{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.070298769771529,
      "grad_norm": 0.041015625,
      "learning_rate": 4.972222222222223e-05,
      "loss": 0.6872987270355224,
      "step": 5
    },
    {
      "epoch": 0.140597539543058,
      "grad_norm": 0.036376953125,
      "learning_rate": 4.937500000000001e-05,
      "loss": 0.6830456733703614,
      "step": 10
    },
    {
      "epoch": 0.210896309314587,
      "grad_norm": 0.038330078125,
      "learning_rate": 4.902777777777778e-05,
      "loss": 0.7479233264923095,
      "step": 15
    },
    {
      "epoch": 0.281195079086116,
      "grad_norm": 0.0380859375,
      "learning_rate": 4.8680555555555554e-05,
      "loss": 0.7160741329193115,
      "step": 20
    },
    {
      "epoch": 0.351493848857645,
      "grad_norm": 0.03955078125,
      "learning_rate": 4.8333333333333334e-05,
      "loss": 0.6858582973480225,
      "step": 25
    },
    {
      "epoch": 0.421792618629174,
      "grad_norm": 0.038818359375,
      "learning_rate": 4.7986111111111113e-05,
      "loss": 0.6775042533874511,
      "step": 30
    },
    {
      "epoch": 0.492091388400703,
      "grad_norm": 0.03271484375,
      "learning_rate": 4.7638888888888887e-05,
      "loss": 0.6517538070678711,
      "step": 35
    },
    {
      "epoch": 0.562390158172232,
      "grad_norm": 0.039306640625,
      "learning_rate": 4.7291666666666666e-05,
      "loss": 0.7560918807983399,
      "step": 40
    },
    {
      "epoch": 0.632688927943761,
      "grad_norm": 0.037109375,
      "learning_rate": 4.6944444444444446e-05,
      "loss": 0.7019021511077881,
      "step": 45
    },
    {
      "epoch": 0.70298769771529,
      "grad_norm": 0.03369140625,
      "learning_rate": 4.6597222222222226e-05,
      "loss": 0.6687473297119141,
      "step": 50
    },
    {
      "epoch": 0.773286467486819,
      "grad_norm": 0.03369140625,
      "learning_rate": 4.6250000000000006e-05,
      "loss": 0.6842537879943847,
      "step": 55
    },
    {
      "epoch": 0.843585237258348,
      "grad_norm": 0.03173828125,
      "learning_rate": 4.590277777777778e-05,
      "loss": 0.6241245269775391,
      "step": 60
    },
    {
      "epoch": 0.9138840070298769,
      "grad_norm": 0.038818359375,
      "learning_rate": 4.555555555555556e-05,
      "loss": 0.6967287063598633,
      "step": 65
    },
    {
      "epoch": 0.984182776801406,
      "grad_norm": 0.036376953125,
      "learning_rate": 4.520833333333334e-05,
      "loss": 0.6635632038116455,
      "step": 70
    },
    {
      "epoch": 1.0421792618629173,
      "grad_norm": 0.032958984375,
      "learning_rate": 4.486111111111111e-05,
      "loss": 0.6175796985626221,
      "step": 75
    },
    {
      "epoch": 1.1124780316344465,
      "grad_norm": 0.033203125,
      "learning_rate": 4.4513888888888885e-05,
      "loss": 0.5492826938629151,
      "step": 80
    },
    {
      "epoch": 1.1827768014059754,
      "grad_norm": 0.047119140625,
      "learning_rate": 4.4166666666666665e-05,
      "loss": 0.5715642452239991,
      "step": 85
    },
    {
      "epoch": 1.2530755711775043,
      "grad_norm": 0.03857421875,
      "learning_rate": 4.3819444444444445e-05,
      "loss": 0.6231389522552491,
      "step": 90
    },
    {
      "epoch": 1.3233743409490333,
      "grad_norm": 0.040283203125,
      "learning_rate": 4.3472222222222225e-05,
      "loss": 0.5583981513977051,
      "step": 95
    },
    {
      "epoch": 1.3936731107205624,
      "grad_norm": 0.04736328125,
      "learning_rate": 4.3125000000000005e-05,
      "loss": 0.5893191814422607,
      "step": 100
    },
    {
      "epoch": 1.4639718804920914,
      "grad_norm": 0.041015625,
      "learning_rate": 4.277777777777778e-05,
      "loss": 0.5815530776977539,
      "step": 105
    },
    {
      "epoch": 1.5342706502636205,
      "grad_norm": 0.0361328125,
      "learning_rate": 4.243055555555556e-05,
      "loss": 0.5973546504974365,
      "step": 110
    },
    {
      "epoch": 1.6045694200351495,
      "grad_norm": 0.041259765625,
      "learning_rate": 4.208333333333334e-05,
      "loss": 0.5985394954681397,
      "step": 115
    },
    {
      "epoch": 1.6748681898066784,
      "grad_norm": 0.0311279296875,
      "learning_rate": 4.173611111111112e-05,
      "loss": 0.5578798294067383,
      "step": 120
    },
    {
      "epoch": 1.7451669595782073,
      "grad_norm": 0.036376953125,
      "learning_rate": 4.138888888888889e-05,
      "loss": 0.5978553295135498,
      "step": 125
    },
    {
      "epoch": 1.8154657293497363,
      "grad_norm": 0.041748046875,
      "learning_rate": 4.104166666666667e-05,
      "loss": 0.6134780406951904,
      "step": 130
    },
    {
      "epoch": 1.8857644991212654,
      "grad_norm": 0.041748046875,
      "learning_rate": 4.0694444444444444e-05,
      "loss": 0.5452652454376221,
      "step": 135
    },
    {
      "epoch": 1.9560632688927944,
      "grad_norm": 0.03759765625,
      "learning_rate": 4.0347222222222223e-05,
      "loss": 0.5957761287689209,
      "step": 140
    },
    {
      "epoch": 2.0140597539543057,
      "grad_norm": 0.04248046875,
      "learning_rate": 4e-05,
      "loss": 0.5168804168701172,
      "step": 145
    },
    {
      "epoch": 2.0843585237258346,
      "grad_norm": 0.037353515625,
      "learning_rate": 3.9652777777777776e-05,
      "loss": 0.5173678398132324,
      "step": 150
    },
    {
      "epoch": 2.1546572934973636,
      "grad_norm": 0.049072265625,
      "learning_rate": 3.9305555555555556e-05,
      "loss": 0.4964570999145508,
      "step": 155
    },
    {
      "epoch": 2.224956063268893,
      "grad_norm": 0.03759765625,
      "learning_rate": 3.8958333333333336e-05,
      "loss": 0.5181522846221924,
      "step": 160
    },
    {
      "epoch": 2.295254833040422,
      "grad_norm": 0.040283203125,
      "learning_rate": 3.8611111111111116e-05,
      "loss": 0.5013093948364258,
      "step": 165
    },
    {
      "epoch": 2.365553602811951,
      "grad_norm": 0.042236328125,
      "learning_rate": 3.826388888888889e-05,
      "loss": 0.4920492649078369,
      "step": 170
    },
    {
      "epoch": 2.4358523725834798,
      "grad_norm": 0.04638671875,
      "learning_rate": 3.791666666666667e-05,
      "loss": 0.5080994129180908,
      "step": 175
    },
    {
      "epoch": 2.5061511423550087,
      "grad_norm": 0.052001953125,
      "learning_rate": 3.756944444444445e-05,
      "loss": 0.4756940364837646,
      "step": 180
    },
    {
      "epoch": 2.5764499121265376,
      "grad_norm": 0.03662109375,
      "learning_rate": 3.722222222222222e-05,
      "loss": 0.5371941566467285,
      "step": 185
    },
    {
      "epoch": 2.6467486818980666,
      "grad_norm": 0.0439453125,
      "learning_rate": 3.6875e-05,
      "loss": 0.5158291816711426,
      "step": 190
    },
    {
      "epoch": 2.717047451669596,
      "grad_norm": 0.04150390625,
      "learning_rate": 3.6527777777777775e-05,
      "loss": 0.4983774185180664,
      "step": 195
    },
    {
      "epoch": 2.787346221441125,
      "grad_norm": 0.039794921875,
      "learning_rate": 3.6180555555555555e-05,
      "loss": 0.4556784152984619,
      "step": 200
    },
    {
      "epoch": 2.857644991212654,
      "grad_norm": 0.048828125,
      "learning_rate": 3.5833333333333335e-05,
      "loss": 0.5201966762542725,
      "step": 205
    },
    {
      "epoch": 2.9279437609841827,
      "grad_norm": 0.047607421875,
      "learning_rate": 3.5486111111111115e-05,
      "loss": 0.5155319690704345,
      "step": 210
    },
    {
      "epoch": 2.9982425307557117,
      "grad_norm": 0.043212890625,
      "learning_rate": 3.513888888888889e-05,
      "loss": 0.5122783660888672,
      "step": 215
    },
    {
      "epoch": 3.0562390158172232,
      "grad_norm": 0.055419921875,
      "learning_rate": 3.479166666666667e-05,
      "loss": 0.4267068386077881,
      "step": 220
    },
    {
      "epoch": 3.126537785588752,
      "grad_norm": 0.047119140625,
      "learning_rate": 3.444444444444445e-05,
      "loss": 0.412123966217041,
      "step": 225
    },
    {
      "epoch": 3.196836555360281,
      "grad_norm": 0.045654296875,
      "learning_rate": 3.409722222222223e-05,
      "loss": 0.4540102958679199,
      "step": 230
    },
    {
      "epoch": 3.26713532513181,
      "grad_norm": 0.04443359375,
      "learning_rate": 3.375000000000001e-05,
      "loss": 0.42369518280029295,
      "step": 235
    },
    {
      "epoch": 3.3374340949033394,
      "grad_norm": 0.04833984375,
      "learning_rate": 3.340277777777778e-05,
      "loss": 0.4314465045928955,
      "step": 240
    },
    {
      "epoch": 3.4077328646748684,
      "grad_norm": 0.046142578125,
      "learning_rate": 3.3055555555555553e-05,
      "loss": 0.38359851837158204,
      "step": 245
    },
    {
      "epoch": 3.4780316344463973,
      "grad_norm": 0.05712890625,
      "learning_rate": 3.270833333333333e-05,
      "loss": 0.45005264282226565,
      "step": 250
    },
    {
      "epoch": 3.5483304042179262,
      "grad_norm": 0.046142578125,
      "learning_rate": 3.236111111111111e-05,
      "loss": 0.4752476692199707,
      "step": 255
    },
    {
      "epoch": 3.618629173989455,
      "grad_norm": 0.060546875,
      "learning_rate": 3.2013888888888886e-05,
      "loss": 0.3875174045562744,
      "step": 260
    },
    {
      "epoch": 3.688927943760984,
      "grad_norm": 0.0546875,
      "learning_rate": 3.1666666666666666e-05,
      "loss": 0.40928921699523924,
      "step": 265
    },
    {
      "epoch": 3.759226713532513,
      "grad_norm": 0.044189453125,
      "learning_rate": 3.1319444444444446e-05,
      "loss": 0.4359605312347412,
      "step": 270
    },
    {
      "epoch": 3.8295254833040424,
      "grad_norm": 0.044921875,
      "learning_rate": 3.0972222222222226e-05,
      "loss": 0.3749080657958984,
      "step": 275
    },
    {
      "epoch": 3.899824253075571,
      "grad_norm": 0.04443359375,
      "learning_rate": 3.0625000000000006e-05,
      "loss": 0.47571258544921874,
      "step": 280
    },
    {
      "epoch": 3.9701230228471003,
      "grad_norm": 0.052734375,
      "learning_rate": 3.0277777777777776e-05,
      "loss": 0.4136314868927002,
      "step": 285
    },
    {
      "epoch": 4.028119507908611,
      "grad_norm": 0.068359375,
      "learning_rate": 2.9930555555555555e-05,
      "loss": 0.38009254932403563,
      "step": 290
    },
    {
      "epoch": 4.098418277680141,
      "grad_norm": 0.053466796875,
      "learning_rate": 2.9583333333333335e-05,
      "loss": 0.3919001817703247,
      "step": 295
    },
    {
      "epoch": 4.168717047451669,
      "grad_norm": 0.051513671875,
      "learning_rate": 2.9236111111111115e-05,
      "loss": 0.3375861167907715,
      "step": 300
    },
    {
      "epoch": 4.239015817223199,
      "grad_norm": 0.049560546875,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 0.34033329486846925,
      "step": 305
    },
    {
      "epoch": 4.309314586994727,
      "grad_norm": 0.0537109375,
      "learning_rate": 2.8541666666666668e-05,
      "loss": 0.38448970317840575,
      "step": 310
    },
    {
      "epoch": 4.3796133567662565,
      "grad_norm": 0.05810546875,
      "learning_rate": 2.8194444444444445e-05,
      "loss": 0.3189067840576172,
      "step": 315
    },
    {
      "epoch": 4.449912126537786,
      "grad_norm": 0.0537109375,
      "learning_rate": 2.7847222222222224e-05,
      "loss": 0.31183125972747805,
      "step": 320
    },
    {
      "epoch": 4.520210896309314,
      "grad_norm": 0.053466796875,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.36228208541870116,
      "step": 325
    },
    {
      "epoch": 4.590509666080844,
      "grad_norm": 0.07275390625,
      "learning_rate": 2.7152777777777777e-05,
      "loss": 0.3445222616195679,
      "step": 330
    },
    {
      "epoch": 4.660808435852372,
      "grad_norm": 0.064453125,
      "learning_rate": 2.6805555555555557e-05,
      "loss": 0.3464776039123535,
      "step": 335
    },
    {
      "epoch": 4.731107205623902,
      "grad_norm": 0.06005859375,
      "learning_rate": 2.6458333333333334e-05,
      "loss": 0.36103522777557373,
      "step": 340
    },
    {
      "epoch": 4.801405975395431,
      "grad_norm": 0.04443359375,
      "learning_rate": 2.6111111111111114e-05,
      "loss": 0.35750935077667234,
      "step": 345
    },
    {
      "epoch": 4.8717047451669595,
      "grad_norm": 0.0751953125,
      "learning_rate": 2.5763888888888887e-05,
      "loss": 0.37065398693084717,
      "step": 350
    },
    {
      "epoch": 4.942003514938489,
      "grad_norm": 0.04736328125,
      "learning_rate": 2.5416666666666667e-05,
      "loss": 0.3531635284423828,
      "step": 355
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0869140625,
      "learning_rate": 2.5069444444444447e-05,
      "loss": 0.3129526853561401,
      "step": 360
    }
  ],
  "logging_steps": 5,
  "max_steps": 720,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.78970818510848e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}