{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9965277777777777,
  "eval_steps": 500,
  "global_step": 1150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034722222222222224,
      "grad_norm": 2.54878306388855,
      "learning_rate": 1.6379310344827587e-06,
      "loss": 2.5199,
      "step": 20
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 2.2638280391693115,
      "learning_rate": 3.362068965517242e-06,
      "loss": 2.3584,
      "step": 40
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 1.9315502643585205,
      "learning_rate": 5.086206896551724e-06,
      "loss": 2.1832,
      "step": 60
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 1.7287458181381226,
      "learning_rate": 6.810344827586207e-06,
      "loss": 2.0124,
      "step": 80
    },
    {
      "epoch": 0.1736111111111111,
      "grad_norm": 2.1096012592315674,
      "learning_rate": 8.53448275862069e-06,
      "loss": 1.8975,
      "step": 100
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 2.182361125946045,
      "learning_rate": 9.999793100349294e-06,
      "loss": 1.8837,
      "step": 120
    },
    {
      "epoch": 0.24305555555555555,
      "grad_norm": 2.6428465843200684,
      "learning_rate": 9.987843743451796e-06,
      "loss": 1.7797,
      "step": 140
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 2.0262956619262695,
      "learning_rate": 9.957553516178782e-06,
      "loss": 1.7065,
      "step": 160
    },
    {
      "epoch": 0.3125,
      "grad_norm": 2.2093276977539062,
      "learning_rate": 9.909033799150947e-06,
      "loss": 1.7603,
      "step": 180
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 2.3105509281158447,
      "learning_rate": 9.842463004902127e-06,
      "loss": 1.6663,
      "step": 200
    },
    {
      "epoch": 0.3819444444444444,
      "grad_norm": 2.660855770111084,
      "learning_rate": 9.758085921836076e-06,
      "loss": 1.6556,
      "step": 220
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 2.4641621112823486,
      "learning_rate": 9.656212814111567e-06,
      "loss": 1.6587,
      "step": 240
    },
    {
      "epoch": 0.4513888888888889,
      "grad_norm": 2.65177583694458,
      "learning_rate": 9.53721828076571e-06,
      "loss": 1.6424,
      "step": 260
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 2.779574394226074,
      "learning_rate": 9.401539878270545e-06,
      "loss": 1.6302,
      "step": 280
    },
    {
      "epoch": 0.5208333333333334,
      "grad_norm": 2.8638408184051514,
      "learning_rate": 9.249676511588e-06,
      "loss": 1.6312,
      "step": 300
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 3.208831787109375,
      "learning_rate": 9.082186599639429e-06,
      "loss": 1.6097,
      "step": 320
    },
    {
      "epoch": 0.5902777777777778,
      "grad_norm": 2.5734481811523438,
      "learning_rate": 8.899686021935554e-06,
      "loss": 1.5967,
      "step": 340
    },
    {
      "epoch": 0.625,
      "grad_norm": 2.6115477085113525,
      "learning_rate": 8.702845853917242e-06,
      "loss": 1.5803,
      "step": 360
    },
    {
      "epoch": 0.6597222222222222,
      "grad_norm": 2.46243953704834,
      "learning_rate": 8.492389899334572e-06,
      "loss": 1.5576,
      "step": 380
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 3.08601975440979,
      "learning_rate": 8.269092028737885e-06,
      "loss": 1.5434,
      "step": 400
    },
    {
      "epoch": 0.7291666666666666,
      "grad_norm": 2.877305030822754,
      "learning_rate": 8.033773333867498e-06,
      "loss": 1.5266,
      "step": 420
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 2.7357547283172607,
      "learning_rate": 7.78729910840572e-06,
      "loss": 1.518,
      "step": 440
    },
    {
      "epoch": 0.7986111111111112,
      "grad_norm": 3.0699241161346436,
      "learning_rate": 7.530575666193283e-06,
      "loss": 1.5126,
      "step": 460
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 3.164865255355835,
      "learning_rate": 7.26454700860997e-06,
      "loss": 1.4973,
      "step": 480
    },
    {
      "epoch": 0.8680555555555556,
      "grad_norm": 3.363128662109375,
      "learning_rate": 6.990191353373876e-06,
      "loss": 1.504,
      "step": 500
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 3.5045032501220703,
      "learning_rate": 6.708517537523264e-06,
      "loss": 1.4595,
      "step": 520
    },
    {
      "epoch": 0.9375,
      "grad_norm": 3.302361488342285,
      "learning_rate": 6.420561307807713e-06,
      "loss": 1.4815,
      "step": 540
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 2.9132392406463623,
      "learning_rate": 6.12738151212918e-06,
      "loss": 1.4925,
      "step": 560
    },
    {
      "epoch": 1.0069444444444444,
      "grad_norm": 3.870426654815674,
      "learning_rate": 5.830056206037482e-06,
      "loss": 1.4602,
      "step": 580
    },
    {
      "epoch": 1.0416666666666667,
      "grad_norm": 3.9702446460723877,
      "learning_rate": 5.529678688597081e-06,
      "loss": 1.3977,
      "step": 600
    },
    {
      "epoch": 1.0763888888888888,
      "grad_norm": 3.6180670261383057,
      "learning_rate": 5.2273534822017105e-06,
      "loss": 1.4009,
      "step": 620
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 3.728706121444702,
      "learning_rate": 4.924192271119554e-06,
      "loss": 1.3649,
      "step": 640
    },
    {
      "epoch": 1.1458333333333333,
      "grad_norm": 2.9779577255249023,
      "learning_rate": 4.621309813703385e-06,
      "loss": 1.3779,
      "step": 660
    },
    {
      "epoch": 1.1805555555555556,
      "grad_norm": 4.165585517883301,
      "learning_rate": 4.319819843296952e-06,
      "loss": 1.3897,
      "step": 680
    },
    {
      "epoch": 1.2152777777777777,
      "grad_norm": 3.635356903076172,
      "learning_rate": 4.020830972910433e-06,
      "loss": 1.3946,
      "step": 700
    },
    {
      "epoch": 1.25,
      "grad_norm": 3.2752726078033447,
      "learning_rate": 3.7254426187239567e-06,
      "loss": 1.3435,
      "step": 720
    },
    {
      "epoch": 1.2847222222222223,
      "grad_norm": 3.6443591117858887,
      "learning_rate": 3.4347409574088896e-06,
      "loss": 1.3629,
      "step": 740
    },
    {
      "epoch": 1.3194444444444444,
      "grad_norm": 4.365672588348389,
      "learning_rate": 3.149794932132331e-06,
      "loss": 1.3711,
      "step": 760
    },
    {
      "epoch": 1.3541666666666667,
      "grad_norm": 4.400868892669678,
      "learning_rate": 2.871652321931161e-06,
      "loss": 1.347,
      "step": 780
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 2.929353713989258,
      "learning_rate": 2.601335888909005e-06,
      "loss": 1.358,
      "step": 800
    },
    {
      "epoch": 1.4236111111111112,
      "grad_norm": 3.9870338439941406,
      "learning_rate": 2.339839617423318e-06,
      "loss": 1.3254,
      "step": 820
    },
    {
      "epoch": 1.4583333333333333,
      "grad_norm": 3.580916404724121,
      "learning_rate": 2.0881250590915316e-06,
      "loss": 1.3363,
      "step": 840
    },
    {
      "epoch": 1.4930555555555556,
      "grad_norm": 3.867156505584717,
      "learning_rate": 1.8471177970560712e-06,
      "loss": 1.3519,
      "step": 860
    },
    {
      "epoch": 1.5277777777777777,
      "grad_norm": 3.1973142623901367,
      "learning_rate": 1.6177040425095664e-06,
      "loss": 1.3078,
      "step": 880
    },
    {
      "epoch": 1.5625,
      "grad_norm": 3.530712604522705,
      "learning_rate": 1.40072737599522e-06,
      "loss": 1.3631,
      "step": 900
    },
    {
      "epoch": 1.5972222222222223,
      "grad_norm": 3.1694910526275635,
      "learning_rate": 1.196985645464921e-06,
      "loss": 1.3391,
      "step": 920
    },
    {
      "epoch": 1.6319444444444444,
      "grad_norm": 4.059397220611572,
      "learning_rate": 1.0072280325013185e-06,
      "loss": 1.3277,
      "step": 940
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 4.044768810272217,
      "learning_rate": 8.321522974916968e-07,
      "loss": 1.3542,
      "step": 960
    },
    {
      "epoch": 1.7013888888888888,
      "grad_norm": 4.220571994781494,
      "learning_rate": 6.724022138834341e-07,
      "loss": 1.3201,
      "step": 980
    },
    {
      "epoch": 1.7361111111111112,
      "grad_norm": 3.351271390914917,
      "learning_rate": 5.285652009556075e-07,
      "loss": 1.3154,
      "step": 1000
    },
    {
      "epoch": 1.7708333333333335,
      "grad_norm": 4.178652286529541,
      "learning_rate": 4.0117016381130636e-07,
      "loss": 1.3207,
      "step": 1020
    },
    {
      "epoch": 1.8055555555555556,
      "grad_norm": 4.209657669067383,
      "learning_rate": 2.906855485332305e-07,
      "loss": 1.293,
      "step": 1040
    },
    {
      "epoch": 1.8402777777777777,
      "grad_norm": 3.878786563873291,
      "learning_rate": 1.975176196540185e-07,
      "loss": 1.3221,
      "step": 1060
    },
    {
      "epoch": 1.875,
      "grad_norm": 3.886103868484497,
      "learning_rate": 1.2200896627521718e-07,
      "loss": 1.3304,
      "step": 1080
    },
    {
      "epoch": 1.9097222222222223,
      "grad_norm": 3.7067108154296875,
      "learning_rate": 6.443724232808146e-08,
      "loss": 1.3055,
      "step": 1100
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 4.1525983810424805,
      "learning_rate": 2.501414560839577e-08,
      "loss": 1.2896,
      "step": 1120
    },
    {
      "epoch": 1.9791666666666665,
      "grad_norm": 3.4590396881103516,
      "learning_rate": 3.884639339534202e-09,
      "loss": 1.3044,
      "step": 1140
    }
  ],
  "logging_steps": 20,
  "max_steps": 1152,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3329226634294067e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}