Files
Qwen2-0.2B-it/trainer_state.json
ModelHub XC ca47e0c5e7 初始化项目,由ModelHub XC社区提供模型
Model: FlameF0X/Qwen2-0.2B-it
Source: Original Platform
2026-07-25 05:09:09 +08:00

315 lines
7.8 KiB
JSON

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.807384615384615,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.24615384615384617,
"grad_norm": 0.09971032291650772,
"learning_rate": 7.921600000000001e-05,
"loss": 3.8301455688476564,
"step": 50
},
{
"epoch": 0.49230769230769234,
"grad_norm": 0.0911579355597496,
"learning_rate": 7.8416e-05,
"loss": 3.0332159423828124,
"step": 100
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.10190442204475403,
"learning_rate": 7.7616e-05,
"loss": 2.7591339111328126,
"step": 150
},
{
"epoch": 0.9846153846153847,
"grad_norm": 0.09316737949848175,
"learning_rate": 7.6816e-05,
"loss": 2.617864074707031,
"step": 200
},
{
"epoch": 1.2264615384615385,
"grad_norm": 0.08559751510620117,
"learning_rate": 7.601600000000001e-05,
"loss": 2.3154002380371095,
"step": 250
},
{
"epoch": 1.4726153846153847,
"grad_norm": 0.0818333625793457,
"learning_rate": 7.5216e-05,
"loss": 2.227242126464844,
"step": 300
},
{
"epoch": 1.7187692307692308,
"grad_norm": 0.09082052856683731,
"learning_rate": 7.441600000000001e-05,
"loss": 2.1838539123535154,
"step": 350
},
{
"epoch": 1.964923076923077,
"grad_norm": 0.08575436472892761,
"learning_rate": 7.361600000000001e-05,
"loss": 2.1341651916503905,
"step": 400
},
{
"epoch": 2.206769230769231,
"grad_norm": 0.08966775238513947,
"learning_rate": 7.2816e-05,
"loss": 1.9519345092773437,
"step": 450
},
{
"epoch": 2.452923076923077,
"grad_norm": 0.08918383717536926,
"learning_rate": 7.201600000000001e-05,
"loss": 1.8568724060058595,
"step": 500
},
{
"epoch": 2.699076923076923,
"grad_norm": 0.09143362194299698,
"learning_rate": 7.1216e-05,
"loss": 1.8383006286621093,
"step": 550
},
{
"epoch": 2.9452307692307693,
"grad_norm": 0.0969746857881546,
"learning_rate": 7.0416e-05,
"loss": 1.8297712707519531,
"step": 600
},
{
"epoch": 3.187076923076923,
"grad_norm": 0.09824724495410919,
"learning_rate": 6.9616e-05,
"loss": 1.6545506286621094,
"step": 650
},
{
"epoch": 3.4332307692307693,
"grad_norm": 0.08493440598249435,
"learning_rate": 6.8816e-05,
"loss": 1.6011067199707032,
"step": 700
},
{
"epoch": 3.6793846153846155,
"grad_norm": 0.08676321804523468,
"learning_rate": 6.801600000000001e-05,
"loss": 1.5964797973632812,
"step": 750
},
{
"epoch": 3.9255384615384616,
"grad_norm": 0.09471355378627777,
"learning_rate": 6.7216e-05,
"loss": 1.5877139282226562,
"step": 800
},
{
"epoch": 4.1673846153846155,
"grad_norm": 0.08782424032688141,
"learning_rate": 6.641600000000001e-05,
"loss": 1.4405186462402344,
"step": 850
},
{
"epoch": 4.413538461538462,
"grad_norm": 0.09666605293750763,
"learning_rate": 6.5616e-05,
"loss": 1.383701171875,
"step": 900
},
{
"epoch": 4.659692307692308,
"grad_norm": 0.10380911082029343,
"learning_rate": 6.481600000000001e-05,
"loss": 1.375392608642578,
"step": 950
},
{
"epoch": 4.905846153846154,
"grad_norm": 0.10152668505907059,
"learning_rate": 6.4016e-05,
"loss": 1.3678237915039062,
"step": 1000
},
{
"epoch": 5.147692307692307,
"grad_norm": 0.102939173579216,
"learning_rate": 6.321600000000001e-05,
"loss": 1.257767333984375,
"step": 1050
},
{
"epoch": 5.3938461538461535,
"grad_norm": 0.09689474105834961,
"learning_rate": 6.241600000000001e-05,
"loss": 1.179140625,
"step": 1100
},
{
"epoch": 5.64,
"grad_norm": 0.09813547879457474,
"learning_rate": 6.1616e-05,
"loss": 1.1883023071289063,
"step": 1150
},
{
"epoch": 5.886153846153846,
"grad_norm": 0.10634688287973404,
"learning_rate": 6.0816e-05,
"loss": 1.196829605102539,
"step": 1200
},
{
"epoch": 6.128,
"grad_norm": 0.10477212816476822,
"learning_rate": 6.0016e-05,
"loss": 1.0858740234375,
"step": 1250
},
{
"epoch": 6.374153846153846,
"grad_norm": 0.10455155372619629,
"learning_rate": 5.9216000000000004e-05,
"loss": 0.9896931457519531,
"step": 1300
},
{
"epoch": 6.6203076923076924,
"grad_norm": 0.10506019741296768,
"learning_rate": 5.8416000000000004e-05,
"loss": 1.0163351440429687,
"step": 1350
},
{
"epoch": 6.866461538461539,
"grad_norm": 0.1090712919831276,
"learning_rate": 5.7616e-05,
"loss": 1.0064225006103515,
"step": 1400
},
{
"epoch": 7.108307692307692,
"grad_norm": 0.10628747940063477,
"learning_rate": 5.6816000000000006e-05,
"loss": 0.931029052734375,
"step": 1450
},
{
"epoch": 7.354461538461538,
"grad_norm": 0.1018829494714737,
"learning_rate": 5.601600000000001e-05,
"loss": 0.8393967437744141,
"step": 1500
},
{
"epoch": 7.600615384615384,
"grad_norm": 0.11559069901704788,
"learning_rate": 5.521600000000001e-05,
"loss": 0.8411316680908203,
"step": 1550
},
{
"epoch": 7.8467692307692305,
"grad_norm": 0.12172011286020279,
"learning_rate": 5.441600000000001e-05,
"loss": 0.8445599365234375,
"step": 1600
},
{
"epoch": 8.088615384615384,
"grad_norm": 0.09611531347036362,
"learning_rate": 5.3616e-05,
"loss": 0.7935149383544922,
"step": 1650
},
{
"epoch": 8.334769230769231,
"grad_norm": 0.11105120927095413,
"learning_rate": 5.2816000000000004e-05,
"loss": 0.6863140106201172,
"step": 1700
},
{
"epoch": 8.580923076923076,
"grad_norm": 0.10133285075426102,
"learning_rate": 5.2016000000000005e-05,
"loss": 0.6949832153320312,
"step": 1750
},
{
"epoch": 8.827076923076923,
"grad_norm": 0.11194281280040741,
"learning_rate": 5.1216000000000006e-05,
"loss": 0.7070323944091796,
"step": 1800
},
{
"epoch": 9.068923076923078,
"grad_norm": 0.093862384557724,
"learning_rate": 5.0416e-05,
"loss": 0.6766038513183594,
"step": 1850
},
{
"epoch": 9.315076923076923,
"grad_norm": 0.1024981439113617,
"learning_rate": 4.9616e-05,
"loss": 0.5633995056152343,
"step": 1900
},
{
"epoch": 9.56123076923077,
"grad_norm": 0.10483216494321823,
"learning_rate": 4.8816e-05,
"loss": 0.5755315399169922,
"step": 1950
},
{
"epoch": 9.807384615384615,
"grad_norm": 0.11396331340074539,
"learning_rate": 4.8016e-05,
"loss": 0.5865091705322265,
"step": 2000
}
],
"logging_steps": 50,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 25,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.019225655836672e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}