{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.990379746835443,
  "eval_steps": 500,
  "global_step": 738,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 6.559766181680777,
      "learning_rate": 5e-06,
      "loss": 0.7469,
      "step": 10
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 2.0645407865130565,
      "learning_rate": 5e-06,
      "loss": 0.6482,
      "step": 20
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 2.192313459271068,
      "learning_rate": 5e-06,
      "loss": 0.6153,
      "step": 30
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 1.3146303292450665,
      "learning_rate": 5e-06,
      "loss": 0.5992,
      "step": 40
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 4.0197909191598376,
      "learning_rate": 5e-06,
      "loss": 0.5961,
      "step": 50
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 2.658139591723639,
      "learning_rate": 5e-06,
      "loss": 0.5883,
      "step": 60
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 3.05141456733358,
      "learning_rate": 5e-06,
      "loss": 0.578,
      "step": 70
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 1.550977980533193,
      "learning_rate": 5e-06,
      "loss": 0.581,
      "step": 80
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 1.5325403635274513,
      "learning_rate": 5e-06,
      "loss": 0.5782,
      "step": 90
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 1.3553457823507413,
      "learning_rate": 5e-06,
      "loss": 0.5733,
      "step": 100
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 1.9379260555134865,
      "learning_rate": 5e-06,
      "loss": 0.5698,
      "step": 110
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 1.5182450105686285,
      "learning_rate": 5e-06,
      "loss": 0.5694,
      "step": 120
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.196138670028915,
      "learning_rate": 5e-06,
      "loss": 0.5631,
      "step": 130
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 1.6047169596984416,
      "learning_rate": 5e-06,
      "loss": 0.5631,
      "step": 140
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 2.561229989585886,
      "learning_rate": 5e-06,
      "loss": 0.5606,
      "step": 150
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 2.0457845948979396,
      "learning_rate": 5e-06,
      "loss": 0.5628,
      "step": 160
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 2.1629027472393845,
      "learning_rate": 5e-06,
      "loss": 0.5594,
      "step": 170
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.7203051094851745,
      "learning_rate": 5e-06,
      "loss": 0.5612,
      "step": 180
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.6424314613227078,
      "learning_rate": 5e-06,
      "loss": 0.5534,
      "step": 190
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.6961150692619482,
      "learning_rate": 5e-06,
      "loss": 0.5553,
      "step": 200
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.575333089935049,
      "learning_rate": 5e-06,
      "loss": 0.5542,
      "step": 210
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.4596900420741143,
      "learning_rate": 5e-06,
      "loss": 0.5542,
      "step": 220
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.3253755066505102,
      "learning_rate": 5e-06,
      "loss": 0.5502,
      "step": 230
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.0645682091565618,
      "learning_rate": 5e-06,
      "loss": 0.5522,
      "step": 240
    },
    {
      "epoch": 0.9964556962025316,
      "eval_loss": 0.0690777450799942,
      "eval_runtime": 253.2419,
      "eval_samples_per_second": 52.535,
      "eval_steps_per_second": 0.411,
      "step": 246
    },
    {
      "epoch": 1.0131645569620253,
      "grad_norm": 2.2167473800014803,
      "learning_rate": 5e-06,
      "loss": 0.5352,
      "step": 250
    },
    {
      "epoch": 1.0536708860759494,
      "grad_norm": 1.7633980281740598,
      "learning_rate": 5e-06,
      "loss": 0.4945,
      "step": 260
    },
    {
      "epoch": 1.0941772151898734,
      "grad_norm": 1.2606315717897887,
      "learning_rate": 5e-06,
      "loss": 0.4929,
      "step": 270
    },
    {
      "epoch": 1.1346835443037975,
      "grad_norm": 1.6049596178131293,
      "learning_rate": 5e-06,
      "loss": 0.4906,
      "step": 280
    },
    {
      "epoch": 1.1751898734177215,
      "grad_norm": 1.3361496575935954,
      "learning_rate": 5e-06,
      "loss": 0.4965,
      "step": 290
    },
    {
      "epoch": 1.2156962025316456,
      "grad_norm": 1.6838379949154632,
      "learning_rate": 5e-06,
      "loss": 0.4935,
      "step": 300
    },
    {
      "epoch": 1.2562025316455696,
      "grad_norm": 1.2287081540136666,
      "learning_rate": 5e-06,
      "loss": 0.4946,
      "step": 310
    },
    {
      "epoch": 1.2967088607594937,
      "grad_norm": 1.1041418905025817,
      "learning_rate": 5e-06,
      "loss": 0.4952,
      "step": 320
    },
    {
      "epoch": 1.3372151898734177,
      "grad_norm": 1.1567183179957015,
      "learning_rate": 5e-06,
      "loss": 0.4939,
      "step": 330
    },
    {
      "epoch": 1.3777215189873417,
      "grad_norm": 1.0827873207690484,
      "learning_rate": 5e-06,
      "loss": 0.4997,
      "step": 340
    },
    {
      "epoch": 1.4182278481012658,
      "grad_norm": 1.384887984465678,
      "learning_rate": 5e-06,
      "loss": 0.4956,
      "step": 350
    },
    {
      "epoch": 1.4587341772151898,
      "grad_norm": 1.4028817280629426,
      "learning_rate": 5e-06,
      "loss": 0.4997,
      "step": 360
    },
    {
      "epoch": 1.4992405063291139,
      "grad_norm": 1.1049684628387706,
      "learning_rate": 5e-06,
      "loss": 0.4981,
      "step": 370
    },
    {
      "epoch": 1.539746835443038,
      "grad_norm": 1.2590051489674519,
      "learning_rate": 5e-06,
      "loss": 0.4981,
      "step": 380
    },
    {
      "epoch": 1.5802531645569622,
      "grad_norm": 1.1357365609688317,
      "learning_rate": 5e-06,
      "loss": 0.4968,
      "step": 390
    },
    {
      "epoch": 1.620759493670886,
      "grad_norm": 1.1106976894525098,
      "learning_rate": 5e-06,
      "loss": 0.4977,
      "step": 400
    },
    {
      "epoch": 1.6612658227848103,
      "grad_norm": 1.3665599034101343,
      "learning_rate": 5e-06,
      "loss": 0.4931,
      "step": 410
    },
    {
      "epoch": 1.701772151898734,
      "grad_norm": 1.304233943964937,
      "learning_rate": 5e-06,
      "loss": 0.4937,
      "step": 420
    },
    {
      "epoch": 1.7422784810126584,
      "grad_norm": 1.4646233158776383,
      "learning_rate": 5e-06,
      "loss": 0.496,
      "step": 430
    },
    {
      "epoch": 1.7827848101265822,
      "grad_norm": 1.2915317661859655,
      "learning_rate": 5e-06,
      "loss": 0.4984,
      "step": 440
    },
    {
      "epoch": 1.8232911392405065,
      "grad_norm": 1.480881353690771,
      "learning_rate": 5e-06,
      "loss": 0.4962,
      "step": 450
    },
    {
      "epoch": 1.8637974683544303,
      "grad_norm": 1.2523408662507558,
      "learning_rate": 5e-06,
      "loss": 0.4963,
      "step": 460
    },
    {
      "epoch": 1.9043037974683545,
      "grad_norm": 1.1003232267021519,
      "learning_rate": 5e-06,
      "loss": 0.493,
      "step": 470
    },
    {
      "epoch": 1.9448101265822784,
      "grad_norm": 1.1189004594261551,
      "learning_rate": 5e-06,
      "loss": 0.4994,
      "step": 480
    },
    {
      "epoch": 1.9853164556962026,
      "grad_norm": 1.574886373546533,
      "learning_rate": 5e-06,
      "loss": 0.4996,
      "step": 490
    },
    {
      "epoch": 1.9974683544303797,
      "eval_loss": 0.06833568215370178,
      "eval_runtime": 254.4783,
      "eval_samples_per_second": 52.28,
      "eval_steps_per_second": 0.409,
      "step": 493
    },
    {
      "epoch": 2.0263291139240507,
      "grad_norm": 2.3014937314441917,
      "learning_rate": 5e-06,
      "loss": 0.4488,
      "step": 500
    },
    {
      "epoch": 2.0668354430379745,
      "grad_norm": 1.5839634313845277,
      "learning_rate": 5e-06,
      "loss": 0.4174,
      "step": 510
    },
    {
      "epoch": 2.1073417721518988,
      "grad_norm": 1.5382506185743696,
      "learning_rate": 5e-06,
      "loss": 0.4122,
      "step": 520
    },
    {
      "epoch": 2.1478481012658226,
      "grad_norm": 1.9423195334308014,
      "learning_rate": 5e-06,
      "loss": 0.4176,
      "step": 530
    },
    {
      "epoch": 2.188354430379747,
      "grad_norm": 1.7133386724331026,
      "learning_rate": 5e-06,
      "loss": 0.4155,
      "step": 540
    },
    {
      "epoch": 2.2288607594936707,
      "grad_norm": 1.5970886196077994,
      "learning_rate": 5e-06,
      "loss": 0.4159,
      "step": 550
    },
    {
      "epoch": 2.269367088607595,
      "grad_norm": 1.698428644338184,
      "learning_rate": 5e-06,
      "loss": 0.4168,
      "step": 560
    },
    {
      "epoch": 2.309873417721519,
      "grad_norm": 1.4211509452212008,
      "learning_rate": 5e-06,
      "loss": 0.4171,
      "step": 570
    },
    {
      "epoch": 2.350379746835443,
      "grad_norm": 1.5618144695743699,
      "learning_rate": 5e-06,
      "loss": 0.4213,
      "step": 580
    },
    {
      "epoch": 2.390886075949367,
      "grad_norm": 1.6889726651564196,
      "learning_rate": 5e-06,
      "loss": 0.4217,
      "step": 590
    },
    {
      "epoch": 2.431392405063291,
      "grad_norm": 1.3913389067387658,
      "learning_rate": 5e-06,
      "loss": 0.4203,
      "step": 600
    },
    {
      "epoch": 2.4718987341772154,
      "grad_norm": 1.3963990757058133,
      "learning_rate": 5e-06,
      "loss": 0.4202,
      "step": 610
    },
    {
      "epoch": 2.512405063291139,
      "grad_norm": 1.9356587258448503,
      "learning_rate": 5e-06,
      "loss": 0.4238,
      "step": 620
    },
    {
      "epoch": 2.552911392405063,
      "grad_norm": 1.6113295443045734,
      "learning_rate": 5e-06,
      "loss": 0.4173,
      "step": 630
    },
    {
      "epoch": 2.5934177215189873,
      "grad_norm": 1.9607308696000172,
      "learning_rate": 5e-06,
      "loss": 0.4234,
      "step": 640
    },
    {
      "epoch": 2.6339240506329116,
      "grad_norm": 1.2271048631932833,
      "learning_rate": 5e-06,
      "loss": 0.4259,
      "step": 650
    },
    {
      "epoch": 2.6744303797468354,
      "grad_norm": 1.113804445089212,
      "learning_rate": 5e-06,
      "loss": 0.4249,
      "step": 660
    },
    {
      "epoch": 2.714936708860759,
      "grad_norm": 1.2492433372859684,
      "learning_rate": 5e-06,
      "loss": 0.4285,
      "step": 670
    },
    {
      "epoch": 2.7554430379746835,
      "grad_norm": 1.3017899119460772,
      "learning_rate": 5e-06,
      "loss": 0.4234,
      "step": 680
    },
    {
      "epoch": 2.7959493670886078,
      "grad_norm": 1.540529786978242,
      "learning_rate": 5e-06,
      "loss": 0.4271,
      "step": 690
    },
    {
      "epoch": 2.8364556962025316,
      "grad_norm": 1.3913941622738781,
      "learning_rate": 5e-06,
      "loss": 0.4252,
      "step": 700
    },
    {
      "epoch": 2.876962025316456,
      "grad_norm": 1.1221109278814458,
      "learning_rate": 5e-06,
      "loss": 0.428,
      "step": 710
    },
    {
      "epoch": 2.9174683544303797,
      "grad_norm": 1.3475151536192913,
      "learning_rate": 5e-06,
      "loss": 0.4271,
      "step": 720
    },
    {
      "epoch": 2.957974683544304,
      "grad_norm": 1.1695621792215076,
      "learning_rate": 5e-06,
      "loss": 0.4325,
      "step": 730
    },
    {
      "epoch": 2.990379746835443,
      "eval_loss": 0.07060651481151581,
      "eval_runtime": 253.6051,
      "eval_samples_per_second": 52.46,
      "eval_steps_per_second": 0.41,
      "step": 738
    },
    {
      "epoch": 2.990379746835443,
      "step": 738,
      "total_flos": 2471936214958080.0,
      "train_loss": 0.4994575757644364,
      "train_runtime": 42649.5957,
      "train_samples_per_second": 17.779,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 738,
  "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": 2471936214958080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}