Vigogne_Llama-3.1-8B-Instruct / trainer_state.json
moussaKam's picture
upload
667d69e verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9998107374929026,
"eval_steps": 500,
"global_step": 3962,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0025235000946312535,
"grad_norm": 1.4534096717834473,
"learning_rate": 1.2594458438287156e-06,
"loss": 0.9056,
"step": 10
},
{
"epoch": 0.005047000189262507,
"grad_norm": 0.9612669944763184,
"learning_rate": 2.518891687657431e-06,
"loss": 0.8732,
"step": 20
},
{
"epoch": 0.007570500283893761,
"grad_norm": 0.7495620846748352,
"learning_rate": 3.7783375314861467e-06,
"loss": 0.8402,
"step": 30
},
{
"epoch": 0.010094000378525014,
"grad_norm": 0.765338659286499,
"learning_rate": 5.037783375314862e-06,
"loss": 0.8493,
"step": 40
},
{
"epoch": 0.012617500473156268,
"grad_norm": 0.5078374147415161,
"learning_rate": 6.297229219143577e-06,
"loss": 0.79,
"step": 50
},
{
"epoch": 0.015141000567787522,
"grad_norm": 0.5078111290931702,
"learning_rate": 7.556675062972293e-06,
"loss": 0.8135,
"step": 60
},
{
"epoch": 0.017664500662418776,
"grad_norm": 0.5493185520172119,
"learning_rate": 8.816120906801008e-06,
"loss": 0.8141,
"step": 70
},
{
"epoch": 0.020188000757050028,
"grad_norm": 0.5199134945869446,
"learning_rate": 1.0075566750629725e-05,
"loss": 0.8042,
"step": 80
},
{
"epoch": 0.022711500851681284,
"grad_norm": 0.5342094898223877,
"learning_rate": 1.133501259445844e-05,
"loss": 0.7793,
"step": 90
},
{
"epoch": 0.025235000946312536,
"grad_norm": 0.4974937438964844,
"learning_rate": 1.2594458438287154e-05,
"loss": 0.7755,
"step": 100
},
{
"epoch": 0.027758501040943788,
"grad_norm": 0.6357698440551758,
"learning_rate": 1.385390428211587e-05,
"loss": 0.8445,
"step": 110
},
{
"epoch": 0.030282001135575044,
"grad_norm": 0.42305174469947815,
"learning_rate": 1.5113350125944587e-05,
"loss": 0.8141,
"step": 120
},
{
"epoch": 0.0328055012302063,
"grad_norm": 0.5842427611351013,
"learning_rate": 1.63727959697733e-05,
"loss": 0.778,
"step": 130
},
{
"epoch": 0.03532900132483755,
"grad_norm": 0.5549261569976807,
"learning_rate": 1.7632241813602016e-05,
"loss": 0.7565,
"step": 140
},
{
"epoch": 0.037852501419468804,
"grad_norm": 0.4934644401073456,
"learning_rate": 1.8891687657430733e-05,
"loss": 0.8119,
"step": 150
},
{
"epoch": 0.040376001514100056,
"grad_norm": 0.5441620945930481,
"learning_rate": 2.015113350125945e-05,
"loss": 0.799,
"step": 160
},
{
"epoch": 0.04289950160873131,
"grad_norm": 0.4513319730758667,
"learning_rate": 2.1410579345088162e-05,
"loss": 0.7748,
"step": 170
},
{
"epoch": 0.04542300170336257,
"grad_norm": 0.5183308124542236,
"learning_rate": 2.267002518891688e-05,
"loss": 0.8176,
"step": 180
},
{
"epoch": 0.04794650179799382,
"grad_norm": 0.5419854521751404,
"learning_rate": 2.392947103274559e-05,
"loss": 0.8083,
"step": 190
},
{
"epoch": 0.05047000189262507,
"grad_norm": 0.495588093996048,
"learning_rate": 2.5188916876574308e-05,
"loss": 0.8034,
"step": 200
},
{
"epoch": 0.052993501987256324,
"grad_norm": 0.5842857956886292,
"learning_rate": 2.6448362720403024e-05,
"loss": 0.7939,
"step": 210
},
{
"epoch": 0.055517002081887576,
"grad_norm": 0.47628337144851685,
"learning_rate": 2.770780856423174e-05,
"loss": 0.8022,
"step": 220
},
{
"epoch": 0.058040502176518835,
"grad_norm": 0.513734757900238,
"learning_rate": 2.8967254408060457e-05,
"loss": 0.7521,
"step": 230
},
{
"epoch": 0.06056400227115009,
"grad_norm": 0.4637106657028198,
"learning_rate": 3.0226700251889174e-05,
"loss": 0.7651,
"step": 240
},
{
"epoch": 0.06308750236578134,
"grad_norm": 0.5194531083106995,
"learning_rate": 3.148614609571788e-05,
"loss": 0.8277,
"step": 250
},
{
"epoch": 0.0656110024604126,
"grad_norm": 0.5461646318435669,
"learning_rate": 3.27455919395466e-05,
"loss": 0.8012,
"step": 260
},
{
"epoch": 0.06813450255504384,
"grad_norm": 0.525729238986969,
"learning_rate": 3.4005037783375316e-05,
"loss": 0.7945,
"step": 270
},
{
"epoch": 0.0706580026496751,
"grad_norm": 0.5770601034164429,
"learning_rate": 3.526448362720403e-05,
"loss": 0.7753,
"step": 280
},
{
"epoch": 0.07318150274430635,
"grad_norm": 0.5252787470817566,
"learning_rate": 3.652392947103275e-05,
"loss": 0.7889,
"step": 290
},
{
"epoch": 0.07570500283893761,
"grad_norm": 0.5346773266792297,
"learning_rate": 3.7783375314861465e-05,
"loss": 0.7592,
"step": 300
},
{
"epoch": 0.07822850293356887,
"grad_norm": 0.5902045965194702,
"learning_rate": 3.904282115869018e-05,
"loss": 0.8066,
"step": 310
},
{
"epoch": 0.08075200302820011,
"grad_norm": 0.5109593868255615,
"learning_rate": 4.03022670025189e-05,
"loss": 0.7715,
"step": 320
},
{
"epoch": 0.08327550312283137,
"grad_norm": 0.4999026656150818,
"learning_rate": 4.1561712846347615e-05,
"loss": 0.795,
"step": 330
},
{
"epoch": 0.08579900321746262,
"grad_norm": 0.4799485504627228,
"learning_rate": 4.2821158690176324e-05,
"loss": 0.7621,
"step": 340
},
{
"epoch": 0.08832250331209388,
"grad_norm": 0.5258325338363647,
"learning_rate": 4.408060453400504e-05,
"loss": 0.7471,
"step": 350
},
{
"epoch": 0.09084600340672513,
"grad_norm": 0.5144442319869995,
"learning_rate": 4.534005037783376e-05,
"loss": 0.7888,
"step": 360
},
{
"epoch": 0.09336950350135638,
"grad_norm": 0.5580424666404724,
"learning_rate": 4.659949622166247e-05,
"loss": 0.7865,
"step": 370
},
{
"epoch": 0.09589300359598764,
"grad_norm": 0.5704917907714844,
"learning_rate": 4.785894206549118e-05,
"loss": 0.8025,
"step": 380
},
{
"epoch": 0.09841650369061888,
"grad_norm": 0.4671490490436554,
"learning_rate": 4.91183879093199e-05,
"loss": 0.8083,
"step": 390
},
{
"epoch": 0.10094000378525014,
"grad_norm": 0.5287295579910278,
"learning_rate": 4.999991263591223e-05,
"loss": 0.7433,
"step": 400
},
{
"epoch": 0.1034635038798814,
"grad_norm": 0.5582460165023804,
"learning_rate": 4.9998359513560176e-05,
"loss": 0.7645,
"step": 410
},
{
"epoch": 0.10598700397451265,
"grad_norm": 0.48861467838287354,
"learning_rate": 4.999486510586282e-05,
"loss": 0.8056,
"step": 420
},
{
"epoch": 0.1085105040691439,
"grad_norm": 0.565294086933136,
"learning_rate": 4.9989429684183686e-05,
"loss": 0.8072,
"step": 430
},
{
"epoch": 0.11103400416377515,
"grad_norm": 0.5327048897743225,
"learning_rate": 4.9982053670618626e-05,
"loss": 0.7871,
"step": 440
},
{
"epoch": 0.11355750425840641,
"grad_norm": 0.5085189342498779,
"learning_rate": 4.997273763796312e-05,
"loss": 0.7772,
"step": 450
},
{
"epoch": 0.11608100435303767,
"grad_norm": 0.5682306885719299,
"learning_rate": 4.996148230966775e-05,
"loss": 0.7521,
"step": 460
},
{
"epoch": 0.11860450444766892,
"grad_norm": 0.5310999751091003,
"learning_rate": 4.994828855978202e-05,
"loss": 0.8276,
"step": 470
},
{
"epoch": 0.12112800454230017,
"grad_norm": 0.5132438540458679,
"learning_rate": 4.99331574128865e-05,
"loss": 0.7388,
"step": 480
},
{
"epoch": 0.12365150463693142,
"grad_norm": 0.48004600405693054,
"learning_rate": 4.991609004401324e-05,
"loss": 0.7898,
"step": 490
},
{
"epoch": 0.12617500473156268,
"grad_norm": 0.4942034184932709,
"learning_rate": 4.989708777855453e-05,
"loss": 0.7904,
"step": 500
},
{
"epoch": 0.12869850482619394,
"grad_norm": 0.4329438805580139,
"learning_rate": 4.9876152092159994e-05,
"loss": 0.8144,
"step": 510
},
{
"epoch": 0.1312220049208252,
"grad_norm": 0.4422023892402649,
"learning_rate": 4.985328461062195e-05,
"loss": 0.7894,
"step": 520
},
{
"epoch": 0.13374550501545643,
"grad_norm": 0.4740963876247406,
"learning_rate": 4.98284871097492e-05,
"loss": 0.8185,
"step": 530
},
{
"epoch": 0.1362690051100877,
"grad_norm": 0.5256137847900391,
"learning_rate": 4.98017615152291e-05,
"loss": 0.7917,
"step": 540
},
{
"epoch": 0.13879250520471895,
"grad_norm": 0.48558464646339417,
"learning_rate": 4.977310990247807e-05,
"loss": 0.7791,
"step": 550
},
{
"epoch": 0.1413160052993502,
"grad_norm": 0.5179520845413208,
"learning_rate": 4.974253449648031e-05,
"loss": 0.7854,
"step": 560
},
{
"epoch": 0.14383950539398146,
"grad_norm": 0.4606976807117462,
"learning_rate": 4.971003767161516e-05,
"loss": 0.7776,
"step": 570
},
{
"epoch": 0.1463630054886127,
"grad_norm": 0.4805031716823578,
"learning_rate": 4.9675621951472584e-05,
"loss": 0.7877,
"step": 580
},
{
"epoch": 0.14888650558324396,
"grad_norm": 0.5021762847900391,
"learning_rate": 4.9639290008657304e-05,
"loss": 0.7923,
"step": 590
},
{
"epoch": 0.15141000567787521,
"grad_norm": 0.5204519033432007,
"learning_rate": 4.960104466458118e-05,
"loss": 0.7973,
"step": 600
},
{
"epoch": 0.15393350577250647,
"grad_norm": 0.5029839277267456,
"learning_rate": 4.956088888924414e-05,
"loss": 0.766,
"step": 610
},
{
"epoch": 0.15645700586713773,
"grad_norm": 0.5078247785568237,
"learning_rate": 4.951882580100353e-05,
"loss": 0.7928,
"step": 620
},
{
"epoch": 0.15898050596176896,
"grad_norm": 0.4767574369907379,
"learning_rate": 4.947485866633199e-05,
"loss": 0.7886,
"step": 630
},
{
"epoch": 0.16150400605640022,
"grad_norm": 0.4844212234020233,
"learning_rate": 4.94289908995637e-05,
"loss": 0.7187,
"step": 640
},
{
"epoch": 0.16402750615103148,
"grad_norm": 0.4916108548641205,
"learning_rate": 4.938122606262936e-05,
"loss": 0.8031,
"step": 650
},
{
"epoch": 0.16655100624566274,
"grad_norm": 0.8660295009613037,
"learning_rate": 4.9331567864779457e-05,
"loss": 0.8129,
"step": 660
},
{
"epoch": 0.169074506340294,
"grad_norm": 0.4912508428096771,
"learning_rate": 4.928002016229634e-05,
"loss": 0.7973,
"step": 670
},
{
"epoch": 0.17159800643492523,
"grad_norm": 0.5532618165016174,
"learning_rate": 4.9226586958194647e-05,
"loss": 0.7988,
"step": 680
},
{
"epoch": 0.1741215065295565,
"grad_norm": 0.4351136386394501,
"learning_rate": 4.9171272401910504e-05,
"loss": 0.7453,
"step": 690
},
{
"epoch": 0.17664500662418775,
"grad_norm": 0.4713657796382904,
"learning_rate": 4.9114080788979284e-05,
"loss": 0.793,
"step": 700
},
{
"epoch": 0.179168506718819,
"grad_norm": 0.4904249608516693,
"learning_rate": 4.905501656070202e-05,
"loss": 0.791,
"step": 710
},
{
"epoch": 0.18169200681345027,
"grad_norm": 0.5009727478027344,
"learning_rate": 4.8994084303800525e-05,
"loss": 0.7785,
"step": 720
},
{
"epoch": 0.1842155069080815,
"grad_norm": 0.4555422365665436,
"learning_rate": 4.89312887500612e-05,
"loss": 0.7772,
"step": 730
},
{
"epoch": 0.18673900700271276,
"grad_norm": 0.4672720432281494,
"learning_rate": 4.8866634775967544e-05,
"loss": 0.7796,
"step": 740
},
{
"epoch": 0.18926250709734402,
"grad_norm": 0.42111048102378845,
"learning_rate": 4.880012740232154e-05,
"loss": 0.7741,
"step": 750
},
{
"epoch": 0.19178600719197528,
"grad_norm": 0.5067655444145203,
"learning_rate": 4.873177179385368e-05,
"loss": 0.7603,
"step": 760
},
{
"epoch": 0.19430950728660654,
"grad_norm": 0.4543984532356262,
"learning_rate": 4.866157325882192e-05,
"loss": 0.7766,
"step": 770
},
{
"epoch": 0.19683300738123777,
"grad_norm": 0.46171534061431885,
"learning_rate": 4.858953724859948e-05,
"loss": 0.7651,
"step": 780
},
{
"epoch": 0.19935650747586903,
"grad_norm": 1.1524691581726074,
"learning_rate": 4.851566935725147e-05,
"loss": 0.7538,
"step": 790
},
{
"epoch": 0.20188000757050029,
"grad_norm": 0.4468795657157898,
"learning_rate": 4.843997532110051e-05,
"loss": 0.7735,
"step": 800
},
{
"epoch": 0.20440350766513155,
"grad_norm": 0.6003584861755371,
"learning_rate": 4.836246101828124e-05,
"loss": 0.7862,
"step": 810
},
{
"epoch": 0.2069270077597628,
"grad_norm": 0.44003739953041077,
"learning_rate": 4.828313246828386e-05,
"loss": 0.8073,
"step": 820
},
{
"epoch": 0.20945050785439404,
"grad_norm": 0.4460177421569824,
"learning_rate": 4.820199583148667e-05,
"loss": 0.7788,
"step": 830
},
{
"epoch": 0.2119740079490253,
"grad_norm": 0.4435465633869171,
"learning_rate": 4.811905740867769e-05,
"loss": 0.7963,
"step": 840
},
{
"epoch": 0.21449750804365655,
"grad_norm": 0.5036677718162537,
"learning_rate": 4.803432364056535e-05,
"loss": 0.7925,
"step": 850
},
{
"epoch": 0.2170210081382878,
"grad_norm": 0.46002766489982605,
"learning_rate": 4.794780110727832e-05,
"loss": 0.7683,
"step": 860
},
{
"epoch": 0.21954450823291907,
"grad_norm": 0.4961997866630554,
"learning_rate": 4.785949652785453e-05,
"loss": 0.7911,
"step": 870
},
{
"epoch": 0.2220680083275503,
"grad_norm": 0.5581184029579163,
"learning_rate": 4.776941675971941e-05,
"loss": 0.7739,
"step": 880
},
{
"epoch": 0.22459150842218156,
"grad_norm": 0.4687346816062927,
"learning_rate": 4.767756879815334e-05,
"loss": 0.7928,
"step": 890
},
{
"epoch": 0.22711500851681282,
"grad_norm": 0.5058118104934692,
"learning_rate": 4.758395977574841e-05,
"loss": 0.8065,
"step": 900
},
{
"epoch": 0.22963850861144408,
"grad_norm": 0.49092328548431396,
"learning_rate": 4.748859696185458e-05,
"loss": 0.7966,
"step": 910
},
{
"epoch": 0.23216200870607534,
"grad_norm": 0.4792310893535614,
"learning_rate": 4.739148776201512e-05,
"loss": 0.7383,
"step": 920
},
{
"epoch": 0.23468550880070657,
"grad_norm": 0.4560384750366211,
"learning_rate": 4.729263971739154e-05,
"loss": 0.7869,
"step": 930
},
{
"epoch": 0.23720900889533783,
"grad_norm": 0.46963706612586975,
"learning_rate": 4.719206050417796e-05,
"loss": 0.7748,
"step": 940
},
{
"epoch": 0.2397325089899691,
"grad_norm": 0.4931532144546509,
"learning_rate": 4.7089757933005016e-05,
"loss": 0.7747,
"step": 950
},
{
"epoch": 0.24225600908460035,
"grad_norm": 0.4691235423088074,
"learning_rate": 4.698573994833332e-05,
"loss": 0.7725,
"step": 960
},
{
"epoch": 0.2447795091792316,
"grad_norm": 0.44244667887687683,
"learning_rate": 4.688001462783648e-05,
"loss": 0.7564,
"step": 970
},
{
"epoch": 0.24730300927386284,
"grad_norm": 0.5181055068969727,
"learning_rate": 4.6772590181773866e-05,
"loss": 0.7407,
"step": 980
},
{
"epoch": 0.2498265093684941,
"grad_norm": 0.4613230526447296,
"learning_rate": 4.6663474952353004e-05,
"loss": 0.7437,
"step": 990
},
{
"epoch": 0.25235000946312536,
"grad_norm": 0.5326347351074219,
"learning_rate": 4.6552677413081756e-05,
"loss": 0.809,
"step": 1000
},
{
"epoch": 0.2548735095577566,
"grad_norm": 0.516962468624115,
"learning_rate": 4.644020616811029e-05,
"loss": 0.7867,
"step": 1010
},
{
"epoch": 0.2573970096523879,
"grad_norm": 0.5326249003410339,
"learning_rate": 4.6326069951562924e-05,
"loss": 0.8096,
"step": 1020
},
{
"epoch": 0.25992050974701914,
"grad_norm": 0.42123785614967346,
"learning_rate": 4.6210277626859856e-05,
"loss": 0.7241,
"step": 1030
},
{
"epoch": 0.2624440098416504,
"grad_norm": 0.40459808707237244,
"learning_rate": 4.609283818602884e-05,
"loss": 0.7797,
"step": 1040
},
{
"epoch": 0.2649675099362816,
"grad_norm": 0.4971398115158081,
"learning_rate": 4.5973760749006963e-05,
"loss": 0.7898,
"step": 1050
},
{
"epoch": 0.26749101003091286,
"grad_norm": 0.4381590485572815,
"learning_rate": 4.585305456293235e-05,
"loss": 0.8102,
"step": 1060
},
{
"epoch": 0.2700145101255441,
"grad_norm": 0.6431146264076233,
"learning_rate": 4.5730729001426083e-05,
"loss": 0.7927,
"step": 1070
},
{
"epoch": 0.2725380102201754,
"grad_norm": 0.46233826875686646,
"learning_rate": 4.5606793563864316e-05,
"loss": 0.7656,
"step": 1080
},
{
"epoch": 0.27506151031480663,
"grad_norm": 0.5226401090621948,
"learning_rate": 4.548125787464054e-05,
"loss": 0.7587,
"step": 1090
},
{
"epoch": 0.2775850104094379,
"grad_norm": 0.4273032248020172,
"learning_rate": 4.535413168241821e-05,
"loss": 0.7697,
"step": 1100
},
{
"epoch": 0.28010851050406915,
"grad_norm": 0.4383103549480438,
"learning_rate": 4.522542485937369e-05,
"loss": 0.8039,
"step": 1110
},
{
"epoch": 0.2826320105987004,
"grad_norm": 0.4111369848251343,
"learning_rate": 4.509514740042962e-05,
"loss": 0.7707,
"step": 1120
},
{
"epoch": 0.28515551069333167,
"grad_norm": 0.5138412117958069,
"learning_rate": 4.496330942247873e-05,
"loss": 0.7785,
"step": 1130
},
{
"epoch": 0.28767901078796293,
"grad_norm": 0.49675437808036804,
"learning_rate": 4.482992116359824e-05,
"loss": 0.763,
"step": 1140
},
{
"epoch": 0.29020251088259413,
"grad_norm": 0.4325181841850281,
"learning_rate": 4.469499298225473e-05,
"loss": 0.7344,
"step": 1150
},
{
"epoch": 0.2927260109772254,
"grad_norm": 0.45691972970962524,
"learning_rate": 4.455853535649984e-05,
"loss": 0.7628,
"step": 1160
},
{
"epoch": 0.29524951107185665,
"grad_norm": 0.45635420083999634,
"learning_rate": 4.442055888315646e-05,
"loss": 0.7666,
"step": 1170
},
{
"epoch": 0.2977730111664879,
"grad_norm": 0.44449037313461304,
"learning_rate": 4.4281074276995936e-05,
"loss": 0.7308,
"step": 1180
},
{
"epoch": 0.30029651126111917,
"grad_norm": 0.4645417332649231,
"learning_rate": 4.4140092369905914e-05,
"loss": 0.7385,
"step": 1190
},
{
"epoch": 0.30282001135575043,
"grad_norm": 0.4081282913684845,
"learning_rate": 4.399762411004922e-05,
"loss": 0.7754,
"step": 1200
},
{
"epoch": 0.3053435114503817,
"grad_norm": 0.5219441652297974,
"learning_rate": 4.3853680561013647e-05,
"loss": 0.7903,
"step": 1210
},
{
"epoch": 0.30786701154501295,
"grad_norm": 0.48942479491233826,
"learning_rate": 4.370827290095277e-05,
"loss": 0.7693,
"step": 1220
},
{
"epoch": 0.3103905116396442,
"grad_norm": 0.4511029124259949,
"learning_rate": 4.356141242171795e-05,
"loss": 0.7685,
"step": 1230
},
{
"epoch": 0.31291401173427547,
"grad_norm": 0.46076688170433044,
"learning_rate": 4.3413110527981406e-05,
"loss": 0.745,
"step": 1240
},
{
"epoch": 0.31543751182890667,
"grad_norm": 0.5077107548713684,
"learning_rate": 4.3263378736350566e-05,
"loss": 0.7679,
"step": 1250
},
{
"epoch": 0.31796101192353793,
"grad_norm": 0.4735719561576843,
"learning_rate": 4.311222867447375e-05,
"loss": 0.8021,
"step": 1260
},
{
"epoch": 0.3204845120181692,
"grad_norm": 0.49257341027259827,
"learning_rate": 4.295967208013717e-05,
"loss": 0.7619,
"step": 1270
},
{
"epoch": 0.32300801211280045,
"grad_norm": 0.45219412446022034,
"learning_rate": 4.280572080035348e-05,
"loss": 0.7656,
"step": 1280
},
{
"epoch": 0.3255315122074317,
"grad_norm": 0.4800606369972229,
"learning_rate": 4.2650386790441696e-05,
"loss": 0.7618,
"step": 1290
},
{
"epoch": 0.32805501230206296,
"grad_norm": 0.5180128812789917,
"learning_rate": 4.2493682113098855e-05,
"loss": 0.766,
"step": 1300
},
{
"epoch": 0.3305785123966942,
"grad_norm": 0.45564642548561096,
"learning_rate": 4.233561893746323e-05,
"loss": 0.7944,
"step": 1310
},
{
"epoch": 0.3331020124913255,
"grad_norm": 0.46252918243408203,
"learning_rate": 4.217620953816935e-05,
"loss": 0.749,
"step": 1320
},
{
"epoch": 0.33562551258595674,
"grad_norm": 0.531288743019104,
"learning_rate": 4.2015466294394756e-05,
"loss": 0.7869,
"step": 1330
},
{
"epoch": 0.338149012680588,
"grad_norm": 0.5134521722793579,
"learning_rate": 4.185340168889868e-05,
"loss": 0.7568,
"step": 1340
},
{
"epoch": 0.3406725127752192,
"grad_norm": 0.43066537380218506,
"learning_rate": 4.169002830705274e-05,
"loss": 0.7527,
"step": 1350
},
{
"epoch": 0.34319601286985046,
"grad_norm": 0.4531955122947693,
"learning_rate": 4.152535883586352e-05,
"loss": 0.738,
"step": 1360
},
{
"epoch": 0.3457195129644817,
"grad_norm": 0.4627138376235962,
"learning_rate": 4.135940606298738e-05,
"loss": 0.7441,
"step": 1370
},
{
"epoch": 0.348243013059113,
"grad_norm": 0.4333173632621765,
"learning_rate": 4.119218287573743e-05,
"loss": 0.7344,
"step": 1380
},
{
"epoch": 0.35076651315374424,
"grad_norm": 0.421912282705307,
"learning_rate": 4.102370226008271e-05,
"loss": 0.7828,
"step": 1390
},
{
"epoch": 0.3532900132483755,
"grad_norm": 0.4382674992084503,
"learning_rate": 4.085397729963976e-05,
"loss": 0.7526,
"step": 1400
},
{
"epoch": 0.35581351334300676,
"grad_norm": 0.4683435559272766,
"learning_rate": 4.06830211746566e-05,
"loss": 0.7804,
"step": 1410
},
{
"epoch": 0.358337013437638,
"grad_norm": 0.49529722332954407,
"learning_rate": 4.051084716098921e-05,
"loss": 0.7565,
"step": 1420
},
{
"epoch": 0.3608605135322693,
"grad_norm": 0.454121470451355,
"learning_rate": 4.0337468629070496e-05,
"loss": 0.7667,
"step": 1430
},
{
"epoch": 0.36338401362690054,
"grad_norm": 0.45073944330215454,
"learning_rate": 4.016289904287212e-05,
"loss": 0.7543,
"step": 1440
},
{
"epoch": 0.36590751372153174,
"grad_norm": 0.5012348890304565,
"learning_rate": 3.9987151958858794e-05,
"loss": 0.7642,
"step": 1450
},
{
"epoch": 0.368431013816163,
"grad_norm": 0.45489585399627686,
"learning_rate": 3.981024102493566e-05,
"loss": 0.7355,
"step": 1460
},
{
"epoch": 0.37095451391079426,
"grad_norm": 0.49024873971939087,
"learning_rate": 3.963217997938834e-05,
"loss": 0.7656,
"step": 1470
},
{
"epoch": 0.3734780140054255,
"grad_norm": 0.4967275857925415,
"learning_rate": 3.945298264981614e-05,
"loss": 0.7493,
"step": 1480
},
{
"epoch": 0.3760015141000568,
"grad_norm": 0.48888593912124634,
"learning_rate": 3.927266295205818e-05,
"loss": 0.7741,
"step": 1490
},
{
"epoch": 0.37852501419468804,
"grad_norm": 0.44507086277008057,
"learning_rate": 3.9091234889112815e-05,
"loss": 0.7632,
"step": 1500
},
{
"epoch": 0.3810485142893193,
"grad_norm": 0.4503888785839081,
"learning_rate": 3.8908712550050154e-05,
"loss": 0.7605,
"step": 1510
},
{
"epoch": 0.38357201438395055,
"grad_norm": 0.42421767115592957,
"learning_rate": 3.8725110108917975e-05,
"loss": 0.7325,
"step": 1520
},
{
"epoch": 0.3860955144785818,
"grad_norm": 0.45737549662590027,
"learning_rate": 3.854044182364098e-05,
"loss": 0.7644,
"step": 1530
},
{
"epoch": 0.3886190145732131,
"grad_norm": 0.46508800983428955,
"learning_rate": 3.835472203491367e-05,
"loss": 0.7492,
"step": 1540
},
{
"epoch": 0.3911425146678443,
"grad_norm": 0.42231640219688416,
"learning_rate": 3.816796516508658e-05,
"loss": 0.7495,
"step": 1550
},
{
"epoch": 0.39366601476247554,
"grad_norm": 0.44611889123916626,
"learning_rate": 3.798018571704638e-05,
"loss": 0.7468,
"step": 1560
},
{
"epoch": 0.3961895148571068,
"grad_norm": 0.4249905049800873,
"learning_rate": 3.779139827308956e-05,
"loss": 0.7757,
"step": 1570
},
{
"epoch": 0.39871301495173805,
"grad_norm": 0.46931806206703186,
"learning_rate": 3.760161749379008e-05,
"loss": 0.7576,
"step": 1580
},
{
"epoch": 0.4012365150463693,
"grad_norm": 0.4227593243122101,
"learning_rate": 3.7410858116860836e-05,
"loss": 0.7415,
"step": 1590
},
{
"epoch": 0.40376001514100057,
"grad_norm": 0.4338664710521698,
"learning_rate": 3.721913495600923e-05,
"loss": 0.7676,
"step": 1600
},
{
"epoch": 0.40628351523563183,
"grad_norm": 0.4017735719680786,
"learning_rate": 3.7026462899786726e-05,
"loss": 0.7171,
"step": 1610
},
{
"epoch": 0.4088070153302631,
"grad_norm": 0.4449094235897064,
"learning_rate": 3.683285691043272e-05,
"loss": 0.7617,
"step": 1620
},
{
"epoch": 0.41133051542489435,
"grad_norm": 0.4355940818786621,
"learning_rate": 3.663833202271257e-05,
"loss": 0.7616,
"step": 1630
},
{
"epoch": 0.4138540155195256,
"grad_norm": 0.4568544328212738,
"learning_rate": 3.6442903342750084e-05,
"loss": 0.7141,
"step": 1640
},
{
"epoch": 0.4163775156141568,
"grad_norm": 0.46118539571762085,
"learning_rate": 3.624658604685443e-05,
"loss": 0.7347,
"step": 1650
},
{
"epoch": 0.41890101570878807,
"grad_norm": 0.49249446392059326,
"learning_rate": 3.604939538034158e-05,
"loss": 0.7557,
"step": 1660
},
{
"epoch": 0.42142451580341933,
"grad_norm": 0.5076271891593933,
"learning_rate": 3.585134665635041e-05,
"loss": 0.7512,
"step": 1670
},
{
"epoch": 0.4239480158980506,
"grad_norm": 0.4391838312149048,
"learning_rate": 3.565245525465355e-05,
"loss": 0.782,
"step": 1680
},
{
"epoch": 0.42647151599268185,
"grad_norm": 0.43777164816856384,
"learning_rate": 3.5452736620463064e-05,
"loss": 0.7442,
"step": 1690
},
{
"epoch": 0.4289950160873131,
"grad_norm": 0.4787698984146118,
"learning_rate": 3.525220626323097e-05,
"loss": 0.7263,
"step": 1700
},
{
"epoch": 0.43151851618194437,
"grad_norm": 0.4493311941623688,
"learning_rate": 3.5050879755444877e-05,
"loss": 0.7771,
"step": 1710
},
{
"epoch": 0.4340420162765756,
"grad_norm": 0.4277406334877014,
"learning_rate": 3.484877273141866e-05,
"loss": 0.7533,
"step": 1720
},
{
"epoch": 0.4365655163712069,
"grad_norm": 0.44397228956222534,
"learning_rate": 3.464590088607839e-05,
"loss": 0.7581,
"step": 1730
},
{
"epoch": 0.43908901646583814,
"grad_norm": 0.4278891086578369,
"learning_rate": 3.444227997374345e-05,
"loss": 0.7726,
"step": 1740
},
{
"epoch": 0.44161251656046935,
"grad_norm": 0.4884257912635803,
"learning_rate": 3.4237925806903184e-05,
"loss": 0.7537,
"step": 1750
},
{
"epoch": 0.4441360166551006,
"grad_norm": 0.39494335651397705,
"learning_rate": 3.403285425498889e-05,
"loss": 0.7513,
"step": 1760
},
{
"epoch": 0.44665951674973187,
"grad_norm": 0.4903046488761902,
"learning_rate": 3.3827081243141534e-05,
"loss": 0.7259,
"step": 1770
},
{
"epoch": 0.4491830168443631,
"grad_norm": 0.47485992312431335,
"learning_rate": 3.362062275097496e-05,
"loss": 0.7674,
"step": 1780
},
{
"epoch": 0.4517065169389944,
"grad_norm": 0.47219303250312805,
"learning_rate": 3.341349481133507e-05,
"loss": 0.7234,
"step": 1790
},
{
"epoch": 0.45423001703362564,
"grad_norm": 0.4186359643936157,
"learning_rate": 3.320571350905466e-05,
"loss": 0.7587,
"step": 1800
},
{
"epoch": 0.4567535171282569,
"grad_norm": 0.4978404641151428,
"learning_rate": 3.299729497970444e-05,
"loss": 0.7754,
"step": 1810
},
{
"epoch": 0.45927701722288816,
"grad_norm": 0.45416682958602905,
"learning_rate": 3.278825540833995e-05,
"loss": 0.7464,
"step": 1820
},
{
"epoch": 0.4618005173175194,
"grad_norm": 0.433159202337265,
"learning_rate": 3.2578611028244656e-05,
"loss": 0.7355,
"step": 1830
},
{
"epoch": 0.4643240174121507,
"grad_norm": 0.47343000769615173,
"learning_rate": 3.2368378119669363e-05,
"loss": 0.7115,
"step": 1840
},
{
"epoch": 0.4668475175067819,
"grad_norm": 0.39492008090019226,
"learning_rate": 3.215757300856796e-05,
"loss": 0.731,
"step": 1850
},
{
"epoch": 0.46937101760141314,
"grad_norm": 0.4586881697177887,
"learning_rate": 3.194621206532957e-05,
"loss": 0.7729,
"step": 1860
},
{
"epoch": 0.4718945176960444,
"grad_norm": 0.5566070675849915,
"learning_rate": 3.173431170350732e-05,
"loss": 0.7454,
"step": 1870
},
{
"epoch": 0.47441801779067566,
"grad_norm": 0.44794589281082153,
"learning_rate": 3.152188837854369e-05,
"loss": 0.7682,
"step": 1880
},
{
"epoch": 0.4769415178853069,
"grad_norm": 0.45499035716056824,
"learning_rate": 3.130895858649264e-05,
"loss": 0.7243,
"step": 1890
},
{
"epoch": 0.4794650179799382,
"grad_norm": 0.4766923487186432,
"learning_rate": 3.109553886273863e-05,
"loss": 0.7582,
"step": 1900
},
{
"epoch": 0.48198851807456944,
"grad_norm": 0.4546712040901184,
"learning_rate": 3.088164578071246e-05,
"loss": 0.7318,
"step": 1910
},
{
"epoch": 0.4845120181692007,
"grad_norm": 0.46813201904296875,
"learning_rate": 3.066729595060431e-05,
"loss": 0.7199,
"step": 1920
},
{
"epoch": 0.48703551826383196,
"grad_norm": 0.5136599540710449,
"learning_rate": 3.0452506018073833e-05,
"loss": 0.7531,
"step": 1930
},
{
"epoch": 0.4895590183584632,
"grad_norm": 0.48750588297843933,
"learning_rate": 3.0237292662957473e-05,
"loss": 0.7373,
"step": 1940
},
{
"epoch": 0.4920825184530944,
"grad_norm": 0.42763668298721313,
"learning_rate": 3.0021672597973207e-05,
"loss": 0.7256,
"step": 1950
},
{
"epoch": 0.4946060185477257,
"grad_norm": 0.44293949007987976,
"learning_rate": 2.9805662567422676e-05,
"loss": 0.7644,
"step": 1960
},
{
"epoch": 0.49712951864235694,
"grad_norm": 0.5033817887306213,
"learning_rate": 2.9589279345890895e-05,
"loss": 0.7521,
"step": 1970
},
{
"epoch": 0.4996530187369882,
"grad_norm": 0.3790980577468872,
"learning_rate": 2.9372539736943577e-05,
"loss": 0.7437,
"step": 1980
},
{
"epoch": 0.5021765188316195,
"grad_norm": 0.3884977400302887,
"learning_rate": 2.9155460571822245e-05,
"loss": 0.7309,
"step": 1990
},
{
"epoch": 0.5047000189262507,
"grad_norm": 0.4705371558666229,
"learning_rate": 2.893805870813717e-05,
"loss": 0.7223,
"step": 2000
},
{
"epoch": 0.5072235190208819,
"grad_norm": 0.42519432306289673,
"learning_rate": 2.872035102855826e-05,
"loss": 0.7247,
"step": 2010
},
{
"epoch": 0.5097470191155132,
"grad_norm": 0.4545595347881317,
"learning_rate": 2.850235443950402e-05,
"loss": 0.7047,
"step": 2020
},
{
"epoch": 0.5122705192101444,
"grad_norm": 0.4008665382862091,
"learning_rate": 2.8284085869828665e-05,
"loss": 0.7417,
"step": 2030
},
{
"epoch": 0.5147940193047758,
"grad_norm": 0.4608813226222992,
"learning_rate": 2.8065562269507463e-05,
"loss": 0.7508,
"step": 2040
},
{
"epoch": 0.517317519399407,
"grad_norm": 0.5732349157333374,
"learning_rate": 2.7846800608320485e-05,
"loss": 0.7352,
"step": 2050
},
{
"epoch": 0.5198410194940383,
"grad_norm": 0.39458563923835754,
"learning_rate": 2.7627817874534762e-05,
"loss": 0.7205,
"step": 2060
},
{
"epoch": 0.5223645195886695,
"grad_norm": 0.473949670791626,
"learning_rate": 2.7408631073585068e-05,
"loss": 0.7096,
"step": 2070
},
{
"epoch": 0.5248880196833008,
"grad_norm": 0.45874857902526855,
"learning_rate": 2.7189257226753305e-05,
"loss": 0.7349,
"step": 2080
},
{
"epoch": 0.527411519777932,
"grad_norm": 0.41197165846824646,
"learning_rate": 2.696971336984672e-05,
"loss": 0.7522,
"step": 2090
},
{
"epoch": 0.5299350198725632,
"grad_norm": 0.5001893639564514,
"learning_rate": 2.6750016551874945e-05,
"loss": 0.7249,
"step": 2100
},
{
"epoch": 0.5324585199671945,
"grad_norm": 0.4561350345611572,
"learning_rate": 2.6530183833726025e-05,
"loss": 0.732,
"step": 2110
},
{
"epoch": 0.5349820200618257,
"grad_norm": 0.4732155203819275,
"learning_rate": 2.6310232286841546e-05,
"loss": 0.7581,
"step": 2120
},
{
"epoch": 0.537505520156457,
"grad_norm": 0.44940948486328125,
"learning_rate": 2.609017899189092e-05,
"loss": 0.7439,
"step": 2130
},
{
"epoch": 0.5400290202510882,
"grad_norm": 0.4435223639011383,
"learning_rate": 2.587004103744495e-05,
"loss": 0.7016,
"step": 2140
},
{
"epoch": 0.5425525203457195,
"grad_norm": 0.4022032618522644,
"learning_rate": 2.564983551864882e-05,
"loss": 0.7124,
"step": 2150
},
{
"epoch": 0.5450760204403508,
"grad_norm": 0.5092436671257019,
"learning_rate": 2.54295795358945e-05,
"loss": 0.7355,
"step": 2160
},
{
"epoch": 0.5475995205349821,
"grad_norm": 0.43439218401908875,
"learning_rate": 2.5209290193492834e-05,
"loss": 0.7301,
"step": 2170
},
{
"epoch": 0.5501230206296133,
"grad_norm": 0.4191984236240387,
"learning_rate": 2.4988984598345247e-05,
"loss": 0.6951,
"step": 2180
},
{
"epoch": 0.5526465207242445,
"grad_norm": 0.42209818959236145,
"learning_rate": 2.4768679858615304e-05,
"loss": 0.746,
"step": 2190
},
{
"epoch": 0.5551700208188758,
"grad_norm": 0.49302446842193604,
"learning_rate": 2.454839308240014e-05,
"loss": 0.7687,
"step": 2200
},
{
"epoch": 0.557693520913507,
"grad_norm": 0.46349719166755676,
"learning_rate": 2.4328141376401903e-05,
"loss": 0.7203,
"step": 2210
},
{
"epoch": 0.5602170210081383,
"grad_norm": 0.4288594722747803,
"learning_rate": 2.4107941844599312e-05,
"loss": 0.709,
"step": 2220
},
{
"epoch": 0.5627405211027695,
"grad_norm": 0.42657721042633057,
"learning_rate": 2.3887811586919424e-05,
"loss": 0.7385,
"step": 2230
},
{
"epoch": 0.5652640211974008,
"grad_norm": 0.447419673204422,
"learning_rate": 2.3667767697909694e-05,
"loss": 0.7199,
"step": 2240
},
{
"epoch": 0.567787521292032,
"grad_norm": 0.460227906703949,
"learning_rate": 2.3447827265410517e-05,
"loss": 0.76,
"step": 2250
},
{
"epoch": 0.5703110213866633,
"grad_norm": 0.48693689703941345,
"learning_rate": 2.3228007369228178e-05,
"loss": 0.7893,
"step": 2260
},
{
"epoch": 0.5728345214812945,
"grad_norm": 0.4543781578540802,
"learning_rate": 2.3008325079808576e-05,
"loss": 0.7431,
"step": 2270
},
{
"epoch": 0.5753580215759259,
"grad_norm": 0.44196173548698425,
"learning_rate": 2.2788797456911503e-05,
"loss": 0.7024,
"step": 2280
},
{
"epoch": 0.5778815216705571,
"grad_norm": 0.4773748517036438,
"learning_rate": 2.2569441548285934e-05,
"loss": 0.7366,
"step": 2290
},
{
"epoch": 0.5804050217651883,
"grad_norm": 0.35127493739128113,
"learning_rate": 2.2350274388346064e-05,
"loss": 0.6932,
"step": 2300
},
{
"epoch": 0.5829285218598196,
"grad_norm": 0.4260622262954712,
"learning_rate": 2.213131299684858e-05,
"loss": 0.7481,
"step": 2310
},
{
"epoch": 0.5854520219544508,
"grad_norm": 0.49954676628112793,
"learning_rate": 2.191257437757086e-05,
"loss": 0.7196,
"step": 2320
},
{
"epoch": 0.5879755220490821,
"grad_norm": 0.41478589177131653,
"learning_rate": 2.16940755169906e-05,
"loss": 0.744,
"step": 2330
},
{
"epoch": 0.5904990221437133,
"grad_norm": 0.4980543255805969,
"learning_rate": 2.1475833382966647e-05,
"loss": 0.7798,
"step": 2340
},
{
"epoch": 0.5930225222383446,
"grad_norm": 0.4331112802028656,
"learning_rate": 2.1257864923421404e-05,
"loss": 0.7616,
"step": 2350
},
{
"epoch": 0.5955460223329758,
"grad_norm": 0.38317206501960754,
"learning_rate": 2.1040187065024605e-05,
"loss": 0.6863,
"step": 2360
},
{
"epoch": 0.5980695224276071,
"grad_norm": 0.44444334506988525,
"learning_rate": 2.0822816711878978e-05,
"loss": 0.7482,
"step": 2370
},
{
"epoch": 0.6005930225222383,
"grad_norm": 0.47149887681007385,
"learning_rate": 2.0605770744207413e-05,
"loss": 0.7289,
"step": 2380
},
{
"epoch": 0.6031165226168695,
"grad_norm": 0.4344223737716675,
"learning_rate": 2.0389066017042192e-05,
"loss": 0.708,
"step": 2390
},
{
"epoch": 0.6056400227115009,
"grad_norm": 0.8328418135643005,
"learning_rate": 2.0172719358916042e-05,
"loss": 0.709,
"step": 2400
},
{
"epoch": 0.6081635228061321,
"grad_norm": 0.4812801480293274,
"learning_rate": 1.9956747570555288e-05,
"loss": 0.7526,
"step": 2410
},
{
"epoch": 0.6106870229007634,
"grad_norm": 0.43277397751808167,
"learning_rate": 1.9741167423575186e-05,
"loss": 0.6928,
"step": 2420
},
{
"epoch": 0.6132105229953946,
"grad_norm": 0.41379523277282715,
"learning_rate": 1.9525995659177484e-05,
"loss": 0.7236,
"step": 2430
},
{
"epoch": 0.6157340230900259,
"grad_norm": 0.4115571081638336,
"learning_rate": 1.9311248986850365e-05,
"loss": 0.7191,
"step": 2440
},
{
"epoch": 0.6182575231846571,
"grad_norm": 0.4394511282444,
"learning_rate": 1.9096944083070866e-05,
"loss": 0.7345,
"step": 2450
},
{
"epoch": 0.6207810232792884,
"grad_norm": 0.46809184551239014,
"learning_rate": 1.8883097590009775e-05,
"loss": 0.7342,
"step": 2460
},
{
"epoch": 0.6233045233739196,
"grad_norm": 0.4622188210487366,
"learning_rate": 1.866972611423936e-05,
"loss": 0.7239,
"step": 2470
},
{
"epoch": 0.6258280234685509,
"grad_norm": 0.5006013512611389,
"learning_rate": 1.8456846225443648e-05,
"loss": 0.6781,
"step": 2480
},
{
"epoch": 0.6283515235631821,
"grad_norm": 0.43140849471092224,
"learning_rate": 1.8244474455131792e-05,
"loss": 0.7201,
"step": 2490
},
{
"epoch": 0.6308750236578133,
"grad_norm": 0.44335806369781494,
"learning_rate": 1.8032627295354183e-05,
"loss": 0.7117,
"step": 2500
},
{
"epoch": 0.6333985237524447,
"grad_norm": 0.5342260003089905,
"learning_rate": 1.7821321197421837e-05,
"loss": 0.7597,
"step": 2510
},
{
"epoch": 0.6359220238470759,
"grad_norm": 0.46154212951660156,
"learning_rate": 1.761057257062876e-05,
"loss": 0.7391,
"step": 2520
},
{
"epoch": 0.6384455239417072,
"grad_norm": 0.4077001214027405,
"learning_rate": 1.740039778097772e-05,
"loss": 0.6893,
"step": 2530
},
{
"epoch": 0.6409690240363384,
"grad_norm": 0.4284549057483673,
"learning_rate": 1.7190813149909274e-05,
"loss": 0.7196,
"step": 2540
},
{
"epoch": 0.6434925241309697,
"grad_norm": 0.4528105556964874,
"learning_rate": 1.6981834953034344e-05,
"loss": 0.7245,
"step": 2550
},
{
"epoch": 0.6460160242256009,
"grad_norm": 0.46201303601264954,
"learning_rate": 1.677347941887028e-05,
"loss": 0.6907,
"step": 2560
},
{
"epoch": 0.6485395243202322,
"grad_norm": 0.4665580987930298,
"learning_rate": 1.656576272758061e-05,
"loss": 0.7494,
"step": 2570
},
{
"epoch": 0.6510630244148634,
"grad_norm": 0.44148868322372437,
"learning_rate": 1.6358701009718577e-05,
"loss": 0.7224,
"step": 2580
},
{
"epoch": 0.6535865245094946,
"grad_norm": 0.41278114914894104,
"learning_rate": 1.615231034497444e-05,
"loss": 0.7381,
"step": 2590
},
{
"epoch": 0.6561100246041259,
"grad_norm": 0.4944005012512207,
"learning_rate": 1.5946606760926865e-05,
"loss": 0.7103,
"step": 2600
},
{
"epoch": 0.6586335246987571,
"grad_norm": 0.5193942785263062,
"learning_rate": 1.574160623179816e-05,
"loss": 0.7289,
"step": 2610
},
{
"epoch": 0.6611570247933884,
"grad_norm": 0.47881239652633667,
"learning_rate": 1.553732467721392e-05,
"loss": 0.6884,
"step": 2620
},
{
"epoch": 0.6636805248880197,
"grad_norm": 0.3865389823913574,
"learning_rate": 1.5333777960966616e-05,
"loss": 0.6947,
"step": 2630
},
{
"epoch": 0.666204024982651,
"grad_norm": 0.41780009865760803,
"learning_rate": 1.5130981889783795e-05,
"loss": 0.7063,
"step": 2640
},
{
"epoch": 0.6687275250772822,
"grad_norm": 0.4426202178001404,
"learning_rate": 1.4928952212100483e-05,
"loss": 0.7349,
"step": 2650
},
{
"epoch": 0.6712510251719135,
"grad_norm": 0.4114045202732086,
"learning_rate": 1.4727704616836296e-05,
"loss": 0.7294,
"step": 2660
},
{
"epoch": 0.6737745252665447,
"grad_norm": 0.44464120268821716,
"learning_rate": 1.4527254732177043e-05,
"loss": 0.717,
"step": 2670
},
{
"epoch": 0.676298025361176,
"grad_norm": 0.4169268012046814,
"learning_rate": 1.4327618124361114e-05,
"loss": 0.722,
"step": 2680
},
{
"epoch": 0.6788215254558072,
"grad_norm": 0.42548105120658875,
"learning_rate": 1.412881029647065e-05,
"loss": 0.687,
"step": 2690
},
{
"epoch": 0.6813450255504384,
"grad_norm": 0.4200035631656647,
"learning_rate": 1.3930846687227664e-05,
"loss": 0.7011,
"step": 2700
},
{
"epoch": 0.6838685256450697,
"grad_norm": 0.43831759691238403,
"learning_rate": 1.3733742669795049e-05,
"loss": 0.7447,
"step": 2710
},
{
"epoch": 0.6863920257397009,
"grad_norm": 0.4923849403858185,
"learning_rate": 1.3537513550582853e-05,
"loss": 0.7263,
"step": 2720
},
{
"epoch": 0.6889155258343322,
"grad_norm": 0.4158725142478943,
"learning_rate": 1.3342174568059527e-05,
"loss": 0.7009,
"step": 2730
},
{
"epoch": 0.6914390259289634,
"grad_norm": 0.4092692732810974,
"learning_rate": 1.3147740891568661e-05,
"loss": 0.6921,
"step": 2740
},
{
"epoch": 0.6939625260235948,
"grad_norm": 0.43437299132347107,
"learning_rate": 1.2954227620150904e-05,
"loss": 0.7377,
"step": 2750
},
{
"epoch": 0.696486026118226,
"grad_norm": 0.45701101422309875,
"learning_rate": 1.2761649781371479e-05,
"loss": 0.7088,
"step": 2760
},
{
"epoch": 0.6990095262128573,
"grad_norm": 0.42999330163002014,
"learning_rate": 1.257002233015318e-05,
"loss": 0.7286,
"step": 2770
},
{
"epoch": 0.7015330263074885,
"grad_norm": 0.4685601592063904,
"learning_rate": 1.2379360147614994e-05,
"loss": 0.7034,
"step": 2780
},
{
"epoch": 0.7040565264021197,
"grad_norm": 0.4414807856082916,
"learning_rate": 1.2189678039916532e-05,
"loss": 0.6826,
"step": 2790
},
{
"epoch": 0.706580026496751,
"grad_norm": 0.4224618673324585,
"learning_rate": 1.2000990737108225e-05,
"loss": 0.6999,
"step": 2800
},
{
"epoch": 0.7091035265913822,
"grad_norm": 0.5020971298217773,
"learning_rate": 1.1813312891987392e-05,
"loss": 0.734,
"step": 2810
},
{
"epoch": 0.7116270266860135,
"grad_norm": 0.4721106290817261,
"learning_rate": 1.1626659078960424e-05,
"loss": 0.7062,
"step": 2820
},
{
"epoch": 0.7141505267806447,
"grad_norm": 0.43608254194259644,
"learning_rate": 1.1441043792910936e-05,
"loss": 0.7132,
"step": 2830
},
{
"epoch": 0.716674026875276,
"grad_norm": 0.47143277525901794,
"learning_rate": 1.1256481448074179e-05,
"loss": 0.7037,
"step": 2840
},
{
"epoch": 0.7191975269699072,
"grad_norm": 0.44380879402160645,
"learning_rate": 1.1072986376917638e-05,
"loss": 0.7114,
"step": 2850
},
{
"epoch": 0.7217210270645386,
"grad_norm": 0.41831108927726746,
"learning_rate": 1.0890572829028087e-05,
"loss": 0.7452,
"step": 2860
},
{
"epoch": 0.7242445271591698,
"grad_norm": 0.4085826575756073,
"learning_rate": 1.0709254970004937e-05,
"loss": 0.6973,
"step": 2870
},
{
"epoch": 0.7267680272538011,
"grad_norm": 0.39444825053215027,
"learning_rate": 1.0529046880360263e-05,
"loss": 0.6945,
"step": 2880
},
{
"epoch": 0.7292915273484323,
"grad_norm": 0.3804919421672821,
"learning_rate": 1.034996255442529e-05,
"loss": 0.7419,
"step": 2890
},
{
"epoch": 0.7318150274430635,
"grad_norm": 0.3947986364364624,
"learning_rate": 1.0172015899263712e-05,
"loss": 0.7092,
"step": 2900
},
{
"epoch": 0.7343385275376948,
"grad_norm": 0.4076451361179352,
"learning_rate": 9.995220733591639e-06,
"loss": 0.6974,
"step": 2910
},
{
"epoch": 0.736862027632326,
"grad_norm": 0.39703309535980225,
"learning_rate": 9.819590786704572e-06,
"loss": 0.7296,
"step": 2920
},
{
"epoch": 0.7393855277269573,
"grad_norm": 0.4251289665699005,
"learning_rate": 9.645139697411149e-06,
"loss": 0.7106,
"step": 2930
},
{
"epoch": 0.7419090278215885,
"grad_norm": 0.44590967893600464,
"learning_rate": 9.471881012974071e-06,
"loss": 0.7285,
"step": 2940
},
{
"epoch": 0.7444325279162198,
"grad_norm": 0.46388325095176697,
"learning_rate": 9.299828188058013e-06,
"loss": 0.7135,
"step": 2950
},
{
"epoch": 0.746956028010851,
"grad_norm": 0.431956946849823,
"learning_rate": 9.128994583684838e-06,
"loss": 0.695,
"step": 2960
},
{
"epoch": 0.7494795281054824,
"grad_norm": 0.41202619671821594,
"learning_rate": 8.959393466195972e-06,
"loss": 0.7424,
"step": 2970
},
{
"epoch": 0.7520030282001136,
"grad_norm": 0.41577231884002686,
"learning_rate": 8.791038006222233e-06,
"loss": 0.7222,
"step": 2980
},
{
"epoch": 0.7545265282947448,
"grad_norm": 0.4451634883880615,
"learning_rate": 8.623941277660994e-06,
"loss": 0.7017,
"step": 2990
},
{
"epoch": 0.7570500283893761,
"grad_norm": 0.4805489182472229,
"learning_rate": 8.458116256660981e-06,
"loss": 0.7407,
"step": 3000
},
{
"epoch": 0.7595735284840073,
"grad_norm": 0.415554404258728,
"learning_rate": 8.293575820614508e-06,
"loss": 0.7122,
"step": 3010
},
{
"epoch": 0.7620970285786386,
"grad_norm": 0.42586177587509155,
"learning_rate": 8.130332747157542e-06,
"loss": 0.6742,
"step": 3020
},
{
"epoch": 0.7646205286732698,
"grad_norm": 0.5801184177398682,
"learning_rate": 7.968399713177366e-06,
"loss": 0.7278,
"step": 3030
},
{
"epoch": 0.7671440287679011,
"grad_norm": 0.4051037132740021,
"learning_rate": 7.807789293828204e-06,
"loss": 0.7334,
"step": 3040
},
{
"epoch": 0.7696675288625323,
"grad_norm": 0.44045910239219666,
"learning_rate": 7.648513961554607e-06,
"loss": 0.6804,
"step": 3050
},
{
"epoch": 0.7721910289571636,
"grad_norm": 0.3936316967010498,
"learning_rate": 7.4905860851229605e-06,
"loss": 0.7251,
"step": 3060
},
{
"epoch": 0.7747145290517948,
"grad_norm": 0.4889877736568451,
"learning_rate": 7.334017928660902e-06,
"loss": 0.7208,
"step": 3070
},
{
"epoch": 0.7772380291464261,
"grad_norm": 0.4045318067073822,
"learning_rate": 7.1788216507049865e-06,
"loss": 0.7035,
"step": 3080
},
{
"epoch": 0.7797615292410573,
"grad_norm": 0.45931798219680786,
"learning_rate": 7.0250093032564494e-06,
"loss": 0.672,
"step": 3090
},
{
"epoch": 0.7822850293356886,
"grad_norm": 0.42762941122055054,
"learning_rate": 6.872592830845339e-06,
"loss": 0.7027,
"step": 3100
},
{
"epoch": 0.7848085294303199,
"grad_norm": 0.4001401662826538,
"learning_rate": 6.72158406960289e-06,
"loss": 0.7308,
"step": 3110
},
{
"epoch": 0.7873320295249511,
"grad_norm": 0.3829699158668518,
"learning_rate": 6.571994746342439e-06,
"loss": 0.7069,
"step": 3120
},
{
"epoch": 0.7898555296195824,
"grad_norm": 0.4204135537147522,
"learning_rate": 6.4238364776486785e-06,
"loss": 0.6928,
"step": 3130
},
{
"epoch": 0.7923790297142136,
"grad_norm": 0.4242267608642578,
"learning_rate": 6.277120768975644e-06,
"loss": 0.7346,
"step": 3140
},
{
"epoch": 0.7949025298088449,
"grad_norm": 0.49215856194496155,
"learning_rate": 6.131859013753155e-06,
"loss": 0.6918,
"step": 3150
},
{
"epoch": 0.7974260299034761,
"grad_norm": 0.45208001136779785,
"learning_rate": 5.988062492502117e-06,
"loss": 0.6806,
"step": 3160
},
{
"epoch": 0.7999495299981074,
"grad_norm": 0.39334243535995483,
"learning_rate": 5.8457423719584435e-06,
"loss": 0.6936,
"step": 3170
},
{
"epoch": 0.8024730300927386,
"grad_norm": 0.4453311860561371,
"learning_rate": 5.704909704205949e-06,
"loss": 0.7286,
"step": 3180
},
{
"epoch": 0.8049965301873698,
"grad_norm": 0.446539968252182,
"learning_rate": 5.565575425818054e-06,
"loss": 0.7129,
"step": 3190
},
{
"epoch": 0.8075200302820011,
"grad_norm": 0.4576982259750366,
"learning_rate": 5.427750357008468e-06,
"loss": 0.6787,
"step": 3200
},
{
"epoch": 0.8100435303766323,
"grad_norm": 0.43956705927848816,
"learning_rate": 5.291445200790982e-06,
"loss": 0.7249,
"step": 3210
},
{
"epoch": 0.8125670304712637,
"grad_norm": 0.3920847773551941,
"learning_rate": 5.156670542148267e-06,
"loss": 0.7237,
"step": 3220
},
{
"epoch": 0.8150905305658949,
"grad_norm": 0.4733986556529999,
"learning_rate": 5.023436847209887e-06,
"loss": 0.7165,
"step": 3230
},
{
"epoch": 0.8176140306605262,
"grad_norm": 0.39961108565330505,
"learning_rate": 4.891754462439557e-06,
"loss": 0.6806,
"step": 3240
},
{
"epoch": 0.8201375307551574,
"grad_norm": 0.472107470035553,
"learning_rate": 4.761633613831645e-06,
"loss": 0.7165,
"step": 3250
},
{
"epoch": 0.8226610308497887,
"grad_norm": 0.48432740569114685,
"learning_rate": 4.6330844061170914e-06,
"loss": 0.6869,
"step": 3260
},
{
"epoch": 0.8251845309444199,
"grad_norm": 0.4450688064098358,
"learning_rate": 4.506116821978662e-06,
"loss": 0.6968,
"step": 3270
},
{
"epoch": 0.8277080310390512,
"grad_norm": 0.3828079402446747,
"learning_rate": 4.380740721275786e-06,
"loss": 0.7258,
"step": 3280
},
{
"epoch": 0.8302315311336824,
"grad_norm": 0.5289183259010315,
"learning_rate": 4.25696584027882e-06,
"loss": 0.7084,
"step": 3290
},
{
"epoch": 0.8327550312283136,
"grad_norm": 0.4827065169811249,
"learning_rate": 4.134801790913006e-06,
"loss": 0.6704,
"step": 3300
},
{
"epoch": 0.8352785313229449,
"grad_norm": 0.5083085298538208,
"learning_rate": 4.014258060012005e-06,
"loss": 0.7284,
"step": 3310
},
{
"epoch": 0.8378020314175761,
"grad_norm": 0.38500750064849854,
"learning_rate": 3.895344008581222e-06,
"loss": 0.6969,
"step": 3320
},
{
"epoch": 0.8403255315122075,
"grad_norm": 0.4650344252586365,
"learning_rate": 3.7780688710708223e-06,
"loss": 0.6856,
"step": 3330
},
{
"epoch": 0.8428490316068387,
"grad_norm": 0.4428897202014923,
"learning_rate": 3.6624417546586574e-06,
"loss": 0.6628,
"step": 3340
},
{
"epoch": 0.84537253170147,
"grad_norm": 0.4858897626399994,
"learning_rate": 3.548471638542991e-06,
"loss": 0.726,
"step": 3350
},
{
"epoch": 0.8478960317961012,
"grad_norm": 0.4039098024368286,
"learning_rate": 3.436167373245247e-06,
"loss": 0.7078,
"step": 3360
},
{
"epoch": 0.8504195318907325,
"grad_norm": 0.43264418840408325,
"learning_rate": 3.325537679922672e-06,
"loss": 0.7173,
"step": 3370
},
{
"epoch": 0.8529430319853637,
"grad_norm": 0.48531806468963623,
"learning_rate": 3.2165911496911173e-06,
"loss": 0.6934,
"step": 3380
},
{
"epoch": 0.8554665320799949,
"grad_norm": 0.4327000081539154,
"learning_rate": 3.1093362429578414e-06,
"loss": 0.7103,
"step": 3390
},
{
"epoch": 0.8579900321746262,
"grad_norm": 0.3971143066883087,
"learning_rate": 3.0037812887645483e-06,
"loss": 0.728,
"step": 3400
},
{
"epoch": 0.8605135322692574,
"grad_norm": 0.3819441497325897,
"learning_rate": 2.8999344841405373e-06,
"loss": 0.6971,
"step": 3410
},
{
"epoch": 0.8630370323638887,
"grad_norm": 0.4157625734806061,
"learning_rate": 2.7978038934662024e-06,
"loss": 0.6919,
"step": 3420
},
{
"epoch": 0.8655605324585199,
"grad_norm": 0.43926429748535156,
"learning_rate": 2.697397447846725e-06,
"loss": 0.7088,
"step": 3430
},
{
"epoch": 0.8680840325531513,
"grad_norm": 0.4086776673793793,
"learning_rate": 2.5987229444962237e-06,
"loss": 0.723,
"step": 3440
},
{
"epoch": 0.8706075326477825,
"grad_norm": 0.4299987256526947,
"learning_rate": 2.501788046132203e-06,
"loss": 0.7267,
"step": 3450
},
{
"epoch": 0.8731310327424138,
"grad_norm": 0.4047602713108063,
"learning_rate": 2.4066002803805386e-06,
"loss": 0.7044,
"step": 3460
},
{
"epoch": 0.875654532837045,
"grad_norm": 0.47258859872817993,
"learning_rate": 2.313167039190861e-06,
"loss": 0.7114,
"step": 3470
},
{
"epoch": 0.8781780329316763,
"grad_norm": 0.4289475977420807,
"learning_rate": 2.2214955782625752e-06,
"loss": 0.7081,
"step": 3480
},
{
"epoch": 0.8807015330263075,
"grad_norm": 0.4776837229728699,
"learning_rate": 2.1315930164813507e-06,
"loss": 0.7302,
"step": 3490
},
{
"epoch": 0.8832250331209387,
"grad_norm": 0.4333973228931427,
"learning_rate": 2.0434663353663536e-06,
"loss": 0.7042,
"step": 3500
},
{
"epoch": 0.88574853321557,
"grad_norm": 0.46293777227401733,
"learning_rate": 1.9571223785280314e-06,
"loss": 0.7028,
"step": 3510
},
{
"epoch": 0.8882720333102012,
"grad_norm": 0.4550043046474457,
"learning_rate": 1.8725678511367001e-06,
"loss": 0.7129,
"step": 3520
},
{
"epoch": 0.8907955334048325,
"grad_norm": 0.43017250299453735,
"learning_rate": 1.789809319401825e-06,
"loss": 0.7154,
"step": 3530
},
{
"epoch": 0.8933190334994637,
"grad_norm": 0.4087255895137787,
"learning_rate": 1.7088532100621224e-06,
"loss": 0.6848,
"step": 3540
},
{
"epoch": 0.895842533594095,
"grad_norm": 0.40603166818618774,
"learning_rate": 1.629705809886467e-06,
"loss": 0.688,
"step": 3550
},
{
"epoch": 0.8983660336887263,
"grad_norm": 0.3984641432762146,
"learning_rate": 1.5523732651857082e-06,
"loss": 0.708,
"step": 3560
},
{
"epoch": 0.9008895337833576,
"grad_norm": 0.457427054643631,
"learning_rate": 1.4768615813353398e-06,
"loss": 0.7051,
"step": 3570
},
{
"epoch": 0.9034130338779888,
"grad_norm": 0.3801426887512207,
"learning_rate": 1.4031766223091603e-06,
"loss": 0.6992,
"step": 3580
},
{
"epoch": 0.90593653397262,
"grad_norm": 0.39176779985427856,
"learning_rate": 1.3313241102239054e-06,
"loss": 0.6811,
"step": 3590
},
{
"epoch": 0.9084600340672513,
"grad_norm": 0.41780802607536316,
"learning_rate": 1.261309624894863e-06,
"loss": 0.7203,
"step": 3600
},
{
"epoch": 0.9109835341618825,
"grad_norm": 0.3884226679801941,
"learning_rate": 1.1931386034025882e-06,
"loss": 0.7038,
"step": 3610
},
{
"epoch": 0.9135070342565138,
"grad_norm": 0.3755139410495758,
"learning_rate": 1.1268163396706583e-06,
"loss": 0.7193,
"step": 3620
},
{
"epoch": 0.916030534351145,
"grad_norm": 0.3906721770763397,
"learning_rate": 1.0623479840545874e-06,
"loss": 0.6594,
"step": 3630
},
{
"epoch": 0.9185540344457763,
"grad_norm": 0.4476547837257385,
"learning_rate": 9.997385429418555e-07,
"loss": 0.7282,
"step": 3640
},
{
"epoch": 0.9210775345404075,
"grad_norm": 0.4512433707714081,
"learning_rate": 9.389928783631207e-07,
"loss": 0.7275,
"step": 3650
},
{
"epoch": 0.9236010346350388,
"grad_norm": 0.4227374494075775,
"learning_rate": 8.801157076146705e-07,
"loss": 0.6884,
"step": 3660
},
{
"epoch": 0.92612453472967,
"grad_norm": 0.46542125940322876,
"learning_rate": 8.231116028920765e-07,
"loss": 0.6995,
"step": 3670
},
{
"epoch": 0.9286480348243014,
"grad_norm": 0.4018099308013916,
"learning_rate": 7.679849909351472e-07,
"loss": 0.6846,
"step": 3680
},
{
"epoch": 0.9311715349189326,
"grad_norm": 0.46164804697036743,
"learning_rate": 7.147401526841485e-07,
"loss": 0.6821,
"step": 3690
},
{
"epoch": 0.9336950350135638,
"grad_norm": 0.44453224539756775,
"learning_rate": 6.633812229473791e-07,
"loss": 0.7343,
"step": 3700
},
{
"epoch": 0.9362185351081951,
"grad_norm": 0.4445902109146118,
"learning_rate": 6.139121900800515e-07,
"loss": 0.683,
"step": 3710
},
{
"epoch": 0.9387420352028263,
"grad_norm": 0.4326709508895874,
"learning_rate": 5.663368956745963e-07,
"loss": 0.6887,
"step": 3720
},
{
"epoch": 0.9412655352974576,
"grad_norm": 0.4491145610809326,
"learning_rate": 5.206590342623164e-07,
"loss": 0.6878,
"step": 3730
},
{
"epoch": 0.9437890353920888,
"grad_norm": 0.42220959067344666,
"learning_rate": 4.768821530264977e-07,
"loss": 0.7293,
"step": 3740
},
{
"epoch": 0.9463125354867201,
"grad_norm": 0.43391677737236023,
"learning_rate": 4.350096515269325e-07,
"loss": 0.7175,
"step": 3750
},
{
"epoch": 0.9488360355813513,
"grad_norm": 0.43437376618385315,
"learning_rate": 3.950447814359409e-07,
"loss": 0.7162,
"step": 3760
},
{
"epoch": 0.9513595356759826,
"grad_norm": 0.4475696086883545,
"learning_rate": 3.5699064628583745e-07,
"loss": 0.6984,
"step": 3770
},
{
"epoch": 0.9538830357706138,
"grad_norm": 0.38860946893692017,
"learning_rate": 3.2085020122793186e-07,
"loss": 0.701,
"step": 3780
},
{
"epoch": 0.956406535865245,
"grad_norm": 0.41958314180374146,
"learning_rate": 2.8662625280304613e-07,
"loss": 0.6944,
"step": 3790
},
{
"epoch": 0.9589300359598764,
"grad_norm": 0.4484213590621948,
"learning_rate": 2.5432145872355816e-07,
"loss": 0.6876,
"step": 3800
},
{
"epoch": 0.9614535360545076,
"grad_norm": 0.4424046277999878,
"learning_rate": 2.2393832766701706e-07,
"loss": 0.7071,
"step": 3810
},
{
"epoch": 0.9639770361491389,
"grad_norm": 0.38398098945617676,
"learning_rate": 1.9547921908133483e-07,
"loss": 0.7069,
"step": 3820
},
{
"epoch": 0.9665005362437701,
"grad_norm": 0.46120497584342957,
"learning_rate": 1.689463430015442e-07,
"loss": 0.6891,
"step": 3830
},
{
"epoch": 0.9690240363384014,
"grad_norm": 0.4390755295753479,
"learning_rate": 1.443417598781971e-07,
"loss": 0.7045,
"step": 3840
},
{
"epoch": 0.9715475364330326,
"grad_norm": 0.45651644468307495,
"learning_rate": 1.2166738041733684e-07,
"loss": 0.7043,
"step": 3850
},
{
"epoch": 0.9740710365276639,
"grad_norm": 0.4153136610984802,
"learning_rate": 1.0092496543212814e-07,
"loss": 0.6998,
"step": 3860
},
{
"epoch": 0.9765945366222951,
"grad_norm": 0.40442293882369995,
"learning_rate": 8.211612570611926e-08,
"loss": 0.6918,
"step": 3870
},
{
"epoch": 0.9791180367169264,
"grad_norm": 0.4135897159576416,
"learning_rate": 6.524232186815305e-08,
"loss": 0.6865,
"step": 3880
},
{
"epoch": 0.9816415368115576,
"grad_norm": 0.43170320987701416,
"learning_rate": 5.03048642789411e-08,
"loss": 0.6825,
"step": 3890
},
{
"epoch": 0.9841650369061888,
"grad_norm": 0.5247434973716736,
"learning_rate": 3.730491292930072e-08,
"loss": 0.6978,
"step": 3900
},
{
"epoch": 0.9866885370008202,
"grad_norm": 0.5228101015090942,
"learning_rate": 2.624347735007693e-08,
"loss": 0.7135,
"step": 3910
},
{
"epoch": 0.9892120370954514,
"grad_norm": 0.4438874125480652,
"learning_rate": 1.7121416533749658e-08,
"loss": 0.7048,
"step": 3920
},
{
"epoch": 0.9917355371900827,
"grad_norm": 0.40782466530799866,
"learning_rate": 9.939438867723194e-09,
"loss": 0.705,
"step": 3930
},
{
"epoch": 0.9942590372847139,
"grad_norm": 0.4269384443759918,
"learning_rate": 4.6981020793118725e-09,
"loss": 0.7149,
"step": 3940
},
{
"epoch": 0.9967825373793452,
"grad_norm": 0.4239284098148346,
"learning_rate": 1.3978131924385906e-09,
"loss": 0.6901,
"step": 3950
},
{
"epoch": 0.9993060374739764,
"grad_norm": 0.4434085488319397,
"learning_rate": 3.88284960184393e-11,
"loss": 0.7212,
"step": 3960
}
],
"logging_steps": 10,
"max_steps": 3962,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.1480232846728102e+19,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}