{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5413,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018474043968224645,
      "grad_norm": 0.13603828847408295,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.4189,
      "step": 100
    },
    {
      "epoch": 0.03694808793644929,
      "grad_norm": 0.21061019599437714,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.4272,
      "step": 200
    },
    {
      "epoch": 0.05542213190467393,
      "grad_norm": 0.16636639833450317,
      "learning_rate": 6e-06,
      "loss": 2.3945,
      "step": 300
    },
    {
      "epoch": 0.07389617587289858,
      "grad_norm": 0.25446009635925293,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.4208,
      "step": 400
    },
    {
      "epoch": 0.09237021984112322,
      "grad_norm": 0.34781575202941895,
      "learning_rate": 1e-05,
      "loss": 2.3269,
      "step": 500
    },
    {
      "epoch": 0.11084426380934786,
      "grad_norm": 0.38206952810287476,
      "learning_rate": 1.2e-05,
      "loss": 2.3088,
      "step": 600
    },
    {
      "epoch": 0.1293183077775725,
      "grad_norm": 0.46091267466545105,
      "learning_rate": 1.4e-05,
      "loss": 2.28,
      "step": 700
    },
    {
      "epoch": 0.14779235174579716,
      "grad_norm": 0.52289879322052,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.2588,
      "step": 800
    },
    {
      "epoch": 0.1662663957140218,
      "grad_norm": 0.6144861578941345,
      "learning_rate": 1.8e-05,
      "loss": 2.2285,
      "step": 900
    },
    {
      "epoch": 0.18474043968224643,
      "grad_norm": 0.5469977259635925,
      "learning_rate": 2e-05,
      "loss": 2.2167,
      "step": 1000
    },
    {
      "epoch": 0.2032144836504711,
      "grad_norm": 0.6013001203536987,
      "learning_rate": 1.9974670975035436e-05,
      "loss": 2.2091,
      "step": 1100
    },
    {
      "epoch": 0.22168852761869573,
      "grad_norm": 0.646751344203949,
      "learning_rate": 1.9898812212042866e-05,
      "loss": 2.1852,
      "step": 1200
    },
    {
      "epoch": 0.24016257158692036,
      "grad_norm": 0.6461096405982971,
      "learning_rate": 1.9772807996722613e-05,
      "loss": 2.1638,
      "step": 1300
    },
    {
      "epoch": 0.258636615555145,
      "grad_norm": 0.701188862323761,
      "learning_rate": 1.9597296641857785e-05,
      "loss": 2.1498,
      "step": 1400
    },
    {
      "epoch": 0.27711065952336966,
      "grad_norm": 0.6271322965621948,
      "learning_rate": 1.937316725374616e-05,
      "loss": 2.1256,
      "step": 1500
    },
    {
      "epoch": 0.2955847034915943,
      "grad_norm": 0.759938657283783,
      "learning_rate": 1.9101555228161095e-05,
      "loss": 2.1666,
      "step": 1600
    },
    {
      "epoch": 0.31405874745981893,
      "grad_norm": 0.8668082356452942,
      "learning_rate": 1.8783836498657935e-05,
      "loss": 2.0683,
      "step": 1700
    },
    {
      "epoch": 0.3325327914280436,
      "grad_norm": 0.6333598494529724,
      "learning_rate": 1.842162056636294e-05,
      "loss": 2.1202,
      "step": 1800
    },
    {
      "epoch": 0.35100683539626826,
      "grad_norm": 1.2562055587768555,
      "learning_rate": 1.8016742346554438e-05,
      "loss": 2.0678,
      "step": 1900
    },
    {
      "epoch": 0.36948087936449286,
      "grad_norm": 0.797377347946167,
      "learning_rate": 1.757125287333986e-05,
      "loss": 2.1482,
      "step": 2000
    },
    {
      "epoch": 0.3879549233327175,
      "grad_norm": 0.8891714215278625,
      "learning_rate": 1.7087408909516908e-05,
      "loss": 2.0704,
      "step": 2100
    },
    {
      "epoch": 0.4064289673009422,
      "grad_norm": 0.7375055551528931,
      "learning_rate": 1.6567661514253307e-05,
      "loss": 2.0947,
      "step": 2200
    },
    {
      "epoch": 0.4249030112691668,
      "grad_norm": 0.8577471971511841,
      "learning_rate": 1.6014643626499038e-05,
      "loss": 2.0871,
      "step": 2300
    },
    {
      "epoch": 0.44337705523739146,
      "grad_norm": 1.0253443717956543,
      "learning_rate": 1.543115672703105e-05,
      "loss": 2.083,
      "step": 2400
    },
    {
      "epoch": 0.4618510992056161,
      "grad_norm": 0.6721712946891785,
      "learning_rate": 1.482015664669798e-05,
      "loss": 2.0974,
      "step": 2500
    },
    {
      "epoch": 0.48032514317384073,
      "grad_norm": 0.8794868588447571,
      "learning_rate": 1.4184738592757442e-05,
      "loss": 2.0854,
      "step": 2600
    },
    {
      "epoch": 0.4987991871420654,
      "grad_norm": 0.8709807395935059,
      "learning_rate": 1.352812146915967e-05,
      "loss": 2.0224,
      "step": 2700
    },
    {
      "epoch": 0.51727323111029,
      "grad_norm": 0.9674624800682068,
      "learning_rate": 1.2853631570207828e-05,
      "loss": 2.0736,
      "step": 2800
    },
    {
      "epoch": 0.5357472750785147,
      "grad_norm": 0.952232837677002,
      "learning_rate": 1.2164685730199688e-05,
      "loss": 2.0518,
      "step": 2900
    },
    {
      "epoch": 0.5542213190467393,
      "grad_norm": 0.8109374046325684,
      "learning_rate": 1.1464774014411416e-05,
      "loss": 2.0703,
      "step": 3000
    },
    {
      "epoch": 0.5726953630149639,
      "grad_norm": 0.9935118556022644,
      "learning_rate": 1.0757442039107453e-05,
      "loss": 2.0455,
      "step": 3100
    },
    {
      "epoch": 0.5911694069831886,
      "grad_norm": 1.1586925983428955,
      "learning_rate": 1.0046273010139933e-05,
      "loss": 2.0953,
      "step": 3200
    },
    {
      "epoch": 0.6096434509514133,
      "grad_norm": 0.9651207327842712,
      "learning_rate": 9.334869571126606e-06,
      "loss": 2.0118,
      "step": 3300
    },
    {
      "epoch": 0.6281174949196379,
      "grad_norm": 0.9459812641143799,
      "learning_rate": 8.626835553160812e-06,
      "loss": 2.0098,
      "step": 3400
    },
    {
      "epoch": 0.6465915388878626,
      "grad_norm": 1.0193432569503784,
      "learning_rate": 7.925757718505905e-06,
      "loss": 2.0608,
      "step": 3500
    },
    {
      "epoch": 0.6650655828560872,
      "grad_norm": 1.116503357887268,
      "learning_rate": 7.235187590757096e-06,
      "loss": 2.0356,
      "step": 3600
    },
    {
      "epoch": 0.6835396268243118,
      "grad_norm": 1.1280616521835327,
      "learning_rate": 6.558623463515508e-06,
      "loss": 2.0329,
      "step": 3700
    },
    {
      "epoch": 0.7020136707925365,
      "grad_norm": 1.1691473722457886,
      "learning_rate": 5.89949267871493e-06,
      "loss": 2.0155,
      "step": 3800
    },
    {
      "epoch": 0.7204877147607611,
      "grad_norm": 1.1276525259017944,
      "learning_rate": 5.261134264376e-06,
      "loss": 2.0515,
      "step": 3900
    },
    {
      "epoch": 0.7389617587289857,
      "grad_norm": 0.9956721663475037,
      "learning_rate": 4.646782019741341e-06,
      "loss": 2.0469,
      "step": 4000
    },
    {
      "epoch": 0.7574358026972104,
      "grad_norm": 0.7289612889289856,
      "learning_rate": 4.05954813347923e-06,
      "loss": 2.04,
      "step": 4100
    },
    {
      "epoch": 0.775909846665435,
      "grad_norm": 0.8100431561470032,
      "learning_rate": 3.5024074179427013e-06,
      "loss": 1.9854,
      "step": 4200
    },
    {
      "epoch": 0.7943838906336597,
      "grad_norm": 1.2641098499298096,
      "learning_rate": 2.9781822393502733e-06,
      "loss": 2.0523,
      "step": 4300
    },
    {
      "epoch": 0.8128579346018844,
      "grad_norm": 1.4096829891204834,
      "learning_rate": 2.489528220229076e-06,
      "loss": 1.9835,
      "step": 4400
    },
    {
      "epoch": 0.831331978570109,
      "grad_norm": 0.9369058609008789,
      "learning_rate": 2.0389207865489768e-06,
      "loss": 2.0281,
      "step": 4500
    },
    {
      "epoch": 0.8498060225383336,
      "grad_norm": 0.9278631806373596,
      "learning_rate": 1.6286426276973566e-06,
      "loss": 2.037,
      "step": 4600
    },
    {
      "epoch": 0.8682800665065583,
      "grad_norm": 0.917284369468689,
      "learning_rate": 1.2607721328198097e-06,
      "loss": 2.0221,
      "step": 4700
    },
    {
      "epoch": 0.8867541104747829,
      "grad_norm": 1.1175345182418823,
      "learning_rate": 9.371728621060306e-07,
      "loss": 2.0185,
      "step": 4800
    },
    {
      "epoch": 0.9052281544430075,
      "grad_norm": 0.8119403123855591,
      "learning_rate": 6.594841063573099e-07,
      "loss": 1.9912,
      "step": 4900
    },
    {
      "epoch": 0.9237021984112322,
      "grad_norm": 0.82546067237854,
      "learning_rate": 4.2911258265898814e-07,
      "loss": 1.9846,
      "step": 5000
    },
    {
      "epoch": 0.9421762423794569,
      "grad_norm": 1.3545786142349243,
      "learning_rate": 2.472253082260456e-07,
      "loss": 1.9997,
      "step": 5100
    },
    {
      "epoch": 0.9606502863476815,
      "grad_norm": 1.112060308456421,
      "learning_rate": 1.1474368852145035e-07,
      "loss": 2.0152,
      "step": 5200
    },
    {
      "epoch": 0.9791243303159062,
      "grad_norm": 1.0460844039916992,
      "learning_rate": 3.233884959577327e-08,
      "loss": 2.0241,
      "step": 5300
    },
    {
      "epoch": 0.9975983742841308,
      "grad_norm": 1.0712796449661255,
      "learning_rate": 4.2823829348170866e-10,
      "loss": 2.0704,
      "step": 5400
    },
    {
      "epoch": 1.0,
      "step": 5413,
      "total_flos": 9.84840481406976e+16,
      "train_loss": 2.112572115185123,
      "train_runtime": 1452.1865,
      "train_samples_per_second": 7.455,
      "train_steps_per_second": 3.727
    }
  ],
  "logging_steps": 100,
  "max_steps": 5413,
  "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": 9.84840481406976e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}