{
  "best_global_step": 536,
  "best_metric": 2.8649895191192627,
  "best_model_checkpoint": "gpt2-finetuned/checkpoint-536",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 536,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 4.323858737945557,
      "learning_rate": 1.0588235294117648e-05,
      "loss": 3.5710372924804688,
      "step": 10
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 3.9307808876037598,
      "learning_rate": 1.9922928709055876e-05,
      "loss": 3.3915550231933596,
      "step": 20
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 3.703219175338745,
      "learning_rate": 1.9537572254335264e-05,
      "loss": 3.30927734375,
      "step": 30
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 3.3923251628875732,
      "learning_rate": 1.9152215799614644e-05,
      "loss": 3.2569236755371094,
      "step": 40
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 3.6839487552642822,
      "learning_rate": 1.8766859344894028e-05,
      "loss": 3.2078022003173827,
      "step": 50
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 3.1598305702209473,
      "learning_rate": 1.838150289017341e-05,
      "loss": 3.1958980560302734,
      "step": 60
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 3.5608792304992676,
      "learning_rate": 1.7996146435452795e-05,
      "loss": 3.1352081298828125,
      "step": 70
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 3.694288492202759,
      "learning_rate": 1.761078998073218e-05,
      "loss": 3.1180818557739256,
      "step": 80
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 3.2345361709594727,
      "learning_rate": 1.722543352601156e-05,
      "loss": 3.121156692504883,
      "step": 90
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 2.8083014488220215,
      "learning_rate": 1.6840077071290947e-05,
      "loss": 3.091750907897949,
      "step": 100
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": 3.5092177391052246,
      "learning_rate": 1.645472061657033e-05,
      "loss": 3.085820198059082,
      "step": 110
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 3.606647491455078,
      "learning_rate": 1.606936416184971e-05,
      "loss": 3.103367233276367,
      "step": 120
    },
    {
      "epoch": 0.48598130841121495,
      "grad_norm": 2.9848923683166504,
      "learning_rate": 1.5684007707129095e-05,
      "loss": 3.1185840606689452,
      "step": 130
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": 3.9700093269348145,
      "learning_rate": 1.529865125240848e-05,
      "loss": 3.111907386779785,
      "step": 140
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 4.307053565979004,
      "learning_rate": 1.4913294797687862e-05,
      "loss": 3.1015724182128905,
      "step": 150
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 4.230574607849121,
      "learning_rate": 1.4527938342967245e-05,
      "loss": 3.1573991775512695,
      "step": 160
    },
    {
      "epoch": 0.6355140186915887,
      "grad_norm": 3.484198808670044,
      "learning_rate": 1.414258188824663e-05,
      "loss": 3.09665470123291,
      "step": 170
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 3.7458720207214355,
      "learning_rate": 1.3757225433526014e-05,
      "loss": 3.0797067642211915,
      "step": 180
    },
    {
      "epoch": 0.7102803738317757,
      "grad_norm": 3.599705457687378,
      "learning_rate": 1.3371868978805396e-05,
      "loss": 3.02014045715332,
      "step": 190
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 3.341883659362793,
      "learning_rate": 1.298651252408478e-05,
      "loss": 3.0037511825561523,
      "step": 200
    },
    {
      "epoch": 0.7850467289719626,
      "grad_norm": 3.6026880741119385,
      "learning_rate": 1.2601156069364162e-05,
      "loss": 2.995482063293457,
      "step": 210
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": 3.875734329223633,
      "learning_rate": 1.2215799614643546e-05,
      "loss": 3.0261470794677736,
      "step": 220
    },
    {
      "epoch": 0.8598130841121495,
      "grad_norm": 3.5683584213256836,
      "learning_rate": 1.1830443159922928e-05,
      "loss": 2.9946710586547853,
      "step": 230
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 4.219651699066162,
      "learning_rate": 1.1445086705202313e-05,
      "loss": 3.067545509338379,
      "step": 240
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 3.2647459506988525,
      "learning_rate": 1.1059730250481697e-05,
      "loss": 3.047348976135254,
      "step": 250
    },
    {
      "epoch": 0.9719626168224299,
      "grad_norm": 3.6350138187408447,
      "learning_rate": 1.067437379576108e-05,
      "loss": 3.044650077819824,
      "step": 260
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.9178810119628906,
      "eval_runtime": 22.6583,
      "eval_samples_per_second": 41.927,
      "eval_steps_per_second": 20.964,
      "step": 268
    },
    {
      "epoch": 1.0074766355140188,
      "grad_norm": 3.5870800018310547,
      "learning_rate": 1.0289017341040463e-05,
      "loss": 2.9937585830688476,
      "step": 270
    },
    {
      "epoch": 1.0448598130841122,
      "grad_norm": 4.361166000366211,
      "learning_rate": 9.903660886319847e-06,
      "loss": 3.0103271484375,
      "step": 280
    },
    {
      "epoch": 1.0822429906542057,
      "grad_norm": 3.9424304962158203,
      "learning_rate": 9.51830443159923e-06,
      "loss": 2.9879344940185546,
      "step": 290
    },
    {
      "epoch": 1.1196261682242992,
      "grad_norm": 4.069947719573975,
      "learning_rate": 9.132947976878613e-06,
      "loss": 2.987399673461914,
      "step": 300
    },
    {
      "epoch": 1.1570093457943926,
      "grad_norm": 4.206397533416748,
      "learning_rate": 8.747591522157996e-06,
      "loss": 2.9407649993896485,
      "step": 310
    },
    {
      "epoch": 1.194392523364486,
      "grad_norm": 4.135429382324219,
      "learning_rate": 8.36223506743738e-06,
      "loss": 2.9791286468505858,
      "step": 320
    },
    {
      "epoch": 1.2317757009345796,
      "grad_norm": 4.783056259155273,
      "learning_rate": 7.976878612716764e-06,
      "loss": 2.982815742492676,
      "step": 330
    },
    {
      "epoch": 1.269158878504673,
      "grad_norm": 4.636116981506348,
      "learning_rate": 7.591522157996147e-06,
      "loss": 3.0075199127197267,
      "step": 340
    },
    {
      "epoch": 1.3065420560747665,
      "grad_norm": 4.425142765045166,
      "learning_rate": 7.206165703275531e-06,
      "loss": 3.0005060195922852,
      "step": 350
    },
    {
      "epoch": 1.34392523364486,
      "grad_norm": 3.986107349395752,
      "learning_rate": 6.820809248554914e-06,
      "loss": 2.9552526473999023,
      "step": 360
    },
    {
      "epoch": 1.3813084112149534,
      "grad_norm": 4.123307228088379,
      "learning_rate": 6.435452793834297e-06,
      "loss": 2.9348220825195312,
      "step": 370
    },
    {
      "epoch": 1.4186915887850469,
      "grad_norm": 4.234403133392334,
      "learning_rate": 6.0500963391136806e-06,
      "loss": 2.963719940185547,
      "step": 380
    },
    {
      "epoch": 1.45607476635514,
      "grad_norm": 5.90896463394165,
      "learning_rate": 5.664739884393064e-06,
      "loss": 2.98101749420166,
      "step": 390
    },
    {
      "epoch": 1.4934579439252336,
      "grad_norm": 3.8738784790039062,
      "learning_rate": 5.279383429672448e-06,
      "loss": 2.9381120681762694,
      "step": 400
    },
    {
      "epoch": 1.5308411214953273,
      "grad_norm": 4.2729268074035645,
      "learning_rate": 4.894026974951831e-06,
      "loss": 3.004109191894531,
      "step": 410
    },
    {
      "epoch": 1.5682242990654207,
      "grad_norm": 4.344122886657715,
      "learning_rate": 4.508670520231214e-06,
      "loss": 2.8942329406738283,
      "step": 420
    },
    {
      "epoch": 1.6056074766355142,
      "grad_norm": 4.170741081237793,
      "learning_rate": 4.123314065510597e-06,
      "loss": 2.9949222564697267,
      "step": 430
    },
    {
      "epoch": 1.6429906542056076,
      "grad_norm": 4.825467109680176,
      "learning_rate": 3.7379576107899813e-06,
      "loss": 2.9415472030639647,
      "step": 440
    },
    {
      "epoch": 1.680373831775701,
      "grad_norm": 4.231213569641113,
      "learning_rate": 3.3526011560693642e-06,
      "loss": 2.94517822265625,
      "step": 450
    },
    {
      "epoch": 1.7177570093457943,
      "grad_norm": 4.937946319580078,
      "learning_rate": 2.9672447013487476e-06,
      "loss": 3.005815315246582,
      "step": 460
    },
    {
      "epoch": 1.7551401869158878,
      "grad_norm": 4.124006748199463,
      "learning_rate": 2.5818882466281314e-06,
      "loss": 2.965633201599121,
      "step": 470
    },
    {
      "epoch": 1.7925233644859813,
      "grad_norm": 3.962216854095459,
      "learning_rate": 2.1965317919075148e-06,
      "loss": 2.9793548583984375,
      "step": 480
    },
    {
      "epoch": 1.8299065420560747,
      "grad_norm": 4.627573013305664,
      "learning_rate": 1.8111753371868982e-06,
      "loss": 2.9587646484375,
      "step": 490
    },
    {
      "epoch": 1.8672897196261682,
      "grad_norm": 5.371633529663086,
      "learning_rate": 1.4258188824662813e-06,
      "loss": 2.9544118881225585,
      "step": 500
    },
    {
      "epoch": 1.9046728971962616,
      "grad_norm": 4.382261276245117,
      "learning_rate": 1.040462427745665e-06,
      "loss": 2.9408926010131835,
      "step": 510
    },
    {
      "epoch": 1.9420560747663551,
      "grad_norm": 4.642389297485352,
      "learning_rate": 6.551059730250482e-07,
      "loss": 2.942763328552246,
      "step": 520
    },
    {
      "epoch": 1.9794392523364486,
      "grad_norm": 4.728512763977051,
      "learning_rate": 2.697495183044316e-07,
      "loss": 2.9559442520141603,
      "step": 530
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.8649895191192627,
      "eval_runtime": 22.662,
      "eval_samples_per_second": 41.92,
      "eval_steps_per_second": 20.96,
      "step": 536
    }
  ],
  "logging_steps": 10,
  "max_steps": 536,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 54,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5813915102208000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}