{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.2620169651272386,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03770028275212064,
      "grad_norm": 3.2918148040771484,
      "learning_rate": 4.9995083170283816e-05,
      "loss": 4.3742,
      "num_input_tokens_seen": 50544,
      "step": 5
    },
    {
      "epoch": 0.07540056550424128,
      "grad_norm": 3.0331127643585205,
      "learning_rate": 4.998033461515242e-05,
      "loss": 3.8434,
      "num_input_tokens_seen": 104080,
      "step": 10
    },
    {
      "epoch": 0.11310084825636192,
      "grad_norm": 3.322950601577759,
      "learning_rate": 4.9955760135896534e-05,
      "loss": 3.6027,
      "num_input_tokens_seen": 155776,
      "step": 15
    },
    {
      "epoch": 0.15080113100848255,
      "grad_norm": 2.7705531120300293,
      "learning_rate": 4.992136939879856e-05,
      "loss": 3.4102,
      "num_input_tokens_seen": 203184,
      "step": 20
    },
    {
      "epoch": 0.1885014137606032,
      "grad_norm": 3.4572091102600098,
      "learning_rate": 4.9877175931330346e-05,
      "loss": 3.153,
      "num_input_tokens_seen": 255744,
      "step": 25
    },
    {
      "epoch": 0.22620169651272384,
      "grad_norm": 2.0412893295288086,
      "learning_rate": 4.982319711683221e-05,
      "loss": 3.0949,
      "num_input_tokens_seen": 307808,
      "step": 30
    },
    {
      "epoch": 0.2639019792648445,
      "grad_norm": 2.0765998363494873,
      "learning_rate": 4.975945418767529e-05,
      "loss": 3.0392,
      "num_input_tokens_seen": 358192,
      "step": 35
    },
    {
      "epoch": 0.3016022620169651,
      "grad_norm": 2.2433698177337646,
      "learning_rate": 4.968597221690986e-05,
      "loss": 3.0685,
      "num_input_tokens_seen": 408832,
      "step": 40
    },
    {
      "epoch": 0.3393025447690858,
      "grad_norm": 2.7639973163604736,
      "learning_rate": 4.96027801084029e-05,
      "loss": 3.0385,
      "num_input_tokens_seen": 458368,
      "step": 45
    },
    {
      "epoch": 0.3770028275212064,
      "grad_norm": 2.0680019855499268,
      "learning_rate": 4.950991058546893e-05,
      "loss": 3.1079,
      "num_input_tokens_seen": 512160,
      "step": 50
    },
    {
      "epoch": 0.41470311027332707,
      "grad_norm": 2.181554079055786,
      "learning_rate": 4.940740017799833e-05,
      "loss": 2.9883,
      "num_input_tokens_seen": 562928,
      "step": 55
    },
    {
      "epoch": 0.4524033930254477,
      "grad_norm": 2.0724411010742188,
      "learning_rate": 4.929528920808854e-05,
      "loss": 2.969,
      "num_input_tokens_seen": 613072,
      "step": 60
    },
    {
      "epoch": 0.49010367577756836,
      "grad_norm": 2.5529158115386963,
      "learning_rate": 4.917362177418342e-05,
      "loss": 3.0019,
      "num_input_tokens_seen": 664640,
      "step": 65
    },
    {
      "epoch": 0.527803958529689,
      "grad_norm": 2.3983142375946045,
      "learning_rate": 4.904244573372733e-05,
      "loss": 2.9984,
      "num_input_tokens_seen": 716800,
      "step": 70
    },
    {
      "epoch": 0.5655042412818096,
      "grad_norm": 2.206209182739258,
      "learning_rate": 4.8901812684340564e-05,
      "loss": 2.9848,
      "num_input_tokens_seen": 766528,
      "step": 75
    },
    {
      "epoch": 0.6032045240339302,
      "grad_norm": 2.22698974609375,
      "learning_rate": 4.8751777943523634e-05,
      "loss": 2.9169,
      "num_input_tokens_seen": 817376,
      "step": 80
    },
    {
      "epoch": 0.6409048067860509,
      "grad_norm": 2.4569709300994873,
      "learning_rate": 4.8592400526898314e-05,
      "loss": 2.8844,
      "num_input_tokens_seen": 864688,
      "step": 85
    },
    {
      "epoch": 0.6786050895381716,
      "grad_norm": 2.195237636566162,
      "learning_rate": 4.842374312499405e-05,
      "loss": 2.9422,
      "num_input_tokens_seen": 913216,
      "step": 90
    },
    {
      "epoch": 0.7163053722902922,
      "grad_norm": 2.54585599899292,
      "learning_rate": 4.824587207858888e-05,
      "loss": 2.8431,
      "num_input_tokens_seen": 964144,
      "step": 95
    },
    {
      "epoch": 0.7540056550424128,
      "grad_norm": 2.3841867446899414,
      "learning_rate": 4.805885735261454e-05,
      "loss": 2.8377,
      "num_input_tokens_seen": 1018768,
      "step": 100
    },
    {
      "epoch": 0.7917059377945335,
      "grad_norm": 2.359386920928955,
      "learning_rate": 4.786277250863599e-05,
      "loss": 2.7843,
      "num_input_tokens_seen": 1070592,
      "step": 105
    },
    {
      "epoch": 0.8294062205466541,
      "grad_norm": 2.0952038764953613,
      "learning_rate": 4.765769467591625e-05,
      "loss": 2.8218,
      "num_input_tokens_seen": 1125392,
      "step": 110
    },
    {
      "epoch": 0.8671065032987747,
      "grad_norm": 2.222754955291748,
      "learning_rate": 4.744370452107789e-05,
      "loss": 2.877,
      "num_input_tokens_seen": 1176256,
      "step": 115
    },
    {
      "epoch": 0.9048067860508954,
      "grad_norm": 2.3233537673950195,
      "learning_rate": 4.722088621637309e-05,
      "loss": 2.9028,
      "num_input_tokens_seen": 1225376,
      "step": 120
    },
    {
      "epoch": 0.942507068803016,
      "grad_norm": 2.400575876235962,
      "learning_rate": 4.698932740657479e-05,
      "loss": 2.762,
      "num_input_tokens_seen": 1277024,
      "step": 125
    },
    {
      "epoch": 0.9802073515551367,
      "grad_norm": 2.592116117477417,
      "learning_rate": 4.6749119174501975e-05,
      "loss": 2.9164,
      "num_input_tokens_seen": 1322912,
      "step": 130
    },
    {
      "epoch": 1.0179076343072573,
      "grad_norm": 2.563326120376587,
      "learning_rate": 4.6500356005192514e-05,
      "loss": 2.736,
      "num_input_tokens_seen": 1368624,
      "step": 135
    },
    {
      "epoch": 1.055607917059378,
      "grad_norm": 2.3927371501922607,
      "learning_rate": 4.6243135748737864e-05,
      "loss": 2.7414,
      "num_input_tokens_seen": 1417664,
      "step": 140
    },
    {
      "epoch": 1.0933081998114986,
      "grad_norm": 2.597975492477417,
      "learning_rate": 4.597755958179406e-05,
      "loss": 2.6961,
      "num_input_tokens_seen": 1469120,
      "step": 145
    },
    {
      "epoch": 1.1310084825636193,
      "grad_norm": 2.932581663131714,
      "learning_rate": 4.570373196778427e-05,
      "loss": 2.6134,
      "num_input_tokens_seen": 1521632,
      "step": 150
    },
    {
      "epoch": 1.1687087653157398,
      "grad_norm": 3.28389310836792,
      "learning_rate": 4.5421760615808474e-05,
      "loss": 2.7548,
      "num_input_tokens_seen": 1565296,
      "step": 155
    },
    {
      "epoch": 1.2064090480678604,
      "grad_norm": 2.927279233932495,
      "learning_rate": 4.513175643827647e-05,
      "loss": 2.702,
      "num_input_tokens_seen": 1617088,
      "step": 160
    },
    {
      "epoch": 1.244109330819981,
      "grad_norm": 2.840573310852051,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 2.6893,
      "num_input_tokens_seen": 1663584,
      "step": 165
    },
    {
      "epoch": 1.2818096135721018,
      "grad_norm": 2.6322081089019775,
      "learning_rate": 4.4528109009727336e-05,
      "loss": 2.5671,
      "num_input_tokens_seen": 1713744,
      "step": 170
    },
    {
      "epoch": 1.3195098963242224,
      "grad_norm": 3.1280879974365234,
      "learning_rate": 4.42147032012394e-05,
      "loss": 2.7682,
      "num_input_tokens_seen": 1762768,
      "step": 175
    },
    {
      "epoch": 1.3572101790763431,
      "grad_norm": 3.1128265857696533,
      "learning_rate": 4.389373935885646e-05,
      "loss": 2.7062,
      "num_input_tokens_seen": 1815808,
      "step": 180
    },
    {
      "epoch": 1.3949104618284638,
      "grad_norm": 2.952150344848633,
      "learning_rate": 4.356534373254316e-05,
      "loss": 2.7092,
      "num_input_tokens_seen": 1871040,
      "step": 185
    },
    {
      "epoch": 1.4326107445805842,
      "grad_norm": 3.0146102905273438,
      "learning_rate": 4.322964549552943e-05,
      "loss": 2.6518,
      "num_input_tokens_seen": 1924048,
      "step": 190
    },
    {
      "epoch": 1.4703110273327051,
      "grad_norm": 2.999300956726074,
      "learning_rate": 4.288677669350066e-05,
      "loss": 2.6592,
      "num_input_tokens_seen": 1972720,
      "step": 195
    },
    {
      "epoch": 1.5080113100848256,
      "grad_norm": 3.575253963470459,
      "learning_rate": 4.2536872192658036e-05,
      "loss": 2.716,
      "num_input_tokens_seen": 2022112,
      "step": 200
    },
    {
      "epoch": 1.5457115928369463,
      "grad_norm": 3.1339428424835205,
      "learning_rate": 4.218006962666934e-05,
      "loss": 2.6746,
      "num_input_tokens_seen": 2072000,
      "step": 205
    },
    {
      "epoch": 1.583411875589067,
      "grad_norm": 3.130823850631714,
      "learning_rate": 4.181650934253132e-05,
      "loss": 2.6306,
      "num_input_tokens_seen": 2125632,
      "step": 210
    },
    {
      "epoch": 1.6211121583411876,
      "grad_norm": 3.1828997135162354,
      "learning_rate": 4.144633434536467e-05,
      "loss": 2.5678,
      "num_input_tokens_seen": 2174464,
      "step": 215
    },
    {
      "epoch": 1.6588124410933083,
      "grad_norm": 3.3879778385162354,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 2.7334,
      "num_input_tokens_seen": 2223408,
      "step": 220
    },
    {
      "epoch": 1.6965127238454287,
      "grad_norm": 3.5921592712402344,
      "learning_rate": 4.06867251845213e-05,
      "loss": 2.6658,
      "num_input_tokens_seen": 2281296,
      "step": 225
    },
    {
      "epoch": 1.7342130065975496,
      "grad_norm": 3.4126648902893066,
      "learning_rate": 4.0297589810356165e-05,
      "loss": 2.6567,
      "num_input_tokens_seen": 2334176,
      "step": 230
    },
    {
      "epoch": 1.77191328934967,
      "grad_norm": 3.504786252975464,
      "learning_rate": 3.9902437184657784e-05,
      "loss": 2.6131,
      "num_input_tokens_seen": 2389296,
      "step": 235
    },
    {
      "epoch": 1.8096135721017907,
      "grad_norm": 3.459768056869507,
      "learning_rate": 3.9501422739279956e-05,
      "loss": 2.662,
      "num_input_tokens_seen": 2442800,
      "step": 240
    },
    {
      "epoch": 1.8473138548539114,
      "grad_norm": 2.944490909576416,
      "learning_rate": 3.909470421180201e-05,
      "loss": 2.6339,
      "num_input_tokens_seen": 2494912,
      "step": 245
    },
    {
      "epoch": 1.885014137606032,
      "grad_norm": 3.4897429943084717,
      "learning_rate": 3.8682441583483314e-05,
      "loss": 2.6338,
      "num_input_tokens_seen": 2544624,
      "step": 250
    },
    {
      "epoch": 1.9227144203581528,
      "grad_norm": 3.15039324760437,
      "learning_rate": 3.8264797016335205e-05,
      "loss": 2.6844,
      "num_input_tokens_seen": 2597792,
      "step": 255
    },
    {
      "epoch": 1.9604147031102732,
      "grad_norm": 3.5575578212738037,
      "learning_rate": 3.7841934789335164e-05,
      "loss": 2.5939,
      "num_input_tokens_seen": 2646544,
      "step": 260
    },
    {
      "epoch": 1.998114985862394,
      "grad_norm": 3.97521710395813,
      "learning_rate": 3.741402123380828e-05,
      "loss": 2.7393,
      "num_input_tokens_seen": 2700224,
      "step": 265
    },
    {
      "epoch": 2.0358152686145146,
      "grad_norm": 3.1736276149749756,
      "learning_rate": 3.6981224668001424e-05,
      "loss": 2.4495,
      "num_input_tokens_seen": 2749104,
      "step": 270
    },
    {
      "epoch": 2.0735155513666355,
      "grad_norm": 3.633033275604248,
      "learning_rate": 3.654371533087586e-05,
      "loss": 2.3823,
      "num_input_tokens_seen": 2802992,
      "step": 275
    },
    {
      "epoch": 2.111215834118756,
      "grad_norm": 3.4200243949890137,
      "learning_rate": 3.610166531514436e-05,
      "loss": 2.474,
      "num_input_tokens_seen": 2844512,
      "step": 280
    },
    {
      "epoch": 2.1489161168708764,
      "grad_norm": 4.055693626403809,
      "learning_rate": 3.565524849957921e-05,
      "loss": 2.4776,
      "num_input_tokens_seen": 2894400,
      "step": 285
    },
    {
      "epoch": 2.1866163996229973,
      "grad_norm": 4.254647254943848,
      "learning_rate": 3.520464048061758e-05,
      "loss": 2.4709,
      "num_input_tokens_seen": 2944688,
      "step": 290
    },
    {
      "epoch": 2.2243166823751177,
      "grad_norm": 4.337226390838623,
      "learning_rate": 3.47500185032913e-05,
      "loss": 2.5009,
      "num_input_tokens_seen": 2994672,
      "step": 295
    },
    {
      "epoch": 2.2620169651272386,
      "grad_norm": 4.424121379852295,
      "learning_rate": 3.4291561391508185e-05,
      "loss": 2.4524,
      "num_input_tokens_seen": 3045344,
      "step": 300
    }
  ],
  "logging_steps": 5,
  "max_steps": 792,
  "num_input_tokens_seen": 3045344,
  "num_train_epochs": 6,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.718184608517325e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}