{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9880159786950733,
  "eval_steps": 500,
  "global_step": 561,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05326231691078562,
      "grad_norm": 10.043872386995645,
      "learning_rate": 5e-06,
      "loss": 0.9027,
      "step": 10
    },
    {
      "epoch": 0.10652463382157124,
      "grad_norm": 3.5873792834266096,
      "learning_rate": 5e-06,
      "loss": 0.812,
      "step": 20
    },
    {
      "epoch": 0.15978695073235685,
      "grad_norm": 1.6541921693779105,
      "learning_rate": 5e-06,
      "loss": 0.7822,
      "step": 30
    },
    {
      "epoch": 0.21304926764314247,
      "grad_norm": 2.9676058520395694,
      "learning_rate": 5e-06,
      "loss": 0.7606,
      "step": 40
    },
    {
      "epoch": 0.2663115845539281,
      "grad_norm": 1.2283778691151885,
      "learning_rate": 5e-06,
      "loss": 0.7332,
      "step": 50
    },
    {
      "epoch": 0.3195739014647137,
      "grad_norm": 1.5118726910174631,
      "learning_rate": 5e-06,
      "loss": 0.7221,
      "step": 60
    },
    {
      "epoch": 0.37283621837549935,
      "grad_norm": 1.4995166965541817,
      "learning_rate": 5e-06,
      "loss": 0.7165,
      "step": 70
    },
    {
      "epoch": 0.42609853528628494,
      "grad_norm": 1.1573105641307837,
      "learning_rate": 5e-06,
      "loss": 0.708,
      "step": 80
    },
    {
      "epoch": 0.4793608521970706,
      "grad_norm": 0.6329039589127555,
      "learning_rate": 5e-06,
      "loss": 0.6902,
      "step": 90
    },
    {
      "epoch": 0.5326231691078562,
      "grad_norm": 0.6967482378462392,
      "learning_rate": 5e-06,
      "loss": 0.6936,
      "step": 100
    },
    {
      "epoch": 0.5858854860186418,
      "grad_norm": 1.0258384410770847,
      "learning_rate": 5e-06,
      "loss": 0.6849,
      "step": 110
    },
    {
      "epoch": 0.6391478029294274,
      "grad_norm": 0.6790507748606548,
      "learning_rate": 5e-06,
      "loss": 0.6991,
      "step": 120
    },
    {
      "epoch": 0.6924101198402131,
      "grad_norm": 0.6426377105957765,
      "learning_rate": 5e-06,
      "loss": 0.6802,
      "step": 130
    },
    {
      "epoch": 0.7456724367509987,
      "grad_norm": 1.2825548485478584,
      "learning_rate": 5e-06,
      "loss": 0.6927,
      "step": 140
    },
    {
      "epoch": 0.7989347536617842,
      "grad_norm": 1.2061088462661143,
      "learning_rate": 5e-06,
      "loss": 0.6811,
      "step": 150
    },
    {
      "epoch": 0.8521970705725699,
      "grad_norm": 0.6711727236495032,
      "learning_rate": 5e-06,
      "loss": 0.6874,
      "step": 160
    },
    {
      "epoch": 0.9054593874833555,
      "grad_norm": 0.5700786999189973,
      "learning_rate": 5e-06,
      "loss": 0.689,
      "step": 170
    },
    {
      "epoch": 0.9587217043941412,
      "grad_norm": 0.6424611481692418,
      "learning_rate": 5e-06,
      "loss": 0.6759,
      "step": 180
    },
    {
      "epoch": 0.996005326231691,
      "eval_loss": 0.6789066195487976,
      "eval_runtime": 66.7611,
      "eval_samples_per_second": 75.763,
      "eval_steps_per_second": 0.599,
      "step": 187
    },
    {
      "epoch": 1.0119840213049267,
      "grad_norm": 0.7982749587499836,
      "learning_rate": 5e-06,
      "loss": 0.6589,
      "step": 190
    },
    {
      "epoch": 1.0652463382157125,
      "grad_norm": 0.7591350142806961,
      "learning_rate": 5e-06,
      "loss": 0.6137,
      "step": 200
    },
    {
      "epoch": 1.118508655126498,
      "grad_norm": 0.7399944259795829,
      "learning_rate": 5e-06,
      "loss": 0.6147,
      "step": 210
    },
    {
      "epoch": 1.1717709720372835,
      "grad_norm": 0.7128707470380614,
      "learning_rate": 5e-06,
      "loss": 0.6169,
      "step": 220
    },
    {
      "epoch": 1.2250332889480693,
      "grad_norm": 0.6390434495921663,
      "learning_rate": 5e-06,
      "loss": 0.6171,
      "step": 230
    },
    {
      "epoch": 1.2782956058588548,
      "grad_norm": 0.6835653985742169,
      "learning_rate": 5e-06,
      "loss": 0.6168,
      "step": 240
    },
    {
      "epoch": 1.3315579227696404,
      "grad_norm": 0.7382391212184931,
      "learning_rate": 5e-06,
      "loss": 0.6265,
      "step": 250
    },
    {
      "epoch": 1.3848202396804261,
      "grad_norm": 0.5665114450124694,
      "learning_rate": 5e-06,
      "loss": 0.6193,
      "step": 260
    },
    {
      "epoch": 1.4380825565912116,
      "grad_norm": 0.5296907389070354,
      "learning_rate": 5e-06,
      "loss": 0.622,
      "step": 270
    },
    {
      "epoch": 1.4913448735019974,
      "grad_norm": 0.546717125266996,
      "learning_rate": 5e-06,
      "loss": 0.6239,
      "step": 280
    },
    {
      "epoch": 1.544607190412783,
      "grad_norm": 0.6531122146180807,
      "learning_rate": 5e-06,
      "loss": 0.6211,
      "step": 290
    },
    {
      "epoch": 1.5978695073235687,
      "grad_norm": 0.5744613077225782,
      "learning_rate": 5e-06,
      "loss": 0.6193,
      "step": 300
    },
    {
      "epoch": 1.6511318242343542,
      "grad_norm": 0.6725000329350213,
      "learning_rate": 5e-06,
      "loss": 0.6157,
      "step": 310
    },
    {
      "epoch": 1.7043941411451398,
      "grad_norm": 0.5467410656311016,
      "learning_rate": 5e-06,
      "loss": 0.6153,
      "step": 320
    },
    {
      "epoch": 1.7576564580559255,
      "grad_norm": 0.6575779238804216,
      "learning_rate": 5e-06,
      "loss": 0.6183,
      "step": 330
    },
    {
      "epoch": 1.810918774966711,
      "grad_norm": 0.6389106370178078,
      "learning_rate": 5e-06,
      "loss": 0.6213,
      "step": 340
    },
    {
      "epoch": 1.8641810918774966,
      "grad_norm": 0.5812488086714392,
      "learning_rate": 5e-06,
      "loss": 0.616,
      "step": 350
    },
    {
      "epoch": 1.9174434087882823,
      "grad_norm": 0.662384247335092,
      "learning_rate": 5e-06,
      "loss": 0.6046,
      "step": 360
    },
    {
      "epoch": 1.9707057256990679,
      "grad_norm": 0.5577067863493724,
      "learning_rate": 5e-06,
      "loss": 0.6133,
      "step": 370
    },
    {
      "epoch": 1.9973368841544608,
      "eval_loss": 0.672442615032196,
      "eval_runtime": 66.0876,
      "eval_samples_per_second": 76.535,
      "eval_steps_per_second": 0.605,
      "step": 375
    },
    {
      "epoch": 2.0239680426098534,
      "grad_norm": 0.914487856356494,
      "learning_rate": 5e-06,
      "loss": 0.5838,
      "step": 380
    },
    {
      "epoch": 2.077230359520639,
      "grad_norm": 1.0411320535838575,
      "learning_rate": 5e-06,
      "loss": 0.5542,
      "step": 390
    },
    {
      "epoch": 2.130492676431425,
      "grad_norm": 0.7322670502543674,
      "learning_rate": 5e-06,
      "loss": 0.5535,
      "step": 400
    },
    {
      "epoch": 2.1837549933422102,
      "grad_norm": 0.6759246932223949,
      "learning_rate": 5e-06,
      "loss": 0.5567,
      "step": 410
    },
    {
      "epoch": 2.237017310252996,
      "grad_norm": 0.6733943048111352,
      "learning_rate": 5e-06,
      "loss": 0.5531,
      "step": 420
    },
    {
      "epoch": 2.2902796271637818,
      "grad_norm": 0.5804880093973978,
      "learning_rate": 5e-06,
      "loss": 0.5543,
      "step": 430
    },
    {
      "epoch": 2.343541944074567,
      "grad_norm": 0.6550606815593909,
      "learning_rate": 5e-06,
      "loss": 0.5548,
      "step": 440
    },
    {
      "epoch": 2.396804260985353,
      "grad_norm": 0.7005642588379877,
      "learning_rate": 5e-06,
      "loss": 0.56,
      "step": 450
    },
    {
      "epoch": 2.4500665778961386,
      "grad_norm": 0.6514987724499162,
      "learning_rate": 5e-06,
      "loss": 0.5553,
      "step": 460
    },
    {
      "epoch": 2.5033288948069243,
      "grad_norm": 0.598180037970062,
      "learning_rate": 5e-06,
      "loss": 0.5552,
      "step": 470
    },
    {
      "epoch": 2.5565912117177096,
      "grad_norm": 0.6716187874030446,
      "learning_rate": 5e-06,
      "loss": 0.5629,
      "step": 480
    },
    {
      "epoch": 2.6098535286284954,
      "grad_norm": 0.6417933456363174,
      "learning_rate": 5e-06,
      "loss": 0.5632,
      "step": 490
    },
    {
      "epoch": 2.6631158455392807,
      "grad_norm": 0.5930259103461313,
      "learning_rate": 5e-06,
      "loss": 0.5608,
      "step": 500
    },
    {
      "epoch": 2.7163781624500665,
      "grad_norm": 0.5696407448709899,
      "learning_rate": 5e-06,
      "loss": 0.5576,
      "step": 510
    },
    {
      "epoch": 2.7696404793608522,
      "grad_norm": 0.6956493623428277,
      "learning_rate": 5e-06,
      "loss": 0.5514,
      "step": 520
    },
    {
      "epoch": 2.822902796271638,
      "grad_norm": 0.5861405184973314,
      "learning_rate": 5e-06,
      "loss": 0.5556,
      "step": 530
    },
    {
      "epoch": 2.8761651131824233,
      "grad_norm": 0.7349516316012534,
      "learning_rate": 5e-06,
      "loss": 0.5602,
      "step": 540
    },
    {
      "epoch": 2.929427430093209,
      "grad_norm": 0.7210951093860754,
      "learning_rate": 5e-06,
      "loss": 0.558,
      "step": 550
    },
    {
      "epoch": 2.982689747003995,
      "grad_norm": 0.6051360012000235,
      "learning_rate": 5e-06,
      "loss": 0.5585,
      "step": 560
    },
    {
      "epoch": 2.9880159786950733,
      "eval_loss": 0.6807268261909485,
      "eval_runtime": 63.8046,
      "eval_samples_per_second": 79.273,
      "eval_steps_per_second": 0.627,
      "step": 561
    },
    {
      "epoch": 2.9880159786950733,
      "step": 561,
      "total_flos": 939277135380480.0,
      "train_loss": 0.6320187783071276,
      "train_runtime": 9641.2734,
      "train_samples_per_second": 29.899,
      "train_steps_per_second": 0.058
    }
  ],
  "logging_steps": 10,
  "max_steps": 561,
  "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": 939277135380480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}