{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 645,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07751937984496124,
      "grad_norm": 2.245417356491089,
      "learning_rate": 5e-05,
      "loss": 2.1087,
      "step": 10
    },
    {
      "epoch": 0.15503875968992248,
      "grad_norm": 3.3328239917755127,
      "learning_rate": 0.0001,
      "loss": 1.7547,
      "step": 20
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 1.6743243932724,
      "learning_rate": 9.993684783030088e-05,
      "loss": 1.3868,
      "step": 30
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 1.585747480392456,
      "learning_rate": 9.974755084906502e-05,
      "loss": 1.1455,
      "step": 40
    },
    {
      "epoch": 0.3875968992248062,
      "grad_norm": 1.2781128883361816,
      "learning_rate": 9.94325872368957e-05,
      "loss": 1.1394,
      "step": 50
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 1.3732120990753174,
      "learning_rate": 9.899275261921234e-05,
      "loss": 1.0942,
      "step": 60
    },
    {
      "epoch": 0.5426356589147286,
      "grad_norm": 1.4817951917648315,
      "learning_rate": 9.842915805643155e-05,
      "loss": 0.9934,
      "step": 70
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 1.261801838874817,
      "learning_rate": 9.774322723733216e-05,
      "loss": 1.0093,
      "step": 80
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 1.801243782043457,
      "learning_rate": 9.693669288269372e-05,
      "loss": 1.0686,
      "step": 90
    },
    {
      "epoch": 0.7751937984496124,
      "grad_norm": 1.719342827796936,
      "learning_rate": 9.601159236829352e-05,
      "loss": 0.9973,
      "step": 100
    },
    {
      "epoch": 0.8527131782945736,
      "grad_norm": 1.5797449350357056,
      "learning_rate": 9.497026257831855e-05,
      "loss": 1.0002,
      "step": 110
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 1.790971279144287,
      "learning_rate": 9.381533400219318e-05,
      "loss": 0.9484,
      "step": 120
    },
    {
      "epoch": 1.0077519379844961,
      "grad_norm": 1.6127315759658813,
      "learning_rate": 9.254972408973461e-05,
      "loss": 0.979,
      "step": 130
    },
    {
      "epoch": 1.0852713178294573,
      "grad_norm": 1.4869861602783203,
      "learning_rate": 9.117662988142138e-05,
      "loss": 0.8899,
      "step": 140
    },
    {
      "epoch": 1.1627906976744187,
      "grad_norm": 2.101341962814331,
      "learning_rate": 8.969951993239177e-05,
      "loss": 0.9493,
      "step": 150
    },
    {
      "epoch": 1.2403100775193798,
      "grad_norm": 1.7181503772735596,
      "learning_rate": 8.81221255505724e-05,
      "loss": 0.8715,
      "step": 160
    },
    {
      "epoch": 1.3178294573643412,
      "grad_norm": 2.006377696990967,
      "learning_rate": 8.644843137107059e-05,
      "loss": 0.8846,
      "step": 170
    },
    {
      "epoch": 1.3953488372093024,
      "grad_norm": 2.0157504081726074,
      "learning_rate": 8.468266529064025e-05,
      "loss": 0.9292,
      "step": 180
    },
    {
      "epoch": 1.4728682170542635,
      "grad_norm": 1.704633355140686,
      "learning_rate": 8.282928778764783e-05,
      "loss": 0.8883,
      "step": 190
    },
    {
      "epoch": 1.550387596899225,
      "grad_norm": 1.7320111989974976,
      "learning_rate": 8.089298065451672e-05,
      "loss": 0.874,
      "step": 200
    },
    {
      "epoch": 1.627906976744186,
      "grad_norm": 2.369300127029419,
      "learning_rate": 7.887863517111338e-05,
      "loss": 0.8688,
      "step": 210
    },
    {
      "epoch": 1.7054263565891472,
      "grad_norm": 1.5535732507705688,
      "learning_rate": 7.679133974894983e-05,
      "loss": 0.8726,
      "step": 220
    },
    {
      "epoch": 1.7829457364341086,
      "grad_norm": 1.9749231338500977,
      "learning_rate": 7.463636707741458e-05,
      "loss": 0.8252,
      "step": 230
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 2.261054277420044,
      "learning_rate": 7.241916080450163e-05,
      "loss": 0.846,
      "step": 240
    },
    {
      "epoch": 1.937984496124031,
      "grad_norm": 2.019524097442627,
      "learning_rate": 7.014532178568314e-05,
      "loss": 0.8104,
      "step": 250
    },
    {
      "epoch": 2.0155038759689923,
      "grad_norm": 1.8253782987594604,
      "learning_rate": 6.782059393566253e-05,
      "loss": 0.8436,
      "step": 260
    },
    {
      "epoch": 2.0930232558139537,
      "grad_norm": 1.92261803150177,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8007,
      "step": 270
    },
    {
      "epoch": 2.1705426356589146,
      "grad_norm": 1.959991455078125,
      "learning_rate": 6.304207531449486e-05,
      "loss": 0.8093,
      "step": 280
    },
    {
      "epoch": 2.248062015503876,
      "grad_norm": 2.0819852352142334,
      "learning_rate": 6.0600355496102745e-05,
      "loss": 0.7626,
      "step": 290
    },
    {
      "epoch": 2.3255813953488373,
      "grad_norm": 2.1029396057128906,
      "learning_rate": 5.813185825974419e-05,
      "loss": 0.7995,
      "step": 300
    },
    {
      "epoch": 2.4031007751937983,
      "grad_norm": 2.149883508682251,
      "learning_rate": 5.564281924367408e-05,
      "loss": 0.7867,
      "step": 310
    },
    {
      "epoch": 2.4806201550387597,
      "grad_norm": 2.2461025714874268,
      "learning_rate": 5.313952597646568e-05,
      "loss": 0.778,
      "step": 320
    },
    {
      "epoch": 2.558139534883721,
      "grad_norm": 2.1659789085388184,
      "learning_rate": 5.062830199416764e-05,
      "loss": 0.8143,
      "step": 330
    },
    {
      "epoch": 2.6356589147286824,
      "grad_norm": 2.3656270503997803,
      "learning_rate": 4.811549086650327e-05,
      "loss": 0.8017,
      "step": 340
    },
    {
      "epoch": 2.7131782945736433,
      "grad_norm": 2.3753740787506104,
      "learning_rate": 4.560744017246284e-05,
      "loss": 0.7666,
      "step": 350
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": 2.221393585205078,
      "learning_rate": 4.31104854657681e-05,
      "loss": 0.7679,
      "step": 360
    },
    {
      "epoch": 2.8682170542635657,
      "grad_norm": 2.018345594406128,
      "learning_rate": 4.063093427071376e-05,
      "loss": 0.7507,
      "step": 370
    },
    {
      "epoch": 2.945736434108527,
      "grad_norm": 2.199131965637207,
      "learning_rate": 3.817505014881378e-05,
      "loss": 0.7413,
      "step": 380
    },
    {
      "epoch": 3.0232558139534884,
      "grad_norm": 2.139735698699951,
      "learning_rate": 3.5749036876501194e-05,
      "loss": 0.8139,
      "step": 390
    },
    {
      "epoch": 3.10077519379845,
      "grad_norm": 2.0483205318450928,
      "learning_rate": 3.335902277385067e-05,
      "loss": 0.7209,
      "step": 400
    },
    {
      "epoch": 3.1782945736434107,
      "grad_norm": 2.3175625801086426,
      "learning_rate": 3.101104522390995e-05,
      "loss": 0.7392,
      "step": 410
    },
    {
      "epoch": 3.255813953488372,
      "grad_norm": 2.267725944519043,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 0.7487,
      "step": 420
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 2.491976261138916,
      "learning_rate": 2.6464803391733374e-05,
      "loss": 0.7472,
      "step": 430
    },
    {
      "epoch": 3.4108527131782944,
      "grad_norm": 2.3867716789245605,
      "learning_rate": 2.4278023310924673e-05,
      "loss": 0.7194,
      "step": 440
    },
    {
      "epoch": 3.488372093023256,
      "grad_norm": 2.1725575923919678,
      "learning_rate": 2.215621917559062e-05,
      "loss": 0.7435,
      "step": 450
    },
    {
      "epoch": 3.565891472868217,
      "grad_norm": 2.362307071685791,
      "learning_rate": 2.0104750847124075e-05,
      "loss": 0.7257,
      "step": 460
    },
    {
      "epoch": 3.6434108527131785,
      "grad_norm": 2.3659157752990723,
      "learning_rate": 1.8128800512565513e-05,
      "loss": 0.7498,
      "step": 470
    },
    {
      "epoch": 3.7209302325581395,
      "grad_norm": 2.225560188293457,
      "learning_rate": 1.6233359593948777e-05,
      "loss": 0.7308,
      "step": 480
    },
    {
      "epoch": 3.798449612403101,
      "grad_norm": 2.4101855754852295,
      "learning_rate": 1.4423216139535734e-05,
      "loss": 0.7524,
      "step": 490
    },
    {
      "epoch": 3.875968992248062,
      "grad_norm": 2.295118808746338,
      "learning_rate": 1.2702942728790895e-05,
      "loss": 0.7239,
      "step": 500
    },
    {
      "epoch": 3.953488372093023,
      "grad_norm": 2.7008495330810547,
      "learning_rate": 1.1076884921648834e-05,
      "loss": 0.7305,
      "step": 510
    },
    {
      "epoch": 4.0310077519379846,
      "grad_norm": 2.140915632247925,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7214,
      "step": 520
    },
    {
      "epoch": 4.108527131782946,
      "grad_norm": 2.121488332748413,
      "learning_rate": 8.123597997892918e-06,
      "loss": 0.7247,
      "step": 530
    },
    {
      "epoch": 4.186046511627907,
      "grad_norm": 2.2212812900543213,
      "learning_rate": 6.803829140358237e-06,
      "loss": 0.6995,
      "step": 540
    },
    {
      "epoch": 4.263565891472869,
      "grad_norm": 2.381098985671997,
      "learning_rate": 5.593177559322777e-06,
      "loss": 0.7116,
      "step": 550
    },
    {
      "epoch": 4.341085271317829,
      "grad_norm": 2.4563639163970947,
      "learning_rate": 4.494701465750217e-06,
      "loss": 0.7106,
      "step": 560
    },
    {
      "epoch": 4.4186046511627906,
      "grad_norm": 2.1021621227264404,
      "learning_rate": 3.511175705587433e-06,
      "loss": 0.7203,
      "step": 570
    },
    {
      "epoch": 4.496124031007752,
      "grad_norm": 2.3174192905426025,
      "learning_rate": 2.6450847502627884e-06,
      "loss": 0.6485,
      "step": 580
    },
    {
      "epoch": 4.573643410852713,
      "grad_norm": 2.161879301071167,
      "learning_rate": 1.8986164206957035e-06,
      "loss": 0.7654,
      "step": 590
    },
    {
      "epoch": 4.651162790697675,
      "grad_norm": 2.362793207168579,
      "learning_rate": 1.2736563606711382e-06,
      "loss": 0.694,
      "step": 600
    },
    {
      "epoch": 4.728682170542635,
      "grad_norm": 2.0738697052001953,
      "learning_rate": 7.717832735397335e-07,
      "loss": 0.7161,
      "step": 610
    },
    {
      "epoch": 4.8062015503875966,
      "grad_norm": 2.522212505340576,
      "learning_rate": 3.9426493427611177e-07,
      "loss": 0.7234,
      "step": 620
    },
    {
      "epoch": 4.883720930232558,
      "grad_norm": 2.2969350814819336,
      "learning_rate": 1.420549869693033e-07,
      "loss": 0.7234,
      "step": 630
    },
    {
      "epoch": 4.961240310077519,
      "grad_norm": 2.1702637672424316,
      "learning_rate": 1.5790535835003008e-08,
      "loss": 0.726,
      "step": 640
    }
  ],
  "logging_steps": 10,
  "max_steps": 645,
  "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": 6.745720297183642e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}