{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.5555555555555554,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.19568008184432983,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.743,
      "step": 1
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.1960965245962143,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.9395,
      "step": 2
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.19083181023597717,
      "learning_rate": 3e-06,
      "loss": 0.9456,
      "step": 3
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.21329426765441895,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8674,
      "step": 4
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.22335226833820343,
      "learning_rate": 5e-06,
      "loss": 0.8332,
      "step": 5
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.193553164601326,
      "learning_rate": 6e-06,
      "loss": 0.7133,
      "step": 6
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.1858656108379364,
      "learning_rate": 7e-06,
      "loss": 0.9214,
      "step": 7
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.214676171541214,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9407,
      "step": 8
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.20595382153987885,
      "learning_rate": 9e-06,
      "loss": 0.8862,
      "step": 9
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.24974201619625092,
      "learning_rate": 1e-05,
      "loss": 0.7367,
      "step": 10
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.19453175365924835,
      "learning_rate": 9.987260573051268e-06,
      "loss": 0.8232,
      "step": 11
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.1651102900505066,
      "learning_rate": 9.949107209404664e-06,
      "loss": 0.9059,
      "step": 12
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.17140182852745056,
      "learning_rate": 9.885734329855798e-06,
      "loss": 0.8703,
      "step": 13
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.23574431240558624,
      "learning_rate": 9.797464868072489e-06,
      "loss": 0.7074,
      "step": 14
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.2225610464811325,
      "learning_rate": 9.68474862499881e-06,
      "loss": 0.8139,
      "step": 15
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.21732008457183838,
      "learning_rate": 9.548159976772593e-06,
      "loss": 0.8215,
      "step": 16
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.20930981636047363,
      "learning_rate": 9.388394947836278e-06,
      "loss": 0.7565,
      "step": 17
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2180735021829605,
      "learning_rate": 9.206267664155906e-06,
      "loss": 0.7212,
      "step": 18
    },
    {
      "epoch": 1.0555555555555556,
      "grad_norm": 0.19505858421325684,
      "learning_rate": 9.002706204621802e-06,
      "loss": 0.795,
      "step": 19
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.15985409915447235,
      "learning_rate": 8.778747871771293e-06,
      "loss": 0.7864,
      "step": 20
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 0.14533071219921112,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.8788,
      "step": 21
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.16130374372005463,
      "learning_rate": 8.274303669726427e-06,
      "loss": 0.7935,
      "step": 22
    },
    {
      "epoch": 1.2777777777777777,
      "grad_norm": 0.2337110936641693,
      "learning_rate": 7.996388332556735e-06,
      "loss": 0.7538,
      "step": 23
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.1405537873506546,
      "learning_rate": 7.703204087277989e-06,
      "loss": 0.792,
      "step": 24
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 0.15972167253494263,
      "learning_rate": 7.396244933600285e-06,
      "loss": 0.713,
      "step": 25
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.13147059082984924,
      "learning_rate": 7.0770750650094335e-06,
      "loss": 0.7298,
      "step": 26
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.14095576107501984,
      "learning_rate": 6.747320897995493e-06,
      "loss": 0.8924,
      "step": 27
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.12625615298748016,
      "learning_rate": 6.408662784207149e-06,
      "loss": 0.763,
      "step": 28
    },
    {
      "epoch": 1.6111111111111112,
      "grad_norm": 0.1273408979177475,
      "learning_rate": 6.062826447764883e-06,
      "loss": 0.6831,
      "step": 29
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.11066637188196182,
      "learning_rate": 5.711574191366427e-06,
      "loss": 0.8164,
      "step": 30
    },
    {
      "epoch": 1.7222222222222223,
      "grad_norm": 0.10837733000516891,
      "learning_rate": 5.356695915996162e-06,
      "loss": 0.7147,
      "step": 31
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.11306577175855637,
      "learning_rate": 5e-06,
      "loss": 0.7393,
      "step": 32
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 0.09451240301132202,
      "learning_rate": 4.643304084003839e-06,
      "loss": 0.8658,
      "step": 33
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.12831491231918335,
      "learning_rate": 4.2884258086335755e-06,
      "loss": 0.741,
      "step": 34
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 0.10294996201992035,
      "learning_rate": 3.937173552235117e-06,
      "loss": 0.7591,
      "step": 35
    },
    {
      "epoch": 2.0555555555555554,
      "grad_norm": 0.10132957249879837,
      "learning_rate": 3.5913372157928515e-06,
      "loss": 1.2196,
      "step": 36
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 0.11689897626638412,
      "learning_rate": 3.252679102004509e-06,
      "loss": 0.7569,
      "step": 37
    },
    {
      "epoch": 2.1666666666666665,
      "grad_norm": 0.09816595911979675,
      "learning_rate": 2.9229249349905686e-06,
      "loss": 0.7079,
      "step": 38
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.09971238672733307,
      "learning_rate": 2.603755066399718e-06,
      "loss": 0.7155,
      "step": 39
    },
    {
      "epoch": 2.2777777777777777,
      "grad_norm": 0.096501424908638,
      "learning_rate": 2.296795912722014e-06,
      "loss": 0.7408,
      "step": 40
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.10212745517492294,
      "learning_rate": 2.0036116674432653e-06,
      "loss": 0.6515,
      "step": 41
    },
    {
      "epoch": 2.388888888888889,
      "grad_norm": 0.09364734590053558,
      "learning_rate": 1.7256963302735752e-06,
      "loss": 0.7529,
      "step": 42
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.09163379669189453,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.7507,
      "step": 43
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.09199802577495575,
      "learning_rate": 1.2212521282287093e-06,
      "loss": 0.7617,
      "step": 44
    },
    {
      "epoch": 2.5555555555555554,
      "grad_norm": 0.10740058124065399,
      "learning_rate": 9.972937953781985e-07,
      "loss": 0.6267,
      "step": 45
    }
  ],
  "logging_steps": 1,
  "max_steps": 54,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.743128682158096e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}