{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7094017094017095,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 0.2997426986694336,
      "learning_rate": 5e-05,
      "loss": 0.9476,
      "step": 1
    },
    {
      "epoch": 0.03418803418803419,
      "eval_loss": 1.2048848867416382,
      "eval_runtime": 3.4576,
      "eval_samples_per_second": 14.461,
      "eval_steps_per_second": 3.76,
      "step": 1
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 0.39732587337493896,
      "learning_rate": 0.0001,
      "loss": 1.0399,
      "step": 2
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.41230157017707825,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.0647,
      "step": 3
    },
    {
      "epoch": 0.13675213675213677,
      "grad_norm": 0.3619644343852997,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.0962,
      "step": 4
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 0.5769338011741638,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.228,
      "step": 5
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.7016761898994446,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.1309,
      "step": 6
    },
    {
      "epoch": 0.23931623931623933,
      "grad_norm": 1.0003128051757812,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.1807,
      "step": 7
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 0.8136112689971924,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.9264,
      "step": 8
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.7829558253288269,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.9914,
      "step": 9
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 0.5833770036697388,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.9621,
      "step": 10
    },
    {
      "epoch": 0.37606837606837606,
      "grad_norm": 0.42219626903533936,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.9636,
      "step": 11
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.5771196484565735,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.0986,
      "step": 12
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.7427020072937012,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.2312,
      "step": 13
    },
    {
      "epoch": 0.47863247863247865,
      "grad_norm": 0.6502723693847656,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.0046,
      "step": 14
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.2675360143184662,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.805,
      "step": 15
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 0.24937307834625244,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.8361,
      "step": 16
    },
    {
      "epoch": 0.5811965811965812,
      "grad_norm": 0.32915517687797546,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.8624,
      "step": 17
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.3165777027606964,
      "learning_rate": 7.75e-05,
      "loss": 0.9041,
      "step": 18
    },
    {
      "epoch": 0.6495726495726496,
      "grad_norm": 0.29354873299598694,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.9773,
      "step": 19
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 0.3859802186489105,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.107,
      "step": 20
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.47748714685440063,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.9861,
      "step": 21
    },
    {
      "epoch": 0.7521367521367521,
      "grad_norm": 0.28590238094329834,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.7694,
      "step": 22
    },
    {
      "epoch": 0.7863247863247863,
      "grad_norm": 0.26038798689842224,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.8208,
      "step": 23
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.2839949131011963,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.8718,
      "step": 24
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 0.2815213203430176,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.8584,
      "step": 25
    },
    {
      "epoch": 0.8547008547008547,
      "eval_loss": 0.9388629794120789,
      "eval_runtime": 3.503,
      "eval_samples_per_second": 14.274,
      "eval_steps_per_second": 3.711,
      "step": 25
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.28909528255462646,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.9418,
      "step": 26
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.38391032814979553,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.0341,
      "step": 27
    },
    {
      "epoch": 0.9572649572649573,
      "grad_norm": 0.44489622116088867,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.9819,
      "step": 28
    },
    {
      "epoch": 0.9914529914529915,
      "grad_norm": 0.6754913330078125,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.9653,
      "step": 29
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.5481194853782654,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.4565,
      "step": 30
    },
    {
      "epoch": 1.0598290598290598,
      "grad_norm": 0.2325354814529419,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.7719,
      "step": 31
    },
    {
      "epoch": 1.0940170940170941,
      "grad_norm": 0.26181185245513916,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.8039,
      "step": 32
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 0.2746793329715729,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.8383,
      "step": 33
    },
    {
      "epoch": 1.1623931623931625,
      "grad_norm": 0.28374120593070984,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.905,
      "step": 34
    },
    {
      "epoch": 1.1965811965811965,
      "grad_norm": 0.4092039167881012,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.0047,
      "step": 35
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.5275164246559143,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.8573,
      "step": 36
    },
    {
      "epoch": 1.264957264957265,
      "grad_norm": 0.2732887864112854,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.664,
      "step": 37
    },
    {
      "epoch": 1.2991452991452992,
      "grad_norm": 0.23111304640769958,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.7862,
      "step": 38
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.2312902808189392,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.7616,
      "step": 39
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 0.25998955965042114,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.837,
      "step": 40
    },
    {
      "epoch": 1.4017094017094016,
      "grad_norm": 0.3226254880428314,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.9217,
      "step": 41
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.476153165102005,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.006,
      "step": 42
    },
    {
      "epoch": 1.4700854700854702,
      "grad_norm": 0.47047027945518494,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.7943,
      "step": 43
    },
    {
      "epoch": 1.5042735042735043,
      "grad_norm": 0.2968030571937561,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.5807,
      "step": 44
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.2597537934780121,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.8635,
      "step": 45
    },
    {
      "epoch": 1.5726495726495726,
      "grad_norm": 0.2324274331331253,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.7664,
      "step": 46
    },
    {
      "epoch": 1.606837606837607,
      "grad_norm": 0.249767005443573,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.7848,
      "step": 47
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.29912737011909485,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.8973,
      "step": 48
    },
    {
      "epoch": 1.6752136752136753,
      "grad_norm": 0.40372592210769653,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.9817,
      "step": 49
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 0.47870293259620667,
      "learning_rate": 1e-05,
      "loss": 0.8148,
      "step": 50
    },
    {
      "epoch": 1.7094017094017095,
      "eval_loss": 0.8940553069114685,
      "eval_runtime": 3.5034,
      "eval_samples_per_second": 14.272,
      "eval_steps_per_second": 3.711,
      "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": 5.968083617316864e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}