{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 41,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024844720496894408,
      "grad_norm": 19.018810272216797,
      "learning_rate": 0.0,
      "loss": 1.9774,
      "step": 1
    },
    {
      "epoch": 0.049689440993788817,
      "grad_norm": 17.34918785095215,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.0557,
      "step": 2
    },
    {
      "epoch": 0.07453416149068323,
      "grad_norm": 15.720738410949707,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.0259,
      "step": 3
    },
    {
      "epoch": 0.09937888198757763,
      "grad_norm": 38.2593879699707,
      "learning_rate": 6e-06,
      "loss": 1.9182,
      "step": 4
    },
    {
      "epoch": 0.12422360248447205,
      "grad_norm": 13.10262680053711,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.7606,
      "step": 5
    },
    {
      "epoch": 0.14906832298136646,
      "grad_norm": 16.064571380615234,
      "learning_rate": 1e-05,
      "loss": 1.4032,
      "step": 6
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 10.83020305633545,
      "learning_rate": 9.980973490458728e-06,
      "loss": 1.3487,
      "step": 7
    },
    {
      "epoch": 0.19875776397515527,
      "grad_norm": 51.90104293823242,
      "learning_rate": 9.924038765061042e-06,
      "loss": 1.2696,
      "step": 8
    },
    {
      "epoch": 0.2236024844720497,
      "grad_norm": 9.72624397277832,
      "learning_rate": 9.829629131445342e-06,
      "loss": 1.2287,
      "step": 9
    },
    {
      "epoch": 0.2484472049689441,
      "grad_norm": 10.273947715759277,
      "learning_rate": 9.698463103929542e-06,
      "loss": 1.0862,
      "step": 10
    },
    {
      "epoch": 0.2732919254658385,
      "grad_norm": 9.789734840393066,
      "learning_rate": 9.531538935183252e-06,
      "loss": 1.1393,
      "step": 11
    },
    {
      "epoch": 0.2981366459627329,
      "grad_norm": 7.638786315917969,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.8413,
      "step": 12
    },
    {
      "epoch": 0.32298136645962733,
      "grad_norm": 6.785307884216309,
      "learning_rate": 9.09576022144496e-06,
      "loss": 1.0334,
      "step": 13
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 6.185614585876465,
      "learning_rate": 8.83022221559489e-06,
      "loss": 1.071,
      "step": 14
    },
    {
      "epoch": 0.37267080745341613,
      "grad_norm": 7.575466632843018,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.9299,
      "step": 15
    },
    {
      "epoch": 0.39751552795031053,
      "grad_norm": 4.955533027648926,
      "learning_rate": 8.213938048432697e-06,
      "loss": 0.7759,
      "step": 16
    },
    {
      "epoch": 0.422360248447205,
      "grad_norm": 5.2840576171875,
      "learning_rate": 7.86788218175523e-06,
      "loss": 0.8976,
      "step": 17
    },
    {
      "epoch": 0.4472049689440994,
      "grad_norm": 4.835018157958984,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.6962,
      "step": 18
    },
    {
      "epoch": 0.4720496894409938,
      "grad_norm": 5.007014274597168,
      "learning_rate": 7.113091308703498e-06,
      "loss": 0.8196,
      "step": 19
    },
    {
      "epoch": 0.4968944099378882,
      "grad_norm": 4.863272190093994,
      "learning_rate": 6.710100716628345e-06,
      "loss": 0.7313,
      "step": 20
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 4.301552772521973,
      "learning_rate": 6.294095225512604e-06,
      "loss": 0.6396,
      "step": 21
    },
    {
      "epoch": 0.546583850931677,
      "grad_norm": 5.151806354522705,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.7904,
      "step": 22
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 3.952173948287964,
      "learning_rate": 5.435778713738292e-06,
      "loss": 0.6056,
      "step": 23
    },
    {
      "epoch": 0.5962732919254659,
      "grad_norm": 8.719491958618164,
      "learning_rate": 5e-06,
      "loss": 0.656,
      "step": 24
    },
    {
      "epoch": 0.6211180124223602,
      "grad_norm": 4.962159156799316,
      "learning_rate": 4.564221286261709e-06,
      "loss": 0.7472,
      "step": 25
    },
    {
      "epoch": 0.6459627329192547,
      "grad_norm": 4.91154146194458,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.7455,
      "step": 26
    },
    {
      "epoch": 0.6708074534161491,
      "grad_norm": 4.54485559463501,
      "learning_rate": 3.705904774487396e-06,
      "loss": 0.6753,
      "step": 27
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 5.184722900390625,
      "learning_rate": 3.289899283371657e-06,
      "loss": 0.7555,
      "step": 28
    },
    {
      "epoch": 0.7204968944099379,
      "grad_norm": 4.566318988800049,
      "learning_rate": 2.886908691296504e-06,
      "loss": 0.7016,
      "step": 29
    },
    {
      "epoch": 0.7453416149068323,
      "grad_norm": 6.3649516105651855,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.7042,
      "step": 30
    },
    {
      "epoch": 0.7701863354037267,
      "grad_norm": 6.356813430786133,
      "learning_rate": 2.132117818244771e-06,
      "loss": 0.5577,
      "step": 31
    },
    {
      "epoch": 0.7950310559006211,
      "grad_norm": 5.374373435974121,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.7394,
      "step": 32
    },
    {
      "epoch": 0.8198757763975155,
      "grad_norm": 4.238478660583496,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.615,
      "step": 33
    },
    {
      "epoch": 0.84472049689441,
      "grad_norm": 4.526385307312012,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.7121,
      "step": 34
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 4.031436920166016,
      "learning_rate": 9.042397785550405e-07,
      "loss": 0.5622,
      "step": 35
    },
    {
      "epoch": 0.8944099378881988,
      "grad_norm": 4.70968770980835,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.753,
      "step": 36
    },
    {
      "epoch": 0.9192546583850931,
      "grad_norm": 5.0172858238220215,
      "learning_rate": 4.6846106481675035e-07,
      "loss": 0.7087,
      "step": 37
    },
    {
      "epoch": 0.9440993788819876,
      "grad_norm": 4.015413761138916,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.5832,
      "step": 38
    },
    {
      "epoch": 0.968944099378882,
      "grad_norm": 5.031809329986572,
      "learning_rate": 1.7037086855465902e-07,
      "loss": 0.766,
      "step": 39
    },
    {
      "epoch": 0.9937888198757764,
      "grad_norm": 5.375775337219238,
      "learning_rate": 7.59612349389599e-08,
      "loss": 0.7813,
      "step": 40
    },
    {
      "epoch": 1.0,
      "grad_norm": 5.375775337219238,
      "learning_rate": 1.9026509541272276e-08,
      "loss": 0.179,
      "step": 41
    },
    {
      "epoch": 1.0,
      "step": 41,
      "total_flos": 9533860949786624.0,
      "train_loss": 0.9509323602769433,
      "train_runtime": 194.3273,
      "train_samples_per_second": 3.314,
      "train_steps_per_second": 0.211
    }
  ],
  "logging_steps": 1,
  "max_steps": 41,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9533860949786624.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}