{
  "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": 35.48504262720802,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.0899,
      "step": 10
    },
    {
      "epoch": 0.08,
      "grad_norm": 16.48187608589097,
      "learning_rate": 2.5333333333333338e-06,
      "loss": 0.5249,
      "step": 20
    },
    {
      "epoch": 0.12,
      "grad_norm": 10.468238992764016,
      "learning_rate": 3.866666666666667e-06,
      "loss": 0.3168,
      "step": 30
    },
    {
      "epoch": 0.16,
      "grad_norm": 9.024637955946732,
      "learning_rate": 5.2e-06,
      "loss": 0.3364,
      "step": 40
    },
    {
      "epoch": 0.2,
      "grad_norm": 6.073313045678999,
      "learning_rate": 6.533333333333334e-06,
      "loss": 0.2806,
      "step": 50
    },
    {
      "epoch": 0.24,
      "grad_norm": 5.687855097745657,
      "learning_rate": 7.866666666666667e-06,
      "loss": 0.2787,
      "step": 60
    },
    {
      "epoch": 0.28,
      "grad_norm": 7.1809472777573635,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.3306,
      "step": 70
    },
    {
      "epoch": 0.32,
      "grad_norm": 7.194716178236872,
      "learning_rate": 9.99913355769784e-06,
      "loss": 0.3409,
      "step": 80
    },
    {
      "epoch": 0.36,
      "grad_norm": 4.198748238410053,
      "learning_rate": 9.989389530100242e-06,
      "loss": 0.3485,
      "step": 90
    },
    {
      "epoch": 0.4,
      "grad_norm": 7.892891880606895,
      "learning_rate": 9.968839595802982e-06,
      "loss": 0.3538,
      "step": 100
    },
    {
      "epoch": 0.44,
      "grad_norm": 6.998920140370734,
      "learning_rate": 9.937528261387753e-06,
      "loss": 0.3176,
      "step": 110
    },
    {
      "epoch": 0.48,
      "grad_norm": 7.374807966049285,
      "learning_rate": 9.89552334023258e-06,
      "loss": 0.3123,
      "step": 120
    },
    {
      "epoch": 0.52,
      "grad_norm": 6.20558262495305,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.3996,
      "step": 130
    },
    {
      "epoch": 0.56,
      "grad_norm": 9.62426466622868,
      "learning_rate": 9.779819593824909e-06,
      "loss": 0.297,
      "step": 140
    },
    {
      "epoch": 0.6,
      "grad_norm": 8.635680958421968,
      "learning_rate": 9.70637135712256e-06,
      "loss": 0.31,
      "step": 150
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.232390024132561,
      "learning_rate": 9.622730168061568e-06,
      "loss": 0.2816,
      "step": 160
    },
    {
      "epoch": 0.68,
      "grad_norm": 3.695162741603393,
      "learning_rate": 9.529077174832466e-06,
      "loss": 0.2902,
      "step": 170
    },
    {
      "epoch": 0.72,
      "grad_norm": 2.8436007785521564,
      "learning_rate": 9.425615208964217e-06,
      "loss": 0.286,
      "step": 180
    },
    {
      "epoch": 0.76,
      "grad_norm": 3.087524553818655,
      "learning_rate": 9.312568346036288e-06,
      "loss": 0.3148,
      "step": 190
    },
    {
      "epoch": 0.8,
      "grad_norm": 4.601577314459775,
      "learning_rate": 9.190181420380838e-06,
      "loss": 0.306,
      "step": 200
    },
    {
      "epoch": 0.84,
      "grad_norm": 2.909610972090332,
      "learning_rate": 9.058719494826076e-06,
      "loss": 0.3021,
      "step": 210
    },
    {
      "epoch": 0.88,
      "grad_norm": 4.340156720044649,
      "learning_rate": 8.9184672866292e-06,
      "loss": 0.3793,
      "step": 220
    },
    {
      "epoch": 0.92,
      "grad_norm": 4.517487511541375,
      "learning_rate": 8.769728550842217e-06,
      "loss": 0.3205,
      "step": 230
    },
    {
      "epoch": 0.96,
      "grad_norm": 5.479883695257259,
      "learning_rate": 8.61282542244614e-06,
      "loss": 0.2903,
      "step": 240
    },
    {
      "epoch": 1.0,
      "grad_norm": 5.455068019285842,
      "learning_rate": 8.44809771867835e-06,
      "loss": 0.2974,
      "step": 250
    },
    {
      "epoch": 1.04,
      "grad_norm": 3.6092951322383837,
      "learning_rate": 8.275902203064125e-06,
      "loss": 0.1821,
      "step": 260
    },
    {
      "epoch": 1.08,
      "grad_norm": 4.192933227036564,
      "learning_rate": 8.096611812746302e-06,
      "loss": 0.2386,
      "step": 270
    },
    {
      "epoch": 1.12,
      "grad_norm": 3.3167996311633456,
      "learning_rate": 7.910614850786448e-06,
      "loss": 0.2272,
      "step": 280
    },
    {
      "epoch": 1.16,
      "grad_norm": 4.068655472873125,
      "learning_rate": 7.718314145186918e-06,
      "loss": 0.167,
      "step": 290
    },
    {
      "epoch": 1.2,
      "grad_norm": 4.007296325372359,
      "learning_rate": 7.520126176455084e-06,
      "loss": 0.2593,
      "step": 300
    },
    {
      "epoch": 1.24,
      "grad_norm": 2.817920804738045,
      "learning_rate": 7.31648017559931e-06,
      "loss": 0.1997,
      "step": 310
    },
    {
      "epoch": 1.28,
      "grad_norm": 2.7743725972139743,
      "learning_rate": 7.107817194510157e-06,
      "loss": 0.2198,
      "step": 320
    },
    {
      "epoch": 1.32,
      "grad_norm": 2.8263528430159073,
      "learning_rate": 6.8945891507402075e-06,
      "loss": 0.2121,
      "step": 330
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 2.76737686079553,
      "learning_rate": 6.677257848751276e-06,
      "loss": 0.2219,
      "step": 340
    },
    {
      "epoch": 1.4,
      "grad_norm": 2.9387440745751534,
      "learning_rate": 6.456293979748778e-06,
      "loss": 0.1814,
      "step": 350
    },
    {
      "epoch": 1.44,
      "grad_norm": 2.9525223454355887,
      "learning_rate": 6.23217610226939e-06,
      "loss": 0.2227,
      "step": 360
    },
    {
      "epoch": 1.48,
      "grad_norm": 3.8813673476773336,
      "learning_rate": 6.005389605729824e-06,
      "loss": 0.221,
      "step": 370
    },
    {
      "epoch": 1.52,
      "grad_norm": 3.0211148351187442,
      "learning_rate": 5.776425659181438e-06,
      "loss": 0.2186,
      "step": 380
    },
    {
      "epoch": 1.56,
      "grad_norm": 3.353673660930103,
      "learning_rate": 5.54578014754744e-06,
      "loss": 0.2259,
      "step": 390
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.759096393662257,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.1703,
      "step": 400
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 2.5075521908308627,
      "learning_rate": 5.081445096329229e-06,
      "loss": 0.2054,
      "step": 410
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 2.667218907894434,
      "learning_rate": 4.8487612030691975e-06,
      "loss": 0.1908,
      "step": 420
    },
    {
      "epoch": 1.72,
      "grad_norm": 3.7467375716198794,
      "learning_rate": 4.6164048593659076e-06,
      "loss": 0.1961,
      "step": 430
    },
    {
      "epoch": 1.76,
      "grad_norm": 2.0673735404525795,
      "learning_rate": 4.384879297319398e-06,
      "loss": 0.1939,
      "step": 440
    },
    {
      "epoch": 1.8,
      "grad_norm": 2.977965453692763,
      "learning_rate": 4.154685949741631e-06,
      "loss": 0.2254,
      "step": 450
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 4.207758072866126,
      "learning_rate": 3.926323364164684e-06,
      "loss": 0.2024,
      "step": 460
    },
    {
      "epoch": 1.88,
      "grad_norm": 3.8669669126524124,
      "learning_rate": 3.700286123097814e-06,
      "loss": 0.1879,
      "step": 470
    },
    {
      "epoch": 1.92,
      "grad_norm": 3.5441123121527967,
      "learning_rate": 3.4770637728718608e-06,
      "loss": 0.1948,
      "step": 480
    },
    {
      "epoch": 1.96,
      "grad_norm": 3.2798797246303466,
      "learning_rate": 3.2571397633909252e-06,
      "loss": 0.2235,
      "step": 490
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.2871674589145363,
      "learning_rate": 3.040990401087508e-06,
      "loss": 0.2277,
      "step": 500
    },
    {
      "epoch": 2.04,
      "grad_norm": 3.0673565792695654,
      "learning_rate": 2.82908381734886e-06,
      "loss": 0.1267,
      "step": 510
    },
    {
      "epoch": 2.08,
      "grad_norm": 2.6046689356940163,
      "learning_rate": 2.6218789546486235e-06,
      "loss": 0.1412,
      "step": 520
    },
    {
      "epoch": 2.12,
      "grad_norm": 2.5729189110537,
      "learning_rate": 2.4198245725796427e-06,
      "loss": 0.1202,
      "step": 530
    },
    {
      "epoch": 2.16,
      "grad_norm": 3.502942746638977,
      "learning_rate": 2.2233582759406065e-06,
      "loss": 0.1407,
      "step": 540
    },
    {
      "epoch": 2.2,
      "grad_norm": 2.9354585601623295,
      "learning_rate": 2.0329055669814936e-06,
      "loss": 0.1324,
      "step": 550
    },
    {
      "epoch": 2.24,
      "grad_norm": 2.388511910600407,
      "learning_rate": 1.8488789238604676e-06,
      "loss": 0.1358,
      "step": 560
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 1.875782926642573,
      "learning_rate": 1.671676907308018e-06,
      "loss": 0.0976,
      "step": 570
    },
    {
      "epoch": 2.32,
      "grad_norm": 2.464354656406682,
      "learning_rate": 1.5016832974331725e-06,
      "loss": 0.1121,
      "step": 580
    },
    {
      "epoch": 2.36,
      "grad_norm": 2.2360057587719795,
      "learning_rate": 1.339266262541249e-06,
      "loss": 0.1228,
      "step": 590
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.2693254276644237,
      "learning_rate": 1.1847775617632746e-06,
      "loss": 0.1613,
      "step": 600
    },
    {
      "epoch": 2.44,
      "grad_norm": 2.415277875645134,
      "learning_rate": 1.0385517832240472e-06,
      "loss": 0.1337,
      "step": 610
    },
    {
      "epoch": 2.48,
      "grad_norm": 2.6495067745174463,
      "learning_rate": 9.009056193987569e-07,
      "loss": 0.0975,
      "step": 620
    },
    {
      "epoch": 2.52,
      "grad_norm": 2.1271611125817196,
      "learning_rate": 7.72137181227608e-07,
      "loss": 0.1073,
      "step": 630
    },
    {
      "epoch": 2.56,
      "grad_norm": 2.383144498016058,
      "learning_rate": 6.52525352473905e-07,
      "loss": 0.1216,
      "step": 640
    },
    {
      "epoch": 2.6,
      "grad_norm": 2.31305492224638,
      "learning_rate": 5.423291857239177e-07,
      "loss": 0.1255,
      "step": 650
    },
    {
      "epoch": 2.64,
      "grad_norm": 2.819752170788764,
      "learning_rate": 4.417873413366702e-07,
      "loss": 0.1121,
      "step": 660
    },
    {
      "epoch": 2.68,
      "grad_norm": 1.8190497192872692,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.1003,
      "step": 670
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 2.4397321549581075,
      "learning_rate": 2.705162439235648e-07,
      "loss": 0.1226,
      "step": 680
    },
    {
      "epoch": 2.76,
      "grad_norm": 2.1508054212933962,
      "learning_rate": 2.0015792595656225e-07,
      "loss": 0.1546,
      "step": 690
    },
    {
      "epoch": 2.8,
      "grad_norm": 3.6112413918959363,
      "learning_rate": 1.4019499710726913e-07,
      "loss": 0.1267,
      "step": 700
    },
    {
      "epoch": 2.84,
      "grad_norm": 3.5252224980555376,
      "learning_rate": 9.075732372720414e-08,
      "loss": 0.121,
      "step": 710
    },
    {
      "epoch": 2.88,
      "grad_norm": 2.4820036298044506,
      "learning_rate": 5.19519768082738e-08,
      "loss": 0.137,
      "step": 720
    },
    {
      "epoch": 2.92,
      "grad_norm": 1.9548504439015364,
      "learning_rate": 2.386300009084408e-08,
      "loss": 0.1089,
      "step": 730
    },
    {
      "epoch": 2.96,
      "grad_norm": 2.013463783227666,
      "learning_rate": 6.551228043715218e-09,
      "loss": 0.1258,
      "step": 740
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.6783259480742636,
      "learning_rate": 5.4154110206150465e-11,
      "loss": 0.1466,
      "step": 750
    },
    {
      "epoch": 3.0,
      "step": 750,
      "total_flos": 1930678763520.0,
      "train_loss": 0.23004729866981508,
      "train_runtime": 1545.5894,
      "train_samples_per_second": 1.941,
      "train_steps_per_second": 0.485
    }
  ],
  "logging_steps": 10,
  "max_steps": 750,
  "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": 1930678763520.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}