codellama-7b-sft-lora-func-names / trainer_state.json
hynky's picture
hynky HF staff
Model save
c8eaa54
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.03548406174226743,
"eval_steps": 180,
"global_step": 900,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.444444444444445e-07,
"loss": 1.4612,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 2.222222222222222e-06,
"loss": 1.4717,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 4.444444444444444e-06,
"loss": 1.4887,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 6.666666666666667e-06,
"loss": 1.4126,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 8.888888888888888e-06,
"loss": 1.2639,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 1.1111111111111113e-05,
"loss": 1.1005,
"step": 25
},
{
"epoch": 0.0,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.0341,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 1.555555555555556e-05,
"loss": 1.0016,
"step": 35
},
{
"epoch": 0.0,
"learning_rate": 1.7777777777777777e-05,
"loss": 0.9879,
"step": 40
},
{
"epoch": 0.0,
"learning_rate": 2e-05,
"loss": 0.947,
"step": 45
},
{
"epoch": 0.0,
"learning_rate": 2.2222222222222227e-05,
"loss": 0.9558,
"step": 50
},
{
"epoch": 0.0,
"learning_rate": 2.444444444444445e-05,
"loss": 0.9208,
"step": 55
},
{
"epoch": 0.0,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.9096,
"step": 60
},
{
"epoch": 0.0,
"learning_rate": 2.888888888888889e-05,
"loss": 0.8924,
"step": 65
},
{
"epoch": 0.0,
"learning_rate": 3.111111111111112e-05,
"loss": 0.8883,
"step": 70
},
{
"epoch": 0.0,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.879,
"step": 75
},
{
"epoch": 0.0,
"learning_rate": 3.555555555555555e-05,
"loss": 0.8643,
"step": 80
},
{
"epoch": 0.0,
"learning_rate": 3.777777777777778e-05,
"loss": 0.8491,
"step": 85
},
{
"epoch": 0.0,
"learning_rate": 4e-05,
"loss": 0.8485,
"step": 90
},
{
"epoch": 0.0,
"learning_rate": 3.999623940897003e-05,
"loss": 0.8734,
"step": 95
},
{
"epoch": 0.0,
"learning_rate": 3.998495905008461e-05,
"loss": 0.8522,
"step": 100
},
{
"epoch": 0.0,
"learning_rate": 3.996616316542537e-05,
"loss": 0.8434,
"step": 105
},
{
"epoch": 0.0,
"learning_rate": 3.993985882335584e-05,
"loss": 0.8312,
"step": 110
},
{
"epoch": 0.0,
"learning_rate": 3.9906055915863316e-05,
"loss": 0.8248,
"step": 115
},
{
"epoch": 0.0,
"learning_rate": 3.9864767154838864e-05,
"loss": 0.8387,
"step": 120
},
{
"epoch": 0.0,
"learning_rate": 3.9816008067296905e-05,
"loss": 0.8191,
"step": 125
},
{
"epoch": 0.01,
"learning_rate": 3.9759796989536185e-05,
"loss": 0.8047,
"step": 130
},
{
"epoch": 0.01,
"learning_rate": 3.9696155060244166e-05,
"loss": 0.7999,
"step": 135
},
{
"epoch": 0.01,
"learning_rate": 3.9625106212547696e-05,
"loss": 0.7841,
"step": 140
},
{
"epoch": 0.01,
"learning_rate": 3.9546677165012714e-05,
"loss": 0.7546,
"step": 145
},
{
"epoch": 0.01,
"learning_rate": 3.946089741159648e-05,
"loss": 0.7539,
"step": 150
},
{
"epoch": 0.01,
"learning_rate": 3.9367799210556124e-05,
"loss": 0.7346,
"step": 155
},
{
"epoch": 0.01,
"learning_rate": 3.926741757231761e-05,
"loss": 0.7315,
"step": 160
},
{
"epoch": 0.01,
"learning_rate": 3.915979024630978e-05,
"loss": 0.744,
"step": 165
},
{
"epoch": 0.01,
"learning_rate": 3.904495770676831e-05,
"loss": 0.7298,
"step": 170
},
{
"epoch": 0.01,
"learning_rate": 3.892296313751502e-05,
"loss": 0.7385,
"step": 175
},
{
"epoch": 0.01,
"learning_rate": 3.879385241571817e-05,
"loss": 0.7541,
"step": 180
},
{
"epoch": 0.01,
"eval_loss": 0.7222402691841125,
"eval_runtime": 118.1542,
"eval_samples_per_second": 16.927,
"eval_steps_per_second": 4.232,
"step": 180
},
{
"epoch": 0.01,
"learning_rate": 3.865767409464002e-05,
"loss": 0.7311,
"step": 185
},
{
"epoch": 0.01,
"learning_rate": 3.8514479385377813e-05,
"loss": 0.7376,
"step": 190
},
{
"epoch": 0.01,
"learning_rate": 3.8364322137605484e-05,
"loss": 0.727,
"step": 195
},
{
"epoch": 0.01,
"learning_rate": 3.8207258819322936e-05,
"loss": 0.739,
"step": 200
},
{
"epoch": 0.01,
"learning_rate": 3.804334849562076e-05,
"loss": 0.741,
"step": 205
},
{
"epoch": 0.01,
"learning_rate": 3.787265280646825e-05,
"loss": 0.7216,
"step": 210
},
{
"epoch": 0.01,
"learning_rate": 3.7695235943533155e-05,
"loss": 0.7115,
"step": 215
},
{
"epoch": 0.01,
"learning_rate": 3.7511164626041823e-05,
"loss": 0.731,
"step": 220
},
{
"epoch": 0.01,
"learning_rate": 3.732050807568878e-05,
"loss": 0.7185,
"step": 225
},
{
"epoch": 0.01,
"learning_rate": 3.7123337990605335e-05,
"loss": 0.729,
"step": 230
},
{
"epoch": 0.01,
"learning_rate": 3.691972851839682e-05,
"loss": 0.7485,
"step": 235
},
{
"epoch": 0.01,
"learning_rate": 3.6709756228258735e-05,
"loss": 0.7344,
"step": 240
},
{
"epoch": 0.01,
"learning_rate": 3.649350008218214e-05,
"loss": 0.7527,
"step": 245
},
{
"epoch": 0.01,
"learning_rate": 3.6271041405259354e-05,
"loss": 0.7381,
"step": 250
},
{
"epoch": 0.01,
"learning_rate": 3.604246385510088e-05,
"loss": 0.7512,
"step": 255
},
{
"epoch": 0.01,
"learning_rate": 3.580785339037519e-05,
"loss": 0.7368,
"step": 260
},
{
"epoch": 0.01,
"learning_rate": 3.5567298238483206e-05,
"loss": 0.7228,
"step": 265
},
{
"epoch": 0.01,
"learning_rate": 3.532088886237956e-05,
"loss": 0.7361,
"step": 270
},
{
"epoch": 0.01,
"learning_rate": 3.506871792655321e-05,
"loss": 0.727,
"step": 275
},
{
"epoch": 0.01,
"learning_rate": 3.48108802621801e-05,
"loss": 0.7198,
"step": 280
},
{
"epoch": 0.01,
"learning_rate": 3.4547472831460976e-05,
"loss": 0.736,
"step": 285
},
{
"epoch": 0.01,
"learning_rate": 3.4278594691157985e-05,
"loss": 0.7552,
"step": 290
},
{
"epoch": 0.01,
"learning_rate": 3.400434695534337e-05,
"loss": 0.7316,
"step": 295
},
{
"epoch": 0.01,
"learning_rate": 3.372483275737468e-05,
"loss": 0.7235,
"step": 300
},
{
"epoch": 0.01,
"learning_rate": 3.3440157211110454e-05,
"loss": 0.7189,
"step": 305
},
{
"epoch": 0.01,
"learning_rate": 3.315042737138128e-05,
"loss": 0.7358,
"step": 310
},
{
"epoch": 0.01,
"learning_rate": 3.285575219373079e-05,
"loss": 0.7252,
"step": 315
},
{
"epoch": 0.01,
"learning_rate": 3.255624249344198e-05,
"loss": 0.7157,
"step": 320
},
{
"epoch": 0.01,
"learning_rate": 3.2252010903864057e-05,
"loss": 0.7175,
"step": 325
},
{
"epoch": 0.01,
"learning_rate": 3.194317183405573e-05,
"loss": 0.7417,
"step": 330
},
{
"epoch": 0.01,
"learning_rate": 3.1629841425760534e-05,
"loss": 0.736,
"step": 335
},
{
"epoch": 0.01,
"learning_rate": 3.1312137509730776e-05,
"loss": 0.7194,
"step": 340
},
{
"epoch": 0.01,
"learning_rate": 3.0990179561416124e-05,
"loss": 0.7222,
"step": 345
},
{
"epoch": 0.01,
"learning_rate": 3.066408865603383e-05,
"loss": 0.7196,
"step": 350
},
{
"epoch": 0.01,
"learning_rate": 3.0333987423037262e-05,
"loss": 0.714,
"step": 355
},
{
"epoch": 0.01,
"learning_rate": 3.0000000000000004e-05,
"loss": 0.7126,
"step": 360
},
{
"epoch": 0.01,
"eval_loss": 0.7118021249771118,
"eval_runtime": 117.7706,
"eval_samples_per_second": 16.982,
"eval_steps_per_second": 4.246,
"step": 360
},
{
"epoch": 0.01,
"learning_rate": 2.9662251985932773e-05,
"loss": 0.7159,
"step": 365
},
{
"epoch": 0.01,
"learning_rate": 2.9320870394050783e-05,
"loss": 0.7249,
"step": 370
},
{
"epoch": 0.01,
"learning_rate": 2.897598360400925e-05,
"loss": 0.7182,
"step": 375
},
{
"epoch": 0.01,
"learning_rate": 2.8627721313625073e-05,
"loss": 0.7083,
"step": 380
},
{
"epoch": 0.02,
"learning_rate": 2.8276214490102788e-05,
"loss": 0.7238,
"step": 385
},
{
"epoch": 0.02,
"learning_rate": 2.792159532078314e-05,
"loss": 0.7137,
"step": 390
},
{
"epoch": 0.02,
"learning_rate": 2.7563997163432853e-05,
"loss": 0.7182,
"step": 395
},
{
"epoch": 0.02,
"learning_rate": 2.720355449609421e-05,
"loss": 0.7285,
"step": 400
},
{
"epoch": 0.02,
"learning_rate": 2.684040286651338e-05,
"loss": 0.6988,
"step": 405
},
{
"epoch": 0.02,
"learning_rate": 2.6474678841166426e-05,
"loss": 0.7217,
"step": 410
},
{
"epoch": 0.02,
"learning_rate": 2.6106519953902268e-05,
"loss": 0.7185,
"step": 415
},
{
"epoch": 0.02,
"learning_rate": 2.5736064654221808e-05,
"loss": 0.7303,
"step": 420
},
{
"epoch": 0.02,
"learning_rate": 2.536345225521275e-05,
"loss": 0.7134,
"step": 425
},
{
"epoch": 0.02,
"learning_rate": 2.4988822881159627e-05,
"loss": 0.7215,
"step": 430
},
{
"epoch": 0.02,
"learning_rate": 2.4612317414848804e-05,
"loss": 0.7219,
"step": 435
},
{
"epoch": 0.02,
"learning_rate": 2.423407744458822e-05,
"loss": 0.7253,
"step": 440
},
{
"epoch": 0.02,
"learning_rate": 2.3854245210961798e-05,
"loss": 0.7251,
"step": 445
},
{
"epoch": 0.02,
"learning_rate": 2.3472963553338614e-05,
"loss": 0.7259,
"step": 450
},
{
"epoch": 0.02,
"learning_rate": 2.3090375856156813e-05,
"loss": 0.7412,
"step": 455
},
{
"epoch": 0.02,
"learning_rate": 2.2706625995002626e-05,
"loss": 0.7316,
"step": 460
},
{
"epoch": 0.02,
"learning_rate": 2.2321858282504606e-05,
"loss": 0.7166,
"step": 465
},
{
"epoch": 0.02,
"learning_rate": 2.1936217414063584e-05,
"loss": 0.7453,
"step": 470
},
{
"epoch": 0.02,
"learning_rate": 2.154984841343862e-05,
"loss": 0.7135,
"step": 475
},
{
"epoch": 0.02,
"learning_rate": 2.1162896578209517e-05,
"loss": 0.712,
"step": 480
},
{
"epoch": 0.02,
"learning_rate": 2.077550742513634e-05,
"loss": 0.7185,
"step": 485
},
{
"epoch": 0.02,
"learning_rate": 2.038782663543649e-05,
"loss": 0.7366,
"step": 490
},
{
"epoch": 0.02,
"learning_rate": 2e-05,
"loss": 0.7302,
"step": 495
},
{
"epoch": 0.02,
"learning_rate": 1.9612173364563517e-05,
"loss": 0.7393,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 1.9224492574863663e-05,
"loss": 0.7296,
"step": 505
},
{
"epoch": 0.02,
"learning_rate": 1.8837103421790486e-05,
"loss": 0.7109,
"step": 510
},
{
"epoch": 0.02,
"learning_rate": 1.8450151586561386e-05,
"loss": 0.7092,
"step": 515
},
{
"epoch": 0.02,
"learning_rate": 1.806378258593642e-05,
"loss": 0.7381,
"step": 520
},
{
"epoch": 0.02,
"learning_rate": 1.7678141717495394e-05,
"loss": 0.733,
"step": 525
},
{
"epoch": 0.02,
"learning_rate": 1.7293374004997384e-05,
"loss": 0.7068,
"step": 530
},
{
"epoch": 0.02,
"learning_rate": 1.6909624143843193e-05,
"loss": 0.7062,
"step": 535
},
{
"epoch": 0.02,
"learning_rate": 1.6527036446661396e-05,
"loss": 0.7342,
"step": 540
},
{
"epoch": 0.02,
"eval_loss": 0.7100361585617065,
"eval_runtime": 117.785,
"eval_samples_per_second": 16.98,
"eval_steps_per_second": 4.245,
"step": 540
},
{
"epoch": 0.02,
"learning_rate": 1.6145754789038205e-05,
"loss": 0.7193,
"step": 545
},
{
"epoch": 0.02,
"learning_rate": 1.5765922555411793e-05,
"loss": 0.7087,
"step": 550
},
{
"epoch": 0.02,
"learning_rate": 1.53876825851512e-05,
"loss": 0.7228,
"step": 555
},
{
"epoch": 0.02,
"learning_rate": 1.5011177118840376e-05,
"loss": 0.7254,
"step": 560
},
{
"epoch": 0.02,
"learning_rate": 1.4636547744787251e-05,
"loss": 0.732,
"step": 565
},
{
"epoch": 0.02,
"learning_rate": 1.4263935345778202e-05,
"loss": 0.7186,
"step": 570
},
{
"epoch": 0.02,
"learning_rate": 1.389348004609774e-05,
"loss": 0.7091,
"step": 575
},
{
"epoch": 0.02,
"learning_rate": 1.3525321158833582e-05,
"loss": 0.7278,
"step": 580
},
{
"epoch": 0.02,
"learning_rate": 1.3159597133486628e-05,
"loss": 0.7088,
"step": 585
},
{
"epoch": 0.02,
"learning_rate": 1.2796445503905797e-05,
"loss": 0.7188,
"step": 590
},
{
"epoch": 0.02,
"learning_rate": 1.2436002836567154e-05,
"loss": 0.7311,
"step": 595
},
{
"epoch": 0.02,
"learning_rate": 1.2078404679216864e-05,
"loss": 0.727,
"step": 600
},
{
"epoch": 0.02,
"learning_rate": 1.1723785509897219e-05,
"loss": 0.7089,
"step": 605
},
{
"epoch": 0.02,
"learning_rate": 1.1372278686374935e-05,
"loss": 0.7108,
"step": 610
},
{
"epoch": 0.02,
"learning_rate": 1.1024016395990758e-05,
"loss": 0.7189,
"step": 615
},
{
"epoch": 0.02,
"learning_rate": 1.067912960594923e-05,
"loss": 0.717,
"step": 620
},
{
"epoch": 0.02,
"learning_rate": 1.033774801406723e-05,
"loss": 0.713,
"step": 625
},
{
"epoch": 0.02,
"learning_rate": 1.0000000000000006e-05,
"loss": 0.7217,
"step": 630
},
{
"epoch": 0.03,
"learning_rate": 9.666012576962743e-06,
"loss": 0.7099,
"step": 635
},
{
"epoch": 0.03,
"learning_rate": 9.33591134396618e-06,
"loss": 0.6947,
"step": 640
},
{
"epoch": 0.03,
"learning_rate": 9.009820438583881e-06,
"loss": 0.7051,
"step": 645
},
{
"epoch": 0.03,
"learning_rate": 8.687862490269232e-06,
"loss": 0.7244,
"step": 650
},
{
"epoch": 0.03,
"learning_rate": 8.370158574239466e-06,
"loss": 0.7233,
"step": 655
},
{
"epoch": 0.03,
"learning_rate": 8.056828165944282e-06,
"loss": 0.712,
"step": 660
},
{
"epoch": 0.03,
"learning_rate": 7.747989096135943e-06,
"loss": 0.7236,
"step": 665
},
{
"epoch": 0.03,
"learning_rate": 7.443757506558033e-06,
"loss": 0.7134,
"step": 670
},
{
"epoch": 0.03,
"learning_rate": 7.1442478062692135e-06,
"loss": 0.714,
"step": 675
},
{
"epoch": 0.03,
"learning_rate": 6.84957262861873e-06,
"loss": 0.7058,
"step": 680
},
{
"epoch": 0.03,
"learning_rate": 6.559842788889552e-06,
"loss": 0.7265,
"step": 685
},
{
"epoch": 0.03,
"learning_rate": 6.275167242625331e-06,
"loss": 0.7119,
"step": 690
},
{
"epoch": 0.03,
"learning_rate": 5.9956530446566305e-06,
"loss": 0.7263,
"step": 695
},
{
"epoch": 0.03,
"learning_rate": 5.721405308842023e-06,
"loss": 0.7274,
"step": 700
},
{
"epoch": 0.03,
"learning_rate": 5.452527168539026e-06,
"loss": 0.7166,
"step": 705
},
{
"epoch": 0.03,
"learning_rate": 5.189119737819912e-06,
"loss": 0.713,
"step": 710
},
{
"epoch": 0.03,
"learning_rate": 4.9312820734467855e-06,
"loss": 0.7253,
"step": 715
},
{
"epoch": 0.03,
"learning_rate": 4.679111137620442e-06,
"loss": 0.7216,
"step": 720
},
{
"epoch": 0.03,
"eval_loss": 0.708259105682373,
"eval_runtime": 117.7068,
"eval_samples_per_second": 16.991,
"eval_steps_per_second": 4.248,
"step": 720
},
{
"epoch": 0.03,
"learning_rate": 4.4327017615168e-06,
"loss": 0.7165,
"step": 725
},
{
"epoch": 0.03,
"learning_rate": 4.1921466096248164e-06,
"loss": 0.7303,
"step": 730
},
{
"epoch": 0.03,
"learning_rate": 3.957536144899123e-06,
"loss": 0.7198,
"step": 735
},
{
"epoch": 0.03,
"learning_rate": 3.7289585947406504e-06,
"loss": 0.7186,
"step": 740
},
{
"epoch": 0.03,
"learning_rate": 3.5064999178178648e-06,
"loss": 0.7438,
"step": 745
},
{
"epoch": 0.03,
"learning_rate": 3.290243771741275e-06,
"loss": 0.7191,
"step": 750
},
{
"epoch": 0.03,
"learning_rate": 3.0802714816031787e-06,
"loss": 0.7132,
"step": 755
},
{
"epoch": 0.03,
"learning_rate": 2.876662009394673e-06,
"loss": 0.7278,
"step": 760
},
{
"epoch": 0.03,
"learning_rate": 2.679491924311226e-06,
"loss": 0.7085,
"step": 765
},
{
"epoch": 0.03,
"learning_rate": 2.488835373958185e-06,
"loss": 0.7115,
"step": 770
},
{
"epoch": 0.03,
"learning_rate": 2.304764056466844e-06,
"loss": 0.7118,
"step": 775
},
{
"epoch": 0.03,
"learning_rate": 2.127347193531757e-06,
"loss": 0.7121,
"step": 780
},
{
"epoch": 0.03,
"learning_rate": 1.9566515043792455e-06,
"loss": 0.7174,
"step": 785
},
{
"epoch": 0.03,
"learning_rate": 1.792741180677069e-06,
"loss": 0.6913,
"step": 790
},
{
"epoch": 0.03,
"learning_rate": 1.6356778623945223e-06,
"loss": 0.7038,
"step": 795
},
{
"epoch": 0.03,
"learning_rate": 1.4855206146221934e-06,
"loss": 0.7156,
"step": 800
},
{
"epoch": 0.03,
"learning_rate": 1.3423259053599891e-06,
"loss": 0.7113,
"step": 805
},
{
"epoch": 0.03,
"learning_rate": 1.2061475842818337e-06,
"loss": 0.727,
"step": 810
},
{
"epoch": 0.03,
"learning_rate": 1.0770368624849947e-06,
"loss": 0.7186,
"step": 815
},
{
"epoch": 0.03,
"learning_rate": 9.550422932316938e-07,
"loss": 0.7088,
"step": 820
},
{
"epoch": 0.03,
"learning_rate": 8.402097536902221e-07,
"loss": 0.7125,
"step": 825
},
{
"epoch": 0.03,
"learning_rate": 7.325824276823934e-07,
"loss": 0.7076,
"step": 830
},
{
"epoch": 0.03,
"learning_rate": 6.322007894438842e-07,
"loss": 0.7099,
"step": 835
},
{
"epoch": 0.03,
"learning_rate": 5.391025884035239e-07,
"loss": 0.7238,
"step": 840
},
{
"epoch": 0.03,
"learning_rate": 4.533228349872887e-07,
"loss": 0.7241,
"step": 845
},
{
"epoch": 0.03,
"learning_rate": 3.748937874523062e-07,
"loss": 0.7248,
"step": 850
},
{
"epoch": 0.03,
"learning_rate": 3.038449397558396e-07,
"loss": 0.7083,
"step": 855
},
{
"epoch": 0.03,
"learning_rate": 2.402030104638198e-07,
"loss": 0.7167,
"step": 860
},
{
"epoch": 0.03,
"learning_rate": 1.839919327030937e-07,
"loss": 0.7277,
"step": 865
},
{
"epoch": 0.03,
"learning_rate": 1.3523284516113955e-07,
"loss": 0.7075,
"step": 870
},
{
"epoch": 0.03,
"learning_rate": 9.394408413668343e-08,
"loss": 0.7134,
"step": 875
},
{
"epoch": 0.03,
"learning_rate": 6.014117664415953e-08,
"loss": 0.7147,
"step": 880
},
{
"epoch": 0.03,
"learning_rate": 3.383683457463649e-08,
"loss": 0.7287,
"step": 885
},
{
"epoch": 0.04,
"learning_rate": 1.5040949915399173e-08,
"loss": 0.7152,
"step": 890
},
{
"epoch": 0.04,
"learning_rate": 3.760591029973171e-09,
"loss": 0.7195,
"step": 895
},
{
"epoch": 0.04,
"learning_rate": 0.0,
"loss": 0.7171,
"step": 900
},
{
"epoch": 0.04,
"eval_loss": 0.7084137797355652,
"eval_runtime": 117.7342,
"eval_samples_per_second": 16.987,
"eval_steps_per_second": 4.247,
"step": 900
},
{
"epoch": 0.04,
"step": 900,
"total_flos": 1.1929120479106826e+18,
"train_loss": 0.7602509791321225,
"train_runtime": 22175.0023,
"train_samples_per_second": 0.649,
"train_steps_per_second": 0.041
}
],
"logging_steps": 5,
"max_steps": 900,
"num_train_epochs": 1,
"save_steps": 180,
"total_flos": 1.1929120479106826e+18,
"trial_name": null,
"trial_params": null
}