{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 3.671875,
      "learning_rate": 7.0492058616206255e-06,
      "loss": 0.3052,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 2.609375,
      "learning_rate": 1.5860713188646405e-05,
      "loss": 0.1795,
      "step": 10
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.49609375,
      "learning_rate": 2.4672220515672193e-05,
      "loss": 0.1007,
      "step": 15
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.28515625,
      "learning_rate": 3.348372784269797e-05,
      "loss": 0.0817,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.26953125,
      "learning_rate": 4.2295235169723756e-05,
      "loss": 0.0735,
      "step": 25
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.68359375,
      "learning_rate": 5.1106742496749544e-05,
      "loss": 0.0708,
      "step": 30
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.35546875,
      "learning_rate": 5.991824982377532e-05,
      "loss": 0.0699,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.52734375,
      "learning_rate": 6.166823133108563e-05,
      "loss": 0.0675,
      "step": 40
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.248046875,
      "learning_rate": 6.16182039934105e-05,
      "loss": 0.0672,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.2041015625,
      "learning_rate": 6.152978248024915e-05,
      "loss": 0.0639,
      "step": 50
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 0.30859375,
      "learning_rate": 6.140311396048403e-05,
      "loss": 0.0619,
      "step": 55
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.326171875,
      "learning_rate": 6.123840926136544e-05,
      "loss": 0.0627,
      "step": 60
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.294921875,
      "learning_rate": 6.103594251761051e-05,
      "loss": 0.0647,
      "step": 65
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.2734375,
      "learning_rate": 6.0796050715132965e-05,
      "loss": 0.0622,
      "step": 70
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.224609375,
      "learning_rate": 6.051913313016328e-05,
      "loss": 0.0617,
      "step": 75
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.375,
      "learning_rate": 6.0205650664692885e-05,
      "loss": 0.0632,
      "step": 80
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 0.421875,
      "learning_rate": 5.985612507934822e-05,
      "loss": 0.0623,
      "step": 85
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.251953125,
      "learning_rate": 5.947113812497171e-05,
      "loss": 0.0611,
      "step": 90
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 0.2158203125,
      "learning_rate": 5.905133057435489e-05,
      "loss": 0.0602,
      "step": 95
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.2177734375,
      "learning_rate": 5.859740115573528e-05,
      "loss": 0.0602,
      "step": 100
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.22265625,
      "learning_rate": 5.811010538983226e-05,
      "loss": 0.0602,
      "step": 105
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.2451171875,
      "learning_rate": 5.7590254332357376e-05,
      "loss": 0.0613,
      "step": 110
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 0.259765625,
      "learning_rate": 5.703871322409211e-05,
      "loss": 0.0618,
      "step": 115
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2109375,
      "learning_rate": 5.645640005078007e-05,
      "loss": 0.061,
      "step": 120
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 0.2294921875,
      "learning_rate": 5.58442840152302e-05,
      "loss": 0.0587,
      "step": 125
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.19921875,
      "learning_rate": 5.5203383924174454e-05,
      "loss": 0.0587,
      "step": 130
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 0.1982421875,
      "learning_rate": 5.453476649256451e-05,
      "loss": 0.0578,
      "step": 135
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1923828125,
      "learning_rate": 5.383954456812999e-05,
      "loss": 0.0591,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.060198914259672165,
      "eval_runtime": 1.2415,
      "eval_samples_per_second": 19.331,
      "eval_steps_per_second": 19.331,
      "step": 140
    },
    {
      "epoch": 1.0357142857142858,
      "grad_norm": 0.203125,
      "learning_rate": 5.311887527915323e-05,
      "loss": 0.0497,
      "step": 145
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.2333984375,
      "learning_rate": 5.23739581085435e-05,
      "loss": 0.0493,
      "step": 150
    },
    {
      "epoch": 1.1071428571428572,
      "grad_norm": 0.263671875,
      "learning_rate": 5.160603289741601e-05,
      "loss": 0.0493,
      "step": 155
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.1982421875,
      "learning_rate": 5.081637778149878e-05,
      "loss": 0.0498,
      "step": 160
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 0.302734375,
      "learning_rate": 5.000630706380186e-05,
      "loss": 0.0498,
      "step": 165
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.212890625,
      "learning_rate": 4.917716902708965e-05,
      "loss": 0.0509,
      "step": 170
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.216796875,
      "learning_rate": 4.833034368979732e-05,
      "loss": 0.0491,
      "step": 175
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.2001953125,
      "learning_rate": 4.74672405091263e-05,
      "loss": 0.0487,
      "step": 180
    },
    {
      "epoch": 1.3214285714285714,
      "grad_norm": 0.2216796875,
      "learning_rate": 4.6589296035141886e-05,
      "loss": 0.0493,
      "step": 185
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.2294921875,
      "learning_rate": 4.569797151977743e-05,
      "loss": 0.0502,
      "step": 190
    },
    {
      "epoch": 1.3928571428571428,
      "grad_norm": 0.24609375,
      "learning_rate": 4.479475048472466e-05,
      "loss": 0.0492,
      "step": 195
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.212890625,
      "learning_rate": 4.3881136252258305e-05,
      "loss": 0.0491,
      "step": 200
    },
    {
      "epoch": 1.4642857142857144,
      "grad_norm": 0.263671875,
      "learning_rate": 4.295864944310448e-05,
      "loss": 0.0501,
      "step": 205
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.228515625,
      "learning_rate": 4.2028825445517566e-05,
      "loss": 0.0501,
      "step": 210
    },
    {
      "epoch": 1.5357142857142856,
      "grad_norm": 0.2119140625,
      "learning_rate": 4.109321185977799e-05,
      "loss": 0.0504,
      "step": 215
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.2080078125,
      "learning_rate": 4.0153365922364295e-05,
      "loss": 0.0492,
      "step": 220
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 0.1943359375,
      "learning_rate": 3.921085191408668e-05,
      "loss": 0.0473,
      "step": 225
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.232421875,
      "learning_rate": 3.826723855649603e-05,
      "loss": 0.0501,
      "step": 230
    },
    {
      "epoch": 1.6785714285714286,
      "grad_norm": 0.220703125,
      "learning_rate": 3.7324096400901615e-05,
      "loss": 0.0493,
      "step": 235
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.2216796875,
      "learning_rate": 3.638299521434351e-05,
      "loss": 0.0498,
      "step": 240
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.2060546875,
      "learning_rate": 3.5445501366870265e-05,
      "loss": 0.0495,
      "step": 245
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.2109375,
      "learning_rate": 3.4513175224470506e-05,
      "loss": 0.0481,
      "step": 250
    },
    {
      "epoch": 1.8214285714285714,
      "grad_norm": 0.197265625,
      "learning_rate": 3.3587568551997774e-05,
      "loss": 0.0493,
      "step": 255
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.208984375,
      "learning_rate": 3.267022193041103e-05,
      "loss": 0.0503,
      "step": 260
    },
    {
      "epoch": 1.8928571428571428,
      "grad_norm": 0.201171875,
      "learning_rate": 3.176266219262975e-05,
      "loss": 0.0485,
      "step": 265
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.1572265625,
      "learning_rate": 3.0866399882271155e-05,
      "loss": 0.0488,
      "step": 270
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 0.21875,
      "learning_rate": 2.9982926739499457e-05,
      "loss": 0.0493,
      "step": 275
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2041015625,
      "learning_rate": 2.911371321817157e-05,
      "loss": 0.0489,
      "step": 280
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.05888582393527031,
      "eval_runtime": 1.1396,
      "eval_samples_per_second": 21.06,
      "eval_steps_per_second": 21.06,
      "step": 280
    }
  ],
  "logging_steps": 5,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.50841030950912e+17,
  "train_batch_size": 100,
  "trial_name": null,
  "trial_params": null
}