PEFT
TensorBoard
sql
spider
text-to-sql
sql fine-tune
LoRA
QLoRa
adapter
spider-natsql-wizard-coder-qlora / trainer_state.json
richardr1126's picture
Upload folder using huggingface_hub
b131b21
raw
history blame
12.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.0,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"learning_rate": 4.4444444444444447e-05,
"loss": 1.5005,
"step": 10
},
{
"epoch": 0.16,
"learning_rate": 8.888888888888889e-05,
"loss": 1.2648,
"step": 20
},
{
"epoch": 0.24,
"learning_rate": 0.00013333333333333334,
"loss": 0.8406,
"step": 30
},
{
"epoch": 0.32,
"learning_rate": 0.00017777777777777779,
"loss": 0.496,
"step": 40
},
{
"epoch": 0.4,
"learning_rate": 0.00019931271477663232,
"loss": 0.2602,
"step": 50
},
{
"epoch": 0.48,
"learning_rate": 0.00019793814432989693,
"loss": 0.1365,
"step": 60
},
{
"epoch": 0.56,
"learning_rate": 0.0001965635738831615,
"loss": 0.131,
"step": 70
},
{
"epoch": 0.64,
"learning_rate": 0.00019518900343642613,
"loss": 0.1219,
"step": 80
},
{
"epoch": 0.72,
"learning_rate": 0.00019381443298969073,
"loss": 0.1053,
"step": 90
},
{
"epoch": 0.8,
"learning_rate": 0.00019243986254295533,
"loss": 0.1071,
"step": 100
},
{
"epoch": 0.88,
"learning_rate": 0.00019106529209621996,
"loss": 0.0878,
"step": 110
},
{
"epoch": 0.96,
"learning_rate": 0.00018969072164948454,
"loss": 0.0863,
"step": 120
},
{
"epoch": 1.04,
"learning_rate": 0.00018831615120274914,
"loss": 0.0918,
"step": 130
},
{
"epoch": 1.12,
"learning_rate": 0.00018694158075601377,
"loss": 0.0898,
"step": 140
},
{
"epoch": 1.2,
"learning_rate": 0.00018556701030927837,
"loss": 0.0829,
"step": 150
},
{
"epoch": 1.28,
"learning_rate": 0.00018419243986254294,
"loss": 0.0721,
"step": 160
},
{
"epoch": 1.36,
"learning_rate": 0.00018281786941580757,
"loss": 0.0752,
"step": 170
},
{
"epoch": 1.44,
"learning_rate": 0.00018144329896907217,
"loss": 0.0821,
"step": 180
},
{
"epoch": 1.52,
"learning_rate": 0.00018006872852233677,
"loss": 0.0741,
"step": 190
},
{
"epoch": 1.6,
"learning_rate": 0.0001786941580756014,
"loss": 0.0665,
"step": 200
},
{
"epoch": 1.68,
"learning_rate": 0.00017731958762886598,
"loss": 0.0833,
"step": 210
},
{
"epoch": 1.76,
"learning_rate": 0.00017594501718213058,
"loss": 0.0726,
"step": 220
},
{
"epoch": 1.84,
"learning_rate": 0.0001745704467353952,
"loss": 0.0624,
"step": 230
},
{
"epoch": 1.92,
"learning_rate": 0.0001731958762886598,
"loss": 0.0716,
"step": 240
},
{
"epoch": 2.0,
"learning_rate": 0.00017182130584192438,
"loss": 0.0827,
"step": 250
},
{
"epoch": 2.08,
"learning_rate": 0.000170446735395189,
"loss": 0.0506,
"step": 260
},
{
"epoch": 2.16,
"learning_rate": 0.00016907216494845361,
"loss": 0.0647,
"step": 270
},
{
"epoch": 2.24,
"learning_rate": 0.00016769759450171822,
"loss": 0.0614,
"step": 280
},
{
"epoch": 2.32,
"learning_rate": 0.00016632302405498285,
"loss": 0.0528,
"step": 290
},
{
"epoch": 2.4,
"learning_rate": 0.00016494845360824742,
"loss": 0.0514,
"step": 300
},
{
"epoch": 2.48,
"learning_rate": 0.00016357388316151202,
"loss": 0.0635,
"step": 310
},
{
"epoch": 2.56,
"learning_rate": 0.00016219931271477665,
"loss": 0.0552,
"step": 320
},
{
"epoch": 2.64,
"learning_rate": 0.00016082474226804125,
"loss": 0.06,
"step": 330
},
{
"epoch": 2.72,
"learning_rate": 0.00015945017182130585,
"loss": 0.0611,
"step": 340
},
{
"epoch": 2.8,
"learning_rate": 0.00015807560137457046,
"loss": 0.0667,
"step": 350
},
{
"epoch": 2.88,
"learning_rate": 0.00015670103092783506,
"loss": 0.0669,
"step": 360
},
{
"epoch": 2.96,
"learning_rate": 0.00015532646048109966,
"loss": 0.0589,
"step": 370
},
{
"epoch": 3.04,
"learning_rate": 0.0001539518900343643,
"loss": 0.0516,
"step": 380
},
{
"epoch": 3.12,
"learning_rate": 0.00015257731958762886,
"loss": 0.0415,
"step": 390
},
{
"epoch": 3.2,
"learning_rate": 0.00015120274914089346,
"loss": 0.043,
"step": 400
},
{
"epoch": 3.28,
"learning_rate": 0.0001498281786941581,
"loss": 0.0449,
"step": 410
},
{
"epoch": 3.36,
"learning_rate": 0.0001484536082474227,
"loss": 0.0467,
"step": 420
},
{
"epoch": 3.44,
"learning_rate": 0.0001470790378006873,
"loss": 0.0442,
"step": 430
},
{
"epoch": 3.52,
"learning_rate": 0.0001457044673539519,
"loss": 0.0501,
"step": 440
},
{
"epoch": 3.6,
"learning_rate": 0.0001443298969072165,
"loss": 0.0468,
"step": 450
},
{
"epoch": 3.68,
"learning_rate": 0.0001429553264604811,
"loss": 0.0503,
"step": 460
},
{
"epoch": 3.76,
"learning_rate": 0.00014158075601374573,
"loss": 0.0503,
"step": 470
},
{
"epoch": 3.84,
"learning_rate": 0.0001402061855670103,
"loss": 0.0477,
"step": 480
},
{
"epoch": 3.92,
"learning_rate": 0.0001388316151202749,
"loss": 0.0467,
"step": 490
},
{
"epoch": 4.0,
"learning_rate": 0.00013745704467353953,
"loss": 0.0525,
"step": 500
},
{
"epoch": 4.08,
"learning_rate": 0.00013608247422680414,
"loss": 0.0434,
"step": 510
},
{
"epoch": 4.16,
"learning_rate": 0.00013470790378006874,
"loss": 0.0371,
"step": 520
},
{
"epoch": 4.24,
"learning_rate": 0.00013333333333333334,
"loss": 0.0393,
"step": 530
},
{
"epoch": 4.32,
"learning_rate": 0.00013195876288659794,
"loss": 0.0378,
"step": 540
},
{
"epoch": 4.4,
"learning_rate": 0.00013058419243986254,
"loss": 0.0358,
"step": 550
},
{
"epoch": 4.48,
"learning_rate": 0.00012920962199312717,
"loss": 0.04,
"step": 560
},
{
"epoch": 4.56,
"learning_rate": 0.00012783505154639175,
"loss": 0.0355,
"step": 570
},
{
"epoch": 4.64,
"learning_rate": 0.00012646048109965635,
"loss": 0.0424,
"step": 580
},
{
"epoch": 4.72,
"learning_rate": 0.00012508591065292098,
"loss": 0.0411,
"step": 590
},
{
"epoch": 4.8,
"learning_rate": 0.00012371134020618558,
"loss": 0.0374,
"step": 600
},
{
"epoch": 4.88,
"learning_rate": 0.00012233676975945018,
"loss": 0.0402,
"step": 610
},
{
"epoch": 4.96,
"learning_rate": 0.00012096219931271477,
"loss": 0.0417,
"step": 620
},
{
"epoch": 5.04,
"learning_rate": 0.00011958762886597938,
"loss": 0.0353,
"step": 630
},
{
"epoch": 5.12,
"learning_rate": 0.000118213058419244,
"loss": 0.0328,
"step": 640
},
{
"epoch": 5.2,
"learning_rate": 0.0001168384879725086,
"loss": 0.0356,
"step": 650
},
{
"epoch": 5.28,
"learning_rate": 0.00011546391752577319,
"loss": 0.0354,
"step": 660
},
{
"epoch": 5.36,
"learning_rate": 0.0001140893470790378,
"loss": 0.0326,
"step": 670
},
{
"epoch": 5.44,
"learning_rate": 0.0001127147766323024,
"loss": 0.0358,
"step": 680
},
{
"epoch": 5.52,
"learning_rate": 0.00011134020618556702,
"loss": 0.0355,
"step": 690
},
{
"epoch": 5.6,
"learning_rate": 0.00010996563573883164,
"loss": 0.0342,
"step": 700
},
{
"epoch": 5.68,
"learning_rate": 0.00010859106529209621,
"loss": 0.0335,
"step": 710
},
{
"epoch": 5.76,
"learning_rate": 0.00010721649484536083,
"loss": 0.0362,
"step": 720
},
{
"epoch": 5.84,
"learning_rate": 0.00010584192439862544,
"loss": 0.0343,
"step": 730
},
{
"epoch": 5.92,
"learning_rate": 0.00010446735395189004,
"loss": 0.0329,
"step": 740
},
{
"epoch": 6.0,
"learning_rate": 0.00010309278350515463,
"loss": 0.0313,
"step": 750
},
{
"epoch": 6.08,
"learning_rate": 0.00010171821305841925,
"loss": 0.028,
"step": 760
},
{
"epoch": 6.16,
"learning_rate": 0.00010034364261168385,
"loss": 0.0317,
"step": 770
},
{
"epoch": 6.24,
"learning_rate": 9.896907216494846e-05,
"loss": 0.029,
"step": 780
},
{
"epoch": 6.32,
"learning_rate": 9.759450171821306e-05,
"loss": 0.0288,
"step": 790
},
{
"epoch": 6.4,
"learning_rate": 9.621993127147767e-05,
"loss": 0.0281,
"step": 800
},
{
"epoch": 6.48,
"learning_rate": 9.484536082474227e-05,
"loss": 0.0309,
"step": 810
},
{
"epoch": 6.56,
"learning_rate": 9.347079037800688e-05,
"loss": 0.0334,
"step": 820
},
{
"epoch": 6.64,
"learning_rate": 9.209621993127147e-05,
"loss": 0.0292,
"step": 830
},
{
"epoch": 6.72,
"learning_rate": 9.072164948453609e-05,
"loss": 0.0331,
"step": 840
},
{
"epoch": 6.8,
"learning_rate": 8.93470790378007e-05,
"loss": 0.0304,
"step": 850
},
{
"epoch": 6.88,
"learning_rate": 8.797250859106529e-05,
"loss": 0.0308,
"step": 860
},
{
"epoch": 6.96,
"learning_rate": 8.65979381443299e-05,
"loss": 0.0318,
"step": 870
},
{
"epoch": 7.04,
"learning_rate": 8.52233676975945e-05,
"loss": 0.0257,
"step": 880
},
{
"epoch": 7.12,
"learning_rate": 8.384879725085911e-05,
"loss": 0.0266,
"step": 890
},
{
"epoch": 7.2,
"learning_rate": 8.247422680412371e-05,
"loss": 0.0251,
"step": 900
},
{
"epoch": 7.28,
"learning_rate": 8.109965635738833e-05,
"loss": 0.0269,
"step": 910
},
{
"epoch": 7.36,
"learning_rate": 7.972508591065293e-05,
"loss": 0.0296,
"step": 920
},
{
"epoch": 7.44,
"learning_rate": 7.835051546391753e-05,
"loss": 0.0285,
"step": 930
},
{
"epoch": 7.52,
"learning_rate": 7.697594501718214e-05,
"loss": 0.0286,
"step": 940
},
{
"epoch": 7.6,
"learning_rate": 7.560137457044673e-05,
"loss": 0.024,
"step": 950
},
{
"epoch": 7.68,
"learning_rate": 7.422680412371135e-05,
"loss": 0.0267,
"step": 960
},
{
"epoch": 7.76,
"learning_rate": 7.285223367697595e-05,
"loss": 0.0296,
"step": 970
},
{
"epoch": 7.84,
"learning_rate": 7.147766323024055e-05,
"loss": 0.0265,
"step": 980
},
{
"epoch": 7.92,
"learning_rate": 7.010309278350515e-05,
"loss": 0.0282,
"step": 990
},
{
"epoch": 8.0,
"learning_rate": 6.872852233676977e-05,
"loss": 0.028,
"step": 1000
}
],
"max_steps": 1500,
"num_train_epochs": 12,
"total_flos": 4.91514246463488e+17,
"trial_name": null,
"trial_params": null
}