{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 3.238205219704208,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.6954,
      "step": 10
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.271242025646856,
      "learning_rate": 2.5333333333333338e-06,
      "loss": 0.6334,
      "step": 20
    },
    {
      "epoch": 0.12,
      "grad_norm": 2.1800513767705887,
      "learning_rate": 3.866666666666667e-06,
      "loss": 0.5616,
      "step": 30
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.1648812039750702,
      "learning_rate": 5.2e-06,
      "loss": 0.5148,
      "step": 40
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.1498397092624104,
      "learning_rate": 6.533333333333334e-06,
      "loss": 0.4828,
      "step": 50
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.439054889387191,
      "learning_rate": 7.866666666666667e-06,
      "loss": 0.4788,
      "step": 60
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.261998263366119,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.4728,
      "step": 70
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.201844069110454,
      "learning_rate": 9.99913355769784e-06,
      "loss": 0.4612,
      "step": 80
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.1591811394080247,
      "learning_rate": 9.989389530100242e-06,
      "loss": 0.4436,
      "step": 90
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.3078102825158529,
      "learning_rate": 9.968839595802982e-06,
      "loss": 0.4572,
      "step": 100
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.3962661244372518,
      "learning_rate": 9.937528261387753e-06,
      "loss": 0.4503,
      "step": 110
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.1977369757824934,
      "learning_rate": 9.89552334023258e-06,
      "loss": 0.4796,
      "step": 120
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.2903900106680968,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.4547,
      "step": 130
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.133608924238385,
      "learning_rate": 9.779819593824909e-06,
      "loss": 0.4402,
      "step": 140
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.2659380507665736,
      "learning_rate": 9.70637135712256e-06,
      "loss": 0.4694,
      "step": 150
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.4145155140111882,
      "learning_rate": 9.622730168061568e-06,
      "loss": 0.4554,
      "step": 160
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.1814401533026162,
      "learning_rate": 9.529077174832466e-06,
      "loss": 0.4291,
      "step": 170
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.1554822616312184,
      "learning_rate": 9.425615208964217e-06,
      "loss": 0.4212,
      "step": 180
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.1661698221732884,
      "learning_rate": 9.312568346036288e-06,
      "loss": 0.4351,
      "step": 190
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4701849159841565,
      "learning_rate": 9.190181420380838e-06,
      "loss": 0.4441,
      "step": 200
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.989465732667978,
      "learning_rate": 9.058719494826076e-06,
      "loss": 0.4131,
      "step": 210
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.239658511180224,
      "learning_rate": 8.9184672866292e-06,
      "loss": 0.4278,
      "step": 220
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.089425874622714,
      "learning_rate": 8.769728550842217e-06,
      "loss": 0.4397,
      "step": 230
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.2147944787643823,
      "learning_rate": 8.61282542244614e-06,
      "loss": 0.4462,
      "step": 240
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1427874903675157,
      "learning_rate": 8.44809771867835e-06,
      "loss": 0.4383,
      "step": 250
    },
    {
      "epoch": 1.04,
      "grad_norm": 1.1462782760971437,
      "learning_rate": 8.275902203064125e-06,
      "loss": 0.3197,
      "step": 260
    },
    {
      "epoch": 1.08,
      "grad_norm": 1.1173783548629352,
      "learning_rate": 8.096611812746302e-06,
      "loss": 0.3217,
      "step": 270
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.2777869200415286,
      "learning_rate": 7.910614850786448e-06,
      "loss": 0.32,
      "step": 280
    },
    {
      "epoch": 1.16,
      "grad_norm": 1.2517126629173954,
      "learning_rate": 7.718314145186918e-06,
      "loss": 0.3252,
      "step": 290
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.1470476886369243,
      "learning_rate": 7.520126176455084e-06,
      "loss": 0.3223,
      "step": 300
    },
    {
      "epoch": 1.24,
      "grad_norm": 1.1129643309958803,
      "learning_rate": 7.31648017559931e-06,
      "loss": 0.3167,
      "step": 310
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.9919930530594523,
      "learning_rate": 7.107817194510157e-06,
      "loss": 0.3178,
      "step": 320
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.0170698896454753,
      "learning_rate": 6.8945891507402075e-06,
      "loss": 0.3081,
      "step": 330
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 1.0642304251855126,
      "learning_rate": 6.677257848751276e-06,
      "loss": 0.3146,
      "step": 340
    },
    {
      "epoch": 1.4,
      "grad_norm": 1.015720677645443,
      "learning_rate": 6.456293979748778e-06,
      "loss": 0.3051,
      "step": 350
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.011871475120043,
      "learning_rate": 6.23217610226939e-06,
      "loss": 0.305,
      "step": 360
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.8935917352634799,
      "learning_rate": 6.005389605729824e-06,
      "loss": 0.3263,
      "step": 370
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.9654676799055634,
      "learning_rate": 5.776425659181438e-06,
      "loss": 0.3067,
      "step": 380
    },
    {
      "epoch": 1.56,
      "grad_norm": 1.0407814220165412,
      "learning_rate": 5.54578014754744e-06,
      "loss": 0.3145,
      "step": 390
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.1735574861995242,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.3142,
      "step": 400
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 1.0352433339394025,
      "learning_rate": 5.081445096329229e-06,
      "loss": 0.2968,
      "step": 410
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 1.0514219097026112,
      "learning_rate": 4.8487612030691975e-06,
      "loss": 0.3198,
      "step": 420
    },
    {
      "epoch": 1.72,
      "grad_norm": 1.1112681652067895,
      "learning_rate": 4.6164048593659076e-06,
      "loss": 0.3064,
      "step": 430
    },
    {
      "epoch": 1.76,
      "grad_norm": 1.0048201676188762,
      "learning_rate": 4.384879297319398e-06,
      "loss": 0.3094,
      "step": 440
    },
    {
      "epoch": 1.8,
      "grad_norm": 1.0758653777705578,
      "learning_rate": 4.154685949741631e-06,
      "loss": 0.298,
      "step": 450
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 1.1664913247689033,
      "learning_rate": 3.926323364164684e-06,
      "loss": 0.3079,
      "step": 460
    },
    {
      "epoch": 1.88,
      "grad_norm": 1.1338425739168947,
      "learning_rate": 3.700286123097814e-06,
      "loss": 0.3022,
      "step": 470
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.015433141233684,
      "learning_rate": 3.4770637728718608e-06,
      "loss": 0.3186,
      "step": 480
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.8460014130005209,
      "learning_rate": 3.2571397633909252e-06,
      "loss": 0.3181,
      "step": 490
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.0261154780948782,
      "learning_rate": 3.040990401087508e-06,
      "loss": 0.3097,
      "step": 500
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.8655997174434865,
      "learning_rate": 2.82908381734886e-06,
      "loss": 0.2099,
      "step": 510
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.9651491328248828,
      "learning_rate": 2.6218789546486235e-06,
      "loss": 0.1884,
      "step": 520
    },
    {
      "epoch": 2.12,
      "grad_norm": 1.2953511119694772,
      "learning_rate": 2.4198245725796427e-06,
      "loss": 0.2003,
      "step": 530
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.9087547978711116,
      "learning_rate": 2.2233582759406065e-06,
      "loss": 0.1917,
      "step": 540
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.9541801827955388,
      "learning_rate": 2.0329055669814936e-06,
      "loss": 0.1986,
      "step": 550
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.8678726633389815,
      "learning_rate": 1.8488789238604676e-06,
      "loss": 0.1924,
      "step": 560
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.8113217057232563,
      "learning_rate": 1.671676907308018e-06,
      "loss": 0.184,
      "step": 570
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.8358564334561136,
      "learning_rate": 1.5016832974331725e-06,
      "loss": 0.1974,
      "step": 580
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.8680751720471733,
      "learning_rate": 1.339266262541249e-06,
      "loss": 0.1996,
      "step": 590
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.9201310980151841,
      "learning_rate": 1.1847775617632746e-06,
      "loss": 0.1911,
      "step": 600
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.8709439322420328,
      "learning_rate": 1.0385517832240472e-06,
      "loss": 0.1806,
      "step": 610
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.9110684302470888,
      "learning_rate": 9.009056193987569e-07,
      "loss": 0.1923,
      "step": 620
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.8600274721721193,
      "learning_rate": 7.72137181227608e-07,
      "loss": 0.1982,
      "step": 630
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.9440305798432147,
      "learning_rate": 6.52525352473905e-07,
      "loss": 0.1907,
      "step": 640
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.8863906599552978,
      "learning_rate": 5.423291857239177e-07,
      "loss": 0.1941,
      "step": 650
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.8566897992226741,
      "learning_rate": 4.417873413366702e-07,
      "loss": 0.1976,
      "step": 660
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.8775191271488543,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.1796,
      "step": 670
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.8190151352692299,
      "learning_rate": 2.705162439235648e-07,
      "loss": 0.1847,
      "step": 680
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.9849452914848762,
      "learning_rate": 2.0015792595656225e-07,
      "loss": 0.1925,
      "step": 690
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.8247035782367392,
      "learning_rate": 1.4019499710726913e-07,
      "loss": 0.1793,
      "step": 700
    },
    {
      "epoch": 2.84,
      "grad_norm": 1.0595539505434528,
      "learning_rate": 9.075732372720414e-08,
      "loss": 0.1986,
      "step": 710
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.9332714846129114,
      "learning_rate": 5.19519768082738e-08,
      "loss": 0.2096,
      "step": 720
    },
    {
      "epoch": 2.92,
      "grad_norm": 1.0945012473014315,
      "learning_rate": 2.386300009084408e-08,
      "loss": 0.1879,
      "step": 730
    },
    {
      "epoch": 2.96,
      "grad_norm": 1.0438096421818555,
      "learning_rate": 6.551228043715218e-09,
      "loss": 0.1868,
      "step": 740
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9128409856387972,
      "learning_rate": 5.4154110206150465e-11,
      "loss": 0.1897,
      "step": 750
    },
    {
      "epoch": 3.0,
      "step": 750,
      "total_flos": 74683443707904.0,
      "train_loss": 0.3264822006225586,
      "train_runtime": 5153.2999,
      "train_samples_per_second": 1.746,
      "train_steps_per_second": 0.146
    }
  ],
  "logging_steps": 10,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 74683443707904.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}