_norm": 90.7743148803711,
"learning_rate": 5.128205128205128e-07,
"loss": 3.4203,
"step": 5
},
{
"epoch": 0.05218525766470972,
"grad_norm": 52.55401611328125,
"learning_rate": 1.153846153846154e-06,
"loss": 2.8478,
"step": 10
},
{
"epoch": 0.07827788649706457,
"grad_norm": 17.9848575592041,
"learning_rate": 1.794871794871795e-06,
"loss": 1.524,
"step": 15
},
{
"epoch": 0.10437051532941943,
"grad_norm": 9.579212188720703,
"learning_rate": 2.435897435897436e-06,
"loss": 0.8379,
"step": 20
},
{
"epoch": 0.1304631441617743,
"grad_norm": 6.430282115936279,
"learning_rate": 3.0769230769230774e-06,
"loss": 0.4496,
"step": 25
},
{
"epoch": 0.15655577299412915,
"grad_norm": 5.243109703063965,
"learning_rate": 3.7179487179487184e-06,
"loss": 0.2512,
"step": 30
},
{
"epoch": 0.182648401826484,
"grad_norm": 5.690948963165283,
"learning_rate": 4.358974358974359e-06,
"loss": 0.183,
"step": 35
},
{
"epoch": 0.20874103065883887,
"grad_norm": 4.116969585418701,
"learning_rate": 5e-06,
"loss": 0.1788,
"step": 40
},
{
"epoch": 0.23483365949119372,
"grad_norm": 2.8701882362365723,
"learning_rate": 4.9974091841168195e-06,
"loss": 0.1605,
"step": 45
},
{
"epoch": 0.2609262883235486,
"grad_norm": 7.059335231781006,
"learning_rate": 4.989642106328829e-06,
"loss": 0.1394,
"step": 50
},
{
"epoch": 0.28701891715590344,
"grad_norm": 3.2651431560516357,
"learning_rate": 4.976714865090827e-06,
"loss": 0.083,
"step": 55
},
{
"epoch": 0.3131115459882583,
"grad_norm": 2.457581043243408,
"learning_rate": 4.958654254084356e-06,
"loss": 0.0896,
"step": 60
},
{
"epoch": 0.33920417482061316,
"grad_norm": 2.72770619392395,
"learning_rate": 4.935497706683698e-06,
"loss": 0.0991,
"step": 65
},
{
"epoch": 0.365296803652968,
"grad_norm": 2.0538723468780518,
"learning_rate": 4.907293218369499e-06,
"loss": 0.0979,
"step": 70
},
{
"epoch": 0.3913894324853229,
"grad_norm": 2.1862363815307617,
"learning_rate": 4.874099247250799e-06,
"loss": 0.0933,
"step": 75
},
{
"epoch": 0.41748206131767773,
"grad_norm": 2.605069637298584,
"learning_rate": 4.835984592901678e-06,
"loss": 0.0959,
"step": 80
},
{
"epoch": 0.4435746901500326,
"grad_norm": 1.2768350839614868,
"learning_rate": 4.793028253763633e-06,
"loss": 0.0749,
"step": 85
},
{
"epoch": 0.46966731898238745,
"grad_norm": 4.374709606170654,
"learning_rate": 4.745319263409241e-06,
"loss": 0.0991,
"step": 90
},
{
"epoch": 0.4957599478147423,
"grad_norm": 1.9398008584976196,
"learning_rate": 4.692956506006486e-06,
"loss": 0.0833,
"step": 95
},
{
"epoch": 0.5218525766470972,
"grad_norm": 1.7450673580169678,
"learning_rate": 4.636048511366222e-06,
"loss": 0.0804,
"step": 100
},
{
"epoch": 0.547945205479452,
"grad_norm": 1.712754249572754,
"learning_rate": 4.5747132299975634e-06,
"loss": 0.0867,
"step": 105
},
{
"epoch": 0.5740378343118069,
"grad_norm": 1.083371877670288,
"learning_rate": 4.509077788637446e-06,
"loss": 0.0688,
"step": 110
},
{
"epoch": 0.6001304631441617,
"grad_norm": 1.936558485031128,
"learning_rate": 4.43927822676105e-06,
"loss": 0.0772,
"step": 115
},
{
"epoch": 0.6262230919765166,
"grad_norm": 1.4485265016555786,
"learning_rate": 4.3654592146192146e-06,
"loss": 0.0767,
"step": 120
},
{
"epoch": 0.6523157208088715,
"grad_norm": 1.4740047454833984,
"learning_rate": 4.287773753387249e-06,
"loss": 0.0715,
"step": 125
},
{
"epoch": 0.6784083496412263,
"grad_norm": 1.7988250255584717,
"learning_rate": 4.206382858046636e-06,
"loss": 0.0823,
"step": 130
},
{
"epoch": 0.7045009784735812,
"grad_norm": 0.9675837159156799,
"learning_rate": 4.12145522365689e-06,
"loss": 0.0955,
"step": 135
},
{
"epoch": 0.730593607305936,
"grad_norm": 1.3645009994506836,
"learning_rate": 4.033166875709291e-06,
"loss": 0.062,
"step": 140
},
{
"epoch": 0.7566862361382909,
"grad_norm": 1.3581523895263672,
"learning_rate": 3.941700805287169e-06,
"loss": 0.0868,
"step": 145
},
{
"epoch": 0.7827788649706457,
"grad_norm": 1.8347728252410889,
"learning_rate": 3.84724658978894e-06,
"loss": 0.0681,
"step": 150
},
{
"epoch": 0.8088714938030006,
"grad_norm": 1.278552770614624,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0709,
"step": 155
},
{
"epoch": 0.8349641226353555,
"grad_norm": 1.676578402519226,
"learning_rate": 3.650162594327881e-06,
"loss": 0.0714,
"step": 160
},
{
"epoch": 0.8610567514677103,
"grad_norm": 0.9458003640174866,
"learning_rate": 3.5479413010416606e-06,
"loss": 0.081,
"step": 165
},
{
"epoch": 0.8871493803000652,
"grad_norm": 1.0945783853530884,
"learning_rate": 3.443547989381536e-06,
"loss": 0.0715,
"step": 170
},
{
"epoch": 0.91324200913242,
"grad_norm": 1.2435601949691772,
"learning_rate": 3.3371990304274654e-06,
"loss": 0.0638,
"step": 175
},
{
"epoch": 0.9393346379647749,
"grad_norm": 1.2059943675994873,
"learning_rate": 3.2291148486370626e-06,
"loss": 0.0683,
"step": 180
},
{
"epoch": 0.9654272667971298,
"grad_norm": 0.6467380523681641,
"learning_rate": 3.11951946498225e-06,
"loss": 0.0709,
"step": 185
},
{
"epoch": 0.9915198956294846,
"grad_norm": 0.8123487830162048,
"learning_rate": 3.0086400326315853e-06,
"loss": 0.0601,
"step": 190
},
{
"epoch": 1.015655577299413,
"grad_norm": 1.2716907262802124,
"learning_rate": 2.896706366140629e-06,
"loss": 0.0579,
"step": 195
},
{
"epoch": 1.0417482061317678,
"grad_norm": 1.656204104423523,
"learning_rate": 2.7839504651261873e-06,
"loss": 0.0623,
"step": 200
}
],
"logging_steps": 5,
"max_steps": 384,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 4.890173722188964e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}