{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2526847757422615,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00505369551484523,
      "grad_norm": 5.525087356567383,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 11.0327,
      "step": 1
    },
    {
      "epoch": 0.00505369551484523,
      "eval_loss": 10.8840913772583,
      "eval_runtime": 8.456,
      "eval_samples_per_second": 39.499,
      "eval_steps_per_second": 9.934,
      "step": 1
    },
    {
      "epoch": 0.01010739102969046,
      "grad_norm": 5.266482830047607,
      "learning_rate": 4.000000000000001e-06,
      "loss": 10.9714,
      "step": 2
    },
    {
      "epoch": 0.015161086544535692,
      "grad_norm": 4.918356895446777,
      "learning_rate": 6e-06,
      "loss": 10.9057,
      "step": 3
    },
    {
      "epoch": 0.02021478205938092,
      "grad_norm": 4.777329921722412,
      "learning_rate": 8.000000000000001e-06,
      "loss": 10.939,
      "step": 4
    },
    {
      "epoch": 0.025268477574226154,
      "grad_norm": 4.73073148727417,
      "learning_rate": 1e-05,
      "loss": 11.0369,
      "step": 5
    },
    {
      "epoch": 0.030322173089071383,
      "grad_norm": 4.6360931396484375,
      "learning_rate": 1.2e-05,
      "loss": 10.8651,
      "step": 6
    },
    {
      "epoch": 0.035375868603916616,
      "grad_norm": 4.678157329559326,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 10.8567,
      "step": 7
    },
    {
      "epoch": 0.04042956411876184,
      "grad_norm": 4.721307754516602,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 10.8247,
      "step": 8
    },
    {
      "epoch": 0.045483259633607075,
      "grad_norm": 4.473278045654297,
      "learning_rate": 1.8e-05,
      "loss": 10.7567,
      "step": 9
    },
    {
      "epoch": 0.05053695514845231,
      "grad_norm": 4.979541301727295,
      "learning_rate": 2e-05,
      "loss": 10.8797,
      "step": 10
    },
    {
      "epoch": 0.05559065066329753,
      "grad_norm": 4.539080619812012,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 10.8282,
      "step": 11
    },
    {
      "epoch": 0.060644346178142766,
      "grad_norm": 4.77044153213501,
      "learning_rate": 2.4e-05,
      "loss": 10.9363,
      "step": 12
    },
    {
      "epoch": 0.065698041692988,
      "grad_norm": 4.023128509521484,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 10.8104,
      "step": 13
    },
    {
      "epoch": 0.07075173720783323,
      "grad_norm": 4.127583026885986,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 10.772,
      "step": 14
    },
    {
      "epoch": 0.07580543272267846,
      "grad_norm": 4.209392070770264,
      "learning_rate": 3e-05,
      "loss": 10.819,
      "step": 15
    },
    {
      "epoch": 0.08085912823752368,
      "grad_norm": 4.107909202575684,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 10.8561,
      "step": 16
    },
    {
      "epoch": 0.08591282375236892,
      "grad_norm": 3.9726462364196777,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 10.702,
      "step": 17
    },
    {
      "epoch": 0.09096651926721415,
      "grad_norm": 3.9486467838287354,
      "learning_rate": 3.6e-05,
      "loss": 10.86,
      "step": 18
    },
    {
      "epoch": 0.09602021478205938,
      "grad_norm": 4.086248397827148,
      "learning_rate": 3.8e-05,
      "loss": 10.6329,
      "step": 19
    },
    {
      "epoch": 0.10107391029690461,
      "grad_norm": 4.198414325714111,
      "learning_rate": 4e-05,
      "loss": 10.6256,
      "step": 20
    },
    {
      "epoch": 0.10612760581174985,
      "grad_norm": 4.264832496643066,
      "learning_rate": 4.2e-05,
      "loss": 10.668,
      "step": 21
    },
    {
      "epoch": 0.11118130132659507,
      "grad_norm": 4.420608997344971,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 10.703,
      "step": 22
    },
    {
      "epoch": 0.1162349968414403,
      "grad_norm": 4.989047050476074,
      "learning_rate": 4.600000000000001e-05,
      "loss": 10.7338,
      "step": 23
    },
    {
      "epoch": 0.12128869235628553,
      "grad_norm": 6.062208652496338,
      "learning_rate": 4.8e-05,
      "loss": 10.8503,
      "step": 24
    },
    {
      "epoch": 0.12634238787113075,
      "grad_norm": 7.2560038566589355,
      "learning_rate": 5e-05,
      "loss": 10.6961,
      "step": 25
    },
    {
      "epoch": 0.131396083385976,
      "grad_norm": 5.42380428314209,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 10.654,
      "step": 26
    },
    {
      "epoch": 0.13644977890082122,
      "grad_norm": 4.605566501617432,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 10.6335,
      "step": 27
    },
    {
      "epoch": 0.14150347441566646,
      "grad_norm": 4.439408779144287,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 10.5825,
      "step": 28
    },
    {
      "epoch": 0.14655716993051168,
      "grad_norm": 4.211907386779785,
      "learning_rate": 5.8e-05,
      "loss": 10.5156,
      "step": 29
    },
    {
      "epoch": 0.15161086544535693,
      "grad_norm": 3.8451991081237793,
      "learning_rate": 6e-05,
      "loss": 10.3591,
      "step": 30
    },
    {
      "epoch": 0.15666456096020215,
      "grad_norm": 3.6254827976226807,
      "learning_rate": 6.2e-05,
      "loss": 10.5195,
      "step": 31
    },
    {
      "epoch": 0.16171825647504737,
      "grad_norm": 3.743040084838867,
      "learning_rate": 6.400000000000001e-05,
      "loss": 10.4644,
      "step": 32
    },
    {
      "epoch": 0.16677195198989261,
      "grad_norm": 3.687465190887451,
      "learning_rate": 6.6e-05,
      "loss": 10.2991,
      "step": 33
    },
    {
      "epoch": 0.17182564750473783,
      "grad_norm": 3.4375765323638916,
      "learning_rate": 6.800000000000001e-05,
      "loss": 10.3176,
      "step": 34
    },
    {
      "epoch": 0.17687934301958308,
      "grad_norm": 3.485527753829956,
      "learning_rate": 7e-05,
      "loss": 10.2831,
      "step": 35
    },
    {
      "epoch": 0.1819330385344283,
      "grad_norm": 3.4168219566345215,
      "learning_rate": 7.2e-05,
      "loss": 10.1887,
      "step": 36
    },
    {
      "epoch": 0.18698673404927352,
      "grad_norm": 2.9851391315460205,
      "learning_rate": 7.4e-05,
      "loss": 10.2611,
      "step": 37
    },
    {
      "epoch": 0.19204042956411876,
      "grad_norm": 3.173752784729004,
      "learning_rate": 7.6e-05,
      "loss": 10.0005,
      "step": 38
    },
    {
      "epoch": 0.19709412507896398,
      "grad_norm": 3.038637161254883,
      "learning_rate": 7.800000000000001e-05,
      "loss": 10.1846,
      "step": 39
    },
    {
      "epoch": 0.20214782059380923,
      "grad_norm": 3.0100479125976562,
      "learning_rate": 8e-05,
      "loss": 10.121,
      "step": 40
    },
    {
      "epoch": 0.20720151610865445,
      "grad_norm": 3.1173861026763916,
      "learning_rate": 8.2e-05,
      "loss": 10.055,
      "step": 41
    },
    {
      "epoch": 0.2122552116234997,
      "grad_norm": 2.935340166091919,
      "learning_rate": 8.4e-05,
      "loss": 9.9977,
      "step": 42
    },
    {
      "epoch": 0.21730890713834491,
      "grad_norm": 2.8017685413360596,
      "learning_rate": 8.6e-05,
      "loss": 9.9614,
      "step": 43
    },
    {
      "epoch": 0.22236260265319013,
      "grad_norm": 2.6707160472869873,
      "learning_rate": 8.800000000000001e-05,
      "loss": 10.0095,
      "step": 44
    },
    {
      "epoch": 0.22741629816803538,
      "grad_norm": 2.65998911857605,
      "learning_rate": 9e-05,
      "loss": 9.9824,
      "step": 45
    },
    {
      "epoch": 0.2324699936828806,
      "grad_norm": 2.622680902481079,
      "learning_rate": 9.200000000000001e-05,
      "loss": 9.8679,
      "step": 46
    },
    {
      "epoch": 0.23752368919772585,
      "grad_norm": 2.7016119956970215,
      "learning_rate": 9.4e-05,
      "loss": 9.8601,
      "step": 47
    },
    {
      "epoch": 0.24257738471257106,
      "grad_norm": 2.5022776126861572,
      "learning_rate": 9.6e-05,
      "loss": 10.012,
      "step": 48
    },
    {
      "epoch": 0.2476310802274163,
      "grad_norm": 2.6630473136901855,
      "learning_rate": 9.8e-05,
      "loss": 9.919,
      "step": 49
    },
    {
      "epoch": 0.2526847757422615,
      "grad_norm": 3.5715386867523193,
      "learning_rate": 0.0001,
      "loss": 9.9513,
      "step": 50
    },
    {
      "epoch": 0.2526847757422615,
      "eval_loss": 9.72451114654541,
      "eval_runtime": 8.5338,
      "eval_samples_per_second": 39.139,
      "eval_steps_per_second": 9.843,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 197,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 56810370760704.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}