{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00048,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8e-06,
      "grad_norm": 2.7957773208618164,
      "learning_rate": 4e-05,
      "loss": 3.3745,
      "step": 1
    },
    {
      "epoch": 1.6e-05,
      "grad_norm": 3.007798910140991,
      "learning_rate": 8e-05,
      "loss": 3.5783,
      "step": 2
    },
    {
      "epoch": 2.4e-05,
      "grad_norm": 2.924086332321167,
      "learning_rate": 0.00012,
      "loss": 3.4897,
      "step": 3
    },
    {
      "epoch": 3.2e-05,
      "grad_norm": 2.641416549682617,
      "learning_rate": 0.00016,
      "loss": 3.2239,
      "step": 4
    },
    {
      "epoch": 4e-05,
      "grad_norm": 2.3493382930755615,
      "learning_rate": 0.0002,
      "loss": 3.0593,
      "step": 5
    },
    {
      "epoch": 4.8e-05,
      "grad_norm": 2.65859317779541,
      "learning_rate": 0.00019636363636363636,
      "loss": 2.6891,
      "step": 6
    },
    {
      "epoch": 5.6e-05,
      "grad_norm": 2.7041451930999756,
      "learning_rate": 0.00019272727272727274,
      "loss": 2.5238,
      "step": 7
    },
    {
      "epoch": 6.4e-05,
      "grad_norm": 2.3512747287750244,
      "learning_rate": 0.0001890909090909091,
      "loss": 2.0734,
      "step": 8
    },
    {
      "epoch": 7.2e-05,
      "grad_norm": 2.050905466079712,
      "learning_rate": 0.00018545454545454545,
      "loss": 1.9127,
      "step": 9
    },
    {
      "epoch": 8e-05,
      "grad_norm": 1.9004530906677246,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.7048,
      "step": 10
    },
    {
      "epoch": 8.8e-05,
      "grad_norm": 1.8062632083892822,
      "learning_rate": 0.0001781818181818182,
      "loss": 1.3749,
      "step": 11
    },
    {
      "epoch": 9.6e-05,
      "grad_norm": 1.781510829925537,
      "learning_rate": 0.00017454545454545454,
      "loss": 1.3298,
      "step": 12
    },
    {
      "epoch": 0.000104,
      "grad_norm": 1.8835322856903076,
      "learning_rate": 0.0001709090909090909,
      "loss": 1.3832,
      "step": 13
    },
    {
      "epoch": 0.000112,
      "grad_norm": 1.8062396049499512,
      "learning_rate": 0.00016727272727272728,
      "loss": 1.1426,
      "step": 14
    },
    {
      "epoch": 0.00012,
      "grad_norm": 1.5448161363601685,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9988,
      "step": 15
    },
    {
      "epoch": 0.000128,
      "grad_norm": 1.8640860319137573,
      "learning_rate": 0.00016,
      "loss": 1.0413,
      "step": 16
    },
    {
      "epoch": 0.000136,
      "grad_norm": 1.8167814016342163,
      "learning_rate": 0.00015636363636363637,
      "loss": 0.9421,
      "step": 17
    },
    {
      "epoch": 0.000144,
      "grad_norm": 1.890179991722107,
      "learning_rate": 0.00015272727272727275,
      "loss": 1.0484,
      "step": 18
    },
    {
      "epoch": 0.000152,
      "grad_norm": 1.942975401878357,
      "learning_rate": 0.0001490909090909091,
      "loss": 0.9183,
      "step": 19
    },
    {
      "epoch": 0.00016,
      "grad_norm": 1.880692481994629,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.7171,
      "step": 20
    },
    {
      "epoch": 0.000168,
      "grad_norm": 1.7045783996582031,
      "learning_rate": 0.00014181818181818184,
      "loss": 0.811,
      "step": 21
    },
    {
      "epoch": 0.000176,
      "grad_norm": 1.7415192127227783,
      "learning_rate": 0.0001381818181818182,
      "loss": 0.6903,
      "step": 22
    },
    {
      "epoch": 0.000184,
      "grad_norm": 2.0383002758026123,
      "learning_rate": 0.00013454545454545455,
      "loss": 0.7369,
      "step": 23
    },
    {
      "epoch": 0.000192,
      "grad_norm": 1.9076192378997803,
      "learning_rate": 0.00013090909090909093,
      "loss": 0.7835,
      "step": 24
    },
    {
      "epoch": 0.0002,
      "grad_norm": 2.624040126800537,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.9158,
      "step": 25
    },
    {
      "epoch": 0.000208,
      "grad_norm": 1.7511118650436401,
      "learning_rate": 0.00012363636363636364,
      "loss": 0.5601,
      "step": 26
    },
    {
      "epoch": 0.000216,
      "grad_norm": 1.684621810913086,
      "learning_rate": 0.00012,
      "loss": 0.5804,
      "step": 27
    },
    {
      "epoch": 0.000224,
      "grad_norm": 1.7437366247177124,
      "learning_rate": 0.00011636363636363636,
      "loss": 0.5813,
      "step": 28
    },
    {
      "epoch": 0.000232,
      "grad_norm": 2.6971840858459473,
      "learning_rate": 0.00011272727272727272,
      "loss": 0.7485,
      "step": 29
    },
    {
      "epoch": 0.00024,
      "grad_norm": 1.9661293029785156,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.5978,
      "step": 30
    },
    {
      "epoch": 0.000248,
      "grad_norm": 1.6104350090026855,
      "learning_rate": 0.00010545454545454545,
      "loss": 0.5289,
      "step": 31
    },
    {
      "epoch": 0.000256,
      "grad_norm": 1.752379059791565,
      "learning_rate": 0.00010181818181818181,
      "loss": 0.599,
      "step": 32
    },
    {
      "epoch": 0.000264,
      "grad_norm": 2.094172477722168,
      "learning_rate": 9.818181818181818e-05,
      "loss": 0.6017,
      "step": 33
    },
    {
      "epoch": 0.000272,
      "grad_norm": 1.609321117401123,
      "learning_rate": 9.454545454545455e-05,
      "loss": 0.501,
      "step": 34
    },
    {
      "epoch": 0.00028,
      "grad_norm": 1.3293076753616333,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.436,
      "step": 35
    },
    {
      "epoch": 0.000288,
      "grad_norm": 1.6249406337738037,
      "learning_rate": 8.727272727272727e-05,
      "loss": 0.4532,
      "step": 36
    },
    {
      "epoch": 0.000296,
      "grad_norm": 1.4620122909545898,
      "learning_rate": 8.363636363636364e-05,
      "loss": 0.4738,
      "step": 37
    },
    {
      "epoch": 0.000304,
      "grad_norm": 1.9694863557815552,
      "learning_rate": 8e-05,
      "loss": 0.5152,
      "step": 38
    },
    {
      "epoch": 0.000312,
      "grad_norm": 1.1704041957855225,
      "learning_rate": 7.636363636363637e-05,
      "loss": 0.3199,
      "step": 39
    },
    {
      "epoch": 0.00032,
      "grad_norm": 1.327712059020996,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.3782,
      "step": 40
    },
    {
      "epoch": 0.000328,
      "grad_norm": 1.397344708442688,
      "learning_rate": 6.90909090909091e-05,
      "loss": 0.3945,
      "step": 41
    },
    {
      "epoch": 0.000336,
      "grad_norm": 1.6803901195526123,
      "learning_rate": 6.545454545454546e-05,
      "loss": 0.4109,
      "step": 42
    },
    {
      "epoch": 0.000344,
      "grad_norm": 1.6322376728057861,
      "learning_rate": 6.181818181818182e-05,
      "loss": 0.4245,
      "step": 43
    },
    {
      "epoch": 0.000352,
      "grad_norm": 1.462713599205017,
      "learning_rate": 5.818181818181818e-05,
      "loss": 0.2721,
      "step": 44
    },
    {
      "epoch": 0.00036,
      "grad_norm": 1.3061343431472778,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.3547,
      "step": 45
    },
    {
      "epoch": 0.000368,
      "grad_norm": 1.59852135181427,
      "learning_rate": 5.090909090909091e-05,
      "loss": 0.3411,
      "step": 46
    },
    {
      "epoch": 0.000376,
      "grad_norm": 1.4914323091506958,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 0.3284,
      "step": 47
    },
    {
      "epoch": 0.000384,
      "grad_norm": 1.2796622514724731,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 0.3091,
      "step": 48
    },
    {
      "epoch": 0.000392,
      "grad_norm": 1.1500067710876465,
      "learning_rate": 4e-05,
      "loss": 0.2738,
      "step": 49
    },
    {
      "epoch": 0.0004,
      "grad_norm": 1.8404273986816406,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.3663,
      "step": 50
    },
    {
      "epoch": 0.000408,
      "grad_norm": 1.394667387008667,
      "learning_rate": 3.272727272727273e-05,
      "loss": 0.3179,
      "step": 51
    },
    {
      "epoch": 0.000416,
      "grad_norm": 1.4143589735031128,
      "learning_rate": 2.909090909090909e-05,
      "loss": 0.3087,
      "step": 52
    },
    {
      "epoch": 0.000424,
      "grad_norm": 1.250054955482483,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 0.2461,
      "step": 53
    },
    {
      "epoch": 0.000432,
      "grad_norm": 1.222795844078064,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 0.3028,
      "step": 54
    },
    {
      "epoch": 0.00044,
      "grad_norm": 1.5463387966156006,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.3442,
      "step": 55
    },
    {
      "epoch": 0.000448,
      "grad_norm": 1.1312841176986694,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 0.2695,
      "step": 56
    },
    {
      "epoch": 0.000456,
      "grad_norm": 1.3885492086410522,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 0.2838,
      "step": 57
    },
    {
      "epoch": 0.000464,
      "grad_norm": 1.1695365905761719,
      "learning_rate": 7.272727272727272e-06,
      "loss": 0.2596,
      "step": 58
    },
    {
      "epoch": 0.000472,
      "grad_norm": 1.4500614404678345,
      "learning_rate": 3.636363636363636e-06,
      "loss": 0.3092,
      "step": 59
    },
    {
      "epoch": 0.00048,
      "grad_norm": 1.3651001453399658,
      "learning_rate": 0.0,
      "loss": 0.2966,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 170083856891904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}