{
  "best_metric": 0.9725916385650635,
  "best_model_checkpoint": "./outputs/instruct-lora-8b-aplly_chat_template-environmental/checkpoint-1600",
  "epoch": 1.8870539663815984,
  "eval_steps": 20,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011795930404010617,
      "eval_loss": 1.42765212059021,
      "eval_runtime": 63.0401,
      "eval_samples_per_second": 23.905,
      "eval_steps_per_second": 5.98,
      "step": 1
    },
    {
      "epoch": 0.023591860808021232,
      "grad_norm": 0.8140115737915039,
      "learning_rate": 2.3622047244094487e-06,
      "loss": 1.4383,
      "step": 20
    },
    {
      "epoch": 0.023591860808021232,
      "eval_loss": 1.4257409572601318,
      "eval_runtime": 63.0141,
      "eval_samples_per_second": 23.915,
      "eval_steps_per_second": 5.983,
      "step": 20
    },
    {
      "epoch": 0.047183721616042465,
      "grad_norm": 0.8540558218955994,
      "learning_rate": 4.7244094488188975e-06,
      "loss": 1.4736,
      "step": 40
    },
    {
      "epoch": 0.047183721616042465,
      "eval_loss": 1.4058444499969482,
      "eval_runtime": 65.5526,
      "eval_samples_per_second": 22.989,
      "eval_steps_per_second": 5.751,
      "step": 40
    },
    {
      "epoch": 0.0707755824240637,
      "grad_norm": 0.9564130902290344,
      "learning_rate": 7.086614173228346e-06,
      "loss": 1.3855,
      "step": 60
    },
    {
      "epoch": 0.0707755824240637,
      "eval_loss": 1.3293768167495728,
      "eval_runtime": 62.9854,
      "eval_samples_per_second": 23.926,
      "eval_steps_per_second": 5.986,
      "step": 60
    },
    {
      "epoch": 0.09436744323208493,
      "grad_norm": 0.9375326037406921,
      "learning_rate": 9.448818897637795e-06,
      "loss": 1.3151,
      "step": 80
    },
    {
      "epoch": 0.09436744323208493,
      "eval_loss": 1.256630301475525,
      "eval_runtime": 62.9741,
      "eval_samples_per_second": 23.93,
      "eval_steps_per_second": 5.987,
      "step": 80
    },
    {
      "epoch": 0.11795930404010617,
      "grad_norm": 0.9875860810279846,
      "learning_rate": 1.1811023622047245e-05,
      "loss": 1.2527,
      "step": 100
    },
    {
      "epoch": 0.11795930404010617,
      "eval_loss": 1.2264838218688965,
      "eval_runtime": 65.3152,
      "eval_samples_per_second": 23.073,
      "eval_steps_per_second": 5.772,
      "step": 100
    },
    {
      "epoch": 0.1415511648481274,
      "grad_norm": 1.0547633171081543,
      "learning_rate": 1.4173228346456692e-05,
      "loss": 1.2557,
      "step": 120
    },
    {
      "epoch": 0.1415511648481274,
      "eval_loss": 1.2046794891357422,
      "eval_runtime": 62.9226,
      "eval_samples_per_second": 23.95,
      "eval_steps_per_second": 5.991,
      "step": 120
    },
    {
      "epoch": 0.16514302565614863,
      "grad_norm": 1.010538101196289,
      "learning_rate": 1.6535433070866142e-05,
      "loss": 1.2405,
      "step": 140
    },
    {
      "epoch": 0.16514302565614863,
      "eval_loss": 1.188104271888733,
      "eval_runtime": 62.9407,
      "eval_samples_per_second": 23.943,
      "eval_steps_per_second": 5.99,
      "step": 140
    },
    {
      "epoch": 0.18873488646416986,
      "grad_norm": 1.1231751441955566,
      "learning_rate": 1.889763779527559e-05,
      "loss": 1.2074,
      "step": 160
    },
    {
      "epoch": 0.18873488646416986,
      "eval_loss": 1.1720376014709473,
      "eval_runtime": 62.9691,
      "eval_samples_per_second": 23.932,
      "eval_steps_per_second": 5.987,
      "step": 160
    },
    {
      "epoch": 0.21232674727219109,
      "grad_norm": 1.2803903818130493,
      "learning_rate": 2.1259842519685038e-05,
      "loss": 1.1897,
      "step": 180
    },
    {
      "epoch": 0.21232674727219109,
      "eval_loss": 1.1597559452056885,
      "eval_runtime": 63.1045,
      "eval_samples_per_second": 23.881,
      "eval_steps_per_second": 5.974,
      "step": 180
    },
    {
      "epoch": 0.23591860808021234,
      "grad_norm": 1.2758204936981201,
      "learning_rate": 2.362204724409449e-05,
      "loss": 1.145,
      "step": 200
    },
    {
      "epoch": 0.23591860808021234,
      "eval_loss": 1.1493200063705444,
      "eval_runtime": 65.8866,
      "eval_samples_per_second": 22.873,
      "eval_steps_per_second": 5.722,
      "step": 200
    },
    {
      "epoch": 0.25951046888823354,
      "grad_norm": 1.517013430595398,
      "learning_rate": 2.5984251968503937e-05,
      "loss": 1.1508,
      "step": 220
    },
    {
      "epoch": 0.25951046888823354,
      "eval_loss": 1.1411106586456299,
      "eval_runtime": 62.986,
      "eval_samples_per_second": 23.926,
      "eval_steps_per_second": 5.985,
      "step": 220
    },
    {
      "epoch": 0.2831023296962548,
      "grad_norm": 1.6017550230026245,
      "learning_rate": 2.8346456692913385e-05,
      "loss": 1.1406,
      "step": 240
    },
    {
      "epoch": 0.2831023296962548,
      "eval_loss": 1.1336663961410522,
      "eval_runtime": 62.9587,
      "eval_samples_per_second": 23.936,
      "eval_steps_per_second": 5.988,
      "step": 240
    },
    {
      "epoch": 0.30669419050427604,
      "grad_norm": 1.5281150341033936,
      "learning_rate": 2.9999490518144496e-05,
      "loss": 1.1156,
      "step": 260
    },
    {
      "epoch": 0.30669419050427604,
      "eval_loss": 1.1270569562911987,
      "eval_runtime": 66.1576,
      "eval_samples_per_second": 22.779,
      "eval_steps_per_second": 5.699,
      "step": 260
    },
    {
      "epoch": 0.33028605131229727,
      "grad_norm": 1.4530911445617676,
      "learning_rate": 2.9990434025704478e-05,
      "loss": 1.1439,
      "step": 280
    },
    {
      "epoch": 0.33028605131229727,
      "eval_loss": 1.118715524673462,
      "eval_runtime": 62.9289,
      "eval_samples_per_second": 23.948,
      "eval_steps_per_second": 5.991,
      "step": 280
    },
    {
      "epoch": 0.3538779121203185,
      "grad_norm": 1.4522110223770142,
      "learning_rate": 2.9970063582150774e-05,
      "loss": 1.0991,
      "step": 300
    },
    {
      "epoch": 0.3538779121203185,
      "eval_loss": 1.1142727136611938,
      "eval_runtime": 62.9463,
      "eval_samples_per_second": 23.941,
      "eval_steps_per_second": 5.989,
      "step": 300
    },
    {
      "epoch": 0.3774697729283397,
      "grad_norm": 1.6753257513046265,
      "learning_rate": 2.9938394561968347e-05,
      "loss": 1.1037,
      "step": 320
    },
    {
      "epoch": 0.3774697729283397,
      "eval_loss": 1.1066044569015503,
      "eval_runtime": 62.9455,
      "eval_samples_per_second": 23.941,
      "eval_steps_per_second": 5.989,
      "step": 320
    },
    {
      "epoch": 0.40106163373636095,
      "grad_norm": 1.5857524871826172,
      "learning_rate": 2.9895450867183358e-05,
      "loss": 1.0821,
      "step": 340
    },
    {
      "epoch": 0.40106163373636095,
      "eval_loss": 1.1023849248886108,
      "eval_runtime": 62.9815,
      "eval_samples_per_second": 23.928,
      "eval_steps_per_second": 5.986,
      "step": 340
    },
    {
      "epoch": 0.42465349454438217,
      "grad_norm": 1.6321624517440796,
      "learning_rate": 2.9841264909323215e-05,
      "loss": 1.0355,
      "step": 360
    },
    {
      "epoch": 0.42465349454438217,
      "eval_loss": 1.0976252555847168,
      "eval_runtime": 63.0759,
      "eval_samples_per_second": 23.892,
      "eval_steps_per_second": 5.977,
      "step": 360
    },
    {
      "epoch": 0.4482453553524034,
      "grad_norm": 1.7007124423980713,
      "learning_rate": 2.9775877584954185e-05,
      "loss": 1.0705,
      "step": 380
    },
    {
      "epoch": 0.4482453553524034,
      "eval_loss": 1.0898144245147705,
      "eval_runtime": 63.0529,
      "eval_samples_per_second": 23.901,
      "eval_steps_per_second": 5.979,
      "step": 380
    },
    {
      "epoch": 0.4718372161604247,
      "grad_norm": 1.6532444953918457,
      "learning_rate": 2.9699338244814873e-05,
      "loss": 1.058,
      "step": 400
    },
    {
      "epoch": 0.4718372161604247,
      "eval_loss": 1.0839428901672363,
      "eval_runtime": 63.0318,
      "eval_samples_per_second": 23.909,
      "eval_steps_per_second": 5.981,
      "step": 400
    },
    {
      "epoch": 0.4954290769684459,
      "grad_norm": 1.7736274003982544,
      "learning_rate": 2.961170465656906e-05,
      "loss": 1.073,
      "step": 420
    },
    {
      "epoch": 0.4954290769684459,
      "eval_loss": 1.0811110734939575,
      "eval_runtime": 65.7766,
      "eval_samples_per_second": 22.911,
      "eval_steps_per_second": 5.732,
      "step": 420
    },
    {
      "epoch": 0.5190209377764671,
      "grad_norm": 1.7278027534484863,
      "learning_rate": 2.9513042961205828e-05,
      "loss": 1.0669,
      "step": 440
    },
    {
      "epoch": 0.5190209377764671,
      "eval_loss": 1.0773712396621704,
      "eval_runtime": 63.1642,
      "eval_samples_per_second": 23.858,
      "eval_steps_per_second": 5.969,
      "step": 440
    },
    {
      "epoch": 0.5426127985844883,
      "grad_norm": 1.7342020273208618,
      "learning_rate": 2.940342762312002e-05,
      "loss": 1.0742,
      "step": 460
    },
    {
      "epoch": 0.5426127985844883,
      "eval_loss": 1.07448410987854,
      "eval_runtime": 63.1172,
      "eval_samples_per_second": 23.876,
      "eval_steps_per_second": 5.973,
      "step": 460
    },
    {
      "epoch": 0.5662046593925096,
      "grad_norm": 1.688236117362976,
      "learning_rate": 2.9282941373910622e-05,
      "loss": 1.0391,
      "step": 480
    },
    {
      "epoch": 0.5662046593925096,
      "eval_loss": 1.0696014165878296,
      "eval_runtime": 63.5007,
      "eval_samples_per_second": 23.732,
      "eval_steps_per_second": 5.937,
      "step": 480
    },
    {
      "epoch": 0.5897965202005309,
      "grad_norm": 1.6653029918670654,
      "learning_rate": 2.915167514993952e-05,
      "loss": 1.0388,
      "step": 500
    },
    {
      "epoch": 0.5897965202005309,
      "eval_loss": 1.0648998022079468,
      "eval_runtime": 63.0976,
      "eval_samples_per_second": 23.884,
      "eval_steps_per_second": 5.975,
      "step": 500
    },
    {
      "epoch": 0.6133883810085521,
      "grad_norm": 1.7940328121185303,
      "learning_rate": 2.9009728023697777e-05,
      "loss": 1.0483,
      "step": 520
    },
    {
      "epoch": 0.6133883810085521,
      "eval_loss": 1.0635266304016113,
      "eval_runtime": 63.1023,
      "eval_samples_per_second": 23.882,
      "eval_steps_per_second": 5.974,
      "step": 520
    },
    {
      "epoch": 0.6369802418165733,
      "grad_norm": 1.7853456735610962,
      "learning_rate": 2.8857207129031153e-05,
      "loss": 1.0767,
      "step": 540
    },
    {
      "epoch": 0.6369802418165733,
      "eval_loss": 1.0566504001617432,
      "eval_runtime": 63.0964,
      "eval_samples_per_second": 23.884,
      "eval_steps_per_second": 5.975,
      "step": 540
    },
    {
      "epoch": 0.6605721026245945,
      "grad_norm": 1.8145803213119507,
      "learning_rate": 2.869422758028145e-05,
      "loss": 1.0273,
      "step": 560
    },
    {
      "epoch": 0.6605721026245945,
      "eval_loss": 1.0557910203933716,
      "eval_runtime": 63.1078,
      "eval_samples_per_second": 23.88,
      "eval_steps_per_second": 5.974,
      "step": 560
    },
    {
      "epoch": 0.6841639634326158,
      "grad_norm": 1.7679259777069092,
      "learning_rate": 2.852091238540454e-05,
      "loss": 1.021,
      "step": 580
    },
    {
      "epoch": 0.6841639634326158,
      "eval_loss": 1.0533658266067505,
      "eval_runtime": 65.8301,
      "eval_samples_per_second": 22.892,
      "eval_steps_per_second": 5.727,
      "step": 580
    },
    {
      "epoch": 0.707755824240637,
      "grad_norm": 1.6286741495132446,
      "learning_rate": 2.8337392353130755e-05,
      "loss": 1.0429,
      "step": 600
    },
    {
      "epoch": 0.707755824240637,
      "eval_loss": 1.0482341051101685,
      "eval_runtime": 63.1283,
      "eval_samples_per_second": 23.872,
      "eval_steps_per_second": 5.972,
      "step": 600
    },
    {
      "epoch": 0.7313476850486582,
      "grad_norm": 2.0246284008026123,
      "learning_rate": 2.81438059942377e-05,
      "loss": 1.001,
      "step": 620
    },
    {
      "epoch": 0.7313476850486582,
      "eval_loss": 1.0442626476287842,
      "eval_runtime": 63.0773,
      "eval_samples_per_second": 23.891,
      "eval_steps_per_second": 5.977,
      "step": 620
    },
    {
      "epoch": 0.7549395458566794,
      "grad_norm": 1.8399453163146973,
      "learning_rate": 2.7940299417009968e-05,
      "loss": 1.0257,
      "step": 640
    },
    {
      "epoch": 0.7549395458566794,
      "eval_loss": 1.0410016775131226,
      "eval_runtime": 66.0639,
      "eval_samples_per_second": 22.811,
      "eval_steps_per_second": 5.707,
      "step": 640
    },
    {
      "epoch": 0.7785314066647007,
      "grad_norm": 1.7166261672973633,
      "learning_rate": 2.772702621696468e-05,
      "loss": 0.9959,
      "step": 660
    },
    {
      "epoch": 0.7785314066647007,
      "eval_loss": 1.036692500114441,
      "eval_runtime": 62.9935,
      "eval_samples_per_second": 23.923,
      "eval_steps_per_second": 5.985,
      "step": 660
    },
    {
      "epoch": 0.8021232674727219,
      "grad_norm": 1.8086529970169067,
      "learning_rate": 2.7504147360926084e-05,
      "loss": 0.9912,
      "step": 680
    },
    {
      "epoch": 0.8021232674727219,
      "eval_loss": 1.0342631340026855,
      "eval_runtime": 62.9732,
      "eval_samples_per_second": 23.931,
      "eval_steps_per_second": 5.987,
      "step": 680
    },
    {
      "epoch": 0.8257151282807431,
      "grad_norm": 1.7481584548950195,
      "learning_rate": 2.7271831065536684e-05,
      "loss": 0.9986,
      "step": 700
    },
    {
      "epoch": 0.8257151282807431,
      "eval_loss": 1.0320111513137817,
      "eval_runtime": 63.187,
      "eval_samples_per_second": 23.85,
      "eval_steps_per_second": 5.966,
      "step": 700
    },
    {
      "epoch": 0.8493069890887643,
      "grad_norm": 1.8035798072814941,
      "learning_rate": 2.7030252670296612e-05,
      "loss": 0.9972,
      "step": 720
    },
    {
      "epoch": 0.8493069890887643,
      "eval_loss": 1.0306118726730347,
      "eval_runtime": 62.9945,
      "eval_samples_per_second": 23.923,
      "eval_steps_per_second": 5.985,
      "step": 720
    },
    {
      "epoch": 0.8728988498967856,
      "grad_norm": 1.7504149675369263,
      "learning_rate": 2.677959450522709e-05,
      "loss": 0.9923,
      "step": 740
    },
    {
      "epoch": 0.8728988498967856,
      "eval_loss": 1.028536081314087,
      "eval_runtime": 66.0048,
      "eval_samples_per_second": 22.832,
      "eval_steps_per_second": 5.712,
      "step": 740
    },
    {
      "epoch": 0.8964907107048068,
      "grad_norm": 1.9125969409942627,
      "learning_rate": 2.6520045753257774e-05,
      "loss": 0.9862,
      "step": 760
    },
    {
      "epoch": 0.8964907107048068,
      "eval_loss": 1.0277767181396484,
      "eval_runtime": 62.8849,
      "eval_samples_per_second": 23.964,
      "eval_steps_per_second": 5.995,
      "step": 760
    },
    {
      "epoch": 0.9200825715128281,
      "grad_norm": 1.7713780403137207,
      "learning_rate": 2.625180230744195e-05,
      "loss": 1.0248,
      "step": 780
    },
    {
      "epoch": 0.9200825715128281,
      "eval_loss": 1.024271845817566,
      "eval_runtime": 62.9468,
      "eval_samples_per_second": 23.941,
      "eval_steps_per_second": 5.989,
      "step": 780
    },
    {
      "epoch": 0.9436744323208494,
      "grad_norm": 1.794228196144104,
      "learning_rate": 2.597506662310728e-05,
      "loss": 0.9898,
      "step": 800
    },
    {
      "epoch": 0.9436744323208494,
      "eval_loss": 1.024512767791748,
      "eval_runtime": 65.8042,
      "eval_samples_per_second": 22.901,
      "eval_steps_per_second": 5.729,
      "step": 800
    },
    {
      "epoch": 0.9672662931288706,
      "grad_norm": 2.150176525115967,
      "learning_rate": 2.569004756505373e-05,
      "loss": 0.9838,
      "step": 820
    },
    {
      "epoch": 0.9672662931288706,
      "eval_loss": 1.0203757286071777,
      "eval_runtime": 63.2378,
      "eval_samples_per_second": 23.831,
      "eval_steps_per_second": 5.962,
      "step": 820
    },
    {
      "epoch": 0.9908581539368918,
      "grad_norm": 1.892907977104187,
      "learning_rate": 2.539696024991391e-05,
      "loss": 0.9655,
      "step": 840
    },
    {
      "epoch": 0.9908581539368918,
      "eval_loss": 1.0187581777572632,
      "eval_runtime": 62.8975,
      "eval_samples_per_second": 23.96,
      "eval_steps_per_second": 5.994,
      "step": 840
    },
    {
      "epoch": 1.0141551164848128,
      "grad_norm": 1.8649617433547974,
      "learning_rate": 2.5096025883795e-05,
      "loss": 0.9747,
      "step": 860
    },
    {
      "epoch": 1.0141551164848128,
      "eval_loss": 1.0219627618789673,
      "eval_runtime": 62.8985,
      "eval_samples_per_second": 23.959,
      "eval_steps_per_second": 5.994,
      "step": 860
    },
    {
      "epoch": 1.037746977292834,
      "grad_norm": 1.9797245264053345,
      "learning_rate": 2.4787471595324554e-05,
      "loss": 0.9133,
      "step": 880
    },
    {
      "epoch": 1.037746977292834,
      "eval_loss": 1.0162080526351929,
      "eval_runtime": 62.9338,
      "eval_samples_per_second": 23.946,
      "eval_steps_per_second": 5.99,
      "step": 880
    },
    {
      "epoch": 1.0613388381008553,
      "grad_norm": 1.9416215419769287,
      "learning_rate": 2.447153026422637e-05,
      "loss": 0.9122,
      "step": 900
    },
    {
      "epoch": 1.0613388381008553,
      "eval_loss": 1.014188528060913,
      "eval_runtime": 62.9073,
      "eval_samples_per_second": 23.956,
      "eval_steps_per_second": 5.993,
      "step": 900
    },
    {
      "epoch": 1.0849306989088765,
      "grad_norm": 2.022336721420288,
      "learning_rate": 2.4148440345555778e-05,
      "loss": 0.9089,
      "step": 920
    },
    {
      "epoch": 1.0849306989088765,
      "eval_loss": 1.0171178579330444,
      "eval_runtime": 62.9354,
      "eval_samples_per_second": 23.945,
      "eval_steps_per_second": 5.99,
      "step": 920
    },
    {
      "epoch": 1.1085225597168977,
      "grad_norm": 2.2142956256866455,
      "learning_rate": 2.38184456897269e-05,
      "loss": 0.9315,
      "step": 940
    },
    {
      "epoch": 1.1085225597168977,
      "eval_loss": 1.0155071020126343,
      "eval_runtime": 63.3545,
      "eval_samples_per_second": 23.787,
      "eval_steps_per_second": 5.951,
      "step": 940
    },
    {
      "epoch": 1.132114420524919,
      "grad_norm": 1.9037110805511475,
      "learning_rate": 2.3481795358467866e-05,
      "loss": 0.9469,
      "step": 960
    },
    {
      "epoch": 1.132114420524919,
      "eval_loss": 1.0110633373260498,
      "eval_runtime": 64.9111,
      "eval_samples_per_second": 23.216,
      "eval_steps_per_second": 5.808,
      "step": 960
    },
    {
      "epoch": 1.1557062813329402,
      "grad_norm": 2.169173240661621,
      "learning_rate": 2.3138743436842772e-05,
      "loss": 0.9255,
      "step": 980
    },
    {
      "epoch": 1.1557062813329402,
      "eval_loss": 1.0110522508621216,
      "eval_runtime": 62.9115,
      "eval_samples_per_second": 23.954,
      "eval_steps_per_second": 5.993,
      "step": 980
    },
    {
      "epoch": 1.1792981421409614,
      "grad_norm": 1.8711203336715698,
      "learning_rate": 2.278954884148232e-05,
      "loss": 0.9322,
      "step": 1000
    },
    {
      "epoch": 1.1792981421409614,
      "eval_loss": 1.0103003978729248,
      "eval_runtime": 62.9309,
      "eval_samples_per_second": 23.947,
      "eval_steps_per_second": 5.991,
      "step": 1000
    },
    {
      "epoch": 1.2028900029489826,
      "grad_norm": 1.9024525880813599,
      "learning_rate": 2.2434475125167866e-05,
      "loss": 0.8943,
      "step": 1020
    },
    {
      "epoch": 1.2028900029489826,
      "eval_loss": 1.0080772638320923,
      "eval_runtime": 63.4989,
      "eval_samples_per_second": 23.733,
      "eval_steps_per_second": 5.937,
      "step": 1020
    },
    {
      "epoch": 1.2264818637570039,
      "grad_norm": 2.0306591987609863,
      "learning_rate": 2.207379027791632e-05,
      "loss": 0.8974,
      "step": 1040
    },
    {
      "epoch": 1.2264818637570039,
      "eval_loss": 1.005001187324524,
      "eval_runtime": 62.9683,
      "eval_samples_per_second": 23.933,
      "eval_steps_per_second": 5.987,
      "step": 1040
    },
    {
      "epoch": 1.250073724565025,
      "grad_norm": 2.0461585521698,
      "learning_rate": 2.170776652471611e-05,
      "loss": 0.8922,
      "step": 1060
    },
    {
      "epoch": 1.250073724565025,
      "eval_loss": 1.0041309595108032,
      "eval_runtime": 62.9406,
      "eval_samples_per_second": 23.943,
      "eval_steps_per_second": 5.99,
      "step": 1060
    },
    {
      "epoch": 1.2736655853730463,
      "grad_norm": 2.301267385482788,
      "learning_rate": 2.133668012006682e-05,
      "loss": 0.9341,
      "step": 1080
    },
    {
      "epoch": 1.2736655853730463,
      "eval_loss": 1.0036579370498657,
      "eval_runtime": 62.8908,
      "eval_samples_per_second": 23.962,
      "eval_steps_per_second": 5.995,
      "step": 1080
    },
    {
      "epoch": 1.2972574461810675,
      "grad_norm": 2.170428991317749,
      "learning_rate": 2.096081113947753e-05,
      "loss": 0.9075,
      "step": 1100
    },
    {
      "epoch": 1.2972574461810675,
      "eval_loss": 1.0047935247421265,
      "eval_runtime": 62.9099,
      "eval_samples_per_second": 23.955,
      "eval_steps_per_second": 5.993,
      "step": 1100
    },
    {
      "epoch": 1.3208493069890888,
      "grad_norm": 2.1537463665008545,
      "learning_rate": 2.058044326808132e-05,
      "loss": 0.9296,
      "step": 1120
    },
    {
      "epoch": 1.3208493069890888,
      "eval_loss": 1.0024445056915283,
      "eval_runtime": 64.9442,
      "eval_samples_per_second": 23.205,
      "eval_steps_per_second": 5.805,
      "step": 1120
    },
    {
      "epoch": 1.34444116779711,
      "grad_norm": 2.0056726932525635,
      "learning_rate": 2.0195863586525413e-05,
      "loss": 0.9133,
      "step": 1140
    },
    {
      "epoch": 1.34444116779711,
      "eval_loss": 1.0002470016479492,
      "eval_runtime": 62.892,
      "eval_samples_per_second": 23.962,
      "eval_steps_per_second": 5.994,
      "step": 1140
    },
    {
      "epoch": 1.3680330286051312,
      "grad_norm": 2.3192081451416016,
      "learning_rate": 1.9807362354298556e-05,
      "loss": 0.9447,
      "step": 1160
    },
    {
      "epoch": 1.3680330286051312,
      "eval_loss": 1.0005617141723633,
      "eval_runtime": 62.9711,
      "eval_samples_per_second": 23.932,
      "eval_steps_per_second": 5.987,
      "step": 1160
    },
    {
      "epoch": 1.3916248894131524,
      "grad_norm": 2.085900068283081,
      "learning_rate": 1.9415232790659206e-05,
      "loss": 0.8843,
      "step": 1180
    },
    {
      "epoch": 1.3916248894131524,
      "eval_loss": 0.9992862939834595,
      "eval_runtime": 65.4435,
      "eval_samples_per_second": 23.027,
      "eval_steps_per_second": 5.761,
      "step": 1180
    },
    {
      "epoch": 1.4152167502211737,
      "grad_norm": 2.2436399459838867,
      "learning_rate": 1.9019770853329856e-05,
      "loss": 0.9046,
      "step": 1200
    },
    {
      "epoch": 1.4152167502211737,
      "eval_loss": 0.996922492980957,
      "eval_runtime": 62.9124,
      "eval_samples_per_second": 23.954,
      "eval_steps_per_second": 5.992,
      "step": 1200
    },
    {
      "epoch": 1.4388086110291949,
      "grad_norm": 2.1963181495666504,
      "learning_rate": 1.8621275015124457e-05,
      "loss": 0.8844,
      "step": 1220
    },
    {
      "epoch": 1.4388086110291949,
      "eval_loss": 0.9958762526512146,
      "eval_runtime": 62.9054,
      "eval_samples_per_second": 23.957,
      "eval_steps_per_second": 5.993,
      "step": 1220
    },
    {
      "epoch": 1.462400471837216,
      "grad_norm": 2.19089674949646,
      "learning_rate": 1.82200460386777e-05,
      "loss": 0.923,
      "step": 1240
    },
    {
      "epoch": 1.462400471837216,
      "eval_loss": 0.9949436783790588,
      "eval_runtime": 62.9162,
      "eval_samples_per_second": 23.952,
      "eval_steps_per_second": 5.992,
      "step": 1240
    },
    {
      "epoch": 1.4859923326452373,
      "grad_norm": 2.2525527477264404,
      "learning_rate": 1.7816386749445935e-05,
      "loss": 0.8587,
      "step": 1260
    },
    {
      "epoch": 1.4859923326452373,
      "eval_loss": 0.9949393272399902,
      "eval_runtime": 62.931,
      "eval_samples_per_second": 23.947,
      "eval_steps_per_second": 5.991,
      "step": 1260
    },
    {
      "epoch": 1.5095841934532586,
      "grad_norm": 2.4868662357330322,
      "learning_rate": 1.7410601807151304e-05,
      "loss": 0.8878,
      "step": 1280
    },
    {
      "epoch": 1.5095841934532586,
      "eval_loss": 0.9940009713172913,
      "eval_runtime": 64.7991,
      "eval_samples_per_second": 23.256,
      "eval_steps_per_second": 5.818,
      "step": 1280
    },
    {
      "epoch": 1.53317605426128,
      "grad_norm": 1.9369481801986694,
      "learning_rate": 1.700299747584139e-05,
      "loss": 0.904,
      "step": 1300
    },
    {
      "epoch": 1.53317605426128,
      "eval_loss": 0.9907172918319702,
      "eval_runtime": 62.932,
      "eval_samples_per_second": 23.946,
      "eval_steps_per_second": 5.991,
      "step": 1300
    },
    {
      "epoch": 1.556767915069301,
      "grad_norm": 2.2156777381896973,
      "learning_rate": 1.659388139273806e-05,
      "loss": 0.9121,
      "step": 1320
    },
    {
      "epoch": 1.556767915069301,
      "eval_loss": 0.9908357262611389,
      "eval_runtime": 62.9132,
      "eval_samples_per_second": 23.954,
      "eval_steps_per_second": 5.992,
      "step": 1320
    },
    {
      "epoch": 1.5803597758773225,
      "grad_norm": 2.393859386444092,
      "learning_rate": 1.6183562336049867e-05,
      "loss": 0.9023,
      "step": 1340
    },
    {
      "epoch": 1.5803597758773225,
      "eval_loss": 0.9863225221633911,
      "eval_runtime": 65.5958,
      "eval_samples_per_second": 22.974,
      "eval_steps_per_second": 5.747,
      "step": 1340
    },
    {
      "epoch": 1.6039516366853435,
      "grad_norm": 2.1125807762145996,
      "learning_rate": 1.5772349991923366e-05,
      "loss": 0.892,
      "step": 1360
    },
    {
      "epoch": 1.6039516366853435,
      "eval_loss": 0.9855474233627319,
      "eval_runtime": 62.9171,
      "eval_samples_per_second": 23.952,
      "eval_steps_per_second": 5.992,
      "step": 1360
    },
    {
      "epoch": 1.627543497493365,
      "grad_norm": 2.1116766929626465,
      "learning_rate": 1.536055472070907e-05,
      "loss": 0.9116,
      "step": 1380
    },
    {
      "epoch": 1.627543497493365,
      "eval_loss": 0.9856626391410828,
      "eval_runtime": 62.9526,
      "eval_samples_per_second": 23.939,
      "eval_steps_per_second": 5.989,
      "step": 1380
    },
    {
      "epoch": 1.651135358301386,
      "grad_norm": 2.2223665714263916,
      "learning_rate": 1.4948487322718669e-05,
      "loss": 0.8816,
      "step": 1400
    },
    {
      "epoch": 1.651135358301386,
      "eval_loss": 0.9842101335525513,
      "eval_runtime": 63.0292,
      "eval_samples_per_second": 23.91,
      "eval_steps_per_second": 5.981,
      "step": 1400
    },
    {
      "epoch": 1.6747272191094074,
      "grad_norm": 2.2404255867004395,
      "learning_rate": 1.4536458803650085e-05,
      "loss": 0.859,
      "step": 1420
    },
    {
      "epoch": 1.6747272191094074,
      "eval_loss": 0.9844129085540771,
      "eval_runtime": 63.0729,
      "eval_samples_per_second": 23.893,
      "eval_steps_per_second": 5.977,
      "step": 1420
    },
    {
      "epoch": 1.6983190799174284,
      "grad_norm": 2.072277784347534,
      "learning_rate": 1.4124780139857582e-05,
      "loss": 0.9234,
      "step": 1440
    },
    {
      "epoch": 1.6983190799174284,
      "eval_loss": 0.9798393845558167,
      "eval_runtime": 64.8962,
      "eval_samples_per_second": 23.222,
      "eval_steps_per_second": 5.809,
      "step": 1440
    },
    {
      "epoch": 1.7219109407254498,
      "grad_norm": 2.4477767944335938,
      "learning_rate": 1.3713762043644008e-05,
      "loss": 0.889,
      "step": 1460
    },
    {
      "epoch": 1.7219109407254498,
      "eval_loss": 0.9810368418693542,
      "eval_runtime": 62.9029,
      "eval_samples_per_second": 23.958,
      "eval_steps_per_second": 5.993,
      "step": 1460
    },
    {
      "epoch": 1.7455028015334708,
      "grad_norm": 2.2249417304992676,
      "learning_rate": 1.3303714728752293e-05,
      "loss": 0.8679,
      "step": 1480
    },
    {
      "epoch": 1.7455028015334708,
      "eval_loss": 0.9801770448684692,
      "eval_runtime": 62.9129,
      "eval_samples_per_second": 23.954,
      "eval_steps_per_second": 5.992,
      "step": 1480
    },
    {
      "epoch": 1.7690946623414923,
      "grad_norm": 2.2835938930511475,
      "learning_rate": 1.2894947676233291e-05,
      "loss": 0.8896,
      "step": 1500
    },
    {
      "epoch": 1.7690946623414923,
      "eval_loss": 0.9786974787712097,
      "eval_runtime": 65.11,
      "eval_samples_per_second": 23.145,
      "eval_steps_per_second": 5.79,
      "step": 1500
    },
    {
      "epoch": 1.7926865231495133,
      "grad_norm": 2.386866569519043,
      "learning_rate": 1.2487769400866573e-05,
      "loss": 0.8687,
      "step": 1520
    },
    {
      "epoch": 1.7926865231495133,
      "eval_loss": 0.9775878190994263,
      "eval_runtime": 62.9587,
      "eval_samples_per_second": 23.936,
      "eval_steps_per_second": 5.988,
      "step": 1520
    },
    {
      "epoch": 1.8162783839575347,
      "grad_norm": 2.3122761249542236,
      "learning_rate": 1.2082487218310524e-05,
      "loss": 0.8992,
      "step": 1540
    },
    {
      "epoch": 1.8162783839575347,
      "eval_loss": 0.9774647951126099,
      "eval_runtime": 62.8905,
      "eval_samples_per_second": 23.962,
      "eval_steps_per_second": 5.995,
      "step": 1540
    },
    {
      "epoch": 1.8398702447655557,
      "grad_norm": 2.2307450771331787,
      "learning_rate": 1.1679407013157457e-05,
      "loss": 0.9041,
      "step": 1560
    },
    {
      "epoch": 1.8398702447655557,
      "eval_loss": 0.9749870300292969,
      "eval_runtime": 62.9232,
      "eval_samples_per_second": 23.95,
      "eval_steps_per_second": 5.991,
      "step": 1560
    },
    {
      "epoch": 1.8634621055735772,
      "grad_norm": 2.1991312503814697,
      "learning_rate": 1.1278833008068863e-05,
      "loss": 0.8804,
      "step": 1580
    },
    {
      "epoch": 1.8634621055735772,
      "eval_loss": 0.973229169845581,
      "eval_runtime": 62.9112,
      "eval_samples_per_second": 23.954,
      "eval_steps_per_second": 5.993,
      "step": 1580
    },
    {
      "epoch": 1.8870539663815984,
      "grad_norm": 2.1787588596343994,
      "learning_rate": 1.088106753416491e-05,
      "loss": 0.9004,
      "step": 1600
    },
    {
      "epoch": 1.8870539663815984,
      "eval_loss": 0.9725916385650635,
      "eval_runtime": 62.9975,
      "eval_samples_per_second": 23.922,
      "eval_steps_per_second": 5.984,
      "step": 1600
    }
  ],
  "logging_steps": 20,
  "max_steps": 2541,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "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": 3.937740637329162e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}