{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500.0,
  "global_step": 469,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021321961620469083,
      "grad_norm": 43.0,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 2.9051132202148438,
      "step": 1,
      "token_acc": 0.7277310924369748
    },
    {
      "epoch": 0.021321961620469083,
      "grad_norm": 22.625,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.441012912326389,
      "step": 10,
      "token_acc": 0.7579183406521536
    },
    {
      "epoch": 0.042643923240938165,
      "grad_norm": 5.4375,
      "learning_rate": 1.9994015129908345e-05,
      "loss": 0.8593629837036133,
      "step": 20,
      "token_acc": 0.7911111111111111
    },
    {
      "epoch": 0.06396588486140725,
      "grad_norm": 4.625,
      "learning_rate": 1.9946179143004327e-05,
      "loss": 0.6798801422119141,
      "step": 30,
      "token_acc": 0.8122553191489361
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 4.84375,
      "learning_rate": 1.9850736134393288e-05,
      "loss": 0.6295328140258789,
      "step": 40,
      "token_acc": 0.8224060022167278
    },
    {
      "epoch": 0.10660980810234541,
      "grad_norm": 5.28125,
      "learning_rate": 1.970814293853572e-05,
      "loss": 0.6145264625549316,
      "step": 50,
      "token_acc": 0.8277070335868729
    },
    {
      "epoch": 0.1279317697228145,
      "grad_norm": 5.71875,
      "learning_rate": 1.951908207253421e-05,
      "loss": 0.5874358177185058,
      "step": 60,
      "token_acc": 0.832194705380017
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 4.84375,
      "learning_rate": 1.9284458469290354e-05,
      "loss": 0.5833245754241944,
      "step": 70,
      "token_acc": 0.8283689140156949
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 5.3125,
      "learning_rate": 1.9005395146076618e-05,
      "loss": 0.588797664642334,
      "step": 80,
      "token_acc": 0.8285130996937734
    },
    {
      "epoch": 0.19189765458422176,
      "grad_norm": 4.9375,
      "learning_rate": 1.8683227829255333e-05,
      "loss": 0.5961318969726562,
      "step": 90,
      "token_acc": 0.8281675749318801
    },
    {
      "epoch": 0.21321961620469082,
      "grad_norm": 5.625,
      "learning_rate": 1.8319498560873475e-05,
      "loss": 0.5879468441009521,
      "step": 100,
      "token_acc": 0.8282130056323604
    },
    {
      "epoch": 0.2345415778251599,
      "grad_norm": 4.9375,
      "learning_rate": 1.791594831773494e-05,
      "loss": 0.5458186626434326,
      "step": 110,
      "token_acc": 0.8368572395128552
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 4.8125,
      "learning_rate": 1.7474508678278914e-05,
      "loss": 0.5461445331573487,
      "step": 120,
      "token_acc": 0.8417710802573654
    },
    {
      "epoch": 0.2771855010660981,
      "grad_norm": 4.8125,
      "learning_rate": 1.699729257715053e-05,
      "loss": 0.5506069183349609,
      "step": 130,
      "token_acc": 0.8393039049235993
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 4.59375,
      "learning_rate": 1.648658419171666e-05,
      "loss": 0.56076021194458,
      "step": 140,
      "token_acc": 0.832009565291656
    },
    {
      "epoch": 0.31982942430703626,
      "grad_norm": 4.375,
      "learning_rate": 1.594482800893474e-05,
      "loss": 0.5413748741149902,
      "step": 150,
      "token_acc": 0.8403925186614107
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 4.84375,
      "learning_rate": 1.5374617124905565e-05,
      "loss": 0.5552651405334472,
      "step": 160,
      "token_acc": 0.8403886776510351
    },
    {
      "epoch": 0.3624733475479744,
      "grad_norm": 17.625,
      "learning_rate": 1.4778680833113928e-05,
      "loss": 0.5687627792358398,
      "step": 170,
      "token_acc": 0.8335312075983717
    },
    {
      "epoch": 0.3837953091684435,
      "grad_norm": 4.65625,
      "learning_rate": 1.4159871560765432e-05,
      "loss": 0.5532018184661865,
      "step": 180,
      "token_acc": 0.8383640846866763
    },
    {
      "epoch": 0.4051172707889126,
      "grad_norm": 4.84375,
      "learning_rate": 1.352115121574829e-05,
      "loss": 0.5434678077697754,
      "step": 190,
      "token_acc": 0.8393686165273909
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 5.625,
      "learning_rate": 1.2865577009569825e-05,
      "loss": 0.5481713294982911,
      "step": 200,
      "token_acc": 0.8371288798920378
    },
    {
      "epoch": 0.44776119402985076,
      "grad_norm": 7.6875,
      "learning_rate": 1.2196286824125728e-05,
      "loss": 0.5360486030578613,
      "step": 210,
      "token_acc": 0.8407146451937595
    },
    {
      "epoch": 0.4690831556503198,
      "grad_norm": 4.53125,
      "learning_rate": 1.1516484192343425e-05,
      "loss": 0.5320311546325683,
      "step": 220,
      "token_acc": 0.8416673741404194
    },
    {
      "epoch": 0.4904051172707889,
      "grad_norm": 5.3125,
      "learning_rate": 1.082942296458922e-05,
      "loss": 0.5446446418762207,
      "step": 230,
      "token_acc": 0.8414119236615436
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 5.09375,
      "learning_rate": 1.0138391734232832e-05,
      "loss": 0.5085601806640625,
      "step": 240,
      "token_acc": 0.8489312782082943
    },
    {
      "epoch": 0.5330490405117271,
      "grad_norm": 4.75,
      "learning_rate": 9.446698096915848e-06,
      "loss": 0.5495187759399414,
      "step": 250,
      "token_acc": 0.8368993037867211
    },
    {
      "epoch": 0.5543710021321961,
      "grad_norm": 4.9375,
      "learning_rate": 8.75765281886647e-06,
      "loss": 0.5613573551177978,
      "step": 260,
      "token_acc": 0.8375316990701606
    },
    {
      "epoch": 0.5756929637526652,
      "grad_norm": 4.8125,
      "learning_rate": 8.074553990038396e-06,
      "loss": 0.5430341720581054,
      "step": 270,
      "token_acc": 0.8400202719824309
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 4.5625,
      "learning_rate": 7.400671237924202e-06,
      "loss": 0.5135886192321777,
      "step": 280,
      "token_acc": 0.8479239195041182
    },
    {
      "epoch": 0.6183368869936035,
      "grad_norm": 5.875,
      "learning_rate": 6.739230077603259e-06,
      "loss": 0.5393872261047363,
      "step": 290,
      "token_acc": 0.8358839942504439
    },
    {
      "epoch": 0.6396588486140725,
      "grad_norm": 4.71875,
      "learning_rate": 6.093396472932103e-06,
      "loss": 0.5145103454589843,
      "step": 300,
      "token_acc": 0.841726618705036
    },
    {
      "epoch": 0.6609808102345416,
      "grad_norm": 4.8125,
      "learning_rate": 5.466261682774519e-06,
      "loss": 0.5321601867675781,
      "step": 310,
      "token_acc": 0.8421635434412266
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 4.78125,
      "learning_rate": 4.860827464804383e-06,
      "loss": 0.53086256980896,
      "step": 320,
      "token_acc": 0.841112047177759
    },
    {
      "epoch": 0.7036247334754797,
      "grad_norm": 5.0,
      "learning_rate": 4.2799917077026394e-06,
      "loss": 0.5327719688415528,
      "step": 330,
      "token_acc": 0.8390072111353346
    },
    {
      "epoch": 0.7249466950959488,
      "grad_norm": 5.03125,
      "learning_rate": 3.7265345605193814e-06,
      "loss": 0.5248814582824707,
      "step": 340,
      "token_acc": 0.8462834990729816
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 5.0,
      "learning_rate": 3.2031051255924082e-06,
      "loss": 0.5124996662139892,
      "step": 350,
      "token_acc": 0.8435970110796187
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 5.09375,
      "learning_rate": 2.7122087787160168e-06,
      "loss": 0.5450184345245361,
      "step": 360,
      "token_acc": 0.8357380688124306
    },
    {
      "epoch": 0.7889125799573561,
      "grad_norm": 4.90625,
      "learning_rate": 2.256195177251659e-06,
      "loss": 0.5345516204833984,
      "step": 370,
      "token_acc": 0.8386361718288463
    },
    {
      "epoch": 0.8102345415778252,
      "grad_norm": 5.09375,
      "learning_rate": 1.8372470135791344e-06,
      "loss": 0.5218245029449463,
      "step": 380,
      "token_acc": 0.8449079962689732
    },
    {
      "epoch": 0.8315565031982942,
      "grad_norm": 5.03125,
      "learning_rate": 1.457369567719581e-06,
      "loss": 0.5236470222473144,
      "step": 390,
      "token_acc": 0.8448715767987753
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 4.90625,
      "learning_rate": 1.118381109136174e-06,
      "loss": 0.49837121963500974,
      "step": 400,
      "token_acc": 0.8512574027980431
    },
    {
      "epoch": 0.8742004264392325,
      "grad_norm": 4.8125,
      "learning_rate": 8.219041936540395e-07,
      "loss": 0.5413351058959961,
      "step": 410,
      "token_acc": 0.841102587878277
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 4.84375,
      "learning_rate": 5.693578971562963e-07,
      "loss": 0.5475930213928223,
      "step": 420,
      "token_acc": 0.8388290713324361
    },
    {
      "epoch": 0.9168443496801706,
      "grad_norm": 5.0,
      "learning_rate": 3.6195102322937545e-07,
      "loss": 0.5307172775268555,
      "step": 430,
      "token_acc": 0.8429056924384027
    },
    {
      "epoch": 0.9381663113006397,
      "grad_norm": 5.0625,
      "learning_rate": 2.006763172689996e-07,
      "loss": 0.5404001712799072,
      "step": 440,
      "token_acc": 0.8392032826124124
    },
    {
      "epoch": 0.9594882729211087,
      "grad_norm": 4.75,
      "learning_rate": 8.630571474074312e-08,
      "loss": 0.5237876892089843,
      "step": 450,
      "token_acc": 0.8413437129801997
    },
    {
      "epoch": 0.9808102345415778,
      "grad_norm": 4.65625,
      "learning_rate": 1.9386646339238925e-08,
      "loss": 0.534755277633667,
      "step": 460,
      "token_acc": 0.8429147755925366
    }
  ],
  "logging_steps": 10,
  "max_steps": 469,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.015212785725604e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}