{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9880794701986755,
  "eval_steps": 500,
  "global_step": 564,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 2.3983146952234486,
      "learning_rate": 5e-06,
      "loss": 0.9851,
      "step": 10
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": 1.7246649174554667,
      "learning_rate": 5e-06,
      "loss": 0.8319,
      "step": 20
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": 3.601038796091522,
      "learning_rate": 5e-06,
      "loss": 0.8075,
      "step": 30
    },
    {
      "epoch": 0.2119205298013245,
      "grad_norm": 1.2059052889786372,
      "learning_rate": 5e-06,
      "loss": 0.7915,
      "step": 40
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 1.3608839677655582,
      "learning_rate": 5e-06,
      "loss": 0.7709,
      "step": 50
    },
    {
      "epoch": 0.31788079470198677,
      "grad_norm": 1.2434441624370192,
      "learning_rate": 5e-06,
      "loss": 0.7621,
      "step": 60
    },
    {
      "epoch": 0.3708609271523179,
      "grad_norm": 0.9441777855534653,
      "learning_rate": 5e-06,
      "loss": 0.7454,
      "step": 70
    },
    {
      "epoch": 0.423841059602649,
      "grad_norm": 1.5125978662591961,
      "learning_rate": 5e-06,
      "loss": 0.7248,
      "step": 80
    },
    {
      "epoch": 0.4768211920529801,
      "grad_norm": 0.7471461569802452,
      "learning_rate": 5e-06,
      "loss": 0.7275,
      "step": 90
    },
    {
      "epoch": 0.5298013245033113,
      "grad_norm": 0.645516397675585,
      "learning_rate": 5e-06,
      "loss": 0.7123,
      "step": 100
    },
    {
      "epoch": 0.5827814569536424,
      "grad_norm": 0.7251445711578004,
      "learning_rate": 5e-06,
      "loss": 0.7117,
      "step": 110
    },
    {
      "epoch": 0.6357615894039735,
      "grad_norm": 0.651327566584479,
      "learning_rate": 5e-06,
      "loss": 0.7119,
      "step": 120
    },
    {
      "epoch": 0.6887417218543046,
      "grad_norm": 0.6140018870668793,
      "learning_rate": 5e-06,
      "loss": 0.7053,
      "step": 130
    },
    {
      "epoch": 0.7417218543046358,
      "grad_norm": 0.5388085038750972,
      "learning_rate": 5e-06,
      "loss": 0.7022,
      "step": 140
    },
    {
      "epoch": 0.7947019867549668,
      "grad_norm": 1.010650981679106,
      "learning_rate": 5e-06,
      "loss": 0.6987,
      "step": 150
    },
    {
      "epoch": 0.847682119205298,
      "grad_norm": 1.1037782052291758,
      "learning_rate": 5e-06,
      "loss": 0.6976,
      "step": 160
    },
    {
      "epoch": 0.9006622516556292,
      "grad_norm": 0.666699690620748,
      "learning_rate": 5e-06,
      "loss": 0.705,
      "step": 170
    },
    {
      "epoch": 0.9536423841059603,
      "grad_norm": 0.5794869194974834,
      "learning_rate": 5e-06,
      "loss": 0.7042,
      "step": 180
    },
    {
      "epoch": 0.9960264900662251,
      "eval_loss": 0.6996881365776062,
      "eval_runtime": 101.9424,
      "eval_samples_per_second": 49.901,
      "eval_steps_per_second": 0.392,
      "step": 188
    },
    {
      "epoch": 1.0066225165562914,
      "grad_norm": 0.8762129194412334,
      "learning_rate": 5e-06,
      "loss": 0.6861,
      "step": 190
    },
    {
      "epoch": 1.0596026490066226,
      "grad_norm": 0.7641648019922738,
      "learning_rate": 5e-06,
      "loss": 0.6399,
      "step": 200
    },
    {
      "epoch": 1.1125827814569536,
      "grad_norm": 0.6026445432992825,
      "learning_rate": 5e-06,
      "loss": 0.6342,
      "step": 210
    },
    {
      "epoch": 1.1655629139072847,
      "grad_norm": 0.5607709134599749,
      "learning_rate": 5e-06,
      "loss": 0.6285,
      "step": 220
    },
    {
      "epoch": 1.218543046357616,
      "grad_norm": 0.723598523167553,
      "learning_rate": 5e-06,
      "loss": 0.654,
      "step": 230
    },
    {
      "epoch": 1.271523178807947,
      "grad_norm": 0.6634015008522252,
      "learning_rate": 5e-06,
      "loss": 0.6474,
      "step": 240
    },
    {
      "epoch": 1.3245033112582782,
      "grad_norm": 0.5676178378824602,
      "learning_rate": 5e-06,
      "loss": 0.6356,
      "step": 250
    },
    {
      "epoch": 1.3774834437086092,
      "grad_norm": 0.6219906931731467,
      "learning_rate": 5e-06,
      "loss": 0.6396,
      "step": 260
    },
    {
      "epoch": 1.4304635761589404,
      "grad_norm": 0.5539002206307158,
      "learning_rate": 5e-06,
      "loss": 0.6395,
      "step": 270
    },
    {
      "epoch": 1.4834437086092715,
      "grad_norm": 0.6706880554061717,
      "learning_rate": 5e-06,
      "loss": 0.6364,
      "step": 280
    },
    {
      "epoch": 1.5364238410596025,
      "grad_norm": 0.6250744115575335,
      "learning_rate": 5e-06,
      "loss": 0.6455,
      "step": 290
    },
    {
      "epoch": 1.589403973509934,
      "grad_norm": 0.5666575820633527,
      "learning_rate": 5e-06,
      "loss": 0.6352,
      "step": 300
    },
    {
      "epoch": 1.6423841059602649,
      "grad_norm": 0.8049891928557037,
      "learning_rate": 5e-06,
      "loss": 0.634,
      "step": 310
    },
    {
      "epoch": 1.695364238410596,
      "grad_norm": 0.8098028256502842,
      "learning_rate": 5e-06,
      "loss": 0.6379,
      "step": 320
    },
    {
      "epoch": 1.7483443708609272,
      "grad_norm": 0.6314929024368203,
      "learning_rate": 5e-06,
      "loss": 0.6394,
      "step": 330
    },
    {
      "epoch": 1.8013245033112582,
      "grad_norm": 0.824620474103318,
      "learning_rate": 5e-06,
      "loss": 0.6414,
      "step": 340
    },
    {
      "epoch": 1.8543046357615895,
      "grad_norm": 0.5854556799760776,
      "learning_rate": 5e-06,
      "loss": 0.6393,
      "step": 350
    },
    {
      "epoch": 1.9072847682119205,
      "grad_norm": 0.6825161397864904,
      "learning_rate": 5e-06,
      "loss": 0.6408,
      "step": 360
    },
    {
      "epoch": 1.9602649006622517,
      "grad_norm": 0.5897191051228083,
      "learning_rate": 5e-06,
      "loss": 0.6362,
      "step": 370
    },
    {
      "epoch": 1.9973509933774833,
      "eval_loss": 0.6881988644599915,
      "eval_runtime": 101.7242,
      "eval_samples_per_second": 50.008,
      "eval_steps_per_second": 0.393,
      "step": 377
    },
    {
      "epoch": 2.013245033112583,
      "grad_norm": 0.8098259238713678,
      "learning_rate": 5e-06,
      "loss": 0.6249,
      "step": 380
    },
    {
      "epoch": 2.066225165562914,
      "grad_norm": 0.8384706128552907,
      "learning_rate": 5e-06,
      "loss": 0.5796,
      "step": 390
    },
    {
      "epoch": 2.119205298013245,
      "grad_norm": 0.7877590869928718,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 400
    },
    {
      "epoch": 2.172185430463576,
      "grad_norm": 0.8214423131053483,
      "learning_rate": 5e-06,
      "loss": 0.5881,
      "step": 410
    },
    {
      "epoch": 2.225165562913907,
      "grad_norm": 0.708950143379715,
      "learning_rate": 5e-06,
      "loss": 0.5788,
      "step": 420
    },
    {
      "epoch": 2.2781456953642385,
      "grad_norm": 0.6491889315422662,
      "learning_rate": 5e-06,
      "loss": 0.5778,
      "step": 430
    },
    {
      "epoch": 2.3311258278145695,
      "grad_norm": 0.6858462236619034,
      "learning_rate": 5e-06,
      "loss": 0.5821,
      "step": 440
    },
    {
      "epoch": 2.384105960264901,
      "grad_norm": 0.780640823583864,
      "learning_rate": 5e-06,
      "loss": 0.5768,
      "step": 450
    },
    {
      "epoch": 2.437086092715232,
      "grad_norm": 0.7173053514977337,
      "learning_rate": 5e-06,
      "loss": 0.5759,
      "step": 460
    },
    {
      "epoch": 2.4900662251655628,
      "grad_norm": 0.7004632879605499,
      "learning_rate": 5e-06,
      "loss": 0.5787,
      "step": 470
    },
    {
      "epoch": 2.543046357615894,
      "grad_norm": 0.7028579263335615,
      "learning_rate": 5e-06,
      "loss": 0.579,
      "step": 480
    },
    {
      "epoch": 2.596026490066225,
      "grad_norm": 0.9012109929919548,
      "learning_rate": 5e-06,
      "loss": 0.5848,
      "step": 490
    },
    {
      "epoch": 2.6490066225165565,
      "grad_norm": 0.6237112161014274,
      "learning_rate": 5e-06,
      "loss": 0.584,
      "step": 500
    },
    {
      "epoch": 2.7019867549668874,
      "grad_norm": 0.6803732464125802,
      "learning_rate": 5e-06,
      "loss": 0.5918,
      "step": 510
    },
    {
      "epoch": 2.7549668874172184,
      "grad_norm": 0.7496234836165662,
      "learning_rate": 5e-06,
      "loss": 0.5797,
      "step": 520
    },
    {
      "epoch": 2.80794701986755,
      "grad_norm": 0.6761315878843943,
      "learning_rate": 5e-06,
      "loss": 0.5921,
      "step": 530
    },
    {
      "epoch": 2.8609271523178808,
      "grad_norm": 0.6002390896713952,
      "learning_rate": 5e-06,
      "loss": 0.5887,
      "step": 540
    },
    {
      "epoch": 2.9139072847682117,
      "grad_norm": 0.6064169883870584,
      "learning_rate": 5e-06,
      "loss": 0.5919,
      "step": 550
    },
    {
      "epoch": 2.966887417218543,
      "grad_norm": 0.5890652422466117,
      "learning_rate": 5e-06,
      "loss": 0.5826,
      "step": 560
    },
    {
      "epoch": 2.9880794701986755,
      "eval_loss": 0.6938396692276001,
      "eval_runtime": 102.1596,
      "eval_samples_per_second": 49.795,
      "eval_steps_per_second": 0.392,
      "step": 564
    },
    {
      "epoch": 2.9880794701986755,
      "step": 564,
      "total_flos": 944302247116800.0,
      "train_loss": 0.6565315867146702,
      "train_runtime": 17042.4484,
      "train_samples_per_second": 17.011,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 564,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 944302247116800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}