KKHYA/qwen3-1.7b-fft-coding
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: KKHYA/qwen3-1.7b-fft-coding
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-16 06:52:16 +08:00
commit 7d4564573e
18 changed files with 8348 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

701
trainer_state.json Normal file
View File

@@ -0,0 +1,701 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"eval_steps": 500,
"global_step": 940,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.042666666666666665,
"grad_norm": 22.81595230102539,
"learning_rate": 9.574468085106384e-07,
"loss": 1.291497802734375,
"step": 10
},
{
"epoch": 0.08533333333333333,
"grad_norm": 8.337886810302734,
"learning_rate": 2.021276595744681e-06,
"loss": 1.182865810394287,
"step": 20
},
{
"epoch": 0.128,
"grad_norm": 2.478001594543457,
"learning_rate": 3.0851063829787237e-06,
"loss": 0.9575789451599122,
"step": 30
},
{
"epoch": 0.17066666666666666,
"grad_norm": 1.4279086589813232,
"learning_rate": 4.148936170212766e-06,
"loss": 0.8388131141662598,
"step": 40
},
{
"epoch": 0.21333333333333335,
"grad_norm": 1.040152907371521,
"learning_rate": 5.212765957446809e-06,
"loss": 0.8148186683654786,
"step": 50
},
{
"epoch": 0.256,
"grad_norm": 0.9204385876655579,
"learning_rate": 6.276595744680851e-06,
"loss": 0.7651220321655273,
"step": 60
},
{
"epoch": 0.2986666666666667,
"grad_norm": 0.8933783769607544,
"learning_rate": 7.340425531914894e-06,
"loss": 0.7899383544921875,
"step": 70
},
{
"epoch": 0.3413333333333333,
"grad_norm": 0.926196277141571,
"learning_rate": 8.404255319148937e-06,
"loss": 0.7782301902770996,
"step": 80
},
{
"epoch": 0.384,
"grad_norm": 0.9980058073997498,
"learning_rate": 9.46808510638298e-06,
"loss": 0.7684392929077148,
"step": 90
},
{
"epoch": 0.4266666666666667,
"grad_norm": 0.9042799472808838,
"learning_rate": 9.999138160172624e-06,
"loss": 0.7520565032958985,
"step": 100
},
{
"epoch": 0.4693333333333333,
"grad_norm": 0.8850747346878052,
"learning_rate": 9.99224522409411e-06,
"loss": 0.7115557670593262,
"step": 110
},
{
"epoch": 0.512,
"grad_norm": 0.9096830487251282,
"learning_rate": 9.97846885608885e-06,
"loss": 0.7434285163879395,
"step": 120
},
{
"epoch": 0.5546666666666666,
"grad_norm": 0.940818190574646,
"learning_rate": 9.957828051355817e-06,
"loss": 0.7457537651062012,
"step": 130
},
{
"epoch": 0.5973333333333334,
"grad_norm": 0.9445077180862427,
"learning_rate": 9.930351269950144e-06,
"loss": 0.7388599872589111,
"step": 140
},
{
"epoch": 0.64,
"grad_norm": 0.8463093042373657,
"learning_rate": 9.896076397541676e-06,
"loss": 0.7285007476806641,
"step": 150
},
{
"epoch": 0.6826666666666666,
"grad_norm": 0.8920971751213074,
"learning_rate": 9.855050693177286e-06,
"loss": 0.7659842491149902,
"step": 160
},
{
"epoch": 0.7253333333333334,
"grad_norm": 0.9197255969047546,
"learning_rate": 9.807330724118906e-06,
"loss": 0.724073839187622,
"step": 170
},
{
"epoch": 0.768,
"grad_norm": 0.9320898652076721,
"learning_rate": 9.752982287847193e-06,
"loss": 0.747947883605957,
"step": 180
},
{
"epoch": 0.8106666666666666,
"grad_norm": 0.8373203277587891,
"learning_rate": 9.692080321338317e-06,
"loss": 0.7283991813659668,
"step": 190
},
{
"epoch": 0.8533333333333334,
"grad_norm": 0.8440167307853699,
"learning_rate": 9.624708797739002e-06,
"loss": 0.7407590389251709,
"step": 200
},
{
"epoch": 0.896,
"grad_norm": 0.9070562720298767,
"learning_rate": 9.550960610582251e-06,
"loss": 0.724196481704712,
"step": 210
},
{
"epoch": 0.9386666666666666,
"grad_norm": 0.8882600665092468,
"learning_rate": 9.47093744570344e-06,
"loss": 0.7334166526794433,
"step": 220
},
{
"epoch": 0.9813333333333333,
"grad_norm": 0.9043309688568115,
"learning_rate": 9.384749641033358e-06,
"loss": 0.8169802665710449,
"step": 230
},
{
"epoch": 1.0213333333333334,
"grad_norm": 0.8862775564193726,
"learning_rate": 9.292516034461517e-06,
"loss": 0.7211981773376465,
"step": 240
},
{
"epoch": 1.064,
"grad_norm": 0.8914813995361328,
"learning_rate": 9.194363799979517e-06,
"loss": 0.6335953712463379,
"step": 250
},
{
"epoch": 1.1066666666666667,
"grad_norm": 0.9117757081985474,
"learning_rate": 9.090428272330381e-06,
"loss": 0.6689927577972412,
"step": 260
},
{
"epoch": 1.1493333333333333,
"grad_norm": 0.9108397364616394,
"learning_rate": 8.980852760405645e-06,
"loss": 0.6809295654296875,
"step": 270
},
{
"epoch": 1.192,
"grad_norm": 0.9220501780509949,
"learning_rate": 8.865788349647496e-06,
"loss": 0.6914172172546387,
"step": 280
},
{
"epoch": 1.2346666666666666,
"grad_norm": 0.8409727215766907,
"learning_rate": 8.745393693728395e-06,
"loss": 0.6650928974151611,
"step": 290
},
{
"epoch": 1.2773333333333334,
"grad_norm": 0.9512217044830322,
"learning_rate": 8.619834795795458e-06,
"loss": 0.6717124938964844,
"step": 300
},
{
"epoch": 1.32,
"grad_norm": 0.8877426385879517,
"learning_rate": 8.489284779581179e-06,
"loss": 0.6726479530334473,
"step": 310
},
{
"epoch": 1.3626666666666667,
"grad_norm": 0.8496021032333374,
"learning_rate": 8.353923650696119e-06,
"loss": 0.6797503471374512,
"step": 320
},
{
"epoch": 1.4053333333333333,
"grad_norm": 0.8745173811912537,
"learning_rate": 8.213938048432697e-06,
"loss": 0.6944191932678223,
"step": 330
},
{
"epoch": 1.448,
"grad_norm": 0.8742923736572266,
"learning_rate": 8.069520988422292e-06,
"loss": 0.619914960861206,
"step": 340
},
{
"epoch": 1.4906666666666666,
"grad_norm": 0.9417562484741211,
"learning_rate": 7.920871596500473e-06,
"loss": 0.6835647583007812,
"step": 350
},
{
"epoch": 1.5333333333333332,
"grad_norm": 0.9726133942604065,
"learning_rate": 7.768194834147362e-06,
"loss": 0.6706738471984863,
"step": 360
},
{
"epoch": 1.576,
"grad_norm": 0.8959471583366394,
"learning_rate": 7.611701215881635e-06,
"loss": 0.690638542175293,
"step": 370
},
{
"epoch": 1.6186666666666667,
"grad_norm": 0.9309572577476501,
"learning_rate": 7.4516065189978625e-06,
"loss": 0.6714137077331543,
"step": 380
},
{
"epoch": 1.6613333333333333,
"grad_norm": 0.9652783274650574,
"learning_rate": 7.288131486047414e-06,
"loss": 0.6779637336730957,
"step": 390
},
{
"epoch": 1.704,
"grad_norm": 0.8535190224647522,
"learning_rate": 7.121501520473137e-06,
"loss": 0.6494068622589111,
"step": 400
},
{
"epoch": 1.7466666666666666,
"grad_norm": 0.9693210124969482,
"learning_rate": 6.9519463758174745e-06,
"loss": 0.6467916011810303,
"step": 410
},
{
"epoch": 1.7893333333333334,
"grad_norm": 0.913555383682251,
"learning_rate": 6.77969983893257e-06,
"loss": 0.6865511894226074,
"step": 420
},
{
"epoch": 1.8319999999999999,
"grad_norm": 0.8626614212989807,
"learning_rate": 6.604999407629137e-06,
"loss": 0.6830032348632813,
"step": 430
},
{
"epoch": 1.8746666666666667,
"grad_norm": 0.9277188777923584,
"learning_rate": 6.428085963208567e-06,
"loss": 0.6937445640563965,
"step": 440
},
{
"epoch": 1.9173333333333333,
"grad_norm": 0.9122670292854309,
"learning_rate": 6.249203438329799e-06,
"loss": 0.6877000331878662,
"step": 450
},
{
"epoch": 1.96,
"grad_norm": 0.8714756369590759,
"learning_rate": 6.0685984806689055e-06,
"loss": 0.6529797077178955,
"step": 460
},
{
"epoch": 2.0,
"grad_norm": 1.4163620471954346,
"learning_rate": 5.886520112835128e-06,
"loss": 0.6860092163085938,
"step": 470
},
{
"epoch": 2.042666666666667,
"grad_norm": 0.8940126299858093,
"learning_rate": 5.703219389012317e-06,
"loss": 0.6075316905975342,
"step": 480
},
{
"epoch": 2.0853333333333333,
"grad_norm": 0.9413266181945801,
"learning_rate": 5.518949048799176e-06,
"loss": 0.5943183422088623,
"step": 490
},
{
"epoch": 2.128,
"grad_norm": 0.932360827922821,
"learning_rate": 5.3339631687256085e-06,
"loss": 0.5897200107574463,
"step": 500
},
{
"epoch": 2.1706666666666665,
"grad_norm": 0.9619448184967041,
"learning_rate": 5.148516811925684e-06,
"loss": 0.6106101036071777,
"step": 510
},
{
"epoch": 2.2133333333333334,
"grad_norm": 0.9640690684318542,
"learning_rate": 4.962865676450239e-06,
"loss": 0.6104888916015625,
"step": 520
},
{
"epoch": 2.2560000000000002,
"grad_norm": 0.9159106612205505,
"learning_rate": 4.777265742704039e-06,
"loss": 0.5798359870910644,
"step": 530
},
{
"epoch": 2.2986666666666666,
"grad_norm": 0.9406466484069824,
"learning_rate": 4.591972920493638e-06,
"loss": 0.6197110652923584,
"step": 540
},
{
"epoch": 2.3413333333333335,
"grad_norm": 1.0240126848220825,
"learning_rate": 4.40724269617256e-06,
"loss": 0.5831963539123535,
"step": 550
},
{
"epoch": 2.384,
"grad_norm": 0.9565466046333313,
"learning_rate": 4.223329780370359e-06,
"loss": 0.598298454284668,
"step": 560
},
{
"epoch": 2.4266666666666667,
"grad_norm": 0.9118269085884094,
"learning_rate": 4.04048775679127e-06,
"loss": 0.5884403705596923,
"step": 570
},
{
"epoch": 2.469333333333333,
"grad_norm": 0.9704470038414001,
"learning_rate": 3.858968732566685e-06,
"loss": 0.5839417457580567,
"step": 580
},
{
"epoch": 2.512,
"grad_norm": 0.949148416519165,
"learning_rate": 3.6790229906435706e-06,
"loss": 0.6246652126312255,
"step": 590
},
{
"epoch": 2.554666666666667,
"grad_norm": 0.9721353054046631,
"learning_rate": 3.5008986446881088e-06,
"loss": 0.6042469024658204,
"step": 600
},
{
"epoch": 2.5973333333333333,
"grad_norm": 1.11699378490448,
"learning_rate": 3.3248412969804065e-06,
"loss": 0.6285554885864257,
"step": 610
},
{
"epoch": 2.64,
"grad_norm": 1.023742437362671,
"learning_rate": 3.1510936997719557e-06,
"loss": 0.6006599426269531,
"step": 620
},
{
"epoch": 2.6826666666666665,
"grad_norm": 1.056766390800476,
"learning_rate": 2.9798954205727886e-06,
"loss": 0.5928638458251954,
"step": 630
},
{
"epoch": 2.7253333333333334,
"grad_norm": 1.0377728939056396,
"learning_rate": 2.811482511829842e-06,
"loss": 0.6103617668151855,
"step": 640
},
{
"epoch": 2.768,
"grad_norm": 0.9824387431144714,
"learning_rate": 2.6460871854519594e-06,
"loss": 0.5874536514282227,
"step": 650
},
{
"epoch": 2.8106666666666666,
"grad_norm": 1.0173842906951904,
"learning_rate": 2.483937492630345e-06,
"loss": 0.5812715053558349,
"step": 660
},
{
"epoch": 2.8533333333333335,
"grad_norm": 1.1885449886322021,
"learning_rate": 2.3252570093959e-06,
"loss": 0.609982681274414,
"step": 670
},
{
"epoch": 2.896,
"grad_norm": 0.974206805229187,
"learning_rate": 2.1702645283470238e-06,
"loss": 0.6121101379394531,
"step": 680
},
{
"epoch": 2.9386666666666668,
"grad_norm": 0.9060782194137573,
"learning_rate": 2.0191737569729492e-06,
"loss": 0.6171843528747558,
"step": 690
},
{
"epoch": 2.981333333333333,
"grad_norm": 1.0292282104492188,
"learning_rate": 1.872193022988526e-06,
"loss": 0.5880200386047363,
"step": 700
},
{
"epoch": 3.021333333333333,
"grad_norm": 1.00603449344635,
"learning_rate": 1.7295249870867898e-06,
"loss": 0.5795096397399903,
"step": 710
},
{
"epoch": 3.064,
"grad_norm": 0.9750069379806519,
"learning_rate": 1.5913663635053578e-06,
"loss": 0.5702518463134766,
"step": 720
},
{
"epoch": 3.1066666666666665,
"grad_norm": 0.9798346161842346,
"learning_rate": 1.457907648791943e-06,
"loss": 0.5839662551879883,
"step": 730
},
{
"epoch": 3.1493333333333333,
"grad_norm": 1.0039501190185547,
"learning_rate": 1.329332859142967e-06,
"loss": 0.5281820297241211,
"step": 740
},
{
"epoch": 3.192,
"grad_norm": 0.9754037857055664,
"learning_rate": 1.205819276677464e-06,
"loss": 0.5751385688781738,
"step": 750
},
{
"epoch": 3.2346666666666666,
"grad_norm": 0.990886926651001,
"learning_rate": 1.0875372049960697e-06,
"loss": 0.5494537353515625,
"step": 760
},
{
"epoch": 3.2773333333333334,
"grad_norm": 0.9957782626152039,
"learning_rate": 9.746497343621857e-07,
"loss": 0.5537368297576905,
"step": 770
},
{
"epoch": 3.32,
"grad_norm": 1.0468347072601318,
"learning_rate": 8.673125168290713e-07,
"loss": 0.55874662399292,
"step": 780
},
{
"epoch": 3.3626666666666667,
"grad_norm": 0.949479877948761,
"learning_rate": 7.656735516229125e-07,
"loss": 0.565284252166748,
"step": 790
},
{
"epoch": 3.405333333333333,
"grad_norm": 1.3505475521087646,
"learning_rate": 6.698729810778065e-07,
"loss": 0.5531235694885254,
"step": 800
},
{
"epoch": 3.448,
"grad_norm": 1.0080723762512207,
"learning_rate": 5.800428974040311e-07,
"loss": 0.5778326511383056,
"step": 810
},
{
"epoch": 3.490666666666667,
"grad_norm": 0.9772297143936157,
"learning_rate": 4.963071605560144e-07,
"loss": 0.5518184661865234,
"step": 820
},
{
"epoch": 3.533333333333333,
"grad_norm": 1.0470722913742065,
"learning_rate": 4.187812274511427e-07,
"loss": 0.5773732185363769,
"step": 830
},
{
"epoch": 3.576,
"grad_norm": 0.9107851982116699,
"learning_rate": 3.4757199277490106e-07,
"loss": 0.5663552284240723,
"step": 840
},
{
"epoch": 3.618666666666667,
"grad_norm": 0.9870362281799316,
"learning_rate": 2.8277764159181484e-07,
"loss": 0.5664983272552491,
"step": 850
},
{
"epoch": 3.6613333333333333,
"grad_norm": 1.0563737154006958,
"learning_rate": 2.2448751396543788e-07,
"loss": 0.5846799373626709,
"step": 860
},
{
"epoch": 3.7039999999999997,
"grad_norm": 1.0350754261016846,
"learning_rate": 1.7278198177405614e-07,
"loss": 0.5573970794677734,
"step": 870
},
{
"epoch": 3.7466666666666666,
"grad_norm": 1.0310237407684326,
"learning_rate": 1.2773233789193816e-07,
"loss": 0.5604241371154786,
"step": 880
},
{
"epoch": 3.7893333333333334,
"grad_norm": 0.9566333889961243,
"learning_rate": 8.940069788894389e-08,
"loss": 0.5811796188354492,
"step": 890
},
{
"epoch": 3.832,
"grad_norm": 0.9202328324317932,
"learning_rate": 5.783991438403802e-08,
"loss": 0.5551981449127197,
"step": 900
},
{
"epoch": 3.8746666666666667,
"grad_norm": 0.9610781073570251,
"learning_rate": 3.309350417077972e-08,
"loss": 0.5618691444396973,
"step": 910
},
{
"epoch": 3.9173333333333336,
"grad_norm": 0.9684038162231445,
"learning_rate": 1.5195588215283773e-08,
"loss": 0.5391227722167968,
"step": 920
},
{
"epoch": 3.96,
"grad_norm": 0.9603227972984314,
"learning_rate": 4.170844609387992e-09,
"loss": 0.5671097278594971,
"step": 930
},
{
"epoch": 4.0,
"grad_norm": 1.651139497756958,
"learning_rate": 3.447454388127991e-11,
"loss": 0.5210320949554443,
"step": 940
},
{
"epoch": 4.0,
"step": 940,
"total_flos": 7.974893111623025e+17,
"train_loss": 0.6604051219656112,
"train_runtime": 3155.399,
"train_samples_per_second": 38.03,
"train_steps_per_second": 0.298
}
],
"logging_steps": 10,
"max_steps": 940,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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": 7.974893111623025e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}