{
  "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": 2.9706010818481445,
      "learning_rate": 1.6379310344827587e-06,
      "loss": 2.6526,
      "step": 20
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 2.301450252532959,
      "learning_rate": 3.362068965517242e-06,
      "loss": 2.4373,
      "step": 40
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 1.887258768081665,
      "learning_rate": 5.086206896551724e-06,
      "loss": 2.2579,
      "step": 60
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 1.8088752031326294,
      "learning_rate": 6.810344827586207e-06,
      "loss": 2.0574,
      "step": 80
    },
    {
      "epoch": 0.1736111111111111,
      "grad_norm": 2.360595464706421,
      "learning_rate": 8.53448275862069e-06,
      "loss": 1.9347,
      "step": 100
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 2.33787202835083,
      "learning_rate": 9.999793100349294e-06,
      "loss": 1.9226,
      "step": 120
    },
    {
      "epoch": 0.24305555555555555,
      "grad_norm": 2.6820693016052246,
      "learning_rate": 9.987843743451796e-06,
      "loss": 1.7899,
      "step": 140
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 2.2135610580444336,
      "learning_rate": 9.957553516178782e-06,
      "loss": 1.7165,
      "step": 160
    },
    {
      "epoch": 0.3125,
      "grad_norm": 2.3095242977142334,
      "learning_rate": 9.909033799150947e-06,
      "loss": 1.7574,
      "step": 180
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 2.454951286315918,
      "learning_rate": 9.842463004902127e-06,
      "loss": 1.6666,
      "step": 200
    },
    {
      "epoch": 0.3819444444444444,
      "grad_norm": 2.481191635131836,
      "learning_rate": 9.758085921836076e-06,
      "loss": 1.6552,
      "step": 220
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 2.6448044776916504,
      "learning_rate": 9.656212814111567e-06,
      "loss": 1.6608,
      "step": 240
    },
    {
      "epoch": 0.4513888888888889,
      "grad_norm": 2.7130963802337646,
      "learning_rate": 9.53721828076571e-06,
      "loss": 1.6351,
      "step": 260
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 2.743367910385132,
      "learning_rate": 9.401539878270545e-06,
      "loss": 1.6349,
      "step": 280
    },
    {
      "epoch": 0.5208333333333334,
      "grad_norm": 3.0086171627044678,
      "learning_rate": 9.249676511588e-06,
      "loss": 1.6278,
      "step": 300
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 2.9393539428710938,
      "learning_rate": 9.082186599639429e-06,
      "loss": 1.6052,
      "step": 320
    },
    {
      "epoch": 0.5902777777777778,
      "grad_norm": 2.597963333129883,
      "learning_rate": 8.899686021935554e-06,
      "loss": 1.5917,
      "step": 340
    },
    {
      "epoch": 0.625,
      "grad_norm": 2.7481658458709717,
      "learning_rate": 8.702845853917242e-06,
      "loss": 1.5707,
      "step": 360
    },
    {
      "epoch": 0.6597222222222222,
      "grad_norm": 2.4585466384887695,
      "learning_rate": 8.492389899334572e-06,
      "loss": 1.5603,
      "step": 380
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 2.9498300552368164,
      "learning_rate": 8.269092028737885e-06,
      "loss": 1.5495,
      "step": 400
    },
    {
      "epoch": 0.7291666666666666,
      "grad_norm": 3.2819886207580566,
      "learning_rate": 8.033773333867498e-06,
      "loss": 1.5243,
      "step": 420
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 2.6484131813049316,
      "learning_rate": 7.78729910840572e-06,
      "loss": 1.5168,
      "step": 440
    },
    {
      "epoch": 0.7986111111111112,
      "grad_norm": 3.1172244548797607,
      "learning_rate": 7.530575666193283e-06,
      "loss": 1.5212,
      "step": 460
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 3.2422311305999756,
      "learning_rate": 7.26454700860997e-06,
      "loss": 1.502,
      "step": 480
    },
    {
      "epoch": 0.8680555555555556,
      "grad_norm": 3.3628528118133545,
      "learning_rate": 6.990191353373876e-06,
      "loss": 1.4961,
      "step": 500
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 3.575122833251953,
      "learning_rate": 6.708517537523264e-06,
      "loss": 1.4765,
      "step": 520
    },
    {
      "epoch": 0.9375,
      "grad_norm": 3.2372570037841797,
      "learning_rate": 6.420561307807713e-06,
      "loss": 1.4824,
      "step": 540
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 2.8427066802978516,
      "learning_rate": 6.12738151212918e-06,
      "loss": 1.5022,
      "step": 560
    },
    {
      "epoch": 1.0069444444444444,
      "grad_norm": 3.6458754539489746,
      "learning_rate": 5.830056206037482e-06,
      "loss": 1.46,
      "step": 580
    },
    {
      "epoch": 1.0416666666666667,
      "grad_norm": 2.912978172302246,
      "learning_rate": 5.529678688597081e-06,
      "loss": 1.398,
      "step": 600
    },
    {
      "epoch": 1.0763888888888888,
      "grad_norm": 3.1993274688720703,
      "learning_rate": 5.2273534822017105e-06,
      "loss": 1.4026,
      "step": 620
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 3.731698989868164,
      "learning_rate": 4.924192271119554e-06,
      "loss": 1.3785,
      "step": 640
    },
    {
      "epoch": 1.1458333333333333,
      "grad_norm": 2.932826519012451,
      "learning_rate": 4.621309813703385e-06,
      "loss": 1.3778,
      "step": 660
    },
    {
      "epoch": 1.1805555555555556,
      "grad_norm": 4.353283882141113,
      "learning_rate": 4.319819843296952e-06,
      "loss": 1.3851,
      "step": 680
    },
    {
      "epoch": 1.2152777777777777,
      "grad_norm": 3.4666543006896973,
      "learning_rate": 4.020830972910433e-06,
      "loss": 1.3936,
      "step": 700
    },
    {
      "epoch": 1.25,
      "grad_norm": 3.56022572517395,
      "learning_rate": 3.7254426187239567e-06,
      "loss": 1.347,
      "step": 720
    },
    {
      "epoch": 1.2847222222222223,
      "grad_norm": 3.4826321601867676,
      "learning_rate": 3.4347409574088896e-06,
      "loss": 1.3648,
      "step": 740
    },
    {
      "epoch": 1.3194444444444444,
      "grad_norm": 4.019125461578369,
      "learning_rate": 3.149794932132331e-06,
      "loss": 1.3877,
      "step": 760
    },
    {
      "epoch": 1.3541666666666667,
      "grad_norm": 4.1424455642700195,
      "learning_rate": 2.871652321931161e-06,
      "loss": 1.3616,
      "step": 780
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 2.841132879257202,
      "learning_rate": 2.601335888909005e-06,
      "loss": 1.3681,
      "step": 800
    },
    {
      "epoch": 1.4236111111111112,
      "grad_norm": 3.864380359649658,
      "learning_rate": 2.339839617423318e-06,
      "loss": 1.3329,
      "step": 820
    },
    {
      "epoch": 1.4583333333333333,
      "grad_norm": 3.7631781101226807,
      "learning_rate": 2.0881250590915316e-06,
      "loss": 1.3516,
      "step": 840
    },
    {
      "epoch": 1.4930555555555556,
      "grad_norm": 3.9342710971832275,
      "learning_rate": 1.8471177970560712e-06,
      "loss": 1.3654,
      "step": 860
    },
    {
      "epoch": 1.5277777777777777,
      "grad_norm": 3.125939130783081,
      "learning_rate": 1.6177040425095664e-06,
      "loss": 1.3275,
      "step": 880
    },
    {
      "epoch": 1.5625,
      "grad_norm": 3.5633015632629395,
      "learning_rate": 1.40072737599522e-06,
      "loss": 1.3625,
      "step": 900
    },
    {
      "epoch": 1.5972222222222223,
      "grad_norm": 3.0462486743927,
      "learning_rate": 1.196985645464921e-06,
      "loss": 1.3374,
      "step": 920
    },
    {
      "epoch": 1.6319444444444444,
      "grad_norm": 4.204705715179443,
      "learning_rate": 1.0072280325013185e-06,
      "loss": 1.3436,
      "step": 940
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 3.840958833694458,
      "learning_rate": 8.321522974916968e-07,
      "loss": 1.3617,
      "step": 960
    },
    {
      "epoch": 1.7013888888888888,
      "grad_norm": 4.040160179138184,
      "learning_rate": 6.724022138834341e-07,
      "loss": 1.3318,
      "step": 980
    },
    {
      "epoch": 1.7361111111111112,
      "grad_norm": 3.265064001083374,
      "learning_rate": 5.285652009556075e-07,
      "loss": 1.3269,
      "step": 1000
    },
    {
      "epoch": 1.7708333333333335,
      "grad_norm": 4.094176769256592,
      "learning_rate": 4.0117016381130636e-07,
      "loss": 1.3373,
      "step": 1020
    },
    {
      "epoch": 1.8055555555555556,
      "grad_norm": 3.8886730670928955,
      "learning_rate": 2.906855485332305e-07,
      "loss": 1.3045,
      "step": 1040
    },
    {
      "epoch": 1.8402777777777777,
      "grad_norm": 3.6427135467529297,
      "learning_rate": 1.975176196540185e-07,
      "loss": 1.3346,
      "step": 1060
    },
    {
      "epoch": 1.875,
      "grad_norm": 4.0230793952941895,
      "learning_rate": 1.2200896627521718e-07,
      "loss": 1.3439,
      "step": 1080
    },
    {
      "epoch": 1.9097222222222223,
      "grad_norm": 3.616853952407837,
      "learning_rate": 6.443724232808146e-08,
      "loss": 1.3216,
      "step": 1100
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 4.038498401641846,
      "learning_rate": 2.501414560839577e-08,
      "loss": 1.2977,
      "step": 1120
    },
    {
      "epoch": 1.9791666666666665,
      "grad_norm": 3.5531771183013916,
      "learning_rate": 3.884639339534202e-09,
      "loss": 1.317,
      "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": 2.3405557230187315e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}