lldois/v52_public091_full_lr2e5_ep1
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: lldois/v52_public091_full_lr2e5_ep1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 11:17:10 +08:00
commit 6ba3c93ef6
17 changed files with 2931 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

267
trainer_state.json Normal file
View File

@@ -0,0 +1,267 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 326,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03067484662576687,
"grad_norm": 8.0,
"learning_rate": 1.8e-05,
"loss": 2.659077453613281,
"step": 10
},
{
"epoch": 0.06134969325153374,
"grad_norm": 3.296875,
"learning_rate": 1.995999715857997e-05,
"loss": 2.113694763183594,
"step": 20
},
{
"epoch": 0.09202453987730061,
"grad_norm": 2.984375,
"learning_rate": 1.9822126571413616e-05,
"loss": 1.8163612365722657,
"step": 30
},
{
"epoch": 0.12269938650306748,
"grad_norm": 3.375,
"learning_rate": 1.9587255619128648e-05,
"loss": 1.7940385818481446,
"step": 40
},
{
"epoch": 0.15337423312883436,
"grad_norm": 2.90625,
"learning_rate": 1.9257703816543144e-05,
"loss": 1.702846145629883,
"step": 50
},
{
"epoch": 0.18404907975460122,
"grad_norm": 2.890625,
"learning_rate": 1.8836725718049562e-05,
"loss": 1.6503068923950195,
"step": 60
},
{
"epoch": 0.2147239263803681,
"grad_norm": 3.265625,
"learning_rate": 1.8328478776615336e-05,
"loss": 1.6176418304443358,
"step": 70
},
{
"epoch": 0.24539877300613497,
"grad_norm": 3.125,
"learning_rate": 1.7737982286028938e-05,
"loss": 1.649836540222168,
"step": 80
},
{
"epoch": 0.27607361963190186,
"grad_norm": 2.671875,
"learning_rate": 1.7071067811865477e-05,
"loss": 1.6427200317382813,
"step": 90
},
{
"epoch": 0.3067484662576687,
"grad_norm": 2.5625,
"learning_rate": 1.6334321600700612e-05,
"loss": 1.5673911094665527,
"step": 100
},
{
"epoch": 0.3374233128834356,
"grad_norm": 3.453125,
"learning_rate": 1.5535019536322158e-05,
"loss": 1.5665663719177245,
"step": 110
},
{
"epoch": 0.36809815950920244,
"grad_norm": 3.28125,
"learning_rate": 1.4681055285292138e-05,
"loss": 1.549239158630371,
"step": 120
},
{
"epoch": 0.3987730061349693,
"grad_norm": 3.015625,
"learning_rate": 1.3780862341472183e-05,
"loss": 1.5795641899108888,
"step": 130
},
{
"epoch": 0.4294478527607362,
"grad_norm": 2.90625,
"learning_rate": 1.2843330739377003e-05,
"loss": 1.5186445236206054,
"step": 140
},
{
"epoch": 0.4601226993865031,
"grad_norm": 2.890625,
"learning_rate": 1.1877719258869827e-05,
"loss": 1.5579788208007812,
"step": 150
},
{
"epoch": 0.49079754601226994,
"grad_norm": 3.578125,
"learning_rate": 1.0893563988239773e-05,
"loss": 1.5645319938659668,
"step": 160
},
{
"epoch": 0.5214723926380368,
"grad_norm": 2.671875,
"learning_rate": 9.900584148664705e-06,
"loss": 1.5919049263000489,
"step": 170
},
{
"epoch": 0.5521472392638037,
"grad_norm": 2.25,
"learning_rate": 8.908586110108794e-06,
"loss": 1.571799087524414,
"step": 180
},
{
"epoch": 0.5828220858895705,
"grad_norm": 2.625,
"learning_rate": 7.927366546564911e-06,
"loss": 1.5389130592346192,
"step": 190
},
{
"epoch": 0.6134969325153374,
"grad_norm": 2.640625,
"learning_rate": 6.966615687051517e-06,
"loss": 1.5266441345214843,
"step": 200
},
{
"epoch": 0.6441717791411042,
"grad_norm": 3.015625,
"learning_rate": 6.03582161782806e-06,
"loss": 1.5582975387573241,
"step": 210
},
{
"epoch": 0.6748466257668712,
"grad_norm": 2.921875,
"learning_rate": 5.144176580911431e-06,
"loss": 1.5671936988830566,
"step": 220
},
{
"epoch": 0.7055214723926381,
"grad_norm": 2.4375,
"learning_rate": 4.3004861942610575e-06,
"loss": 1.5731188774108886,
"step": 230
},
{
"epoch": 0.7361963190184049,
"grad_norm": 3.328125,
"learning_rate": 3.513082490146864e-06,
"loss": 1.5142654418945312,
"step": 240
},
{
"epoch": 0.7668711656441718,
"grad_norm": 3.046875,
"learning_rate": 2.7897416305068325e-06,
"loss": 1.5008227348327636,
"step": 250
},
{
"epoch": 0.7975460122699386,
"grad_norm": 2.875,
"learning_rate": 2.137607111912734e-06,
"loss": 1.585028839111328,
"step": 260
},
{
"epoch": 0.8282208588957055,
"grad_norm": 2.640625,
"learning_rate": 1.5631192185484557e-06,
"loss": 1.571006679534912,
"step": 270
},
{
"epoch": 0.8588957055214724,
"grad_norm": 3.046875,
"learning_rate": 1.0719514199022473e-06,
"loss": 1.5311025619506835,
"step": 280
},
{
"epoch": 0.8895705521472392,
"grad_norm": 2.78125,
"learning_rate": 6.689543412899913e-07,
"loss": 1.5679447174072265,
"step": 290
},
{
"epoch": 0.9202453987730062,
"grad_norm": 2.6875,
"learning_rate": 3.5810786053987025e-07,
"loss": 1.5297722816467285,
"step": 300
},
{
"epoch": 0.950920245398773,
"grad_norm": 2.75,
"learning_rate": 1.4248180391703614e-07,
"loss": 1.5922201156616211,
"step": 310
},
{
"epoch": 0.9815950920245399,
"grad_norm": 2.796875,
"learning_rate": 2.420562944358329e-08,
"loss": 1.512490463256836,
"step": 320
},
{
"epoch": 1.0,
"step": 326,
"total_flos": 1.563295846805975e+17,
"train_loss": 1.6355595296145948,
"train_runtime": 2594.717,
"train_samples_per_second": 0.503,
"train_steps_per_second": 0.126
}
],
"logging_steps": 10,
"max_steps": 326,
"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": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.563295846805975e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}