{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0084282388141468,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.214119407073399e-05,
      "eval_loss": 0.7306418418884277,
      "eval_runtime": 769.1337,
      "eval_samples_per_second": 12.991,
      "eval_steps_per_second": 6.496,
      "step": 1
    },
    {
      "epoch": 0.00021070597035366997,
      "grad_norm": 0.40135258436203003,
      "learning_rate": 5e-05,
      "loss": 0.6852,
      "step": 5
    },
    {
      "epoch": 0.00042141194070733994,
      "grad_norm": 0.5674983859062195,
      "learning_rate": 0.0001,
      "loss": 0.6687,
      "step": 10
    },
    {
      "epoch": 0.0006321179110610099,
      "grad_norm": 0.37096917629241943,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5997,
      "step": 15
    },
    {
      "epoch": 0.0008428238814146799,
      "grad_norm": 0.32088199257850647,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.5823,
      "step": 20
    },
    {
      "epoch": 0.00105352985176835,
      "grad_norm": 0.2716768980026245,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5327,
      "step": 25
    },
    {
      "epoch": 0.0012642358221220198,
      "grad_norm": 0.3887002170085907,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4721,
      "step": 30
    },
    {
      "epoch": 0.00147494179247569,
      "grad_norm": 0.29545557498931885,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5009,
      "step": 35
    },
    {
      "epoch": 0.0016856477628293598,
      "grad_norm": 0.37248632311820984,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.5086,
      "step": 40
    },
    {
      "epoch": 0.0018963537331830298,
      "grad_norm": 0.48823219537734985,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.501,
      "step": 45
    },
    {
      "epoch": 0.0021070597035367,
      "grad_norm": 0.6302451491355896,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.4082,
      "step": 50
    },
    {
      "epoch": 0.0021070597035367,
      "eval_loss": 0.46660560369491577,
      "eval_runtime": 772.4477,
      "eval_samples_per_second": 12.936,
      "eval_steps_per_second": 6.468,
      "step": 50
    },
    {
      "epoch": 0.0023177656738903696,
      "grad_norm": 0.2764967978000641,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4263,
      "step": 55
    },
    {
      "epoch": 0.0025284716442440396,
      "grad_norm": 0.2731228470802307,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.5004,
      "step": 60
    },
    {
      "epoch": 0.0027391776145977097,
      "grad_norm": 0.25533390045166016,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4838,
      "step": 65
    },
    {
      "epoch": 0.00294988358495138,
      "grad_norm": 0.2774222493171692,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.456,
      "step": 70
    },
    {
      "epoch": 0.0031605895553050494,
      "grad_norm": 0.3047914505004883,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4601,
      "step": 75
    },
    {
      "epoch": 0.0033712955256587195,
      "grad_norm": 0.32493507862091064,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4616,
      "step": 80
    },
    {
      "epoch": 0.0035820014960123896,
      "grad_norm": 0.32692256569862366,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4568,
      "step": 85
    },
    {
      "epoch": 0.0037927074663660597,
      "grad_norm": 0.38204264640808105,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.4275,
      "step": 90
    },
    {
      "epoch": 0.00400341343671973,
      "grad_norm": 0.5144729614257812,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4091,
      "step": 95
    },
    {
      "epoch": 0.0042141194070734,
      "grad_norm": 1.130403995513916,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.4399,
      "step": 100
    },
    {
      "epoch": 0.0042141194070734,
      "eval_loss": 0.43319445848464966,
      "eval_runtime": 772.5186,
      "eval_samples_per_second": 12.934,
      "eval_steps_per_second": 6.467,
      "step": 100
    },
    {
      "epoch": 0.004424825377427069,
      "grad_norm": 0.27533236145973206,
      "learning_rate": 5e-05,
      "loss": 0.4307,
      "step": 105
    },
    {
      "epoch": 0.004635531347780739,
      "grad_norm": 0.27929797768592834,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.4849,
      "step": 110
    },
    {
      "epoch": 0.004846237318134409,
      "grad_norm": 0.2581718862056732,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4329,
      "step": 115
    },
    {
      "epoch": 0.005056943288488079,
      "grad_norm": 0.2721578776836395,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.4343,
      "step": 120
    },
    {
      "epoch": 0.005267649258841749,
      "grad_norm": 0.29581791162490845,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4061,
      "step": 125
    },
    {
      "epoch": 0.0054783552291954194,
      "grad_norm": 0.35202425718307495,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4492,
      "step": 130
    },
    {
      "epoch": 0.0056890611995490895,
      "grad_norm": 0.37017086148262024,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4112,
      "step": 135
    },
    {
      "epoch": 0.00589976716990276,
      "grad_norm": 0.41043344140052795,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.4235,
      "step": 140
    },
    {
      "epoch": 0.006110473140256429,
      "grad_norm": 0.5290806293487549,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.4248,
      "step": 145
    },
    {
      "epoch": 0.006321179110610099,
      "grad_norm": 1.3881969451904297,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3672,
      "step": 150
    },
    {
      "epoch": 0.006321179110610099,
      "eval_loss": 0.4205006957054138,
      "eval_runtime": 772.5032,
      "eval_samples_per_second": 12.935,
      "eval_steps_per_second": 6.467,
      "step": 150
    },
    {
      "epoch": 0.006531885080963769,
      "grad_norm": 0.23568226397037506,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4266,
      "step": 155
    },
    {
      "epoch": 0.006742591051317439,
      "grad_norm": 0.2838892936706543,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.4394,
      "step": 160
    },
    {
      "epoch": 0.006953297021671109,
      "grad_norm": 0.2912816107273102,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.4807,
      "step": 165
    },
    {
      "epoch": 0.007164002992024779,
      "grad_norm": 0.2774169445037842,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.4735,
      "step": 170
    },
    {
      "epoch": 0.007374708962378449,
      "grad_norm": 0.3025800883769989,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4458,
      "step": 175
    },
    {
      "epoch": 0.007585414932732119,
      "grad_norm": 0.3525184690952301,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.4749,
      "step": 180
    },
    {
      "epoch": 0.007796120903085789,
      "grad_norm": 0.37918704748153687,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.4072,
      "step": 185
    },
    {
      "epoch": 0.00800682687343946,
      "grad_norm": 0.38551801443099976,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.4123,
      "step": 190
    },
    {
      "epoch": 0.008217532843793129,
      "grad_norm": 0.5288830399513245,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.3952,
      "step": 195
    },
    {
      "epoch": 0.0084282388141468,
      "grad_norm": 1.1451185941696167,
      "learning_rate": 0.0,
      "loss": 0.3828,
      "step": 200
    },
    {
      "epoch": 0.0084282388141468,
      "eval_loss": 0.41791725158691406,
      "eval_runtime": 772.551,
      "eval_samples_per_second": 12.934,
      "eval_steps_per_second": 6.467,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "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": 6.547507206370099e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}