{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.979591836734694,
  "eval_steps": 500,
  "global_step": 438,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 28.75,
      "learning_rate": 1.2405214087609793e-05,
      "loss": 3.4643,
      "step": 5
    },
    {
      "epoch": 0.06802721088435375,
      "grad_norm": 38.25,
      "learning_rate": 2.791173169712203e-05,
      "loss": 4.2336,
      "step": 10
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 32.0,
      "learning_rate": 4.341824930663428e-05,
      "loss": 2.0587,
      "step": 15
    },
    {
      "epoch": 0.1360544217687075,
      "grad_norm": 0.84765625,
      "learning_rate": 5.8924766916146515e-05,
      "loss": 1.0773,
      "step": 20
    },
    {
      "epoch": 0.17006802721088435,
      "grad_norm": 42.75,
      "learning_rate": 7.443128452565876e-05,
      "loss": 0.6339,
      "step": 25
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.1826171875,
      "learning_rate": 8.9937802135171e-05,
      "loss": 0.3862,
      "step": 30
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 72.5,
      "learning_rate": 0.00010544431974468325,
      "loss": 2.4785,
      "step": 35
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 35.75,
      "learning_rate": 0.0001085248274824069,
      "loss": 1.4148,
      "step": 40
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 74.5,
      "learning_rate": 0.0001084403787497468,
      "loss": 0.8793,
      "step": 45
    },
    {
      "epoch": 0.3401360544217687,
      "grad_norm": 35.5,
      "learning_rate": 0.00010829110362886751,
      "loss": 0.4985,
      "step": 50
    },
    {
      "epoch": 0.3741496598639456,
      "grad_norm": 2.328125,
      "learning_rate": 0.00010807722553920126,
      "loss": 0.382,
      "step": 55
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 17.5,
      "learning_rate": 0.00010779906459116616,
      "loss": 0.6253,
      "step": 60
    },
    {
      "epoch": 0.4421768707482993,
      "grad_norm": 16.375,
      "learning_rate": 0.00010745703710705828,
      "loss": 0.3236,
      "step": 65
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 55.75,
      "learning_rate": 0.00010705165499794393,
      "loss": 0.3981,
      "step": 70
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 25.625,
      "learning_rate": 0.00010658352499748452,
      "loss": 0.6889,
      "step": 75
    },
    {
      "epoch": 0.54421768707483,
      "grad_norm": 235.0,
      "learning_rate": 0.00010605334775384088,
      "loss": 1.3471,
      "step": 80
    },
    {
      "epoch": 0.5782312925170068,
      "grad_norm": 6.34375,
      "learning_rate": 0.00010546191678101621,
      "loss": 0.7067,
      "step": 85
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 33.0,
      "learning_rate": 0.00010481011727120708,
      "loss": 0.2755,
      "step": 90
    },
    {
      "epoch": 0.6462585034013606,
      "grad_norm": 29.875,
      "learning_rate": 0.00010409892476994003,
      "loss": 0.376,
      "step": 95
    },
    {
      "epoch": 0.6802721088435374,
      "grad_norm": 20.5,
      "learning_rate": 0.0001033294037159768,
      "loss": 0.5199,
      "step": 100
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 9.0625,
      "learning_rate": 0.00010250270584817341,
      "loss": 0.4744,
      "step": 105
    },
    {
      "epoch": 0.7482993197278912,
      "grad_norm": 49.25,
      "learning_rate": 0.0001016200684816775,
      "loss": 0.3467,
      "step": 110
    },
    {
      "epoch": 0.782312925170068,
      "grad_norm": 54.75,
      "learning_rate": 0.00010068281265604425,
      "loss": 0.4323,
      "step": 115
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 25.75,
      "learning_rate": 9.969234115804185e-05,
      "loss": 0.5117,
      "step": 120
    },
    {
      "epoch": 0.8503401360544217,
      "grad_norm": 27.375,
      "learning_rate": 9.865013642210685e-05,
      "loss": 0.3461,
      "step": 125
    },
    {
      "epoch": 0.8843537414965986,
      "grad_norm": 27.0,
      "learning_rate": 9.755775831159075e-05,
      "loss": 0.3838,
      "step": 130
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 22.0,
      "learning_rate": 9.641684178411933e-05,
      "loss": 0.3031,
      "step": 135
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 15.25,
      "learning_rate": 9.522909444455842e-05,
      "loss": 0.4872,
      "step": 140
    },
    {
      "epoch": 0.9863945578231292,
      "grad_norm": 8.375,
      "learning_rate": 9.399629398924927e-05,
      "loss": 0.2626,
      "step": 145
    },
    {
      "epoch": 0.9931972789115646,
      "eval_loss": 0.21089103817939758,
      "eval_runtime": 1.2585,
      "eval_samples_per_second": 20.66,
      "eval_steps_per_second": 20.66,
      "step": 146
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": 23.75,
      "learning_rate": 9.272028554533782e-05,
      "loss": 0.1617,
      "step": 150
    },
    {
      "epoch": 1.054421768707483,
      "grad_norm": 3.421875,
      "learning_rate": 9.140297890918105e-05,
      "loss": 0.2647,
      "step": 155
    },
    {
      "epoch": 1.08843537414966,
      "grad_norm": 7.5625,
      "learning_rate": 9.004634568796285e-05,
      "loss": 0.4115,
      "step": 160
    },
    {
      "epoch": 1.1224489795918366,
      "grad_norm": 14.1875,
      "learning_rate": 8.865241634879804e-05,
      "loss": 0.2492,
      "step": 165
    },
    {
      "epoch": 1.1564625850340136,
      "grad_norm": 9.1875,
      "learning_rate": 8.722327717974095e-05,
      "loss": 0.3327,
      "step": 170
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 9.4375,
      "learning_rate": 8.57610671672471e-05,
      "loss": 0.4109,
      "step": 175
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": 20.25,
      "learning_rate": 8.426797479476129e-05,
      "loss": 0.4426,
      "step": 180
    },
    {
      "epoch": 1.2585034013605443,
      "grad_norm": 66.0,
      "learning_rate": 8.27462347672239e-05,
      "loss": 0.3577,
      "step": 185
    },
    {
      "epoch": 1.2925170068027212,
      "grad_norm": 4.75,
      "learning_rate": 8.119812466639757e-05,
      "loss": 0.201,
      "step": 190
    },
    {
      "epoch": 1.3265306122448979,
      "grad_norm": 5.84375,
      "learning_rate": 7.962596154202029e-05,
      "loss": 0.1453,
      "step": 195
    },
    {
      "epoch": 1.3605442176870748,
      "grad_norm": 8.4375,
      "learning_rate": 7.80320984438872e-05,
      "loss": 0.072,
      "step": 200
    },
    {
      "epoch": 1.3945578231292517,
      "grad_norm": 10.75,
      "learning_rate": 7.641892090005088e-05,
      "loss": 0.0673,
      "step": 205
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 20.5,
      "learning_rate": 7.478884334641178e-05,
      "loss": 0.2137,
      "step": 210
    },
    {
      "epoch": 1.4625850340136055,
      "grad_norm": 13.875,
      "learning_rate": 7.314430551304253e-05,
      "loss": 0.1786,
      "step": 215
    },
    {
      "epoch": 1.4965986394557822,
      "grad_norm": 7.65625,
      "learning_rate": 7.148776877265426e-05,
      "loss": 0.0821,
      "step": 220
    },
    {
      "epoch": 1.5306122448979593,
      "grad_norm": 16.25,
      "learning_rate": 6.982171245667071e-05,
      "loss": 0.1904,
      "step": 225
    },
    {
      "epoch": 1.564625850340136,
      "grad_norm": 4.46875,
      "learning_rate": 6.81486301444235e-05,
      "loss": 0.0449,
      "step": 230
    },
    {
      "epoch": 1.598639455782313,
      "grad_norm": 14.5625,
      "learning_rate": 6.64710259310227e-05,
      "loss": 0.1493,
      "step": 235
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": 25.75,
      "learning_rate": 6.479141067948843e-05,
      "loss": 0.1877,
      "step": 240
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 12.75,
      "learning_rate": 6.311229826275292e-05,
      "loss": 0.1844,
      "step": 245
    },
    {
      "epoch": 1.7006802721088436,
      "grad_norm": 13.5,
      "learning_rate": 6.143620180115768e-05,
      "loss": 0.2923,
      "step": 250
    },
    {
      "epoch": 1.7346938775510203,
      "grad_norm": 2.15625,
      "learning_rate": 5.9765629901077215e-05,
      "loss": 0.059,
      "step": 255
    },
    {
      "epoch": 1.7687074829931972,
      "grad_norm": 0.26953125,
      "learning_rate": 5.8103082900298425e-05,
      "loss": 0.0561,
      "step": 260
    },
    {
      "epoch": 1.8027210884353742,
      "grad_norm": 8.875,
      "learning_rate": 5.645104912577601e-05,
      "loss": 0.1103,
      "step": 265
    },
    {
      "epoch": 1.836734693877551,
      "grad_norm": 8.4375,
      "learning_rate": 5.481200116936402e-05,
      "loss": 0.1003,
      "step": 270
    },
    {
      "epoch": 1.870748299319728,
      "grad_norm": 6.0,
      "learning_rate": 5.31883921870983e-05,
      "loss": 0.0788,
      "step": 275
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 1.6171875,
      "learning_rate": 5.158265222756847e-05,
      "loss": 0.0819,
      "step": 280
    },
    {
      "epoch": 1.9387755102040818,
      "grad_norm": 14.1875,
      "learning_rate": 4.999718459487458e-05,
      "loss": 0.0352,
      "step": 285
    },
    {
      "epoch": 1.9727891156462585,
      "grad_norm": 0.60546875,
      "learning_rate": 4.843436225161211e-05,
      "loss": 0.1354,
      "step": 290
    },
    {
      "epoch": 1.9863945578231292,
      "eval_loss": 0.17950406670570374,
      "eval_runtime": 1.156,
      "eval_samples_per_second": 22.491,
      "eval_steps_per_second": 22.491,
      "step": 292
    },
    {
      "epoch": 2.006802721088435,
      "grad_norm": 1.0703125,
      "learning_rate": 4.689652426726917e-05,
      "loss": 0.0795,
      "step": 295
    },
    {
      "epoch": 2.0408163265306123,
      "grad_norm": 0.0264892578125,
      "learning_rate": 4.5385972317351206e-05,
      "loss": 0.1034,
      "step": 300
    },
    {
      "epoch": 2.074829931972789,
      "grad_norm": 0.060791015625,
      "learning_rate": 4.3904967238473124e-05,
      "loss": 0.0467,
      "step": 305
    },
    {
      "epoch": 2.108843537414966,
      "grad_norm": 4.5625,
      "learning_rate": 4.2455725644574884e-05,
      "loss": 0.0525,
      "step": 310
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.08984375,
      "learning_rate": 4.1040416609324844e-05,
      "loss": 0.0122,
      "step": 315
    },
    {
      "epoch": 2.17687074829932,
      "grad_norm": 17.25,
      "learning_rate": 3.966115841967671e-05,
      "loss": 0.1311,
      "step": 320
    },
    {
      "epoch": 2.2108843537414966,
      "grad_norm": 3.390625,
      "learning_rate": 3.832001540543833e-05,
      "loss": 0.1173,
      "step": 325
    },
    {
      "epoch": 2.2448979591836733,
      "grad_norm": 4.59375,
      "learning_rate": 3.701899484959829e-05,
      "loss": 0.0816,
      "step": 330
    },
    {
      "epoch": 2.2789115646258504,
      "grad_norm": 0.06591796875,
      "learning_rate": 3.5760043984034015e-05,
      "loss": 0.0235,
      "step": 335
    },
    {
      "epoch": 2.312925170068027,
      "grad_norm": 12.375,
      "learning_rate": 3.454504707509821e-05,
      "loss": 0.0807,
      "step": 340
    },
    {
      "epoch": 2.3469387755102042,
      "grad_norm": 0.016357421875,
      "learning_rate": 3.337582260344549e-05,
      "loss": 0.0603,
      "step": 345
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.06884765625,
      "learning_rate": 3.225412054232022e-05,
      "loss": 0.0107,
      "step": 350
    },
    {
      "epoch": 2.4149659863945576,
      "grad_norm": 0.07080078125,
      "learning_rate": 3.118161973837903e-05,
      "loss": 0.003,
      "step": 355
    },
    {
      "epoch": 2.4489795918367347,
      "grad_norm": 0.55078125,
      "learning_rate": 3.0159925398968314e-05,
      "loss": 0.0248,
      "step": 360
    },
    {
      "epoch": 2.4829931972789114,
      "grad_norm": 1.015625,
      "learning_rate": 2.9190566689617188e-05,
      "loss": 0.0651,
      "step": 365
    },
    {
      "epoch": 2.5170068027210886,
      "grad_norm": 0.0218505859375,
      "learning_rate": 2.8274994445342093e-05,
      "loss": 0.0021,
      "step": 370
    },
    {
      "epoch": 2.5510204081632653,
      "grad_norm": 0.037353515625,
      "learning_rate": 2.741457899918822e-05,
      "loss": 0.0111,
      "step": 375
    },
    {
      "epoch": 2.5850340136054424,
      "grad_norm": 54.75,
      "learning_rate": 2.6610608131257937e-05,
      "loss": 0.0358,
      "step": 380
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.078125,
      "learning_rate": 2.5864285141295854e-05,
      "loss": 0.0004,
      "step": 385
    },
    {
      "epoch": 2.6530612244897958,
      "grad_norm": 0.005767822265625,
      "learning_rate": 2.517672704771522e-05,
      "loss": 0.0003,
      "step": 390
    },
    {
      "epoch": 2.687074829931973,
      "grad_norm": 2.015625,
      "learning_rate": 2.4548962915761334e-05,
      "loss": 0.0006,
      "step": 395
    },
    {
      "epoch": 2.7210884353741496,
      "grad_norm": 13.875,
      "learning_rate": 2.3981932317313933e-05,
      "loss": 0.0117,
      "step": 400
    },
    {
      "epoch": 2.7551020408163263,
      "grad_norm": 0.2216796875,
      "learning_rate": 2.347648392463406e-05,
      "loss": 0.0074,
      "step": 405
    },
    {
      "epoch": 2.7891156462585034,
      "grad_norm": 11.4375,
      "learning_rate": 2.303337424015989e-05,
      "loss": 0.0291,
      "step": 410
    },
    {
      "epoch": 2.8231292517006805,
      "grad_norm": 18.0,
      "learning_rate": 2.2653266464252818e-05,
      "loss": 0.0245,
      "step": 415
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 7.25,
      "learning_rate": 2.2336729502588305e-05,
      "loss": 0.0082,
      "step": 420
    },
    {
      "epoch": 2.891156462585034,
      "grad_norm": 0.09716796875,
      "learning_rate": 2.2084237114677194e-05,
      "loss": 0.0224,
      "step": 425
    },
    {
      "epoch": 2.925170068027211,
      "grad_norm": 0.012451171875,
      "learning_rate": 2.18961672047919e-05,
      "loss": 0.0002,
      "step": 430
    },
    {
      "epoch": 2.9591836734693877,
      "grad_norm": 0.0341796875,
      "learning_rate": 2.1772801256358705e-05,
      "loss": 0.0299,
      "step": 435
    },
    {
      "epoch": 2.979591836734694,
      "eval_loss": 0.00994242262095213,
      "eval_runtime": 1.1603,
      "eval_samples_per_second": 22.408,
      "eval_steps_per_second": 22.408,
      "step": 438
    }
  ],
  "logging_steps": 5,
  "max_steps": 441,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.330567101743104e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}