679 lines
14 KiB
JSON
679 lines
14 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.07312,
|
|
"eval_steps": 500,
|
|
"global_step": 914,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 8e-05,
|
|
"grad_norm": 7.481872081756592,
|
|
"learning_rate": 0.0,
|
|
"loss": 10.994789123535156,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.0008,
|
|
"grad_norm": 6.929096698760986,
|
|
"learning_rate": 0.0,
|
|
"loss": 10.839588589138454,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.0016,
|
|
"grad_norm": 2.6677963733673096,
|
|
"learning_rate": 0.0,
|
|
"loss": 9.918109893798828,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.0024,
|
|
"grad_norm": 2.397674322128296,
|
|
"learning_rate": 0.0,
|
|
"loss": 9.269318389892579,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 0.0032,
|
|
"grad_norm": 1.8475602865219116,
|
|
"learning_rate": 0.0,
|
|
"loss": 8.905154418945312,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.004,
|
|
"grad_norm": 1.469852328300476,
|
|
"learning_rate": 0.0,
|
|
"loss": 8.406952667236329,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 0.0048,
|
|
"grad_norm": 1.1983022689819336,
|
|
"learning_rate": 0.0,
|
|
"loss": 7.9277900695800785,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.0056,
|
|
"grad_norm": 1.6187549829483032,
|
|
"learning_rate": 0.0,
|
|
"loss": 7.585640716552734,
|
|
"step": 70
|
|
},
|
|
{
|
|
"epoch": 0.0064,
|
|
"grad_norm": 0.983756959438324,
|
|
"learning_rate": 0.0,
|
|
"loss": 7.446015930175781,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.0072,
|
|
"grad_norm": 1.2614742517471313,
|
|
"learning_rate": 0.0,
|
|
"loss": 7.360189056396484,
|
|
"step": 90
|
|
},
|
|
{
|
|
"epoch": 0.008,
|
|
"grad_norm": 1.6991254091262817,
|
|
"learning_rate": 0.0,
|
|
"loss": 7.271273040771485,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.0088,
|
|
"grad_norm": 1.2997796535491943,
|
|
"learning_rate": 0.0,
|
|
"loss": 7.150358581542969,
|
|
"step": 110
|
|
},
|
|
{
|
|
"epoch": 0.0096,
|
|
"grad_norm": 1.1440973281860352,
|
|
"learning_rate": 0.0,
|
|
"loss": 7.097750091552735,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.0104,
|
|
"grad_norm": 1.7426985502243042,
|
|
"learning_rate": 0.0,
|
|
"loss": 7.137723541259765,
|
|
"step": 130
|
|
},
|
|
{
|
|
"epoch": 0.0112,
|
|
"grad_norm": 1.5796011686325073,
|
|
"learning_rate": 0.0,
|
|
"loss": 6.837922668457031,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 0.012,
|
|
"grad_norm": 1.0700732469558716,
|
|
"learning_rate": 0.0,
|
|
"loss": 6.7390892028808596,
|
|
"step": 150
|
|
},
|
|
{
|
|
"epoch": 0.0128,
|
|
"grad_norm": 1.3321928977966309,
|
|
"learning_rate": 0.0,
|
|
"loss": 6.5840301513671875,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 0.0136,
|
|
"grad_norm": 1.0948106050491333,
|
|
"learning_rate": 0.0,
|
|
"loss": 6.431011962890625,
|
|
"step": 170
|
|
},
|
|
{
|
|
"epoch": 0.0144,
|
|
"grad_norm": 1.3568321466445923,
|
|
"learning_rate": 0.0,
|
|
"loss": 6.383031845092773,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 0.0152,
|
|
"grad_norm": 1.16302490234375,
|
|
"learning_rate": 0.0,
|
|
"loss": 6.226947021484375,
|
|
"step": 190
|
|
},
|
|
{
|
|
"epoch": 0.016,
|
|
"grad_norm": 1.226240873336792,
|
|
"learning_rate": 0.0,
|
|
"loss": 6.014730834960938,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.0168,
|
|
"grad_norm": 1.616997241973877,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.9844104766845705,
|
|
"step": 210
|
|
},
|
|
{
|
|
"epoch": 0.0176,
|
|
"grad_norm": 1.4099252223968506,
|
|
"learning_rate": 0.0,
|
|
"loss": 6.112431335449219,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 0.0184,
|
|
"grad_norm": 1.4300403594970703,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.857472610473633,
|
|
"step": 230
|
|
},
|
|
{
|
|
"epoch": 0.0192,
|
|
"grad_norm": 1.0074694156646729,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.77098503112793,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 0.02,
|
|
"grad_norm": 1.257699966430664,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.567762756347657,
|
|
"step": 250
|
|
},
|
|
{
|
|
"epoch": 0.0208,
|
|
"grad_norm": 1.1900246143341064,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.512705993652344,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 0.0216,
|
|
"grad_norm": 1.05792236328125,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.472368621826172,
|
|
"step": 270
|
|
},
|
|
{
|
|
"epoch": 0.0224,
|
|
"grad_norm": 1.0392916202545166,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.335597991943359,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 0.0232,
|
|
"grad_norm": 1.0150176286697388,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.463570785522461,
|
|
"step": 290
|
|
},
|
|
{
|
|
"epoch": 0.024,
|
|
"grad_norm": 1.0932813882827759,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.4247283935546875,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.0248,
|
|
"grad_norm": 1.149474024772644,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.2318778991699215,
|
|
"step": 310
|
|
},
|
|
{
|
|
"epoch": 0.0256,
|
|
"grad_norm": 1.0105016231536865,
|
|
"learning_rate": 0.0,
|
|
"loss": 5.318963623046875,
|
|
"step": 320
|
|
},
|
|
{
|
|
"epoch": 0.0264,
|
|
"grad_norm": 1.2110768556594849,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.900788116455078,
|
|
"step": 330
|
|
},
|
|
{
|
|
"epoch": 0.0272,
|
|
"grad_norm": 0.868516206741333,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.820335769653321,
|
|
"step": 340
|
|
},
|
|
{
|
|
"epoch": 0.028,
|
|
"grad_norm": 0.829369843006134,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.799337768554688,
|
|
"step": 350
|
|
},
|
|
{
|
|
"epoch": 0.0288,
|
|
"grad_norm": 2.0908939838409424,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.735381317138672,
|
|
"step": 360
|
|
},
|
|
{
|
|
"epoch": 0.0296,
|
|
"grad_norm": 1.4280335903167725,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.382848739624023,
|
|
"step": 370
|
|
},
|
|
{
|
|
"epoch": 0.0304,
|
|
"grad_norm": 0.8578271269798279,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.491080093383789,
|
|
"step": 380
|
|
},
|
|
{
|
|
"epoch": 0.0312,
|
|
"grad_norm": 1.4359986782073975,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.886473083496094,
|
|
"step": 390
|
|
},
|
|
{
|
|
"epoch": 0.032,
|
|
"grad_norm": 0.8874498009681702,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.8443553924560545,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.0328,
|
|
"grad_norm": 1.2885181903839111,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.658852767944336,
|
|
"step": 410
|
|
},
|
|
{
|
|
"epoch": 0.0336,
|
|
"grad_norm": 0.9997056126594543,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.777051544189453,
|
|
"step": 420
|
|
},
|
|
{
|
|
"epoch": 0.0344,
|
|
"grad_norm": 0.9759546518325806,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.488846206665039,
|
|
"step": 430
|
|
},
|
|
{
|
|
"epoch": 0.0352,
|
|
"grad_norm": 0.7758691310882568,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.184576416015625,
|
|
"step": 440
|
|
},
|
|
{
|
|
"epoch": 0.036,
|
|
"grad_norm": 1.0744699239730835,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.537790298461914,
|
|
"step": 450
|
|
},
|
|
{
|
|
"epoch": 0.0368,
|
|
"grad_norm": 0.923533022403717,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.523368835449219,
|
|
"step": 460
|
|
},
|
|
{
|
|
"epoch": 0.0376,
|
|
"grad_norm": 0.6118951439857483,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.9889678955078125,
|
|
"step": 470
|
|
},
|
|
{
|
|
"epoch": 0.0384,
|
|
"grad_norm": 0.892911434173584,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.316759872436523,
|
|
"step": 480
|
|
},
|
|
{
|
|
"epoch": 0.0392,
|
|
"grad_norm": 0.9929479360580444,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.161303329467773,
|
|
"step": 490
|
|
},
|
|
{
|
|
"epoch": 0.04,
|
|
"grad_norm": 0.8405442237854004,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.262095642089844,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.0408,
|
|
"grad_norm": 0.7923921346664429,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.012786483764648,
|
|
"step": 510
|
|
},
|
|
{
|
|
"epoch": 0.0416,
|
|
"grad_norm": 0.724445104598999,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.276238250732422,
|
|
"step": 520
|
|
},
|
|
{
|
|
"epoch": 0.0424,
|
|
"grad_norm": 0.6988783478736877,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.759166717529297,
|
|
"step": 530
|
|
},
|
|
{
|
|
"epoch": 0.0432,
|
|
"grad_norm": 0.7946400046348572,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.3265869140625,
|
|
"step": 540
|
|
},
|
|
{
|
|
"epoch": 0.044,
|
|
"grad_norm": 0.8674063086509705,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.605390548706055,
|
|
"step": 550
|
|
},
|
|
{
|
|
"epoch": 0.0448,
|
|
"grad_norm": 0.9302084445953369,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.235034942626953,
|
|
"step": 560
|
|
},
|
|
{
|
|
"epoch": 0.0456,
|
|
"grad_norm": 1.1511927843093872,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.065582656860352,
|
|
"step": 570
|
|
},
|
|
{
|
|
"epoch": 0.0464,
|
|
"grad_norm": 0.8550519347190857,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.10020637512207,
|
|
"step": 580
|
|
},
|
|
{
|
|
"epoch": 0.0472,
|
|
"grad_norm": 0.7273553013801575,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.9567726135253904,
|
|
"step": 590
|
|
},
|
|
{
|
|
"epoch": 0.048,
|
|
"grad_norm": 0.7848784327507019,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.9126663208007812,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 0.0488,
|
|
"grad_norm": 0.8796048760414124,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.819412612915039,
|
|
"step": 610
|
|
},
|
|
{
|
|
"epoch": 0.0496,
|
|
"grad_norm": 0.7737526297569275,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.302072906494141,
|
|
"step": 620
|
|
},
|
|
{
|
|
"epoch": 0.0504,
|
|
"grad_norm": 1.1110758781433105,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.017117309570312,
|
|
"step": 630
|
|
},
|
|
{
|
|
"epoch": 0.0512,
|
|
"grad_norm": 0.8170852661132812,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.7205204010009765,
|
|
"step": 640
|
|
},
|
|
{
|
|
"epoch": 0.052,
|
|
"grad_norm": 1.0170948505401611,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.85927734375,
|
|
"step": 650
|
|
},
|
|
{
|
|
"epoch": 0.0528,
|
|
"grad_norm": 0.7588558793067932,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.8514785766601562,
|
|
"step": 660
|
|
},
|
|
{
|
|
"epoch": 0.0536,
|
|
"grad_norm": 0.9129968881607056,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.984285354614258,
|
|
"step": 670
|
|
},
|
|
{
|
|
"epoch": 0.0544,
|
|
"grad_norm": 0.8319804072380066,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.324806976318359,
|
|
"step": 680
|
|
},
|
|
{
|
|
"epoch": 0.0552,
|
|
"grad_norm": 0.8046982288360596,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.807140350341797,
|
|
"step": 690
|
|
},
|
|
{
|
|
"epoch": 0.056,
|
|
"grad_norm": 0.8416018486022949,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.331145858764648,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 0.0568,
|
|
"grad_norm": 0.7169877290725708,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.792818069458008,
|
|
"step": 710
|
|
},
|
|
{
|
|
"epoch": 0.0576,
|
|
"grad_norm": 0.8876171708106995,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.9738525390625,
|
|
"step": 720
|
|
},
|
|
{
|
|
"epoch": 0.0584,
|
|
"grad_norm": 0.8260897397994995,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.021589279174805,
|
|
"step": 730
|
|
},
|
|
{
|
|
"epoch": 0.0592,
|
|
"grad_norm": 0.8444461226463318,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.108542251586914,
|
|
"step": 740
|
|
},
|
|
{
|
|
"epoch": 0.06,
|
|
"grad_norm": 0.798984706401825,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.817498779296875,
|
|
"step": 750
|
|
},
|
|
{
|
|
"epoch": 0.0608,
|
|
"grad_norm": 0.7406821846961975,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.017255401611328,
|
|
"step": 760
|
|
},
|
|
{
|
|
"epoch": 0.0616,
|
|
"grad_norm": 0.765076756477356,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.6126125335693358,
|
|
"step": 770
|
|
},
|
|
{
|
|
"epoch": 0.0624,
|
|
"grad_norm": 0.789610743522644,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.592012405395508,
|
|
"step": 780
|
|
},
|
|
{
|
|
"epoch": 0.0632,
|
|
"grad_norm": 0.9570745825767517,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.878557586669922,
|
|
"step": 790
|
|
},
|
|
{
|
|
"epoch": 0.064,
|
|
"grad_norm": 0.6547969579696655,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.6419254302978517,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 0.0648,
|
|
"grad_norm": 1.231814980506897,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.977242279052734,
|
|
"step": 810
|
|
},
|
|
{
|
|
"epoch": 0.0656,
|
|
"grad_norm": 0.7694600224494934,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.7174278259277345,
|
|
"step": 820
|
|
},
|
|
{
|
|
"epoch": 0.0664,
|
|
"grad_norm": 0.7207898497581482,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.79962272644043,
|
|
"step": 830
|
|
},
|
|
{
|
|
"epoch": 0.0672,
|
|
"grad_norm": 0.7741470336914062,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.642398452758789,
|
|
"step": 840
|
|
},
|
|
{
|
|
"epoch": 0.068,
|
|
"grad_norm": 0.6558142900466919,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.854899215698242,
|
|
"step": 850
|
|
},
|
|
{
|
|
"epoch": 0.0688,
|
|
"grad_norm": 0.6257121562957764,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.70367317199707,
|
|
"step": 860
|
|
},
|
|
{
|
|
"epoch": 0.0696,
|
|
"grad_norm": 0.6313413977622986,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.448344039916992,
|
|
"step": 870
|
|
},
|
|
{
|
|
"epoch": 0.0704,
|
|
"grad_norm": 0.9329156875610352,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.9527435302734375,
|
|
"step": 880
|
|
},
|
|
{
|
|
"epoch": 0.0712,
|
|
"grad_norm": 0.6971497535705566,
|
|
"learning_rate": 0.0,
|
|
"loss": 4.154458999633789,
|
|
"step": 890
|
|
},
|
|
{
|
|
"epoch": 0.072,
|
|
"grad_norm": 0.7026866674423218,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.5829681396484374,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 0.0728,
|
|
"grad_norm": 0.7691475749015808,
|
|
"learning_rate": 0.0,
|
|
"loss": 3.7083820343017577,
|
|
"step": 910
|
|
}
|
|
],
|
|
"logging_steps": 10,
|
|
"max_steps": 914,
|
|
"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": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.1077690815676416e+16,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|