{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.688172043010753,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.053763440860215055,
      "grad_norm": 3.0181329250335693,
      "learning_rate": 3.6e-05,
      "loss": 0.6001,
      "step": 10
    },
    {
      "epoch": 0.10752688172043011,
      "grad_norm": 1.7442196607589722,
      "learning_rate": 7.6e-05,
      "loss": 0.2891,
      "step": 20
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 1.5924317836761475,
      "learning_rate": 9.998250366089848e-05,
      "loss": 0.2614,
      "step": 30
    },
    {
      "epoch": 0.21505376344086022,
      "grad_norm": 1.3713581562042236,
      "learning_rate": 9.97858104436822e-05,
      "loss": 0.2364,
      "step": 40
    },
    {
      "epoch": 0.26881720430107525,
      "grad_norm": 1.3055821657180786,
      "learning_rate": 9.937141654477528e-05,
      "loss": 0.1779,
      "step": 50
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.9266240000724792,
      "learning_rate": 9.87411340032603e-05,
      "loss": 0.1571,
      "step": 60
    },
    {
      "epoch": 0.3763440860215054,
      "grad_norm": 1.0376759767532349,
      "learning_rate": 9.789771888432375e-05,
      "loss": 0.137,
      "step": 70
    },
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 0.7397834062576294,
      "learning_rate": 9.684485922768422e-05,
      "loss": 0.1182,
      "step": 80
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 0.5904547572135925,
      "learning_rate": 9.558715892073323e-05,
      "loss": 0.1046,
      "step": 90
    },
    {
      "epoch": 0.5376344086021505,
      "grad_norm": 1.022401213645935,
      "learning_rate": 9.413011756690685e-05,
      "loss": 0.1056,
      "step": 100
    },
    {
      "epoch": 0.5913978494623656,
      "grad_norm": 0.7747468948364258,
      "learning_rate": 9.248010643731935e-05,
      "loss": 0.1006,
      "step": 110
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.8032405972480774,
      "learning_rate": 9.064434061081562e-05,
      "loss": 0.0902,
      "step": 120
    },
    {
      "epoch": 0.6989247311827957,
      "grad_norm": 0.6915440559387207,
      "learning_rate": 8.863084742426719e-05,
      "loss": 0.0861,
      "step": 130
    },
    {
      "epoch": 0.7526881720430108,
      "grad_norm": 0.7343285083770752,
      "learning_rate": 8.644843137107059e-05,
      "loss": 0.0873,
      "step": 140
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 0.6028986573219299,
      "learning_rate": 8.410663560133784e-05,
      "loss": 0.0831,
      "step": 150
    },
    {
      "epoch": 0.8602150537634409,
      "grad_norm": 0.5441303253173828,
      "learning_rate": 8.161570019212921e-05,
      "loss": 0.0772,
      "step": 160
    },
    {
      "epoch": 0.9139784946236559,
      "grad_norm": 0.5184003114700317,
      "learning_rate": 7.898651737020166e-05,
      "loss": 0.0739,
      "step": 170
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 0.38568446040153503,
      "learning_rate": 7.623058388307269e-05,
      "loss": 0.0729,
      "step": 180
    },
    {
      "epoch": 1.021505376344086,
      "grad_norm": 0.5226582288742065,
      "learning_rate": 7.335995072666848e-05,
      "loss": 0.0733,
      "step": 190
    },
    {
      "epoch": 1.075268817204301,
      "grad_norm": 0.6022420525550842,
      "learning_rate": 7.038717044938519e-05,
      "loss": 0.0773,
      "step": 200
    },
    {
      "epoch": 1.129032258064516,
      "grad_norm": 0.6212151646614075,
      "learning_rate": 6.732524226298841e-05,
      "loss": 0.0684,
      "step": 210
    },
    {
      "epoch": 1.1827956989247312,
      "grad_norm": 0.5427640080451965,
      "learning_rate": 6.418755520036775e-05,
      "loss": 0.0678,
      "step": 220
    },
    {
      "epoch": 1.2365591397849462,
      "grad_norm": 0.6625052690505981,
      "learning_rate": 6.0987829568702656e-05,
      "loss": 0.073,
      "step": 230
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.37876975536346436,
      "learning_rate": 5.7740056954050084e-05,
      "loss": 0.0684,
      "step": 240
    },
    {
      "epoch": 1.3440860215053765,
      "grad_norm": 0.3789575397968292,
      "learning_rate": 5.445843903969854e-05,
      "loss": 0.0573,
      "step": 250
    },
    {
      "epoch": 1.3978494623655915,
      "grad_norm": 0.380149245262146,
      "learning_rate": 5.1157325505820694e-05,
      "loss": 0.0618,
      "step": 260
    },
    {
      "epoch": 1.4516129032258065,
      "grad_norm": 0.4945651888847351,
      "learning_rate": 4.785115128197298e-05,
      "loss": 0.0632,
      "step": 270
    },
    {
      "epoch": 1.5053763440860215,
      "grad_norm": 0.47128596901893616,
      "learning_rate": 4.4554373426821374e-05,
      "loss": 0.0619,
      "step": 280
    },
    {
      "epoch": 1.5591397849462365,
      "grad_norm": 0.3431663513183594,
      "learning_rate": 4.1281407911102425e-05,
      "loss": 0.0605,
      "step": 290
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 0.3071378171443939,
      "learning_rate": 3.8046566580251e-05,
      "loss": 0.0539,
      "step": 300
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.25178495049476624,
      "learning_rate": 3.4863994572341843e-05,
      "loss": 0.0547,
      "step": 310
    },
    {
      "epoch": 1.7204301075268817,
      "grad_norm": 0.3284253478050232,
      "learning_rate": 3.1747608464999725e-05,
      "loss": 0.0558,
      "step": 320
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 0.40466904640197754,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 0.0519,
      "step": 330
    },
    {
      "epoch": 1.827956989247312,
      "grad_norm": 0.3861023485660553,
      "learning_rate": 2.5767553603881767e-05,
      "loss": 0.0534,
      "step": 340
    },
    {
      "epoch": 1.881720430107527,
      "grad_norm": 0.4377838671207428,
      "learning_rate": 2.29300341084631e-05,
      "loss": 0.0507,
      "step": 350
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 0.3389015197753906,
      "learning_rate": 2.0210884686272368e-05,
      "loss": 0.0533,
      "step": 360
    },
    {
      "epoch": 1.989247311827957,
      "grad_norm": 0.2521311938762665,
      "learning_rate": 1.7621995485879062e-05,
      "loss": 0.0536,
      "step": 370
    },
    {
      "epoch": 2.043010752688172,
      "grad_norm": 0.30193665623664856,
      "learning_rate": 1.517468706104589e-05,
      "loss": 0.0562,
      "step": 380
    },
    {
      "epoch": 2.096774193548387,
      "grad_norm": 0.3276124596595764,
      "learning_rate": 1.2879660868827508e-05,
      "loss": 0.0497,
      "step": 390
    },
    {
      "epoch": 2.150537634408602,
      "grad_norm": 0.2738921642303467,
      "learning_rate": 1.0746952474821614e-05,
      "loss": 0.0505,
      "step": 400
    },
    {
      "epoch": 2.204301075268817,
      "grad_norm": 0.23493026196956635,
      "learning_rate": 8.785887670194138e-06,
      "loss": 0.05,
      "step": 410
    },
    {
      "epoch": 2.258064516129032,
      "grad_norm": 0.27332600951194763,
      "learning_rate": 7.005041692367154e-06,
      "loss": 0.0478,
      "step": 420
    },
    {
      "epoch": 2.3118279569892475,
      "grad_norm": 0.23733267188072205,
      "learning_rate": 5.412201727687644e-06,
      "loss": 0.0485,
      "step": 430
    },
    {
      "epoch": 2.3655913978494625,
      "grad_norm": 0.3148542046546936,
      "learning_rate": 4.01433286004283e-06,
      "loss": 0.0486,
      "step": 440
    },
    {
      "epoch": 2.4193548387096775,
      "grad_norm": 0.17621102929115295,
      "learning_rate": 2.817547614320615e-06,
      "loss": 0.0459,
      "step": 450
    },
    {
      "epoch": 2.4731182795698925,
      "grad_norm": 0.3627742528915405,
      "learning_rate": 1.8270792278934302e-06,
      "loss": 0.0447,
      "step": 460
    },
    {
      "epoch": 2.5268817204301075,
      "grad_norm": 0.2204674929380417,
      "learning_rate": 1.0472587670027678e-06,
      "loss": 0.0432,
      "step": 470
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 0.2851138114929199,
      "learning_rate": 4.814961881085045e-07,
      "loss": 0.049,
      "step": 480
    },
    {
      "epoch": 2.6344086021505375,
      "grad_norm": 0.22748719155788422,
      "learning_rate": 1.3226542701689215e-07,
      "loss": 0.0452,
      "step": 490
    },
    {
      "epoch": 2.688172043010753,
      "grad_norm": 0.29575690627098083,
      "learning_rate": 1.0935809887702154e-09,
      "loss": 0.0484,
      "step": 500
    },
    {
      "epoch": 2.688172043010753,
      "step": 500,
      "total_flos": 0.0,
      "train_loss": 0.09292892861366273,
      "train_runtime": 1122.3185,
      "train_samples_per_second": 42.769,
      "train_steps_per_second": 0.446
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}