gsmyrnis's picture
End of training
ea50523 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1470,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02040816326530612,
"grad_norm": 7.778071589344308,
"learning_rate": 6.756756756756758e-07,
"loss": 0.8354,
"step": 10
},
{
"epoch": 0.04081632653061224,
"grad_norm": 3.0197649197148544,
"learning_rate": 1.3513513513513515e-06,
"loss": 0.736,
"step": 20
},
{
"epoch": 0.061224489795918366,
"grad_norm": 1.6185593920539272,
"learning_rate": 2.0270270270270273e-06,
"loss": 0.6712,
"step": 30
},
{
"epoch": 0.08163265306122448,
"grad_norm": 1.5428582304546115,
"learning_rate": 2.702702702702703e-06,
"loss": 0.6315,
"step": 40
},
{
"epoch": 0.10204081632653061,
"grad_norm": 1.7211785189281783,
"learning_rate": 3.3783783783783788e-06,
"loss": 0.6102,
"step": 50
},
{
"epoch": 0.12244897959183673,
"grad_norm": 2.559107572127415,
"learning_rate": 4.0540540540540545e-06,
"loss": 0.6067,
"step": 60
},
{
"epoch": 0.14285714285714285,
"grad_norm": 2.314900289599986,
"learning_rate": 4.72972972972973e-06,
"loss": 0.5976,
"step": 70
},
{
"epoch": 0.16326530612244897,
"grad_norm": 1.585557769101424,
"learning_rate": 4.999794894487084e-06,
"loss": 0.6048,
"step": 80
},
{
"epoch": 0.1836734693877551,
"grad_norm": 1.746887510895138,
"learning_rate": 4.998541607324267e-06,
"loss": 0.5888,
"step": 90
},
{
"epoch": 0.20408163265306123,
"grad_norm": 3.353300338752779,
"learning_rate": 4.996149614425655e-06,
"loss": 0.5946,
"step": 100
},
{
"epoch": 0.22448979591836735,
"grad_norm": 2.8435118056608255,
"learning_rate": 4.992620127143546e-06,
"loss": 0.5859,
"step": 110
},
{
"epoch": 0.24489795918367346,
"grad_norm": 2.100533655111189,
"learning_rate": 4.987954932879781e-06,
"loss": 0.5875,
"step": 120
},
{
"epoch": 0.2653061224489796,
"grad_norm": 2.3315284939616605,
"learning_rate": 4.982156394180578e-06,
"loss": 0.5787,
"step": 130
},
{
"epoch": 0.2857142857142857,
"grad_norm": 2.239136455760216,
"learning_rate": 4.975227447540084e-06,
"loss": 0.5844,
"step": 140
},
{
"epoch": 0.30612244897959184,
"grad_norm": 2.129725342439742,
"learning_rate": 4.967171601913286e-06,
"loss": 0.5777,
"step": 150
},
{
"epoch": 0.32653061224489793,
"grad_norm": 2.5819786560128186,
"learning_rate": 4.957992936939001e-06,
"loss": 0.585,
"step": 160
},
{
"epoch": 0.3469387755102041,
"grad_norm": 1.7001590677192884,
"learning_rate": 4.947696100873868e-06,
"loss": 0.5773,
"step": 170
},
{
"epoch": 0.3673469387755102,
"grad_norm": 1.7263599397345204,
"learning_rate": 4.936286308238376e-06,
"loss": 0.5824,
"step": 180
},
{
"epoch": 0.3877551020408163,
"grad_norm": 1.8366911838390632,
"learning_rate": 4.923769337176137e-06,
"loss": 0.5791,
"step": 190
},
{
"epoch": 0.40816326530612246,
"grad_norm": 1.3905029741864174,
"learning_rate": 4.910151526527711e-06,
"loss": 0.5767,
"step": 200
},
{
"epoch": 0.42857142857142855,
"grad_norm": 1.148322568291514,
"learning_rate": 4.895439772620496e-06,
"loss": 0.5728,
"step": 210
},
{
"epoch": 0.4489795918367347,
"grad_norm": 1.6127960821049323,
"learning_rate": 4.879641525776294e-06,
"loss": 0.5784,
"step": 220
},
{
"epoch": 0.46938775510204084,
"grad_norm": 1.291452047677863,
"learning_rate": 4.8627647865383185e-06,
"loss": 0.5755,
"step": 230
},
{
"epoch": 0.4897959183673469,
"grad_norm": 1.2840139593689956,
"learning_rate": 4.844818101619563e-06,
"loss": 0.574,
"step": 240
},
{
"epoch": 0.5102040816326531,
"grad_norm": 1.8038609241857482,
"learning_rate": 4.825810559574577e-06,
"loss": 0.5709,
"step": 250
},
{
"epoch": 0.5306122448979592,
"grad_norm": 1.4347005717657924,
"learning_rate": 4.805751786196844e-06,
"loss": 0.5657,
"step": 260
},
{
"epoch": 0.5510204081632653,
"grad_norm": 1.193365239502765,
"learning_rate": 4.784651939644088e-06,
"loss": 0.5702,
"step": 270
},
{
"epoch": 0.5714285714285714,
"grad_norm": 1.7823342346005195,
"learning_rate": 4.762521705293985e-06,
"loss": 0.566,
"step": 280
},
{
"epoch": 0.5918367346938775,
"grad_norm": 1.2403759513997483,
"learning_rate": 4.739372290332876e-06,
"loss": 0.5668,
"step": 290
},
{
"epoch": 0.6122448979591837,
"grad_norm": 1.863444933423126,
"learning_rate": 4.715215418080228e-06,
"loss": 0.5671,
"step": 300
},
{
"epoch": 0.6326530612244898,
"grad_norm": 1.4221353274898374,
"learning_rate": 4.690063322051714e-06,
"loss": 0.5718,
"step": 310
},
{
"epoch": 0.6530612244897959,
"grad_norm": 1.6811648872628475,
"learning_rate": 4.6639287397639175e-06,
"loss": 0.5632,
"step": 320
},
{
"epoch": 0.673469387755102,
"grad_norm": 1.4152595096160547,
"learning_rate": 4.636824906283807e-06,
"loss": 0.562,
"step": 330
},
{
"epoch": 0.6938775510204082,
"grad_norm": 1.4843724359941501,
"learning_rate": 4.608765547526235e-06,
"loss": 0.5599,
"step": 340
},
{
"epoch": 0.7142857142857143,
"grad_norm": 1.4557344773873018,
"learning_rate": 4.5797648733028665e-06,
"loss": 0.5614,
"step": 350
},
{
"epoch": 0.7346938775510204,
"grad_norm": 1.2086032121032202,
"learning_rate": 4.54983757012605e-06,
"loss": 0.5634,
"step": 360
},
{
"epoch": 0.7551020408163265,
"grad_norm": 1.2423711642376856,
"learning_rate": 4.518998793771276e-06,
"loss": 0.5615,
"step": 370
},
{
"epoch": 0.7755102040816326,
"grad_norm": 1.2875724524685657,
"learning_rate": 4.487264161601997e-06,
"loss": 0.5514,
"step": 380
},
{
"epoch": 0.7959183673469388,
"grad_norm": 1.1225946056234728,
"learning_rate": 4.454649744660687e-06,
"loss": 0.5647,
"step": 390
},
{
"epoch": 0.8163265306122449,
"grad_norm": 1.2503911438284534,
"learning_rate": 4.4211720595301474e-06,
"loss": 0.5551,
"step": 400
},
{
"epoch": 0.8367346938775511,
"grad_norm": 1.2909414765131615,
"learning_rate": 4.386848059969186e-06,
"loss": 0.5492,
"step": 410
},
{
"epoch": 0.8571428571428571,
"grad_norm": 1.3184301150941293,
"learning_rate": 4.351695128326899e-06,
"loss": 0.5449,
"step": 420
},
{
"epoch": 0.8775510204081632,
"grad_norm": 1.2586947786363358,
"learning_rate": 4.315731066739907e-06,
"loss": 0.5555,
"step": 430
},
{
"epoch": 0.8979591836734694,
"grad_norm": 1.4262738599752862,
"learning_rate": 4.278974088117002e-06,
"loss": 0.5543,
"step": 440
},
{
"epoch": 0.9183673469387755,
"grad_norm": 1.4446508113688332,
"learning_rate": 4.241442806915776e-06,
"loss": 0.5493,
"step": 450
},
{
"epoch": 0.9387755102040817,
"grad_norm": 1.298816139110553,
"learning_rate": 4.203156229715885e-06,
"loss": 0.5562,
"step": 460
},
{
"epoch": 0.9591836734693877,
"grad_norm": 1.2637066502227081,
"learning_rate": 4.164133745593752e-06,
"loss": 0.5502,
"step": 470
},
{
"epoch": 0.9795918367346939,
"grad_norm": 1.0561664250294849,
"learning_rate": 4.1243951163035515e-06,
"loss": 0.5524,
"step": 480
},
{
"epoch": 1.0,
"grad_norm": 1.068711582818471,
"learning_rate": 4.083960466269468e-06,
"loss": 0.5482,
"step": 490
},
{
"epoch": 1.0,
"eval_loss": 0.5568229556083679,
"eval_runtime": 44.6985,
"eval_samples_per_second": 295.267,
"eval_steps_per_second": 1.163,
"step": 490
},
{
"epoch": 1.0204081632653061,
"grad_norm": 1.6967871170326598,
"learning_rate": 4.042850272394296e-06,
"loss": 0.4815,
"step": 500
},
{
"epoch": 1.0408163265306123,
"grad_norm": 1.329681106394839,
"learning_rate": 4.001085353689527e-06,
"loss": 0.4746,
"step": 510
},
{
"epoch": 1.0612244897959184,
"grad_norm": 1.1249203575095268,
"learning_rate": 3.958686860732198e-06,
"loss": 0.4712,
"step": 520
},
{
"epoch": 1.0816326530612246,
"grad_norm": 1.7553226916997662,
"learning_rate": 3.915676264953819e-06,
"loss": 0.473,
"step": 530
},
{
"epoch": 1.1020408163265305,
"grad_norm": 1.814402186020549,
"learning_rate": 3.8720753477668174e-06,
"loss": 0.4728,
"step": 540
},
{
"epoch": 1.1224489795918366,
"grad_norm": 1.780073335115998,
"learning_rate": 3.8279061895340065e-06,
"loss": 0.4715,
"step": 550
},
{
"epoch": 1.1428571428571428,
"grad_norm": 1.8264269071746542,
"learning_rate": 3.783191158386649e-06,
"loss": 0.4703,
"step": 560
},
{
"epoch": 1.163265306122449,
"grad_norm": 1.4978817218835796,
"learning_rate": 3.7379528988968004e-06,
"loss": 0.4738,
"step": 570
},
{
"epoch": 1.183673469387755,
"grad_norm": 1.4615376013915895,
"learning_rate": 3.6922143206096463e-06,
"loss": 0.4719,
"step": 580
},
{
"epoch": 1.2040816326530612,
"grad_norm": 1.8203771196800125,
"learning_rate": 3.645998586441664e-06,
"loss": 0.4722,
"step": 590
},
{
"epoch": 1.2244897959183674,
"grad_norm": 1.7300255308447494,
"learning_rate": 3.5993291009504583e-06,
"loss": 0.4743,
"step": 600
},
{
"epoch": 1.2448979591836735,
"grad_norm": 1.5452609367603438,
"learning_rate": 3.5522294984822414e-06,
"loss": 0.4742,
"step": 610
},
{
"epoch": 1.2653061224489797,
"grad_norm": 1.4110906025605625,
"learning_rate": 3.504723631202927e-06,
"loss": 0.478,
"step": 620
},
{
"epoch": 1.2857142857142856,
"grad_norm": 1.2668133255763068,
"learning_rate": 3.4568355570189293e-06,
"loss": 0.4758,
"step": 630
},
{
"epoch": 1.306122448979592,
"grad_norm": 1.1536880529657885,
"learning_rate": 3.4085895273937616e-06,
"loss": 0.4725,
"step": 640
},
{
"epoch": 1.3265306122448979,
"grad_norm": 1.2378783567029548,
"learning_rate": 3.3600099750666186e-06,
"loss": 0.4682,
"step": 650
},
{
"epoch": 1.346938775510204,
"grad_norm": 1.3094029659983764,
"learning_rate": 3.3111215016791615e-06,
"loss": 0.48,
"step": 660
},
{
"epoch": 1.3673469387755102,
"grad_norm": 1.413780733952238,
"learning_rate": 3.2619488653167524e-06,
"loss": 0.4776,
"step": 670
},
{
"epoch": 1.3877551020408163,
"grad_norm": 1.1451278058611685,
"learning_rate": 3.2125169679704816e-06,
"loss": 0.4777,
"step": 680
},
{
"epoch": 1.4081632653061225,
"grad_norm": 1.168070145148228,
"learning_rate": 3.1628508429263055e-06,
"loss": 0.4756,
"step": 690
},
{
"epoch": 1.4285714285714286,
"grad_norm": 1.1109475835139078,
"learning_rate": 3.112975642087696e-06,
"loss": 0.4727,
"step": 700
},
{
"epoch": 1.4489795918367347,
"grad_norm": 1.2678867479201292,
"learning_rate": 3.0629166232382244e-06,
"loss": 0.4776,
"step": 710
},
{
"epoch": 1.469387755102041,
"grad_norm": 1.1561029802658416,
"learning_rate": 3.012699137250523e-06,
"loss": 0.4738,
"step": 720
},
{
"epoch": 1.489795918367347,
"grad_norm": 1.1313128254815696,
"learning_rate": 2.962348615248099e-06,
"loss": 0.4797,
"step": 730
},
{
"epoch": 1.510204081632653,
"grad_norm": 1.2587718327059303,
"learning_rate": 2.9118905557265194e-06,
"loss": 0.4735,
"step": 740
},
{
"epoch": 1.5306122448979593,
"grad_norm": 1.1013738197897254,
"learning_rate": 2.861350511640466e-06,
"loss": 0.475,
"step": 750
},
{
"epoch": 1.5510204081632653,
"grad_norm": 1.1227769485684345,
"learning_rate": 2.81075407746322e-06,
"loss": 0.4749,
"step": 760
},
{
"epoch": 1.5714285714285714,
"grad_norm": 1.0818370734100442,
"learning_rate": 2.760126876225113e-06,
"loss": 0.4753,
"step": 770
},
{
"epoch": 1.5918367346938775,
"grad_norm": 1.0587953555625602,
"learning_rate": 2.7094945465375237e-06,
"loss": 0.47,
"step": 780
},
{
"epoch": 1.6122448979591837,
"grad_norm": 1.1618625324803182,
"learning_rate": 2.6588827296089765e-06,
"loss": 0.4746,
"step": 790
},
{
"epoch": 1.6326530612244898,
"grad_norm": 1.2352446476841303,
"learning_rate": 2.608317056259933e-06,
"loss": 0.4733,
"step": 800
},
{
"epoch": 1.6530612244897958,
"grad_norm": 1.0937135850117063,
"learning_rate": 2.557823133942836e-06,
"loss": 0.4793,
"step": 810
},
{
"epoch": 1.6734693877551021,
"grad_norm": 1.126671194089832,
"learning_rate": 2.507426533773994e-06,
"loss": 0.4709,
"step": 820
},
{
"epoch": 1.693877551020408,
"grad_norm": 1.1253283659142022,
"learning_rate": 2.4571527775838637e-06,
"loss": 0.4741,
"step": 830
},
{
"epoch": 1.7142857142857144,
"grad_norm": 1.1309032305899065,
"learning_rate": 2.407027324992293e-06,
"loss": 0.4735,
"step": 840
},
{
"epoch": 1.7346938775510203,
"grad_norm": 1.1311416180631535,
"learning_rate": 2.357075560515267e-06,
"loss": 0.4742,
"step": 850
},
{
"epoch": 1.7551020408163265,
"grad_norm": 1.0615765131524626,
"learning_rate": 2.3073227807096903e-06,
"loss": 0.4764,
"step": 860
},
{
"epoch": 1.7755102040816326,
"grad_norm": 1.1511014505350845,
"learning_rate": 2.2577941813627137e-06,
"loss": 0.4675,
"step": 870
},
{
"epoch": 1.7959183673469388,
"grad_norm": 1.1577030186189212,
"learning_rate": 2.2085148447320886e-06,
"loss": 0.4762,
"step": 880
},
{
"epoch": 1.816326530612245,
"grad_norm": 1.0977519312106587,
"learning_rate": 2.1595097268440215e-06,
"loss": 0.4728,
"step": 890
},
{
"epoch": 1.836734693877551,
"grad_norm": 1.1107484368711582,
"learning_rate": 2.110803644854949e-06,
"loss": 0.472,
"step": 900
},
{
"epoch": 1.8571428571428572,
"grad_norm": 1.1592418760463674,
"learning_rate": 2.062421264483641e-06,
"loss": 0.4715,
"step": 910
},
{
"epoch": 1.8775510204081631,
"grad_norm": 1.0540592699686717,
"learning_rate": 2.0143870875199952e-06,
"loss": 0.4732,
"step": 920
},
{
"epoch": 1.8979591836734695,
"grad_norm": 1.1457616506688253,
"learning_rate": 1.9667254394168497e-06,
"loss": 0.4726,
"step": 930
},
{
"epoch": 1.9183673469387754,
"grad_norm": 1.0508307850745724,
"learning_rate": 1.9194604569710933e-06,
"loss": 0.4682,
"step": 940
},
{
"epoch": 1.9387755102040818,
"grad_norm": 1.0174568043397745,
"learning_rate": 1.8726160761003172e-06,
"loss": 0.4714,
"step": 950
},
{
"epoch": 1.9591836734693877,
"grad_norm": 1.1472581629373104,
"learning_rate": 1.8262160197211954e-06,
"loss": 0.4694,
"step": 960
},
{
"epoch": 1.9795918367346939,
"grad_norm": 1.1908224015497966,
"learning_rate": 1.780283785735729e-06,
"loss": 0.4734,
"step": 970
},
{
"epoch": 2.0,
"grad_norm": 1.2121370436582353,
"learning_rate": 1.734842635131455e-06,
"loss": 0.4704,
"step": 980
},
{
"epoch": 2.0,
"eval_loss": 0.5511366724967957,
"eval_runtime": 52.0352,
"eval_samples_per_second": 253.636,
"eval_steps_per_second": 0.999,
"step": 980
},
{
"epoch": 2.020408163265306,
"grad_norm": 1.8051946996767576,
"learning_rate": 1.689915580201614e-06,
"loss": 0.3994,
"step": 990
},
{
"epoch": 2.0408163265306123,
"grad_norm": 1.1478153392823722,
"learning_rate": 1.6455253728912765e-06,
"loss": 0.4039,
"step": 1000
},
{
"epoch": 2.061224489795918,
"grad_norm": 1.1584353460539132,
"learning_rate": 1.6016944932753123e-06,
"loss": 0.3966,
"step": 1010
},
{
"epoch": 2.0816326530612246,
"grad_norm": 1.116691322240523,
"learning_rate": 1.558445138174033e-06,
"loss": 0.3956,
"step": 1020
},
{
"epoch": 2.1020408163265305,
"grad_norm": 1.2064468569146183,
"learning_rate": 1.5157992099122896e-06,
"loss": 0.3993,
"step": 1030
},
{
"epoch": 2.122448979591837,
"grad_norm": 1.139941688958116,
"learning_rate": 1.4737783052277017e-06,
"loss": 0.3961,
"step": 1040
},
{
"epoch": 2.142857142857143,
"grad_norm": 1.0807209086306862,
"learning_rate": 1.432403704333643e-06,
"loss": 0.3947,
"step": 1050
},
{
"epoch": 2.163265306122449,
"grad_norm": 1.2684450483524876,
"learning_rate": 1.3916963601425293e-06,
"loss": 0.3969,
"step": 1060
},
{
"epoch": 2.183673469387755,
"grad_norm": 1.1513016140487604,
"learning_rate": 1.3516768876548404e-06,
"loss": 0.393,
"step": 1070
},
{
"epoch": 2.204081632653061,
"grad_norm": 1.1528208336686618,
"learning_rate": 1.3123655535192873e-06,
"loss": 0.3951,
"step": 1080
},
{
"epoch": 2.2244897959183674,
"grad_norm": 1.114096425157638,
"learning_rate": 1.2737822657693763e-06,
"loss": 0.3979,
"step": 1090
},
{
"epoch": 2.2448979591836733,
"grad_norm": 1.137857862533777,
"learning_rate": 1.235946563741594e-06,
"loss": 0.3997,
"step": 1100
},
{
"epoch": 2.2653061224489797,
"grad_norm": 1.1835334812821745,
"learning_rate": 1.1988776081802975e-06,
"loss": 0.3899,
"step": 1110
},
{
"epoch": 2.2857142857142856,
"grad_norm": 1.1680694095477702,
"learning_rate": 1.1625941715343404e-06,
"loss": 0.3966,
"step": 1120
},
{
"epoch": 2.306122448979592,
"grad_norm": 1.1446186179544782,
"learning_rate": 1.1271146284503326e-06,
"loss": 0.396,
"step": 1130
},
{
"epoch": 2.326530612244898,
"grad_norm": 1.11805038713306,
"learning_rate": 1.0924569464673593e-06,
"loss": 0.3904,
"step": 1140
},
{
"epoch": 2.3469387755102042,
"grad_norm": 1.1390452730330538,
"learning_rate": 1.0586386769178644e-06,
"loss": 0.3975,
"step": 1150
},
{
"epoch": 2.36734693877551,
"grad_norm": 1.1201370952508136,
"learning_rate": 1.0256769460393087e-06,
"loss": 0.3967,
"step": 1160
},
{
"epoch": 2.387755102040816,
"grad_norm": 1.1392432124449605,
"learning_rate": 9.935884463011108e-07,
"loss": 0.3996,
"step": 1170
},
{
"epoch": 2.4081632653061225,
"grad_norm": 1.2588827341992963,
"learning_rate": 9.623894279512455e-07,
"loss": 0.396,
"step": 1180
},
{
"epoch": 2.4285714285714284,
"grad_norm": 1.077230551463912,
"learning_rate": 9.320956907868051e-07,
"loss": 0.3937,
"step": 1190
},
{
"epoch": 2.4489795918367347,
"grad_norm": 1.11076242811804,
"learning_rate": 9.027225761526653e-07,
"loss": 0.3952,
"step": 1200
},
{
"epoch": 2.4693877551020407,
"grad_norm": 1.09876781476475,
"learning_rate": 8.742849591723315e-07,
"loss": 0.3959,
"step": 1210
},
{
"epoch": 2.489795918367347,
"grad_norm": 1.147140927511145,
"learning_rate": 8.467972412148767e-07,
"loss": 0.398,
"step": 1220
},
{
"epoch": 2.510204081632653,
"grad_norm": 1.1822473270970597,
"learning_rate": 8.202733426018117e-07,
"loss": 0.3964,
"step": 1230
},
{
"epoch": 2.5306122448979593,
"grad_norm": 1.13658360907236,
"learning_rate": 7.947266955575562e-07,
"loss": 0.3927,
"step": 1240
},
{
"epoch": 2.5510204081632653,
"grad_norm": 1.161600360604373,
"learning_rate": 7.701702374070962e-07,
"loss": 0.395,
"step": 1250
},
{
"epoch": 2.571428571428571,
"grad_norm": 1.1360953648560599,
"learning_rate": 7.466164040242694e-07,
"loss": 0.393,
"step": 1260
},
{
"epoch": 2.5918367346938775,
"grad_norm": 1.0871899727126686,
"learning_rate": 7.24077123533992e-07,
"loss": 0.3954,
"step": 1270
},
{
"epoch": 2.612244897959184,
"grad_norm": 1.1448805596871288,
"learning_rate": 7.025638102716238e-07,
"loss": 0.3956,
"step": 1280
},
{
"epoch": 2.63265306122449,
"grad_norm": 1.15756019184531,
"learning_rate": 6.820873590025216e-07,
"loss": 0.3976,
"step": 1290
},
{
"epoch": 2.6530612244897958,
"grad_norm": 1.1241749432401325,
"learning_rate": 6.626581394047174e-07,
"loss": 0.3984,
"step": 1300
},
{
"epoch": 2.673469387755102,
"grad_norm": 1.0729517449985635,
"learning_rate": 6.442859908175084e-07,
"loss": 0.3959,
"step": 1310
},
{
"epoch": 2.693877551020408,
"grad_norm": 1.1503013647826037,
"learning_rate": 6.269802172586215e-07,
"loss": 0.397,
"step": 1320
},
{
"epoch": 2.7142857142857144,
"grad_norm": 1.0665491356834242,
"learning_rate": 6.107495827124764e-07,
"loss": 0.39,
"step": 1330
},
{
"epoch": 2.7346938775510203,
"grad_norm": 1.0915048516830226,
"learning_rate": 5.956023066919313e-07,
"loss": 0.3959,
"step": 1340
},
{
"epoch": 2.7551020408163263,
"grad_norm": 1.109246892499863,
"learning_rate": 5.815460600757599e-07,
"loss": 0.3959,
"step": 1350
},
{
"epoch": 2.7755102040816326,
"grad_norm": 1.0721604859361742,
"learning_rate": 5.685879612239649e-07,
"loss": 0.3966,
"step": 1360
},
{
"epoch": 2.795918367346939,
"grad_norm": 1.099826021414002,
"learning_rate": 5.567345723729062e-07,
"loss": 0.3981,
"step": 1370
},
{
"epoch": 2.816326530612245,
"grad_norm": 1.1271135580966902,
"learning_rate": 5.459918963120477e-07,
"loss": 0.3958,
"step": 1380
},
{
"epoch": 2.836734693877551,
"grad_norm": 1.1076320060744895,
"learning_rate": 5.363653733440328e-07,
"loss": 0.3937,
"step": 1390
},
{
"epoch": 2.857142857142857,
"grad_norm": 1.2274793148430172,
"learning_rate": 5.278598785296044e-07,
"loss": 0.3955,
"step": 1400
},
{
"epoch": 2.877551020408163,
"grad_norm": 1.118998176569128,
"learning_rate": 5.2047971921878e-07,
"loss": 0.3935,
"step": 1410
},
{
"epoch": 2.8979591836734695,
"grad_norm": 1.0904203190313753,
"learning_rate": 5.142286328695235e-07,
"loss": 0.3991,
"step": 1420
},
{
"epoch": 2.9183673469387754,
"grad_norm": 1.09693683808665,
"learning_rate": 5.091097851550239e-07,
"loss": 0.3984,
"step": 1430
},
{
"epoch": 2.938775510204082,
"grad_norm": 1.136997659277711,
"learning_rate": 5.051257683605363e-07,
"loss": 0.3977,
"step": 1440
},
{
"epoch": 2.9591836734693877,
"grad_norm": 1.1088368453362634,
"learning_rate": 5.022786000705963e-07,
"loss": 0.3948,
"step": 1450
},
{
"epoch": 2.979591836734694,
"grad_norm": 1.0739107650188835,
"learning_rate": 5.005697221472769e-07,
"loss": 0.3949,
"step": 1460
},
{
"epoch": 3.0,
"grad_norm": 1.116205224878417,
"learning_rate": 5e-07,
"loss": 0.3994,
"step": 1470
},
{
"epoch": 3.0,
"eval_loss": 0.5735070705413818,
"eval_runtime": 51.0398,
"eval_samples_per_second": 258.583,
"eval_steps_per_second": 1.019,
"step": 1470
},
{
"epoch": 3.0,
"step": 1470,
"total_flos": 2462304750796800.0,
"train_loss": 0.48433749789283387,
"train_runtime": 9163.976,
"train_samples_per_second": 82.091,
"train_steps_per_second": 0.16
}
],
"logging_steps": 10,
"max_steps": 1470,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 2462304750796800.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}