{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0256410256410255,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020512820512820513,
      "grad_norm": 0.27392467856407166,
      "learning_rate": 5e-05,
      "loss": 10.3777,
      "step": 1
    },
    {
      "epoch": 0.020512820512820513,
      "eval_loss": 10.361001014709473,
      "eval_runtime": 0.1085,
      "eval_samples_per_second": 460.906,
      "eval_steps_per_second": 119.836,
      "step": 1
    },
    {
      "epoch": 0.041025641025641026,
      "grad_norm": 0.25582176446914673,
      "learning_rate": 0.0001,
      "loss": 10.3865,
      "step": 2
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 0.26716944575309753,
      "learning_rate": 9.990365154573717e-05,
      "loss": 10.3909,
      "step": 3
    },
    {
      "epoch": 0.08205128205128205,
      "grad_norm": 0.26691415905952454,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.377,
      "step": 4
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.2653815448284149,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.3614,
      "step": 5
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": 0.26841723918914795,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3729,
      "step": 6
    },
    {
      "epoch": 0.14358974358974358,
      "grad_norm": 0.26555824279785156,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.3624,
      "step": 7
    },
    {
      "epoch": 0.1641025641025641,
      "grad_norm": 0.28176870942115784,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3538,
      "step": 8
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.29940441250801086,
      "learning_rate": 9.535927336897098e-05,
      "loss": 10.3422,
      "step": 9
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.2969837486743927,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.3536,
      "step": 10
    },
    {
      "epoch": 0.22564102564102564,
      "grad_norm": 0.32547885179519653,
      "learning_rate": 9.241613255361455e-05,
      "loss": 10.3439,
      "step": 11
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": 0.36328232288360596,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3582,
      "step": 12
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.2886030375957489,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.3679,
      "step": 13
    },
    {
      "epoch": 0.28717948717948716,
      "grad_norm": 0.28365519642829895,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3806,
      "step": 14
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.28843188285827637,
      "learning_rate": 8.467056167950311e-05,
      "loss": 10.3658,
      "step": 15
    },
    {
      "epoch": 0.3282051282051282,
      "grad_norm": 0.32489144802093506,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.3655,
      "step": 16
    },
    {
      "epoch": 0.3487179487179487,
      "grad_norm": 0.3091577887535095,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.3532,
      "step": 17
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.32906556129455566,
      "learning_rate": 7.75e-05,
      "loss": 10.3349,
      "step": 18
    },
    {
      "epoch": 0.38974358974358975,
      "grad_norm": 0.34548500180244446,
      "learning_rate": 7.490299105985507e-05,
      "loss": 10.341,
      "step": 19
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.37832456827163696,
      "learning_rate": 7.222075445642904e-05,
      "loss": 10.325,
      "step": 20
    },
    {
      "epoch": 0.4307692307692308,
      "grad_norm": 0.3871876299381256,
      "learning_rate": 6.946477593864228e-05,
      "loss": 10.3289,
      "step": 21
    },
    {
      "epoch": 0.4512820512820513,
      "grad_norm": 0.4060368835926056,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.3275,
      "step": 22
    },
    {
      "epoch": 0.4717948717948718,
      "grad_norm": 0.41607245802879333,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.3152,
      "step": 23
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": 0.44980254769325256,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.3351,
      "step": 24
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.3639810383319855,
      "learning_rate": 5.794314081535644e-05,
      "loss": 10.3489,
      "step": 25
    },
    {
      "epoch": 0.5128205128205128,
      "eval_loss": 10.325359344482422,
      "eval_runtime": 0.1127,
      "eval_samples_per_second": 443.568,
      "eval_steps_per_second": 115.328,
      "step": 25
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.3735477328300476,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.3638,
      "step": 26
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.40442419052124023,
      "learning_rate": 5.205685918464356e-05,
      "loss": 10.3493,
      "step": 27
    },
    {
      "epoch": 0.5743589743589743,
      "grad_norm": 0.4136633276939392,
      "learning_rate": 4.912632135009769e-05,
      "loss": 10.3471,
      "step": 28
    },
    {
      "epoch": 0.5948717948717949,
      "grad_norm": 0.4036528170108795,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 10.3383,
      "step": 29
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.4409363567829132,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.3206,
      "step": 30
    },
    {
      "epoch": 0.6358974358974359,
      "grad_norm": 0.4363512694835663,
      "learning_rate": 4.053522406135775e-05,
      "loss": 10.3195,
      "step": 31
    },
    {
      "epoch": 0.6564102564102564,
      "grad_norm": 0.463379442691803,
      "learning_rate": 3.777924554357096e-05,
      "loss": 10.3117,
      "step": 32
    },
    {
      "epoch": 0.676923076923077,
      "grad_norm": 0.4670124650001526,
      "learning_rate": 3.509700894014496e-05,
      "loss": 10.322,
      "step": 33
    },
    {
      "epoch": 0.6974358974358974,
      "grad_norm": 0.48348817229270935,
      "learning_rate": 3.250000000000001e-05,
      "loss": 10.317,
      "step": 34
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.4953899383544922,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 10.3039,
      "step": 35
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.5270515084266663,
      "learning_rate": 2.760573569460757e-05,
      "loss": 10.3209,
      "step": 36
    },
    {
      "epoch": 0.7589743589743589,
      "grad_norm": 0.45620572566986084,
      "learning_rate": 2.53294383204969e-05,
      "loss": 10.3266,
      "step": 37
    },
    {
      "epoch": 0.7794871794871795,
      "grad_norm": 0.4399639070034027,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.3413,
      "step": 38
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.48100805282592773,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 10.3435,
      "step": 39
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.47446703910827637,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 10.3281,
      "step": 40
    },
    {
      "epoch": 0.841025641025641,
      "grad_norm": 0.45964911580085754,
      "learning_rate": 1.758386744638546e-05,
      "loss": 10.3178,
      "step": 41
    },
    {
      "epoch": 0.8615384615384616,
      "grad_norm": 0.4649491012096405,
      "learning_rate": 1.602885682970026e-05,
      "loss": 10.3261,
      "step": 42
    },
    {
      "epoch": 0.882051282051282,
      "grad_norm": 0.48598578572273254,
      "learning_rate": 1.464072663102903e-05,
      "loss": 10.3031,
      "step": 43
    },
    {
      "epoch": 0.9025641025641026,
      "grad_norm": 0.4957486391067505,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 10.3039,
      "step": 44
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.5371110439300537,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 10.301,
      "step": 45
    },
    {
      "epoch": 0.9435897435897436,
      "grad_norm": 0.5200509428977966,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 10.2927,
      "step": 46
    },
    {
      "epoch": 0.9641025641025641,
      "grad_norm": 0.533359169960022,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 10.2995,
      "step": 47
    },
    {
      "epoch": 0.9846153846153847,
      "grad_norm": 0.5610686540603638,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 10.3117,
      "step": 48
    },
    {
      "epoch": 1.005128205128205,
      "grad_norm": 0.6099296808242798,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 12.8753,
      "step": 49
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.4803837835788727,
      "learning_rate": 1e-05,
      "loss": 10.1881,
      "step": 50
    },
    {
      "epoch": 1.0256410256410255,
      "eval_loss": 10.305089950561523,
      "eval_runtime": 0.1031,
      "eval_samples_per_second": 485.182,
      "eval_steps_per_second": 126.147,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 42768059596800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}