{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 0.4841386675834656,
      "learning_rate": 4.997807075247146e-05,
      "loss": 0.688,
      "num_input_tokens_seen": 46776,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.3365215063095093,
      "learning_rate": 4.991232148123761e-05,
      "loss": 0.763,
      "num_input_tokens_seen": 85136,
      "step": 10
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.5198595523834229,
      "learning_rate": 4.980286753286195e-05,
      "loss": 0.6882,
      "num_input_tokens_seen": 126584,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.40807807445526123,
      "learning_rate": 4.964990092676263e-05,
      "loss": 0.6951,
      "num_input_tokens_seen": 167968,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.439756840467453,
      "learning_rate": 4.9453690018345144e-05,
      "loss": 0.5008,
      "num_input_tokens_seen": 206832,
      "step": 25
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.45932796597480774,
      "learning_rate": 4.9214579028215776e-05,
      "loss": 0.542,
      "num_input_tokens_seen": 243656,
      "step": 30
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.3281826376914978,
      "learning_rate": 4.893298743830168e-05,
      "loss": 0.5369,
      "num_input_tokens_seen": 284016,
      "step": 35
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.2551577389240265,
      "learning_rate": 4.860940925593703e-05,
      "loss": 0.4948,
      "num_input_tokens_seen": 327408,
      "step": 40
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.5936368107795715,
      "learning_rate": 4.8244412147206284e-05,
      "loss": 0.5244,
      "num_input_tokens_seen": 363376,
      "step": 45
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.2480110377073288,
      "learning_rate": 4.783863644106502e-05,
      "loss": 0.421,
      "num_input_tokens_seen": 398840,
      "step": 50
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.4601157307624817,
      "learning_rate": 4.7392794005985326e-05,
      "loss": 0.4517,
      "num_input_tokens_seen": 436136,
      "step": 55
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.6387960314750671,
      "learning_rate": 4.690766700109659e-05,
      "loss": 0.4661,
      "num_input_tokens_seen": 475856,
      "step": 60
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.4365377128124237,
      "learning_rate": 4.638410650401267e-05,
      "loss": 0.4928,
      "num_input_tokens_seen": 514496,
      "step": 65
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.2992519438266754,
      "learning_rate": 4.5823031017752485e-05,
      "loss": 0.5424,
      "num_input_tokens_seen": 554424,
      "step": 70
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.828787088394165,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.5419,
      "num_input_tokens_seen": 593264,
      "step": 75
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.2943418622016907,
      "learning_rate": 4.4592336433146e-05,
      "loss": 0.4558,
      "num_input_tokens_seen": 630264,
      "step": 80
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.3707512617111206,
      "learning_rate": 4.3924876391293915e-05,
      "loss": 0.5656,
      "num_input_tokens_seen": 668864,
      "step": 85
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.4809654653072357,
      "learning_rate": 4.3224215685535294e-05,
      "loss": 0.4832,
      "num_input_tokens_seen": 712504,
      "step": 90
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.516292929649353,
      "learning_rate": 4.249158351283414e-05,
      "loss": 0.4626,
      "num_input_tokens_seen": 748872,
      "step": 95
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5604212284088135,
      "learning_rate": 4.172826515897146e-05,
      "loss": 0.4837,
      "num_input_tokens_seen": 788408,
      "step": 100
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.7355071902275085,
      "learning_rate": 4.093559974371725e-05,
      "loss": 0.5144,
      "num_input_tokens_seen": 828448,
      "step": 105
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.46999862790107727,
      "learning_rate": 4.011497787155938e-05,
      "loss": 0.493,
      "num_input_tokens_seen": 864680,
      "step": 110
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.5488362312316895,
      "learning_rate": 3.92678391921108e-05,
      "loss": 0.4083,
      "num_input_tokens_seen": 902568,
      "step": 115
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5053719282150269,
      "learning_rate": 3.8395669874474915e-05,
      "loss": 0.5172,
      "num_input_tokens_seen": 944752,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.44234323501586914,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.5843,
      "num_input_tokens_seen": 988656,
      "step": 125
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.4518623352050781,
      "learning_rate": 3.6582400877996546e-05,
      "loss": 0.4567,
      "num_input_tokens_seen": 1028584,
      "step": 130
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.39792686700820923,
      "learning_rate": 3.564448228912682e-05,
      "loss": 0.418,
      "num_input_tokens_seen": 1065104,
      "step": 135
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.5141780376434326,
      "learning_rate": 3.4687889661302576e-05,
      "loss": 0.3785,
      "num_input_tokens_seen": 1106744,
      "step": 140
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.5755515098571777,
      "learning_rate": 3.3714301183045385e-05,
      "loss": 0.4097,
      "num_input_tokens_seen": 1140672,
      "step": 145
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.4626426696777344,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.4507,
      "num_input_tokens_seen": 1177280,
      "step": 150
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.49699896574020386,
      "learning_rate": 3.172299551538164e-05,
      "loss": 0.368,
      "num_input_tokens_seen": 1215744,
      "step": 155
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.5842998027801514,
      "learning_rate": 3.0708771752766394e-05,
      "loss": 0.4301,
      "num_input_tokens_seen": 1257040,
      "step": 160
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.46173322200775146,
      "learning_rate": 2.9684532864643122e-05,
      "loss": 0.4488,
      "num_input_tokens_seen": 1295992,
      "step": 165
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.4926168918609619,
      "learning_rate": 2.8652075714060295e-05,
      "loss": 0.4075,
      "num_input_tokens_seen": 1334672,
      "step": 170
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.5110897421836853,
      "learning_rate": 2.761321158169134e-05,
      "loss": 0.4991,
      "num_input_tokens_seen": 1379280,
      "step": 175
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.33892518281936646,
      "learning_rate": 2.656976298823284e-05,
      "loss": 0.4894,
      "num_input_tokens_seen": 1419704,
      "step": 180
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.46542254090309143,
      "learning_rate": 2.5523560497083926e-05,
      "loss": 0.4967,
      "num_input_tokens_seen": 1459256,
      "step": 185
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.9100029468536377,
      "learning_rate": 2.447643950291608e-05,
      "loss": 0.5297,
      "num_input_tokens_seen": 1503576,
      "step": 190
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.7347203493118286,
      "learning_rate": 2.3430237011767167e-05,
      "loss": 0.3939,
      "num_input_tokens_seen": 1539904,
      "step": 195
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.6078445315361023,
      "learning_rate": 2.238678841830867e-05,
      "loss": 0.461,
      "num_input_tokens_seen": 1580560,
      "step": 200
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.5878064632415771,
      "learning_rate": 2.1347924285939714e-05,
      "loss": 0.4622,
      "num_input_tokens_seen": 1623608,
      "step": 205
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.6516324877738953,
      "learning_rate": 2.031546713535688e-05,
      "loss": 0.4043,
      "num_input_tokens_seen": 1660744,
      "step": 210
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.9136825203895569,
      "learning_rate": 1.9291228247233605e-05,
      "loss": 0.428,
      "num_input_tokens_seen": 1698784,
      "step": 215
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.751567006111145,
      "learning_rate": 1.827700448461836e-05,
      "loss": 0.3779,
      "num_input_tokens_seen": 1734792,
      "step": 220
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.8802843689918518,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.4526,
      "num_input_tokens_seen": 1776144,
      "step": 225
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.6807656288146973,
      "learning_rate": 1.6285698816954624e-05,
      "loss": 0.4627,
      "num_input_tokens_seen": 1815864,
      "step": 230
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.6222789883613586,
      "learning_rate": 1.5312110338697426e-05,
      "loss": 0.4873,
      "num_input_tokens_seen": 1856168,
      "step": 235
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.5224676728248596,
      "learning_rate": 1.4355517710873184e-05,
      "loss": 0.3234,
      "num_input_tokens_seen": 1899120,
      "step": 240
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.4191940724849701,
      "learning_rate": 1.3417599122003464e-05,
      "loss": 0.4438,
      "num_input_tokens_seen": 1936808,
      "step": 245
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6064372062683105,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.4407,
      "num_input_tokens_seen": 1977312,
      "step": 250
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.5188178420066833,
      "learning_rate": 1.1604330125525079e-05,
      "loss": 0.4401,
      "num_input_tokens_seen": 2018336,
      "step": 255
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.5036932826042175,
      "learning_rate": 1.0732160807889211e-05,
      "loss": 0.3771,
      "num_input_tokens_seen": 2057776,
      "step": 260
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.5732894539833069,
      "learning_rate": 9.88502212844063e-06,
      "loss": 0.4043,
      "num_input_tokens_seen": 2102312,
      "step": 265
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.6521058082580566,
      "learning_rate": 9.064400256282757e-06,
      "loss": 0.4018,
      "num_input_tokens_seen": 2137304,
      "step": 270
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.698835015296936,
      "learning_rate": 8.271734841028553e-06,
      "loss": 0.4258,
      "num_input_tokens_seen": 2176144,
      "step": 275
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.7500255107879639,
      "learning_rate": 7.508416487165862e-06,
      "loss": 0.3912,
      "num_input_tokens_seen": 2211640,
      "step": 280
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.7223864793777466,
      "learning_rate": 6.775784314464717e-06,
      "loss": 0.3458,
      "num_input_tokens_seen": 2247272,
      "step": 285
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.6346307992935181,
      "learning_rate": 6.075123608706093e-06,
      "loss": 0.4255,
      "num_input_tokens_seen": 2285776,
      "step": 290
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.6048356890678406,
      "learning_rate": 5.4076635668540075e-06,
      "loss": 0.4222,
      "num_input_tokens_seen": 2326112,
      "step": 295
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.0743402242660522,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.399,
      "num_input_tokens_seen": 2362816,
      "step": 300
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.6533491015434265,
      "learning_rate": 4.176968982247514e-06,
      "loss": 0.3382,
      "num_input_tokens_seen": 2402328,
      "step": 305
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.7778833508491516,
      "learning_rate": 3.6158934959873353e-06,
      "loss": 0.4465,
      "num_input_tokens_seen": 2445600,
      "step": 310
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.7358531355857849,
      "learning_rate": 3.092332998903416e-06,
      "loss": 0.325,
      "num_input_tokens_seen": 2485840,
      "step": 315
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.7607108354568481,
      "learning_rate": 2.6072059940146775e-06,
      "loss": 0.392,
      "num_input_tokens_seen": 2524760,
      "step": 320
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.7286326289176941,
      "learning_rate": 2.1613635589349756e-06,
      "loss": 0.3672,
      "num_input_tokens_seen": 2562040,
      "step": 325
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.5720709562301636,
      "learning_rate": 1.7555878527937164e-06,
      "loss": 0.3554,
      "num_input_tokens_seen": 2600056,
      "step": 330
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.9434547424316406,
      "learning_rate": 1.3905907440629752e-06,
      "loss": 0.3801,
      "num_input_tokens_seen": 2633392,
      "step": 335
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.9704461693763733,
      "learning_rate": 1.067012561698319e-06,
      "loss": 0.435,
      "num_input_tokens_seen": 2677016,
      "step": 340
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.6400224566459656,
      "learning_rate": 7.854209717842231e-07,
      "loss": 0.4063,
      "num_input_tokens_seen": 2719536,
      "step": 345
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.46599817276000977,
      "learning_rate": 5.463099816548579e-07,
      "loss": 0.4894,
      "num_input_tokens_seen": 2767424,
      "step": 350
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.4850185215473175,
      "learning_rate": 3.5009907323737825e-07,
      "loss": 0.3822,
      "num_input_tokens_seen": 2805832,
      "step": 355
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.8774814605712891,
      "learning_rate": 1.9713246713805588e-07,
      "loss": 0.4028,
      "num_input_tokens_seen": 2845912,
      "step": 360
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.6378630995750427,
      "learning_rate": 8.767851876239074e-08,
      "loss": 0.4293,
      "num_input_tokens_seen": 2888128,
      "step": 365
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.8157021403312683,
      "learning_rate": 2.192924752854042e-08,
      "loss": 0.428,
      "num_input_tokens_seen": 2925024,
      "step": 370
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5457362532615662,
      "learning_rate": 0.0,
      "loss": 0.4766,
      "num_input_tokens_seen": 2965968,
      "step": 375
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 2965968,
      "step": 375,
      "total_flos": 1.2618658999382835e+17,
      "train_loss": 0.45766232585906985,
      "train_runtime": 3803.7297,
      "train_samples_per_second": 1.577,
      "train_steps_per_second": 0.099
    }
  ],
  "logging_steps": 5,
  "max_steps": 375,
  "num_input_tokens_seen": 2965968,
  "num_train_epochs": 3,
  "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": 1.2618658999382835e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}