bart-large-80 / checkpoint-8938 /trainer_state.json
riken01's picture
Upload folder using huggingface_hub
185828d verified
raw
history blame contribute delete
No virus
63.8 kB
{
"best_metric": 4.248934268951416,
"best_model_checkpoint": "autotrain-l6hey-orl0t/checkpoint-8938",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 8938,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005594092638174088,
"grad_norm": 34.332366943359375,
"learning_rate": 7.829977628635347e-07,
"loss": 6.4897,
"step": 25
},
{
"epoch": 0.011188185276348177,
"grad_norm": 23.168872833251953,
"learning_rate": 1.7151379567486951e-06,
"loss": 6.3738,
"step": 50
},
{
"epoch": 0.016782277914522265,
"grad_norm": 20.714399337768555,
"learning_rate": 2.6472781506338553e-06,
"loss": 5.5122,
"step": 75
},
{
"epoch": 0.022376370552696354,
"grad_norm": 17.31004524230957,
"learning_rate": 3.542132736763609e-06,
"loss": 5.5352,
"step": 100
},
{
"epoch": 0.027970463190870442,
"grad_norm": 20.792905807495117,
"learning_rate": 4.47427293064877e-06,
"loss": 5.3902,
"step": 125
},
{
"epoch": 0.03356455582904453,
"grad_norm": 29.867664337158203,
"learning_rate": 5.40641312453393e-06,
"loss": 5.0552,
"step": 150
},
{
"epoch": 0.039158648467218615,
"grad_norm": 17.143095016479492,
"learning_rate": 6.338553318419091e-06,
"loss": 5.0792,
"step": 175
},
{
"epoch": 0.04475274110539271,
"grad_norm": 16.778640747070312,
"learning_rate": 7.270693512304251e-06,
"loss": 5.0412,
"step": 200
},
{
"epoch": 0.05034683374356679,
"grad_norm": 21.074262619018555,
"learning_rate": 8.20283370618941e-06,
"loss": 4.8163,
"step": 225
},
{
"epoch": 0.055940926381740884,
"grad_norm": 21.221630096435547,
"learning_rate": 9.134973900074571e-06,
"loss": 4.9409,
"step": 250
},
{
"epoch": 0.06153501901991497,
"grad_norm": 21.189231872558594,
"learning_rate": 1.006711409395973e-05,
"loss": 5.0649,
"step": 275
},
{
"epoch": 0.06712911165808906,
"grad_norm": 14.992874145507812,
"learning_rate": 1.0999254287844893e-05,
"loss": 4.7542,
"step": 300
},
{
"epoch": 0.07272320429626315,
"grad_norm": 15.733444213867188,
"learning_rate": 1.1931394481730052e-05,
"loss": 4.5938,
"step": 325
},
{
"epoch": 0.07831729693443723,
"grad_norm": 23.274600982666016,
"learning_rate": 1.2863534675615213e-05,
"loss": 4.6138,
"step": 350
},
{
"epoch": 0.08391138957261132,
"grad_norm": 17.92934799194336,
"learning_rate": 1.3795674869500374e-05,
"loss": 4.8809,
"step": 375
},
{
"epoch": 0.08950548221078541,
"grad_norm": 18.286834716796875,
"learning_rate": 1.4727815063385533e-05,
"loss": 4.6919,
"step": 400
},
{
"epoch": 0.09509957484895949,
"grad_norm": 20.009130477905273,
"learning_rate": 1.5659955257270695e-05,
"loss": 4.7557,
"step": 425
},
{
"epoch": 0.10069366748713358,
"grad_norm": 20.796175003051758,
"learning_rate": 1.6592095451155853e-05,
"loss": 4.8059,
"step": 450
},
{
"epoch": 0.10628776012530768,
"grad_norm": 18.083595275878906,
"learning_rate": 1.7524235645041014e-05,
"loss": 4.86,
"step": 475
},
{
"epoch": 0.11188185276348177,
"grad_norm": 17.57659339904785,
"learning_rate": 1.8456375838926178e-05,
"loss": 4.568,
"step": 500
},
{
"epoch": 0.11747594540165585,
"grad_norm": 20.379024505615234,
"learning_rate": 1.9388516032811335e-05,
"loss": 4.9103,
"step": 525
},
{
"epoch": 0.12307003803982994,
"grad_norm": 16.093093872070312,
"learning_rate": 2.0320656226696496e-05,
"loss": 4.5315,
"step": 550
},
{
"epoch": 0.12866413067800403,
"grad_norm": 31.44219970703125,
"learning_rate": 2.1252796420581657e-05,
"loss": 4.6423,
"step": 575
},
{
"epoch": 0.13425822331617812,
"grad_norm": 16.757986068725586,
"learning_rate": 2.2184936614466818e-05,
"loss": 4.5965,
"step": 600
},
{
"epoch": 0.1398523159543522,
"grad_norm": 16.31531524658203,
"learning_rate": 2.311707680835198e-05,
"loss": 4.6928,
"step": 625
},
{
"epoch": 0.1454464085925263,
"grad_norm": 13.83728313446045,
"learning_rate": 2.4049217002237136e-05,
"loss": 4.5197,
"step": 650
},
{
"epoch": 0.15104050123070037,
"grad_norm": 17.00248146057129,
"learning_rate": 2.49813571961223e-05,
"loss": 4.4602,
"step": 675
},
{
"epoch": 0.15663459386887446,
"grad_norm": 22.1146183013916,
"learning_rate": 2.5913497390007457e-05,
"loss": 4.4573,
"step": 700
},
{
"epoch": 0.16222868650704855,
"grad_norm": 16.24863624572754,
"learning_rate": 2.6845637583892618e-05,
"loss": 4.6094,
"step": 725
},
{
"epoch": 0.16782277914522264,
"grad_norm": 15.607491493225098,
"learning_rate": 2.777777777777778e-05,
"loss": 4.4851,
"step": 750
},
{
"epoch": 0.17341687178339674,
"grad_norm": 17.399606704711914,
"learning_rate": 2.8709917971662943e-05,
"loss": 4.7641,
"step": 775
},
{
"epoch": 0.17901096442157083,
"grad_norm": 12.437596321105957,
"learning_rate": 2.9642058165548097e-05,
"loss": 4.6065,
"step": 800
},
{
"epoch": 0.18460505705974492,
"grad_norm": 16.83686637878418,
"learning_rate": 3.057419835943326e-05,
"loss": 4.471,
"step": 825
},
{
"epoch": 0.19019914969791898,
"grad_norm": 17.172122955322266,
"learning_rate": 3.150633855331842e-05,
"loss": 4.7266,
"step": 850
},
{
"epoch": 0.19579324233609308,
"grad_norm": 18.03239631652832,
"learning_rate": 3.243847874720358e-05,
"loss": 4.46,
"step": 875
},
{
"epoch": 0.20138733497426717,
"grad_norm": 11.44616985321045,
"learning_rate": 3.3370618941088744e-05,
"loss": 4.2646,
"step": 900
},
{
"epoch": 0.20698142761244126,
"grad_norm": 18.69893455505371,
"learning_rate": 3.43027591349739e-05,
"loss": 4.5796,
"step": 925
},
{
"epoch": 0.21257552025061535,
"grad_norm": 26.265470504760742,
"learning_rate": 3.523489932885906e-05,
"loss": 4.476,
"step": 950
},
{
"epoch": 0.21816961288878944,
"grad_norm": 28.28611946105957,
"learning_rate": 3.616703952274422e-05,
"loss": 4.9502,
"step": 975
},
{
"epoch": 0.22376370552696354,
"grad_norm": 20.53813362121582,
"learning_rate": 3.709917971662939e-05,
"loss": 4.5447,
"step": 1000
},
{
"epoch": 0.22935779816513763,
"grad_norm": 14.012741088867188,
"learning_rate": 3.8031319910514545e-05,
"loss": 4.7348,
"step": 1025
},
{
"epoch": 0.2349518908033117,
"grad_norm": 15.572279930114746,
"learning_rate": 3.89634601043997e-05,
"loss": 4.7246,
"step": 1050
},
{
"epoch": 0.24054598344148578,
"grad_norm": 13.881638526916504,
"learning_rate": 3.9895600298284866e-05,
"loss": 4.6181,
"step": 1075
},
{
"epoch": 0.24614007607965988,
"grad_norm": 12.749186515808105,
"learning_rate": 4.0827740492170024e-05,
"loss": 4.3893,
"step": 1100
},
{
"epoch": 0.251734168717834,
"grad_norm": 17.131837844848633,
"learning_rate": 4.175988068605519e-05,
"loss": 4.3859,
"step": 1125
},
{
"epoch": 0.25732826135600806,
"grad_norm": 13.731075286865234,
"learning_rate": 4.2692020879940345e-05,
"loss": 4.4761,
"step": 1150
},
{
"epoch": 0.2629223539941821,
"grad_norm": 15.064730644226074,
"learning_rate": 4.36241610738255e-05,
"loss": 4.4364,
"step": 1175
},
{
"epoch": 0.26851644663235624,
"grad_norm": 13.714836120605469,
"learning_rate": 4.455630126771067e-05,
"loss": 4.5969,
"step": 1200
},
{
"epoch": 0.2741105392705303,
"grad_norm": 14.1889009475708,
"learning_rate": 4.5488441461595824e-05,
"loss": 4.9771,
"step": 1225
},
{
"epoch": 0.2797046319087044,
"grad_norm": 14.543293952941895,
"learning_rate": 4.642058165548099e-05,
"loss": 4.6537,
"step": 1250
},
{
"epoch": 0.2852987245468785,
"grad_norm": 18.1214542388916,
"learning_rate": 4.735272184936615e-05,
"loss": 4.6208,
"step": 1275
},
{
"epoch": 0.2908928171850526,
"grad_norm": 13.347675323486328,
"learning_rate": 4.82848620432513e-05,
"loss": 4.6199,
"step": 1300
},
{
"epoch": 0.2964869098232267,
"grad_norm": 17.083444595336914,
"learning_rate": 4.921700223713647e-05,
"loss": 4.8805,
"step": 1325
},
{
"epoch": 0.30208100246140074,
"grad_norm": 24.343929290771484,
"learning_rate": 4.998342449859108e-05,
"loss": 4.6357,
"step": 1350
},
{
"epoch": 0.30767509509957486,
"grad_norm": 16.355289459228516,
"learning_rate": 4.987982761478535e-05,
"loss": 4.674,
"step": 1375
},
{
"epoch": 0.3132691877377489,
"grad_norm": 20.73784828186035,
"learning_rate": 4.978037460633184e-05,
"loss": 4.6211,
"step": 1400
},
{
"epoch": 0.31886328037592304,
"grad_norm": 13.50486946105957,
"learning_rate": 4.9676777722526106e-05,
"loss": 4.7257,
"step": 1425
},
{
"epoch": 0.3244573730140971,
"grad_norm": 14.019612312316895,
"learning_rate": 4.9573180838720376e-05,
"loss": 4.6509,
"step": 1450
},
{
"epoch": 0.3300514656522712,
"grad_norm": 18.581026077270508,
"learning_rate": 4.946958395491464e-05,
"loss": 4.3779,
"step": 1475
},
{
"epoch": 0.3356455582904453,
"grad_norm": 12.192296981811523,
"learning_rate": 4.93659870711089e-05,
"loss": 4.2878,
"step": 1500
},
{
"epoch": 0.34123965092861935,
"grad_norm": 12.066230773925781,
"learning_rate": 4.926239018730317e-05,
"loss": 4.5682,
"step": 1525
},
{
"epoch": 0.3468337435667935,
"grad_norm": 10.833414077758789,
"learning_rate": 4.9158793303497436e-05,
"loss": 4.1772,
"step": 1550
},
{
"epoch": 0.35242783620496754,
"grad_norm": 10.834297180175781,
"learning_rate": 4.905519641969169e-05,
"loss": 4.6879,
"step": 1575
},
{
"epoch": 0.35802192884314166,
"grad_norm": 12.870365142822266,
"learning_rate": 4.895159953588596e-05,
"loss": 4.7267,
"step": 1600
},
{
"epoch": 0.3636160214813157,
"grad_norm": 10.991371154785156,
"learning_rate": 4.8848002652080226e-05,
"loss": 4.6822,
"step": 1625
},
{
"epoch": 0.36921011411948984,
"grad_norm": 14.67126178741455,
"learning_rate": 4.874440576827449e-05,
"loss": 4.3277,
"step": 1650
},
{
"epoch": 0.3748042067576639,
"grad_norm": 13.142556190490723,
"learning_rate": 4.864080888446876e-05,
"loss": 4.513,
"step": 1675
},
{
"epoch": 0.38039829939583797,
"grad_norm": 12.647134780883789,
"learning_rate": 4.853721200066302e-05,
"loss": 4.6069,
"step": 1700
},
{
"epoch": 0.3859923920340121,
"grad_norm": 12.48798942565918,
"learning_rate": 4.8433615116857286e-05,
"loss": 4.846,
"step": 1725
},
{
"epoch": 0.39158648467218615,
"grad_norm": 10.90004825592041,
"learning_rate": 4.833001823305155e-05,
"loss": 4.4091,
"step": 1750
},
{
"epoch": 0.39718057731036027,
"grad_norm": 14.13915729522705,
"learning_rate": 4.822642134924581e-05,
"loss": 4.4192,
"step": 1775
},
{
"epoch": 0.40277466994853434,
"grad_norm": 13.102397918701172,
"learning_rate": 4.812282446544008e-05,
"loss": 4.5444,
"step": 1800
},
{
"epoch": 0.40836876258670846,
"grad_norm": 12.227831840515137,
"learning_rate": 4.8019227581634346e-05,
"loss": 4.712,
"step": 1825
},
{
"epoch": 0.4139628552248825,
"grad_norm": 15.215840339660645,
"learning_rate": 4.791563069782861e-05,
"loss": 4.6632,
"step": 1850
},
{
"epoch": 0.41955694786305664,
"grad_norm": 18.023183822631836,
"learning_rate": 4.781203381402288e-05,
"loss": 4.1778,
"step": 1875
},
{
"epoch": 0.4251510405012307,
"grad_norm": 13.230670928955078,
"learning_rate": 4.770843693021714e-05,
"loss": 4.4197,
"step": 1900
},
{
"epoch": 0.43074513313940477,
"grad_norm": 14.070335388183594,
"learning_rate": 4.7604840046411407e-05,
"loss": 4.6564,
"step": 1925
},
{
"epoch": 0.4363392257775789,
"grad_norm": 20.313472747802734,
"learning_rate": 4.750124316260567e-05,
"loss": 4.5667,
"step": 1950
},
{
"epoch": 0.44193331841575295,
"grad_norm": 15.953713417053223,
"learning_rate": 4.739764627879993e-05,
"loss": 4.5235,
"step": 1975
},
{
"epoch": 0.44752741105392707,
"grad_norm": 10.95453929901123,
"learning_rate": 4.7294049394994197e-05,
"loss": 4.5047,
"step": 2000
},
{
"epoch": 0.45312150369210114,
"grad_norm": 15.660309791564941,
"learning_rate": 4.719045251118847e-05,
"loss": 4.1537,
"step": 2025
},
{
"epoch": 0.45871559633027525,
"grad_norm": 11.03080940246582,
"learning_rate": 4.708685562738273e-05,
"loss": 4.3448,
"step": 2050
},
{
"epoch": 0.4643096889684493,
"grad_norm": 10.359949111938477,
"learning_rate": 4.698325874357699e-05,
"loss": 4.3634,
"step": 2075
},
{
"epoch": 0.4699037816066234,
"grad_norm": 25.401718139648438,
"learning_rate": 4.6879661859771263e-05,
"loss": 4.2735,
"step": 2100
},
{
"epoch": 0.4754978742447975,
"grad_norm": 14.679646492004395,
"learning_rate": 4.677606497596553e-05,
"loss": 4.4465,
"step": 2125
},
{
"epoch": 0.48109196688297157,
"grad_norm": 11.817214965820312,
"learning_rate": 4.667246809215979e-05,
"loss": 4.629,
"step": 2150
},
{
"epoch": 0.4866860595211457,
"grad_norm": 10.622258186340332,
"learning_rate": 4.656887120835405e-05,
"loss": 4.4189,
"step": 2175
},
{
"epoch": 0.49228015215931975,
"grad_norm": 15.188981056213379,
"learning_rate": 4.646527432454832e-05,
"loss": 4.2514,
"step": 2200
},
{
"epoch": 0.49787424479749387,
"grad_norm": 14.326010704040527,
"learning_rate": 4.636167744074259e-05,
"loss": 4.3532,
"step": 2225
},
{
"epoch": 0.503468337435668,
"grad_norm": 16.31020164489746,
"learning_rate": 4.625808055693685e-05,
"loss": 4.2333,
"step": 2250
},
{
"epoch": 0.509062430073842,
"grad_norm": 18.346088409423828,
"learning_rate": 4.6154483673131113e-05,
"loss": 4.4483,
"step": 2275
},
{
"epoch": 0.5146565227120161,
"grad_norm": 15.169132232666016,
"learning_rate": 4.6050886789325384e-05,
"loss": 4.3814,
"step": 2300
},
{
"epoch": 0.5202506153501902,
"grad_norm": 10.011805534362793,
"learning_rate": 4.594728990551964e-05,
"loss": 4.6235,
"step": 2325
},
{
"epoch": 0.5258447079883642,
"grad_norm": 11.23599624633789,
"learning_rate": 4.584369302171391e-05,
"loss": 4.5861,
"step": 2350
},
{
"epoch": 0.5314388006265384,
"grad_norm": 10.484898567199707,
"learning_rate": 4.5740096137908174e-05,
"loss": 4.3894,
"step": 2375
},
{
"epoch": 0.5370328932647125,
"grad_norm": 12.192333221435547,
"learning_rate": 4.563649925410244e-05,
"loss": 4.448,
"step": 2400
},
{
"epoch": 0.5426269859028866,
"grad_norm": 15.25631332397461,
"learning_rate": 4.553290237029671e-05,
"loss": 4.3787,
"step": 2425
},
{
"epoch": 0.5482210785410606,
"grad_norm": 10.27658748626709,
"learning_rate": 4.542930548649097e-05,
"loss": 4.4333,
"step": 2450
},
{
"epoch": 0.5538151711792347,
"grad_norm": 16.127513885498047,
"learning_rate": 4.5325708602685234e-05,
"loss": 4.1792,
"step": 2475
},
{
"epoch": 0.5594092638174089,
"grad_norm": 10.214879035949707,
"learning_rate": 4.5222111718879504e-05,
"loss": 4.6276,
"step": 2500
},
{
"epoch": 0.5650033564555829,
"grad_norm": 10.60392951965332,
"learning_rate": 4.511851483507376e-05,
"loss": 4.5925,
"step": 2525
},
{
"epoch": 0.570597449093757,
"grad_norm": 11.073285102844238,
"learning_rate": 4.5014917951268024e-05,
"loss": 4.4202,
"step": 2550
},
{
"epoch": 0.5761915417319311,
"grad_norm": 14.709641456604004,
"learning_rate": 4.4911321067462294e-05,
"loss": 4.2758,
"step": 2575
},
{
"epoch": 0.5817856343701052,
"grad_norm": 12.901021957397461,
"learning_rate": 4.480772418365656e-05,
"loss": 4.3067,
"step": 2600
},
{
"epoch": 0.5873797270082792,
"grad_norm": 11.27915096282959,
"learning_rate": 4.470412729985082e-05,
"loss": 4.0111,
"step": 2625
},
{
"epoch": 0.5929738196464533,
"grad_norm": 15.488706588745117,
"learning_rate": 4.460053041604509e-05,
"loss": 4.2671,
"step": 2650
},
{
"epoch": 0.5985679122846275,
"grad_norm": 13.603848457336426,
"learning_rate": 4.4496933532239354e-05,
"loss": 4.2589,
"step": 2675
},
{
"epoch": 0.6041620049228015,
"grad_norm": 12.827610969543457,
"learning_rate": 4.439333664843362e-05,
"loss": 4.6476,
"step": 2700
},
{
"epoch": 0.6097560975609756,
"grad_norm": 16.806106567382812,
"learning_rate": 4.428973976462788e-05,
"loss": 4.6188,
"step": 2725
},
{
"epoch": 0.6153501901991497,
"grad_norm": 14.598794937133789,
"learning_rate": 4.4186142880822144e-05,
"loss": 4.4195,
"step": 2750
},
{
"epoch": 0.6209442828373238,
"grad_norm": 10.380790710449219,
"learning_rate": 4.4082545997016414e-05,
"loss": 4.4634,
"step": 2775
},
{
"epoch": 0.6265383754754978,
"grad_norm": 12.62149715423584,
"learning_rate": 4.397894911321068e-05,
"loss": 4.4751,
"step": 2800
},
{
"epoch": 0.632132468113672,
"grad_norm": 10.467231750488281,
"learning_rate": 4.387535222940494e-05,
"loss": 4.2898,
"step": 2825
},
{
"epoch": 0.6377265607518461,
"grad_norm": 12.244780540466309,
"learning_rate": 4.377175534559921e-05,
"loss": 4.3242,
"step": 2850
},
{
"epoch": 0.6433206533900201,
"grad_norm": 12.39667797088623,
"learning_rate": 4.3668158461793474e-05,
"loss": 4.2754,
"step": 2875
},
{
"epoch": 0.6489147460281942,
"grad_norm": 12.747861862182617,
"learning_rate": 4.356456157798773e-05,
"loss": 4.286,
"step": 2900
},
{
"epoch": 0.6545088386663683,
"grad_norm": 22.809650421142578,
"learning_rate": 4.3460964694182e-05,
"loss": 4.3482,
"step": 2925
},
{
"epoch": 0.6601029313045425,
"grad_norm": 10.659783363342285,
"learning_rate": 4.3357367810376264e-05,
"loss": 4.2066,
"step": 2950
},
{
"epoch": 0.6656970239427165,
"grad_norm": 14.72028636932373,
"learning_rate": 4.325377092657053e-05,
"loss": 4.4523,
"step": 2975
},
{
"epoch": 0.6712911165808906,
"grad_norm": 10.166138648986816,
"learning_rate": 4.31501740427648e-05,
"loss": 4.3615,
"step": 3000
},
{
"epoch": 0.6768852092190647,
"grad_norm": 12.992719650268555,
"learning_rate": 4.304657715895906e-05,
"loss": 4.5061,
"step": 3025
},
{
"epoch": 0.6824793018572387,
"grad_norm": 11.16627311706543,
"learning_rate": 4.2942980275153324e-05,
"loss": 4.5588,
"step": 3050
},
{
"epoch": 0.6880733944954128,
"grad_norm": 10.317902565002441,
"learning_rate": 4.2839383391347594e-05,
"loss": 4.3462,
"step": 3075
},
{
"epoch": 0.693667487133587,
"grad_norm": 12.662385940551758,
"learning_rate": 4.273578650754185e-05,
"loss": 4.5361,
"step": 3100
},
{
"epoch": 0.6992615797717611,
"grad_norm": 16.921144485473633,
"learning_rate": 4.263218962373612e-05,
"loss": 4.2344,
"step": 3125
},
{
"epoch": 0.7048556724099351,
"grad_norm": 17.665006637573242,
"learning_rate": 4.2528592739930384e-05,
"loss": 4.2197,
"step": 3150
},
{
"epoch": 0.7104497650481092,
"grad_norm": 9.232120513916016,
"learning_rate": 4.242499585612465e-05,
"loss": 4.511,
"step": 3175
},
{
"epoch": 0.7160438576862833,
"grad_norm": 12.514689445495605,
"learning_rate": 4.232139897231892e-05,
"loss": 4.5251,
"step": 3200
},
{
"epoch": 0.7216379503244573,
"grad_norm": 11.398234367370605,
"learning_rate": 4.221780208851318e-05,
"loss": 4.1084,
"step": 3225
},
{
"epoch": 0.7272320429626314,
"grad_norm": 8.08095932006836,
"learning_rate": 4.2114205204707444e-05,
"loss": 4.1601,
"step": 3250
},
{
"epoch": 0.7328261356008056,
"grad_norm": 12.109641075134277,
"learning_rate": 4.2010608320901714e-05,
"loss": 4.274,
"step": 3275
},
{
"epoch": 0.7384202282389797,
"grad_norm": 10.819121360778809,
"learning_rate": 4.190701143709597e-05,
"loss": 4.5686,
"step": 3300
},
{
"epoch": 0.7440143208771537,
"grad_norm": 11.090829849243164,
"learning_rate": 4.180341455329024e-05,
"loss": 4.5401,
"step": 3325
},
{
"epoch": 0.7496084135153278,
"grad_norm": 11.24759578704834,
"learning_rate": 4.1699817669484504e-05,
"loss": 4.4797,
"step": 3350
},
{
"epoch": 0.7552025061535019,
"grad_norm": 10.916013717651367,
"learning_rate": 4.159622078567877e-05,
"loss": 4.1258,
"step": 3375
},
{
"epoch": 0.7607965987916759,
"grad_norm": 11.953822135925293,
"learning_rate": 4.149262390187304e-05,
"loss": 4.3313,
"step": 3400
},
{
"epoch": 0.7663906914298501,
"grad_norm": 16.665861129760742,
"learning_rate": 4.13890270180673e-05,
"loss": 4.2789,
"step": 3425
},
{
"epoch": 0.7719847840680242,
"grad_norm": 11.539497375488281,
"learning_rate": 4.1285430134261564e-05,
"loss": 4.5436,
"step": 3450
},
{
"epoch": 0.7775788767061983,
"grad_norm": 11.955995559692383,
"learning_rate": 4.118183325045583e-05,
"loss": 4.1149,
"step": 3475
},
{
"epoch": 0.7831729693443723,
"grad_norm": 15.087596893310547,
"learning_rate": 4.107823636665009e-05,
"loss": 4.3523,
"step": 3500
},
{
"epoch": 0.7887670619825464,
"grad_norm": 14.733497619628906,
"learning_rate": 4.0974639482844354e-05,
"loss": 4.2913,
"step": 3525
},
{
"epoch": 0.7943611546207205,
"grad_norm": 10.125676155090332,
"learning_rate": 4.0871042599038624e-05,
"loss": 4.3078,
"step": 3550
},
{
"epoch": 0.7999552472588946,
"grad_norm": 11.222993850708008,
"learning_rate": 4.076744571523289e-05,
"loss": 4.4803,
"step": 3575
},
{
"epoch": 0.8055493398970687,
"grad_norm": 10.871453285217285,
"learning_rate": 4.066384883142715e-05,
"loss": 4.5347,
"step": 3600
},
{
"epoch": 0.8111434325352428,
"grad_norm": 10.571527481079102,
"learning_rate": 4.056025194762142e-05,
"loss": 4.1658,
"step": 3625
},
{
"epoch": 0.8167375251734169,
"grad_norm": 12.036689758300781,
"learning_rate": 4.0456655063815685e-05,
"loss": 4.3284,
"step": 3650
},
{
"epoch": 0.8223316178115909,
"grad_norm": 13.614919662475586,
"learning_rate": 4.035305818000995e-05,
"loss": 4.1228,
"step": 3675
},
{
"epoch": 0.827925710449765,
"grad_norm": 12.302602767944336,
"learning_rate": 4.024946129620421e-05,
"loss": 4.0459,
"step": 3700
},
{
"epoch": 0.8335198030879392,
"grad_norm": 13.102405548095703,
"learning_rate": 4.0145864412398474e-05,
"loss": 4.4641,
"step": 3725
},
{
"epoch": 0.8391138957261133,
"grad_norm": 12.71800422668457,
"learning_rate": 4.0042267528592745e-05,
"loss": 4.206,
"step": 3750
},
{
"epoch": 0.8447079883642873,
"grad_norm": 13.687782287597656,
"learning_rate": 3.993867064478701e-05,
"loss": 4.388,
"step": 3775
},
{
"epoch": 0.8503020810024614,
"grad_norm": 16.609664916992188,
"learning_rate": 3.983507376098127e-05,
"loss": 4.1664,
"step": 3800
},
{
"epoch": 0.8558961736406355,
"grad_norm": 16.731786727905273,
"learning_rate": 3.973147687717554e-05,
"loss": 4.3956,
"step": 3825
},
{
"epoch": 0.8614902662788095,
"grad_norm": 17.152843475341797,
"learning_rate": 3.96278799933698e-05,
"loss": 4.3338,
"step": 3850
},
{
"epoch": 0.8670843589169837,
"grad_norm": 14.199774742126465,
"learning_rate": 3.952428310956406e-05,
"loss": 4.4609,
"step": 3875
},
{
"epoch": 0.8726784515551578,
"grad_norm": 11.605820655822754,
"learning_rate": 3.942068622575833e-05,
"loss": 4.1688,
"step": 3900
},
{
"epoch": 0.8782725441933319,
"grad_norm": 11.608319282531738,
"learning_rate": 3.9317089341952595e-05,
"loss": 4.2122,
"step": 3925
},
{
"epoch": 0.8838666368315059,
"grad_norm": 12.212512016296387,
"learning_rate": 3.921349245814686e-05,
"loss": 4.2482,
"step": 3950
},
{
"epoch": 0.88946072946968,
"grad_norm": 12.425273895263672,
"learning_rate": 3.910989557434113e-05,
"loss": 4.5128,
"step": 3975
},
{
"epoch": 0.8950548221078541,
"grad_norm": 14.292542457580566,
"learning_rate": 3.900629869053539e-05,
"loss": 4.5421,
"step": 4000
},
{
"epoch": 0.9006489147460282,
"grad_norm": 9.911199569702148,
"learning_rate": 3.8902701806729655e-05,
"loss": 4.3237,
"step": 4025
},
{
"epoch": 0.9062430073842023,
"grad_norm": 6.303875923156738,
"learning_rate": 3.879910492292392e-05,
"loss": 4.195,
"step": 4050
},
{
"epoch": 0.9118371000223764,
"grad_norm": 8.433326721191406,
"learning_rate": 3.869550803911818e-05,
"loss": 4.1758,
"step": 4075
},
{
"epoch": 0.9174311926605505,
"grad_norm": 12.792257308959961,
"learning_rate": 3.859191115531245e-05,
"loss": 4.1538,
"step": 4100
},
{
"epoch": 0.9230252852987245,
"grad_norm": 10.63804817199707,
"learning_rate": 3.8488314271506715e-05,
"loss": 4.2415,
"step": 4125
},
{
"epoch": 0.9286193779368986,
"grad_norm": 10.244176864624023,
"learning_rate": 3.838471738770098e-05,
"loss": 4.624,
"step": 4150
},
{
"epoch": 0.9342134705750728,
"grad_norm": 14.590502738952637,
"learning_rate": 3.828112050389525e-05,
"loss": 4.261,
"step": 4175
},
{
"epoch": 0.9398075632132468,
"grad_norm": 17.149826049804688,
"learning_rate": 3.817752362008951e-05,
"loss": 4.0573,
"step": 4200
},
{
"epoch": 0.9454016558514209,
"grad_norm": 10.837606430053711,
"learning_rate": 3.8073926736283775e-05,
"loss": 4.2502,
"step": 4225
},
{
"epoch": 0.950995748489595,
"grad_norm": 13.960970878601074,
"learning_rate": 3.797032985247804e-05,
"loss": 4.1431,
"step": 4250
},
{
"epoch": 0.9565898411277691,
"grad_norm": 10.603372573852539,
"learning_rate": 3.78667329686723e-05,
"loss": 4.2805,
"step": 4275
},
{
"epoch": 0.9621839337659431,
"grad_norm": 14.068360328674316,
"learning_rate": 3.776313608486657e-05,
"loss": 4.2771,
"step": 4300
},
{
"epoch": 0.9677780264041173,
"grad_norm": 12.487285614013672,
"learning_rate": 3.7659539201060835e-05,
"loss": 4.4749,
"step": 4325
},
{
"epoch": 0.9733721190422914,
"grad_norm": 11.214025497436523,
"learning_rate": 3.75559423172551e-05,
"loss": 4.1715,
"step": 4350
},
{
"epoch": 0.9789662116804654,
"grad_norm": 12.117270469665527,
"learning_rate": 3.745234543344937e-05,
"loss": 4.1669,
"step": 4375
},
{
"epoch": 0.9845603043186395,
"grad_norm": 7.657718181610107,
"learning_rate": 3.734874854964363e-05,
"loss": 4.1935,
"step": 4400
},
{
"epoch": 0.9901543969568136,
"grad_norm": 12.381430625915527,
"learning_rate": 3.724929554119012e-05,
"loss": 4.3682,
"step": 4425
},
{
"epoch": 0.9957484895949877,
"grad_norm": 12.749862670898438,
"learning_rate": 3.7145698657384385e-05,
"loss": 4.2554,
"step": 4450
},
{
"epoch": 1.0,
"eval_gen_len": 67.1128,
"eval_loss": 4.290805816650391,
"eval_rouge1": 26.1327,
"eval_rouge2": 10.0836,
"eval_rougeL": 24.9862,
"eval_rougeLsum": 25.321,
"eval_runtime": 1004.8822,
"eval_samples_per_second": 1.112,
"eval_steps_per_second": 0.279,
"step": 4469
},
{
"epoch": 1.0013425822331619,
"grad_norm": 15.127477645874023,
"learning_rate": 3.7042101773578655e-05,
"loss": 3.9898,
"step": 4475
},
{
"epoch": 1.006936674871336,
"grad_norm": 10.354872703552246,
"learning_rate": 3.693850488977292e-05,
"loss": 3.623,
"step": 4500
},
{
"epoch": 1.0125307675095099,
"grad_norm": 13.131593704223633,
"learning_rate": 3.683490800596718e-05,
"loss": 3.7952,
"step": 4525
},
{
"epoch": 1.018124860147684,
"grad_norm": 10.636340141296387,
"learning_rate": 3.673131112216145e-05,
"loss": 3.4462,
"step": 4550
},
{
"epoch": 1.0237189527858581,
"grad_norm": 14.03700065612793,
"learning_rate": 3.662771423835571e-05,
"loss": 3.4108,
"step": 4575
},
{
"epoch": 1.0293130454240322,
"grad_norm": 21.94048309326172,
"learning_rate": 3.652411735454997e-05,
"loss": 3.7664,
"step": 4600
},
{
"epoch": 1.0349071380622064,
"grad_norm": 11.382323265075684,
"learning_rate": 3.642052047074424e-05,
"loss": 3.7189,
"step": 4625
},
{
"epoch": 1.0405012307003805,
"grad_norm": 11.167036056518555,
"learning_rate": 3.6316923586938505e-05,
"loss": 3.7947,
"step": 4650
},
{
"epoch": 1.0460953233385544,
"grad_norm": 13.024956703186035,
"learning_rate": 3.621332670313277e-05,
"loss": 3.6083,
"step": 4675
},
{
"epoch": 1.0516894159767285,
"grad_norm": 11.757680892944336,
"learning_rate": 3.610972981932704e-05,
"loss": 3.5998,
"step": 4700
},
{
"epoch": 1.0572835086149026,
"grad_norm": 14.893111228942871,
"learning_rate": 3.60061329355213e-05,
"loss": 3.6173,
"step": 4725
},
{
"epoch": 1.0628776012530767,
"grad_norm": 9.222747802734375,
"learning_rate": 3.5902536051715565e-05,
"loss": 3.6453,
"step": 4750
},
{
"epoch": 1.0684716938912509,
"grad_norm": 25.488880157470703,
"learning_rate": 3.579893916790983e-05,
"loss": 3.3486,
"step": 4775
},
{
"epoch": 1.074065786529425,
"grad_norm": 10.05694580078125,
"learning_rate": 3.569534228410409e-05,
"loss": 3.7705,
"step": 4800
},
{
"epoch": 1.079659879167599,
"grad_norm": 12.402889251708984,
"learning_rate": 3.559174540029836e-05,
"loss": 3.3739,
"step": 4825
},
{
"epoch": 1.085253971805773,
"grad_norm": 10.890093803405762,
"learning_rate": 3.5488148516492625e-05,
"loss": 3.7975,
"step": 4850
},
{
"epoch": 1.090848064443947,
"grad_norm": 12.410653114318848,
"learning_rate": 3.538455163268689e-05,
"loss": 3.5483,
"step": 4875
},
{
"epoch": 1.0964421570821212,
"grad_norm": 11.636606216430664,
"learning_rate": 3.528095474888116e-05,
"loss": 3.5182,
"step": 4900
},
{
"epoch": 1.1020362497202953,
"grad_norm": 14.367986679077148,
"learning_rate": 3.517735786507542e-05,
"loss": 3.9954,
"step": 4925
},
{
"epoch": 1.1076303423584695,
"grad_norm": 10.753607749938965,
"learning_rate": 3.5073760981269685e-05,
"loss": 3.8582,
"step": 4950
},
{
"epoch": 1.1132244349966436,
"grad_norm": 9.407801628112793,
"learning_rate": 3.497016409746395e-05,
"loss": 3.6181,
"step": 4975
},
{
"epoch": 1.1188185276348177,
"grad_norm": 9.98642349243164,
"learning_rate": 3.486656721365821e-05,
"loss": 3.5989,
"step": 5000
},
{
"epoch": 1.1244126202729916,
"grad_norm": 9.880094528198242,
"learning_rate": 3.476297032985248e-05,
"loss": 3.658,
"step": 5025
},
{
"epoch": 1.1300067129111657,
"grad_norm": 14.001792907714844,
"learning_rate": 3.4659373446046745e-05,
"loss": 3.7073,
"step": 5050
},
{
"epoch": 1.1356008055493398,
"grad_norm": 18.54832649230957,
"learning_rate": 3.455577656224101e-05,
"loss": 3.7806,
"step": 5075
},
{
"epoch": 1.141194898187514,
"grad_norm": 9.804744720458984,
"learning_rate": 3.445217967843528e-05,
"loss": 3.6671,
"step": 5100
},
{
"epoch": 1.146788990825688,
"grad_norm": 8.401939392089844,
"learning_rate": 3.434858279462954e-05,
"loss": 3.8566,
"step": 5125
},
{
"epoch": 1.1523830834638622,
"grad_norm": 10.120752334594727,
"learning_rate": 3.42449859108238e-05,
"loss": 3.8143,
"step": 5150
},
{
"epoch": 1.1579771761020363,
"grad_norm": 16.10240364074707,
"learning_rate": 3.414138902701807e-05,
"loss": 3.7451,
"step": 5175
},
{
"epoch": 1.1635712687402102,
"grad_norm": 10.377949714660645,
"learning_rate": 3.403779214321233e-05,
"loss": 3.6082,
"step": 5200
},
{
"epoch": 1.1691653613783843,
"grad_norm": 10.826866149902344,
"learning_rate": 3.3934195259406595e-05,
"loss": 3.8001,
"step": 5225
},
{
"epoch": 1.1747594540165585,
"grad_norm": 10.02441120147705,
"learning_rate": 3.3830598375600866e-05,
"loss": 3.6624,
"step": 5250
},
{
"epoch": 1.1803535466547326,
"grad_norm": 15.683877944946289,
"learning_rate": 3.372700149179513e-05,
"loss": 3.5834,
"step": 5275
},
{
"epoch": 1.1859476392929067,
"grad_norm": 11.696283340454102,
"learning_rate": 3.362340460798939e-05,
"loss": 3.6069,
"step": 5300
},
{
"epoch": 1.1915417319310808,
"grad_norm": 13.27725601196289,
"learning_rate": 3.351980772418366e-05,
"loss": 3.6614,
"step": 5325
},
{
"epoch": 1.197135824569255,
"grad_norm": 11.811793327331543,
"learning_rate": 3.341621084037792e-05,
"loss": 3.6186,
"step": 5350
},
{
"epoch": 1.2027299172074288,
"grad_norm": 30.400972366333008,
"learning_rate": 3.331261395657219e-05,
"loss": 3.6704,
"step": 5375
},
{
"epoch": 1.208324009845603,
"grad_norm": 11.845870018005371,
"learning_rate": 3.320901707276645e-05,
"loss": 3.6688,
"step": 5400
},
{
"epoch": 1.213918102483777,
"grad_norm": 14.447372436523438,
"learning_rate": 3.3105420188960716e-05,
"loss": 3.8172,
"step": 5425
},
{
"epoch": 1.2195121951219512,
"grad_norm": 9.492889404296875,
"learning_rate": 3.3001823305154986e-05,
"loss": 3.5741,
"step": 5450
},
{
"epoch": 1.2251062877601253,
"grad_norm": 12.105642318725586,
"learning_rate": 3.289822642134925e-05,
"loss": 3.5402,
"step": 5475
},
{
"epoch": 1.2307003803982994,
"grad_norm": 7.518635272979736,
"learning_rate": 3.279462953754351e-05,
"loss": 3.7333,
"step": 5500
},
{
"epoch": 1.2362944730364736,
"grad_norm": 11.485749244689941,
"learning_rate": 3.269103265373778e-05,
"loss": 3.8156,
"step": 5525
},
{
"epoch": 1.2418885656746474,
"grad_norm": 11.726677894592285,
"learning_rate": 3.258743576993204e-05,
"loss": 3.937,
"step": 5550
},
{
"epoch": 1.2474826583128216,
"grad_norm": 13.454861640930176,
"learning_rate": 3.24838388861263e-05,
"loss": 3.5792,
"step": 5575
},
{
"epoch": 1.2530767509509957,
"grad_norm": 17.696428298950195,
"learning_rate": 3.238024200232057e-05,
"loss": 3.5828,
"step": 5600
},
{
"epoch": 1.2586708435891698,
"grad_norm": 12.128670692443848,
"learning_rate": 3.2276645118514836e-05,
"loss": 3.6379,
"step": 5625
},
{
"epoch": 1.264264936227344,
"grad_norm": 11.507698059082031,
"learning_rate": 3.21730482347091e-05,
"loss": 3.5192,
"step": 5650
},
{
"epoch": 1.269859028865518,
"grad_norm": 11.207321166992188,
"learning_rate": 3.206945135090337e-05,
"loss": 3.885,
"step": 5675
},
{
"epoch": 1.2754531215036922,
"grad_norm": 9.954567909240723,
"learning_rate": 3.196585446709763e-05,
"loss": 3.6138,
"step": 5700
},
{
"epoch": 1.281047214141866,
"grad_norm": 9.7274751663208,
"learning_rate": 3.1862257583291896e-05,
"loss": 3.7395,
"step": 5725
},
{
"epoch": 1.2866413067800404,
"grad_norm": 10.094833374023438,
"learning_rate": 3.175866069948616e-05,
"loss": 3.6801,
"step": 5750
},
{
"epoch": 1.2922353994182143,
"grad_norm": 12.403266906738281,
"learning_rate": 3.165506381568042e-05,
"loss": 3.6891,
"step": 5775
},
{
"epoch": 1.2978294920563884,
"grad_norm": 13.569632530212402,
"learning_rate": 3.155146693187469e-05,
"loss": 3.392,
"step": 5800
},
{
"epoch": 1.3034235846945625,
"grad_norm": 10.21789836883545,
"learning_rate": 3.1447870048068956e-05,
"loss": 3.4392,
"step": 5825
},
{
"epoch": 1.3090176773327367,
"grad_norm": 9.875311851501465,
"learning_rate": 3.134427316426322e-05,
"loss": 3.6576,
"step": 5850
},
{
"epoch": 1.3146117699709108,
"grad_norm": 13.931588172912598,
"learning_rate": 3.124067628045749e-05,
"loss": 3.869,
"step": 5875
},
{
"epoch": 1.3202058626090847,
"grad_norm": 9.532690048217773,
"learning_rate": 3.113707939665175e-05,
"loss": 3.7711,
"step": 5900
},
{
"epoch": 1.325799955247259,
"grad_norm": 9.777695655822754,
"learning_rate": 3.1033482512846016e-05,
"loss": 3.4998,
"step": 5925
},
{
"epoch": 1.331394047885433,
"grad_norm": 10.633079528808594,
"learning_rate": 3.092988562904028e-05,
"loss": 3.6,
"step": 5950
},
{
"epoch": 1.336988140523607,
"grad_norm": 11.918797492980957,
"learning_rate": 3.082628874523454e-05,
"loss": 3.6084,
"step": 5975
},
{
"epoch": 1.3425822331617812,
"grad_norm": 11.27762222290039,
"learning_rate": 3.072269186142881e-05,
"loss": 3.6122,
"step": 6000
},
{
"epoch": 1.3481763257999553,
"grad_norm": 18.506898880004883,
"learning_rate": 3.0619094977623076e-05,
"loss": 3.2751,
"step": 6025
},
{
"epoch": 1.3537704184381294,
"grad_norm": 21.525028228759766,
"learning_rate": 3.051549809381734e-05,
"loss": 3.4856,
"step": 6050
},
{
"epoch": 1.3593645110763033,
"grad_norm": 13.029548645019531,
"learning_rate": 3.0411901210011606e-05,
"loss": 3.5935,
"step": 6075
},
{
"epoch": 1.3649586037144776,
"grad_norm": 9.536824226379395,
"learning_rate": 3.0308304326205873e-05,
"loss": 3.569,
"step": 6100
},
{
"epoch": 1.3705526963526515,
"grad_norm": 11.298256874084473,
"learning_rate": 3.0204707442400133e-05,
"loss": 3.8319,
"step": 6125
},
{
"epoch": 1.3761467889908257,
"grad_norm": 8.461627006530762,
"learning_rate": 3.0101110558594396e-05,
"loss": 3.7151,
"step": 6150
},
{
"epoch": 1.3817408816289998,
"grad_norm": 8.925524711608887,
"learning_rate": 2.9997513674788663e-05,
"loss": 3.5296,
"step": 6175
},
{
"epoch": 1.387334974267174,
"grad_norm": 12.109110832214355,
"learning_rate": 2.989391679098293e-05,
"loss": 3.4691,
"step": 6200
},
{
"epoch": 1.392929066905348,
"grad_norm": 9.915245056152344,
"learning_rate": 2.9790319907177193e-05,
"loss": 3.5228,
"step": 6225
},
{
"epoch": 1.398523159543522,
"grad_norm": 12.354578018188477,
"learning_rate": 2.968672302337146e-05,
"loss": 3.5543,
"step": 6250
},
{
"epoch": 1.4041172521816963,
"grad_norm": 13.05074405670166,
"learning_rate": 2.9583126139565726e-05,
"loss": 3.5762,
"step": 6275
},
{
"epoch": 1.4097113448198701,
"grad_norm": 9.809946060180664,
"learning_rate": 2.9479529255759986e-05,
"loss": 3.4119,
"step": 6300
},
{
"epoch": 1.4153054374580443,
"grad_norm": 10.61130142211914,
"learning_rate": 2.937593237195425e-05,
"loss": 3.5493,
"step": 6325
},
{
"epoch": 1.4208995300962184,
"grad_norm": 8.541769027709961,
"learning_rate": 2.9272335488148516e-05,
"loss": 3.607,
"step": 6350
},
{
"epoch": 1.4264936227343925,
"grad_norm": 14.672987937927246,
"learning_rate": 2.9168738604342783e-05,
"loss": 3.3681,
"step": 6375
},
{
"epoch": 1.4320877153725666,
"grad_norm": 16.417062759399414,
"learning_rate": 2.9065141720537046e-05,
"loss": 3.581,
"step": 6400
},
{
"epoch": 1.4376818080107405,
"grad_norm": 11.234773635864258,
"learning_rate": 2.8961544836731313e-05,
"loss": 3.8083,
"step": 6425
},
{
"epoch": 1.4432759006489149,
"grad_norm": 8.443843841552734,
"learning_rate": 2.885794795292558e-05,
"loss": 3.4413,
"step": 6450
},
{
"epoch": 1.4488699932870888,
"grad_norm": 11.358126640319824,
"learning_rate": 2.8754351069119843e-05,
"loss": 3.5337,
"step": 6475
},
{
"epoch": 1.4544640859252629,
"grad_norm": 15.18321418762207,
"learning_rate": 2.8650754185314106e-05,
"loss": 3.7784,
"step": 6500
},
{
"epoch": 1.460058178563437,
"grad_norm": 10.894759178161621,
"learning_rate": 2.854715730150837e-05,
"loss": 3.736,
"step": 6525
},
{
"epoch": 1.4656522712016111,
"grad_norm": 8.780854225158691,
"learning_rate": 2.8443560417702636e-05,
"loss": 3.5959,
"step": 6550
},
{
"epoch": 1.4712463638397852,
"grad_norm": 16.36128044128418,
"learning_rate": 2.8339963533896903e-05,
"loss": 3.6979,
"step": 6575
},
{
"epoch": 1.4768404564779591,
"grad_norm": 10.243796348571777,
"learning_rate": 2.8236366650091166e-05,
"loss": 3.6813,
"step": 6600
},
{
"epoch": 1.4824345491161335,
"grad_norm": 13.104743003845215,
"learning_rate": 2.8132769766285433e-05,
"loss": 3.6853,
"step": 6625
},
{
"epoch": 1.4880286417543074,
"grad_norm": 11.391397476196289,
"learning_rate": 2.80291728824797e-05,
"loss": 3.5911,
"step": 6650
},
{
"epoch": 1.4936227343924815,
"grad_norm": 11.6659574508667,
"learning_rate": 2.792557599867396e-05,
"loss": 3.5579,
"step": 6675
},
{
"epoch": 1.4992168270306556,
"grad_norm": 11.695647239685059,
"learning_rate": 2.7821979114868223e-05,
"loss": 3.5243,
"step": 6700
},
{
"epoch": 1.5048109196688297,
"grad_norm": 9.701094627380371,
"learning_rate": 2.771838223106249e-05,
"loss": 3.6699,
"step": 6725
},
{
"epoch": 1.5104050123070039,
"grad_norm": 15.949247360229492,
"learning_rate": 2.7614785347256757e-05,
"loss": 3.7613,
"step": 6750
},
{
"epoch": 1.5159991049451778,
"grad_norm": 13.379142761230469,
"learning_rate": 2.751118846345102e-05,
"loss": 3.7097,
"step": 6775
},
{
"epoch": 1.521593197583352,
"grad_norm": 10.693124771118164,
"learning_rate": 2.7407591579645287e-05,
"loss": 3.7779,
"step": 6800
},
{
"epoch": 1.527187290221526,
"grad_norm": 7.9651312828063965,
"learning_rate": 2.7303994695839553e-05,
"loss": 3.6414,
"step": 6825
},
{
"epoch": 1.5327813828597001,
"grad_norm": 11.157812118530273,
"learning_rate": 2.7200397812033817e-05,
"loss": 3.6576,
"step": 6850
},
{
"epoch": 1.5383754754978742,
"grad_norm": 12.323993682861328,
"learning_rate": 2.7096800928228077e-05,
"loss": 3.4723,
"step": 6875
},
{
"epoch": 1.5439695681360484,
"grad_norm": 10.302526473999023,
"learning_rate": 2.6993204044422343e-05,
"loss": 3.7213,
"step": 6900
},
{
"epoch": 1.5495636607742225,
"grad_norm": 10.622782707214355,
"learning_rate": 2.688960716061661e-05,
"loss": 3.582,
"step": 6925
},
{
"epoch": 1.5551577534123964,
"grad_norm": 12.592206001281738,
"learning_rate": 2.6786010276810873e-05,
"loss": 3.524,
"step": 6950
},
{
"epoch": 1.5607518460505707,
"grad_norm": 10.893891334533691,
"learning_rate": 2.668241339300514e-05,
"loss": 3.4272,
"step": 6975
},
{
"epoch": 1.5663459386887446,
"grad_norm": 11.728677749633789,
"learning_rate": 2.6578816509199407e-05,
"loss": 3.5618,
"step": 7000
},
{
"epoch": 1.5719400313269187,
"grad_norm": 14.411259651184082,
"learning_rate": 2.647521962539367e-05,
"loss": 3.6041,
"step": 7025
},
{
"epoch": 1.5775341239650928,
"grad_norm": 12.213258743286133,
"learning_rate": 2.6371622741587937e-05,
"loss": 3.5627,
"step": 7050
},
{
"epoch": 1.583128216603267,
"grad_norm": 12.341785430908203,
"learning_rate": 2.6268025857782197e-05,
"loss": 3.631,
"step": 7075
},
{
"epoch": 1.588722309241441,
"grad_norm": 22.097862243652344,
"learning_rate": 2.6164428973976464e-05,
"loss": 3.5977,
"step": 7100
},
{
"epoch": 1.594316401879615,
"grad_norm": 11.355073928833008,
"learning_rate": 2.6060832090170727e-05,
"loss": 3.6045,
"step": 7125
},
{
"epoch": 1.5999104945177893,
"grad_norm": 12.087318420410156,
"learning_rate": 2.5957235206364994e-05,
"loss": 3.5971,
"step": 7150
},
{
"epoch": 1.6055045871559632,
"grad_norm": 12.888108253479004,
"learning_rate": 2.585363832255926e-05,
"loss": 3.4293,
"step": 7175
},
{
"epoch": 1.6110986797941373,
"grad_norm": 11.495614051818848,
"learning_rate": 2.5750041438753524e-05,
"loss": 3.9471,
"step": 7200
},
{
"epoch": 1.6166927724323115,
"grad_norm": 12.585895538330078,
"learning_rate": 2.564644455494779e-05,
"loss": 3.5671,
"step": 7225
},
{
"epoch": 1.6222868650704856,
"grad_norm": 8.79129409790039,
"learning_rate": 2.554284767114205e-05,
"loss": 3.6453,
"step": 7250
},
{
"epoch": 1.6278809577086597,
"grad_norm": 10.552870750427246,
"learning_rate": 2.5439250787336317e-05,
"loss": 3.5649,
"step": 7275
},
{
"epoch": 1.6334750503468336,
"grad_norm": 15.649266242980957,
"learning_rate": 2.533565390353058e-05,
"loss": 3.5291,
"step": 7300
},
{
"epoch": 1.639069142985008,
"grad_norm": 13.944864273071289,
"learning_rate": 2.5232057019724847e-05,
"loss": 3.3558,
"step": 7325
},
{
"epoch": 1.6446632356231818,
"grad_norm": 14.092317581176758,
"learning_rate": 2.5128460135919114e-05,
"loss": 3.6211,
"step": 7350
},
{
"epoch": 1.650257328261356,
"grad_norm": 12.18454647064209,
"learning_rate": 2.5024863252113377e-05,
"loss": 3.7732,
"step": 7375
},
{
"epoch": 1.65585142089953,
"grad_norm": 10.779006958007812,
"learning_rate": 2.492126636830764e-05,
"loss": 3.6804,
"step": 7400
},
{
"epoch": 1.6614455135377042,
"grad_norm": 10.292470932006836,
"learning_rate": 2.4817669484501907e-05,
"loss": 3.5316,
"step": 7425
},
{
"epoch": 1.6670396061758783,
"grad_norm": 13.621623039245605,
"learning_rate": 2.4714072600696174e-05,
"loss": 3.4568,
"step": 7450
},
{
"epoch": 1.6726336988140522,
"grad_norm": 11.503890991210938,
"learning_rate": 2.4610475716890437e-05,
"loss": 3.3641,
"step": 7475
},
{
"epoch": 1.6782277914522266,
"grad_norm": 13.564423561096191,
"learning_rate": 2.45068788330847e-05,
"loss": 3.5669,
"step": 7500
},
{
"epoch": 1.6838218840904005,
"grad_norm": 9.360475540161133,
"learning_rate": 2.4403281949278967e-05,
"loss": 3.6688,
"step": 7525
},
{
"epoch": 1.6894159767285746,
"grad_norm": 13.366150856018066,
"learning_rate": 2.4299685065473234e-05,
"loss": 3.3199,
"step": 7550
},
{
"epoch": 1.6950100693667487,
"grad_norm": 10.094856262207031,
"learning_rate": 2.4196088181667497e-05,
"loss": 3.4633,
"step": 7575
},
{
"epoch": 1.7006041620049228,
"grad_norm": 9.134540557861328,
"learning_rate": 2.409249129786176e-05,
"loss": 3.6078,
"step": 7600
},
{
"epoch": 1.706198254643097,
"grad_norm": 11.252095222473145,
"learning_rate": 2.3988894414056027e-05,
"loss": 3.7198,
"step": 7625
},
{
"epoch": 1.7117923472812708,
"grad_norm": 6.201746940612793,
"learning_rate": 2.388529753025029e-05,
"loss": 3.5264,
"step": 7650
},
{
"epoch": 1.7173864399194452,
"grad_norm": 12.331997871398926,
"learning_rate": 2.3781700646444557e-05,
"loss": 3.4556,
"step": 7675
},
{
"epoch": 1.722980532557619,
"grad_norm": 12.859444618225098,
"learning_rate": 2.367810376263882e-05,
"loss": 3.4533,
"step": 7700
},
{
"epoch": 1.7285746251957932,
"grad_norm": 13.243956565856934,
"learning_rate": 2.3574506878833087e-05,
"loss": 3.7355,
"step": 7725
},
{
"epoch": 1.7341687178339673,
"grad_norm": 11.75436019897461,
"learning_rate": 2.347090999502735e-05,
"loss": 3.6108,
"step": 7750
},
{
"epoch": 1.7397628104721414,
"grad_norm": 13.429585456848145,
"learning_rate": 2.3367313111221614e-05,
"loss": 3.7925,
"step": 7775
},
{
"epoch": 1.7453569031103155,
"grad_norm": 11.077943801879883,
"learning_rate": 2.326371622741588e-05,
"loss": 3.6788,
"step": 7800
},
{
"epoch": 1.7509509957484894,
"grad_norm": 7.700258731842041,
"learning_rate": 2.3160119343610144e-05,
"loss": 3.4562,
"step": 7825
},
{
"epoch": 1.7565450883866638,
"grad_norm": 11.34974479675293,
"learning_rate": 2.305652245980441e-05,
"loss": 3.3855,
"step": 7850
},
{
"epoch": 1.7621391810248377,
"grad_norm": 11.598840713500977,
"learning_rate": 2.2952925575998674e-05,
"loss": 3.6097,
"step": 7875
},
{
"epoch": 1.7677332736630118,
"grad_norm": 11.69258975982666,
"learning_rate": 2.284932869219294e-05,
"loss": 3.6146,
"step": 7900
},
{
"epoch": 1.773327366301186,
"grad_norm": 10.501328468322754,
"learning_rate": 2.2745731808387204e-05,
"loss": 3.6597,
"step": 7925
},
{
"epoch": 1.77892145893936,
"grad_norm": 12.03715705871582,
"learning_rate": 2.264213492458147e-05,
"loss": 3.6975,
"step": 7950
},
{
"epoch": 1.7845155515775342,
"grad_norm": 13.386404991149902,
"learning_rate": 2.2538538040775734e-05,
"loss": 3.6164,
"step": 7975
},
{
"epoch": 1.790109644215708,
"grad_norm": 9.877335548400879,
"learning_rate": 2.2434941156969997e-05,
"loss": 3.614,
"step": 8000
},
{
"epoch": 1.7957037368538824,
"grad_norm": 12.025654792785645,
"learning_rate": 2.2335488148516494e-05,
"loss": 3.743,
"step": 8025
},
{
"epoch": 1.8012978294920563,
"grad_norm": 12.508997917175293,
"learning_rate": 2.2231891264710757e-05,
"loss": 3.7309,
"step": 8050
},
{
"epoch": 1.8068919221302304,
"grad_norm": 12.994415283203125,
"learning_rate": 2.2128294380905024e-05,
"loss": 3.5284,
"step": 8075
},
{
"epoch": 1.8124860147684045,
"grad_norm": 12.859843254089355,
"learning_rate": 2.202469749709929e-05,
"loss": 3.686,
"step": 8100
},
{
"epoch": 1.8180801074065787,
"grad_norm": 15.91470718383789,
"learning_rate": 2.192110061329355e-05,
"loss": 3.3395,
"step": 8125
},
{
"epoch": 1.8236742000447528,
"grad_norm": 10.755178451538086,
"learning_rate": 2.1817503729487817e-05,
"loss": 3.6407,
"step": 8150
},
{
"epoch": 1.8292682926829267,
"grad_norm": 10.679194450378418,
"learning_rate": 2.1713906845682084e-05,
"loss": 3.5509,
"step": 8175
},
{
"epoch": 1.834862385321101,
"grad_norm": 18.6633243560791,
"learning_rate": 2.1610309961876348e-05,
"loss": 3.5166,
"step": 8200
},
{
"epoch": 1.840456477959275,
"grad_norm": 7.9321112632751465,
"learning_rate": 2.150671307807061e-05,
"loss": 3.36,
"step": 8225
},
{
"epoch": 1.8460505705974493,
"grad_norm": 10.757131576538086,
"learning_rate": 2.1403116194264878e-05,
"loss": 3.4811,
"step": 8250
},
{
"epoch": 1.8516446632356232,
"grad_norm": 15.632428169250488,
"learning_rate": 2.1299519310459144e-05,
"loss": 3.5502,
"step": 8275
},
{
"epoch": 1.8572387558737973,
"grad_norm": 19.17276954650879,
"learning_rate": 2.1195922426653408e-05,
"loss": 3.5601,
"step": 8300
},
{
"epoch": 1.8628328485119714,
"grad_norm": 11.047025680541992,
"learning_rate": 2.109232554284767e-05,
"loss": 3.6373,
"step": 8325
},
{
"epoch": 1.8684269411501453,
"grad_norm": 15.699575424194336,
"learning_rate": 2.0988728659041938e-05,
"loss": 3.7378,
"step": 8350
},
{
"epoch": 1.8740210337883196,
"grad_norm": 13.09723949432373,
"learning_rate": 2.08851317752362e-05,
"loss": 3.8717,
"step": 8375
},
{
"epoch": 1.8796151264264935,
"grad_norm": 8.441289901733398,
"learning_rate": 2.0781534891430468e-05,
"loss": 3.2558,
"step": 8400
},
{
"epoch": 1.8852092190646679,
"grad_norm": 12.046778678894043,
"learning_rate": 2.067793800762473e-05,
"loss": 3.3936,
"step": 8425
},
{
"epoch": 1.8908033117028418,
"grad_norm": 10.983031272888184,
"learning_rate": 2.0574341123818998e-05,
"loss": 3.4321,
"step": 8450
},
{
"epoch": 1.896397404341016,
"grad_norm": 12.274590492248535,
"learning_rate": 2.047074424001326e-05,
"loss": 3.4638,
"step": 8475
},
{
"epoch": 1.90199149697919,
"grad_norm": 15.135939598083496,
"learning_rate": 2.0367147356207524e-05,
"loss": 3.5686,
"step": 8500
},
{
"epoch": 1.907585589617364,
"grad_norm": 11.194721221923828,
"learning_rate": 2.026355047240179e-05,
"loss": 3.7067,
"step": 8525
},
{
"epoch": 1.9131796822555382,
"grad_norm": 15.062312126159668,
"learning_rate": 2.0159953588596054e-05,
"loss": 3.5299,
"step": 8550
},
{
"epoch": 1.9187737748937121,
"grad_norm": 12.282342910766602,
"learning_rate": 2.005635670479032e-05,
"loss": 3.5803,
"step": 8575
},
{
"epoch": 1.9243678675318865,
"grad_norm": 14.33022689819336,
"learning_rate": 1.9952759820984584e-05,
"loss": 3.5835,
"step": 8600
},
{
"epoch": 1.9299619601700604,
"grad_norm": 8.249588966369629,
"learning_rate": 1.984916293717885e-05,
"loss": 3.2694,
"step": 8625
},
{
"epoch": 1.9355560528082345,
"grad_norm": 9.1649169921875,
"learning_rate": 1.9745566053373115e-05,
"loss": 3.6105,
"step": 8650
},
{
"epoch": 1.9411501454464086,
"grad_norm": 8.755537986755371,
"learning_rate": 1.964196916956738e-05,
"loss": 3.5554,
"step": 8675
},
{
"epoch": 1.9467442380845825,
"grad_norm": 8.148399353027344,
"learning_rate": 1.9538372285761645e-05,
"loss": 3.5073,
"step": 8700
},
{
"epoch": 1.9523383307227569,
"grad_norm": 10.864067077636719,
"learning_rate": 1.943477540195591e-05,
"loss": 3.6951,
"step": 8725
},
{
"epoch": 1.9579324233609308,
"grad_norm": 13.049738883972168,
"learning_rate": 1.9331178518150175e-05,
"loss": 3.5186,
"step": 8750
},
{
"epoch": 1.963526515999105,
"grad_norm": 5.955536842346191,
"learning_rate": 1.922758163434444e-05,
"loss": 3.479,
"step": 8775
},
{
"epoch": 1.969120608637279,
"grad_norm": 12.35295581817627,
"learning_rate": 1.9123984750538705e-05,
"loss": 3.5103,
"step": 8800
},
{
"epoch": 1.9747147012754531,
"grad_norm": 9.945602416992188,
"learning_rate": 1.9020387866732968e-05,
"loss": 3.6919,
"step": 8825
},
{
"epoch": 1.9803087939136272,
"grad_norm": 9.716672897338867,
"learning_rate": 1.8916790982927235e-05,
"loss": 3.7097,
"step": 8850
},
{
"epoch": 1.9859028865518011,
"grad_norm": 7.3651041984558105,
"learning_rate": 1.88131940991215e-05,
"loss": 3.4111,
"step": 8875
},
{
"epoch": 1.9914969791899755,
"grad_norm": 11.258004188537598,
"learning_rate": 1.8709597215315765e-05,
"loss": 3.4201,
"step": 8900
},
{
"epoch": 1.9970910718281494,
"grad_norm": 14.962812423706055,
"learning_rate": 1.8606000331510028e-05,
"loss": 3.4142,
"step": 8925
},
{
"epoch": 2.0,
"eval_gen_len": 61.8854,
"eval_loss": 4.248934268951416,
"eval_rouge1": 25.7685,
"eval_rouge2": 9.8226,
"eval_rougeL": 24.6426,
"eval_rougeLsum": 24.9756,
"eval_runtime": 700.259,
"eval_samples_per_second": 1.595,
"eval_steps_per_second": 0.4,
"step": 8938
}
],
"logging_steps": 25,
"max_steps": 13407,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1151792816578560.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}