{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 645,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 1.7476660013198853,
      "learning_rate": 4.1538461538461545e-06,
      "loss": 0.4053,
      "step": 10
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 1.2797056436538696,
      "learning_rate": 8.76923076923077e-06,
      "loss": 0.2451,
      "step": 20
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.9715517163276672,
      "learning_rate": 1.3384615384615386e-05,
      "loss": 0.2026,
      "step": 30
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.8870955109596252,
      "learning_rate": 1.8e-05,
      "loss": 0.1818,
      "step": 40
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.706699550151825,
      "learning_rate": 2.2615384615384615e-05,
      "loss": 0.1687,
      "step": 50
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.6627687811851501,
      "learning_rate": 2.7230769230769233e-05,
      "loss": 0.1621,
      "step": 60
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 0.5161024928092957,
      "learning_rate": 2.9996479470277262e-05,
      "loss": 0.1597,
      "step": 70
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 0.45436057448387146,
      "learning_rate": 2.9956892486957502e-05,
      "loss": 0.1527,
      "step": 80
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 0.7213302254676819,
      "learning_rate": 2.9873434360934543e-05,
      "loss": 0.1536,
      "step": 90
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.41891512274742126,
      "learning_rate": 2.9746349889271652e-05,
      "loss": 0.1454,
      "step": 100
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 0.40932586789131165,
      "learning_rate": 2.9576011832620583e-05,
      "loss": 0.1384,
      "step": 110
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 0.6326035857200623,
      "learning_rate": 2.9362919821850365e-05,
      "loss": 0.1401,
      "step": 120
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 0.47325533628463745,
      "learning_rate": 2.9107698892543862e-05,
      "loss": 0.1297,
      "step": 130
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 0.4126339852809906,
      "learning_rate": 2.8811097651660716e-05,
      "loss": 0.1288,
      "step": 140
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.4939899742603302,
      "learning_rate": 2.847398608174417e-05,
      "loss": 0.1339,
      "step": 150
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 0.38328367471694946,
      "learning_rate": 2.8097352989112345e-05,
      "loss": 0.1293,
      "step": 160
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 0.36505013704299927,
      "learning_rate": 2.768230310351898e-05,
      "loss": 0.1272,
      "step": 170
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 0.40006181597709656,
      "learning_rate": 2.7230053837790673e-05,
      "loss": 0.1285,
      "step": 180
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 0.4462541341781616,
      "learning_rate": 2.6741931716945336e-05,
      "loss": 0.1236,
      "step": 190
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.34532684087753296,
      "learning_rate": 2.6219368487265756e-05,
      "loss": 0.1274,
      "step": 200
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 0.4481622576713562,
      "learning_rate": 2.5663896916741064e-05,
      "loss": 0.1213,
      "step": 210
    },
    {
      "epoch": 1.0232558139534884,
      "grad_norm": 0.3308081328868866,
      "learning_rate": 2.5077146299194094e-05,
      "loss": 0.124,
      "step": 220
    },
    {
      "epoch": 1.069767441860465,
      "grad_norm": 0.3247145116329193,
      "learning_rate": 2.446083767528193e-05,
      "loss": 0.1223,
      "step": 230
    },
    {
      "epoch": 1.1162790697674418,
      "grad_norm": 0.31839317083358765,
      "learning_rate": 2.3816778784387097e-05,
      "loss": 0.1162,
      "step": 240
    },
    {
      "epoch": 1.1627906976744187,
      "grad_norm": 0.36601680517196655,
      "learning_rate": 2.3146858762206493e-05,
      "loss": 0.1166,
      "step": 250
    },
    {
      "epoch": 1.2093023255813953,
      "grad_norm": 0.39110299944877625,
      "learning_rate": 2.2453042599590884e-05,
      "loss": 0.1147,
      "step": 260
    },
    {
      "epoch": 1.255813953488372,
      "grad_norm": 0.40319550037384033,
      "learning_rate": 2.173736537888819e-05,
      "loss": 0.1137,
      "step": 270
    },
    {
      "epoch": 1.302325581395349,
      "grad_norm": 0.35869157314300537,
      "learning_rate": 2.10019263046963e-05,
      "loss": 0.1174,
      "step": 280
    },
    {
      "epoch": 1.3488372093023255,
      "grad_norm": 0.39020806550979614,
      "learning_rate": 2.0248882546534327e-05,
      "loss": 0.1141,
      "step": 290
    },
    {
      "epoch": 1.3953488372093024,
      "grad_norm": 0.39524269104003906,
      "learning_rate": 1.9480442911492706e-05,
      "loss": 0.1132,
      "step": 300
    },
    {
      "epoch": 1.441860465116279,
      "grad_norm": 0.3699205219745636,
      "learning_rate": 1.8698861365421433e-05,
      "loss": 0.1119,
      "step": 310
    },
    {
      "epoch": 1.4883720930232558,
      "grad_norm": 0.33726540207862854,
      "learning_rate": 1.7906430421659876e-05,
      "loss": 0.1166,
      "step": 320
    },
    {
      "epoch": 1.5348837209302326,
      "grad_norm": 0.41265928745269775,
      "learning_rate": 1.7105474416700165e-05,
      "loss": 0.1127,
      "step": 330
    },
    {
      "epoch": 1.5813953488372094,
      "grad_norm": 0.3320264220237732,
      "learning_rate": 1.6298342692507765e-05,
      "loss": 0.1115,
      "step": 340
    },
    {
      "epoch": 1.627906976744186,
      "grad_norm": 0.2614348828792572,
      "learning_rate": 1.548740270549671e-05,
      "loss": 0.111,
      "step": 350
    },
    {
      "epoch": 1.6744186046511627,
      "grad_norm": 0.29234352707862854,
      "learning_rate": 1.467503308237204e-05,
      "loss": 0.1087,
      "step": 360
    },
    {
      "epoch": 1.7209302325581395,
      "grad_norm": 0.2900184094905853,
      "learning_rate": 1.3863616643207844e-05,
      "loss": 0.1074,
      "step": 370
    },
    {
      "epoch": 1.7674418604651163,
      "grad_norm": 0.29722127318382263,
      "learning_rate": 1.3055533412225422e-05,
      "loss": 0.1104,
      "step": 380
    },
    {
      "epoch": 1.8139534883720931,
      "grad_norm": 0.38949820399284363,
      "learning_rate": 1.2253153636772158e-05,
      "loss": 0.1091,
      "step": 390
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 0.2845311164855957,
      "learning_rate": 1.1458830834977698e-05,
      "loss": 0.1111,
      "step": 400
    },
    {
      "epoch": 1.9069767441860463,
      "grad_norm": 0.24525171518325806,
      "learning_rate": 1.067489489247974e-05,
      "loss": 0.107,
      "step": 410
    },
    {
      "epoch": 1.9534883720930232,
      "grad_norm": 0.29745063185691833,
      "learning_rate": 9.903645228468024e-06,
      "loss": 0.1071,
      "step": 420
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2796909809112549,
      "learning_rate": 9.147344051091682e-06,
      "loss": 0.1059,
      "step": 430
    },
    {
      "epoch": 2.046511627906977,
      "grad_norm": 0.28045353293418884,
      "learning_rate": 8.408209722012956e-06,
      "loss": 0.1023,
      "step": 440
    },
    {
      "epoch": 2.0930232558139537,
      "grad_norm": 0.21314753592014313,
      "learning_rate": 7.688410249570214e-06,
      "loss": 0.1031,
      "step": 450
    },
    {
      "epoch": 2.13953488372093,
      "grad_norm": 0.3194475471973419,
      "learning_rate": 6.990056929635958e-06,
      "loss": 0.1023,
      "step": 460
    },
    {
      "epoch": 2.186046511627907,
      "grad_norm": 0.21530288457870483,
      "learning_rate": 6.315198152822273e-06,
      "loss": 0.0997,
      "step": 470
    },
    {
      "epoch": 2.2325581395348837,
      "grad_norm": 0.27216485142707825,
      "learning_rate": 5.66581339619819e-06,
      "loss": 0.0968,
      "step": 480
    },
    {
      "epoch": 2.2790697674418605,
      "grad_norm": 0.3025151193141937,
      "learning_rate": 5.043807417142436e-06,
      "loss": 0.0999,
      "step": 490
    },
    {
      "epoch": 2.3255813953488373,
      "grad_norm": 0.27557316422462463,
      "learning_rate": 4.4510046663618e-06,
      "loss": 0.0991,
      "step": 500
    },
    {
      "epoch": 2.3720930232558137,
      "grad_norm": 0.2208959013223648,
      "learning_rate": 3.889143936462915e-06,
      "loss": 0.0985,
      "step": 510
    },
    {
      "epoch": 2.4186046511627906,
      "grad_norm": 0.31590473651885986,
      "learning_rate": 3.359873261773904e-06,
      "loss": 0.0994,
      "step": 520
    },
    {
      "epoch": 2.4651162790697674,
      "grad_norm": 0.28370803594589233,
      "learning_rate": 2.86474508437579e-06,
      "loss": 0.0989,
      "step": 530
    },
    {
      "epoch": 2.511627906976744,
      "grad_norm": 0.2663387358188629,
      "learning_rate": 2.4052117005223457e-06,
      "loss": 0.1022,
      "step": 540
    },
    {
      "epoch": 2.558139534883721,
      "grad_norm": 0.2275928556919098,
      "learning_rate": 1.982621000804979e-06,
      "loss": 0.0926,
      "step": 550
    },
    {
      "epoch": 2.604651162790698,
      "grad_norm": 0.2721380889415741,
      "learning_rate": 1.5982125165573941e-06,
      "loss": 0.0991,
      "step": 560
    },
    {
      "epoch": 2.6511627906976747,
      "grad_norm": 0.24267996847629547,
      "learning_rate": 1.25311378409661e-06,
      "loss": 0.0991,
      "step": 570
    },
    {
      "epoch": 2.697674418604651,
      "grad_norm": 0.22184228897094727,
      "learning_rate": 9.483370374646661e-07,
      "loss": 0.0975,
      "step": 580
    },
    {
      "epoch": 2.744186046511628,
      "grad_norm": 0.28250575065612793,
      "learning_rate": 6.847762393717782e-07,
      "loss": 0.0926,
      "step": 590
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": 0.28555381298065186,
      "learning_rate": 4.632044590496948e-07,
      "loss": 0.0956,
      "step": 600
    },
    {
      "epoch": 2.8372093023255816,
      "grad_norm": 0.29760462045669556,
      "learning_rate": 2.8427160470641255e-07,
      "loss": 0.0966,
      "step": 610
    },
    {
      "epoch": 2.883720930232558,
      "grad_norm": 0.28198060393333435,
      "learning_rate": 1.4850251723345198e-07,
      "loss": 0.0981,
      "step": 620
    },
    {
      "epoch": 2.9302325581395348,
      "grad_norm": 0.27139362692832947,
      "learning_rate": 5.629543075708177e-08,
      "loss": 0.0919,
      "step": 630
    },
    {
      "epoch": 2.9767441860465116,
      "grad_norm": 0.2770179808139801,
      "learning_rate": 7.920804549007011e-09,
      "loss": 0.0927,
      "step": 640
    }
  ],
  "logging_steps": 10,
  "max_steps": 645,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 475511974002688.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}