{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984,
  "eval_steps": 500,
  "global_step": 312,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 0.3705686628818512,
      "learning_rate": 0.00019987329060020616,
      "loss": 2.7276,
      "num_input_tokens_seen": 78104,
      "step": 5
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.28178921341896057,
      "learning_rate": 0.00019949348350626456,
      "loss": 2.6452,
      "num_input_tokens_seen": 157384,
      "step": 10
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.1864372342824936,
      "learning_rate": 0.00019886154122075343,
      "loss": 2.5708,
      "num_input_tokens_seen": 240256,
      "step": 15
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.1788010597229004,
      "learning_rate": 0.00019797906520422677,
      "loss": 2.5831,
      "num_input_tokens_seen": 319032,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.23142138123512268,
      "learning_rate": 0.00019684829181681234,
      "loss": 2.6138,
      "num_input_tokens_seen": 397992,
      "step": 25
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.21496976912021637,
      "learning_rate": 0.00019547208665085457,
      "loss": 2.5461,
      "num_input_tokens_seen": 479904,
      "step": 30
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.2536880671977997,
      "learning_rate": 0.0001938539372689649,
      "loss": 2.5797,
      "num_input_tokens_seen": 555448,
      "step": 35
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.39764249324798584,
      "learning_rate": 0.00019199794436588243,
      "loss": 2.5482,
      "num_input_tokens_seen": 630888,
      "step": 40
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.29237431287765503,
      "learning_rate": 0.00018990881137654258,
      "loss": 2.4726,
      "num_input_tokens_seen": 709456,
      "step": 45
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.24707558751106262,
      "learning_rate": 0.0001875918325566888,
      "loss": 2.5557,
      "num_input_tokens_seen": 788504,
      "step": 50
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.24359019100666046,
      "learning_rate": 0.00018505287956623297,
      "loss": 2.5357,
      "num_input_tokens_seen": 864984,
      "step": 55
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.23572562634944916,
      "learning_rate": 0.00018229838658936564,
      "loss": 2.4798,
      "num_input_tokens_seen": 939136,
      "step": 60
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.41712337732315063,
      "learning_rate": 0.00017933533402912354,
      "loss": 2.5619,
      "num_input_tokens_seen": 1018024,
      "step": 65
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.2777227759361267,
      "learning_rate": 0.00017617123081773591,
      "loss": 2.5334,
      "num_input_tokens_seen": 1095072,
      "step": 70
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.25098717212677,
      "learning_rate": 0.00017281409538757883,
      "loss": 2.5199,
      "num_input_tokens_seen": 1172824,
      "step": 75
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.24321608245372772,
      "learning_rate": 0.00016927243535095997,
      "loss": 2.4897,
      "num_input_tokens_seen": 1244688,
      "step": 80
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.25580549240112305,
      "learning_rate": 0.0001655552259402295,
      "loss": 2.513,
      "num_input_tokens_seen": 1321104,
      "step": 85
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.24990542232990265,
      "learning_rate": 0.00016167188726285434,
      "loss": 2.5533,
      "num_input_tokens_seen": 1402456,
      "step": 90
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.26301833987236023,
      "learning_rate": 0.00015763226042909455,
      "loss": 2.5297,
      "num_input_tokens_seen": 1483648,
      "step": 95
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.23519474267959595,
      "learning_rate": 0.0001534465826127801,
      "loss": 2.518,
      "num_input_tokens_seen": 1560608,
      "step": 100
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.26162955164909363,
      "learning_rate": 0.00014912546110838775,
      "loss": 2.5537,
      "num_input_tokens_seen": 1640728,
      "step": 105
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.2565276026725769,
      "learning_rate": 0.00014467984645016258,
      "loss": 2.489,
      "num_input_tokens_seen": 1722440,
      "step": 110
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.3414108455181122,
      "learning_rate": 0.00014012100466140578,
      "loss": 2.5448,
      "num_input_tokens_seen": 1805984,
      "step": 115
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.2590246796607971,
      "learning_rate": 0.00013546048870425356,
      "loss": 2.4148,
      "num_input_tokens_seen": 1890592,
      "step": 120
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.2765924036502838,
      "learning_rate": 0.00013071010920229909,
      "loss": 2.5512,
      "num_input_tokens_seen": 1971272,
      "step": 125
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.2582058906555176,
      "learning_rate": 0.00012588190451025207,
      "loss": 2.5264,
      "num_input_tokens_seen": 2053352,
      "step": 130
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.2416098713874817,
      "learning_rate": 0.00012098811020648475,
      "loss": 2.5525,
      "num_input_tokens_seen": 2132624,
      "step": 135
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.3602483868598938,
      "learning_rate": 0.00011604112808577603,
      "loss": 2.5029,
      "num_input_tokens_seen": 2210376,
      "step": 140
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.2507006824016571,
      "learning_rate": 0.000111053494730832,
      "loss": 2.5546,
      "num_input_tokens_seen": 2292896,
      "step": 145
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.32158130407333374,
      "learning_rate": 0.00010603784974222861,
      "loss": 2.5431,
      "num_input_tokens_seen": 2376432,
      "step": 150
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.3036045730113983,
      "learning_rate": 0.00010100690370728755,
      "loss": 2.4882,
      "num_input_tokens_seen": 2451848,
      "step": 155
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.31646254658699036,
      "learning_rate": 9.597340598905852e-05,
      "loss": 2.4319,
      "num_input_tokens_seen": 2532816,
      "step": 160
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.2881500720977783,
      "learning_rate": 9.095011241703623e-05,
      "loss": 2.4688,
      "num_input_tokens_seen": 2616160,
      "step": 165
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.27659812569618225,
      "learning_rate": 8.594975296149076e-05,
      "loss": 2.5149,
      "num_input_tokens_seen": 2694864,
      "step": 170
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.4290514290332794,
      "learning_rate": 8.098499947332934e-05,
      "loss": 2.4754,
      "num_input_tokens_seen": 2770464,
      "step": 175
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.28775912523269653,
      "learning_rate": 7.606843357124426e-05,
      "loss": 2.4875,
      "num_input_tokens_seen": 2852888,
      "step": 180
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.2709747850894928,
      "learning_rate": 7.121251475752539e-05,
      "loss": 2.563,
      "num_input_tokens_seen": 2933520,
      "step": 185
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.3473074734210968,
      "learning_rate": 6.642954884333955e-05,
      "loss": 2.4903,
      "num_input_tokens_seen": 3011656,
      "step": 190
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.28855767846107483,
      "learning_rate": 6.173165676349103e-05,
      "loss": 2.5325,
      "num_input_tokens_seen": 3088960,
      "step": 195
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.27710187435150146,
      "learning_rate": 5.713074385969457e-05,
      "loss": 2.4344,
      "num_input_tokens_seen": 3165160,
      "step": 200
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.3773224651813507,
      "learning_rate": 5.263846971020108e-05,
      "loss": 2.4747,
      "num_input_tokens_seen": 3242128,
      "step": 205
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.3007236123085022,
      "learning_rate": 4.826621858223431e-05,
      "loss": 2.4753,
      "num_input_tokens_seen": 3323840,
      "step": 210
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.2919347286224365,
      "learning_rate": 4.40250705821178e-05,
      "loss": 2.513,
      "num_input_tokens_seen": 3404144,
      "step": 215
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.26084381341934204,
      "learning_rate": 3.99257735762021e-05,
      "loss": 2.5244,
      "num_input_tokens_seen": 3481992,
      "step": 220
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.3810001611709595,
      "learning_rate": 3.597871595375121e-05,
      "loss": 2.4893,
      "num_input_tokens_seen": 3562480,
      "step": 225
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.2814476191997528,
      "learning_rate": 3.219390030081091e-05,
      "loss": 2.5374,
      "num_input_tokens_seen": 3648552,
      "step": 230
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.2949189841747284,
      "learning_rate": 2.858091805177554e-05,
      "loss": 2.4568,
      "num_input_tokens_seen": 3720616,
      "step": 235
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.32114091515541077,
      "learning_rate": 2.514892518288988e-05,
      "loss": 2.4686,
      "num_input_tokens_seen": 3804368,
      "step": 240
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.30282753705978394,
      "learning_rate": 2.1906619009284257e-05,
      "loss": 2.5268,
      "num_input_tokens_seen": 3880720,
      "step": 245
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.25529351830482483,
      "learning_rate": 1.8862216144342692e-05,
      "loss": 2.4932,
      "num_input_tokens_seen": 3970064,
      "step": 250
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.25532060861587524,
      "learning_rate": 1.6023431677260214e-05,
      "loss": 2.4882,
      "num_input_tokens_seen": 4052712,
      "step": 255
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.32484114170074463,
      "learning_rate": 1.339745962155613e-05,
      "loss": 2.5897,
      "num_input_tokens_seen": 4133104,
      "step": 260
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.2640307545661926,
      "learning_rate": 1.0990954684091558e-05,
      "loss": 2.4555,
      "num_input_tokens_seen": 4213160,
      "step": 265
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.6774325370788574,
      "learning_rate": 8.810015400790994e-06,
      "loss": 2.5311,
      "num_input_tokens_seen": 4294240,
      "step": 270
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.3231619596481323,
      "learning_rate": 6.860168681805945e-06,
      "loss": 2.4318,
      "num_input_tokens_seen": 4373680,
      "step": 275
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.29059651494026184,
      "learning_rate": 5.146355805285452e-06,
      "loss": 2.4513,
      "num_input_tokens_seen": 4452712,
      "step": 280
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.4263499975204468,
      "learning_rate": 3.6729198952483724e-06,
      "loss": 2.4889,
      "num_input_tokens_seen": 4531416,
      "step": 285
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.3342815935611725,
      "learning_rate": 2.4435949152906145e-06,
      "loss": 2.5461,
      "num_input_tokens_seen": 4617984,
      "step": 290
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.2988833785057068,
      "learning_rate": 1.4614962060194304e-06,
      "loss": 2.4965,
      "num_input_tokens_seen": 4698024,
      "step": 295
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.2836878299713135,
      "learning_rate": 7.291125901946027e-07,
      "loss": 2.5403,
      "num_input_tokens_seen": 4779504,
      "step": 300
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.33278706669807434,
      "learning_rate": 2.4830006558373973e-07,
      "loss": 2.4873,
      "num_input_tokens_seen": 4860096,
      "step": 305
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.29044637084007263,
      "learning_rate": 2.0277101514987184e-08,
      "loss": 2.4988,
      "num_input_tokens_seen": 4942216,
      "step": 310
    },
    {
      "epoch": 0.9984,
      "num_input_tokens_seen": 4974128,
      "step": 312,
      "total_flos": 2.056832720704635e+17,
      "train_loss": 2.5180979997683792,
      "train_runtime": 14081.4059,
      "train_samples_per_second": 1.42,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 5,
  "max_steps": 312,
  "num_input_tokens_seen": 4974128,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.056832720704635e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}