{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 100,
"global_step": 2310,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.021645021645021644,
"grad_norm": 1.49063241481781,
"learning_rate": 4.5e-06,
"loss": 5.15,
"step": 10
},
{
"epoch": 0.04329004329004329,
"grad_norm": 2.3369944095611572,
"learning_rate": 9.5e-06,
"loss": 5.1055,
"step": 20
},
{
"epoch": 0.06493506493506493,
"grad_norm": 2.44476318359375,
"learning_rate": 1.45e-05,
"loss": 4.9139,
"step": 30
},
{
"epoch": 0.08658008658008658,
"grad_norm": 4.037220001220703,
"learning_rate": 1.9500000000000003e-05,
"loss": 4.4762,
"step": 40
},
{
"epoch": 0.10822510822510822,
"grad_norm": 5.722354412078857,
"learning_rate": 2.45e-05,
"loss": 3.7558,
"step": 50
},
{
"epoch": 0.12987012987012986,
"grad_norm": 6.332724571228027,
"learning_rate": 2.95e-05,
"loss": 2.7035,
"step": 60
},
{
"epoch": 0.15151515151515152,
"grad_norm": 2.5632152557373047,
"learning_rate": 3.45e-05,
"loss": 2.0313,
"step": 70
},
{
"epoch": 0.17316017316017315,
"grad_norm": 4.372506141662598,
"learning_rate": 3.9500000000000005e-05,
"loss": 1.5306,
"step": 80
},
{
"epoch": 0.19480519480519481,
"grad_norm": 2.5026726722717285,
"learning_rate": 4.4500000000000004e-05,
"loss": 1.2437,
"step": 90
},
{
"epoch": 0.21645021645021645,
"grad_norm": 1.9875411987304688,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.9561,
"step": 100
},
{
"epoch": 0.21645021645021645,
"eval_loss": 0.19921594858169556,
"eval_runtime": 11.6195,
"eval_samples_per_second": 43.031,
"eval_steps_per_second": 0.688,
"step": 100
},
{
"epoch": 0.23809523809523808,
"grad_norm": 1.7703560590744019,
"learning_rate": 4.979638009049774e-05,
"loss": 0.7735,
"step": 110
},
{
"epoch": 0.2597402597402597,
"grad_norm": 1.7760099172592163,
"learning_rate": 4.957013574660634e-05,
"loss": 0.6721,
"step": 120
},
{
"epoch": 0.2813852813852814,
"grad_norm": 2.115910530090332,
"learning_rate": 4.934389140271494e-05,
"loss": 0.6748,
"step": 130
},
{
"epoch": 0.30303030303030304,
"grad_norm": 2.5156407356262207,
"learning_rate": 4.911764705882353e-05,
"loss": 0.6629,
"step": 140
},
{
"epoch": 0.3246753246753247,
"grad_norm": 1.8950108289718628,
"learning_rate": 4.8891402714932124e-05,
"loss": 0.6032,
"step": 150
},
{
"epoch": 0.3463203463203463,
"grad_norm": 2.0162742137908936,
"learning_rate": 4.8665158371040724e-05,
"loss": 0.5883,
"step": 160
},
{
"epoch": 0.36796536796536794,
"grad_norm": 1.5109184980392456,
"learning_rate": 4.843891402714932e-05,
"loss": 0.6149,
"step": 170
},
{
"epoch": 0.38961038961038963,
"grad_norm": 1.7340754270553589,
"learning_rate": 4.821266968325792e-05,
"loss": 0.589,
"step": 180
},
{
"epoch": 0.41125541125541126,
"grad_norm": 1.6524324417114258,
"learning_rate": 4.798642533936652e-05,
"loss": 0.5883,
"step": 190
},
{
"epoch": 0.4329004329004329,
"grad_norm": 1.5651330947875977,
"learning_rate": 4.7760180995475115e-05,
"loss": 0.5707,
"step": 200
},
{
"epoch": 0.4329004329004329,
"eval_loss": 0.13576850295066833,
"eval_runtime": 10.9595,
"eval_samples_per_second": 45.623,
"eval_steps_per_second": 0.73,
"step": 200
},
{
"epoch": 0.45454545454545453,
"grad_norm": 1.4788271188735962,
"learning_rate": 4.753393665158371e-05,
"loss": 0.5889,
"step": 210
},
{
"epoch": 0.47619047619047616,
"grad_norm": 1.4938485622406006,
"learning_rate": 4.730769230769231e-05,
"loss": 0.5377,
"step": 220
},
{
"epoch": 0.49783549783549785,
"grad_norm": 1.3584009408950806,
"learning_rate": 4.7081447963800906e-05,
"loss": 0.5202,
"step": 230
},
{
"epoch": 0.5194805194805194,
"grad_norm": 3.0394833087921143,
"learning_rate": 4.6855203619909505e-05,
"loss": 0.5044,
"step": 240
},
{
"epoch": 0.5411255411255411,
"grad_norm": 1.2974430322647095,
"learning_rate": 4.6628959276018105e-05,
"loss": 0.5448,
"step": 250
},
{
"epoch": 0.5627705627705628,
"grad_norm": 1.4595730304718018,
"learning_rate": 4.64027149321267e-05,
"loss": 0.4816,
"step": 260
},
{
"epoch": 0.5844155844155844,
"grad_norm": 1.248807430267334,
"learning_rate": 4.61764705882353e-05,
"loss": 0.4622,
"step": 270
},
{
"epoch": 0.6060606060606061,
"grad_norm": 1.4656962156295776,
"learning_rate": 4.595022624434389e-05,
"loss": 0.4807,
"step": 280
},
{
"epoch": 0.6277056277056277,
"grad_norm": 1.5670865774154663,
"learning_rate": 4.572398190045249e-05,
"loss": 0.5012,
"step": 290
},
{
"epoch": 0.6493506493506493,
"grad_norm": 1.6379127502441406,
"learning_rate": 4.549773755656109e-05,
"loss": 0.467,
"step": 300
},
{
"epoch": 0.6493506493506493,
"eval_loss": 0.1379440426826477,
"eval_runtime": 11.0085,
"eval_samples_per_second": 45.419,
"eval_steps_per_second": 0.727,
"step": 300
},
{
"epoch": 0.670995670995671,
"grad_norm": 1.4250965118408203,
"learning_rate": 4.527149321266969e-05,
"loss": 0.4903,
"step": 310
},
{
"epoch": 0.6926406926406926,
"grad_norm": 1.3096636533737183,
"learning_rate": 4.504524886877829e-05,
"loss": 0.468,
"step": 320
},
{
"epoch": 0.7142857142857143,
"grad_norm": 1.3946788311004639,
"learning_rate": 4.481900452488688e-05,
"loss": 0.4628,
"step": 330
},
{
"epoch": 0.7359307359307359,
"grad_norm": 1.3430134057998657,
"learning_rate": 4.459276018099548e-05,
"loss": 0.4711,
"step": 340
},
{
"epoch": 0.7575757575757576,
"grad_norm": 1.246222734451294,
"learning_rate": 4.436651583710407e-05,
"loss": 0.4829,
"step": 350
},
{
"epoch": 0.7792207792207793,
"grad_norm": 1.406936764717102,
"learning_rate": 4.414027149321267e-05,
"loss": 0.4452,
"step": 360
},
{
"epoch": 0.8008658008658008,
"grad_norm": 1.645504355430603,
"learning_rate": 4.391402714932127e-05,
"loss": 0.4385,
"step": 370
},
{
"epoch": 0.8225108225108225,
"grad_norm": 1.7644546031951904,
"learning_rate": 4.368778280542987e-05,
"loss": 0.4514,
"step": 380
},
{
"epoch": 0.8441558441558441,
"grad_norm": 1.7779700756072998,
"learning_rate": 4.346153846153846e-05,
"loss": 0.4785,
"step": 390
},
{
"epoch": 0.8658008658008658,
"grad_norm": 1.3203119039535522,
"learning_rate": 4.323529411764706e-05,
"loss": 0.509,
"step": 400
},
{
"epoch": 0.8658008658008658,
"eval_loss": 0.11263184249401093,
"eval_runtime": 11.019,
"eval_samples_per_second": 45.376,
"eval_steps_per_second": 0.726,
"step": 400
},
{
"epoch": 0.8874458874458875,
"grad_norm": 1.3130112886428833,
"learning_rate": 4.300904977375566e-05,
"loss": 0.4583,
"step": 410
},
{
"epoch": 0.9090909090909091,
"grad_norm": 1.0591143369674683,
"learning_rate": 4.2782805429864254e-05,
"loss": 0.4318,
"step": 420
},
{
"epoch": 0.9307359307359307,
"grad_norm": 1.389012336730957,
"learning_rate": 4.255656108597285e-05,
"loss": 0.4554,
"step": 430
},
{
"epoch": 0.9523809523809523,
"grad_norm": 1.3405207395553589,
"learning_rate": 4.233031674208145e-05,
"loss": 0.4485,
"step": 440
},
{
"epoch": 0.974025974025974,
"grad_norm": 1.2793899774551392,
"learning_rate": 4.2104072398190045e-05,
"loss": 0.4537,
"step": 450
},
{
"epoch": 0.9956709956709957,
"grad_norm": 1.6418206691741943,
"learning_rate": 4.1877828054298645e-05,
"loss": 0.4446,
"step": 460
},
{
"epoch": 1.0173160173160174,
"grad_norm": 1.7021077871322632,
"learning_rate": 4.1651583710407244e-05,
"loss": 0.4476,
"step": 470
},
{
"epoch": 1.0389610389610389,
"grad_norm": 2.451876401901245,
"learning_rate": 4.142533936651584e-05,
"loss": 0.4221,
"step": 480
},
{
"epoch": 1.0606060606060606,
"grad_norm": 1.5263983011245728,
"learning_rate": 4.1199095022624436e-05,
"loss": 0.4121,
"step": 490
},
{
"epoch": 1.0822510822510822,
"grad_norm": 1.1231575012207031,
"learning_rate": 4.0972850678733035e-05,
"loss": 0.4399,
"step": 500
},
{
"epoch": 1.0822510822510822,
"eval_loss": 0.107670359313488,
"eval_runtime": 11.2498,
"eval_samples_per_second": 44.445,
"eval_steps_per_second": 0.711,
"step": 500
},
{
"epoch": 1.103896103896104,
"grad_norm": 1.3337820768356323,
"learning_rate": 4.074660633484163e-05,
"loss": 0.3778,
"step": 510
},
{
"epoch": 1.1255411255411256,
"grad_norm": 1.2338522672653198,
"learning_rate": 4.052036199095023e-05,
"loss": 0.399,
"step": 520
},
{
"epoch": 1.1471861471861473,
"grad_norm": 0.9891630411148071,
"learning_rate": 4.029411764705883e-05,
"loss": 0.4085,
"step": 530
},
{
"epoch": 1.1688311688311688,
"grad_norm": 2.232311964035034,
"learning_rate": 4.0067873303167426e-05,
"loss": 0.4006,
"step": 540
},
{
"epoch": 1.1904761904761905,
"grad_norm": 1.403098225593567,
"learning_rate": 3.984162895927602e-05,
"loss": 0.425,
"step": 550
},
{
"epoch": 1.2121212121212122,
"grad_norm": 1.367215633392334,
"learning_rate": 3.961538461538462e-05,
"loss": 0.3828,
"step": 560
},
{
"epoch": 1.2337662337662338,
"grad_norm": 1.7988994121551514,
"learning_rate": 3.938914027149321e-05,
"loss": 0.3941,
"step": 570
},
{
"epoch": 1.2554112554112553,
"grad_norm": 1.0070048570632935,
"learning_rate": 3.916289592760181e-05,
"loss": 0.3792,
"step": 580
},
{
"epoch": 1.277056277056277,
"grad_norm": 1.2809069156646729,
"learning_rate": 3.893665158371041e-05,
"loss": 0.3711,
"step": 590
},
{
"epoch": 1.2987012987012987,
"grad_norm": 1.369131326675415,
"learning_rate": 3.871040723981901e-05,
"loss": 0.4104,
"step": 600
},
{
"epoch": 1.2987012987012987,
"eval_loss": 0.11119061708450317,
"eval_runtime": 11.018,
"eval_samples_per_second": 45.38,
"eval_steps_per_second": 0.726,
"step": 600
},
{
"epoch": 1.3203463203463204,
"grad_norm": 1.2250093221664429,
"learning_rate": 3.848416289592761e-05,
"loss": 0.3638,
"step": 610
},
{
"epoch": 1.341991341991342,
"grad_norm": 1.4213260412216187,
"learning_rate": 3.82579185520362e-05,
"loss": 0.408,
"step": 620
},
{
"epoch": 1.3636363636363638,
"grad_norm": 1.2376580238342285,
"learning_rate": 3.8031674208144794e-05,
"loss": 0.3746,
"step": 630
},
{
"epoch": 1.3852813852813852,
"grad_norm": 1.5489083528518677,
"learning_rate": 3.780542986425339e-05,
"loss": 0.4002,
"step": 640
},
{
"epoch": 1.406926406926407,
"grad_norm": 1.3500491380691528,
"learning_rate": 3.757918552036199e-05,
"loss": 0.4152,
"step": 650
},
{
"epoch": 1.4285714285714286,
"grad_norm": 1.2030531167984009,
"learning_rate": 3.735294117647059e-05,
"loss": 0.3842,
"step": 660
},
{
"epoch": 1.4502164502164503,
"grad_norm": 1.205944299697876,
"learning_rate": 3.712669683257919e-05,
"loss": 0.3756,
"step": 670
},
{
"epoch": 1.4718614718614718,
"grad_norm": 1.2800495624542236,
"learning_rate": 3.6900452488687784e-05,
"loss": 0.362,
"step": 680
},
{
"epoch": 1.4935064935064934,
"grad_norm": 1.3327527046203613,
"learning_rate": 3.6674208144796376e-05,
"loss": 0.3892,
"step": 690
},
{
"epoch": 1.5151515151515151,
"grad_norm": 1.760610818862915,
"learning_rate": 3.6447963800904976e-05,
"loss": 0.4004,
"step": 700
},
{
"epoch": 1.5151515151515151,
"eval_loss": 0.10533424466848373,
"eval_runtime": 10.9974,
"eval_samples_per_second": 45.465,
"eval_steps_per_second": 0.727,
"step": 700
},
{
"epoch": 1.5367965367965368,
"grad_norm": 1.2114096879959106,
"learning_rate": 3.6221719457013575e-05,
"loss": 0.3773,
"step": 710
},
{
"epoch": 1.5584415584415585,
"grad_norm": 1.234147071838379,
"learning_rate": 3.5995475113122175e-05,
"loss": 0.3654,
"step": 720
},
{
"epoch": 1.5800865800865802,
"grad_norm": 1.1402283906936646,
"learning_rate": 3.5769230769230774e-05,
"loss": 0.3956,
"step": 730
},
{
"epoch": 1.601731601731602,
"grad_norm": 1.3863605260849,
"learning_rate": 3.5542986425339367e-05,
"loss": 0.3847,
"step": 740
},
{
"epoch": 1.6233766233766234,
"grad_norm": 1.1907293796539307,
"learning_rate": 3.5316742081447966e-05,
"loss": 0.3864,
"step": 750
},
{
"epoch": 1.645021645021645,
"grad_norm": 1.4367133378982544,
"learning_rate": 3.509049773755656e-05,
"loss": 0.3764,
"step": 760
},
{
"epoch": 1.6666666666666665,
"grad_norm": 5.571836948394775,
"learning_rate": 3.486425339366516e-05,
"loss": 0.3986,
"step": 770
},
{
"epoch": 1.6883116883116882,
"grad_norm": 1.7412991523742676,
"learning_rate": 3.463800904977376e-05,
"loss": 0.3659,
"step": 780
},
{
"epoch": 1.70995670995671,
"grad_norm": 1.2746937274932861,
"learning_rate": 3.441176470588236e-05,
"loss": 0.405,
"step": 790
},
{
"epoch": 1.7316017316017316,
"grad_norm": 1.7823095321655273,
"learning_rate": 3.418552036199095e-05,
"loss": 0.3756,
"step": 800
},
{
"epoch": 1.7316017316017316,
"eval_loss": 0.10027167201042175,
"eval_runtime": 11.0379,
"eval_samples_per_second": 45.299,
"eval_steps_per_second": 0.725,
"step": 800
},
{
"epoch": 1.7532467532467533,
"grad_norm": 1.605469822883606,
"learning_rate": 3.395927601809955e-05,
"loss": 0.3658,
"step": 810
},
{
"epoch": 1.774891774891775,
"grad_norm": 1.058374285697937,
"learning_rate": 3.373303167420815e-05,
"loss": 0.3687,
"step": 820
},
{
"epoch": 1.7965367965367967,
"grad_norm": 1.0704131126403809,
"learning_rate": 3.350678733031674e-05,
"loss": 0.3884,
"step": 830
},
{
"epoch": 1.8181818181818183,
"grad_norm": 1.3040030002593994,
"learning_rate": 3.328054298642534e-05,
"loss": 0.415,
"step": 840
},
{
"epoch": 1.8398268398268398,
"grad_norm": 1.4915244579315186,
"learning_rate": 3.305429864253394e-05,
"loss": 0.3376,
"step": 850
},
{
"epoch": 1.8614718614718615,
"grad_norm": 1.2545368671417236,
"learning_rate": 3.282805429864253e-05,
"loss": 0.3834,
"step": 860
},
{
"epoch": 1.883116883116883,
"grad_norm": 1.5177216529846191,
"learning_rate": 3.260180995475113e-05,
"loss": 0.3908,
"step": 870
},
{
"epoch": 1.9047619047619047,
"grad_norm": 2.2402610778808594,
"learning_rate": 3.237556561085973e-05,
"loss": 0.3801,
"step": 880
},
{
"epoch": 1.9264069264069263,
"grad_norm": 1.0384106636047363,
"learning_rate": 3.214932126696833e-05,
"loss": 0.3801,
"step": 890
},
{
"epoch": 1.948051948051948,
"grad_norm": 1.3252601623535156,
"learning_rate": 3.192307692307692e-05,
"loss": 0.3787,
"step": 900
},
{
"epoch": 1.948051948051948,
"eval_loss": 0.09781702607870102,
"eval_runtime": 11.1554,
"eval_samples_per_second": 44.821,
"eval_steps_per_second": 0.717,
"step": 900
},
{
"epoch": 1.9696969696969697,
"grad_norm": 1.3580507040023804,
"learning_rate": 3.169683257918552e-05,
"loss": 0.3583,
"step": 910
},
{
"epoch": 1.9913419913419914,
"grad_norm": 1.4314372539520264,
"learning_rate": 3.147058823529412e-05,
"loss": 0.3653,
"step": 920
},
{
"epoch": 2.012987012987013,
"grad_norm": 1.2172566652297974,
"learning_rate": 3.1244343891402714e-05,
"loss": 0.3238,
"step": 930
},
{
"epoch": 2.034632034632035,
"grad_norm": 1.4818902015686035,
"learning_rate": 3.1018099547511314e-05,
"loss": 0.3436,
"step": 940
},
{
"epoch": 2.0562770562770565,
"grad_norm": 1.1465860605239868,
"learning_rate": 3.079185520361991e-05,
"loss": 0.3425,
"step": 950
},
{
"epoch": 2.0779220779220777,
"grad_norm": 1.903261423110962,
"learning_rate": 3.056561085972851e-05,
"loss": 0.3647,
"step": 960
},
{
"epoch": 2.0995670995670994,
"grad_norm": 1.3892687559127808,
"learning_rate": 3.03393665158371e-05,
"loss": 0.3223,
"step": 970
},
{
"epoch": 2.121212121212121,
"grad_norm": 1.5258572101593018,
"learning_rate": 3.01131221719457e-05,
"loss": 0.3668,
"step": 980
},
{
"epoch": 2.142857142857143,
"grad_norm": 1.298425316810608,
"learning_rate": 2.98868778280543e-05,
"loss": 0.3487,
"step": 990
},
{
"epoch": 2.1645021645021645,
"grad_norm": 1.8322169780731201,
"learning_rate": 2.9660633484162896e-05,
"loss": 0.3203,
"step": 1000
},
{
"epoch": 2.1645021645021645,
"eval_loss": 0.10291534662246704,
"eval_runtime": 11.0546,
"eval_samples_per_second": 45.23,
"eval_steps_per_second": 0.724,
"step": 1000
},
{
"epoch": 2.186147186147186,
"grad_norm": 1.371580958366394,
"learning_rate": 2.9434389140271496e-05,
"loss": 0.3089,
"step": 1010
},
{
"epoch": 2.207792207792208,
"grad_norm": 1.2570271492004395,
"learning_rate": 2.9208144796380095e-05,
"loss": 0.3258,
"step": 1020
},
{
"epoch": 2.2294372294372296,
"grad_norm": 1.7881371974945068,
"learning_rate": 2.898190045248869e-05,
"loss": 0.3281,
"step": 1030
},
{
"epoch": 2.2510822510822512,
"grad_norm": 1.2721039056777954,
"learning_rate": 2.8755656108597284e-05,
"loss": 0.3085,
"step": 1040
},
{
"epoch": 2.2727272727272725,
"grad_norm": 1.4111952781677246,
"learning_rate": 2.8529411764705883e-05,
"loss": 0.3368,
"step": 1050
},
{
"epoch": 2.2943722943722946,
"grad_norm": 1.2382339239120483,
"learning_rate": 2.830316742081448e-05,
"loss": 0.3331,
"step": 1060
},
{
"epoch": 2.316017316017316,
"grad_norm": 1.390204906463623,
"learning_rate": 2.807692307692308e-05,
"loss": 0.3604,
"step": 1070
},
{
"epoch": 2.3376623376623376,
"grad_norm": 1.046399712562561,
"learning_rate": 2.7850678733031678e-05,
"loss": 0.3264,
"step": 1080
},
{
"epoch": 2.3593073593073592,
"grad_norm": 1.4382643699645996,
"learning_rate": 2.7624434389140274e-05,
"loss": 0.3108,
"step": 1090
},
{
"epoch": 2.380952380952381,
"grad_norm": 2.0286881923675537,
"learning_rate": 2.7398190045248873e-05,
"loss": 0.3222,
"step": 1100
},
{
"epoch": 2.380952380952381,
"eval_loss": 0.09695376455783844,
"eval_runtime": 11.0788,
"eval_samples_per_second": 45.131,
"eval_steps_per_second": 0.722,
"step": 1100
},
{
"epoch": 2.4025974025974026,
"grad_norm": 1.735385537147522,
"learning_rate": 2.7171945701357466e-05,
"loss": 0.3141,
"step": 1110
},
{
"epoch": 2.4242424242424243,
"grad_norm": 1.3764822483062744,
"learning_rate": 2.6945701357466062e-05,
"loss": 0.3398,
"step": 1120
},
{
"epoch": 2.445887445887446,
"grad_norm": 1.189744234085083,
"learning_rate": 2.671945701357466e-05,
"loss": 0.3216,
"step": 1130
},
{
"epoch": 2.4675324675324677,
"grad_norm": 1.2942255735397339,
"learning_rate": 2.649321266968326e-05,
"loss": 0.3345,
"step": 1140
},
{
"epoch": 2.4891774891774894,
"grad_norm": 1.3467974662780762,
"learning_rate": 2.6266968325791857e-05,
"loss": 0.3554,
"step": 1150
},
{
"epoch": 2.5108225108225106,
"grad_norm": 1.4570668935775757,
"learning_rate": 2.6040723981900456e-05,
"loss": 0.328,
"step": 1160
},
{
"epoch": 2.5324675324675323,
"grad_norm": 1.5922597646713257,
"learning_rate": 2.5814479638009052e-05,
"loss": 0.3139,
"step": 1170
},
{
"epoch": 2.554112554112554,
"grad_norm": 1.2003611326217651,
"learning_rate": 2.5588235294117645e-05,
"loss": 0.2989,
"step": 1180
},
{
"epoch": 2.5757575757575757,
"grad_norm": 2.1363961696624756,
"learning_rate": 2.5361990950226244e-05,
"loss": 0.3263,
"step": 1190
},
{
"epoch": 2.5974025974025974,
"grad_norm": 1.5996774435043335,
"learning_rate": 2.5135746606334844e-05,
"loss": 0.3578,
"step": 1200
},
{
"epoch": 2.5974025974025974,
"eval_loss": 0.09967260807752609,
"eval_runtime": 11.07,
"eval_samples_per_second": 45.167,
"eval_steps_per_second": 0.723,
"step": 1200
},
{
"epoch": 2.619047619047619,
"grad_norm": 1.1521668434143066,
"learning_rate": 2.490950226244344e-05,
"loss": 0.33,
"step": 1210
},
{
"epoch": 2.6406926406926408,
"grad_norm": 1.1272907257080078,
"learning_rate": 2.468325791855204e-05,
"loss": 0.3119,
"step": 1220
},
{
"epoch": 2.6623376623376624,
"grad_norm": 1.270735263824463,
"learning_rate": 2.4457013574660635e-05,
"loss": 0.2898,
"step": 1230
},
{
"epoch": 2.683982683982684,
"grad_norm": 1.0944297313690186,
"learning_rate": 2.423076923076923e-05,
"loss": 0.3235,
"step": 1240
},
{
"epoch": 2.7056277056277054,
"grad_norm": 1.8073984384536743,
"learning_rate": 2.400452488687783e-05,
"loss": 0.3529,
"step": 1250
},
{
"epoch": 2.7272727272727275,
"grad_norm": 1.573345422744751,
"learning_rate": 2.3778280542986426e-05,
"loss": 0.3374,
"step": 1260
},
{
"epoch": 2.7489177489177488,
"grad_norm": 1.2758445739746094,
"learning_rate": 2.3552036199095022e-05,
"loss": 0.3111,
"step": 1270
},
{
"epoch": 2.7705627705627704,
"grad_norm": 1.4875160455703735,
"learning_rate": 2.3325791855203622e-05,
"loss": 0.3152,
"step": 1280
},
{
"epoch": 2.792207792207792,
"grad_norm": 1.3437527418136597,
"learning_rate": 2.309954751131222e-05,
"loss": 0.3366,
"step": 1290
},
{
"epoch": 2.813852813852814,
"grad_norm": 0.9686049818992615,
"learning_rate": 2.2873303167420814e-05,
"loss": 0.3073,
"step": 1300
},
{
"epoch": 2.813852813852814,
"eval_loss": 0.11263589560985565,
"eval_runtime": 11.0755,
"eval_samples_per_second": 45.145,
"eval_steps_per_second": 0.722,
"step": 1300
},
{
"epoch": 2.8354978354978355,
"grad_norm": 1.654786467552185,
"learning_rate": 2.2647058823529413e-05,
"loss": 0.3259,
"step": 1310
},
{
"epoch": 2.857142857142857,
"grad_norm": 1.2647713422775269,
"learning_rate": 2.2420814479638013e-05,
"loss": 0.3261,
"step": 1320
},
{
"epoch": 2.878787878787879,
"grad_norm": 1.293813943862915,
"learning_rate": 2.2194570135746605e-05,
"loss": 0.3361,
"step": 1330
},
{
"epoch": 2.9004329004329006,
"grad_norm": 1.320722222328186,
"learning_rate": 2.1968325791855205e-05,
"loss": 0.3197,
"step": 1340
},
{
"epoch": 2.9220779220779223,
"grad_norm": 1.2165260314941406,
"learning_rate": 2.1742081447963804e-05,
"loss": 0.3408,
"step": 1350
},
{
"epoch": 2.9437229437229435,
"grad_norm": 1.154363989830017,
"learning_rate": 2.15158371040724e-05,
"loss": 0.3594,
"step": 1360
},
{
"epoch": 2.965367965367965,
"grad_norm": 1.7927467823028564,
"learning_rate": 2.1289592760180996e-05,
"loss": 0.3399,
"step": 1370
},
{
"epoch": 2.987012987012987,
"grad_norm": 2.399272918701172,
"learning_rate": 2.1063348416289595e-05,
"loss": 0.3276,
"step": 1380
},
{
"epoch": 3.0086580086580086,
"grad_norm": 1.5982075929641724,
"learning_rate": 2.083710407239819e-05,
"loss": 0.2852,
"step": 1390
},
{
"epoch": 3.0303030303030303,
"grad_norm": 1.479366660118103,
"learning_rate": 2.0610859728506787e-05,
"loss": 0.2805,
"step": 1400
},
{
"epoch": 3.0303030303030303,
"eval_loss": 0.09813899546861649,
"eval_runtime": 11.2539,
"eval_samples_per_second": 44.429,
"eval_steps_per_second": 0.711,
"step": 1400
},
{
"epoch": 3.051948051948052,
"grad_norm": 1.197197437286377,
"learning_rate": 2.0384615384615387e-05,
"loss": 0.2819,
"step": 1410
},
{
"epoch": 3.0735930735930737,
"grad_norm": 1.2043474912643433,
"learning_rate": 2.0158371040723983e-05,
"loss": 0.2739,
"step": 1420
},
{
"epoch": 3.0952380952380953,
"grad_norm": 1.305875301361084,
"learning_rate": 1.9932126696832582e-05,
"loss": 0.2823,
"step": 1430
},
{
"epoch": 3.116883116883117,
"grad_norm": 1.8753947019577026,
"learning_rate": 1.9705882352941178e-05,
"loss": 0.3127,
"step": 1440
},
{
"epoch": 3.1385281385281387,
"grad_norm": 1.1929014921188354,
"learning_rate": 1.9479638009049774e-05,
"loss": 0.2834,
"step": 1450
},
{
"epoch": 3.16017316017316,
"grad_norm": 1.4350407123565674,
"learning_rate": 1.9253393665158374e-05,
"loss": 0.2847,
"step": 1460
},
{
"epoch": 3.1818181818181817,
"grad_norm": 1.4549144506454468,
"learning_rate": 1.902714932126697e-05,
"loss": 0.2891,
"step": 1470
},
{
"epoch": 3.2034632034632033,
"grad_norm": 1.4221315383911133,
"learning_rate": 1.8800904977375566e-05,
"loss": 0.2947,
"step": 1480
},
{
"epoch": 3.225108225108225,
"grad_norm": 1.5852824449539185,
"learning_rate": 1.8574660633484165e-05,
"loss": 0.2988,
"step": 1490
},
{
"epoch": 3.2467532467532467,
"grad_norm": 2.2345638275146484,
"learning_rate": 1.834841628959276e-05,
"loss": 0.3131,
"step": 1500
},
{
"epoch": 3.2467532467532467,
"eval_loss": 0.10453030467033386,
"eval_runtime": 11.0226,
"eval_samples_per_second": 45.361,
"eval_steps_per_second": 0.726,
"step": 1500
},
{
"epoch": 3.2683982683982684,
"grad_norm": 1.0346052646636963,
"learning_rate": 1.8122171945701357e-05,
"loss": 0.2779,
"step": 1510
},
{
"epoch": 3.29004329004329,
"grad_norm": 1.4983434677124023,
"learning_rate": 1.7895927601809956e-05,
"loss": 0.3022,
"step": 1520
},
{
"epoch": 3.311688311688312,
"grad_norm": 1.3768881559371948,
"learning_rate": 1.7669683257918552e-05,
"loss": 0.2966,
"step": 1530
},
{
"epoch": 3.3333333333333335,
"grad_norm": 2.331627130508423,
"learning_rate": 1.744343891402715e-05,
"loss": 0.2875,
"step": 1540
},
{
"epoch": 3.354978354978355,
"grad_norm": 1.2236874103546143,
"learning_rate": 1.7217194570135748e-05,
"loss": 0.277,
"step": 1550
},
{
"epoch": 3.3766233766233764,
"grad_norm": 1.3123564720153809,
"learning_rate": 1.6990950226244347e-05,
"loss": 0.2849,
"step": 1560
},
{
"epoch": 3.398268398268398,
"grad_norm": 1.8533962965011597,
"learning_rate": 1.676470588235294e-05,
"loss": 0.2907,
"step": 1570
},
{
"epoch": 3.41991341991342,
"grad_norm": 1.4100937843322754,
"learning_rate": 1.653846153846154e-05,
"loss": 0.2879,
"step": 1580
},
{
"epoch": 3.4415584415584415,
"grad_norm": 1.474001169204712,
"learning_rate": 1.631221719457014e-05,
"loss": 0.2824,
"step": 1590
},
{
"epoch": 3.463203463203463,
"grad_norm": 1.746888518333435,
"learning_rate": 1.6085972850678734e-05,
"loss": 0.2926,
"step": 1600
},
{
"epoch": 3.463203463203463,
"eval_loss": 0.10039258748292923,
"eval_runtime": 11.0205,
"eval_samples_per_second": 45.37,
"eval_steps_per_second": 0.726,
"step": 1600
},
{
"epoch": 3.484848484848485,
"grad_norm": 1.3926804065704346,
"learning_rate": 1.585972850678733e-05,
"loss": 0.2806,
"step": 1610
},
{
"epoch": 3.5064935064935066,
"grad_norm": 1.2975285053253174,
"learning_rate": 1.563348416289593e-05,
"loss": 0.2834,
"step": 1620
},
{
"epoch": 3.5281385281385282,
"grad_norm": 1.4987730979919434,
"learning_rate": 1.5407239819004526e-05,
"loss": 0.2877,
"step": 1630
},
{
"epoch": 3.54978354978355,
"grad_norm": 1.3945181369781494,
"learning_rate": 1.5180995475113122e-05,
"loss": 0.2571,
"step": 1640
},
{
"epoch": 3.571428571428571,
"grad_norm": 1.3280750513076782,
"learning_rate": 1.495475113122172e-05,
"loss": 0.2687,
"step": 1650
},
{
"epoch": 3.5930735930735933,
"grad_norm": 1.7335435152053833,
"learning_rate": 1.4728506787330317e-05,
"loss": 0.3212,
"step": 1660
},
{
"epoch": 3.6147186147186146,
"grad_norm": 1.2388490438461304,
"learning_rate": 1.4502262443438917e-05,
"loss": 0.2858,
"step": 1670
},
{
"epoch": 3.6363636363636362,
"grad_norm": 2.562535524368286,
"learning_rate": 1.4276018099547511e-05,
"loss": 0.2742,
"step": 1680
},
{
"epoch": 3.658008658008658,
"grad_norm": 1.321783185005188,
"learning_rate": 1.4049773755656109e-05,
"loss": 0.304,
"step": 1690
},
{
"epoch": 3.6796536796536796,
"grad_norm": 1.445235013961792,
"learning_rate": 1.3823529411764708e-05,
"loss": 0.3193,
"step": 1700
},
{
"epoch": 3.6796536796536796,
"eval_loss": 0.1012435331940651,
"eval_runtime": 11.0758,
"eval_samples_per_second": 45.144,
"eval_steps_per_second": 0.722,
"step": 1700
},
{
"epoch": 3.7012987012987013,
"grad_norm": 1.4029107093811035,
"learning_rate": 1.3597285067873302e-05,
"loss": 0.2957,
"step": 1710
},
{
"epoch": 3.722943722943723,
"grad_norm": 1.5768345594406128,
"learning_rate": 1.33710407239819e-05,
"loss": 0.2886,
"step": 1720
},
{
"epoch": 3.7445887445887447,
"grad_norm": 1.216724157333374,
"learning_rate": 1.31447963800905e-05,
"loss": 0.2843,
"step": 1730
},
{
"epoch": 3.7662337662337664,
"grad_norm": 1.4409873485565186,
"learning_rate": 1.2918552036199097e-05,
"loss": 0.2827,
"step": 1740
},
{
"epoch": 3.787878787878788,
"grad_norm": 1.0664066076278687,
"learning_rate": 1.2692307692307691e-05,
"loss": 0.2821,
"step": 1750
},
{
"epoch": 3.8095238095238093,
"grad_norm": 1.540581464767456,
"learning_rate": 1.246606334841629e-05,
"loss": 0.2689,
"step": 1760
},
{
"epoch": 3.8311688311688314,
"grad_norm": 1.1569033861160278,
"learning_rate": 1.2239819004524887e-05,
"loss": 0.2708,
"step": 1770
},
{
"epoch": 3.8528138528138527,
"grad_norm": 1.833857536315918,
"learning_rate": 1.2013574660633485e-05,
"loss": 0.3016,
"step": 1780
},
{
"epoch": 3.8744588744588744,
"grad_norm": 2.1259467601776123,
"learning_rate": 1.1787330316742082e-05,
"loss": 0.301,
"step": 1790
},
{
"epoch": 3.896103896103896,
"grad_norm": 1.0809746980667114,
"learning_rate": 1.156108597285068e-05,
"loss": 0.2567,
"step": 1800
},
{
"epoch": 3.896103896103896,
"eval_loss": 0.09367834776639938,
"eval_runtime": 11.1921,
"eval_samples_per_second": 44.674,
"eval_steps_per_second": 0.715,
"step": 1800
},
{
"epoch": 3.9177489177489178,
"grad_norm": 2.1658575534820557,
"learning_rate": 1.1334841628959276e-05,
"loss": 0.3016,
"step": 1810
},
{
"epoch": 3.9393939393939394,
"grad_norm": 1.4649549722671509,
"learning_rate": 1.1108597285067874e-05,
"loss": 0.2925,
"step": 1820
},
{
"epoch": 3.961038961038961,
"grad_norm": 1.6620761156082153,
"learning_rate": 1.0882352941176471e-05,
"loss": 0.2803,
"step": 1830
},
{
"epoch": 3.982683982683983,
"grad_norm": 1.129351258277893,
"learning_rate": 1.0656108597285067e-05,
"loss": 0.2821,
"step": 1840
},
{
"epoch": 4.004329004329004,
"grad_norm": 1.558613896369934,
"learning_rate": 1.0429864253393667e-05,
"loss": 0.2892,
"step": 1850
},
{
"epoch": 4.025974025974026,
"grad_norm": 1.2767349481582642,
"learning_rate": 1.0203619909502263e-05,
"loss": 0.2511,
"step": 1860
},
{
"epoch": 4.0476190476190474,
"grad_norm": 1.3410160541534424,
"learning_rate": 9.97737556561086e-06,
"loss": 0.2652,
"step": 1870
},
{
"epoch": 4.06926406926407,
"grad_norm": 1.3820221424102783,
"learning_rate": 9.751131221719458e-06,
"loss": 0.2781,
"step": 1880
},
{
"epoch": 4.090909090909091,
"grad_norm": 1.479778528213501,
"learning_rate": 9.524886877828054e-06,
"loss": 0.248,
"step": 1890
},
{
"epoch": 4.112554112554113,
"grad_norm": 1.3408429622650146,
"learning_rate": 9.298642533936652e-06,
"loss": 0.2416,
"step": 1900
},
{
"epoch": 4.112554112554113,
"eval_loss": 0.10034486651420593,
"eval_runtime": 11.0609,
"eval_samples_per_second": 45.204,
"eval_steps_per_second": 0.723,
"step": 1900
},
{
"epoch": 4.134199134199134,
"grad_norm": 1.6059556007385254,
"learning_rate": 9.07239819004525e-06,
"loss": 0.25,
"step": 1910
},
{
"epoch": 4.1558441558441555,
"grad_norm": 1.424112319946289,
"learning_rate": 8.846153846153847e-06,
"loss": 0.2625,
"step": 1920
},
{
"epoch": 4.177489177489178,
"grad_norm": 1.638130784034729,
"learning_rate": 8.619909502262443e-06,
"loss": 0.2623,
"step": 1930
},
{
"epoch": 4.199134199134199,
"grad_norm": 1.5797659158706665,
"learning_rate": 8.393665158371041e-06,
"loss": 0.2646,
"step": 1940
},
{
"epoch": 4.220779220779221,
"grad_norm": 1.5362834930419922,
"learning_rate": 8.167420814479639e-06,
"loss": 0.2544,
"step": 1950
},
{
"epoch": 4.242424242424242,
"grad_norm": 1.6381897926330566,
"learning_rate": 7.941176470588235e-06,
"loss": 0.255,
"step": 1960
},
{
"epoch": 4.264069264069264,
"grad_norm": 1.8974134922027588,
"learning_rate": 7.714932126696834e-06,
"loss": 0.2762,
"step": 1970
},
{
"epoch": 4.285714285714286,
"grad_norm": 1.830533504486084,
"learning_rate": 7.48868778280543e-06,
"loss": 0.2733,
"step": 1980
},
{
"epoch": 4.307359307359308,
"grad_norm": 1.5712575912475586,
"learning_rate": 7.262443438914028e-06,
"loss": 0.256,
"step": 1990
},
{
"epoch": 4.329004329004329,
"grad_norm": 1.6964036226272583,
"learning_rate": 7.0361990950226245e-06,
"loss": 0.2512,
"step": 2000
},
{
"epoch": 4.329004329004329,
"eval_loss": 0.09686653316020966,
"eval_runtime": 11.0207,
"eval_samples_per_second": 45.369,
"eval_steps_per_second": 0.726,
"step": 2000
},
{
"epoch": 4.35064935064935,
"grad_norm": 1.8361965417861938,
"learning_rate": 6.809954751131221e-06,
"loss": 0.243,
"step": 2010
},
{
"epoch": 4.372294372294372,
"grad_norm": 1.6544777154922485,
"learning_rate": 6.58371040723982e-06,
"loss": 0.2711,
"step": 2020
},
{
"epoch": 4.393939393939394,
"grad_norm": 1.1742023229599,
"learning_rate": 6.357466063348416e-06,
"loss": 0.2406,
"step": 2030
},
{
"epoch": 4.415584415584416,
"grad_norm": 1.4244996309280396,
"learning_rate": 6.131221719457014e-06,
"loss": 0.243,
"step": 2040
},
{
"epoch": 4.437229437229437,
"grad_norm": 1.6553417444229126,
"learning_rate": 5.904977375565611e-06,
"loss": 0.2433,
"step": 2050
},
{
"epoch": 4.458874458874459,
"grad_norm": 1.690132737159729,
"learning_rate": 5.678733031674208e-06,
"loss": 0.2563,
"step": 2060
},
{
"epoch": 4.48051948051948,
"grad_norm": 1.625807762145996,
"learning_rate": 5.452488687782806e-06,
"loss": 0.2795,
"step": 2070
},
{
"epoch": 4.5021645021645025,
"grad_norm": 1.5032762289047241,
"learning_rate": 5.226244343891403e-06,
"loss": 0.2638,
"step": 2080
},
{
"epoch": 4.523809523809524,
"grad_norm": 1.5924805402755737,
"learning_rate": 5e-06,
"loss": 0.2327,
"step": 2090
},
{
"epoch": 4.545454545454545,
"grad_norm": 1.765118956565857,
"learning_rate": 4.773755656108597e-06,
"loss": 0.235,
"step": 2100
},
{
"epoch": 4.545454545454545,
"eval_loss": 0.10021113604307175,
"eval_runtime": 11.006,
"eval_samples_per_second": 45.43,
"eval_steps_per_second": 0.727,
"step": 2100
},
{
"epoch": 4.567099567099567,
"grad_norm": 1.4232510328292847,
"learning_rate": 4.547511312217195e-06,
"loss": 0.2444,
"step": 2110
},
{
"epoch": 4.588744588744589,
"grad_norm": 1.6832308769226074,
"learning_rate": 4.321266968325792e-06,
"loss": 0.282,
"step": 2120
},
{
"epoch": 4.6103896103896105,
"grad_norm": 1.4508180618286133,
"learning_rate": 4.0950226244343895e-06,
"loss": 0.2541,
"step": 2130
},
{
"epoch": 4.632034632034632,
"grad_norm": 1.5618845224380493,
"learning_rate": 3.868778280542986e-06,
"loss": 0.2344,
"step": 2140
},
{
"epoch": 4.653679653679654,
"grad_norm": 1.700337529182434,
"learning_rate": 3.642533936651584e-06,
"loss": 0.2605,
"step": 2150
},
{
"epoch": 4.675324675324675,
"grad_norm": 1.8766915798187256,
"learning_rate": 3.416289592760181e-06,
"loss": 0.2657,
"step": 2160
},
{
"epoch": 4.696969696969697,
"grad_norm": 1.39222252368927,
"learning_rate": 3.190045248868778e-06,
"loss": 0.2724,
"step": 2170
},
{
"epoch": 4.7186147186147185,
"grad_norm": 1.7200310230255127,
"learning_rate": 2.9638009049773754e-06,
"loss": 0.2473,
"step": 2180
},
{
"epoch": 4.740259740259741,
"grad_norm": 1.4263789653778076,
"learning_rate": 2.737556561085973e-06,
"loss": 0.2735,
"step": 2190
},
{
"epoch": 4.761904761904762,
"grad_norm": 1.4629650115966797,
"learning_rate": 2.5113122171945704e-06,
"loss": 0.2453,
"step": 2200
},
{
"epoch": 4.761904761904762,
"eval_loss": 0.09669920057058334,
"eval_runtime": 11.2945,
"eval_samples_per_second": 44.269,
"eval_steps_per_second": 0.708,
"step": 2200
},
{
"epoch": 4.783549783549784,
"grad_norm": 1.5298959016799927,
"learning_rate": 2.2850678733031673e-06,
"loss": 0.2527,
"step": 2210
},
{
"epoch": 4.805194805194805,
"grad_norm": 1.4086050987243652,
"learning_rate": 2.058823529411765e-06,
"loss": 0.2351,
"step": 2220
},
{
"epoch": 4.8268398268398265,
"grad_norm": 1.6125555038452148,
"learning_rate": 1.8325791855203622e-06,
"loss": 0.272,
"step": 2230
},
{
"epoch": 4.848484848484849,
"grad_norm": 1.69878089427948,
"learning_rate": 1.6063348416289593e-06,
"loss": 0.2545,
"step": 2240
},
{
"epoch": 4.87012987012987,
"grad_norm": 1.387439250946045,
"learning_rate": 1.3800904977375566e-06,
"loss": 0.2617,
"step": 2250
},
{
"epoch": 4.891774891774892,
"grad_norm": 1.551837682723999,
"learning_rate": 1.153846153846154e-06,
"loss": 0.2384,
"step": 2260
},
{
"epoch": 4.913419913419913,
"grad_norm": 1.6093473434448242,
"learning_rate": 9.276018099547512e-07,
"loss": 0.2494,
"step": 2270
},
{
"epoch": 4.935064935064935,
"grad_norm": 1.4138660430908203,
"learning_rate": 7.013574660633485e-07,
"loss": 0.2371,
"step": 2280
},
{
"epoch": 4.956709956709957,
"grad_norm": 1.7874048948287964,
"learning_rate": 4.751131221719457e-07,
"loss": 0.2562,
"step": 2290
},
{
"epoch": 4.978354978354979,
"grad_norm": 1.470076322555542,
"learning_rate": 2.4886877828054297e-07,
"loss": 0.2483,
"step": 2300
},
{
"epoch": 4.978354978354979,
"eval_loss": 0.09722720086574554,
"eval_runtime": 11.0178,
"eval_samples_per_second": 45.381,
"eval_steps_per_second": 0.726,
"step": 2300
},
{
"epoch": 5.0,
"grad_norm": 1.6692209243774414,
"learning_rate": 2.2624434389140274e-08,
"loss": 0.2477,
"step": 2310
}
],
"logging_steps": 10,
"max_steps": 2310,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.5716476802941583e+19,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}