{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 50,
  "global_step": 685,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.072992700729927,
      "grad_norm": 1.2194373607635498,
      "learning_rate": 5.000000000000001e-07,
      "loss": 3.5968,
      "step": 10
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 1.1968055963516235,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.6726,
      "step": 20
    },
    {
      "epoch": 0.21897810218978103,
      "grad_norm": 1.1814980506896973,
      "learning_rate": 1.5e-06,
      "loss": 3.5953,
      "step": 30
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 1.1611206531524658,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.5831,
      "step": 40
    },
    {
      "epoch": 0.36496350364963503,
      "grad_norm": 1.0345042943954468,
      "learning_rate": 2.5e-06,
      "loss": 3.6277,
      "step": 50
    },
    {
      "epoch": 0.36496350364963503,
      "eval_loss": 3.6583080291748047,
      "eval_runtime": 4.5719,
      "eval_samples_per_second": 106.74,
      "eval_steps_per_second": 13.342,
      "step": 50
    },
    {
      "epoch": 0.43795620437956206,
      "grad_norm": 1.1489139795303345,
      "learning_rate": 3e-06,
      "loss": 3.5835,
      "step": 60
    },
    {
      "epoch": 0.5109489051094891,
      "grad_norm": 1.3421690464019775,
      "learning_rate": 3.5e-06,
      "loss": 3.5992,
      "step": 70
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 1.0778014659881592,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.5575,
      "step": 80
    },
    {
      "epoch": 0.656934306569343,
      "grad_norm": 0.9279437065124512,
      "learning_rate": 4.5e-06,
      "loss": 3.6968,
      "step": 90
    },
    {
      "epoch": 0.7299270072992701,
      "grad_norm": 0.8781314492225647,
      "learning_rate": 5e-06,
      "loss": 3.5835,
      "step": 100
    },
    {
      "epoch": 0.7299270072992701,
      "eval_loss": 3.6277682781219482,
      "eval_runtime": 4.5628,
      "eval_samples_per_second": 106.953,
      "eval_steps_per_second": 13.369,
      "step": 100
    },
    {
      "epoch": 0.8029197080291971,
      "grad_norm": 1.237952709197998,
      "learning_rate": 5.500000000000001e-06,
      "loss": 3.6226,
      "step": 110
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 1.1926833391189575,
      "learning_rate": 6e-06,
      "loss": 3.6014,
      "step": 120
    },
    {
      "epoch": 0.948905109489051,
      "grad_norm": 0.8673391938209534,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 3.6303,
      "step": 130
    },
    {
      "epoch": 1.0218978102189782,
      "grad_norm": 1.0185987949371338,
      "learning_rate": 7e-06,
      "loss": 3.5962,
      "step": 140
    },
    {
      "epoch": 1.094890510948905,
      "grad_norm": 0.8746767044067383,
      "learning_rate": 7.500000000000001e-06,
      "loss": 3.5365,
      "step": 150
    },
    {
      "epoch": 1.094890510948905,
      "eval_loss": 3.578197956085205,
      "eval_runtime": 4.5695,
      "eval_samples_per_second": 106.796,
      "eval_steps_per_second": 13.349,
      "step": 150
    },
    {
      "epoch": 1.167883211678832,
      "grad_norm": 0.9256734848022461,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.5504,
      "step": 160
    },
    {
      "epoch": 1.2408759124087592,
      "grad_norm": 0.7662177681922913,
      "learning_rate": 8.5e-06,
      "loss": 3.5484,
      "step": 170
    },
    {
      "epoch": 1.313868613138686,
      "grad_norm": 0.7936022877693176,
      "learning_rate": 9e-06,
      "loss": 3.547,
      "step": 180
    },
    {
      "epoch": 1.3868613138686132,
      "grad_norm": 0.9237962961196899,
      "learning_rate": 9.5e-06,
      "loss": 3.5648,
      "step": 190
    },
    {
      "epoch": 1.4598540145985401,
      "grad_norm": 0.7705855369567871,
      "learning_rate": 1e-05,
      "loss": 3.4902,
      "step": 200
    },
    {
      "epoch": 1.4598540145985401,
      "eval_loss": 3.515073299407959,
      "eval_runtime": 4.5781,
      "eval_samples_per_second": 106.595,
      "eval_steps_per_second": 13.324,
      "step": 200
    },
    {
      "epoch": 1.5328467153284673,
      "grad_norm": 0.7808473110198975,
      "learning_rate": 9.793814432989691e-06,
      "loss": 3.4803,
      "step": 210
    },
    {
      "epoch": 1.6058394160583942,
      "grad_norm": 0.8358160853385925,
      "learning_rate": 9.587628865979383e-06,
      "loss": 3.4905,
      "step": 220
    },
    {
      "epoch": 1.6788321167883211,
      "grad_norm": 0.8808528184890747,
      "learning_rate": 9.381443298969073e-06,
      "loss": 3.4518,
      "step": 230
    },
    {
      "epoch": 1.7518248175182483,
      "grad_norm": 0.6673774719238281,
      "learning_rate": 9.175257731958764e-06,
      "loss": 3.4631,
      "step": 240
    },
    {
      "epoch": 1.8248175182481752,
      "grad_norm": 0.7009378671646118,
      "learning_rate": 8.969072164948455e-06,
      "loss": 3.4264,
      "step": 250
    },
    {
      "epoch": 1.8248175182481752,
      "eval_loss": 3.4590413570404053,
      "eval_runtime": 4.6618,
      "eval_samples_per_second": 104.68,
      "eval_steps_per_second": 13.085,
      "step": 250
    },
    {
      "epoch": 1.897810218978102,
      "grad_norm": 0.6876445412635803,
      "learning_rate": 8.762886597938146e-06,
      "loss": 3.398,
      "step": 260
    },
    {
      "epoch": 1.9708029197080292,
      "grad_norm": 0.5596441626548767,
      "learning_rate": 8.556701030927836e-06,
      "loss": 3.4173,
      "step": 270
    },
    {
      "epoch": 2.0437956204379564,
      "grad_norm": 0.5952299237251282,
      "learning_rate": 8.350515463917526e-06,
      "loss": 3.3986,
      "step": 280
    },
    {
      "epoch": 2.116788321167883,
      "grad_norm": 0.6578339338302612,
      "learning_rate": 8.144329896907216e-06,
      "loss": 3.3949,
      "step": 290
    },
    {
      "epoch": 2.18978102189781,
      "grad_norm": 0.7148367166519165,
      "learning_rate": 7.938144329896907e-06,
      "loss": 3.3845,
      "step": 300
    },
    {
      "epoch": 2.18978102189781,
      "eval_loss": 3.4218263626098633,
      "eval_runtime": 4.6207,
      "eval_samples_per_second": 105.611,
      "eval_steps_per_second": 13.201,
      "step": 300
    },
    {
      "epoch": 2.2627737226277373,
      "grad_norm": 0.5892521142959595,
      "learning_rate": 7.731958762886599e-06,
      "loss": 3.3821,
      "step": 310
    },
    {
      "epoch": 2.335766423357664,
      "grad_norm": 0.6282438635826111,
      "learning_rate": 7.525773195876289e-06,
      "loss": 3.3522,
      "step": 320
    },
    {
      "epoch": 2.408759124087591,
      "grad_norm": 0.5816407799720764,
      "learning_rate": 7.319587628865979e-06,
      "loss": 3.3891,
      "step": 330
    },
    {
      "epoch": 2.4817518248175183,
      "grad_norm": 0.7334665656089783,
      "learning_rate": 7.113402061855671e-06,
      "loss": 3.3682,
      "step": 340
    },
    {
      "epoch": 2.554744525547445,
      "grad_norm": 0.667533278465271,
      "learning_rate": 6.907216494845361e-06,
      "loss": 3.4053,
      "step": 350
    },
    {
      "epoch": 2.554744525547445,
      "eval_loss": 3.3971924781799316,
      "eval_runtime": 4.558,
      "eval_samples_per_second": 107.065,
      "eval_steps_per_second": 13.383,
      "step": 350
    },
    {
      "epoch": 2.627737226277372,
      "grad_norm": 0.7920149564743042,
      "learning_rate": 6.701030927835052e-06,
      "loss": 3.3418,
      "step": 360
    },
    {
      "epoch": 2.7007299270072993,
      "grad_norm": 0.6718395352363586,
      "learning_rate": 6.494845360824743e-06,
      "loss": 3.379,
      "step": 370
    },
    {
      "epoch": 2.7737226277372264,
      "grad_norm": 0.6475045680999756,
      "learning_rate": 6.288659793814433e-06,
      "loss": 3.3975,
      "step": 380
    },
    {
      "epoch": 2.846715328467153,
      "grad_norm": 0.7203289270401001,
      "learning_rate": 6.082474226804124e-06,
      "loss": 3.4352,
      "step": 390
    },
    {
      "epoch": 2.9197080291970803,
      "grad_norm": 0.5514132976531982,
      "learning_rate": 5.876288659793815e-06,
      "loss": 3.3763,
      "step": 400
    },
    {
      "epoch": 2.9197080291970803,
      "eval_loss": 3.3808703422546387,
      "eval_runtime": 4.5435,
      "eval_samples_per_second": 107.407,
      "eval_steps_per_second": 13.426,
      "step": 400
    },
    {
      "epoch": 2.9927007299270074,
      "grad_norm": 0.5394614934921265,
      "learning_rate": 5.670103092783505e-06,
      "loss": 3.3935,
      "step": 410
    },
    {
      "epoch": 3.065693430656934,
      "grad_norm": 0.6785652041435242,
      "learning_rate": 5.463917525773196e-06,
      "loss": 3.3154,
      "step": 420
    },
    {
      "epoch": 3.1386861313868613,
      "grad_norm": 0.546085774898529,
      "learning_rate": 5.257731958762888e-06,
      "loss": 3.323,
      "step": 430
    },
    {
      "epoch": 3.2116788321167884,
      "grad_norm": 0.7874196171760559,
      "learning_rate": 5.051546391752578e-06,
      "loss": 3.3889,
      "step": 440
    },
    {
      "epoch": 3.2846715328467155,
      "grad_norm": 0.5360156297683716,
      "learning_rate": 4.845360824742268e-06,
      "loss": 3.3871,
      "step": 450
    },
    {
      "epoch": 3.2846715328467155,
      "eval_loss": 3.3709511756896973,
      "eval_runtime": 4.5554,
      "eval_samples_per_second": 107.126,
      "eval_steps_per_second": 13.391,
      "step": 450
    },
    {
      "epoch": 3.3576642335766422,
      "grad_norm": 0.6126905083656311,
      "learning_rate": 4.639175257731959e-06,
      "loss": 3.4215,
      "step": 460
    },
    {
      "epoch": 3.4306569343065694,
      "grad_norm": 0.7156729102134705,
      "learning_rate": 4.4329896907216494e-06,
      "loss": 3.3448,
      "step": 470
    },
    {
      "epoch": 3.5036496350364965,
      "grad_norm": 0.5565685629844666,
      "learning_rate": 4.2268041237113405e-06,
      "loss": 3.3041,
      "step": 480
    },
    {
      "epoch": 3.576642335766423,
      "grad_norm": 0.6424775123596191,
      "learning_rate": 4.020618556701032e-06,
      "loss": 3.3398,
      "step": 490
    },
    {
      "epoch": 3.6496350364963503,
      "grad_norm": 0.5503811836242676,
      "learning_rate": 3.814432989690722e-06,
      "loss": 3.3639,
      "step": 500
    },
    {
      "epoch": 3.6496350364963503,
      "eval_loss": 3.364408493041992,
      "eval_runtime": 4.5774,
      "eval_samples_per_second": 106.611,
      "eval_steps_per_second": 13.326,
      "step": 500
    },
    {
      "epoch": 3.7226277372262775,
      "grad_norm": 0.8552574515342712,
      "learning_rate": 3.6082474226804126e-06,
      "loss": 3.3706,
      "step": 510
    },
    {
      "epoch": 3.795620437956204,
      "grad_norm": 0.6950764060020447,
      "learning_rate": 3.4020618556701037e-06,
      "loss": 3.3846,
      "step": 520
    },
    {
      "epoch": 3.8686131386861313,
      "grad_norm": 0.5460401177406311,
      "learning_rate": 3.195876288659794e-06,
      "loss": 3.3343,
      "step": 530
    },
    {
      "epoch": 3.9416058394160585,
      "grad_norm": 0.5183790326118469,
      "learning_rate": 2.9896907216494846e-06,
      "loss": 3.3234,
      "step": 540
    },
    {
      "epoch": 4.014598540145985,
      "grad_norm": 0.6364532113075256,
      "learning_rate": 2.7835051546391757e-06,
      "loss": 3.2898,
      "step": 550
    },
    {
      "epoch": 4.014598540145985,
      "eval_loss": 3.36006236076355,
      "eval_runtime": 4.5449,
      "eval_samples_per_second": 107.373,
      "eval_steps_per_second": 13.422,
      "step": 550
    },
    {
      "epoch": 4.087591240875913,
      "grad_norm": 0.6407883763313293,
      "learning_rate": 2.577319587628866e-06,
      "loss": 3.3432,
      "step": 560
    },
    {
      "epoch": 4.160583941605839,
      "grad_norm": 0.7432695031166077,
      "learning_rate": 2.3711340206185566e-06,
      "loss": 3.3128,
      "step": 570
    },
    {
      "epoch": 4.233576642335766,
      "grad_norm": 0.5630599856376648,
      "learning_rate": 2.1649484536082477e-06,
      "loss": 3.3308,
      "step": 580
    },
    {
      "epoch": 4.306569343065694,
      "grad_norm": 0.691064178943634,
      "learning_rate": 1.9587628865979384e-06,
      "loss": 3.3607,
      "step": 590
    },
    {
      "epoch": 4.37956204379562,
      "grad_norm": 0.6786036491394043,
      "learning_rate": 1.7525773195876288e-06,
      "loss": 3.3413,
      "step": 600
    },
    {
      "epoch": 4.37956204379562,
      "eval_loss": 3.3572518825531006,
      "eval_runtime": 4.5354,
      "eval_samples_per_second": 107.597,
      "eval_steps_per_second": 13.45,
      "step": 600
    },
    {
      "epoch": 4.452554744525547,
      "grad_norm": 0.5392524600028992,
      "learning_rate": 1.5463917525773197e-06,
      "loss": 3.3262,
      "step": 610
    },
    {
      "epoch": 4.525547445255475,
      "grad_norm": 0.6452904343605042,
      "learning_rate": 1.3402061855670104e-06,
      "loss": 3.3672,
      "step": 620
    },
    {
      "epoch": 4.598540145985401,
      "grad_norm": 0.6458753347396851,
      "learning_rate": 1.134020618556701e-06,
      "loss": 3.3539,
      "step": 630
    },
    {
      "epoch": 4.671532846715328,
      "grad_norm": 0.579394519329071,
      "learning_rate": 9.278350515463919e-07,
      "loss": 3.3627,
      "step": 640
    },
    {
      "epoch": 4.744525547445256,
      "grad_norm": 0.5088974237442017,
      "learning_rate": 7.216494845360824e-07,
      "loss": 3.3574,
      "step": 650
    },
    {
      "epoch": 4.744525547445256,
      "eval_loss": 3.3557839393615723,
      "eval_runtime": 4.5731,
      "eval_samples_per_second": 106.712,
      "eval_steps_per_second": 13.339,
      "step": 650
    },
    {
      "epoch": 4.817518248175182,
      "grad_norm": 0.5745378136634827,
      "learning_rate": 5.154639175257732e-07,
      "loss": 3.3426,
      "step": 660
    },
    {
      "epoch": 4.89051094890511,
      "grad_norm": 0.5284786820411682,
      "learning_rate": 3.0927835051546394e-07,
      "loss": 3.3406,
      "step": 670
    },
    {
      "epoch": 4.963503649635037,
      "grad_norm": 0.5814775824546814,
      "learning_rate": 1.0309278350515465e-07,
      "loss": 3.3041,
      "step": 680
    },
    {
      "epoch": 5.0,
      "step": 685,
      "total_flos": 2.417304476319744e+16,
      "train_loss": 3.435254694249508,
      "train_runtime": 659.3834,
      "train_samples_per_second": 33.243,
      "train_steps_per_second": 1.039
    }
  ],
  "logging_steps": 10,
  "max_steps": 685,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 2.417304476319744e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}